1,184 papers · page 17 of 60
There is growing uptake of shared memory parallelism in high performance computing, and this has increased the need for data race checking during the creation of new parallel codes or parallelizing existing sequential codes. While race checking concepts and implementations have b…
Error-bounded lