Publications

@inproceedings{abc,
	abstract = {Business Rule Management Systems (BRMSs) are widely used in industry for a variety of tasks. Their main advantage is to codify in a succinct and queryable manner vast amounts of constantly evolving logic. In BRMSs, rules are typically captured as facts (tuples) over a collection of criteria, and checking them involves querying the collection of rules to find the best match. In this paper, we focus on a real-world use case from the airline industry: determining the minimum connection time (MCT) between flights. The MCT module is part of the flight search engine, and captures the ever changing constraints at each airport that determine the time to allocate between an arriving and a departing flight for a connection to be feasible. We explore how to use hardware acceleration to (i) improve the performance of the MCT module (lower latency, higher throughput); and (ii) reduce the amount of computing resources needed. A key aspect of the solution is the transformation of a collection of rules into a Non-deterministic Finite state Automaton efficiently implemented on FPGA. Experiments performed on-premises and in the cloud show several orders of magnitude improvement over the existing solution, and the potential to reduce by 40\% the number of machines needed for the flight search engine.},
	author = {Fabio Maschi and Muhsen Owaida and Gustavo Alonso and Matteo Casalino and Anthony Hock-Koon},
	booktitle = {Proceedings of the 2020 International Conference on Management of Data (SIGMOD{\textquoteright}20)},
	title = {Making Search Engines Faster by Lowering the Cost of Querying Business Rules Through FPGAs},
	url = {https://doi.org/10.1145/3318464.3386133},
	venue = {Portland, OR, USA},
	year = {2020}
}

@inproceedings{abc,
	abstract = {Learning from the data stored in a database is an important function
increasingly available in relational engines. Methods using
lower precision input data are of special interest given their overall
higher efficiency. However, in databases, these methods have a
hidden cost: the quantization of the real value into a smaller number
is an expensive step. To address this issue, we present MLWeaving,
a data structure and hardware acceleration technique intended
to speed up learning of generalized linear models over low
precision data. MLWeaving provides a compact in-memory representation
that enables the retrieval of data at any level of precision.
MLWeaving also provides a highly efficient implementation
of stochastic gradient descent on FPGAs and enables the dynamic
tuning of precision, instead of using a fixed precision level during
learning. Experimental results show that MLWeaving converges
up to 16 faster than low-precision implementations of first-order
methods on CPUs. },
	author = {Zeke Wang and Kaan Kara and  and Gustavo Alonso and Onur  Mutlu and Ce Zhang},
	booktitle = {Proceedings of the VLDB 2019},
	title = {Accelerating Generalized Linear Models with MLWeaving: A One-Size-Fits-All System for Any-precision Learning },
	url = {https://dl.acm.org/doi/10.14778/3317315.3317322},
	venue = {Los Angeles, CA, USA},
	year = {2019}
}

@inproceedings{abc,
	abstract = {The ability to perform machine learning (ML) tasks in a database
management system (DBMS) provides the data analyst with a powerful
tool. Unfortunately, integration of ML into a DBMS is challenging
for reasons varying from differences in execution model to
data layout requirements. In this paper, we assume a column-store
main-memory DBMS, optimized for online analytical processing,
as our initial system. On this system, we explore the integration of
coordinate-descent based methods working natively on columnar
format to train generalized linear models. We use a cache-efficient,
partitioned stochastic coordinate descent algorithm providing linear
throughput scalability with the number of cores while preserving
convergence quality, up to 14 cores in our experiments.
Existing column oriented DBMS rely on compression and even
encryption to store data in memory. When those features are considered,
the performance of a CPU based solution suffers. Thus,
in the paper we also show how to exploit hardware acceleration
as part of a hybrid CPU+FPGA system to provide on-the-fly data
transformation combined with an FPGA-based coordinate-descent
engine. The resulting system is a column-store DBMS with its important
features preserved (e.g., data compression) that offers high
performance machine learning capabilities.},
	author = {Kaan Kara and Ken  Eguro and Ce Zhang and Gustavo Alonso},
	booktitle = {Proceedings of the VLDB 2019},
	title = { ColumnML: Column Store Machine Learning with On-the-Fly Data Transformation},
	venue = {Los Angeles, CA, USA},
	year = {2019}
}

@inproceedings{abc,
	abstract = {We design and implement Megaphone, a data migration mechanism
for stateful distributed dataflow engines with latency objectives.
When compared to existing migration mechanisms, Megaphone has
the following differentiating characteristics: (i) migrations can be
subdivided to a configurable granularity to avoid latency spikes, and
(ii) migrations can be prepared ahead of time to avoid runtime coordination.
Megaphone is implemented as a library on an unmodified
timely dataflow implementation, and provides an operator interface
compatible with its existing APIs.We evaluate Megaphone on established
benchmarks with varying amounts of state and observe that
compared to na{\"\i}ve approaches Megaphone reduces service latencies
during reconfiguration by orders of magnitude without significantly
increasing steady-state overhead.},
	author = {Moritz Hoffmann and Andrea Lattuada and Frank McSherry},
	booktitle = {Proceedings of the VLDB 2019},
	title = {Megaphone: Latency-conscious state migration for distributed streaming dataflows},
	venue = {Los Angeles, CA, USA},
	year = {2019}
}

@inproceedings{abc,
	abstract = {We explore the performance and resource trade-offs of two alternative
approaches to streaming state management. When
the state size exceeds the amount of available memory, systems
can either scale out and partition the state across distributed
computing nodes or rely on secondary storage and
divide the state into {\textquoteleft}hot{\textquoteright} and {\textquoteleft}cold{\textquoteright} sets. Scaling out a streaming
computation might introduce coordination overhead
among parallel workers, while flushing state to disk requires
efficient data structures and careful caching policies to minimise
expensive I/O.
To study the characteristics of these state management approaches,
we present an integration of the Timely Dataflow
stream processing engine with the FASTER embedded keyvalue
store. We demonstrate a prototype that allows users to
transparently maintain arbitrary larger-than-memory state
with low overhead by making only minimal changes to application
code. Our preliminary experimental results show
that managed state incurs acceptable overhead over built-in
in-memory data structures and, in some cases, performs better
when relying on secondary storage in a},
	author = {Matthew Brokes and Vasiliki  Kalavri and John Liagouris},
	booktitle = {Proceedings of BIRTE Workshop 2019},
	title = {FASTER State Management for Timely Dataflow},
	venue = {Los Angeles, CA, USA},
	year = {2019}
}

@inproceedings{abc,
	abstract = {Cloud providers and their tenants have a mutual interest in identifying optimal configurations in which to run tenant jobs, i.e., ones that achieve tenants{\textquoteright} performance goals at minimum cost; or ones that maximize performance within a specified budget. However, different tenants may have different performance goals that are opaque to the provider. A consequence of this opacity is that providers today typically offer fixed bundles of cloud resources, which tenants must themselves explore and choose from. This is burdensome for tenants and can lead to choices that are sub-optimal for both parties.

We thus explore a simple, minimal interface, which lets tenants communicate their happiness with cloud infrastructure to the provider, and enables the provider to explore resource configurations that maximize this happiness. Our early results indicate that this interface could strike a good balance between enabling efficient discovery of application resource needs and the complexity of communicating a full description of tenant utility from different configurations to the provider.
},
	author = {Vojislav Dukic and Ankit Singla},
	booktitle = {Proceedings of HotCloud 2019},
	title = {Happiness index: Right-sizing the cloud{\textquoteright}s tenant-provider interface},
	url = {https://www.usenix.org/conference/hotcloud19/presentation/dukic},
	venue = {Washington, US},
	year = {2019}
}

@inproceedings{abc,
	abstract = {Previous research shows that eye-tracking data
contains information about the lexical and syntactic
properties of text, which can be used to
improve natural language processing models.
In this work, we leverage eye movement features
from three corpora with recorded gaze
information to augment a state-of-the-art neural
model for named entity recognition (NER)
with gaze embeddings. These corpora were
manually annotated with named entity labels.
Moreover, we show how gaze features, generalized
on word type level, eliminate the need
for recorded eye-tracking data at test time. The
gaze-augmented models for NER using tokenlevel
and type-level features outperform the
baselines. We present the benefits of eyetracking
features by evaluating the NER models
on both individual datasets as well as in
cross-domain settings.},
	author = {Nora  Hollenstein and Ce Zhang},
	booktitle = {Proceedings of the NAACL-HLT 2019},
	title = {Entity Recognition at First Sight: Improving NER with Eye Movement Information},
	venue = {Minneapolis, USA.},
	year = {2019}
}

@article{abc,
	abstract = {Bayesian methods in machine learning, such as Gaussian processes, have great advantages compared to other techniques. In particular, they provide estimates of the uncertainty associated with a prediction. Extending the Bayesian approach to deep architectures has remained a major challenge. Recent results connected deep feedforward neural networks with Gaussian processes, allowing training without backpropagation. This connection enables us to leverage a quantum algorithm designed for Gaussian processes and develop a new algorithm for Bayesian deep learning on quantum computers. The properties of the kernel matrix in the Gaussian process ensure the efficient execution of the core component of the protocol, quantum matrix inversion, providing at least a polynomial speedup over classical algorithms. Furthermore, we demonstrate the execution of the algorithm on contemporary quantum computers and analyze its robustness with respect to realistic noise models.},
	author = {Zhikuan Zhao and Alejandro Pozas-Kerstjens and Patrick Rebentrost and Peter Wittek},
	pages = {1-11},
	journal = {Springer Quantum Machine Intelligence},
	title = {Bayesian deep learning on a quantum computer},
	url = {https://link.springer.com/article/10.1007/s42484-019-00004-7},
	year = {2019}
}

@inproceedings{abc,
	abstract = {Continuous integration is an indispensable step of modern software engineering practices to systematically
manage the life cycles of system development. Developing a machine learning model is no difference{\textemdash} it is an
engineering process with a life cycle, including design, implementation, tuning, testing, and deployment. However,
most, if not all, existing continuous integration engines do not support machine learning as first-class citizens.
In this paper, we present ease.ml/ci, to our best knowledge, the first continuous integration system for machine
learning. The challenge of building ease.ml/ci is to provide rigorous guarantees, e.g., single accuracy point
error tolerance with 0.999 reliability, with a practical amount of labeling effort, e.g., 2K labels per test. We design
a domain specific language that allows users to specify integration conditions with reliability constraints, and
develop simple novel optimizations that can lower the number of labels required by up to two orders of magnitude
for test conditions popularly used in real production systems.},
	author = {Cedric Renggli and Bojan  Karlas and Bolin Ding and Feng  Liu and Kevin Schawinski and Wentao Wu and Ce Zhang},
	booktitle = {Proceedings of the SysML{\textquoteright}19},
	title = {Continuous Integration of Machine Learning Models: A Rigorous Yet Practical Treatment},
	venue = {Stanford, CA, USA},
	year = {2019}
}

@inproceedings{abc,
	abstract = {We are experiencing an explosive growth in the number of consumer devices, including smartphones, tablets, web-based computers such as Chromebooks, and wearable devices. For this class of devices, energy efficiency is a first-class concern due to the limited battery capacity and thermal power budget. We find that data movement is a major contributor to the total system energy and execution time in consumer devices. The energy and performance costs of moving data between the memory system and the compute units are significantly higher than the costs of computation. As a result, addressing data movement is crucial for consumer devices. In this work, we comprehensively analyze the energy and performance impact of data movement for several widely-used Google consumer workloads: (1) the Chrome web browser; (2) TensorFlow Mobile, Google{\textquoteright}s machine learning framework; (3) video playback, and (4) video capture, both of which are used in many video services such as YouTube and Google Hangouts. We find that processing-inmemory (PIM) can significantly reduce data movement for all of these workloads, by performing part of the computation close to memory. Each workload contains simple primitives and functions that contribute to a significant amount of the overall data movement. We investigate whether these primitives and functions are feasible to implement using PIM, given the limited area and power constraints of consumer devices. Our analysis shows that offloading these primitives to PIM logic, consisting of either simple cores or specialized accelerators, eliminates a large amount of data movement, and significantly reduces total system energy (by an average of 55.4\% across the workloads) and execution time (by an average of 54.2\%).},
	author = {Amirali Boroumand and Saugata Ghose and Youngsok Kim and Rachata Ausavarungnirun and Eric Shiu and Rahul Thakur and Dae-Hyun Kim and Aki Kuusela and Allan Knies and Parthasarathy Ranganathan and Onur Mutlu},
	booktitle = {Proceedings of the 23rd International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS)},
	title = {Google Workloads for Consumer Devices: Mitigating Data Movement Bottlenecks},
	venue = {Williamsburg, VA, USA},
	year = {2018}
}

@inproceedings{abc,
	abstract = {Emerging chips with hundreds and thousands of cores require networks with unprecedented energy/area efficiency and scalability. To address this, we propose Slim NoC (SN): a new on-chip network design that delivers significant improvements in efficiency and scalability compared to the state-of-the-art. The key idea is to use two concepts from graph and number theory, degree-diameter graphs combined with non-prime finite fields, to enable the smallest number of ports for a given core count. SN is inspired by state-of-the-art off-chip topologies; it identifies and distills their advantages for NoC settings while solving several key issues that lead to significant overheads on-chip. SN provides NoC-specific layouts, which further enhance area/energy efficiency. We show how to augment SN with state-of-the-art router microarchitecture schemes such as Elastic Links, to make the network even more scalable and efficient. Our extensive experimental evaluations show that SN outperforms both traditional low-radix topologies (e.g., meshes and tori) and modern high-radix networks (e.g., various Flattened Butterflies) in area, latency, throughput, and static/dynamic power consumption for both synthetic and real workloads. SN provides a promising direction in scalable and energy-efficient NoC topologies.},
	author = {Maciej Besta and Syed M. Hassan and Sudhakar Yalamanchili and Rachata Ausavarungnirun and Onur Mutlu and Torsten Hoefler},
	booktitle = {Proceedings of the 23rd International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS)},
	title = {Slim NoC: A Low-Diameter On-Chip Network Topology for High Energy Efficiency and Scalability},
	venue = {Williamsburg, VA, USA},
	year = {2018}
}

@inproceedings{abc,
	abstract = {Graphics Processing Units (GPUs) exploit large amounts of threadlevel parallelism to provide high instruction throughput and to efficiently hide long-latency stalls. The resulting high throughput, along with continued programmability improvements, have made GPUs an essential computational resource in many domains. Applications from different domains can have vastly different compute and memory demands on the GPU. In a large-scale computing environment, to efficiently accommodate such wide-ranging demands without leaving GPU resources underutilized, multiple applications can share a single GPU, akin to how multiple applications execute concurrently on a CPU. Multi-application concurrency requires several support mechanisms in both hardware and software. One such key mechanism is virtual memory, which manages and protects the address space of each application. However, modern GPUs lack the extensive support for multi-application concurrency available in CPUs, and as a result suffer from high performance overheads when shared by multiple applications, as we demonstrate. We perform a detailed analysis of which multi-application concurrency support limitations hurt GPU performance the most. We find that the poor performance is largely a result of the virtual memory mechanisms employed in modern GPUs. In particular, poor address translation performance is a key obstacle to efficient GPU sharing. State-of-the-art address translation mechanisms, which were designed for single-application execution, experience significant inter-application interference when multiple applications spatially share the GPU. This contention leads to frequent misses in the shared translation lookaside buffer (TLB), where a single miss can induce long-latency stalls for hundreds of threads. As a result, the GPU often cannot schedule enough threads to successfully hide the stalls, which diminishes system throughput and becomes a first-order performance concern. Based on our analysis, we propose MASK, a new GPU framework that provides low-overhead virtual memory support for the concurrent execution of multiple applications. MASK consists of three novel address-translation-aware cache and memory management mechanisms that work together to largely reduce the overhead of address translation: (1) a token-based technique to reduce TLB contention, (2) a bypassing mechanism to improve the effectiveness of cached address translations, and (3) an application-aware memory scheduling scheme to reduce the interference between address translation and data requests. Our evaluations show that MASK restores much of the throughput lost to TLB contention. Relative to a state-of-the-art GPU TLB, MASK improves system throughput by 57.8\%, improves IPC throughput by 43.4\%, and reduces applicationlevel unfairness by 22.4\%. MASK{\textquoteright}s system throughput is within 23.2\% of an ideal GPU system with no address translation overhead.},
	author = {Rachata Ausavarungnirun and Vance Miller and Joshua Landgraf and Saugata Ghose and Jayneel Gandhi and Adwait Jog and Christopher Rossbach and Onur Mutlu},
	booktitle = {Proceedings of the 23rd International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS)},
	title = {MASK: Redesigning the GPU Memory Hierarchy to Support Multi-Application Concurrency},
	venue = {Williamsburg, VA, USA},
	year = {2018}
}

@inproceedings{abc,
	abstract = {Graphics Processing Units (GPUs) employ large register files to accommodate all active threads and accelerate context switching. Unfortunately, register files are a scalability bottleneck for future GPUs due to long access latency, high power consumption, and large silicon area provisioning. Prior work proposes hierarchical register file, to reduce the register file power consumption by caching registers in a smaller register file cache. Unfortunately, this approach does not improve register access latency due to the low hit rate in the register file cache. 
In this paper, we propose the Latency-Tolerant Register File (LTRF) architecture to achieve low latency in a two-level hierarchical structure while keeping power consumption low. We observe that compile-time interval analysis enables us to divide GPU program execution into intervals with an accurate estimate of a warp{\textquoteright}s aggregate register working-set within each interval. The key idea of LTRF is to prefetch the estimated register working-set from the main register file to the register file cache under software control, at the beginning of each interval, and overlap the prefetch latency with the execution of other warps. Our experimental results show that LTRF enables high-capacity yet long-latency main GPU register files, paving the way for various optimizations. As an example optimization, we implement the main register file with emerging high-density high-latency memory technologies, enabling 8{\texttimes} larger capacity and improving overall GPU performance by 31\% while reducing register file power consumption by 46\%.},
	author = {Mohammad Sadrosadati and Amirhossein Mirhosseini and Seyed B. Ehsani and Hamid Sarbazi-Azad and Mario Drumond and Babak Falsafi and Rachata Ausavarungnirun and Onur Mutlu},
	booktitle = {Proceedings of the 23rd International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS)},
	title = {LTRF: Enabling High-Capacity Register Files for GPUs via Hardware/Software Cooperative Register Prefetching},
	url = {https://dl.acm.org/citation.cfm?id=3173211},
	venue = {Williamsburg, VA, USA},
	year = {2018}
}

@inproceedings{abc,
	abstract = {Resource management strategies for many-core systems need to enable sharing of resources such as power, processing cores, and memory bandwidth while coordinating the priority and significance of system- and application-level objectives at runtime in a scalable and robust manner. State-of-the-art approaches use heuristics or machine learning for resource management, but unfortunately lack formalism in providing robustness against unexpected corner cases. While recent efforts deploy classical control-theoretic approaches with some guarantees and formalism, they lack scalability and autonomy to meet changing runtime goals. We present SPECTR, a new resource management approach for many-core systems that leverages formal supervisory control theory (SCT) to combine the strengths of classical control theory with state-of-the-art heuristic approaches to efficiently meet changing runtime goals. SPECTR is a scalable and robust control architecture and a systematic design flow for hierarchical control of many-core systems. SPECTR leverages SCT techniques such as gain scheduling to allow autonomy for individual controllers. It facilitates automatic synthesis of the high-level supervisory controller and its property verification. We implement SPECTR on an Exynos platform containing ARM{\textquoteright}s big.LITTLE-based heterogeneous multi-processor (HMP) and demonstrate that SPECTR{\textquoteright}s use of SCT is key to managing multiple interacting resources (e.g., chip power and processing cores) in the presence of competing objectives (e.g., satisfying QoS vs. power capping). The principles of SPECTR are easily applicable to any resource type and objective as long as the management problem can be modeled using dynamical systems theory (e.g., difference equations), discrete-event dynamic systems, or fuzzy dynamics.},
	author = {Amir M. Rahmani and Bryan Donyanavard and Tiago Mück and Kasra Moazzemi and Axel Jantsch and Onur Mutlu and Nikil Dutt},
	booktitle = {Proceedings of the 23rd International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS)},
	title = {SPECTR: Formal Supervisory Control and Coordination for Many-core Systems Resource Management},
	url = {https://dl.acm.org/citation.cfm?id=3173199},
	venue = {Williamsburg, VA, USA},
	year = {2018}
}

@inproceedings{abc,
	abstract = {NAND flash memory density continues to scale to keep up with the increasing storage demands of data-intensive applications. Unfortunately, as a result of this scaling, the lifetime of NAND flash memory has been decreasing. Each cell in NAND flash memory can endure only a limited number of writes, due to the damage caused by each program and erase operation on the cell. This damage can be partially repaired on its own during the idle time between program or erase operations (known as the dwell time), via a phenomenon known as the self-recovery effect. Prior works study the self-recovery effect for planar (i.e., 2D) NAND flash memory, and propose to exploit it to improve flash lifetime, by applying high temperature to accelerate selfrecovery. However, these findings may not be directly applicable to 3D NAND flash memory, due to significant changes in the design and manufacturing process that are required to enable practical 3D stacking for NAND flash memory. In this paper, we perform the first detailed experimental characterization of the effects of self-recovery and temperature on real, state-of-the-art 3D NAND flash memory devices. We show that these effects influence two major factors of NAND flash memory reliability: (1) retention loss speed (i.e., the speed at which a flash cell leaks charge), and (2) program variation (i.e., the difference in programming speed across flash cells). We find that self-recovery and temperature affect 3D NAND flash memory quite differently than they affect planar NAND flash memory, rendering prior models of self-recovery and temperature ineffective for 3D NAND flash memory. Using our characterization results, we develop a new model for 3D NAND flash memory reliability, which predicts how retention, wearout, self-recovery, and temperature affect raw bit error rates and cell threshold voltages. We show that our model is accurate, with an error of only 4.9\%. Based on our experimental findings and our model, we propose HeatWatch, a new mechanism to improve 3D NAND flash memory reliability. The key idea of HeatWatch is to optimize the read reference voltage, i.e., the voltage applied to the cell during a read operation, by adapting it to the dwell time of the workload and the current operating temperature. HeatWatch (1) efficiently tracks flash memory temperature and dwell time online, (2) sends this information to our reliability model to predict the current voltages of flash cells, and (3) predicts the optimal read reference voltage based on the current cell voltages. Our detailed experimental evaluations show that HeatWatch improves flash lifetime by 3.85{\texttimes} over a baseline that uses a fixed read reference voltage, averaged across 28 real storage workload traces, and comes within 0.9\% of the lifetime of an ideal read reference voltage selection mechanism.},
	author = {Yixin Luo and Saugata Ghose and Yu Cai and Erich F. Haratsch and Onur Mutlu},
	booktitle = {Proceedings of the 24th International Symposium on High-Performance Computer Architecture (HPCA)},
	title = {HeatWatch: Improving 3D NAND Flash Memory Device Reliability by Exploiting Self-Recovery and Temperature-Awareness},
	venue = {Vienna, Austria},
	year = {2018}
}

@inproceedings{abc,
	abstract = {Physically Unclonable Functions (PUFs) are commonly used in cryptography to identify devices based on the uniqueness of their physical microstructures. DRAM-based PUFs have numerous advantages over PUF designs that exploit alternative substrates: DRAM is a major component of many modern systems, and a DRAM-based PUF can generate many unique identifiers. However, none of the prior DRAM PUF proposals provide implementations suitable for runtime-accessible PUF evaluation on commodity DRAM devices. Prior DRAM PUFs exhibit unacceptably high latencies, especially at low temperatures (e.g., >125.8s on average for a 64KiB memory segment below 55{\textopenbullet}C), and they cause high system interference by keeping part of DRAM unavailable during PUF evaluation. In this paper, we introduce the DRAM latency PUF, a new class of fast, reliable DRAM PUFs. The key idea is to reduce DRAM read access latency below the reliable datasheet specifications using software-only system calls. Doing so results in error patterns that reflect the compound effects of manufacturing variations in various DRAM structures (e.g., capacitors, wires, sense amplifiers). Based on a rigorous experimental characterization of 223 modern LPDDR4 DRAM chips, we demonstrate that these error patterns 1) satisfy runtime-accessible PUF requirements, and 2) are quickly generated (i.e., at 88.2ms) irrespective of operating temperature using a real system with no additional hardware modifications. We show that, for a constant DRAM capacity overhead of 64KiB, our implementation of the DRAM latency PUF enables an average (minimum, maximum) PUF evaluation time speedup of 152x (109x, 181x) at 70{\textopenbullet}C and 1426x (868x, 1783x) at 55{\textopenbullet}C when compared to a DRAM retention PUF and achieves greater speedups at even lower temperatures.},
	author = {Jeremie Kim and Minesh Patel and Hasan Hassan and Onur Mutlu},
	booktitle = {Proceedings of the 24th International Symposium on High-Performance Computer Architecture (HPCA)},
	title = {The DRAM Latency PUF: Quickly Evaluating Physical Unclonable Functions by Exploiting the Latency-Reliability Tradeoff in Mod...},
	venue = {Vienna, Austria},
	year = {2018}
}

@inproceedings{abc,
	abstract = {Solid-state drives (SSDs) are used in a wide array of computer systems today, including in datacenters and enterprise servers. As the I/O demands of these systems continue to increase, manufacturers are evolving SSD architectures to keep up with this demand. For example, manufacturers have introduced new high-bandwidth interfaces to replace the conventional SATA host-interface protocol. These new interfaces, such as the NVMe protocol, are designed specifically to enable the high amounts of concurrent I/O bandwidth that SSDs are capable of delivering.

While modern SSDs with sophisticated features such as the NVMe protocol are already on the market, existing SSD simulation tools have fallen behind, as they do not capture these new features. We find that state-of-the-art SSD simulators have three shortcomings that prevent them from accurately modeling the performance of real off-the-shelf SSDs. First, these simulators do not model critical features of new protocols (e.g., NVMe), such as their use of multiple application-level queues for requests and the elimination of OS intervention for I/O request processing. Second, these simulators often do not accurately capture the impact of advanced SSD maintenance algorithms (e.g., garbage collection), as they do not properly or quickly emulate steady-state conditions that can significantly change the behavior of these algorithms in real SSDs. Third, these simulators do not capture the full end-to-end latency of I/O requests, which can incorrectly skew the results reported for SSDs that make use of emerging non-volatile memory technologies. By not accurately modeling these three features, existing simulators report results that deviate significantly from real SSD performance.

In this work, we introduce a new simulator, called MQSim, that accurately models the performance of both modern SSDs and conventional SATA-based SSDs. MQSim faithfully models new high-bandwidth protocol implementations, steady-state SSD conditions, and the full end-to-end latency of requests in modern SSDs. We validate MQSim, showing that it reports performance results that are only 6\%-18\% apart from the measured actual performance of four real state-of-the-art SSDs. We show that by modeling critical features of modern SSDs, MQSim uncovers several real and important issues that were not captured by existing simulators, such as the performance impact of inter-flow interference. We have released MQSim as an open-source tool, and we hope that it can enable researchers to explore directions in new and different areas.},
	author = {Arash Tavakkol and Juan Gomez-Luna and Mohammad Sadrosadati and Saugata Ghose and Onur Mutlu},
	booktitle = {Proceedings of the 16th USENIX Conference on File and Storage Technologies},
	title = {MQsim: a framework for enabling realistic studies of modern multi-queue SSD devices},
	venue = {Oakland, CA, USA},
	year = {2018}
}

@inproceedings{abc,
	abstract = {Betweenness centrality (BC) is a crucial graph problem that measures the significance of a vertex by the number of shortest paths leading through it. We propose Maximal Frontier Betweenness Centrality (MFBC): a succinct BC algorithm based on novel sparse matrix multiplication routines that performs a factor of p1/3 less communication on p processors than the best known alternatives, for graphs with n vertices and average degree k = n/p2/3. We formulate, implement, and prove the correctness of MFBC for weighted graphs by leveraging monoids instead of semirings, which enables a surprisingly succinct formulation. MFBC scales well for both extremely sparse and relatively dense graphs. It automatically searches a space of distributed data decompositions and sparse matrix multiplication algorithms for the most advantageous configuration. The MFBC implementation outperforms the well-known CombBLAS library by up to 8x and shows more robust performance. Our design methodology is readily extensible to other graph problems.},
	author = {Edgar Solomonik and Maciej Besta and Flavio Vella and Torsten Hoefler},
	booktitle = {Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis},
	title = {Scaling Betweenness Centrality using Communication-Efficient Sparse Matrix Multiplication},
	venue = {Denver, CO, USA},
	year = {2017}
}

@article{abc,
	abstract = {Motivation
High throughput DNA sequencing (HTS) technologies generate an excessive number of small DNA segments -called short reads- that cause significant computational burden. To analyze the entire genome, each of the billions of short reads must be mapped to a reference genome based on the similarity between a read and {\textquoteleft}candidate{\textquoteright} locations in that reference genome. The similarity measurement, called alignment, formulated as an approximate string matching problem, is the computational bottleneck because: (i) it is implemented using quadratic-time dynamic programming algorithms and (ii) the majority of candidate locations in the reference genome do not align with a given read due to high dissimilarity. Calculating the alignment of such incorrect candidate locations consumes an overwhelming majority of a modern read mapper{\textquoteright}s execution time. Therefore, it is crucial to develop a fast and effective filter that can detect incorrect candidate locations and eliminate them before invoking computationally costly alignment algorithms.

Results
We propose GateKeeper, a new hardware accelerator that functions as a pre-alignment step that quickly filters out most incorrect candidate locations. GateKeeper is the first design to accelerate pre-alignment using Field-Programmable Gate Arrays (FPGAs), which can perform pre-alignment much faster than software. When implemented on a single FPGA chip, GateKeeper maintains high accuracy (on average >96\%) while providing, on average, 90-fold and 130-fold speedup over the state-of-the-art software pre-alignment techniques, Adjacency Filter and Shifted Hamming Distance (SHD), respectively. The addition of GateKeeper as a pre-alignment step can reduce the verification time of the mrFAST mapper by a factor of 10.},
	author = {Mohammed Alser and Hasan Hassan and Hongyi Xin and Oguz Ergin and Onur Mutlu and Can Alkan},
	pages = {3355-3363},
	journal = {Bioinformatics},
	title = {GateKeeper: a new hardware architecture for accelerating pre-alignment in DNA short read mapping},
	volume = {33},
	year = {2017}
}

@inproceedings{abc,
	abstract = {Optimizing communication performance is imperative for large-scale computing because communication overheads limit the strong scalability of parallel applications. Today{\textquoteright}s network cards contain rather powerful processors optimized for data movement. However, these devices are limited to fixed functions, such as remote direct memory access. We develop sPIN, a portable programming model to offload simple packet processing functions to the network card. To demonstrate the potential of the model, we design a cycle-accurate simulation environment by combining the network simulator LogGOPSim and the CPU simulator gem5. We implement offloaded message matching, datatype processing, and collective communications and demonstrate transparent full-application speedups. Furthermore, we show how sPIN can be used to accelerate redundant in-memory filesystems and several other use cases. Our work investigates a portable packet-processing network acceleration model similar to compute acceleration with CUDA or OpenCL. We show how such network acceleration enables an eco-system that can significantly speed up applications and system services.},
	author = {Torsten Hoefler and Salvatore Di Girolamo and Konstantin Taranov and Ron Brightwell},
	booktitle = {Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis},
	title = {sPIN: High-performance streaming Processing in the Network},
	venue = {Denver, CO, USA},
	year = {2017}
}

@article{abc,
	abstract = {The cost of data movement has always been an important concern in high performance computing (HPC) systems. It has now become the dominant factor in terms of both energy consumption and performance. Support for expression of data locality has been explored in the past, but those efforts have had only modest success in being adopted in HPC applications for various reasons. them However, with the increasing complexity of the memory hierarchy and higher parallelism in emerging HPC systems, locality management has acquired a new urgency. Developers can no longer limit themselves to low-level solutions and ignore the potential for productivity and performance portability obtained by using locality abstractions. Fortunately, the trend emerging in recent literature on the topic alleviates many of the concerns that got in the way of their adoption by application developers. Data locality abstractions are available in the forms of libraries, data structures, languages and runtime systems; a common theme is increasing productivity without sacrificing performance. This paper examines these trends and identifies commonalities that can combine various locality concepts to develop a comprehensive approach to expressing and managing data locality on future large-scale high-performance computing systems.},
	author = {Didem Unat and Anshu Dubey and Torsten Hoefler and John Shalf and Mark Abraham and Mauro Bianco and Bradford L. Chamberlain and Romain Cledat and H. Carter Edwards and Hal Finkel and Karl Fuerlinger and Frank Hannig and Emmanuel Jeannot and Amir Kamil and Jeff Keasler and Paul H. J. Kelly and Vitus Leung and Hatem Ltaief and Naoya Maruyama and Chris J. Newburn and Miquel Pericas},
	pages = {3007-3020},
	journal = {IEEE Transactions on Parallel and Distributed Systems},
	title = {Trends in Data Locality Abstractions for HPC Systems},
	volume = {28},
	year = {2017}
}

@inproceedings{abc,
	abstract = {Contemporary discrete GPUs support rich memory management features such as virtual memory and demand paging. These features simplify GPU programming by providing a virtual address space abstraction similar to CPUs and eliminating manual memory management, but they introduce high performance overheads during (1) address translation and (2) page faults. A GPU relies on high degrees of thread-level parallelism (TLP) to hide memory latency. Address translation can undermine TLP, as a single miss in the translation lookaside buffer (TLB) invokes an expensive serialized page table walk that often stalls multiple threads. Demand paging can also undermine TLP, as multiple threads often stall while they wait for an expensive data transfer over the system I/O (e.g., PCIe) bus when the GPU demands a page.

In modern GPUs, we face a trade-off on how the page size used for memory management affects address translation and demand paging. The address translation overhead is lower when we employ a larger page size (e.g., 2MB large pages, compared with conventional 4KB base pages), which increases TLB coverage and thus reduces TLB misses. Conversely, the demand paging overhead is lower when we employ a smaller page size, which decreases the system I/O bus transfer latency. Support for multiple page sizes can help relax the page size trade-off so that address translation and demand paging optimizations work together synergistically. However, existing page coalescing (i.e., merging base pages into a large page) and splintering (i.e., splitting a large page into base pages) policies require costly base page migrations that undermine the benefits multiple page sizes provide. In this paper, we observe that GPGPU applications present an opportunity to support multiple page sizes without costly data migration, as the applications perform most of their memory allocation en masse (i.e., they allocate a large number of base pages at once). We show that this en masse allocation allows us to create intelligent memory allocation policies which ensure that base pages that are contiguous in virtual memory are allocated to contiguous physical memory pages. As a result, coalescing and splintering operations no longer need to migrate base pages.

We introduce Mosaic, a GPU memory manager that provides application-transparent support for multiple page sizes. Mosaic uses base pages to transfer data over the system I/O bus, and allocates physical memory in a way that (1) preserves base page contiguity and (2) ensures that a large page frame contains pages from only a single memory protection domain. We take advantage of this allocation strategy to design a novel in-place page size selection mechanism that avoids data migration. This mechanism allows the TLB to use large pages, reducing address translation overhead. During data transfer, this mechanism enables the GPU to transfer only the base pages that are needed by the application over the system I/O bus, keeping demand paging overhead low. Our evaluations show that Mosaic reduces address translation overheads while efficiently achieving the benefits of demand paging, compared to a contemporary GPU that uses only a 4KB page size. Relative to a state-of-the-art GPU memory manager, Mosaic improves the performance of homogeneous and heterogeneous multi-application workloads by 55.5\% and 29.7\% on average, respectively, coming within 6.8\% and 15.4\% of the performance of an ideal TLB where all TLB requests are hits.},
	author = {Rachata Ausavarungnirun and Joshua Landgraf and Vance Miller and Saugata Ghose and Jayneel Gandhi and Christopher Rossbach and },
	booktitle = {Proceedings of the 50th Annual IEEE/ACM International Symposium on Microarchitecture},
	title = {Mosaic: a GPU memory manager with application-transparent support for multiple page sizes},
	venue = {Cambridge, MA, USA},
	year = {2017}
}

@inproceedings{abc,
	abstract = {DRAM cells in close proximity can fail depending on the data content in neighboring cells. These failures are called data-dependent failures. Detecting and mitigating these failures online, while the system is running in the field, enables various optimizations that improve reliability, latency, and energy efficiency of the system. For example, a system can improve performance and energy efficiency by using a lower refresh rate for most cells and mitigate the failing cells using higher refresh rates or error correcting codes. All these system optimizations depend on accurately detecting every possible data-dependent failure that could occur with any content in DRAM. Unfortunately, detecting all data-dependent failures requires the knowledge of DRAM internals specific to each DRAM chip. As internal DRAM architecture is not exposed to the system, detecting data-dependent failures at the system-level is a major challenge.

In this paper, we decouple the detection and mitigation of data-dependent failures from physical DRAM organization such that it is possible to detect failures without knowledge of DRAM internals. To this end, we propose MEMCON, a memory content-based detection and mitigation mechanism for data-dependent failures in DRAM. MEMCON does not detect every possible data-dependent failure. Instead, it detects and mitigates failures that occur only with the current content in memory while the programs are running in the system. Such a mechanism needs to detect failures whenever there is a write access that changes the content of memory. As detection of failure with a runtime testing has a high overhead, MEMCON selectively initiates a test on a write, only when the time between two consecutive writes to that page (i.e., write interval) is long enough to provide significant benefit by lowering the refresh rate during that interval. MEMCON builds upon a simple, practical mechanism that predicts the long write intervals based on our observation that the write intervals in real workloads follow a Pareto distribution: the longer a page remains idle after a write, the longer it is expected to remain idle.

Our evaluation shows that compared to a system that uses an aggressive refresh rate, MEMCON reduces refresh operations by 65--74\%, leading to a 10\%/17\%/40\% (min) to 12\%/22\%/50\% (max) performance improvement for a single-core and 10\%/23\%/52\% (min) to 17\%/29\%/65\% (max) performance improvement for a 4-core system using 8/16/32 Gb DRAM chips.},
	author = {Samira Manabi Khan and Chris Wilkerson and Zhe Wang and Alaa R. Alameldeen and Donghyuk Lee and Onur Mutlu},
	booktitle = {Proceedings of the 50th Annual IEEE/ACM International Symposium on Microarchitecture},
	title = {Detecting and mitigating data-dependent DRAM failures by exploiting current memory content},
	venue = {Cambridge, MA, USA},
	year = {2017}
}

@inproceedings{abc,
	abstract = {Many important applications trigger bulk bitwise operations, i.e., bitwise operations on large bit vectors. In fact, recent works design techniques that exploit fast bulk bitwise operations to accelerate databases (bitmap indices, BitWeaving) and web search (BitFunnel). Unfortunately, in existing architectures, the throughput of bulk bitwise operations is limited by the memory bandwidth available to the processing unit (e.g., CPU, GPU, FPGA, processing-in-memory).

To overcome this bottleneck, we propose Ambit, an Accelerator-in-Memory for bulk bitwise operations. Unlike prior works, Ambit exploits the analog operation of DRAM technology to perform bitwise operations completely inside DRAM, thereby exploiting the full internal DRAM bandwidth. Ambit consists of two components. First, simultaneous activation of three DRAM rows that share the same set of sense amplifiers enables the system to perform bitwise AND and OR operations. Second, with modest changes to the sense amplifier, the system can use the inverters present inside the sense amplifier to perform bitwise NOT operations. With these two components, Ambit can perform any bulk bitwise operation efficiently inside DRAM. Ambit largely exploits existing DRAM structure, and hence incurs low cost on top of commodity DRAM designs (1\% of DRAM chip area). Importantly, Ambit uses the modern DRAM interface without any changes, and therefore it can be directly plugged onto the memory bus.

Our extensive circuit simulations show that Ambit works as expected even in the presence of significant process variation. Averaged across seven bulk bitwise operations, Ambit improves performance by 32X and reduces energy consumption by 35X compared to state-of-the-art systems. When integrated with Hybrid Memory Cube (HMC), a 3D-stacked DRAM with a logic layer, Ambit improves performance of bulk bitwise operations by 9.7X compared to processing in the logic layer of the HMC. Ambit improves the performance of three real-world data-intensive applications, 1) database bitmap indices, 2) BitWeaving, a technique to accelerate database scans, and 3) bit-vector-based implementation of sets, by 3X-7X compared to a state-of-the-art baseline using SIMD optimizations. We describe four other applications that can benefit from Ambit, including a recent technique proposed to speed up web search. We believe that large performance and energy improvements provided by Ambit can enable other applications to use bulk bitwise operations.},
	author = {Vivek Seshadri and Donghyuk Lee and Thomas Mullins and Hasan Hassan and Amirali Boroumand and Jeremie Kim and Michael A. Kozuch and Onur Mutlu and Phillip B. Gibbons and Todd C. Mowry},
	booktitle = {Proceedings of the 50th Annual IEEE/ACM International Symposium on Microarchitecture},
	title = {Ambit: in-memory accelerator for bulk bitwise operations using commodity DRAM technology},
	venue = {Cambridge, MA, USA},
	year = {2017}
}

@inproceedings{abc,
	abstract = {Decision tree ensembles are commonly used in a wide range of applications and becoming the de facto algorithm for decision tree based classifiers. Different trees in an ensemble can be processed in parallel during tree inference, making them a suitable use case for FPGAs. Large tree ensembles, however, require careful mapping of trees to on-chip memory and management of memory accesses. As a result, existing FPGA solutions suffer from the inability to scale beyond tens of trees and lack the flexibility to support different tree ensembles. In this paper we present an FPGA tree ensemble classifier together with a software driver to efficiently manage the FPGA{\textquoteright}s memory resources. The classifier architecture efficiently utilizes the FPGA{\textquoteright}s resources to fit half a million tree nodes in on-chip memory, delivering up to 20{\texttimes} speedup over a 10-threaded CPU implementation when fully processing the tree ensemble on the FPGA. It can also combine the CPU and FPGA to scale to tree ensembles that do not fit in on-chip memory, achieving up to an order of magnitude speedup compared to a pure CPU implementation. In addition, the classifier architecture can be programmed at runtime to process varying tree ensemble sizes.},
	author = {Muhsen Owaida and Hantian Zhang and Ce Zhang and Gustavo Alonso},
	booktitle = {Proceedings of the 27th International Conference on Field Programmable Logic and Applications (FPL)},
	title = {Scalable inference of decision tree ensembles: Flexible design for CPU-FPGA platforms},
	venue = {Ghent, Belgium},
	year = {2017}
}

@article{abc,
	abstract = {A number of physical limitations mandate radical changes in the way how we build computing hard- and software, and there is broad consensus that a stronger interaction between hard- and software communities is needed to meet the ever-growing demand for application performance. Under this motivation, representatives from various hard- and software communities have met at the Dagstuhl seminar "Databases on Future Hardware" to discuss the implications in the context of database systems. The outcome of the seminar was not only a much better understanding of each other{\textquoteright}s needs, constraints, and ways of thinking. Very importantly, the group identified topic areas that seem key for the ongoing shift, together with suggestions on how the field could move forward. During the seminar, it turned out that the future of databases is not only a question of technology. Rather, economic considerations have to be taken into account when building next-generation database engines.},
	author = {Gustavo Alonso and Michaela Blott and Jens Teubner},
	pages = {1-18},
	journal = {Dagstuhl Reports},
	title = {Databases on Future Hardware},
	volume = {7},
	year = {2017}
}

@inproceedings{abc,
	abstract = {While the memory footprints of cloud and HPC applications continue to increase, fundamental issues with DRAM scaling are likely to prevent traditional main memory systems, composed of monolithic DRAM, from greatly growing in capacity. Hybrid memory systems can mitigate the scaling limitations of monolithic DRAM by pairing together multiple memory technologies (e.g., different types of DRAM, or DRAM and non-volatile memory) at the same level of the memory hierarchy. The goal of a hybrid main memory is to combine the different advantages of the multiple memory types in a cost-effective manner while avoiding the disadvantages of each technology. Memory pages are placed in and migrated between the different memories within a hybrid memory system, based on the properties of each page. It is important to make intelligent page management (i.e., placement and migration) decisions, as they can significantly affect system performance.In this paper, we propose utility-based hybrid memory management (UH-MEM), a new page management mechanism for various hybrid memories, that systematically estimates the utility (i.e., the system performance benefit) of migrating a page between different memory types, and uses this information to guide data placement. UH-MEM operates in two steps. First, it estimates how much a single application would benefit from migrating one of its pages to a different type of memory, by comprehensively considering access frequency, row buffer locality, and memory-level parallelism. Second, it translates the estimated benefit of a single application to an estimate of the overall system performance benefit from such a migration.We evaluate the effectiveness of UH-MEM with various types of hybrid memories, and show that it significantly improves system performance on each of these hybrid memories. For a memory system with DRAM and non-volatile memory, UH-MEM improves performance by 14\% on average (and up to 26\%) compared to the best of three evaluated state-of-the-art mechanisms across a large number of data-intensive workloads.},
	author = {Yang Li and Saugata Ghose and Jongmoo Choi and Jin Sun and Hui Wang and Onur Mutlu},
	booktitle = {Proceedins of the 2017 IEEE International Conference on Cluster Computing (CLUSTER)},
	title = {Utility-Based Hybrid Memory Management},
	venue = {Honolulu, HI, USA},
	year = {2017}
}

@inproceedings{abc,
	abstract = {Interconnection networks must meet the communication demands of current High-Performance Computing systems. In order to interconnect efficiently the end nodes of these systems with a good performance-to-cost ratio, new network topologies have been proposed in the last years that leverage high-radix switches, such as Slim Fly. Adversarial traffic patterns, however, may reduce severely the performance of Slim Fly networks when using only minimal-path routing. In order to mitigate the performance degradation in these scenarios, Slim Fly networks should configure an oblivious or adaptive non-minimal routing. The non-minimal routing algorithms proposed for Slim Fly usually rely on Valiant{\textquoteright}s algorithm to select the paths, at the cost of doubling the average path-length, as well as the number of Virtual Channels (VCs) required to prevent deadlocks. Moreover, Valiant may introduce additional inefficiencies when applied to Slim Fly networks, such as the "turn-around problem" that we analyze in this work. With the aim of overcoming these drawbacks, we propose in this paper two variants of the Valiant{\textquoteright}s algorithm that improve the non-minimal path selection in Slim Fly networks. They are designed to be combined with adaptive routing algorithms that rely on Valiant to select non-minimalpaths, such as UGAL or PAR, which we have adapted to the Slim Fly topology. Through the results from simulation experiments, we show that our proposals improve the network performance and/or reduce the number of required VCs to prevent deadlocks, even in scenarios with adversarial traffic.},
	author = {Pedro Yebenes and Jesus Escudero-Sahuquillo and Pedro Javier Garcia and Francisco J. Quiles and Torsten Hoefler},
	booktitle = {Proceedings of the 25th Annual Symposium on High-Performance Interconnects (HOTI{\textquoteright}17)},
	title = {Improving Non-Minimal and Adaptive Routing Algorithms in Slim Fly Networks},
	venue = {Santa Clara, CA, USA},
	year = {2017}
}

@inproceedings{abc,
	abstract = {The advent of non-volatile memory (NVM) technologies has added an interesting nuance to the node level memory hierarchy. With modern 100 Gb/s networks, the NVM tier of storage can often be slower than the high performance network in the system; thus, a new challenge arises in the datacenter. Whereas prior efforts have studied the impacts of multiple sources targeting one node (i.e., incast) and have studied multiple flows causing congestion in inter-switch links, it is now possible for a single flow from a single source to overwhelm the bandwidth of a key portion of the memory hierarchy. This can subsequently spread to the switches and lead to congestion trees in a flow-controlled network or excessive packet drops without flow control. In this work we describe protocols which avoid overwhelming the receiver in the case of a source/sink rate mismatch. We design our protocols on top of Portals 4, which enables us to make use of network offload. Our protocol yields up to 4{\texttimes} higher throughput in a 5k node Dragonfly topology for a permutation traffic pattern in which only 1\% of all nodes have a memory write-bandwidth limitation of 1/8th of the network bandwidth.},
	author = {Timo Schneider and James Dinan and Mario Flajslik and Keith D. Underwood and Torsten Hoefler},
	booktitle = {Proceedings of the 25th Annual Symposium on High-Performance Interconnects (HOTI{\textquoteright}17)},
	title = {Fast Networks and Slow Memories: A Mechanism for Mitigating Bandwidth Mismatches},
	venue = {Santa Clara, CA, USA},
	year = {2017}
}

@inproceedings{abc,
	author = {Hantian Zhang and Jerry Li and Kaan Kara and Dan Alistarh and Ji Liu and Ce Zhang},
	booktitle = {Proceedings of the 34th International Conference on Machine Learning, ICML 2017, Sydney, NSW, Australia},
	title = {ZipML: Training Linear Models with End-to-End Low Precision, and a Little Bit of Deep Learning.},
	url = {http://proceedings.mlr.press/v70/zhang17e.html},
	year = {2017}
}

@inproceedings{abc,
	abstract = {The ever increasing amount of data being handled in data centers causes an intrinsic inefficiency: moving data around is expensive in terms of bandwidth, latency, and power consumption, especially given the low computational complexity of many database operations. In this paper we explore near-data processing in database engines, i.e., the option of offloading part of the computation directly to the storage nodes. We implement our ideas in Caribou, an intelligent distributed storage layer incorporating many of the lessons learned while building systems with specialized hardware. Caribou provides access to DRAM/NVRAM storage over the network through a simple key-value store interface, with each storage node providing high-bandwidth near-data processing at line rate and fault tolerance through replication. The result is a highly efficient, distributed, intelligent data storage that can be used to both boost performance and reduce power consumption and real estate usage in the data center thanks to the micro-server architecture adopted.},
	author = {Zsolt Istv{\'a}n and David Sidler and Gustavo Alonso},
	booktitle = {Proceedings of the VLDB Endowment},
	title = {Caribou: Intelligent Distributed Storage},
	venue = {Munich, Germany},
	year = {2017}
}

@inproceedings{abc,
	author = {Debopam Bhattacherjee and Muhammad Tirmazi and Ankit Singla},
	booktitle = {9th USENIX Workshop on Hot Topics in Cloud Computing, HotCloud 2017, Santa Clara, CA, USA},
	title = {A Cloud-based Content Gathering Network.},
	url = {https://www.usenix.org/conference/hotcloud17/program/presentation/bhattacherjee},
	year = {2017}
}

@inproceedings{abc,
	author = {Zhiyu Liu and Irina Calciu and Maurice Herlihy and Onur Mutlu},
	booktitle = {Proceedings of the 29th ACM Symposium on Parallelism in Algorithms and Architectures, SPAA 2017, Washington DC, USA},
	title = {Concurrent Data Structures for Near-Memory Computing.},
	url = {http://doi.acm.org/10.1145/3087556.3087582},
	year = {2017}
}

@inproceedings{abc,
	author = {Xi-Yue Xiang and Wentao Shi and Saugata Ghose and Lu Peng and Onur Mutlu and Nian-Feng Tzeng},
	booktitle = {Proceedings of the International Conference on Supercomputing, ICS 2017, Chicago, IL, USA},
	title = {Carpool: a bufferless on-chip network supporting adaptive multicast and hotspot alleviation.},
	url = {http://doi.acm.org/10.1145/3079079.3079090},
	year = {2017}
}

@inproceedings{abc,
	author = {Minesh Patel and Jeremie Kim and Onur Mutlu},
	booktitle = {Proceedings of the 44th Annual International Symposium on Computer Architecture, ISCA 2017, Toronto, ON, Canada},
	title = {The Reach Profiler (REAPER): Enabling the Mitigation of DRAM Retention Failures via Profiling at Aggressive Conditions.},
	url = {http://doi.acm.org/10.1145/3079856.3080242},
	year = {2017}
}

@inproceedings{abc,
	abstract = {Many distributed systems require coordination between the components involved. With the steady growth of such systems, the probability of failures increases, which necessitates scalable fault-tolerant agreement protocols. The most common practical agreement protocol, for such scenarios, is leader-based atomic broadcast. In this work, we propose AllConcur, a distributed system that provides agreement through a leaderless concurrent atomic broadcast algorithm, thus, not suffering from the bottleneck of a central coordinator. In AllConcur, all components exchange messages concurrently through a logical overlay network that employs early termination to minimize the agreement latency. Our implementation of AllConcur supports standard sockets-based TCP as well as high-performance InfiniBand Verbs communications. AllConcur can handle up to 135 million requests per second and achieves 17x higher throughput than today{\textquoteright}s standard leader-based protocols, such as Libpaxos. Thus, AllConcur is highly competitive with regard to existing solutions and, due to its decentralized approach, enables hitherto unattainable system designs in a variety of fields.},
	author = {Marius Poke and Torsten Hoefler and Colin W. Glass},
	booktitle = {Proceedings of the 26th International Symposium on High-Performance Parallel and Distributed Computing},
	title = {AllConcur: Leaderless Concurrent Atomic Broadcast},
	venue = {Washington, DC, USA},
	year = {2017}
}

@mastersthesis{abc,
	abstract = {The polyhedral model makes a large set of transformations readily available for loop nest optimizations. Like traditional program optimization it is not always clear which of those transformations are profitable and under what circumstances. In traditional compilers this is dealt with the use of hand-crafted heuristics that are often platform specific and not universality {\textquotedblleft}good{\textquotedblright}. In polyhedral compilation the problem of finding the appropriate transformations is formulated as an Integer Linear Program (ILP). However, not all relevant software and hardware aspects are or can be modelled in such an ILP. Consequently, transformations obtained by solving such ILPs are not necessarily optimal.
In this work, we propose the use of data-driven heuristics in polyhedral optimization. To this end, we present a hybrid approach that uses an ILP solver in cooperation with a trained machine learning model that functions as a loop fusion heuristic. The ILP scheduler optimizes individual loops, our heuristic decides which ones should be fused, and then the ILP solver further optimizes the combined loops.
The heuristic discovers by itself how loop fusion interacts with the ILP scheduler, the rest of the compiler, and the hardware without needing a compiler or hardware {\textquotedblleft}expert{\textquotedblright} to teach it.},
	author = {Theodoros Theodoridis },
	school = {169},
	title = {Fused {\textquotedblleft}Learning{\textquotedblright} and {\textquotedblleft}Linear Programming{\textquotedblright}: a Novel Loop Fusion Approach},
	year = {2017}
}

@inproceedings{abc,
	author = {Kevin K. Chang and Abdullah Giray Yaglik{\c c}i and Saugata Ghose and Aditya Agrawal and Niladrish Chatterjee and Abhijith Kashyap and Donghyuk Lee and Mike O{\textquoteright}Connor and Hasan Hassan and Onur Mutlu},
	booktitle = {Proceedings of the 2017 ACM SIGMETRICS / International Conference on Measurement and Modeling of Computer Systems, Urbana-Champaign, IL, USA},
	title = {Understanding Reduced-Voltage Operation in Modern DRAM Devices: Experimental Characterization, Analysis, and Mechanisms.},
	url = {http://doi.acm.org/10.1145/3078505.3078590},
	year = {2017}
}

@inproceedings{abc,
	abstract = {We reduce the cost of communication and synchronization in graph processing by analyzing the fastest way to process graphs: pushing the updates to a shared state or pulling the updates to a private state. We investigate the applicability of this push-pull dichotomy to various algorithms and its impact on complexity, performance, and the amount of used locks, atomics, and reads/writes. We consider 11 graph algorithms, 3 programming models, 2 graph abstractions, and various families of graphs. The conducted analysis illustrates surprising differences between push and pull variants of different algorithms in performance, speed of convergence, and code complexity; the insights are backed up by performance data from hardware counters. We use these findings to illustrate which variant is faster for each algorithm and to develop generic strategies that enable even higher speedups. Our insights can be used to accelerate graph processing engines or libraries on both massively-parallel shared-memory machines as well as distributed-memory systems.},
	author = {Maciej Besta and Michal Podstawski and Linus Groner and Edgar Solomonik and Torsten Hoefler},
	booktitle = {Proceedings of the 26th International Symposium on High-Performance Parallel and Distributed Computing},
	title = {To Push or To Pull: On Reducing Communication and Synchronization in Graph Computations},
	venue = {Washington, DC, USA},
	year = {2017}
}

@inproceedings{abc,
	author = {Donghyuk Lee and Samira Manabi Khan and Lavanya Subramanian and Saugata Ghose and Rachata Ausavarungnirun and Gennady Pekhimenko and Vivek Seshadri and Onur Mutlu},
	booktitle = {Proceedings of the 2017 ACM SIGMETRICS / International Conference on Measurement and Modeling of Computer Systems, Urbana-Champaign, IL, USA},
	title = {Design-Induced Latency Variation in Modern DRAM Chips: Characterization, Analysis, and Latency Reduction Mechanisms.},
	url = {http://doi.acm.org/10.1145/3078505.3078533},
	year = {2017}
}

@inproceedings{abc,
	abstract = {Designing a partial differential equations solver is a complex task which involves making choices about the solution algorithm and its parameters. Such choices are usually done on the basis of personal preference or numerical experiments, which can introduce significant bias on the selection process. In this work we develop a methodology to drive this selection process towards the optimal choices by modelling the accuracy and the performance of the solution algorithm. We show how this methodology can be successfully applied on the linear advection problem. As a result, the selection can be optimally performed with a much lower investment on the development of high-performance versions of the solvers and without using the target architecture for numerical experiments.},
	author = {Andrea Arteaga and Oliver Fuhrer and Torsten Hoefler and Thomas Schulthess},
	booktitle = {Proceedings of the International Conference on Computational Science (ICCS{\textquoteright}17)},
	title = {Model-Driven Choice of Numerical  Methods for the Solution of the Linear Advection Equation},
	venue = {Zurich, Switzerland},
	year = {2017}
}

@inproceedings{abc,
	abstract = {Many large-scale scientific computations require eigenvalue solvers in a scaling regime where efficiency is limited by data movement. We introduce a parallel algorithm for computing the eigenvalues of a dense symmetric matrix, which performs asymptotically less communication than previously known approaches. We provide analysis in the Bulk Synchronous Parallel (BSP) model with additional consideration for communication between a local memory and cache. Given sufficient memory to store c copies of the symmetric matrix, our algorithm requires \Theta(\sqrt{c}) less interprocessor communication than previously known algorithms, for any c\leq p^{1/3} when using p processors. The algorithm first reduces the dense symmetric matrix to a banded matrix with the same eigenvalues. Subsequently, the algorithm employs successive reduction to O(\log p) thinner banded matrices. We employ two new parallel algorithms that achieve lower communication costs for the full-to-band and band-to-band reductions. Both of these algorithms leverage a novel QR factorization algorithm for rectangular matrices.},
	author = {Edgar Solomonik and Grey Ballard and James Demmel and Torsten Hoefler},
	booktitle = {Proceedings of the 29th ACM Symposium on Parallelism in Algorithms and Architectures},
	title = {A Communication-Avoiding Parallel Algorithm for the Symmetric Eigenvalue Problem},
	venue = {Washington, DC, USA},
	year = {2017}
}

@inproceedings{abc,
	abstract = {Vectorization and GPUs will profoundly change graph processing. Traditional graph algorithms tuned for 32- or 64-bit based memory accesses will be inefficient on architectures with 512-bit wide (or larger) instruction units that are already present in the Intel Knights Landing (KNL) manycore CPU. Anticipating this shift, we propose SlimSell: a vectorizable graph representation to accelerate Breadth-First Search (BFS) based on sparse-matrix dense-vector (SpMV) products. SlimSell extends and combines the state-of-the-art SIMD-friendly Sell-C-σ matrix storage format with tropical, real, boolean, and sel-max semiring operations. The resulting design reduces the necessary storage (by up to 50\%) and thus pressure on the memory subsystem. We augment SlimSell with the SlimWork and SlimChunk schemes that reduce the amount of work and improve load balance, further accelerating BFS. We evaluate all the schemes on Intel Haswell multicore CPUs, the state-of-the-art Intel Xeon Phi KNL manycore CPUs, and NVIDIA Tesla GPUs. Our experiments indicate which semiring offers highest speedups for BFS and illustrate that SlimSell accelerates a tuned Graph500 BFS code by up to 33\%. This work shows that vectorization can secure high-performance in BFS based on SpMV products; the proposed principles and designs can be extended to other graph algorithms.},
	author = {Maciej Besta and Florian Marending and Edgar Solomonik and },
	booktitle = {Proceedings of the 31st IEEE International Parallel \& Distributed Processing Symposium (IPDPS{\textquoteright}17)},
	title = {SlimSell: A Vectorized Graph Representation for Breadth-First Search},
	venue = {Orlando, FL, USA},
	year = {2017}
}

@inproceedings{abc,
	abstract = {The constantly increasing gap between communication and computation performance emphasizes the importance of communication-avoidance techniques. Caching is a well-known concept used to reduce accesses to slow local memories. In this work, we extend the caching idea to MPI-3 Remote Memory Access (RMA) operations. Here, caching can avoid inter-node communications and achieve similar benefits for irregular applications as communication-avoiding algorithms for structured applications. We propose CLaMPI, a caching library layered on top of MPI-3 RMA, to automatically optimize code with minimum user intervention. We demonstrate how cached RMA improves the performance of a Barnes Hut simulation and a Local Clustering Coefficient computation up to a factor of 1.8x and 5x, respectively. Due to the low overheads in the cache miss case and the potential benefits, we expect that our ideas around transparent RMA caching will soon be an integral part of many MPI libraries.},
	author = {Salvatore Di Girolamo and Flavio Vella and Torsten Hoefler},
	booktitle = {Proceedings of the 31st IEEE International Parallel \& Distributed Processing Symposium (IPDPS{\textquoteright}17)},
	title = {Transparent Caching for RMA Systems},
	venue = {Orlando, FL, USA},
	year = {2017}
}

@inproceedings{abc,
	author = {Darko Makreshanski and Jana Giceva and Claude Barthels and Gustavo Alonso},
	booktitle = {Proceedings of the 2017 ACM International Conference on Management of Data, SIGMOD Conference 2017, Chicago, IL, USA},
	title = {BatchDB: Efficient Isolated Execution of Hybrid OLTP+OLAP Workloads for Interactive Applications.},
	url = {http://doi.acm.org/10.1145/3035918.3035959},
	year = {2017}
}

@inproceedings{abc,
	abstract = {Implementing parallel operators in multi-core machines often involves a data partitioning step that divides the data into cache-size blocks and arranges them so to allow concurrent threads to process them in parallel. Data partitioning is expensive, in some cases up to 90\% of the cost of, e.g., a parallel hash join. In this paper we explore the use of an FPGA to accelerate data partitioning. We do so in the context of new hybrid architectures where the FPGA is located as a co-processor residing on a socket and with coherent access to the same memory as the CPU residing on the other socket. Such an architecture reduces data transfer overheads between the CPU and the FPGA, enabling hybrid operator execution where the partitioning happens on the FPGA and the build and probe phases of a join happen on the CPU. Our experiments demonstrate that FPGA-based partitioning is significantly faster and more robust than CPU-based partitioning. The results open interesting options as FPGAs are gradually integrated tighter with the CPU.},
	author = {Kaan Kara and Jana Giceva and Gustavo Alonso},
	booktitle = {Proceedings of the 2017 ACM International Conference on Management of Data, SIGMOD Conference 2017},
	title = {FPGA-based Data Partitioning.},
	url = {http://doi.acm.org/10.1145/3035918.3035946},
	venue = {Chicago, IL, USA},
	year = {2017}
}

@inproceedings{abc,
	abstract = {Large-scale parallel programming environments and algorithms require efficient group-communication on computing systems with failing nodes. Existing reliable broadcast algorithms either cannot guarantee that all nodes are reached or are very expensive in terms of the number of messages and latency. This paper proposes Corrected-Gossip, a method that combines Monte Carlo style gossiping with a deterministic correction phase, to construct a Las Vegas style reliable broadcast that guarantees reaching all the nodes at low cost. We analyze the performance of this method both analytically and by simulations and show how it reduces the latency and network load compared to existing algorithms. Our method improves the latency by 20\% and the network load by 53\% compared to the fastest known algorithm on 4,096 nodes. We believe that the principle of corrected-gossip opens an avenue for many other reliable group communication operations.},
	author = {Torsten Hoefler and Amnon Barak and Amnon Shiloh and },
	booktitle = {Proceedings of the 31st IEEE International Parallel \& Distributed Processing Symposium (IPDPS{\textquoteright}17)},
	title = {Corrected Gossip Algorithms for Fast Reliable Broadcast on Unreliable Systems},
	venue = {Orlando, FL, USA},
	year = {2017}
}

@inproceedings{abc,
	author = {David Sidler and Zsolt Istv{\'a}n and Muhsen Owaida and Kaan Kara and Gustavo Alonso},
	booktitle = {Proceedings of the 2017 ACM International Conference on Management of Data, SIGMOD Conference 2017, Chicago, IL, USA},
	title = {doppioDB: A Hardware Accelerated Database.},
	url = {http://doi.acm.org/10.1145/3035918.3058746},
	year = {2017}
}

@inproceedings{abc,
	abstract = {We present a new parallel algorithm for solving triangular systems with multiple right hand sides (TRSM). TRSM is used extensively in numerical linear algebra computations, both to solve triangular linear systems of equations as well as to compute factorizations with triangular matrices, such as Cholesky, LU, and QR. Our algorithm achieves better theoretical scalability than known alternatives, while maintaining numerical stability, via selective use of triangular matrix inversion. We leverage the fact that triangular inversion and matrix multiplication are more parallelizable than the standard TRSM algorithm. By only inverting triangular blocks along the diagonal of the initial matrix, we generalize the usual way of TRSM computation and the full matrix inversion approach. This flexibility leads to an efficient algorithm for any ratio of the number of right hand sides to the triangular matrix dimension. We provide a detailed communication cost analysis for our algorithm as well as for the recursive triangular matrix inversion. This cost analysis makes it possible to determine optimal block sizes and processor grids a priori. Relative to the best known algorithms for TRSM, our approach can require asymptotically fewer messages, while performing optimal amounts of computation and communication in terms of words sent.},
	author = {Tobias Wicky and Edgar Solomonik and Torsten Hoefler},
	booktitle = {Proceedings of the 31st IEEE International Parallel \& Distributed Processing Symposium (IPDPS{\textquoteright}17)},
	title = {Communication-Avoiding Parallel Algorithms for Solving Triangular Systems of Linear Equations},
	venue = {Orlando, FL, USA},
	year = {2017}
}

@inproceedings{abc,
	abstract = {Increasingly complex memory systems and onchip interconnects are developed to mitigate the data movement bottlenecks in manycore processors. One example of such a complex system is the Xeon Phi KNL CPU with three different types of memory, fifteen memory configuration options, and a complex on-chip mesh network connecting up to 72 cores. Users require a detailed understanding of the performance characteristics of the different options to utilize the system efficiently. Unfortunately, peak performance is rarely achievable and achievable performance is hardly documented. We address this with capability models of the memory subsystem, derived by systematic measurements, to guide users to navigate the complex optimization space. As a case study, we provide an extensive model of all memory configuration options for Xeon Phi KNL. We demonstrate how our capability model can be used to automatically derive new close-to-optimal algorithms for various communication functions yielding improvements 5x and 24x over Intel{\textquoteright}s tuned OpenMP and MPI implementations, respectively. Furthermore, we demonstrate how to use the models to assess how efficiently a bitonic sort application utilizes the memory resources. Interestingly, our capability models predict and explain that the high bandwidthMCDRAM does not improve the bitonic sort performance over DRAM.},
	author = {Sabela Ramos and Torsten Hoefler},
	booktitle = {Proceedings of the 31st IEEE International Parallel \& Distributed Processing Symposium (IPDPS{\textquoteright}17)},
	title = {Capability Models for Manycore Memory Systems: A Case-Study with Xeon Phi KNL},
	venue = {Orlando, FL, USA},
	year = {2017}
}

@mastersthesis{abc,
	abstract = {Filed-programmable gate arrays (FPGA) are gaining interest in the high performance computing community due to their potential for high performance at low power. Programming FPGAs has traditionally been done by hardware engineers in languages working on the register transfer level. High-level synthesis opens FPGAs up to a wider audience, by facilitating the transformation of imperative code into hardware circuits. This thesis builds kernels from a C++ source code, exploiting higher level language features such as objects and templates to increase expresiveness and productivity.
By modeling performance in terms of FPGA resources, a scalable matrixmatrix multiplication kernel is constructed. Performance and resource utilization are verified experimentally on an AlphaData 7V3 board, hosting a Xilinx Virtex-7 FPGA. For single precision floating point data,
performance up to 95 GFLOP/s was measured.
A single source-file solution is constructed, solving not only matrixmatrix multiplication, but also the all-pairs shortest path problem by substituting operations and data types. The blocked, hybrid CPUFPGA approach was used to gain further insights in resource utilization for integer data. These results demonstrate that HLS can indeed enable FPGA programming for high performance with little to no prior experience in hardware design.},
	author = {Roman Cattaneo},
	school = {168},
	title = {High-level synthesis of dense matrix operations on FPGA},
	year = {2017}
}

@inproceedings{abc,
	abstract = {We investigate the multi-agent pathfinding (MAPF) problem with n agents on graphs with n vertices: Each agent has a unique start and goal vertex, with the objective of moving all agents in parallel movements to their goal s.t. each vertex and each edge may only be used by one agent at a time. We give a combinatorial classification of all graphs where this problem is solvable in general, including cases where the solvability depends on the initial agent placement.
Furthermore, we present an algorithm solving the MAPF problem in our setting, requiring O(n2)O(n2) rounds, or O(n3)O(n3) moves of individual agents. Complementing these results, we show that there are graphs where {\textohm}(n2){\textohm}(n2) rounds and {\textohm}(n3){\textohm}(n3) moves are required for any algorithm.},
	author = {Klaus-Tycho Foerster and Linus Groner and Torsten Hoefler and Michael Koenig and Sascha Schmid and Roger Wattenhofer},
	booktitle = {Proceedings of the Algorithms and Complexity - 10th International Conference, CIAC 2017},
	title = {Multi-agent Pathfinding with n Agents on Graphs with n Vertices: Combinatorial Classification and Tight Algorithmic Bounds},
	venue = {Athens, Greece},
	year = {2017}
}

@inproceedings{abc,
	abstract = {It is time to reconsider memory protection. The emergence of large non-volatile main memories, scalable interconnects, and rack-scale computers running large numbers of small "micro services" creates significant challenges for memory protection based solely on MMU mechanisms. Central to this is a tension between protection and translation: optimizing for translation performance often comes with a cost in protection flexibility.

We argue that a key-based memory protection scheme, complementary to but separate from regular page-level translation, is a better match for this new world. We present MaKC, a new architecture which combines two levels of capability-based protection to scale fine-grained memory protection at both user and kernel level to large numbers of protection domains without compromising efficiency at scale or ease of revocation.},
	author = {Reto Achermann and Chris Dalton and Paolo Faraboschi and Moritz Hoffmann and Dejan S. Milojicic and Geoffrey Ndu and Alexander Richardson and Timothy Roscoe and Adrian L. Shaw and Robert N. M. Watson},
	booktitle = {Proceedings of the 16th Workshop on Hot Topics in Operating Systems},
	title = {Separating Translation from Protection in Address Spaces with Dynamic Remapping},
	venue = {Whistler, BC, Canada},
	year = {2017}
}

@inproceedings{abc,
	author = {Ce Zhang and Wentao Wu and Tian Li},
	booktitle = {Proceedings of the 2nd Workshop on Human-In-the-Loop Data Analytics, HILDA@SIGMOD 2017, Chicago, IL, USA},
	title = {An Overreaction to the Broken Machine Learning Abstraction: The ease.ml Vision.},
	url = {http://doi.acm.org/10.1145/3077257.3077265},
	year = {2017}
}

@inproceedings{abc,
	author = {Jiawei Jiang and Bin Cui and Ce Zhang and Lele Yu},
	booktitle = {Proceedings of the 2017 ACM International Conference on Management of Data, SIGMOD Conference 2017, Chicago, IL, USA},
	title = {Heterogeneity-aware Distributed Parameter Servers.},
	url = {http://doi.acm.org/10.1145/3035918.3035933},
	year = {2017}
}

@inproceedings{abc,
	abstract = {Taking advantage of recently released hybrid multicore architectures, such as the Intel Xeon+FPGA machine, where the FPGA has coherent access to the main memory through the QPI bus, we explore the benefits of specializing operators to hardware. We focus on two commonly used SQL operators for strings: LIKE, and REGEXP_LIKE, and provide a novel and efficient implementation of these operators in reconfigurable hardware. We integrate the hardware accelerator into MonetDB, a main-memory column store, and demonstrate a significant improvement in response time and throughput. Our Hardware User Defined Function (HUDF) can speed up complex pattern matching by an order of magnitude in comparison to the database running on a 10-core CPU. The insights gained from integrating hardware based string operators into MonetDB should also be useful for future designs combining hardware specialization and databases.},
	author = {David Sidler and Zsolt Istv{\'a}n and Muhsen Owaida and Gustavo Alonso},
	booktitle = {Proceedings of the 2017 ACM International Conference on Management of Data, SIGMOD Conference 2017},
	title = {Accelerating Pattern Matching Queries in Hybrid CPU-FPGA Architectures.},
	url = {http://doi.acm.org/10.1145/3035918.3035954},
	venue = {Chicago, IL, USA},
	year = {2017}
}

@inproceedings{abc,
	author = {Muhsen Owaida and David Sidler and Kaan Kara and Gustavo Alonso},
	booktitle = {25th IEEE Annual International Symposium on Field-Programmable Custom Computing Machines, FCCM 2017, Napa, CA, USA},
	title = {Centaur: A Framework for Hybrid CPU-FPGA Databases.},
	url = {https://doi.org/10.1109/FCCM.2017.37},
	year = {2017}
}

@mastersthesis{abc,
	abstract = {In today{\textquoteright}s world, computer networks have grown immensely in terms of size and com-
plexity. In an attempt to manage the dynamics and scale of these networks, software-
defined networking was introduced, an approach that aims to supervise the behavior
of the network through open interfaces. In order to deal with the challenges that arise
in controlling software-defined networks, complicated analysis of the characteristics and
structures of these networks has to be done. In particular, the network controller has to
be capable of matching user-defined patterns, finding the shortest paths across the net-
work and extracting subgraphs that conform to specific requirements. In this thesis, we
present an Interface of the Property Graph Query Language for Differential Dataflow,
capable of fulfilling these needs. The Property Graph Query Language enables us to
express the three aforementioned tasks in a formal way, whereas Differential Dataflow
provides the proper tools to conduct the analysis.},
	author = {Lukas Striebel},
	school = {164},
	title = {A High-level Graph Query Language Interface for Differential Dataflow},
	year = {2017}
}

@inproceedings{abc,
	abstract = {Stochastic gradient descent (SGD) is a commonly used algorithm for training linear machine learning models. Based on vector algebra, it benefits from the inherent parallelism available in an FPGA. In this paper, we first present a single-precision floating-point SGD implementation on an FPGA that provides similar performance as a 10-core CPU. We then adapt the design to make it capable of processing low-precision data. The low-precision data is obtained from a novel compression scheme-called stochastic quantization, specifically designed for machine learning applications. We test both full-precision and low-precision designs on various regression and classification data sets. We achieve up to an order of magnitude training speedup when using low-precision data compared to a full-precision SGD on the same FPGA and a state-of-the-art multi-core solution, while maintaining the quality of training. We open source the designs presented in this paper.},
	author = {Kaan Kara and Dan Alistarh and Gustavo Alonso and Onur Mutlu and Ce Zhang},
	booktitle = {25th IEEE Annual International Symposium on Field-Programmable Custom Computing Machines, FCCM 2017, Napa, CA, USA},
	title = {FPGA-Accelerated Dense Linear Machine Learning: A Precision-Convergence Trade-Off.},
	url = {https://doi.org/10.1109/FCCM.2017.39},
	venue = {Napa, CA, USA},
	year = {2017}
}

@article{abc,
	author = {Reto Achermann and Lukas Humbel and David Cock and Timothy Roscoe},
	journal = {Proceedings 2nd Workshop on Models for Formal Analysis of Real Systems, MARS@ETAPS 2017, Uppsala, Sweden},
	title = {Formalizing Memory Accesses and Interrupts.},
	url = {http://dx.doi.org/10.4204/EPTCS.244.4},
	year = {2017}
}

@mastersthesis{abc,
	abstract = {Nowadays, major cloud providers provide machine learning services (a.k.a machine
learning clouds) to customers. Microsoft Azure Machine Learning Studio
and Amazon Machine Learning are two of the most popular machine learning
clouds, which raise the level of abstraction for specifying machine learning models
and tasks to ease the deployment of real-world machine learning applications.
However, real-world machine learning applications are not simple in general, and
raising the level of abstraction for machine learning systems rarely comes for
free. Thus, an important question comes out. What is the performance of machine
learning clouds on real-world machine learning problems? In order to answer this
question, we first construct a benchmark data set MLbench with the top winning
solutions of different competitions on Kaggle. And then present the results
obtained by running MLbench on top of these two machine learning clouds evaluated
by Kaggle. Our studying reveals the strength and limitations of these machine
learning clouds, and also point out possible improvement directions.},
	author = {Luyuan Zeng},
	school = {162},
	title = {Evaluate Machine Learning Clouds with Kaggle},
	year = {2017}
}

@mastersthesis{abc,
	abstract = {Training deep learning models has received tremendous research interest recently. In
particular, there has been intensive research on reducing the communication cost of
the training process when using multiple computational devices, through reducing
the precision of the underlying data representation. Naturally, such methods induce
system trade-offs{\textemdash}lowering communication precision could decrease communication
overheads and improve scalability; but, on the other hand, it can also reduce the
accuracy of training. In this paper, we study this trade-off space, and ask: Can lowprecision
communication consistently improve the end-to-end performance of training modern
neural networks, with no accuracy loss?
From the performance point of view, the answer to this question may appear deceptively
easy: compressing communication through low precision should help when the
ratio between communication and computation is high. However, this answer is less
straightforward when we try to generalize this principle across various neural network
architectures (e.g., AlexNet vs. ResNet), number of GPUs (e.g., 2 GPUs vs. 8 GPUs),
machine configurations (e.g., EC2 instances vs. NVIDIA DGX-1), programming models
(e.g., MPI vs. NCCL), and even different GPU architectures (e.g., Kepler vs. Pascal).
Currently, it is not clear how a realistic realization of all these factors maps to the speed
up provided by low-precision communication. In this paper, we conduct an empirical
study to answer this question and report the insights we obtain.},
	author = {Demjan Grubic},
	school = {163},
	title = {Communication-Scalable Machine Learning},
	year = {2017}
}

@inproceedings{abc,
	author = {Zaheer Chothia and John Liagouris and Desislava Dimitrova and Timothy Roscoe},
	booktitle = {Proceedings of the Twelfth European Conference on Computer Systems, EuroSys 2017, Belgrade, Serbia},
	title = {Online Reconstruction of Structural Information from Datacenter Logs.},
	url = {http://doi.acm.org/10.1145/3064176.3064195},
	year = {2017}
}

@mastersthesis{abc,
	abstract = {Tapping the potential of emerging massively parallel architectures requires
a thorough, systematic understanding of application performance.
Graph processing, which lies at the heart of applications such
as social network analysis, combinatorial algorithms, and machine
learning, is especially challenging to model and reason about due to
the rich structure of graphs. There is a need for algorithms, software
abstractions, and models of computation that would enable robust, predictable
performance on today{\textquoteright}s petascale and future exascale systems.
To address these needs, we use a precise yet practical set of models to
survey the existing approaches and their limitations. Based on our insights,
we propose that performance in graph processing can be largely
captured by analyzing the graph representation, and suggest how to
do so. We show how this paradigm is useful in designing and analyzing
new algorithms, using triangle counting as a case study. Moreover,
we present a case study of representations and design choices
for iterative algorithms, demonstrating how our approach enables wellgrounded,
scientific decisions. Finally, we design parameter-oblivious,
communication-avoiding algorithms for global minimum cuts and connected
components that builds on our insights. Experimental evidence
confirms that the proposed techniques are practical: Our implementations
scale up to thousands of cores and outperform comparable existing
codes by up to three orders of magnitude. The representationcentric
approach thus offers a useful and broadly applicable paradigm
that both algorithm designers and developers can build on.},
	author = {Pavel Kalvoda},
	school = {167},
	title = {Representation-Centric Graph Processing},
	year = {2017}
}

@inproceedings{abc,
	author = {Jie Jiang and Jiawei Jiang and Bin Cui and Ce Zhang},
	booktitle = {33rd IEEE International Conference on Data Engineering, ICDE 2017, San Diego, CA, USA},
	title = {TencentBoost: A Gradient Boosting Tree System with Parameter Server.},
	url = {https://doi.org/10.1109/ICDE.2017.87},
	year = {2017}
}

@mastersthesis{abc,
	abstract = {We rst present an application where we helped our astrophysicist collaborators
to recover features from articially degraded images with worse
seeing and higher noise than the original with a performance which far exceeds
simple deconvolution by training a generative adversarial network
(GAN) on galaxy images. However, training time is limiting our potential
to train on larger data sets. It takes 2 hours to train a GAN using
4105 galaxy images for 20 iterations on an NVIDIA TITAN X GPU. We
ask the question: Can we speed up our machine learning training process
by reducing the precision of data representation?...},
	author = {Hantian  Zhang },
	school = {160},
	title = {The ZipML Framework for Training Models with End-to-End Low Precision},
	year = {2017}
}

@inproceedings{abc,
	abstract = {Digital forensic investigators often need to extract data from a seized device that contains NAND flash memory. Many such devices are physically damaged, preventing investigators from using automated techniques to extract the data stored within the device. Instead, investigators turn to chip-off analysis, where they use a thermal-based procedure to physically remove the NAND flash memory chip from the device, and access the chip directly to extract the raw data stored on the chip.

We perform an analysis of the errors introduced into multi-level cell (MLC) NAND flash memory chips after the device has been seized. We make two major observations. First, between the time that a device is seized and the time digital forensic investigators perform data extraction, a large number of errors can be introduced as a result of charge leakage from the cells of the NAND flash memory (known as data retention errors). Second, when thermal-based chip removal is performed, the number of errors in the data stored within NAND flash memory can increase by two or more orders of magnitude, as the high temperature applied to the chip greatly accelerates charge leakage. We demonstrate that the chip-off analysis based forensic data recovery procedure is quite destructive, and can often render most of the data within NAND flash memory uncorrectable, and, thus, unrecoverable.

To mitigate the errors introduced during the forensic recovery process, we explore a new hardware- based approach. We exploit a fine-grained read reference voltage control mechanism implemented in modern NAND flash memory chips, called read-retry, which can compensate for the charge leakage that occurs due to (1) retention loss and (2) thermal-based chip removal. The read-retry mechanism successfully reduces the number of errors, such that the original data can be fully recovered in our tested chips as long as the chips were not heavily used prior to seizure. We conclude that the read-retry mechanism should be adopted as part of the forensic data recovery process. },
	author = {Aya Fukami and Saugata Ghose and Yixin Luo and Yu Cai and Onur Mutlu},
	booktitle = {Proceedings of the 2017 Digital Forensics Conference},
	title = {Improving the Reliability of Chip-Off Forensic Analysis of NAND Flash Memory Devices},
	venue = {{\"U}berlingen, Germany},
	year = {2017}
}

@inproceedings{abc,
	author = {Ilker Nadi Bozkurt and Anthony Aguirre and Balakrishnan Chandrasekaran and Brighten Godfrey and Gregory Laughlin and Bruce M. Maggs and Ankit Singla},
	booktitle = {Passive and Active Measurement - 18th International Conference, PAM 2017, Sydney, NSW, Australia},
	title = {Why Is the Internet so Slow?!},
	url = {http://dx.doi.org/10.1007/978-3-319-54328-4_13},
	year = {2017}
}

@mastersthesis{abc,
	abstract = {Current mainstream processors provide multiple SMT (i.e., simultaneous multithreading) lanes on top of each physical core. These hardware threads share more resources (e.g., execution units and caches) when compared to CPU cores, but are managed by operating systems in the same way as if they were separate physical cores. This Thesis explores the interaction between hardware threads and proposes an extension to the Barrelsh OS, meant to improve the performance of a system by adequately handling SMT lanes. On an Intel Haswell CPU, with 2-way SMT via Hyper-Threading Technology, each SMT lane had 2=3 of the processing power that was yielded by the physical core with a single active hardware thread. The multi-HT CPU Driver (i.e., Barrelsh{\textquoteright}s microker-nel) is able to modify the set of active hardware threads with an overhead in the order of thousands of processor cycles, which means that it can quickly adapt to the parallelism exhibited by the workload.},
	author = {Andrei Poenaru},
	school = {161},
	title = {Explicit OS support for hardware threads},
	year = {2017}
}

@inproceedings{abc,
	author = {Kevin Hsieh and Aaron Harlap and Nandita Vijaykumar and Dimitris Konomis and Gregory R. Ganger and Phillip B. Gibbons and Onur Mutlu},
	booktitle = {14th USENIX Symposium on Networked Systems Design and Implementation, NSDI 2017, Boston, MA, USA},
	title = {Gaia: Geo-Distributed Machine Learning Approaching LAN Speeds.},
	url = {https://www.usenix.org/conference/nsdi17/technical-sessions/presentation/hsieh},
	year = {2017}
}

@inproceedings{abc,
	author = {Onur Mutlu},
	booktitle = {Design, Automation  Test in Europe Conference  Exhibition, DATE 2017, Lausanne, Switzerland},
	title = {The RowHammer problem and other issues we may face as memory becomes denser.},
	url = {https://doi.org/10.23919/DATE.2017.7927156},
	year = {2017}
}

@mastersthesis{abc,
	abstract = {Recent work has indicated that any static data center network is fundamentally
limited, due to its inability to move around network capacity.
Is this truly the case, is the static network not flexible enough to handle
varying (skewed) traffic scenarios through only traffic engineering?
Can we only find refuge in dynamic topologies, introducing on-the-fly
re-arrangement of network links at a cost? In pursuit of these research
goals, three main data center topologies were evaluated: traditional
(oversubscribed) fat-trees, expanders and dynamic topologies. Using
flow optimality evaluation via a linear program, worst case traffic scenarios
were identified and their respective performance measured under
perfect traffic engineering. A custom discrete packet simulator was
used to evaluate the two static topologies under a wide range of traffic
scenarios and compare results to performance claims of recent dynamic
topology research. It was found that the modeling of server up-links is
crucial to a meaningful comparison...},
	author = {Simon Kassing},
	school = {159},
	title = {Static Yet Flexible: Expander Data Center Network Fabrics Master Thesis},
	year = {2017}
}

@inproceedings{abc,
	author = {Hasan Hassan and Nandita Vijaykumar and Samira Manabi Khan and Saugata Ghose and Kevin K. Chang and Gennady Pekhimenko and Donghyuk Lee and Oguz Ergin and Onur Mutlu},
	booktitle = {2017 IEEE International Symposium on High Performance Computer Architecture, HPCA 2017, Austin, TX, USA},
	title = {SoftMC: A Flexible and Practical Open-Source Infrastructure for Enabling Experimental DRAM Studies.},
	url = {https://doi.org/10.1109/HPCA.2017.62},
	year = {2017}
}

@inproceedings{abc,
	author = {Yu Cai and Saugata Ghose and Yixin Luo and Ken Mai and Onur Mutlu and Erich F. Haratsch},
	booktitle = {2017 IEEE International Symposium on High Performance Computer Architecture, HPCA 2017, Austin, TX, USA},
	title = {Vulnerabilities in MLC NAND Flash Memory Programming: Experimental Analysis, Exploits, and Mitigation Techniques.},
	url = {https://doi.org/10.1109/HPCA.2017.61},
	year = {2017}
}

@inproceedings{abc,
	abstract = {Task-based programming offers an elegant way to express units of computation and the dependencies among them, making it easier to distribute the computational load evenly across multiple cores. However, this separation of problem decomposition and parallelism requires a sufficiently large input problem to achieve satisfactory efficiency on a given number of cores. Unfortunately, finding a good match between input size and core count usually requires significant experimentation, which is expensive and sometimes even impractical. In this paper, we propose an automated empirical method for finding the isoefficiency function of a task-based program, binding efficiency, core count, and the input size in one analytical expression. This allows the latter two to be adjusted according to given (realistic) efficiency objectives. Moreover, we not only find (i) the actual isoefficiency function but also (ii) the function one would yield if the program execution was free of resource contention and (iii) an upper bound that could only be reached if the program was able to maintain its average parallelism throughout its execution. The difference between the three helps to explain low efficiency, and in particular, it helps to differentiate between resource contention and structural conflicts related to task dependencies or scheduling. The insights gained can be used to co-design programs and shared system resources.},
	author = {Sergei Shudler and Alexandru Calotoiu and Torsten Hoefler and Felix Wolf},
	booktitle = {Proceedings of the 22nd ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming},
	title = {Isoefficiency in Practice: Configuring and Understanding the Performance of Task-based Applications},
	venue = {Austin, TX, USA},
	year = {2017}
}

@inproceedings{abc,
	author = {Besmira Nushi and Ece Kamar and Eric Horvitz and Donald Kossmann},
	booktitle = {Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence},
	title = {On Human Intellect and Machine Failures: Troubleshooting Integrative Machine Learning Systems.},
	url = {http://aaai.org/ocs/index.php/AAAI/AAAI17/paper/view/15032},
	venue = {San Francisco, California, USA.},
	year = {2017}
}

@inproceedings{abc,
	author = {Kevin K. Chang and Abdullah Giray Yaglik{\c c}i and Saugata Ghose and Aditya Agrawal and Niladrish Chatterjee and Abhijith Kashyap and Donghyuk Lee and Mike O{\textquoteright}Connor and Hasan Hassan and Onur Mutlu},
	booktitle = {CoRR},
	title = {Understanding Reduced-Voltage Operation in Modern DRAM Chips: Characterization, Analysis, and Mechanisms.},
	url = {http://arxiv.org/abs/1705.10292},
	year = {2017}
}

@article{abc,
	author = {Amirali Boroumand and Saugata Ghose and Minesh Patel and Hasan Hassan and Brandon Lucia and Nastaran Hajinazar and Kevin Hsieh and Krishna T. Malladi and Hongzhong Zheng and Onur Mutlu},
	journal = {CoRR},
	title = {LazyPIM: Efficient Support for Cache Coherence in Processing-in-Memory Architectures.},
	url = {http://arxiv.org/abs/1706.03162},
	year = {2017}
}

@inproceedings{abc,
	author = {Xiangru Lian and Ce Zhang and Huan Zhang and Cho-Jui Hsieh and Wei Zhang and Ji Liu},
	booktitle = {CoRR},
	title = {Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descent.},
	url = {http://arxiv.org/abs/1705.09056},
	year = {2017}
}

@inproceedings{abc,
	abstract = {The dark data extraction or knowledge base construction (KBC) problem is to populate a SQL database with information from unstructured data sources including emails, webpages, and pdf reports. KBC is a long-standing problem in industry and research that encompasses problems of data extraction, cleaning, and integration. We describe DeepDive, a system that combines database and machine learning ideas to help develop KBC systems. The key idea in DeepDive is that statistical inference and machine learning are key tools to attack classical data problems in extraction, cleaning, and integration in a unified and more effective manner. DeepDive programs are declarative in that one cannot write probabilistic inference algorithms; instead, one interacts by defining features or rules about the domain. A key reason for this design choice is to enable domain experts to build their own KBC systems. We present the applications, abstractions, and techniques of DeepDive employed to accelerate construction of KBC systems.},
	author = {Ce Zhang and Christopher R{\'e} and Michael J. Cafarella and Jaeho Shin and Feiran Wang and Sen Wu},
	booktitle = {Commun. ACM},
	title = {DeepDive: declarative knowledge base construction.},
	url = {http://doi.acm.org/10.1145/3060586},
	venue = {-},
	year = {2017}
}

@article{abc,
	author = {Vivek Seshadri and Onur Mutlu},
	journal = {Advances in Computers},
	title = {Chapter Four - Simple Operations in Memory to Reduce Data Movement.},
	url = {https://doi.org/10.1016/bs.adcom.2017.04.004},
	year = {2017}
}

@article{abc,
	author = {Onur Mutlu},
	journal = {CoRR},
	title = {The RowHammer Problem and Other Issues We May Face as Memory Becomes Denser.},
	url = {http://arxiv.org/abs/1703.00626},
	year = {2017}
}

@article{abc,
	author = {Kevin K. Chang and A. Giray Yaalik{\c c}i and Saugata Ghose and Aditya Agrawal and Niladrish Chatterjee and Abhijith Kashyap and Donghyuk Lee and Mike O{\textquoteright}Connor and Hasan Hassan and Onur Mutlu},
	journal = {POMACS},
	title = {Understanding Reduced-Voltage Operation in Modern DRAM Devices: Experimental Characterization, Analysis, and Mechanisms.},
	url = {http://doi.acm.org/10.1145/3084447},
	year = {2017}
}

@inproceedings{abc,
	author = {Badrish Chandramouli and Johannes Gehrke and Jonathan Goldstein and Donald Kossmann and Justin J. Levandoski and Renato Marroquin and Wenlei Xie},
	booktitle = {CIDR 2017, 8th Biennial Conference on Innovative Data Systems Research, Chaminade, CA, USA},
	title = {READY: Completeness is in the Eye of the Beholder.},
	url = {http://cidrdb.org/cidr2017/papers/p18-chandramouli-cidr17.pdf},
	year = {2017}
}

@article{abc,
	author = {Lucas Braun and Renato Marroquin and Kai-En Tsay and Donald Kossmann},
	journal = {CoRR},
	title = {MTBase: Optimizing Cross-Tenant Database Queries.},
	url = {http://arxiv.org/abs/1703.04290},
	year = {2017}
}

@article{abc,
	author = {Donghyuk Lee and Samira Manabi Khan and Lavanya Subramanian and Saugata Ghose and Rachata Ausavarungnirun and Gennady Pekhimenko and Vivek Seshadri and Onur Mutlu},
	journal = {POMACS},
	title = {Design-Induced Latency Variation in Modern DRAM Chips: Characterization, Analysis, and Latency Reduction Mechanisms.},
	url = {http://doi.acm.org/10.1145/3084464},
	year = {2017}
}

@inproceedings{abc,
	author = {Claude Barthels and Gustavo Alonso and Torsten Hoefler and Timo Schneider and Ingo M{\"u}ller},
	booktitle = {PVLDB},
	title = {Distributed Join Algorithms on Thousands of Cores.},
	url = {http://www.vldb.org/pvldb/vol10/p517-barthels.pdf},
	year = {2017}
}

@inproceedings{abc,
	author = {Zhipeng Zhang and Yingxia Shao and Bin Cui and Ce Zhang},
	booktitle = {PVLDB},
	title = {An Experimental Evaluation of SimRank-based Similarity Search Algorithms.},
	url = {http://www.vldb.org/pvldb/vol10/p601-zhang.pdf},
	year = {2017}
}

@article{abc,
	author = {Xiangyao Yu and Christopher J. Hughes and Nadathur Satish and Onur Mutlu and Srinivas Devadas},
	journal = {CoRR},
	title = {Banshee: Bandwidth-Efficient DRAM Caching Via Software/Hardware Cooperation.},
	url = {http://arxiv.org/abs/1704.02677},
	year = {2017}
}

@article{abc,
	abstract = {Populating a database with unstructured information is a long-standing problem in industry and research that encompasses problems of extraction, cleaning, and integration. Recent names used for this problem include dealing with dark data and knowledge base construction (KBC). In this work, we describe DeepDive, a system that combines database and machine learning ideas to help develop KBC systems, and we present techniques to make the KBC process more efficient. We observe that the KBC process is iterative, and we develop techniques to incrementally produce inference results for KBC systems. We propose two methods for incremental inference, based respectively on sampling and variational techniques. We also study the tradeoff space of these methods and develop a simple rule-based optimizer. DeepDive includes all of these contributions, and we evaluate DeepDive on five KBC systems, showing that it can speed up KBC inference tasks by up to two orders of magnitude with negligible impact on quality.},
	author = {Christopher De Sa and Alexander Ratner and Christopher R{\'e} and Jaeho Shin and Feiran Wang and Sen Wu and Ce Zhang},
	journal = {VLDB J.},
	title = {Incremental knowledge base construction using DeepDive.},
	url = {http://dx.doi.org/10.1007/s00778-016-0437-2},
	year = {2017}
}

@article{abc,
	abstract = {High-throughput, low-latency networks are becoming a key element in database appliances and data processing systems to reduce the overhead of data movement. In this article, we focus on Remote Direct Memory Access (RDMA), a feature increasingly available in modern networks enabling the network card to directly write to and read from main memory. RDMA has started to attract attention as a technical solution to quite a few performance bottlenecks in distributed data management but there is still much work to be done to make it an effective technology suitable for database engines. In this article, we identify several advantages and drawbacks of RDMA and related technologies, and propose new communication primitives that would bridge the gap between the operations provided by high-speed networks and the needs of data processing systems.},
	author = {Claude Barthels and Gustavo Alonso and Torsten Hoefler},
	journal = {IEEE Data Eng. Bull.},
	title = {Designing Databases for Future High-Performance Networks.},
	url = {http://sites.computer.org/debull/A17mar/p15.pdf},
	year = {2017}
}

@inproceedings{abc,
	author = {Amirali Boroumand and Saugata Ghose and Minesh Patel and Hasan Hassan and Brandon Lucia and Kevin Hsieh and Krishna T. Malladi and Hongzhong Zheng and Onur Mutlu},
	booktitle = {Computer Architecture Letters},
	title = {LazyPIM: An Efficient Cache Coherence Mechanism for Processing-in-Memory.},
	url = {https://doi.org/10.1109/LCA.2016.2577557},
	year = {2017}
}

@article{abc,
	author = {Kevin Schawinski and Ce Zhang and Hantian Zhang and Lucas Fowler and Gokula Krishnan Santhanam},
	journal = {CoRR},
	title = {Generative Adversarial Networks recover features in astrophysical images of galaxies beyond the deconvolution limit.},
	url = {http://arxiv.org/abs/1702.00403},
	year = {2017}
}

@inproceedings{abc,
	author = {Youyou Lu and Jiwu Shu and Long Sun and Onur Mutlu},
	booktitle = {CoRR},
	title = {Improving the Performance and Endurance of Persistent Memory with Loose-Ordering Consistency.},
	url = {http://arxiv.org/abs/1705.03623},
	year = {2017}
}

@article{abc,
	author = {Yu Cai and Saugata Ghose and Erich F. Haratsch and Yixin Luo and Onur Mutlu},
	journal = {CoRR},
	title = {Error Characterization, Mitigation, and Recovery in Flash Memory Based Solid-State Drives.},
	url = {http://arxiv.org/abs/1706.08642},
	year = {2017}
}

@inproceedings{abc,
	author = {Donald Kossmann},
	booktitle = {Datenbanksysteme f{\"u}r Business, Technologie und Web (BTW 2017), 17. Fachtagung des GI-Fachbereichs Datenbanken und Informationssysteme" (DBIS), 6.-10. M{\"a}rz 2017, Stuttgart, Germany, Proceedings},
	title = {Confidentiality {\`a} la Carte with Cipherbase.},
	year = {2017}
}

@inproceedings{abc,
	author = {Heng Guo and Kaan Kara and Ce Zhang},
	booktitle = {CoRR},
	title = {Layerwise Systematic Scan: Deep Boltzmann Machines and Beyond.},
	url = {http://arxiv.org/abs/1705.05154},
	year = {2017}
}

@article{abc,
	author = {Yixin Luo and Saugata Ghose and Tianshi Li and Sriram Govindan and Bikash Sharma and Bryan Kelly and Amirali Boroumand and Onur Mutlu},
	journal = {CoRR},
	title = {Using ECC DRAM to Adaptively Increase Memory Capacity.},
	url = {http://arxiv.org/abs/1706.08870},
	year = {2017}
}

@inproceedings{abc,
	author = {Heqing Huang and Cong Zheng and Junyuan Zeng and Wu Zhou and Sencun Zhu and Peng Liu and Suresh Chari and Ce Zhang},
	booktitle = {2016 IEEE International Conference on Big Data, BigData 2016, Washington DC, USA},
	title = {Android malware development on public malware scanning platforms: A large-scale data-driven study.},
	url = {http://dx.doi.org/10.1109/BigData.2016.7840712},
	year = {2016}
}

@inproceedings{abc,
	abstract = {Tuning large applications requires a clever exploration of the design and configuration space. Especially on supercomputers, this space is so large that its exhaustive traversal via performance experiments becomes too expensive, if not impossible. Manually creating analytical performance models provides insights into optimization opportunities but is extremely laborious if done for applications of realistic size. If we must consider multiple performance-relevant parameters and their possible interactions, a common requirement, this task becomes even more complex. We build on previous work on automatic scalability modeling and significantly extend it to allow insightful modeling of any combination of application execution parameters. Multi-parameter modeling has so far been outside the reach of automatic methods due to the exponential growth of the model search space. We develop a new technique to traverse the search space rapidly and generate insightful performance models that enable a wide range of uses from performance predictions for balanced machine design to performance tuning.},
	author = {Alexandru Calotoiu and David Beckinsale and Christopher W. Earl and Torsten Hoefler and Ian Karlin and Martin Schulz and Felix Wolf},
	booktitle = {Proceedings of the IEEE International Conference on Cluster Computing (CLUSTER) },
	title = {Fast Multi-Parameter Performance Modeling},
	venue = {Taipei, Taiwan},
	year = {2016}
}

@inproceedings{abc,
	abstract = {Lossless networks, such as InfiniBand use flow-control to avoid packet-loss due to congestion. This introduces dependencies between input and output channels, in case of cyclic dependencies the network can deadlock. Deadlocks can be resolved by splitting a physical channel into multiple virtual channels with independent buffers and credit systems. Currently available routing engines for InfiniBand assign entire paths from source to destination nodes to different virtual channels. However, InfiniBand allows changing the virtual channel at every switch. We developed fast routing engines which make use of that fact and map individual hops to virtual channels. Our algorithm imposes a total order on virtual channels and increments the virtual channel at every hop, thus the diameter of the network is an upper bound for the required number of virtual channels. We integrated this algorithm into the InfiniBand software stack. Our algorithms provide deadlock free routing on state-of-the-art low-diameter topologies, using fewer virtual channels than currently available practical approaches, while being faster by a factor of four on large networks. Since low-diameter topologies are common among the largest supercomputers in the world, to provide deadlock-free routing for such systems is very important.},
	author = {Timo Schneider and Otto Bibartiu and Torsten Hoefler},
	booktitle = {Proceedings of the IEEE 24th Annual Symposium on High-Performance Interconnects (HOTI)},
	title = {Ensuring Deadlock-Freedom in Low-Diameter InfiniBand Networks},
	venue = {Santa Clara, CA, USA},
	year = {2016}
}

@mastersthesis{abc,
	author = {Jingyi Wang},
	school = {156},
	title = {Performance Analysis of Decision Tree Learning Algorithms on Multicore CPUs},
	year = {2016}
}

@inproceedings{abc,
	abstract = {Over the last decade, CUDA and the underlying GPU hardware architecture have continuously gained popularity in various high-performance computing application domains such as climate modeling, computational chemistry, or machine learning. Despite this popularity, we lack a single coherent programming model for GPU clusters. We therefore introduce the dCUDA programming model, which implements device-side remote memory access with target notification. To hide instruction pipeline latencies, CUDA programs over-decompose the problem and over-subscribe the device by running many more threads than there are hardware execution units. Whenever a thread stalls, the hardware scheduler immediately proceeds with the execution of another thread ready for execution. This latency hiding technique is key to make best use of the available hardware resources. With dCUDA, we apply latency hiding at cluster scale to automatically overlap computation and communication. Our benchmarks demonstrate perfect overlap for memory bandwidth-bound tasks and good overlap for compute-bound tasks.},
	author = {Tobias Gysi and Jeremia B{\"a}r and Torsten Hoefler},
	booktitle = {Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis},
	title = {dCUDA: Hardware Supported Overlap of Computation and Communication},
	venue = {Salt Lake City, UT, USA},
	year = {2016}
}

@inproceedings{abc,
	author = {Khanh Nguyen and Lu Fang and Guoqing (Harry) Xu and Brian Demsky and Shan Lu and Sanazsadat Alamian and Onur Mutlu},
	booktitle = {12th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2016, Savannah, GA, USA},
	title = {Yak: A High-Performance Big-Data-Friendly Garbage Collector.},
	url = {https://www.usenix.org/conference/osdi16/technical-sessions/presentation/nguyen},
	year = {2016}
}

@inproceedings{abc,
	abstract = {Recent advances in networking hardware have led to a new generation of Remote Memory Access (RMA) networks in which processors from different machines can communicate directly, bypassing the operating system and allowing higher performance. Researchers and practitioners have proposed libraries and programming models for RMA to enable the development of applications running on these networks,

However, the memory models implied by these RMA libraries and languages are often loosely specified, poorly understood, and differ depending on the underlying network architecture and other factors. Hence, it is difficult to precisely reason about the semantics of RMA programs or how changes in the network architecture affect them.

We address this problem with the following contributions: (i) a coreRMA language which serves as a common foundation, formalizing the essential characteristics of RMA programming; (ii) complete axiomatic semantics for that language; (iii) integration of our semantics with an existing constraint solver, enabling us to exhaustively generate coreRMA programs (litmus tests) up to a specified bound and check whether the tests satisfy their specification; and (iv) extensive validation of our semantics on real-world RMA systems. We generated and ran 7441 litmus tests using each of the low-level RMA network APIs: DMAPP, VPI Verbs, and Portals 4. Our results confirmed that our model successfully captures behaviors exhibited by these networks. Moreover, we found RMA programs that behave inconsistently with existing documentation, confirmed by network experts.

Our work provides an important step towards understanding existing RMA networks, thus influencing the design of future RMA interfaces and hardware.},
	author = {Andrei Marian Dan and Patrick Lam and Torsten Hoefler and Martin Vechev},
	booktitle = {Proceedings of the 2016 ACM SIGPLAN International Conference on Object-Oriented Programming, Systems, Languages, and Applications},
	title = {Modeling and Analysis of Remote Memory Access Programming},
	venue = {Amsterdam, Netherlands},
	year = {2016}
}

@inproceedings{abc,
	author = {Stefan Kaestle and Reto Achermann and Roni Haecki and Moritz Hoffmann and Sabela Ramos and Timothy Roscoe},
	booktitle = {12th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2016, Savannah, GA, USA},
	title = {Machine-Aware Atomic Broadcast Trees for Multicores.},
	url = {https://www.usenix.org/conference/osdi16/technical-sessions/presentation/kaestle},
	year = {2016}
}

@mastersthesis{abc,
	author = {Sebastian Wicki},
	school = {155},
	title = {An Online Stream Processor for Timely Dataflow},
	year = {2016}
}

@inproceedings{abc,
	author = {Sangeetha Abdu Jyothi and Ankit Singla and Brighten Godfrey and Alexandra Kolla},
	booktitle = {Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2016, Salt Lake City, UT, USA},
	title = {Measuring and understanding throughput of network topologies.},
	url = {https://doi.org/10.1109/SC.2016.64},
	year = {2016}
}

@inproceedings{abc,
	author = {Ankit Singla},
	booktitle = {Proceedings of the 15th ACM Workshop on Hot Topics in Networks, HotNets 2016, Atlanta, GA, USA},
	title = {Fat-FREE Topologies.},
	url = {http://doi.acm.org/10.1145/3005745.3005747},
	year = {2016}
}

@inproceedings{abc,
	abstract = {MeteoSwiss, the Swiss national weather forecast institute, has selected densely populated accelerator servers as their primary system to compute weather forecast simulation. Servers with multiple accelerator devices that are primarily connected by a PCI-Express (PCIe) network achieve a significantly higher energy efficiency. Memory transfers between accelerators in such a system are subjected to PCIe arbitration policies. In this paper, we study the impact of PCIe topology and develop a congestion-aware performance model for PCIe communication. We present an algorithm for computing congestion factors of every communication in a congestion graph that characterizes the dynamic usage of network resources by an application. Our model applies to any PCIe tree topology. Our validation results on two different topologies of 8 GPU devices demonstrate that our model achieves an accuracy of over 97\% within the PCIe network. We demonstrate the model on a weather forecast application to identify the best algorithms for its communication patterns among GPUs.},
	author = {Maxime Martinasso and Grzegorz Kwasniewski and Sadaf R. Alam},
	booktitle = {Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis},
	title = {A PCIe congestion-aware performance model for densely populated accelerator servers},
	venue = {Salt Lake City, UT, USA},
	year = {2016}
}

@inproceedings{abc,
	abstract = {The goal of the extreme scale plasma turbulence studies described in this paper is to expedite the delivery of reliable predictions on confinement physics in large magnetic fusion systems by using world-class supercomputers to carry out simulations with unprecedented resolution and temporal duration. This has involved architecture-dependent optimizations of performance scaling and addressing code portability and energy issues, with the metrics for multi-platform comparisons being "time-to-solution" and "energy-to-solution". Realistic results addressing how confinement losses caused by plasma turbulence scale from present-day devices to the much larger $25 billion international ITER fusion facility have been enabled by innovative advances in the GTC-P code including (i) implementation of one-sided communication from MPI 3.0 standard; (ii) creative optimization techniques on Xeon Phi processors; and (iii) development of a novel performance model for the key kernels of the PIC code. Results show that modeling data movement is sufficient to predict performance on modern supercomputer platforms.},
	author = {William Tang and Stephane Ethier and Grzegorz Kwasniewski and Torsten Hoefler and Khaled Z. Ibrahim and Kamesh Madduri and Samuel Williams and Leonid Oliker and Carlos Rosales-Fernandez and Tim Williams},
	booktitle = {Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis},
	title = {Extreme Scale Plasma Turbulence Simulations on Top Supercomputers Worldwide},
	venue = {Salt Lake City, UT, USA},
	year = {2016}
}

@inproceedings{abc,
	abstract = {The interconnection network has a large influence on total cost, application performance, energy consumption, and overall system efficiency of a supercomputer. Unfortunately, today{\textquoteright}s routing algorithms do not utilize this important resource most efficiently. We first demonstrate this by defining the dark fiber metric as a measure of unused resource in networks. To improve the utilization, we propose scheduling-aware routing, a new technique that uses the current state of the batch system to determine a new set of network routes and so increases overall system utilization by up to 17.74\%. We also show that our proposed routing increases the throughput of communication benchmarks by up to 17.6\% on a practical InfiniBand installation. Our routing method is implemented in the standard InfiniBand tool set and can immediately be used to optimize systems. In fact, we are using it to improve the utilization of our production petascale supercomputer for more than one year.},
	author = {Jens Domke and Torsten Hoefler},
	booktitle = {Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis},
	title = {Scheduling-Aware Routing for Supercomputers},
	venue = {Salt Lake City, UT, USA},
	year = {2016}
}

@inproceedings{abc,
	author = {Himanshu Chauhan and Irina Calciu and Vijay Chidambaram and Eric Schkufza and Onur Mutlu and Pratap Subrahmanyam},
	booktitle = {4th Workshop on Interactions of NVM/Flash with Operating Systems and Workloads, INFLOW@OSDI 2016, Savannah, GA, USA},
	title = {NVMOVE: Helping Programmers Move to Byte-Based Persistence.},
	url = {https://www.usenix.org/conference/inflow16/workshop-program/presentation/chauhan},
	year = {2016}
}

@inproceedings{abc,
	author = {Nandita Vijaykumar and Kevin Hsieh and Gennady Pekhimenko and Samira Manabi Khan and Ashish Shrestha and Saugata Ghose and Adwait Jog and Phillip B. Gibbons and Onur Mutlu},
	booktitle = {49th Annual IEEE/ACM International Symposium on Microarchitecture, MICRO 2016, Taipei, Taiwan},
	title = {Zorua: A holistic approach to resource virtualization in GPUs.},
	url = {http://dx.doi.org/10.1109/MICRO.2016.7783718},
	year = {2016}
}

@inproceedings{abc,
	author = {Milad Hashemi and Onur Mutlu and Yale N. Patt},
	booktitle = {49th Annual IEEE/ACM International Symposium on Microarchitecture, MICRO 2016, Taipei, Taiwan},
	title = {Continuous runahead: Transparent hardware acceleration for memory intensive workloads.},
	url = {http://dx.doi.org/10.1109/MICRO.2016.7783764},
	year = {2016}
}

@inproceedings{abc,
	author = {Kevin Hsieh and Samira Manabi Khan and Nandita Vijaykumar and Kevin K. Chang and Amirali Boroumand and Saugata Ghose and Onur Mutlu},
	booktitle = {34th IEEE International Conference on Computer Design, ICCD 2016, Scottsdale, AZ, USA},
	title = {Accelerating pointer chasing in 3D-stacked memory: Challenges, mechanisms, evaluation.},
	url = {http://dx.doi.org/10.1109/ICCD.2016.7753257},
	year = {2016}
}

@inproceedings{abc,
	author = {Onur Mutlu},
	booktitle = {2016 International Symposium on Rapid System Prototyping, RSP 2016, Pittsburg, PA, USA},
	title = {Keynote: rethinking memory system design.},
	url = {https://doi.org/10.1145/2990299.2990300},
	year = {2016}
}

@inproceedings{abc,
	author = {Xi-Yue Xiang and Saugata Ghose and Onur Mutlu and Nian-Feng Tzeng},
	booktitle = {34th IEEE International Conference on Computer Design, ICCD 2016, Scottsdale, AZ, USA},
	title = {A model for Application Slowdown Estimation in on-chip networks and its use for improving system fairness and performance.},
	url = {http://dx.doi.org/10.1109/ICCD.2016.7753327},
	year = {2016}
}

@mastersthesis{abc,
	author = {Denny Lin},
	school = {152},
	title = {Blackboxing Performance Monitoring Units},
	year = {2016}
}

@mastersthesis{abc,
	author = {Andrei Parvu},
	school = {153},
	title = {Program Trace Capture and Analysis for ARM},
	year = {2016}
}

@inproceedings{abc,
	author = {Ioannis Mitliagkas and Ce Zhang and Stefan Hadjis and Christopher R{\'e}},
	booktitle = {54th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2016, Monticello, IL, USA},
	title = {Asynchrony begets momentum, with an application to deep learning.},
	url = {http://dx.doi.org/10.1109/ALLERTON.2016.7852343},
	year = {2016}
}

@mastersthesis{abc,
	abstract = {Identifying performance bottlenecks of modern, distributed stream processing engines is a serious challenge. At the same time, such engines are widely used to perform data-parallel tasks such as machine learning, graph processing or sophisticated streaming data analysis. Oftentimes, these tasks are required to produce low-latency results as well as to achieve a high throughput. As computations often consist of complex, iterative dataflows and are distributed over multiple physical machines {\textemdash} with hundreds of worker threads in total {\textemdash} finding the source of a performance problem is a difficult task. While profiling can be used to quantify the time spent in the various steps of a parallel computation, it does not take into account the dependencies between the steps. As a result, optimization efforts are often wasted on components that have little to no influence on query latency or the overall runtime of a program.
In this work, we offer a more effective alternative by applying critical path analysis, a dependency-aware technique. The critical path is defined as the longest sequence of dependent steps in a parallel program{\textquoteright}s execution. Any increase in the execution time of a step on the critical path will therefore result in an equal increase in the total runtime of the computation. We refine existing critical path-based models and apply them to data-parallel systems, which often share common low-level principles. We provide guidelines on the instrumentation necessary to apply our model, as well as a set of trace properties that help verify the correctness of that instrumentation. Furthermore, we develop a novel method to identify phases in a worker thread{\textquoteright}s execution during which it is waiting {\textemdash} e.g. for a message from a different worker{\textemdash}even in the absence of blocking system calls. Through critical path analysis, we can then identify performance bottlenecks in system components, dataflow operators as well as in network communication.
To demonstrate our ideas, we implemented a prototype system capable of performing a critical path analysis of the Timely Dataflow stream processing engine. We show that our system can effectively identify the factors limiting a data-parallel computation{\textquoteright}s overall performance. Furthermore, we demonstrate that our analysis is both efficient and scalable, and can even be performed in real-time in certain configurations.},
	author = {Ralf Sager},
	school = {154},
	title = {Real-Time Performance Analysis of a Modern Data-Parallel Stream Processing Engine},
	year = {2016}
}

@mastersthesis{abc,
	author = {Edona Meta},
	school = {150},
	title = {Question Bias in Repetitive Crowdsourcing Tasks},
	year = {2016}
}

@inproceedings{abc,
	author = {Ashutosh Pattnaik and Xulong Tang and Adwait Jog and Onur Kayiran and Asit K. Mishra and Mahmut T. Kandemir and Onur Mutlu and Chita R. Das},
	booktitle = {Proceedings of the 2016 International Conference on Parallel Architectures and Compilation, PACT 2016, Haifa, Israel},
	title = {Scheduling Techniques for GPU Architectures with Processing-In-Memory Capabilities.},
	url = {http://doi.acm.org/10.1145/2967938.2967940},
	year = {2016}
}

@mastersthesis{abc,
	author = {Matteo Pozzetti},
	school = {151},
	title = {Access Path Design for Quality Assurance in Crowdsourcing},
	year = {2016}
}

@inproceedings{abc,
	author = {Onur Kayiran and Adwait Jog and Ashutosh Pattnaik and Rachata Ausavarungnirun and Xulong Tang and Mahmut T. Kandemir and Gabriel H. Loh and Onur Mutlu and Chita R. Das},
	booktitle = {Proceedings of the 2016 International Conference on Parallel Architectures and Compilation, PACT 2016, Haifa, Israel},
	title = {{\^I}{\textonequarter}C-States: Fine-grained GPU Datapath Power Management.},
	url = {http://doi.acm.org/10.1145/2967938.2967941},
	year = {2016}
}

@inproceedings{abc,
	author = {Kaan Kara and Gustavo Alonso},
	booktitle = {26th International Conference on Field Programmable Logic and Applications, FPL 2016, Lausanne, Switzerland},
	title = {Fast and robust hashing for database operators.},
	url = {http://dx.doi.org/10.1109/FPL.2016.7577353},
	year = {2016}
}

@inproceedings{abc,
	author = {David Sidler and Zsolt Istv{\'a}n and Gustavo Alonso},
	booktitle = {26th International Conference on Field Programmable Logic and Applications, FPL 2016, Lausanne, Switzerland},
	title = {Low-latency TCP/IP stack for data center applications.},
	url = {http://dx.doi.org/10.1109/FPL.2016.7577319},
	year = {2016}
}

@inproceedings{abc,
	author = {Gerd Zellweger and Denny Lin and Timothy Roscoe},
	booktitle = {Proceedings of the 7th ACM SIGOPS Asia-Pacific Workshop on Systems, APSys {\textquoteright}16, Hong Kong, China},
	title = {So many performance events, so little time.},
	url = {http://doi.acm.org/10.1145/2967360.2967375},
	year = {2016}
}

@article{abc,
	abstract = {Network interface cards are one of the key components to achieve efficient parallel performance. In the past, they have gained new functionalities, such as lossless transmission and remote direct memory access, that are now ubiquitous in high-performance systems. Prototypes of next-generation network cards now offer new features that facilitate device programming. In this article, the authors discuss an abstract machine model for offloading architectures. They used the Portals 4 network interface to implement the proposed abstraction model, and they present two microbenchmarks to show the effects of fully offloaded collective communications. They then propose the concept of persistent offloaded operations that can reduce the creation/offloading overhead, and they discuss a possible extension to the current Portals 4 interface to enable their support. The results obtained show how this work can be used to accelerate existing MPI applications.},
	author = {Salvatore Di Girolamo and Pierre Jolivet and Keith D. Underwood and Torsten Hoefler},
	pages = {6-17},
	journal = {IEEE Micro},
	title = {Exploiting Offload Enabled Network Interfaces},
	volume = {36},
	year = {2016}
}

@book{abc,
	abstract = {books do not have abstracts},
	note = {Test},
	title = {Test Book Edit},
	year = {2016}
}

@mastersthesis{abc,
	abstract = {Programmable networks are quickly gaining popularity in both academic research and industry, as they provide a new way to deal with network management. Several deployments by industry including Microsoft and Google already demonstrate the advantages of such paradigm shifts. Despite the initial momentum in the development of logically centralized control logic, i.e. the network controller, a shift towards proprietary industry-driven solutions is observed. Part of the problem is that open source academic-backed controllers have difficulties to scale at the level required by industry operation, particularly when it comes to the speed of operation. This thesis investigates a new approach towards the controller platform by adopting a dataflow processing framework as the computational foundation. At the same time it introduces the base of a more formal way to reason about network
management. Specifically, the thesis builds around a representation of the network as a graph which allows us to specify high-level configuration policies as constraints on top of this graph and use well-understood graph computations in a data-parallel and incremental fashion to calculate the network routing. Our results demonstrate a very competitive performance of the routing module even before potential optimizations are conducted. Furthermore, interaction with the system is intuitive and human-friendly thanks to the higher-level policies we introduce.},
	author = {Christian  St{\"u}ckelberger },
	school = {149},
	title = {Expressing the Routing Logic of a SDN Controller as a Differential Dataflow},
	year = {2016}
}

@inproceedings{abc,
	author = {Jana Giceva and Gerd Zellweger and Gustavo Alonso and Timothy Roscoe},
	booktitle = {Proceedings of the 12th International Workshop on Data Management on New Hardware, DaMoN 2016, San Francisco, CA, USA},
	title = {Customized OS support for data-processing.},
	url = {http://doi.acm.org/10.1145/2933349.2933351},
	year = {2016}
}

@inproceedings{abc,
	author = {Kevin K. Chang and Abhijith Kashyap and Hasan Hassan and Saugata Ghose and Kevin Hsieh and Donghyuk Lee and Tianshi Li and Gennady Pekhimenko and Samira Manabi Khan and Onur Mutlu},
	booktitle = {Proceedings of the 2016 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Science, Antibes Juan-Les-Pins, France},
	title = {Understanding Latency Variation in Modern DRAM Chips: Experimental Characterization, Analysis, and Optimization.},
	url = {http://doi.acm.org/10.1145/2896377.2901453},
	year = {2016}
}

@inproceedings{abc,
	author = {Samira Manabi Khan and Donghyuk Lee and Onur Mutlu},
	booktitle = {46th Annual IEEE/IFIP International Conference on Dependable Systems and Networks, DSN 2016, Toulouse, France},
	title = {PARBOR: An Efficient System-Level Technique to Detect Data-Dependent Failures in DRAM.},
	url = {http://dx.doi.org/10.1109/DSN.2016.30},
	year = {2016}
}

@inproceedings{abc,
	abstract = {Lossless interconnection networks are omnipresent in high performance computing systems, data centers and network-on-chip architectures. Such networks require efficient and deadlock-free routing functions to utilize the available hardware. Topology-aware routing functions become increasingly inapplicable, due to irregular topologies, which either are irregular by design or as a result of hardware failures. Existing topology-agnostic routing methods either suffer from poor load balancing or are not bounded in the number of virtual channels needed to resolve deadlocks in the routing tables. We propose a novel topology-agnostic routing approach which implicitly avoids deadlocks during the path calculation instead of solving both problems separately. We present a model implementation, called Nue, of a destination-based and oblivious routing function. Nue routing heuristically optimizes the load balancing while enforcing deadlock-freedom without exceeding a given number of virtual channels, which we demonstrate based on the InfiniBand architecture.},
	author = {Jens Domke and Torsten Hoefler and Satoshi Matsuoka},
	booktitle = {Proceedings of the 25th ACM International Symposium on High-Performance Parallel and Distributed Computing},
	title = {Routing on the Dependency Graph: A New Approach to Deadlock-Free High-Performance Routing},
	venue = {Kyoto, Japan},
	year = {2016}
}

@inproceedings{abc,
	author = {Adwait Jog and Onur Kayiran and Ashutosh Pattnaik and Mahmut T. Kandemir and Onur Mutlu and Ravishankar Iyer and Chita R. Das},
	booktitle = {Proceedings of the 2016 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Science, Antibes Juan-Les-Pins, France},
	title = {Exploiting Core Criticality for Enhanced GPU Performance.},
	url = {http://doi.acm.org/10.1145/2896377.2901468},
	year = {2016}
}

@inproceedings{abc,
	abstract = {We propose a topology-aware distributed Reader-Writer lock that accelerates irregular workloads for supercomputers and data centers. The core idea behind the lock is a modular design that is an interplay of three distributed data structures: a counter of readers/writers in the critical section, a set of queues for ordering writers waiting for the lock, and a tree that binds all the queues and synchronizes writers with readers. Each structure is associated with a parameter for favoring either readers or writers, enabling adjustable performance that can be viewed as a point in a three dimensional parameter space. We also develop a distributed topology-aware MCS lock that is a building block of the above design and improves state-of-the-art MPI implementations. Both schemes use non-blocking Remote Memory Access (RMA) techniques for highest performance and scalability. We evaluate our schemes on a Cray XC30 and illustrate that they outperform state-of-the-art MPI-3 RMA locking protocols by 81\% and 73\%, respectively. Finally, we use them to accelerate a distributed hashtable that represents irregular workloads such as key-value stores or graph processing.},
	author = {Patrick Schmid and Maciej Besta and Torsten Hoefler},
	booktitle = {Proceedings of the 25th ACM International Symposium on High-Performance Parallel and Distributed Computing},
	title = {High-Performance Distributed RMA Locks},
	venue = {Kyoto, Japan},
	year = {2016}
}

@inproceedings{abc,
	abstract = {DeepDive is a system for extracting relational databases from dark data: the mass of text, tables, and images that are widely collected and stored but which cannot be exploited by standard relational tools. If the information in dark data - scientific papers, Web classified ads, customer service notes, and so on - were instead in a relational database, it would give analysts a massive and valuable new set of "big data." DeepDive is distinctive when compared to previous information extraction systems in its ability to obtain very high precision and recall at reasonable engineering cost; in a number of applications, we have used DeepDive to create databases with accuracy that meets that of human annotators. To date we have successfully deployed DeepDive to create data-centric applications for insurance, materials science, genomics, paleontologists, law enforcement, and others. The data unlocked by DeepDive represents a massive opportunity for industry, government, and scientific researchers. DeepDive is enabled by an unusual design that combines large-scale probabilistic inference with a novel developer interaction cycle. This design is enabled by several core innovations around probabilistic training and inference.},
	author = {Ce Zhang and Jaeho Shin and Christopher R{\'e} and Michael J. Cafarella and Feng Niu},
	booktitle = {Proceedings of the 2016 International Conference on Management of Data, SIGMOD Conference 2016},
	title = {Extracting Databases from Dark Data with DeepDive.},
	url = {http://doi.acm.org/10.1145/2882903.2904442},
	venue = {San Francisco, CA, USA},
	year = {2016}
}

@inproceedings{abc,
	author = {Kevin Hsieh and Eiman Ebrahimi and Gwangsun Kim and Niladrish Chatterjee and Mike O{\textquoteright}Connor and Nandita Vijaykumar and Onur Mutlu and Stephen W. Keckler},
	booktitle = {43rd ACM/IEEE Annual International Symposium on Computer Architecture, ISCA 2016, Seoul, South Korea},
	title = {Transparent Offloading and Mapping (TOM): Enabling Programmer-Transparent Near-Data Processing in GPU Systems.},
	url = {http://doi.ieeecomputersociety.org/10.1109/ISCA.2016.27},
	year = {2016}
}

@inproceedings{abc,
	abstract = {Programming today{\textquoteright}s increasingly complex heterogeneous hardware is difficult, as it commonly requires the use of data-parallel languages, pragma annotations, specialized libraries, or DSL compilers. Adding explicit accelerator support into a larger code base is not only costly, but also introduces additional complexity that hinders long-term maintenance. We propose a new heterogeneous compiler that brings us closer to the dream of automatic accelerator mapping. Starting from a sequential compiler IR, we automatically generate a hybrid executable that - in combination with a new data management system - transparently offloads suitable code regions. Our approach is almost regression free for a wide range of applications while improving a range of compute kernels as well as two full SPEC CPU applications. We expect our work to reduce the initial cost of accelerator usage and to free developer time to investigate algorithmic changes.},
	author = {Tobias Grosser and Torsten Hoefler},
	booktitle = {Proceedings of the 2016 International Conference on Supercomputing},
	title = {Polly-ACC: Transparent compilation to heterogeneous hardware},
	venue = {Istanbul, Turkey},
	year = {2016}
}

@inproceedings{abc,
	author = {Pratanu Roy and Arijit Khan and Gustavo Alonso},
	booktitle = {Proceedings of the 2016 International Conference on Management of Data, SIGMOD Conference 2016, San Francisco, CA, USA},
	title = {Augmented Sketch: Faster and More Accurate Stream Processing.},
	url = {http://doi.acm.org/10.1145/2882903.2882948},
	year = {2016}
}

@inproceedings{abc,
	author = {Milad Hashemi and Khubaib and Eiman Ebrahimi and Onur Mutlu and Yale N. Patt},
	booktitle = {43rd ACM/IEEE Annual International Symposium on Computer Architecture, ISCA 2016, Seoul, South Korea},
	title = {Accelerating Dependent Cache Misses with an Enhanced Memory Controller.},
	url = {http://dx.doi.org/10.1109/ISCA.2016.46},
	year = {2016}
}

@inproceedings{abc,
	abstract = {We discuss the paper selection process of the ACM PASC16 conference. The conference spans multiple scientific fields used to very different publication cultures. We aim to combine the strengths of the conference and journal publication schemes in order to design an attractive high-quality publication venue for works in large-scale computational science. We use four non-standard key ideas to design a paper selection process for ACM PASC16: (1) no pre-selected committee, (2) short revision process, (3) full double-blindness, and (4) suggested expert reviews. In this overview, we describe our observations of the process and anlayse the data in an attempt to characterize the effectiveness of the mechanisms used. We believe that the adoption of some or all of these ideas could prove beneficial beyond ACM PASC16.},
	author = {Torsten Hoefler},
	booktitle = {Proceedings of the Platform for Advanced Scientific Computing Conference},
	title = {Selecting Technical Papers for an Interdisciplinary Conference: The PASC Review Process},
	venue = {Lausanne, Switzerland},
	year = {2016}
}

@inproceedings{abc,
	author = {Markus Pilman and Martin Kaufmann and Florian K{\"o}hl and Donald Kossmann and Damien Profeta},
	booktitle = {Proceedings of the 2016 International Conference on Management of Data, SIGMOD Conference 2016, San Francisco, CA, USA},
	title = {ParTime: Parallel Temporal Aggregation.},
	url = {http://doi.acm.org/10.1145/2882903.2903732},
	year = {2016}
}

@inproceedings{abc,
	author = {Wayne P. Burleson and Onur Mutlu and Mohit Tiwari},
	booktitle = {Proceedings of the 53rd Annual Design Automation Conference, DAC 2016, Austin, TX, USA},
	title = {Invited - Who is the major threat to tomorrow{\textquoteright}s security?: you, the hardware designer.},
	url = {http://doi.acm.org/10.1145/2897937.2905022},
	year = {2016}
}

@inproceedings{abc,
	author = {Arijit Khan and Benjamin Zehnder and Donald Kossmann},
	booktitle = {32nd IEEE International Conference on Data Engineering, ICDE 2016, Helsinki, Finland},
	title = {Revenue maximization by viral marketing: A social network host{\textquoteright}s perspective.},
	url = {http://dx.doi.org/10.1109/ICDE.2016.7498227},
	year = {2016}
}

@inproceedings{abc,
	author = {Zsolt Istv{\'a}n and David Sidler and Gustavo Alonso},
	booktitle = {24th IEEE Annual International Symposium on Field-Programmable Custom Computing Machines, FCCM 2016, Washington, DC, USA},
	title = {Runtime Parameterizable Regular Expression Operators for Databases.},
	url = {http://doi.ieeecomputersociety.org/10.1109/FCCM.2016.61},
	year = {2016}
}

@mastersthesis{abc,
	author = {Claudio Foellmi},
	school = {146},
	title = {OS Development in Rust},
	year = {2016}
}

@phdthesis{abc,
	author = {Pravin Shinde},
	school = {23474},
	title = {Rethinking host network stack architecture using a dataflow modeling approach },
	year = {2016}
}

@inproceedings{abc,
	author = {Gustavo Alonso},
	booktitle = {2016 IEEE International Conference on Cloud Engineering, IC2E 2016, Berlin, Germany},
	title = {Generalization versus Specialization in Cloud Computing Infrastructures.},
	url = {http://dx.doi.org/10.1109/IC2E.2016.50},
	year = {2016}
}

@mastersthesis{abc,
	author = {Andrea Lattuada},
	school = {144},
	title = {Programmable scheduling in a stream processing system},
	year = {2016}
}

@inproceedings{abc,
	author = {Izzat El Hajj and Alex Merritt and Gerd Zellweger and Dejan S. Milojicic and Reto Achermann and Paolo Faraboschi and Wen-Mei W. Hwu and Timothy Roscoe and Karsten Schwan},
	booktitle = {Proceedings of the Twenty-First International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS {\textquoteright}16, Atlanta, GA, USA},
	title = {SpaceJMP: Programming with Multiple Virtual Address Spaces.},
	url = {http://doi.acm.org/10.1145/2872362.2872366},
	year = {2016}
}

@inproceedings{abc,
	author = {Gennady Pekhimenko and Evgeny Bolotin and Nandita Vijaykumar and Onur Mutlu and Todd C. Mowry and Stephen W. Keckler},
	booktitle = {2016 IEEE International Symposium on High Performance Computer Architecture, HPCA 2016, Barcelona, Spain},
	title = {A case for toggle-aware compression for GPU systems.},
	url = {http://dx.doi.org/10.1109/HPCA.2016.7446064},
	year = {2016}
}

@inproceedings{abc,
	author = {Hasan Hassan and Gennady Pekhimenko and Nandita Vijaykumar and Vivek Seshadri and Donghyuk Lee and Oguz Ergin and Onur Mutlu},
	booktitle = {2016 IEEE International Symposium on High Performance Computer Architecture, HPCA 2016, Barcelona, Spain},
	title = {ChargeCache: Reducing DRAM latency by exploiting row access locality.},
	url = {http://dx.doi.org/10.1109/HPCA.2016.7446096},
	year = {2016}
}

@inproceedings{abc,
	abstract = {Consensus mechanisms for ensuring consistency are some of the most expensive operations in managing large amounts of data. Often, there is a trade off that involves reducing the coordination overhead at the price of accepting possible data loss or inconsistencies. As the demand for more efficient data centers increases, it is important to provide better ways of ensuring consistency without affecting performance.

In this paper we show that consensus (atomic broadcast) can be removed from the critical path of performance by moving it to hardware. As a proof of concept, we implement Zookeeper{\textquoteright}s atomic broadcast at the network level using an FPGA. Our design uses both TCP and an application specific network protocol. The design can be used to push more value into the network, e.g., by extending the functionality of middleboxes or adding inexpensive consensus to in-network processing nodes.

To illustrate how this hardware consensus can be used in practical systems, we have combined it with a mainmemory key value store running on specialized microservers (built as well on FPGAs). This results in a distributed service similar to Zookeeper that exhibits high and stable performance. This work can be used as a blueprint for further specialized designs.},
	author = {Zsolt Istv{\'a}n and David Sidler and Gustavo Alonso and Marko Vukolic},
	booktitle = {13th USENIX Symposium on Networked Systems Design and Implementation, NSDI 2016},
	title = {Consensus in a Box: Inexpensive Coordination in Hardware.},
	url = {https://www.usenix.org/conference/nsdi16/technical-sessions/presentation/istvan},
	venue = {Santa Clara, CA, USA},
	year = {2016}
}

@inproceedings{abc,
	author = {Yang Li and Di Wang and Saugata Ghose and Jie Liu and Sriram Govindan and Sean James and Eric Peterson and John Siegler and Rachata Ausavarungnirun and Onur Mutlu},
	booktitle = {2016 IEEE International Symposium on High Performance Computer Architecture, HPCA 2016, Barcelona, Spain},
	title = {SizeCap: Efficiently handling power surges in fuel cell powered data centers.},
	url = {http://dx.doi.org/10.1109/HPCA.2016.7446085},
	year = {2016}
}

@inproceedings{abc,
	author = {Kevin K. Chang and Prashant J. Nair and Donghyuk Lee and Saugata Ghose and Moinuddin K. Qureshi and Onur Mutlu},
	booktitle = {2016 IEEE International Symposium on High Performance Computer Architecture, HPCA 2016, Barcelona, Spain},
	title = {Low-Cost Inter-Linked Subarrays (LISA): Enabling fast inter-subarray data movement in DRAM.},
	url = {http://dx.doi.org/10.1109/HPCA.2016.7446095},
	year = {2016}
}

@inproceedings{abc,
	author = {Gustavo Alonso},
	booktitle = {Proceedings of the 19th International Conference on Extending Database Technology, EDBT 2016, Bordeaux, France},
	title = {Data Processing in Modern Hardware.},
	url = {http://dx.doi.org/10.5441/002/edbt.2016.03},
	venue = {Bordeaux, France, March 15-16, 2016.},
	year = {2016}
}

@article{abc,
	abstract = {Relaxed synchronization offers the potential for maintaining application scalability, by allowing many processes to make independent progress when some processes suffer delays. Yet the benefits of this approach for important parallel workloads have not been investigated in detail. In this paper, we use a validated simulation approach to explore the noise-mitigation effects of idealized nonblocking collectives, in workloads where these collectives are a major contributor to total execution time. Although nonblocking collectives are unlikely to provide significant noise mitigation to applications in the low operating system noise environments expected in next-generation high-performance computing systems, we show that they can potentially improve application runtime with respect to other noise types.},
	author = {Patrick M. Widener and Scott Levy and Kurt B. Ferreira and Torsten Hoefler},
	pages = {121-133},
	journal = {The International Journal of High Performance Computing Applications},
	title = {On noise and the performance benefit of nonblocking collectives},
	volume = {30},
	year = {2016}
}

@article{abc,
	author = {Ioannis Mitliagkas and Ce Zhang and Stefan Hadjis and Christopher R{\'e}},
	journal = {CoRR},
	title = {Asynchrony begets Momentum, with an Application to Deep Learning.},
	url = {http://arxiv.org/abs/1605.09774},
	year = {2016}
}

@article{abc,
	author = {Donghyuk Lee and Yoongu Kim and Vivek Seshadri and Jamie Liu and Lavanya Subramanian and Onur Mutlu},
	journal = {CoRR},
	title = {Tiered-Latency DRAM (TL-DRAM).},
	url = {http://arxiv.org/abs/1601.06903},
	year = {2016}
}

@inproceedings{abc,
	author = {Lavanya Subramanian and Donghyuk Lee and Vivek Seshadri and Harsha Rastogi and Onur Mutlu},
	booktitle = {IEEE Trans. Parallel Distrib. Syst.},
	title = {BLISS: Balancing Performance, Fairness and Complexity in Memory Access Scheduling.},
	url = {http://dx.doi.org/10.1109/TPDS.2016.2526003},
	year = {2016}
}

@article{abc,
	author = {Donghyuk Lee and Yoongu Kim and Gennady Pekhimenko and Samira Manabi Khan and Vivek Seshadri and Kevin Kai-Wei Chang and Onur Mutlu},
	journal = {CoRR},
	title = {Adaptive-Latency DRAM (AL-DRAM).},
	url = {http://arxiv.org/abs/1603.08454},
	year = {2016}
}

@article{abc,
	author = {Xinghao Pan and Maximilian Lam and Stephen Tu and Dimitris S. Papailiopoulos and Ce Zhang and Michael I. Jordan and Kannan Ramchandran and Christopher R{\'e} and Benjamin Recht},
	journal = {CoRR},
	title = {CYCLADES: Conflict-free Asynchronous Machine Learning.},
	url = {http://arxiv.org/abs/1605.09721},
	year = {2016}
}

@inproceedings{abc,
	author = {Daniel J. Abadi and Rakesh Agrawal and Anastasia Ailamaki and Magdalena Balazinska and Philip A. Bernstein and Michael J. Carey and Surajit Chaudhuri and Jeffrey Dean and AnHai Doan and Michael J. Franklin and Johannes Gehrke and Laura M. Haas and Alon Y. Halevy and Joseph M. Hellerstein and Yannis E. Ioannidis and H. V. Jagadish and Donald Kossmann and Samuel Madden and Sharad Mehrotra and Tova Milo and Jeffrey F. Naughton and Raghu Ramakrishnan and Volker Markl and Christopher Olston and Beng Chin Ooi and Christopher R{\'e} and Dan Suciu and Michael Stonebraker and Todd Walter and Jennifer Widom},
	booktitle = {Commun. ACM},
	title = {The Beckman report on database research.},
	url = {http://doi.acm.org/10.1145/2845915},
	year = {2016}
}

@article{abc,
	author = {Yoongu Kim and Ross Daly and Jeremie Kim and Chris Fallin and Ji-Hye Lee and Donghyuk Lee and Chris Wilkerson and Konrad Lai and Onur Mutlu},
	journal = {CoRR},
	title = {RowHammer: Reliability Analysis and Security Implications.},
	url = {http://arxiv.org/abs/1603.00747},
	year = {2016}
}

@inproceedings{abc,
	author = {Ioannis Mitliagkas and Ce Zhang and Stefan Hadjis and Christopher R{\'e}},
	booktitle = {ETH Z{\"u}rich},
	title = {Asynchrony begets Momentum, with an Application to Deep Learning},
	year = {2016}
}

@article{abc,
	author = {Stefan Hadjis and Ce Zhang and Ioannis Mitliagkas and Christopher R{\'e}},
	journal = {CoRR},
	title = {Omnivore: An Optimizer for Multi-device Deep Learning on CPUs and GPUs.},
	url = {http://arxiv.org/abs/1606.04487},
	year = {2016}
}

@article{abc,
	author = {Yixin Luo and Sriram Govindan and Bikash Sharma and Mark Santaniello and Justin Meza and Aman Kansal and Jie Liu and Badriddine M. Khessib and Kushagra Vaid and Onur Mutlu},
	journal = {CoRR},
	title = {Heterogeneous-Reliability Memory: Exploiting Application-Level Memory Error Tolerance.},
	url = {http://arxiv.org/abs/1602.00729},
	year = {2016}
}

@article{abc,
	abstract = {The dark data extraction or knowledge base construction (KBC) problem is to populate a SQL database with information from unstructured data sources including emails, webpages, and pdf reports. KBC is a long-standing problem in industry and research that encompasses problems of data extraction, cleaning, and integration. We describe DeepDive, a system that combines database and machine learning ideas to help develop KBC systems. The key idea in DeepDive is that statistical inference and machine learning are key tools to attack classical data problems in extraction, cleaning, and integration in a unified and more effective manner. DeepDive programs are declarative in that one cannot write probabilistic inference algorithms; instead, one interacts by defining features or rules about the domain. A key reason for this design choice is to enable domain experts to build their own KBC systems. We present the applications, abstractions, and techniques of DeepDive employed to accelerate construction of KBC systems.},
	author = {Christopher De Sa and Alexander Ratner and Christopher R{\'e} and Jaeho Shin and Feiran Wang and Sen Wu and Ce Zhang},
	journal = {SIGMOD Record},
	title = {DeepDive: Declarative Knowledge Base Construction.},
	url = {http://doi.acm.org/10.1145/2949741.2949756},
	year = {2016}
}

@article{abc,
	author = {Emily K. Mallory and Ce Zhang and Christopher R{\'e} and Russ B. Altman},
	journal = {Bioinformatics},
	title = {Large-scale extraction of gene interactions from full-text literature using DeepDive.},
	url = {http://dx.doi.org/10.1093/bioinformatics/btv476},
	year = {2016}
}

@inproceedings{abc,
	author = {Zaheer Chothia and John Liagouris and Frank McSherry and Timothy Roscoe},
	booktitle = {PVLDB},
	title = {Explaining Outputs in Modern Data Analytics.},
	url = {http://www.vldb.org/pvldb/vol9/p1137-chothia.pdf},
	year = {2016}
}

@article{abc,
	author = {Rachata Ausavarungnirun and Chris Fallin and Xiangyao Yu and Kevin Kai-Wei Chang and Greg Nazario and Reetuparna Das and Gabriel H. Loh and Onur Mutlu},
	journal = {CoRR},
	title = {Achieving both High Energy Efficiency and High Performance in On-Chip Communication using Hierarchical Rings with Deflection Routing.},
	url = {http://arxiv.org/abs/1602.06005},
	year = {2016}
}

@inproceedings{abc,
	author = {Hongyi Xin and Sunny Nahar and Richard Zhu and John Emmons and Gennady Pekhimenko and Carl Kingsford and Can Alkan and Onur Mutlu},
	booktitle = {Bioinformatics},
	title = {Optimal seed solver: optimizing seed selection in read mapping.},
	url = {http://dx.doi.org/10.1093/bioinformatics/btv670},
	year = {2016}
}

@inproceedings{abc,
	author = {Dejan S. Milojicic and Timothy Roscoe},
	booktitle = {IEEE Computer},
	title = {Outlook on Operating Systems.},
	url = {http://dx.doi.org/10.1109/MC.2016.19},
	year = {2016}
}

@inproceedings{abc,
	author = {Onur Mutlu and Richard A. Belgard and Thomas R. Gross and Norman P. Jouppi and John L. Hennessy and Steven A. Przybylski and Chris Rowen and Yale N. Patt and Wen-Mei W. Hwu and Stephen W. Melvin and Michael Shebanow and Tse-Yu Yeh and Andy Wolfe},
	booktitle = {IEEE Micro},
	title = {Common Bonds: MIPS, HPS, Two-Level Branch Prediction, and Compressed Code RISC Processor.},
	url = {http://dx.doi.org/10.1109/MM.2016.66},
	year = {2016}
}

@article{abc,
	abstract = {Modern Graphics Processing Units (GPUs) are well provisioned to support the concurrent execution of thousands of threads. Unfortunately, different bottlenecks during execution and heterogeneous application requirements create imbalances in utilization of resources in the cores. For example, when a GPU is bottlenecked by the available off-chip memory bandwidth, its computational resources are often overwhelmingly idle, waiting for data from memory to arrive. 
This work describes the Core-Assisted Bottleneck Acceleration (CABA) framework that employs idle on-chip resources to alleviate different bottlenecks in GPU execution. CABA provides flexible mechanisms to automatically generate "assist warps" that execute on GPU cores to perform specific tasks that can improve GPU performance and efficiency. 
CABA enables the use of idle computational units and pipelines to alleviate the memory bandwidth bottleneck, e.g., by using assist warps to perform data compression to transfer less data from memory. Conversely, the same framework can be employed to handle cases where the GPU is bottlenecked by the available computational units, in which case the memory pipelines are idle and can be used by CABA to speed up computation, e.g., by performing memoization using assist warps. 
We provide a comprehensive design and evaluation of CABA to perform effective and flexible data compression in the GPU memory hierarchy to alleviate the memory bandwidth bottleneck. Our extensive evaluations show that CABA, when used to implement data compression, provides an average performance improvement of 41.7\% (as high as 2.6X) across a variety of memory-bandwidth-sensitive GPGPU applications.},
	author = {Nandita Vijaykumar and Gennady Pekhimenko and Adwait Jog and Saugata Ghose and Abhishek Bhowmick and Rachata Ausavarungnirun and Chita R. Das and Mahmut T. Kandemir and Todd C. Mowry and Onur Mutlu},
	journal = {CoRR},
	title = {A Framework for Accelerating Bottlenecks in GPU Execution with Assist Warps.},
	url = {http://arxiv.org/abs/1602.01348},
	year = {2016}
}

@inproceedings{abc,
	author = {Amir Yazdanbakhsh and Gennady Pekhimenko and Bradley Thwaites and Hadi Esmaeilzadeh and Onur Mutlu and Todd C. Mowry},
	booktitle = {TACO},
	title = {RFVP: Rollback-Free Value Prediction with Safe-to-Approximate Loads.},
	url = {http://doi.acm.org/10.1145/2836168},
	year = {2016}
}

@inproceedings{abc,
	author = {Kevin Kai-Wei Chang and Gabriel H. Loh and Mithuna Thottethodi and Yasuko Eckert and Mike O{\textquoteright}Connor and Srilatha Manne and Lisa Hsu and Lavanya Subramanian and Onur Mutlu},
	booktitle = {CoRR},
	title = {Enabling Efficient Dynamic Resizing of Large DRAM Caches via A Hardware Consistent Hashing Mechanism.},
	url = {http://arxiv.org/abs/1602.00722},
	year = {2016}
}

@inproceedings{abc,
	author = {Donghyuk Lee and Saugata Ghose and Gennady Pekhimenko and Samira Manabi Khan and Onur Mutlu},
	booktitle = {TACO},
	title = {Simultaneous Multi-Layer Access: Improving 3D-Stacked Memory Bandwidth at Low Cost.},
	url = {http://doi.acm.org/10.1145/2832911},
	year = {2016}
}

@inproceedings{abc,
	author = {Yixin Luo and Saugata Ghose and Yu Cai and Erich F. Haratsch and Onur Mutlu},
	booktitle = {IEEE Journal on Selected Areas in Communications},
	title = {Enabling Accurate and Practical Online Flash Channel Modeling for Modern MLC NAND Flash Memory.},
	url = {http://dx.doi.org/10.1109/JSAC.2016.2603608},
	year = {2016}
}

@inproceedings{abc,
	author = {Darko Makreshanski and Georgios Giannikis and Gustavo Alonso and Donald Kossmann},
	booktitle = {PVLDB},
	title = {MQJoin: Efficient Shared Execution of Main-Memory Joins.},
	url = {http://www.vldb.org/pvldb/vol9/p480-makreshanski.pdf},
	year = {2016}
}

@article{abc,
	author = {Mohammed Alser and Hasan Hassan and Hongyi Xin and Oguz Ergin and Onur Mutlu and Can Alkan},
	journal = {CoRR},
	title = {GateKeeper: Enabling Fast Pre-Alignment in DNA Short Read Mapping with a New Streaming Accelerator Architecture.},
	url = {http://arxiv.org/abs/1604.01789},
	year = {2016}
}

@article{abc,
	author = {Vivek Seshadri and Donghyuk Lee and Thomas Mullins and Hasan Hassan and Amirali Boroumand and Jeremie Kim and Michael A. Kozuch and Onur Mutlu and Phillip B. Gibbons and Todd C. Mowry},
	journal = {CoRR},
	title = {Buddy-RAM: Improving the Performance and Efficiency of Bulk Bitwise Operations Using DRAM.},
	url = {http://arxiv.org/abs/1611.09988},
	year = {2016}
}

@inproceedings{abc,
	author = {Hiroyuki Usui and Lavanya Subramanian and Kevin Kai-Wei Chang and Onur Mutlu},
	booktitle = {TACO},
	title = {DASH: Deadline-Aware High-Performance Memory Scheduler for Heterogeneous Systems with Hardware Accelerators.},
	url = {http://doi.acm.org/10.1145/2847255},
	year = {2016}
}

@article{abc,
	author = {Vivek Seshadri and Onur Mutlu},
	journal = {CoRR},
	title = {The Processing Using Memory Paradigm: In-DRAM Bulk Copy, Initialization, Bitwise AND and OR.},
	url = {http://arxiv.org/abs/1610.09603},
	year = {2016}
}

@article{abc,
	author = {Onur Mutlu and Richard A. Belgard and Nick Tredennick and Mike Schlansker},
	journal = {IEEE Micro},
	title = {The 2014 MICRO Test of Time Award Winners: From 1978 to 1992.},
	url = {http://dx.doi.org/10.1109/MM.2016.7},
	year = {2016}
}

@article{abc,
	author = {Ce Zhang and Arun Kumar and Christopher R{\'e}},
	journal = {ACM Trans. Database Syst.},
	title = {Materialization Optimizations for Feature Selection Workloads.},
	url = {http://doi.acm.org/10.1145/2877204},
	year = {2016}
}

@article{abc,
	author = {Arijit Khan and Gustavo Segovia and Donald Kossmann},
	journal = {CoRR},
	title = {Let{\textquoteright}s Do Smart Routing: For Distributed Graph Querying with Decoupled Storage.},
	url = {http://arxiv.org/abs/1611.03959},
	year = {2016}
}

@article{abc,
	author = {Amir Yazdanbakhsh and Bradley Thwaites and Hadi Esmaeilzadeh and Gennady Pekhimenko and Onur Mutlu and Todd C. Mowry},
	journal = {IEEE Design  Test},
	title = {Mitigating the Memory Bottleneck With Approximate Load Value Prediction.},
	url = {http://dx.doi.org/10.1109/MDAT.2015.2504899},
	year = {2016}
}

@article{abc,
	author = {Donghyuk Lee and Samira Manabi Khan and Lavanya Subramanian and Rachata Ausavarungnirun and Gennady Pekhimenko and Vivek Seshadri and Saugata Ghose and Onur Mutlu},
	journal = {CoRR},
	title = {Reducing DRAM Latency by Exploiting Design-Induced Latency Variation in Modern DRAM Chips.},
	url = {http://arxiv.org/abs/1610.09604},
	year = {2016}
}

@article{abc,
	author = {Rachata Ausavarungnirun and Chris Fallin and Xiangyao Yu and Kevin Kai-Wei Chang and Greg Nazario and Reetuparna Das and Gabriel H. Loh and Onur Mutlu},
	journal = {Parallel Computing},
	title = {A case for hierarchical rings with deflection routing: An energy-efficient on-chip communication substrate.},
	url = {http://dx.doi.org/10.1016/j.parco.2016.01.009},
	year = {2016}
}

@article{abc,
	author = {Besmira Nushi and Ece Kamar and Eric Horvitz and Donald Kossmann},
	journal = {CoRR},
	title = {On Human Intellect and Machine Failures: Troubleshooting Integrative Machine Learning Systems.},
	url = {http://arxiv.org/abs/1611.08309},
	year = {2016}
}

@inproceedings{abc,
	author = {Simon Peter and Jialin Li and Irene Zhang and Dan R. K. Ports and Doug Woos and Arvind Krishnamurthy and Thomas E. Anderson and Timothy Roscoe},
	booktitle = {ACM Trans. Comput. Syst.},
	title = {Arrakis: The Operating System Is the Control Plane.},
	url = {http://doi.acm.org/10.1145/2812806},
	year = {2016}
}

@article{abc,
	author = {Anja Gruenheid and Donald Kossmann and Divesh Srivastava},
	journal = {CoRR},
	title = {Online Event Integration with StoryPivot.},
	url = {http://arxiv.org/abs/1610.07732},
	year = {2016}
}

@inproceedings{abc,
	author = {Hyoseung Kim and Dionisio de Niz and Bj{\"o}rn Andersson and Mark H. Klein and Onur Mutlu and Ragunathan Rajkumar},
	booktitle = {Real-Time Systems},
	title = {Bounding and reducing memory interference in COTS-based multi-core systems.},
	url = {http://dx.doi.org/10.1007/s11241-016-9248-1},
	year = {2016}
}

@article{abc,
	abstract = {We present ZipML, the first framework for training dense generalized linear models using end-to-end low-precision representation--in ZipML, all movements of data, including those for input samples, model, and gradients, are represented using as little as two bits per component. Within our framework, we have successfully compressed, separately, the input data by 16x, gradient by 16x, and model by 16x while still getting the same training result. Even for the most challenging datasets, we find that robust convergence can be ensured using only an end-to-end 8-bit representation or a 6-bit representation if only samples are quantized. Our work builds on previous research on using low-precision representations for gradient and model in the context of stochastic gradient descent. Our main technical contribution is a new set of techniques which allow the training samples to be processed with low precision, without affecting the convergence of the algorithm. In turn, this leads to a system where all data items move in a quantized, low precision format. In particular, we first establish that randomized rounding, while sufficient when quantizing the model and the gradients, is biased when quantizing samples, and thus leads to a different training result. We propose two new data representations which converge to the same solution as in the original data representation both in theory and empirically and require as little as 2-bits per component. As a result, if the original data is stored as 32-bit floats, we decrease the bandwidth footprint for each training iteration by up to 16x. Our results hold for models such as linear regression and least squares SVM. ZipML raises interesting theoretical questions related to the robustness of SGD to approximate data, model, and gradient representations. We conclude this working paper by a description of ongoing work extending these preliminary results. },
	author = {Hantian Zhang and Kaan Kara and Jerry Li and Dan Alistarh and Ji Liu and Ce Zhang},
	journal = {CoRR},
	title = {ZipML: An End-to-end Bitwise Framework for Dense Generalized Linear Models.},
	url = {http://arxiv.org/abs/1611.05402},
	year = {2016}
}

@inproceedings{abc,
	author = {Yoongu Kim and Weikun Yang and Onur Mutlu},
	booktitle = {Computer Architecture Letters},
	title = {Ramulator: A Fast and Extensible DRAM Simulator.},
	url = {http://dx.doi.org/10.1109/LCA.2015.2414456},
	year = {2016}
}

@article{abc,
	author = {Kevin Kai-Wei Chang and Donghyuk Lee and Zeshan Chishti and Alaa R. Alameldeen and Chris Wilkerson and Yoongu Kim and Onur Mutlu},
	journal = {CoRR},
	title = {Reducing Performance Impact of DRAM Refresh by Parallelizing Refreshes with Accesses.},
	url = {http://arxiv.org/abs/1601.06352},
	year = {2016}
}

@article{abc,
	abstract = {The increase in the number of cores per processor and the complexity of memory hierarchies make cache coherence key for programmability of current shared memory systems. However, ignoring its detailed architectural characteristics can harm performance significantly. In order to assist performance-centric programming, we propose a methodology to allow semi-automatic performance tuning with the systematic translation from an algorithm to an analytic performance model for cache line transfers. For this, we design a simple interface for cache line aware optimization, a translation methodology, and a full performance model that exposes the block-based design of caches to middleware designers. We investigate two different architectures to show the applicability of our techniques and methods: the many-core accelerator Intel Xeon Phi and a multi-core processor with a NUMA configuration (Intel Sandy Bridge). We use mathematical optimization techniques to tune synchronization algorithms to the microarchitectures, identifying three techniques to design and optimize data transfers in our model: single-use, single-step broadcast, and private cache lines.},
	author = {Sabela Ramos and Torsten Hoefler},
	pages = {2824-2837},
	journal = {IEEE Transactions on Parallel and Distributed Systems},
	title = {Cache Line Aware Algorithm Design for Cache-Coherent Architectures},
	volume = {27},
	year = {2016}
}

@inproceedings{abc,
	author = {Nugman Su and Onur Kaya and Sennur Ulukus and Mutlu Koca},
	booktitle = {2015 IEEE Global Communications Conference, GLOBECOM 2015, San Diego, CA, USA},
	title = {Cooperative Multiple Access under Energy Harvesting Constraints.},
	url = {http://dx.doi.org/10.1109/GLOCOM.2014.7417655},
	year = {2015}
}

@mastersthesis{abc,
	author = {Samuel Zehnder},
	school = {143},
	title = {A Scalable Distributed Locking Service using One-Sided Atomic Operations},
	year = {2015}
}

@inproceedings{abc,
	author = {Christopher De Sa and Ce Zhang and Kunle Olukotun and Christopher R{\'e}},
	booktitle = {Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015},
	title = {Rapidly Mixing Gibbs Sampling for a Class of Factor Graphs Using Hierarchy Width.},
	url = {http://papers.nips.cc/paper/5757-rapidly-mixing-gibbs-sampling-for-a-class-of-factor-graphs-using-hierarchy-width},
	venue = {Montreal, Quebec, Canada},
	year = {2015}
}

@inproceedings{abc,
	author = {Christopher De Sa and Ce Zhang and Kunle Olukotun and Christopher R{\'e}},
	booktitle = {Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015},
	title = {Taming the Wild: A Unified Analysis of Hogwild-Style Algorithms.},
	url = {http://papers.nips.cc/paper/5717-taming-the-wild-a-unified-analysis-of-hogwild-style-algorithms},
	venue = {Montreal, Quebec, Canada},
	year = {2015}
}

@inproceedings{abc,
	author = {Lavanya Subramanian and Vivek Seshadri and Arnab Ghosh and Samira Manabi Khan and Onur Mutlu},
	booktitle = {Proceedings of the 48th International Symposium on Microarchitecture, MICRO 2015, Waikiki, HI, USA},
	title = {The application slowdown model: quantifying and controlling the impact of inter-application interference at shared caches and main memory.},
	url = {http://doi.acm.org/10.1145/2830772.2830803},
	year = {2015}
}

@inproceedings{abc,
	author = {Vivek Seshadri and Thomas Mullins and Amirali Boroumand and Onur Mutlu and Phillip B. Gibbons and Michael A. Kozuch and Todd C. Mowry},
	booktitle = {Proceedings of the 48th International Symposium on Microarchitecture, MICRO 2015, Waikiki, HI, USA},
	title = {Gather-scatter DRAM: in-DRAM address translation to improve the spatial locality of non-unit strided accesses.},
	url = {http://doi.acm.org/10.1145/2830772.2830820},
	year = {2015}
}

@inproceedings{abc,
	author = {Jinglei Ren and Jishen Zhao and Samira Manabi Khan and Jongmoo Choi and Yongwei Wu and Onur Mutlu},
	booktitle = {Proceedings of the 48th International Symposium on Microarchitecture, MICRO 2015, Waikiki, HI, USA},
	title = {ThyNVM: enabling software-transparent crash consistency in persistent memory systems.},
	url = {http://doi.acm.org/10.1145/2830772.2830802},
	year = {2015}
}

@inproceedings{abc,
	author = {Onur Mutlu},
	booktitle = {Proceedings of the 8th International Workshop on Network on Chip Architectures, NoCArc {\textquoteright}15, Waikiki, HI, USA},
	title = {Rethinking Memory System Design (along with Interconnects).},
	url = {http://doi.acm.org/10.1145/2835512.2835520},
	year = {2015}
}

@inproceedings{abc,
	author = {Torsten Hoefler and Roberto Belli},
	booktitle = {Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2015, Austin, TX, USA},
	title = {Scientific benchmarking of parallel computing systems: twelve ways to tell the masses when reporting performance results.},
	url = {http://doi.acm.org/10.1145/2807591.2807644},
	year = {2015}
}

@inproceedings{abc,
	author = {Besmira Nushi and Adish Singla and Anja Gruenheid and Erfan Zamanian and Andreas Krause and Donald Kossmann},
	booktitle = {Proceedings of the Third AAAI Conference on Human Computation and Crowdsourcing, HCOMP 2015},
	title = {Crowd Access Path Optimization: Diversity Matters.},
	url = {http://www.aaai.org/ocs/index.php/HCOMP/HCOMP15/paper/view/11577},
	venue = {San Diego, California.},
	year = {2015}
}

@inproceedings{abc,
	author = {Georgios Kathareios and Cyriel Minkenberg and Bogdan Prisacari and Germ{\'a}n Rodr{\'\i}guez and Torsten Hoefler},
	booktitle = {Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2015, Austin, TX, USA},
	title = {Cost-effective diameter-two topologies: analysis and evaluation.},
	url = {http://doi.acm.org/10.1145/2807591.2807652},
	year = {2015}
}

@inproceedings{abc,
	author = {Donghyuk Lee and Lavanya Subramanian and Rachata Ausavarungnirun and Jongmoo Choi and Onur Mutlu},
	booktitle = {2015 International Conference on Parallel Architecture and Compilation, PACT 2015, San Francisco, CA, USA},
	title = {Decoupled Direct Memory Access: Isolating CPU and IO Traffic by Leveraging a Dual-Data-Port DRAM.},
	url = {http://dx.doi.org/10.1109/PACT.2015.51},
	year = {2015}
}

@inproceedings{abc,
	author = {Rachata Ausavarungnirun and Saugata Ghose and Onur Kayiran and Gabriel H. Loh and Chita R. Das and Mahmut T. Kandemir and Onur Mutlu},
	booktitle = {2015 International Conference on Parallel Architecture and Compilation, PACT 2015, San Francisco, CA, USA},
	title = {Exploiting Inter-Warp Heterogeneity to Improve GPGPU Performance.},
	url = {http://dx.doi.org/10.1109/PACT.2015.38},
	year = {2015}
}

@mastersthesis{abc,
	author = {Martynas Pumputis},
	school = {141},
	title = {Message Passing for Programming Languages and Operating Systems},
	year = {2015}
}

@inproceedings{abc,
	author = {Zsolt Istv{\'a}n and David Sidler and Gustavo Alonso},
	booktitle = {25th International Conference on Field Programmable Logic and Applications, FPL 2015, London, United Kingdom},
	title = {Building a distributed key-value store with FPGA-based microservers.},
	url = {http://dx.doi.org/10.1109/FPL.2015.7293967},
	year = {2015}
}

@mastersthesis{abc,
	author = {Andreas M. Nufer},
	school = {139},
	title = {Top-k Reliable Color Set in Uncertain Graphs},
	year = {2015}
}

@mastersthesis{abc,
	author = {Roni Haecki},
	school = {136},
	title = {Consensus on a multicore machine},
	year = {2015}
}

@mastersthesis{abc,
	author = {Kevin Bocksrocker},
	school = {140},
	title = {Efficient Scan in Log-Structured Memory Data Stores},
	year = {2015}
}

@inproceedings{abc,
	author = {Mohammad Fattah and Antti Airola and Rachata Ausavarungnirun and Nima Mirzaei and Pasi Liljeberg and Juha Plosila and Siamak Mohammadi and Tapio Pahikkala and Onur Mutlu and Hannu Tenhunen},
	booktitle = {Proceedings of the 9th International Symposium on Networks-on-Chip, NOCS 2015, Vancouver, BC, Canada},
	title = {A Low-Overhead, Fully-Distributed, Guaranteed-Delivery Routing Algorithm for Faulty Network-on-Chips.},
	url = {http://doi.acm.org/10.1145/2786572.2786591},
	year = {2015}
}

@inproceedings{abc,
	author = {Tobias Grosser and Sven Verdoolaege and Albert Cohen},
	booktitle = {ACM Trans. Program. Lang. Syst.},
	title = {Polyhedral AST Generation Is More Than Scanning Polyhedra.},
	url = {http://doi.acm.org/10.1145/2743016},
	year = {2015}
}

@article{abc,
	author = {Besmira Nushi and Adish Singla and Anja Gruenheid and Erfan Zamanian and Andreas Krause and Donald Kossmann},
	journal = {CoRR},
	title = {Crowd Access Path Optimization: Diversity Matters.},
	url = {http://arxiv.org/abs/1508.01951},
	year = {2015}
}

@mastersthesis{abc,
	author = {Alessandro Dovis},
	school = {133},
	title = {Decoupling of Data Processing Systems over RDMA/InfiniBand},
	year = {2015}
}

@mastersthesis{abc,
	author = {Gustavo Segovia},
	school = {135},
	title = {Distributed Graph Querying with Decoupled Storage and Smart Routing},
	year = {2015}
}

@inproceedings{abc,
	author = {Hastagiri P. Vanchinathan and Andreas Marfurt and Charles-Antoine Robelin and Donald Kossmann and Andreas Krause},
	booktitle = {Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Sydney, NSW, Australia},
	title = {Discovering Valuable items from Massive Data.},
	url = {http://doi.acm.org/10.1145/2783258.2783360},
	year = {2015}
}

@inproceedings{abc,
	author = {Alessandra Loro and Anja Gruenheid and Donald Kossmann and Damien Profeta and Philippe Beaudequin},
	booktitle = {PVLDB},
	title = {Indexing and Selecting Hierarchical Business Logic.},
	url = {http://www.vldb.org/pvldb/vol8/p1656-loro.pdf},
	year = {2015}
}

@inproceedings{abc,
	author = {Arijit Khan and Lei Chen},
	booktitle = {PVLDB},
	title = {On Uncertain Graphs Modeling and Queries.},
	url = {http://www.vldb.org/pvldb/vol8/p2042-khan.pdf},
	year = {2015}
}

@inproceedings{abc,
	author = {Timothy L. Harris and Stefan Kaestle},
	booktitle = {2015 USENIX Annual Technical Conference, USENIX ATC {\textquoteright}15},
	title = {Callisto-RTS: Fine-Grain Parallel Loops.},
	url = {https://www.usenix.org/conference/atc15/technical-session/presentation/harris},
	venue = {Santa Clara, CA, USA},
	year = {2015}
}

@inproceedings{abc,
	author = {Stefan Kaestle and Reto Achermann and Timothy Roscoe and Timothy L. Harris},
	booktitle = {2015 USENIX Annual Technical Conference, USENIX ATC {\textquoteright}15},
	title = {Shoal: Smart Allocation and Replication of Memory For Parallel Programs.},
	url = {https://www.usenix.org/conference/atc15/technical-session/presentation/kaestle},
	venue = {Santa Clara, CA, USA},
	year = {2015}
}

@inproceedings{abc,
	author = {Darko Makreshanski and Justin J. Levandoski and Ryan Stutsman},
	booktitle = {PVLDB},
	title = {To Lock, Swap, or Elide: On the Interplay of Hardware Transactional Memory and Lock-Free Indexing.},
	url = {http://www.vldb.org/pvldb/vol8/p1298-makreshanski.pdf},
	year = {2015}
}

@article{abc,
	author = {Torsten Hoefler and James Dinan and Rajeev Thakur and Brian W. Barrett and Pavan Balaji and William Gropp and Keith D. Underwood},
	journal = {TOPC},
	title = {Remote Memory Access Programming in MPI-3.},
	url = {http://doi.acm.org/10.1145/2780584},
	year = {2015}
}

@phdthesis{abc,
	author = {Simon Loesing},
	school = {22441},
	title = {Architecture for Elastic Database Serv{\^\i}ces},
	year = {2015}
}

@inproceedings{abc,
	author = {Onur Mutlu},
	booktitle = {2015 International Conference on Embedded Computer Systems: Architectures, Modeling, and Simulation, SAMOS 2015, Samos, Greece},
	title = {Rethinking memory system design for data-intensive computing.},
	url = {http://dx.doi.org/10.1109/SAMOS.2015.7363650},
	year = {2015}
}

@inproceedings{abc,
	author = {Claude Barthels and Simon Loesing and Gustavo Alonso and Donald Kossmann},
	booktitle = {Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data, Melbourne, Victoria, Australia},
	title = {Rack-Scale In-Memory Join Processing using RDMA.},
	url = {http://doi.acm.org/10.1145/2723372.2750547},
	year = {2015}
}

@inproceedings{abc,
	author = {Moinuddin K. Qureshi and Dae-Hyun Kim and Samira Manabi Khan and Prashant J. Nair and Onur Mutlu},
	booktitle = {45th Annual IEEE/IFIP International Conference on Dependable Systems and Networks, DSN 2015, Rio de Janeiro, Brazil},
	title = {AVATAR: A Variable-Retention-Time (VRT) Aware Refresh for DRAM Systems.},
	url = {http://dx.doi.org/10.1109/DSN.2015.58},
	year = {2015}
}

@article{abc,
	author = {Hastagiri P. Vanchinathan and Andreas Marfurt and Charles-Antoine Robelin and Donald Kossmann and Andreas Krause},
	journal = {CoRR},
	title = {Discovering Valuable Items from Massive Data.},
	url = {http://arxiv.org/abs/1506.00935},
	year = {2015}
}

@inproceedings{abc,
	abstract = {Modern Graphics Processing Units (GPUs) are well provisioned to support the concurrent execution of thousands of threads. Unfortunately, diUerent bottlenecks during execution and heterogeneous application requirements create imbalances in utilization of resources in the 
 cores. For example, when a GPU is bottlenecked by the available on-chip memory bandwidth, its computational resources are often overwhelmingly idle, waiting for data from memory to arrive. This paper introduces the Core-Assisted Bottleneck Acceleration (CABA) framework that employs idle on-chip resources to alleviate different bottlenecks in GPU execution. CABA provides flexible mechanisms to automatically generate {\textquotedblleft}assist warps{\textquotedblright} that execute on GPU cores to perform specific tasks that can improve GPU performance and 
 efficiency. CABA enables the use of idle computational units and pipelines to alleviate the memory bandwidth bottleneck, e.g., by using assist warps to perform data compression to transfer less data from memory. Conversely, the same framework can be employed to handle cases where the GPU is bottlenecked by the available computational units, in which case the memory pipelines are idle and can be used by CABA to speed up computation, e.g., by performing memoization using assist warps. We provide a comprehensive design and evaluation of CABA to perform effective and flexible data compression in the GPU memory hierarchy to alleviate the memory bandwidth bottleneck. Our extensive evaluations show that CABA, when used to implement data compression, provides an average performance improvement of 41.7\% (as high as 2.6X) across a variety of memory-bandwidth-sensitive GPGPU applications.},
	author = {Nandita Vijaykumar and Gennady Pekhimenko and Adwait Jog and Abhishek Bhowmick and Rachata Ausavarungnirun and Chita R. Das and Mahmut T. Kandemir and Todd C. Mowry and Onur Mutlu},
	booktitle = {Proceedings of the 42nd Annual International Symposium on Computer Architecture},
	title = {A case for core-assisted bottleneck acceleration in GPUs: enabling flexible data compression with assist warps.},
	url = {http://doi.acm.org/10.1145/2749469.2750399},
	venue = {Portland, OR, USA},
	year = {2015}
}

@inproceedings{abc,
	author = {Lucas Braun and Thomas Etter and Georgios Gasparis and Martin Kaufmann and Donald Kossmann and Daniel Widmer and Aharon Avitzur and Anthony Iliopoulos and Eliezer Levy and Ning Liang},
	booktitle = {Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data, Melbourne, Victoria, Australia},
	title = {Analytics in Motion: High Performance Event-Processing AND Real-Time Analytics in the Same Database.},
	url = {http://doi.acm.org/10.1145/2723372.2742783},
	year = {2015}
}

@inproceedings{abc,
	author = {Taeho Lee and Christos Pappas and Cristina Basescu and Jun Han and Torsten Hoefler and Adrian Perrig},
	booktitle = {The 10th International Conference on Future Internet, CFI {\textquoteright}15, Seoul, Republic of Korea},
	title = {Source-Based Path Selection: The Data Plane Perspective.},
	url = {http://doi.acm.org/10.1145/2775088.2775090},
	year = {2015}
}

@inproceedings{abc,
	author = {Junwhan Ahn and Sungjoo Yoo and Onur Mutlu and Kiyoung Choi},
	booktitle = {Proceedings of the 42nd Annual International Symposium on Computer Architecture, Portland, OR, USA},
	title = {PIM-enabled instructions: a low-overhead, locality-aware processing-in-memory architecture.},
	url = {http://doi.acm.org/10.1145/2749469.2750385},
	year = {2015}
}

@inproceedings{abc,
	author = {Anja Gruenheid and Donald Kossmann and Theodoros Rekatsinas and Divesh Srivastava},
	booktitle = {Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data, Melbourne, Victoria, Australia},
	title = {StoryPivot: Comparing and Contrasting Story Evolution.},
	url = {http://doi.acm.org/10.1145/2723372.2735356},
	year = {2015}
}

@inproceedings{abc,
	abstract = {Bi-temporal databases support system (transaction) and application time, enabling users to query the history as recorded today and as it was known in the past. In this paper, we study windows over both system and application time, i.e., bi-temporal windows. We propose a two-dimensional index that supports one-time and continuous queries over fixed and sliding bi-temporal windows, covering static and streaming data. We demonstrate the advantages of the proposed index compared to the state-of-the-art in terms of query performance, index update overhead and space footprint.},
	author = {Chang Ge and Martin Kaufmann and Lukasz Golab and Peter M. Fischer and Anil K. Goel},
	booktitle = {Proceedings of the 27th International Conference on Scientific and Statistical Database Management, SSDBM {\textquoteright}15},
	title = {Indexing bi-temporal windows.},
	url = {http://doi.acm.org/10.1145/2791347.2791373},
	venue = {La Jolla, CA, USA},
	year = {2015}
}

@inproceedings{abc,
	author = {Vivek Seshadri and Gennady Pekhimenko and Olatunji Ruwase and Onur Mutlu and Phillip B. Gibbons and Michael A. Kozuch and Todd C. Mowry and Trishul M. Chilimbi},
	booktitle = {Proceedings of the 42nd Annual International Symposium on Computer Architecture, Portland, OR, USA},
	title = {Page overlays: an enhanced virtual memory framework to enable fine-grained memory management.},
	url = {http://doi.acm.org/10.1145/2749469.2750379},
	year = {2015}
}

@inproceedings{abc,
	author = {Philip A. Bernstein and Sudipto Das and Bailu Ding and Markus Pilman},
	booktitle = {Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data, Melbourne, Victoria, Australia},
	title = {Optimizing Optimistic Concurrency Control for Tree-Structured, Log-Structured Databases.},
	url = {http://doi.acm.org/10.1145/2723372.2737788},
	year = {2015}
}

@inproceedings{abc,
	author = {Junwhan Ahn and Sungpack Hong and Sungjoo Yoo and Onur Mutlu and Kiyoung Choi},
	booktitle = {Proceedings of the 42nd Annual International Symposium on Computer Architecture, Portland, OR, USA},
	title = {A scalable processing-in-memory accelerator for parallel graph processing.},
	url = {http://doi.acm.org/10.1145/2749469.2750386},
	year = {2015}
}

@inproceedings{abc,
	author = {Tobias Gysi and Tobias Grosser and Torsten Hoefler},
	booktitle = {Proceedings of the 29th ACM on International Conference on Supercomputing, ICS{\textquoteright}15, Newport Beach/Irvine, CA, USA},
	title = {MODESTO: Data-centric Analytic Optimization of Complex Stencil Programs on Heterogeneous Architectures.},
	url = {http://doi.acm.org/10.1145/2751205.2751223},
	year = {2015}
}

@inproceedings{abc,
	author = {Maciej Besta and Torsten Hoefler},
	booktitle = {Proceedings of the 29th ACM on International Conference on Supercomputing, ICS{\textquoteright}15, Newport Beach/Irvine, CA, USA},
	title = {Active Access: A Mechanism for High-Performance Distributed Data-Centric Computations.},
	url = {http://doi.acm.org/10.1145/2751205.2751219},
	year = {2015}
}

@inproceedings{abc,
	author = {Tobias Grosser and Sebastian Pop and Louis-No{\"e}l Pouchet and P. Sadayappan and Sebastian Pop},
	booktitle = {Proceedings of the 29th ACM on International Conference on Supercomputing, ICS{\textquoteright}15, Newport Beach/Irvine, CA, USA},
	title = {Optimistic Delinearization of Parametrically Sized Arrays.},
	url = {http://doi.acm.org/10.1145/2751205.2751248},
	year = {2015}
}

@inproceedings{abc,
	author = {Justin Meza and Qiang Wu and Sanjev Kumar and Onur Mutlu},
	booktitle = {Proceedings of the 2015 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems, Portland, OR, USA},
	title = {A Large-Scale Study of Flash Memory Failures in the Field.},
	url = {http://doi.acm.org/10.1145/2745844.2745848},
	year = {2015}
}

@inproceedings{abc,
	author = {Sergei Shudler and Alexandru Calotoiu and Torsten Hoefler and Alexandre Strube and Felix Wolf},
	booktitle = {Proceedings of the 29th ACM on International Conference on Supercomputing, ICS{\textquoteright}15, Newport Beach/Irvine, CA, USA},
	title = {Exascaling Your Library: Will Your Implementation Meet Your Expectations?},
	url = {http://doi.acm.org/10.1145/2751205.2751216},
	year = {2015}
}

@inproceedings{abc,
	abstract = {The online communities available on the Web have shown to be significantly interactive and capable of collectively solving difficult tasks. Nevertheless, it is still a challenge to decide how a task should be dispatched through the network due to the high diversity of the communities and the dynamically changing expertise and social availability of their members. We introduce CrowdSTAR, a framework designed to route tasks across and within online crowds. CrowdSTAR indexes the topic-specific expertise and social features of the crowd contributors and then uses a routing algorithm, which suggests the best sources to ask based on the knowledge vs. availability trade-offs. We experimented with the proposed framework for question and answering scenarios by using two popular social networks as crowd candidates: Twitter and Quora.},
	author = {Besmira Nushi and Omar Alonso and Martin Hentschel and Vasileios Kandylas},
	booktitle = {Engineering the Web in the Big Data Era - 15th International Conference, ICWE 2015},
	title = {CrowdSTAR: A Social Task Routing Framework for Online Communities.},
	url = {http://dx.doi.org/10.1007/978-3-319-19890-3_15},
	venue = {Rotterdam, The Netherlands},
	year = {2015}
}

@inproceedings{abc,
	author = {Maciej Besta and Torsten Hoefler},
	booktitle = {Proceedings of the 24th International Symposium on High-Performance Parallel and Distributed Computing, HPDC 2015, Portland, OR, USA},
	title = {Accelerating Irregular Computations with Hardware Transactional Memory and Active Messages.},
	url = {http://doi.acm.org/10.1145/2749246.2749263},
	year = {2015}
}

@inproceedings{abc,
	author = {Justin Meza and Qiang Wu and Sanjeev Kumar and Onur Mutlu},
	booktitle = {45th Annual IEEE/IFIP International Conference on Dependable Systems and Networks, DSN 2015, Rio de Janeiro, Brazil},
	title = {Revisiting Memory Errors in Large-Scale Production Data Centers: Analysis and Modeling of New Trends from the Field.},
	url = {http://dx.doi.org/10.1109/DSN.2015.57},
	year = {2015}
}

@inproceedings{abc,
	author = {Sabela Ramos and Torsten Hoefler},
	booktitle = {Proceedings of the 24th International Symposium on High-Performance Parallel and Distributed Computing, HPDC 2015, Portland, OR, USA},
	title = {Cache Line Aware Optimizations for ccNUMA Systems.},
	url = {http://doi.acm.org/10.1145/2749246.2749256},
	year = {2015}
}

@inproceedings{abc,
	author = {Simon Loesing and Markus Pilman and Thomas Etter and Donald Kossmann},
	booktitle = {Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data, Melbourne, Victoria, Australia},
	title = {On the Design and Scalability of Distributed Shared-Data Databases.},
	url = {http://doi.acm.org/10.1145/2723372.2751519},
	year = {2015}
}

@inproceedings{abc,
	author = {Yu Cai and Yixin Luo and Saugata Ghose and Onur Mutlu},
	booktitle = {45th Annual IEEE/IFIP International Conference on Dependable Systems and Networks, DSN 2015, Rio de Janeiro, Brazil},
	title = {Read Disturb Errors in MLC NAND Flash Memory: Characterization, Mitigation, and Recovery.},
	url = {http://dx.doi.org/10.1109/DSN.2015.49},
	year = {2015}
}

@inproceedings{abc,
	author = {Marius Poke and Torsten Hoefler},
	booktitle = {Proceedings of the 24th International Symposium on High-Performance Parallel and Distributed Computing, HPDC 2015, Portland, OR, USA},
	title = {DARE: High-Performance State Machine Replication on RDMA Networks.},
	url = {http://doi.acm.org/10.1145/2749246.2749267},
	year = {2015}
}

@inproceedings{abc,
	author = {Ionel Gog and Jana Giceva and Malte Schwarzkopf and Kapil Vaswani and Dimitrios Vytiniotis and G. Ramalingam and Manuel Costa and Derek Gordon Murray and Steven Hand and Michael Isard},
	booktitle = {15th Workshop on Hot Topics in Operating Systems, HotOS XV, Kartause Ittingen, Switzerland},
	title = {Broom: Sweeping Out Garbage Collection from Big Data Systems.},
	url = {https://www.usenix.org/conference/hotos15/workshop-program/presentation/gog},
	year = {2015}
}

@inproceedings{abc,
	author = {Torsten Hoefler and Robert B. Ross and Timothy Roscoe},
	booktitle = {15th Workshop on Hot Topics in Operating Systems, HotOS XV, Kartause Ittingen, Switzerland},
	title = {Distributing the Data Plane for Remote Storage Access.},
	url = {https://www.usenix.org/conference/hotos15/workshop-program/presentation/hoefler},
	year = {2015}
}

@inproceedings{abc,
	author = {Yixin Luo and Yu Cai and Saugata Ghose and Jongmoo Choi and Onur Mutlu},
	booktitle = {IEEE 31st Symposium on Mass Storage Systems and Technologies, MSST 2015, Santa Clara, CA, USA},
	title = {WARM: Improving NAND flash memory lifetime with write-hotness aware retention management.},
	url = {http://dx.doi.org/10.1109/MSST.2015.7208284},
	year = {2015}
}

@inproceedings{abc,
	author = {Simon Gerber and Gerd Zellweger and Reto Achermann and Kornilios Kourtis and Timothy Roscoe and Dejan S. Milojicic},
	booktitle = {15th Workshop on Hot Topics in Operating Systems, HotOS XV, Kartause Ittingen, Switzerland},
	title = {Not Your Parents{\textquoteright} Physical Address Space.},
	url = {https://www.usenix.org/conference/hotos15/workshop-program/presentation/gerber},
	year = {2015}
}

@inproceedings{abc,
	author = {Dongwoo Kang and Seungjae Baek and Jongmoo Choi and Donghee Lee and Sam H. Noh and Onur Mutlu},
	booktitle = {IEEE 31st Symposium on Mass Storage Systems and Technologies, MSST 2015, Santa Clara, CA, USA},
	title = {Amnesic cache management for non-volatile memory.},
	url = {http://dx.doi.org/10.1109/MSST.2015.7208291},
	year = {2015}
}

@inproceedings{abc,
	author = {David Sidler and Gustavo Alonso and Michaela Blott and Kimon Karras and Kees A. Vissers and Raymond Carley},
	booktitle = {23rd IEEE Annual International Symposium on Field-Programmable Custom Computing Machines, FCCM 2015, Vancouver, BC, Canada},
	title = {Scalable 10Gbps TCP/IP Stack Architecture for Reconfigurable Hardware.},
	url = {http://dx.doi.org/10.1109/FCCM.2015.12},
	year = {2015}
}

@inproceedings{abc,
	author = {Stefan Hadjis and Firas Abuzaid and Ce Zhang and Christopher R{\'e}},
	booktitle = {Proceedings of the Fourth Workshop on Data analytics in the Cloud, DanaC 2015, Melbourne, VIC, Australia},
	title = {Caffe con Troll: Shallow Ideas to Speed Up Deep Learning.},
	url = {http://doi.acm.org/10.1145/2799562.2799641},
	year = {2015}
}

@inproceedings{abc,
	author = {Roberto Belli and Torsten Hoefler},
	booktitle = {2015 IEEE International Parallel and Distributed Processing Symposium, IPDPS 2015, Hyderabad, India},
	title = {Notified Access: Extending Remote Memory Access Programming Models for Producer-Consumer Synchronization.},
	url = {http://dx.doi.org/10.1109/IPDPS.2015.30},
	year = {2015}
}

@inproceedings{abc,
	author = {Torsten Hoefler and Laxmikant V. Kale},
	booktitle = {2015 IEEE International Parallel and Distributed Processing Symposium Workshop, IPDPS 2015, Hyderabad, India},
	title = {HIPS-LSPP Keynotes.},
	url = {http://dx.doi.org/10.1109/IPDPSW.2015.173},
	year = {2015}
}

@phdthesis{abc,
	author = {Tahmineh Sanamrad},
	school = {22450},
	title = {Encrypting Databases in the Cloud Threats and Solutions},
	year = {2015}
}

@inproceedings{abc,
	author = {Martin Kaufmann and Peter M. Fischer and Norman May and Chang Ge and Anil K. Goel and Donald Kossmann},
	booktitle = {31st IEEE International Conference on Data Engineering, ICDE 2015, Seoul, South Korea},
	title = {Bi-temporal Timeline Index: A data structure for Processing Queries on bi-temporal data.},
	url = {http://dx.doi.org/10.1109/ICDE.2015.7113307},
	year = {2015}
}

@inproceedings{abc,
	author = {Arvind Arasu and Ken Eguro and Manas Joglekar and Raghav Kaushik and Donald Kossmann and Ravishankar Ramamurthy},
	booktitle = {31st IEEE International Conference on Data Engineering, ICDE 2015, Seoul, South Korea},
	title = {Transaction processing on confidential data using cipherbase.},
	url = {http://dx.doi.org/10.1109/ICDE.2015.7113304},
	year = {2015}
}

@article{abc,
	author = {Zsolt Istv{\'a}n and Gustavo Alonso and Michaela Blott and Kees A. Vissers},
	journal = {TRETS},
	title = {A Hash Table for Line-Rate Data Processing.},
	url = {http://doi.acm.org/10.1145/2629582},
	year = {2015}
}

@inproceedings{abc,
	author = {Hui Wang and Canturk Isci and Lavanya Subramanian and Jongmoo Choi and Depei Qian and Onur Mutlu},
	booktitle = {Proceedings of the 11th ACM SIGPLAN/SIGOPS International Conference on Virtual Execution Environments, Istanbul, Turkey},
	title = {A-DRM: Architecture-aware Distributed Resource Management of Virtualized Clusters.},
	url = {http://doi.acm.org/10.1145/2731186.2731202},
	year = {2015}
}

@inproceedings{abc,
	author = {Yu Cai and Ken Mai and Onur Mutlu},
	booktitle = {Sixteenth International Symposium on Quality Electronic Design, ISQED 2015, Santa Clara, CA, USA},
	title = {Comparative evaluation of FPGA and ASIC implementations of bufferless and buffered routing algorithms for on-chip networks.},
	url = {http://dx.doi.org/10.1109/ISQED.2015.7085472},
	year = {2015}
}

@article{abc,
	author = {Tudor-Ioan Salomie and Gustavo Alonso},
	journal = {IEEE Data Eng. Bull.},
	title = {Scaling Off-the-Shelf Databases with Vela: An approach based on Virtualization and Replication.},
	url = {http://sites.computer.org/debull/A15mar/p58.pdf},
	year = {2015}
}

@inproceedings{abc,
	author = {Gennady Pekhimenko and Tyler Huberty and Rui Cai and Onur Mutlu and Phillip B. Gibbons and Michael A. Kozuch and Todd C. Mowry},
	booktitle = {21st IEEE International Symposium on High Performance Computer Architecture, HPCA 2015, Burlingame, CA, USA},
	title = {Exploiting compressed block size as an indicator of future reuse.},
	url = {http://dx.doi.org/10.1109/HPCA.2015.7056021},
	year = {2015}
}

@inproceedings{abc,
	author = {Yu Cai and Yixin Luo and Erich F. Haratsch and Ken Mai and Onur Mutlu},
	booktitle = {21st IEEE International Symposium on High Performance Computer Architecture, HPCA 2015, Burlingame, CA, USA},
	title = {Data retention in MLC NAND flash memory: Characterization, optimization, and recovery.},
	url = {http://dx.doi.org/10.1109/HPCA.2015.7056062},
	year = {2015}
}

@inproceedings{abc,
	author = {Donghyuk Lee and Yoongu Kim and Gennady Pekhimenko and Samira Manabi Khan and Vivek Seshadri and Kevin Kai-Wei Chang and Onur Mutlu},
	booktitle = {21st IEEE International Symposium on High Performance Computer Architecture, HPCA 2015, Burlingame, CA, USA},
	title = {Adaptive-latency DRAM: Optimizing DRAM timing for the common-case.},
	url = {http://dx.doi.org/10.1109/HPCA.2015.7056057},
	year = {2015}
}

@article{abc,
	author = {Kamil Iskra and Torsten Hoefler},
	journal = {IJHPCA},
	title = {Operating systems and runtime environments on supercomputers.},
	url = {http://dx.doi.org/10.1177/1094342014560666},
	year = {2015}
}

@article{abc,
	author = {Louis Woods and Gustavo Alonso and Jens Teubner},
	journal = {TRETS},
	title = {Parallelizing Data Processing on FPGAs with Shifter Lists.},
	url = {http://doi.acm.org/10.1145/2629551},
	year = {2015}
}

@mastersthesis{abc,
	author = {Philipp Rohr},
	school = {128},
	title = {Temporal Graph Data Management for in-memory Database Systems},
	year = {2015}
}

@inproceedings{abc,
	author = {Jaeho Shin and Sen Wu and Feiran Wang and Christopher De Sa and Ce Zhang and Christopher R{\'e}},
	booktitle = {PVLDB},
	title = {Incremental Knowledge Base Construction Using DeepDive.},
	url = {http://www.vldb.org/pvldb/vol8/p1310-shin.pdf},
	year = {2015}
}

@article{abc,
	author = {Sen Wu and Ce Zhang and Feiran Wang and Christopher R{\'e}},
	journal = {CoRR},
	title = {Incremental Knowledge Base Construction Using DeepDive.},
	url = {http://arxiv.org/abs/1502.00731},
	year = {2015}
}

@article{abc,
	author = {Christopher De Sa and Ce Zhang and Kunle Olukotun and Christopher R{\'e}},
	journal = {CoRR},
	title = {Rapidly Mixing Gibbs Sampling for a Class of Factor Graphs Using Hierarchy Width.},
	url = {http://arxiv.org/abs/1510.00756},
	year = {2015}
}

@article{abc,
	author = {Yuke Zhu and Ce Zhang and Christopher R{\'e} and Li Fei-Fei},
	journal = {CoRR},
	title = {Building a Large-scale Multimodal Knowledge Base for Visual Question Answering.},
	url = {http://arxiv.org/abs/1507.05670},
	year = {2015}
}

@article{abc,
	author = {Yang Li and Jongmoo Choi and Jin Sun and Saugata Ghose and Hui Wang and Justin Meza and Jinglei Ren and Onur Mutlu},
	journal = {CoRR},
	title = {Managing Hybrid Main Memories with a Page-Utility Driven Performance Model.},
	url = {http://arxiv.org/abs/1507.03303},
	year = {2015}
}

@inproceedings{abc,
	author = {Gennady Pekhimenko and Evgeny Bolotin and Mike O{\textquoteright}Connor and Onur Mutlu and Todd C. Mowry and Stephen W. Keckler},
	booktitle = {Computer Architecture Letters},
	title = {Toggle-Aware Compression for GPUs.},
	url = {http://dx.doi.org/10.1109/LCA.2015.2430853},
	year = {2015}
}

@inproceedings{abc,
	author = {Vivek Seshadri and Kevin Hsieh and Amirali Boroumand and Donghyuk Lee and Michael A. Kozuch and Onur Mutlu and Phillip B. Gibbons and Todd C. Mowry},
	booktitle = {Computer Architecture Letters},
	title = {Fast Bulk Bitwise AND and OR in DRAM.},
	url = {http://dx.doi.org/10.1109/LCA.2015.2434872},
	year = {2015}
}

@inproceedings{abc,
	author = {Ankit Singla and Balakrishnan Chandrasekaran and Brighten Godfrey and Bruce M. Maggs},
	booktitle = {CoRR},
	title = {Towards a Speed of Light Internet.},
	url = {http://arxiv.org/abs/1505.03449},
	year = {2015}
}

@inproceedings{abc,
	author = {Cagri Balkesen and Jens Teubner and Gustavo Alonso and M. Tamer {\"O}zsu},
	booktitle = {IEEE Trans. Knowl. Data Eng.},
	title = {Main-Memory Hash Joins on Modern Processor Architectures.},
	url = {http://doi.ieeecomputersociety.org/10.1109/TKDE.2014.2313874},
	year = {2015}
}

@article{abc,
	author = {Hiroyuki Usui and Lavanya Subramanian and Kevin Kai-Wei Chang and Onur Mutlu},
	journal = {CoRR},
	title = {SQUASH: Simple QoS-Aware High-Performance Memory Scheduler for Heterogeneous Systems with Hardware Accelerators.},
	url = {http://arxiv.org/abs/1505.07502},
	year = {2015}
}

@inproceedings{abc,
	author = {Youyou Lu and Jiwu Shu and Jia Guo and Shuai Li and Onur Mutlu},
	booktitle = {IEEE Trans. Computers},
	title = {High-Performance and Lightweight Transaction Support in Flash-Based SSDs.},
	url = {http://dx.doi.org/10.1109/TC.2015.2389828},
	year = {2015}
}

@inproceedings{abc,
	author = {Onur Mutlu and Richard A. Belgard},
	booktitle = {IEEE Micro},
	title = {Introducing the MICRO Test of Time Awards: Concept, Process, 2014 Winners, and the Future.},
	url = {http://doi.ieeecomputersociety.org/10.1109/MM.2015.32},
	year = {2015}
}

@article{abc,
	author = {Firas Abuzaid and Stefan Hadjis and Ce Zhang and Christopher R{\'e}},
	journal = {CoRR},
	title = {Caffe con Troll: Shallow Ideas to Speed Up Deep Learning.},
	url = {http://arxiv.org/abs/1504.04343},
	year = {2015}
}

@article{abc,
	author = {Hongyi Xin and Richard Zhu and Sunny Nahar and John Emmons and Gennady Pekhimenko and Carl Kingsford and Can Alkan and Onur Mutlu},
	journal = {CoRR},
	title = {Optimal Seed Solver: Optimizing Seed Selection in Read Mapping.},
	url = {http://arxiv.org/abs/1506.08235},
	year = {2015}
}

@article{abc,
	author = {Lavanya Subramanian and Donghyuk Lee and Vivek Seshadri and Harsha Rastogi and Onur Mutlu},
	journal = {CoRR},
	title = {The Blacklisting Memory Scheduler: Balancing Performance, Fairness and Complexity.},
	url = {http://arxiv.org/abs/1504.00390},
	year = {2015}
}

@article{abc,
	author = {Christopher De Sa and Ce Zhang and Kunle Olukotun and Christopher R{\'e}},
	journal = {CoRR},
	title = {Taming the Wild: A Unified Analysis of Hogwild!-Style Algorithms.},
	url = {http://arxiv.org/abs/1506.06438},
	year = {2015}
}

@inproceedings{abc,
	author = {Onur {\"U}lgen and Mutlu Avci},
	booktitle = {Computer Languages, Systems  Structures},
	title = {The intelligent memory allocator selector.},
	url = {http://dx.doi.org/10.1016/j.cl.2015.09.003},
	year = {2015}
}

@inproceedings{abc,
	author = {Hongyi Xin and John Greth and John Emmons and Gennady Pekhimenko and Carl Kingsford and Can Alkan and Onur Mutlu},
	booktitle = {Bioinformatics},
	title = {Shifted Hamming distance: a fast and accurate SIMD-friendly filter to accelerate alignment verification in read mapping.},
	url = {http://dx.doi.org/10.1093/bioinformatics/btu856},
	year = {2015}
}

@article{abc,
	author = {Donghyuk Lee and Gennady Pekhimenko and Samira Manabi Khan and Saugata Ghose and Onur Mutlu},
	journal = {CoRR},
	title = {Simultaneous Multi Layer Access: A High Bandwidth and Low Cost 3D-Stacked Memory Interface.},
	url = {http://arxiv.org/abs/1506.03160},
	year = {2015}
}

@inproceedings{abc,
	author = {Carsten Binnig and Stefan Hildenbrand and Franz F{\"a}rber and Donald Kossmann and Juchang Lee and Norman May},
	booktitle = {VLDB J.},
	title = {Distributed snapshot isolation: global transactions pay globally, local transactions pay locally.},
	url = {http://dx.doi.org/10.1007/s00778-014-0359-9},
	year = {2014}
}

@inproceedings{abc,
	author = {Jishen Zhao and Onur Mutlu and Yuan Xie},
	booktitle = {47th Annual IEEE/ACM International Symposium on Microarchitecture, MICRO 2014, Cambridge, United Kingdom},
	title = {FIRM: Fair and High-Performance Memory Control for Persistent Memory Systems.},
	url = {http://dx.doi.org/10.1109/MICRO.2014.47},
	year = {2014}
}

@inproceedings{abc,
	author = {Onur Kayiran and Nachiappan Chidambaram Nachiappan and Adwait Jog and Rachata Ausavarungnirun and Mahmut T. Kandemir and Gabriel H. Loh and Onur Mutlu and Chita R. Das},
	booktitle = {47th Annual IEEE/ACM International Symposium on Microarchitecture, MICRO 2014, Cambridge, United Kingdom},
	title = {Managing GPU Concurrency in Heterogeneous Architectures.},
	url = {http://dx.doi.org/10.1109/MICRO.2014.62},
	year = {2014}
}

@inproceedings{abc,
	author = {Yingbo Zhou and Utkarsh Porwal and Ce Zhang and Hung Q. Ngo and Long Nguyen and Christopher R{\'e} and Venu Govindaraju},
	booktitle = {Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014},
	title = {Parallel Feature Selection Inspired by Group Testing.},
	url = {http://papers.nips.cc/paper/5296-parallel-feature-selection-inspired-by-group-testing},
	venue = {Montreal, Quebec, Canada},
	year = {2014}
}

@inproceedings{abc,
	author = {Louis Woods and Zsolt Istv{\'a}n and Gustavo Alonso},
	booktitle = {PVLDB},
	title = {Ibex - An Intelligent Storage Engine with Support for Advanced SQL Off-loading.},
	url = {http://www.vldb.org/pvldb/vol7/p963-woods.pdf},
	year = {2014}
}

@inproceedings{abc,
	author = {Jana Giceva and Gustavo Alonso and Timothy Roscoe and Timothy L. Harris},
	booktitle = {PVLDB},
	title = {Deployment of Query Plans on Multicores.},
	url = {http://www.vldb.org/pvldb/vol8/p233-giceva.pdf},
	year = {2014}
}

@phdthesis{abc,
	author = {Georgios Giannikis},
	school = {22063},
	title = {Work Sharing Data Processing Systems},
	year = {2014}
}

@inproceedings{abc,
	author = {Rachata Ausavarungnirun and Chris Fallin and Xiangyao Yu and Kevin Kai-Wei Chang and Greg Nazario and Reetuparna Das and Gabriel H. Loh and Onur Mutlu},
	booktitle = {26th IEEE International Symposium on Computer Architecture and High Performance Computing, SBAC-PAD 2014, Paris, France},
	title = {Design and Evaluation of Hierarchical Rings with Deflection Routing.},
	url = {http://dx.doi.org/10.1109/SBAC-PAD.2014.31},
	year = {2014}
}

@inproceedings{abc,
	author = {Stefan C. M{\"u}ller and Gustavo Alonso and Adam Amara and Andr{\'e} Csillaghy},
	booktitle = {11th USENIX Symposium on Operating Systems Design and Implementation, OSDI {\textquoteright}14, Broomfield, CO, USA},
	title = {Pydron: Semi-Automatic Parallelization for Multi-Core and the Cloud.},
	url = {https://www.usenix.org/conference/osdi14/technical-sessions/presentation/muller},
	year = {2014}
}

@inproceedings{abc,
	author = {Andrew Baumann and Chris Hawblitzel and Kornilios Kourtis and Timothy L. Harris and Timothy Roscoe},
	booktitle = {2014 Conference on Timely Results in Operating Systems, TRIOS {\textquoteright}14, Broomfield, CO, USA},
	title = {Cosh: Clear OS Data Sharing In An Incoherent World.},
	url = {https://www.usenix.org/conference/trios14/technical-sessions/presentation/baumann},
	year = {2014}
}

@inproceedings{abc,
	author = {Gerd Zellweger and Simon Gerber and Kornilios Kourtis and Timothy Roscoe},
	booktitle = {11th USENIX Symposium on Operating Systems Design and Implementation, OSDI {\textquoteright}14, Broomfield, CO, USA},
	title = {Decoupling Cores, Kernels, and Operating Systems.},
	url = {https://www.usenix.org/conference/osdi14/technical-sessions/presentation/zellweger},
	year = {2014}
}

@inproceedings{abc,
	abstract = {For many Internet services, reducing latency improves the user experience and increases revenue for the service provider. While in principle latencies could nearly match the speed of light, we find that infrastructural inefficiencies and protocol overheads cause today{\textquoteright}s Internet to be much slower than this bound: typically by more than one, and often, by more than two orders of magnitude. Bridging this large gap would not only add value to today{\textquoteright}s Internet applications, but could also open the door to exciting new applications. Thus, we propose a grand challenge for the networking research community: a speed-of-light Internet. To inform this research agenda, we investigate the causes of latency inflation in the Internet across the network stack. We also discuss a few broad avenues for latency improvement.},
	author = {Ankit Singla and Balakrishnan Chandrasekaran and Brighten Godfrey and Bruce M. Maggs},
	booktitle = {Proceedings of the 13th ACM Workshop on Hot Topics in Networks, HotNets-XIII},
	title = {The Internet at the Speed of Light.},
	url = {http://doi.acm.org/10.1145/2670518.2673876},
	venue = {Los Angeles, CA, USA},
	year = {2014}
}

@inproceedings{abc,
	author = {Simon Peter and Jialin Li and Irene Zhang and Dan R. K. Ports and Doug Woos and Arvind Krishnamurthy and Thomas E. Anderson and Timothy Roscoe},
	booktitle = {11th USENIX Symposium on Operating Systems Design and Implementation, OSDI {\textquoteright}14, Broomfield, CO, USA},
	title = {Arrakis: The Operating System is the Control Plane.},
	url = {https://www.usenix.org/conference/osdi14/technical-sessions/presentation/peter},
	year = {2014}
}

@inproceedings{abc,
	author = {Youyou Lu and Jiwu Shu and Long Sun and Onur Mutlu},
	booktitle = {32nd IEEE International Conference on Computer Design, ICCD 2014, Seoul, South Korea},
	title = {Loose-Ordering Consistency for persistent memory.},
	url = {http://dx.doi.org/10.1109/ICCD.2014.6974684},
	year = {2014}
}

@mastersthesis{abc,
	author = {Reto Achermann},
	school = {118},
	title = {Message Passing and Bulk Transport on Heterogeneous Multiprocessors},
	year = {2014}
}

@inproceedings{abc,
	author = {Chris Fallin and Chris Wilkerson and Onur Mutlu},
	booktitle = {32nd IEEE International Conference on Computer Design, ICCD 2014, Seoul, South Korea},
	title = {The heterogeneous block architecture.},
	url = {http://dx.doi.org/10.1109/ICCD.2014.6974710},
	year = {2014}
}

@inproceedings{abc,
	author = {Lavanya Subramanian and Donghyuk Lee and Vivek Seshadri and Harsha Rastogi and Onur Mutlu},
	booktitle = {32nd IEEE International Conference on Computer Design, ICCD 2014, Seoul, South Korea},
	title = {The Blacklisting Memory Scheduler: Achieving high performance and fairness at low cost.},
	url = {http://dx.doi.org/10.1109/ICCD.2014.6974655},
	year = {2014}
}

@mastersthesis{abc,
	author = {Raphael Fuchs},
	school = {119},
	title = {Hardware Transactional Memory and Message Passing},
	year = {2014}
}

@inproceedings{abc,
	author = {Stefan C. Muller and Gustavo Alonso and Andr{\'e} Csillaghy},
	booktitle = {IEEE Computer},
	title = {Scaling Astroinformatics: Python + Automatic Parallelization.},
	url = {http://dx.doi.org/10.1109/MC.2014.262},
	year = {2014}
}

@inproceedings{abc,
	author = {Tobias Grosser and Sven Verdoolaege and Albert Cohen and P. Sadayappan},
	booktitle = {Parallel Processing Letters},
	title = {The Relation Between Diamond Tiling and Hexagonal Tiling.},
	url = {http://dx.doi.org/10.1142/S0129626414410023},
	year = {2014}
}

@mastersthesis{abc,
	author = {Moritz Hoffmann},
	school = {115},
	title = {Completeness is in the eye of the beholder: A sandbox concept for databases},
	year = {2014}
}

@mastersthesis{abc,
	author = {Benjamin Zehnder},
	school = {117},
	title = {Towards Revenue Maximization by Viral Marketing: A Social Network Host\&$\#$146;s Perspective},
	year = {2014}
}

@inproceedings{abc,
	author = {Victor Bittorf and Marcel Kornacker and Christopher R{\'e} and Ce Zhang},
	booktitle = {Proceedings of the 2nd International Workshop on In Memory Data Management and Analytics, IMDM 2014, Hangzhou, China},
	title = {Tradeoffs in Main-Memory Statistical Analytics from Impala to DimmWitted.},
	url = {http://www-db.in.tum.de/hosted/imdm2014/papers/bittorf.pdf},
	year = {2014}
}

@inproceedings{abc,
	author = {James A. Jablin and Thomas B. Jablin and Onur Mutlu and Maurice Herlihy},
	booktitle = {International Conference on Parallel Architectures and Compilation, PACT {\textquoteright}14, Edmonton, AB, Canada},
	title = {Warp-aware trace scheduling for GPUs.},
	url = {http://doi.acm.org/10.1145/2628071.2628101},
	year = {2014}
}

@inproceedings{abc,
	author = {Bradley Thwaites and Gennady Pekhimenko and Hadi Esmaeilzadeh and Amir Yazdanbakhsh and Onur Mutlu and Jongse Park and Girish Mururu and Todd C. Mowry},
	booktitle = {International Conference on Parallel Architectures and Compilation, PACT {\textquoteright}14, Edmonton, AB, Canada},
	title = {Rollback-free value prediction with approximate loads.},
	url = {http://doi.acm.org/10.1145/2628071.2628110},
	year = {2014}
}

@inproceedings{abc,
	author = {Philipp Unterbrunner and Gustavo Alonso and Donald Kossmann},
	booktitle = {The VLDB Journal; Nov. 2013},
	title = {High Availability, Elasticity, and Strong Consistency for Massively Parallel Scans over Relational Data.},
	year = {2014}
}

@inproceedings{abc,
	author = {Arijit Khan and Sameh Elnikety},
	booktitle = {PVLDB},
	title = {Systems for Big-Graphs.},
	url = {http://www.vldb.org/pvldb/vol7/p1709-khan.pdf},
	year = {2014}
}

@inproceedings{abc,
	author = {Tahmineh Sanamrad and Lucas Braun and Donald Kossmann and Ramarathnam Venkatesan},
	booktitle = {Data and Applications Security and Privacy XXVIII - 28th Annual IFIP WG 11.3 Working Conference, DBSec 2014, Vienna, Austria},
	title = {Randomly Partitioned Encryption for Cloud Databases.},
	url = {http://dx.doi.org/10.1007/978-3-662-43936-4_20},
	year = {2014}
}

@phdthesis{abc,
	author = {Louis Woods},
	school = {21967},
	title = {FPGA-Enhanced Data Processing Systems},
	year = {2014}
}

@inproceedings{abc,
	author = {Zaheer Chothia and Qin Yin and Timothy Roscoe},
	booktitle = {Asia-Pacific Workshop on Systems, APSys{\textquoteright}14, Beijing, China},
	title = {Grok the data center.},
	url = {http://doi.acm.org/10.1145/2637166.2637234},
	year = {2014}
}

@inproceedings{abc,
	author = {Yixin Luo and Sriram Govindan and Bikash Sharma and Mark Santaniello and Justin Meza and Aman Kansal and Jie Liu and Badriddine M. Khessib and Kushagra Vaid and Onur Mutlu},
	booktitle = {44th Annual IEEE/IFIP International Conference on Dependable Systems and Networks, DSN 2014, Atlanta, GA, USA},
	title = {Characterizing Application Memory Error Vulnerability to Optimize Datacenter Cost via Heterogeneous-Reliability Memory.},
	url = {http://dx.doi.org/10.1109/DSN.2014.50},
	year = {2014}
}

@phdthesis{abc,
	author = {Martin Kaufmann},
	school = {21964},
	title = {Storing and Processing Temporal Data in Main Memory Column Stores},
	year = {2014}
}

@inproceedings{abc,
	author = {Ce Zhang and Arun Kumar and Christopher R{\'e}},
	booktitle = {International Conference on Management of Data, SIGMOD 2014, Snowbird, UT, USA},
	title = {Materialization optimizations for feature selection workloads.},
	url = {http://doi.acm.org/10.1145/2588555.2593678},
	year = {2014}
}

@inproceedings{abc,
	author = {Yoongu Kim and Ross Daly and Jeremie Kim and Chris Fallin and Ji-Hye Lee and Donghyuk Lee and Chris Wilkerson and Konrad Lai and Onur Mutlu},
	booktitle = {ACM/IEEE 41st International Symposium on Computer Architecture, ISCA 2014, Minneapolis, MN, USA},
	title = {Flipping bits in memory without accessing them: An experimental study of DRAM disturbance errors.},
	url = {http://dx.doi.org/10.1109/ISCA.2014.6853210},
	year = {2014}
}

@inproceedings{abc,
	author = {Vivek Seshadri and Abhishek Bhowmick and Onur Mutlu and Phillip B. Gibbons and Michael A. Kozuch and Todd C. Mowry},
	booktitle = {ACM/IEEE 41st International Symposium on Computer Architecture, ISCA 2014, Minneapolis, MN, USA},
	title = {The Dirty-Block Index.},
	url = {http://dx.doi.org/10.1109/ISCA.2014.6853204},
	year = {2014}
}

@inproceedings{abc,
	author = {Samira Manabi Khan and Donghyuk Lee and Yoongu Kim and Alaa R. Alameldeen and Chris Wilkerson and Onur Mutlu},
	booktitle = {ACM SIGMETRICS / International Conference on Measurement and Modeling of Computer Systems, SIGMETRICS {\textquoteright}14, Austin, TX},
	title = {The efficacy of error mitigation techniques for DRAM retention failures: a comparative experimental study.},
	url = {http://doi.acm.org/10.1145/2591971.2592000},
	year = {2014}
}

@inproceedings{abc,
	author = {Zsolt Istv{\'a}n and Louis Woods and Gustavo Alonso},
	booktitle = {International Conference on Management of Data, SIGMOD 2014, Snowbird, UT, USA},
	title = {Histograms as a side effect of data movement for big data.},
	url = {http://doi.acm.org/10.1145/2588555.2612174},
	year = {2014}
}

@inproceedings{abc,
	author = {Yu Cai and Gulay Yalcin and Onur Mutlu and Erich F. Haratsch and Osman S. Unsal and Adri{\'a}n Cristal and Ken Mai},
	booktitle = {ACM SIGMETRICS / International Conference on Measurement and Modeling of Computer Systems, SIGMETRICS {\textquoteright}14, Austin, TX},
	title = {Neighbor-cell assisted error correction for MLC NAND flash memories.},
	url = {http://doi.acm.org/10.1145/2591971.2591994},
	year = {2014}
}

@inproceedings{abc,
	author = {Arijit Khan and Pouya Yanki and Bojana Dimcheva and Donald Kossmann},
	booktitle = {International Conference on Management of Data, SIGMOD 2014, Snowbird, UT, USA},
	title = {Towards indexing functions: answering scalar product queries.},
	url = {http://doi.acm.org/10.1145/2588555.2610493},
	year = {2014}
}

@inproceedings{abc,
	author = {Sangeetha Abdu Jyothi and Ankit Singla and Brighten Godfrey and Alexandra Kolla},
	booktitle = {ACM SIGMETRICS / International Conference on Measurement and Modeling of Computer Systems, SIGMETRICS {\textquoteright}14, Austin, TX},
	title = {Measuring throughput of data center network topologies.},
	url = {http://doi.acm.org/10.1145/2591971.2592040},
	year = {2014}
}

@inproceedings{abc,
	author = {Nandish Jayaram and Arijit Khan and Chengkai Li and Xifeng Yan and Ramez Elmasri},
	booktitle = {Second International Workshop on Graph Data Management Experiences and Systems, GRADES 2014, co-loated with SIGMOD/PODS 2014, Snowbird, Utah, USA},
	title = {Towards a Query-by-Example System for Knowledge Graphs.},
	url = {http://event.cwi.nl/grades2014/11-jayaram.pdf},
	year = {2014}
}

@inproceedings{abc,
	author = {Pratanu Roy and Jens Teubner and Rainer Gemulla},
	booktitle = {PVLDB},
	title = {Low-Latency Handshake Join.},
	url = {http://www.vldb.org/pvldb/vol7/p709-roy.pdf},
	year = {2014}
}

@inproceedings{abc,
	author = {Anja Gruenheid and Xin Dong and Divesh Srivastava},
	booktitle = {PVLDB},
	title = {Incremental Record Linkage.},
	url = {http://www.vldb.org/pvldb/vol7/p697-gruenheid.pdf},
	year = {2014}
}

@mastersthesis{abc,
	author = {Bojana Dimcheva},
	school = {112},
	title = {Indexing Scalar Product Queries},
	year = {2014}
}

@phdthesis{abc,
	author = {Cagri Balkesen},
	school = {21954},
	title = {In-Memory Parallel Join Processing on Multi-Core Processors},
	year = {2014}
}

@inproceedings{abc,
	author = {Hyoseung Kim and Dionisio de Niz and Bj{\"o}rn Andersson and Mark H. Klein and Onur Mutlu and Ragunathan Rajkumar},
	booktitle = {20th IEEE Real-Time and Embedded Technology and Applications Symposium, RTAS 2014, Berlin, Germany},
	title = {Bounding memory interference delay in COTS-based multi-core systems.},
	url = {http://dx.doi.org/10.1109/RTAS.2014.6925998},
	year = {2014}
}

@inproceedings{abc,
	author = {Christian Tinnefeld and Donald Kossmann and Joos-Hendrik B{\"o}se and Hasso Plattner},
	booktitle = {Workshops Proceedings of the 30th International Conference on Data Engineering Workshops, ICDE 2014, Chicago, IL, USA},
	title = {Parallel join executions in RAMCloud.},
	url = {http://dx.doi.org/10.1109/ICDEW.2014.6818325},
	year = {2014}
}

@inproceedings{abc,
	author = {Ankit Singla and Brighten Godfrey and Alexandra Kolla},
	booktitle = {Proceedings of the 11th USENIX Symposium on Networked Systems Design and Implementation, NSDI 2014, Seattle, WA, USA},
	title = {High Throughput Data Center Topology Design.},
	url = {https://www.usenix.org/conference/nsdi14/technical-sessions/presentation/singla},
	year = {2014}
}

@inproceedings{abc,
	author = {Brent Stephens and Alan L. Cox and Ankit Singla and John B. Carter and Colin Dixon and Wes Felter},
	booktitle = {2014 IEEE Conference on Computer Communications, INFOCOM 2014, Toronto, Canada},
	title = {Practical DCB for improved data center networks.},
	url = {http://dx.doi.org/10.1109/INFOCOM.2014.6848121},
	year = {2014}
}

@inproceedings{abc,
	abstract = {After more than a decade of a virtual standstill, the adoption of temporal data management features has recently picked up speed, driven by customer demand and the inclusion of temporal expressions into SQL:2011. Most of the big commercial DBMS now include support for bitemporal data and operators. 
In this paper, we perform a thorough analysis of these commercial temporal DBMS: We investigate their architecture, determine their performance and study the impact of performance tuning. This analysis utilizes our recent (TPCTC 2013) benchmark proposal, which includes a comprehensive temporal workload definition.
The results of our analysis show that the support for temporal data is still in its infancy:  All systems store their data in regular, statically partitioned tables and rely on standard indexes as well as query rewrites for their operations. As shown by our measurements, this causes considerable performance variations on slight workload variations and a significant effort for performance tuning. In some cases, there is considerable overhead for temporal operations even after extensive tuning.},
	author = {Martin Kaufmann and Peter M. Fischer and Norman May and Donald Kossmann},
	booktitle = {EDBT: 17th International Conference on Extending Database Technology},
	title = {Benchmarking Bitemporal Database Systems:  Ready for the Future or Stuck in the Past?},
	year = {2014}
}

@inproceedings{abc,
	author = {Arijit Khan and Francesco Bonchi and Aristides Gionis and Francesco Gullo},
	booktitle = {Proceedings of the 17th International Conference on Extending Database Technology, EDBT 2014, Athens, Greece},
	title = {Fast Reliability Search in Uncertain Graphs.},
	url = {http://dx.doi.org/10.5441/002/edbt.2014.48},
	year = {2014}
}

@inproceedings{abc,
	author = {Martin Kaufmann and Peter M. Fischer and Norman May and Donald Kossmann},
	booktitle = {Proceedings of the 17th International Conference on Extending Database Technology, EDBT 2014, Athens, Greece},
	title = {Benchmarking Bitemporal Database Systems: Ready for the Future or Stuck in the Past?},
	url = {http://dx.doi.org/10.5441/002/edbt.2014.80},
	year = {2014}
}

@inproceedings{abc,
	author = {Kevin Kai-Wei Chang and Donghyuk Lee and Zeshan Chishti and Alaa R. Alameldeen and Chris Wilkerson and Yoongu Kim and Onur Mutlu},
	booktitle = {20th IEEE International Symposium on High Performance Computer Architecture, HPCA 2014, Orlando, FL, USA},
	title = {Improving DRAM performance by parallelizing refreshes with accesses.},
	url = {http://dx.doi.org/10.1109/HPCA.2014.6835946},
	year = {2014}
}

@inproceedings{abc,
	author = {Samira Manabi Khan and Alaa R. Alameldeen and Chris Wilkerson and Onur Mutlu and Daniel A. Jim{\'e}nez},
	booktitle = {20th IEEE International Symposium on High Performance Computer Architecture, HPCA 2014, Orlando, FL, USA},
	title = {Improving cache performance using read-write partitioning.},
	url = {http://dx.doi.org/10.1109/HPCA.2014.6835954},
	year = {2014}
}

@inproceedings{abc,
	author = {Georgios Giannikis and Darko Makreshanski and Gustavo Alonso and Donald Kossmann},
	booktitle = {PVLDB},
	title = {Shared Workload Optimization.},
	url = {http://www.vldb.org/pvldb/vol7/p429-giannikis.pdf},
	year = {2014}
}

@inproceedings{abc,
	author = {Tobias Grosser and Albert Cohen and Justin Holewinski and P. Sadayappan and Sven Verdoolaege},
	booktitle = {12th Annual IEEE/ACM International Symposium on Code Generation and Optimization, CGO 2014, Orlando, FL, USA},
	title = {Hybrid Hexagonal/Classical Tiling for GPUs.},
	url = {http://doi.acm.org/10.1145/2544137.2544160},
	year = {2014}
}

@mastersthesis{abc,
	author = {Alessandra Loro},
	school = {104},
	title = {Business Rules Retrieval and Processing},
	year = {2014}
}

@phdthesis{abc,
	author = {Ercan Ucan},
	school = {21762},
	title = {Data storage, transfers and communication in personal clouds },
	year = {2014}
}

@article{abc,
	author = {Shanan Peters and Ce Zhang and Miron Livny and Christopher R{\'e}},
	journal = {CoRR},
	title = {A machine-compiled macroevolutionary history of Phanerozoic life.},
	url = {http://arxiv.org/abs/1406.2963},
	year = {2014}
}

@inproceedings{abc,
	author = {Vivek Seshadri and Samihan Yedkar and Hongyi Xin and Onur Mutlu and Phillip B. Gibbons and Michael A. Kozuch and Todd C. Mowry},
	booktitle = {TACO},
	title = {Mitigating Prefetcher-Caused Pollution Using Informed Caching Policies for Prefetched Blocks.},
	url = {http://doi.acm.org/10.1145/2677956},
	year = {2014}
}

@inproceedings{abc,
	author = {Christopher R{\'e} and Amir Abbas Sadeghian and Zifei Shan and Jaeho Shin and Feiran Wang and Sen Wu and Ce Zhang},
	booktitle = {IEEE Data Eng. Bull.},
	title = {Feature Engineering for Knowledge Base Construction.},
	url = {http://sites.computer.org/debull/A14sept/p26.pdf},
	year = {2014}
}

@phdthesis{abc,
	author = {Tudor-Ioan Salomie},
	school = {21753},
	title = {Cloud-ready scalable and elastic data processing using off-the-shelf databases, replication and virtualization},
	year = {2014}
}

@article{abc,
	author = {Ce Zhang and Christopher R{\'e}},
	journal = {CoRR},
	title = {DimmWitted: A Study of Main-Memory Statistical Analytics.},
	url = {http://arxiv.org/abs/1403.7550},
	year = {2014}
}

@article{abc,
	author = {Ce Zhang and Christopher R{\'e} and Amir Abbas Sadeghian and Zifei Shan and Jaeho Shin and Feiran Wang and Sen Wu},
	journal = {CoRR},
	title = {Feature Engineering for Knowledge Base Construction.},
	url = {http://arxiv.org/abs/1407.6439},
	year = {2014}
}

@inproceedings{abc,
	abstract = {The online communities available on the Web have shown to be significantly interactive and capable of collectively solving difficult tasks. Nevertheless, it is still a challenge to decide how a task should be dispatched through the network due to the high diversity of the communities and the dynamically changing expertise and social availability of their members. We introduce CrowdSTAR, a framework designed to route tasks across and within online crowds. CrowdSTAR indexes the topic-specific expertise and social features of the crowd contributors and then uses a routing algorithm, which suggests the best sources to ask based on the knowledge vs. availability trade-offs. We experimented with the proposed framework for question and answering scenarios by using two popular social networks as crowd candidates: Twitter and Quora.},
	author = {Besmira Nushi and Omar Alonso and Martin Hentschel and Vasileios Kandylas},
	booktitle = {CoRR},
	title = {CrowdSTAR: A Social Task Routing Framework for Online Communities.},
	url = {http://arxiv.org/abs/1407.6714},
	venue = {-},
	year = {2014}
}

@inproceedings{abc,
	author = {Ce Zhang and Christopher R{\'e}},
	booktitle = {PVLDB},
	title = {DimmWitted: A Study of Main-Memory Statistical Analytics.},
	url = {http://www.vldb.org/pvldb/vol7/p1283-zhang.pdf},
	year = {2014}
}

@inproceedings{abc,
	author = {HanBin Yoon and Justin Meza and Naveen Muralimanohar and Norman P. Jouppi and Onur Mutlu},
	booktitle = {TACO},
	title = {Efficient Data Mapping and Buffering Techniques for Multilevel Cell Phase-Change Memories.},
	url = {http://doi.acm.org/10.1145/2669365},
	year = {2014}
}

@inproceedings{abc,
	author = {Vivek Seshadri and Yoongu Kim and Chris Fallin and Donghyuk Lee and Rachata Ausavarungnirun and Gennady Pekhimenko and Yixin Luo and Onur Mutlu and Phillip B. Gibbons and Michael A. Kozuch and Todd C. Mowry},
	booktitle = {The 46th Annual IEEE/ACM International Symposium on Microarchitecture, MICRO-46, Davis, CA, USA},
	title = {RowClone: fast and energy-efficient in-DRAM bulk data copy and initialization.},
	url = {http://doi.acm.org/10.1145/2540708.2540725},
	year = {2013}
}

@inproceedings{abc,
	author = {Gennady Pekhimenko and Vivek Seshadri and Yoongu Kim and Hongyi Xin and Onur Mutlu and Phillip B. Gibbons and Michael A. Kozuch and Todd C. Mowry},
	booktitle = {The 46th Annual IEEE/ACM International Symposium on Microarchitecture, MICRO-46, Davis, CA, USA},
	title = {Linearly compressed pages: a low-complexity, low-latency main memory compression framework.},
	url = {http://doi.acm.org/10.1145/2540708.2540724},
	year = {2013}
}

@inproceedings{abc,
	author = {Srikrishna Sridhar and Stephen J. Wright and Christopher R{\'e} and Ji Liu and Victor Bittorf and Ce Zhang},
	booktitle = {Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a meeting held December 5-8, 2013, Lake Tahoe, Nevada, United States.},
	title = {An Approximate, Efficient LP Solver for LP Rounding.},
	url = {http://papers.nips.cc/paper/4990-an-approximate-efficient-lp-solver-for-lp-rounding},
	venue = {Lake Tahoe, Nevada, United States.},
	year = {2013}
}

@inproceedings{abc,
	author = {Tushar Khot and Ce Zhang and Jude W. Shavlik and Sriraam Natarajan and Christopher R{\'e}},
	booktitle = {Proceedings of The Twenty-Second Text REtrieval Conference, TREC 2013, Gaithersburg, Maryland, USA},
	title = {Bootstrapping Knowledge Base Acceleration.},
	url = {http://trec.nist.gov/pubs/trec22/papers/wisc-kba.pdf},
	year = {2013}
}

@inproceedings{abc,
	author = {Pravin Shinde and Antoine Kaufmann and Kornilios Kourtis and Timothy Roscoe},
	booktitle = {Proceedings of the Seventh Workshop on Programming Languages and Operating Systems, PLOS 2013, Farmington, Pennsylvania, USA},
	title = {Modeling NICs with Unicorn.},
	url = {http://doi.acm.org/10.1145/2525528.2525532},
	year = {2013}
}

@inproceedings{abc,
	author = {John R. Frank and Steven J. Bauer and Max Kleiman-Weiner and Daniel A. Roberts and Nilesh Tripuraneni and Ce Zhang and Christopher R{\'e} and Ellen M. Voorhees and Ian Soboroff},
	booktitle = {Proceedings of The Twenty-Second Text REtrieval Conference, TREC 2013, Gaithersburg, Maryland, USA},
	title = {Evaluating Stream Filtering for Entity Profile Updates for TREC 2013.},
	url = {http://trec.nist.gov/pubs/trec22/papers/KBA.OVERVIEW.pdf},
	year = {2013}
}

@inproceedings{abc,
	author = {Youyou Lu and Jiwu Shu and Jia Guo and Shuai Li and Onur Mutlu},
	booktitle = {2013 IEEE 31st International Conference on Computer Design, ICCD 2013, Asheville, NC, USA},
	title = {LightTx: A lightweight transactional design in flash-based SSDs to support flexible transactions.},
	url = {http://dx.doi.org/10.1109/ICCD.2013.6657033},
	year = {2013}
}

@inproceedings{abc,
	author = {Yu Cai and Onur Mutlu and Erich F. Haratsch and Ken Mai},
	booktitle = {2013 IEEE 31st International Conference on Computer Design, ICCD 2013, Asheville, NC, USA},
	title = {Program interference in MLC NAND flash memory: Characterization, modeling, and mitigation.},
	url = {http://dx.doi.org/10.1109/ICCD.2013.6657034},
	year = {2013}
}

@mastersthesis{abc,
	author = {Denitsa Dobreva},
	school = {101},
	title = {Enterprise Social Networks Analysis},
	year = {2013}
}

@mastersthesis{abc,
	author = {Patrick B{\"a}nziger},
	school = {94},
	title = {Exploiting multi-core parallelism with pipelining to solve skyline queries},
	year = {2013}
}

@mastersthesis{abc,
	author = {Lynn Aders},
	school = {93},
	title = {Joins based on the Access Path Model for Crowdsourced Databases},
	year = {2013}
}

@inproceedings{abc,
	author = {Arvind Arasu and Ken Eguro and Raghav Kaushik and Donald Kossmann and Ravishankar Ramamurthy and Ramarathnam Venkatesan},
	booktitle = {23rd International Conference on Field programmable Logic and Applications, FPL 2013, Porto, Portugal},
	title = {A secure coprocessor for database applications.},
	url = {http://dx.doi.org/10.1109/FPL.2013.6645524},
	year = {2013}
}

@mastersthesis{abc,
	author = {Daniel Widmer},
	school = {90},
	title = {Real-Time Analytics in a High Volume Event Processing System},
	year = {2013}
}

@inproceedings{abc,
	author = {Zsolt Istv{\'a}n and Gustavo Alonso and Michaela Blott and Kees A. Vissers},
	booktitle = {23rd International Conference on Field programmable Logic and Applications, FPL 2013, Porto, Portugal},
	title = {A flexible hash table design for 10GBPS key-value stores on FPGAS.},
	url = {http://dx.doi.org/10.1109/FPL.2013.6645520},
	year = {2013}
}

@inproceedings{abc,
	author = {Louis Woods and Zsolt Istv{\'a}n and Gustavo Alonso},
	booktitle = {23rd International Conference on Field programmable Logic and Applications, FPL 2013, Porto, Portugal},
	title = {Hybrid FPGA-accelerated SQL query processing.},
	url = {http://dx.doi.org/10.1109/FPL.2013.6645619},
	year = {2013}
}

@inproceedings{abc,
	author = {Martin Kaufmann and Peter M. Fischer and Norman May and Andreas Tonder and Donald Kossmann},
	booktitle = {Performance Characterization and Benchmarking - 5th TPC Technology Conference, TPCTC 2013, Trento, Italy},
	title = {TPC-BiH: A Benchmark for Bitemporal Databases.},
	url = {http://dx.doi.org/10.1007/978-3-319-04936-6_2},
	venue = {Revised Selected Papers},
	year = {2013}
}

@inproceedings{abc,
	author = {Anja Gruenheid and Donald Kossmann},
	booktitle = {Proceedings of the First VLDB Workshop on Databases and Crowdsourcing, DBCrowd 2013, Riva del Garda, Trento, Italy},
	title = {Cost and Quality Trade-Offs in Crowdsourcing.},
	url = {http://ceur-ws.org/Vol-1025/vision2.pdf},
	year = {2013}
}

@inproceedings{abc,
	author = {Vidhya Govindaraju and Ce Zhang and Christopher R{\'e}},
	booktitle = {Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics, ACL 2013},
	title = {Understanding Tables in Context Using Standard NLP Toolkits.},
	url = {http://aclweb.org/anthology/P/P13/P13-2116.pdf},
	venue = {Sofia, Bulgaria, Volume 2: Short Papers},
	year = {2013}
}

@inproceedings{abc,
	author = {Arvind Arasu and Spyros Blanas and Ken Eguro and Manas Joglekar and Raghav Kaushik and Donald Kossmann and Ravishankar Ramamurthy and Prasang Upadhyaya and Ramarathnam Venkatesan},
	booktitle = {Proceedings of the ACM SIGMOD International Conference on Management of Data, SIGMOD 2013, New York, NY, USA},
	title = {Secure database-as-a-service with Cipherbase.},
	url = {http://doi.acm.org/10.1145/2463676.2467797},
	year = {2013}
}

@inproceedings{abc,
	author = {Adwait Jog and Onur Kayiran and Asit K. Mishra and Mahmut T. Kandemir and Onur Mutlu and Ravishankar Iyer and Chita R. Das},
	booktitle = {The 40th Annual International Symposium on Computer Architecture, ISCA{\textquoteright}13, Tel-Aviv, Israel},
	title = {Orchestrated scheduling and prefetching for GPGPUs.},
	url = {http://doi.acm.org/10.1145/2485922.2485951},
	year = {2013}
}

@inproceedings{abc,
	author = {Ce Zhang and Christopher R{\'e}},
	booktitle = {Proceedings of the ACM SIGMOD International Conference on Management of Data, SIGMOD 2013, New York, NY, USA},
	title = {Towards high-throughput gibbs sampling at scale: a study across storage managers.},
	url = {http://doi.acm.org/10.1145/2463676.2463702},
	year = {2013}
}

@inproceedings{abc,
	author = {Jamie Liu and Ben Jaiyen and Yoongu Kim and Chris Wilkerson and Onur Mutlu},
	booktitle = {The 40th Annual International Symposium on Computer Architecture, ISCA{\textquoteright}13, Tel-Aviv, Israel},
	title = {An experimental study of data retention behavior in modern DRAM devices: implications for retention time profiling mechanisms.},
	url = {http://doi.acm.org/10.1145/2485922.2485928},
	year = {2013}
}

@mastersthesis{abc,
	author = {Zaheer Chothia},
	school = {84},
	title = {Investigating OS/DB co-design with SharedDB and Barrelfish},
	year = {2013}
}

@inproceedings{abc,
	author = {Ce Zhang and Vidhya Govindaraju and Jackson Borchardt and Tim Foltz and Christopher R{\'e} and Shanan Peters},
	booktitle = {Proceedings of the ACM SIGMOD International Conference on Management of Data, SIGMOD 2013, New York, NY, USA},
	title = {GeoDeepDive: statistical inference using familiar data-processing languages.},
	url = {http://doi.acm.org/10.1145/2463676.2463680},
	year = {2013}
}

@inproceedings{abc,
	author = {Jos{\'e} A. Joao and M. Aater Suleman and Onur Mutlu and Yale N. Patt},
	booktitle = {The 40th Annual International Symposium on Computer Architecture, ISCA{\textquoteright}13, Tel-Aviv, Israel},
	title = {Utility-based acceleration of multithreaded applications on asymmetric CMPs.},
	url = {http://doi.acm.org/10.1145/2485922.2485936},
	year = {2013}
}

@inproceedings{abc,
	author = {Martin Kaufmann and Amin Amiri Manjili and Panagiotis Vagenas and Peter M. Fischer and Donald Kossmann and Franz F{\"a}rber and Norman May},
	booktitle = {Proceedings of the ACM SIGMOD International Conference on Management of Data, SIGMOD 2013, New York, NY, USA},
	title = {Timeline index: a unified data structure for processing queries on temporal data in SAP HANA.},
	url = {http://doi.acm.org/10.1145/2463676.2465293},
	year = {2013}
}

@inproceedings{abc,
	author = {Cagri Balkesen and Nesime Tatbul and M. Tamer {\"O}zsu},
	booktitle = {The 7th ACM International Conference on Distributed Event-Based Systems, DEBS {\textquoteright}13, Arlington, TX},
	title = {Adaptive input admission and management for parallel stream processing.},
	url = {http://doi.acm.org/10.1145/2488222.2488258},
	year = {2013}
}

@inproceedings{abc,
	author = {Georgios Giannikis and Darko Makreshanski and Gustavo Alonso and Donald Kossmann},
	booktitle = {Proceedings of the ACM SIGMOD International Conference on Management of Data, SIGMOD 2013, New York, NY, USA},
	title = {Workload optimization using SharedDB.},
	url = {http://doi.acm.org/10.1145/2463676.2463678},
	year = {2013}
}

@inproceedings{abc,
	author = {Cagri Balkesen and Nihal Dindar and Matthias Wetter and Nesime Tatbul},
	booktitle = {The 7th ACM International Conference on Distributed Event-Based Systems, DEBS {\textquoteright}13, Arlington, TX},
	title = {RIP: run-based intra-query parallelism for scalable complex event processing.},
	url = {http://doi.acm.org/10.1145/2488222.2488257},
	year = {2013}
}

@inproceedings{abc,
	author = {Louis Woods and Jens Teubner and Gustavo Alonso},
	booktitle = {Proceedings of the ACM SIGMOD International Conference on Management of Data, SIGMOD 2013, New York, NY, USA},
	title = {Less watts, more performance: an intelligent storage engine for data appliances.},
	url = {http://doi.acm.org/10.1145/2463676.2463685},
	year = {2013}
}

@inproceedings{abc,
	author = {Boris Glavic and Kyumars Sheykh Esmaili and Peter M. Fischer and Nesime Tatbul},
	booktitle = {The 7th ACM International Conference on Distributed Event-Based Systems, DEBS {\textquoteright}13, Arlington, TX},
	title = {Ariadne: managing fine-grained provenance on data streams.},
	url = {http://doi.acm.org/10.1145/2488222.2488256},
	year = {2013}
}

@mastersthesis{abc,
	author = {Lukas Humbel},
	school = {83},
	title = {Multicore Virtualization over a Multikernel},
	year = {2013}
}

@inproceedings{abc,
	author = {Asit K. Mishra and Onur Mutlu and Chita R. Das},
	booktitle = {The 50th Annual Design Automation Conference 2013, DAC {\textquoteright}13, Austin, TX, USA},
	title = {A heterogeneous multiple network-on-chip design: an application-aware approach.},
	url = {http://doi.acm.org/10.1145/2463209.2488779},
	year = {2013}
}

@inproceedings{abc,
	author = {Pravin Shinde and Antoine Kaufmann and Timothy Roscoe and Stefan Kaestle},
	booktitle = {14th Workshop on Hot Topics in Operating Systems, HotOS XIV, Santa Ana Pueblo, New Mexico, USA},
	title = {We Need to Talk About NICs.},
	url = {https://www.usenix.org/conference/hotos13/session/shinde},
	year = {2013}
}

@inproceedings{abc,
	author = {Ercan Ucan and Timothy Roscoe},
	booktitle = {Networked Systems - First International Conference, NETYS 2013, Marrakech, Morocco},
	title = {Establishing Efficient Routes between Personal Clouds.},
	url = {http://dx.doi.org/10.1007/978-3-642-40148-0_6},
	venue = {Revised Selected Papers},
	year = {2013}
}

@inproceedings{abc,
	author = {Chuanjun Zhang and Glenn G. Ko and Jungwook Choi and Shang-nien Tsai and Minje Kim and Abner Guzm{\'a}n-Rivera and Rob A. Rutenbar and Paris Smaragdis and Mi Sun Park and Narayanan Vijaykrishnan and Hongyi Xin and Onur Mutlu and Bin Li and Li Zhao and Mei Chen},
	booktitle = {2012 IEEE International Symposium on Performance Analysis of Systems  Software, Austin, TX, USA},
	title = {EMERALD: Characterization of emerging applications and algorithms for low-power devices.},
	url = {http://dx.doi.org/10.1109/ISPASS.2013.6557154},
	year = {2013}
}

@mastersthesis{abc,
	author = {Filip Curcic},
	school = {81},
	title = {Timeline Index on RamCloud},
	year = {2013}
}

@inproceedings{abc,
	author = {Gustavo Alonso},
	booktitle = {29th IEEE International Conference on Data Engineering, ICDE 2013, Brisbane, Australia},
	title = {Hardware killed the software star.},
	url = {http://doi.ieeecomputersociety.org/10.1109/ICDE.2013.6544807},
	year = {2013}
}

@inproceedings{abc,
	author = {Cagri Balkesen and Jens Teubner and Gustavo Alonso and M. Tamer {\"O}zsu},
	booktitle = {29th IEEE International Conference on Data Engineering, ICDE 2013, Brisbane, Australia},
	title = {Main-memory hash joins on multi-core CPUs: Tuning to the underlying hardware.},
	url = {http://doi.ieeecomputersociety.org/10.1109/ICDE.2013.6544839},
	year = {2013}
}

@inproceedings{abc,
	author = {Junda Liu and Aurojit Panda and Ankit Singla and Brighten Godfrey and Michael Schapira and Scott Shenker},
	booktitle = {Proceedings of the 10th USENIX Symposium on Networked Systems Design and Implementation, NSDI 2013, Lombard, IL, USA},
	title = {Ensuring Connectivity via Data Plane Mechanisms.},
	url = {https://www.usenix.org/conference/nsdi13/technical-sessions/presentation/liu_junda},
	year = {2013}
}

@mastersthesis{abc,
	author = {David Sidler},
	school = {74},
	title = {Column Storage for FPGA-accelerated Data Analytics},
	year = {2013}
}

@inproceedings{abc,
	author = {Martin Kaufmann and Amin Amiri Manjili and Stefan Hildenbrand and Donald Kossmann and Andreas Tonder},
	booktitle = {29th IEEE International Conference on Data Engineering, ICDE 2013, Brisbane, Australia},
	title = {Time travel in column stores.},
	url = {http://doi.ieeecomputersociety.org/10.1109/ICDE.2013.6544818},
	year = {2013}
}

@mastersthesis{abc,
	author = {Georgios Gasparis},
	school = {78},
	title = {AIM: A System for Handling Enormous Workloads under Strict Latency and Scalability Regulations},
	year = {2013}
}

@inproceedings{abc,
	author = {Tudor-Ioan Salomie and Gustavo Alonso and Timothy Roscoe and Kevin Elphinstone},
	booktitle = {Eighth Eurosys Conference 2013, EuroSys {\textquoteright}13, Prague, Czech Republic},
	title = {Application level ballooning for efficient server consolidation.},
	url = {http://doi.acm.org/10.1145/2465351.2465384},
	year = {2013}
}

@inproceedings{abc,
	author = {Martin Kaufmann and Peter M. Fischer and Donald Kossmann and Norman May},
	booktitle = {29th IEEE International Conference on Data Engineering, ICDE 2013, Brisbane, Australia},
	title = {A generic database benchmarking service.},
	url = {http://doi.ieeecomputersociety.org/10.1109/ICDE.2013.6544923},
	year = {2013}
}

@inproceedings{abc,
	author = {Emre Kultursay and Mahmut T. Kandemir and Anand Sivasubramaniam and Onur Mutlu},
	booktitle = {2012 IEEE International Symposium on Performance Analysis of Systems  Software, Austin, TX, USA},
	title = {Evaluating STT-RAM as an energy-efficient main memory alternative.},
	url = {http://dx.doi.org/10.1109/ISPASS.2013.6557176},
	year = {2013}
}

@mastersthesis{abc,
	author = {Danilo Medic},
	school = {80},
	title = {Model Driven Optical Form Recognition},
	year = {2013}
}

@inproceedings{abc,
	author = {Gernot Heiser and Etienne Le Sueur and Adrian Danis and Aleksander Budzynowski and Tudor-Ioan Salomie and Gustavo Alonso},
	booktitle = {Eighth Eurosys Conference 2013, EuroSys {\textquoteright}13, Prague, Czech Republic},
	title = {RapiLog: reducing system complexity through verification.},
	url = {http://doi.acm.org/10.1145/2465351.2465383},
	year = {2013}
}

@inproceedings{abc,
	author = {Louis Woods and Gustavo Alonso and Jens Teubner},
	booktitle = {21st IEEE Annual International Symposium on Field-Programmable Custom Computing Machines, FCCM 2013, Seattle, WA, USA},
	title = {Parallel Computation of Skyline Queries.},
	url = {http://doi.ieeecomputersociety.org/10.1109/FCCM.2013.18},
	year = {2013}
}

@mastersthesis{abc,
	author = {Ilias Rinis},
	school = {75},
	title = {Exploring scalable transactional data processing in a cluster of multicores},
	year = {2013}
}

@mastersthesis{abc,
	author = {Karolina Alexiou},
	school = {82},
	title = {Adaptive Range Filters for Query Optimization},
	year = {2013}
}

@mastersthesis{abc,
	author = {Andreas Tschofen},
	school = {71},
	title = {Joint Inference of Concepts and Networks of Documents},
	year = {2013}
}

@inproceedings{abc,
	author = {Yu Cai and Erich F. Haratsch and Onur Mutlu and Ken Mai},
	booktitle = {Design, Automation and Test in Europe, DATE 13, Grenoble, France},
	title = {Threshold voltage distribution in MLC NAND flash memory: characterization, analysis, and modeling.},
	year = {2013}
}

@mastersthesis{abc,
	author = {Zsolt Istv{\'a}n},
	school = {85},
	title = {Hash Table for Large Key-Value Stores on FPGAs},
	year = {2013}
}

@inproceedings{abc,
	author = {Adwait Jog and Onur Kayiran and Nachiappan Chidambaram Nachiappan and Asit K. Mishra and Mahmut T. Kandemir and Onur Mutlu and Ravishankar Iyer and Chita R. Das},
	booktitle = {Architectural Support for Programming Languages and Operating Systems, ASPLOS {\textquoteright}13, Houston, TX},
	title = {OWL: cooperative thread array aware scheduling techniques for improving GPGPU performance.},
	url = {http://doi.acm.org/10.1145/2451116.2451158},
	year = {2013}
}

@mastersthesis{abc,
	author = {Julien Ribon},
	school = {70},
	title = {Big Data Query Parallelization},
	year = {2013}
}

@inproceedings{abc,
	author = {Christian Tinnefeld and Donald Kossmann and Martin Grund and Joos-Hendrik B{\"o}se and Frank Renkes and Vishal Sikka and Hasso Plattner},
	booktitle = {Joint 2013 EDBT/ICDT Conferences, EDBT {\textquoteright}13 Proceedings, Genoa, Italy},
	title = {Elastic online analytical processing on RAMCloud.},
	url = {http://doi.acm.org/10.1145/2452376.2452429},
	year = {2013}
}

@inproceedings{abc,
	author = {Reetuparna Das and Rachata Ausavarungnirun and Onur Mutlu and Akhilesh Kumar and Mani Azimi},
	booktitle = {19th IEEE International Symposium on High Performance Computer Architecture, HPCA 2013, Shenzhen, China},
	title = {Application-to-core mapping policies to reduce memory system interference in multi-core systems.},
	url = {http://dx.doi.org/10.1109/HPCA.2013.6522311},
	year = {2013}
}

@inproceedings{abc,
	author = {Donghyuk Lee and Yoongu Kim and Vivek Seshadri and Jamie Liu and Lavanya Subramanian and Onur Mutlu},
	booktitle = {19th IEEE International Symposium on High Performance Computer Architecture, HPCA 2013, Shenzhen, China},
	title = {Tiered-latency DRAM: A low latency and low cost DRAM architecture.},
	url = {http://dx.doi.org/10.1109/HPCA.2013.6522354},
	year = {2013}
}

@inproceedings{abc,
	author = {Lavanya Subramanian and Vivek Seshadri and Yoongu Kim and Ben Jaiyen and Onur Mutlu},
	booktitle = {19th IEEE International Symposium on High Performance Computer Architecture, HPCA 2013, Shenzhen, China},
	title = {MISE: Providing performance predictability and improving fairness in shared main memory systems.},
	url = {http://dx.doi.org/10.1109/HPCA.2013.6522356},
	year = {2013}
}

@inproceedings{abc,
	author = {Mario Paolucci and Donald Kossmann and Rosaria Conte and Paul Lukowicz and Panos Argyrakis and Ann Blandford and Giulia Bonelli and Stuart Anderson and Sara de Freitas and Bruce Edmonds and G. Nigel Gilbert and Markus H. Gross and J{\"o}rn Kohlhammer and Petros Koumoutsakos and Andreas Krause and Bj{\"o}rn-Ola Linn{\'e}r and Philipp Slusallek and Olga Sorkine-Hornung and Robert W. Sumner and Dirk Helbing},
	booktitle = {CoRR},
	title = {Towards a living earth simulator},
	url = {http://arxiv.org/abs/1304.1903},
	year = {2013}
}

@inproceedings{abc,
	author = {Boris Glavic and Ren{\'e}e J. Miller and Gustavo Alonso},
	booktitle = {In Search of Elegance in the Theory and Practice of Computation - Essays Dedicated to Peter Buneman},
	title = {Using SQL for Efficient Generation and Querying of Provenance Information.},
	url = {http://dx.doi.org/10.1007/978-3-642-41660-6_16},
	year = {2013}
}

@techreport{abc,
	abstract = {An increasing number of applications such as risk evaluation in banking or inventory management require support for temporal data.
After more than a decade of standstill, the recent adoption of some bitemporal features in SQL:2011 has reinvigorated the support among commercial database vendors, who incorporate an increasing number of relevant bitemporal features. Naturally, assessing the performance and scalability of temporal data storage and operations is of great concern for potential users.
The cost of keeping and querying history with novel operations (such as time travel, temporal joins or temporal aggregations) is not adequately reflected in any existing benchmark.
In this paper, we present a benchmark proposal which provides comprehensive coverage of the bitemporal data management.
It builds on the solid foundations of TPC-H but extends it with a rich set of queries and update scenarios.
This workload stems both from real-life temporal applications from SAP{\textquoteright}s customer base and a systematic coverage of temporal operators proposed in the academic literature.
In the accompanying paper we present preliminary results of our benchmark on a number of temporal database systems, also highlighting the need for certain language extensions.
In the appendix of this technical report we provide all details required to implement the benchmark.},
	author = {Martin Kaufmann and Peter M. Fischer and Norman May and Donald Kossmann},
	title = {Benchmarking Databases with History Support},
	url = {http://dx.doi.org/10.3929/ethz-a-009994978},
	year = {2013}
}

@article{abc,
	author = {Cagri Balkesen and Gustavo Alonso and Jens Teubner and M. Tamer {\"O}zsu},
	journal = {PVLDB},
	title = {Multi-Core, Main-Memory Joins: Sort vs. Hash Revisited.},
	url = {http://www.vldb.org/pvldb/vol7/p85-balkesen.pdf},
	year = {2013}
}

@article{abc,
	author = {Fosca Giannotti and Dino Pedreschi and Alex Pentland and Paul Lukowicz and Donald Kossmann and James L. Crowley and Dirk Helbing},
	journal = {CoRR},
	title = {A planetary nervous system for social mining and collective awareness},
	url = {http://arxiv.org/abs/1304.3700},
	year = {2013}
}

@inproceedings{abc,
	author = {Michaela Blott and Kimon Karras and Ling Liu and Kees Vissers and Jeremia B{\"a}r and Zsolt Istv{\'a}n},
	booktitle = {Procedings of HotCloud {\textquoteright}13 (5th USENIX Workshop on Hot Topics in Cloud Computing)},
	title = {Achieving 10Gbps line-rate key-value stores with FPGAs},
	venue = {San Hose, CA, USA},
	year = {2013}
}

@inproceedings{abc,
	author = {Martin Kaufmann},
	booktitle = {PVLDB},
	title = {Storing and Processing Temporal Data in a Main Memory Column Store.},
	url = {http://www.vldb.org/pvldb/vol6/p1444-kaufmann.pdf},
	year = {2013}
}

@inproceedings{abc,
	author = {Arvind Arasu and Spyros Blanas and Ken Eguro and Raghav Kaushik and Donald Kossmann and Ravishankar Ramamurthy and Ramarathnam Venkatesan},
	booktitle = {CIDR 2013, Sixth Biennial Conference on Innovative Data Systems Research, Asilomar, CA, USA},
	title = {Orthogonal Security with Cipherbase.},
	url = {http://www.cidrdb.org/cidr2013/Papers/CIDR13_Paper33.pdf},
	year = {2013}
}

@inproceedings{abc,
	author = {Tahmineh Sanamrad and Donald Kossmann},
	booktitle = {Proceedings of the  Workshop on Secure Data Management Workshop, in conjunction with VLDB, Riva del Garda, Italy},
	title = {Query Log Attack on Encrypted Databases},
	year = {2013}
}

@inproceedings{abc,
	author = {Martin Kaufmann and Panagiotis Vagenas and Peter M. Fischer and Donald Kossmann and Franz F{\"a}rber},
	booktitle = {PVLDB},
	title = {Comprehensive and Interactive Temporal Query Processing with SAP HANA.},
	url = {http://www.vldb.org/pvldb/vol6/p1210-kaufmann.pdf},
	year = {2013}
}

@inproceedings{abc,
	author = {Jana Giceva and Tudor-Ioan Salomie and Adrian Sch{\"u}pbach and Gustavo Alonso and Timothy Roscoe},
	booktitle = {CIDR 2013, Sixth Biennial Conference on Innovative Data Systems Research, Asilomar, CA, USA},
	title = {COD: Database / Operating System Co-Design.},
	url = {http://www.cidrdb.org/cidr2013/Papers/CIDR13_Paper71.pdf},
	year = {2013}
}

@article{abc,
	author = {Chongling Nie and Louis Woods and Jens Teubner},
	journal = {ACM Transactions on Database Systems (TODS), vol. 38(4)},
	title = {XLynx\&$\#$151;An FPGA-based XML Filter for Hybrid XQuery Processing.},
	year = {2013}
}

@article{abc,
	author = {Ankit Singla and Brighten Godfrey and Alexandra Kolla},
	journal = {CoRR},
	title = {High Throughput Data Center Topology Design.},
	url = {http://arxiv.org/abs/1309.7066},
	year = {2013}
}

@inproceedings{abc,
	author = {Michael Anderson and Dolan Antenucci and Victor Bittorf and Matthew Burgess and Michael J. Cafarella and Arun Kumar and Feng Niu and Yongjoo Park and Christopher R{\'e} and Ce Zhang},
	booktitle = {CIDR 2013, Sixth Biennial Conference on Innovative Data Systems Research, Asilomar, CA, USA},
	title = {Brainwash: A Data System for Feature Engineering.},
	url = {http://www.cidrdb.org/cidr2013/Papers/CIDR13_Paper82.pdf},
	year = {2013}
}

@article{abc,
	author = {Ankit Singla and Brighten Godfrey and Kevin R. Fall and Gianluca Iannaccone and Sylvia Ratnasamy},
	journal = {CoRR},
	title = {Scalable Routing on Flat Names},
	url = {http://arxiv.org/abs/1302.6156},
	year = {2013}
}

@inproceedings{abc,
	author = {Nihal Dindar and Nesime Tatbul and Ren{\'e}e J. Miller and Laura M. Haas and Irina Botan},
	booktitle = {VLDB J.},
	title = {Modeling the execution semantics of stream processing engines with SECRET.},
	url = {http://dx.doi.org/10.1007/s00778-012-0297-3},
	year = {2013}
}

@inproceedings{abc,
	author = {Cagri Balkesen and Louis Woods and Jens Teubner},
	booktitle = {Datenbanksysteme f{\"u}r Business, Technologie und Web (BTW), - Workshopband, 15. Fachtagung des GI-Fachbereichs "Datenbanken und Informationssysteme" (DBIS), 11.-15.3.2013 in Magdeburg, Germany. Proceedings},
	title = {Tutorium: Neue Hardwarearchitekturen f{\"u}r das Datenmanagement (DPMH).},
	year = {2013}
}

@inproceedings{abc,
	author = {Karolina Alexiou and Donald Kossmann and Per-Ake Larson},
	booktitle = {PVLDB},
	title = {Adaptive Range Filters for Cold Data: Avoiding Trips to Siberia.},
	url = {http://www.vldb.org/pvldb/vol6/p1714-kossmann.pdf},
	year = {2013}
}

@article{abc,
	author = {Anja Gruenheid and Donald Kossmann and Besmira Nushi and Yuri Gurevich},
	journal = {Bulletin of the EATCS},
	title = {When is A=B?},
	url = {http://eatcs.org/beatcs/index.php/beatcs/article/view/206},
	year = {2013}
}

@article{abc,
	author = {Hongyi Xin and Donghyuk Lee and Farhad Hormozdiari and Samihan Yedkar and Onur Mutlu and Can Alkan},
	journal = {BMC Genomics},
	title = {Accelerating read mapping with FastHASH.},
	url = {http://dx.doi.org/10.1186/1471-2164-14-S1-S13},
	year = {2013}
}

@inproceedings{abc,
	abstract = {Many problems in machine learning can be solved by rounding the solution of an appropriate linear program (LP). This paper shows that we can recover solutions of comparable quality by rounding an approximate LP solution instead of the ex- act one. These approximate LP solutions can be computed efficiently by applying a parallel stochastic-coordinate-descent method to a quadratic-penalty formulation of the LP. We derive worst-case runtime and solution quality guarantees of this scheme using novel perturbation and convergence analysis. Our experiments demonstrate that on such combinatorial problems as vertex cover, independent set and multiway-cut, our approximate rounding scheme is up to an order of magnitude faster than Cplex (a commercial LP solver) while producing solutions of similar quality.},
	author = {Srikrishna Sridhar and Victor Bittorf and Ji Liu and Ce Zhang and Christopher R{\'e} and Stephen J. Wright},
	booktitle = {CoRR},
	title = {An Approximate, Efficient Solver for LP Rounding.},
	url = {http://arxiv.org/abs/1311.2661},
	venue = {-},
	year = {2013}
}

@techreport{abc,
	author = {Tahmineh Sanamrad and Lucas Braun and Andreas Marfurt and Donald Kossmann and Ramarathnam Venkatesan},
	title = {POP: A new Encryption Scheme for Dynamic Databases},
	year = {2013}
}

@inproceedings{abc,
	author = {Ioana Giurgiu and Claris Castillo and Asser N. Tantawi and Malgorzata Steinder},
	booktitle = {Middleware 2012 - ACM/IFIP/USENIX 13th International Middleware Conference, Montreal, QC, Canada},
	title = {Enabling Efficient Placement of Virtual Infrastructures in the Cloud.},
	url = {http://dx.doi.org/10.1007/978-3-642-35170-9_17},
	year = {2012}
}

@inproceedings{abc,
	author = {Ioana Giurgiu and Oriana Riva and Gustavo Alonso},
	booktitle = {Middleware 2012 - ACM/IFIP/USENIX 13th International Middleware Conference, Montreal, QC, Canada},
	title = {Dynamic Software Deployment from Clouds to Mobile Devices.},
	url = {http://dx.doi.org/10.1007/978-3-642-35170-9_20},
	year = {2012}
}

@mastersthesis{abc,
	author = {Matthias Wetter},
	school = {64},
	title = {Parallel Processing of Pattern Matching Queries},
	year = {2012}
}

@phdthesis{abc,
	author = {Adrian Sch{\"u}pbach},
	school = {20930},
	title = {Tackling OS Complexity with declarative techniques},
	year = {2012}
}

@phdthesis{abc,
	author = {Qin Yin},
	school = {20932},
	title = {Declarative Recource Management for Virtual Network Systems},
	year = {2012}
}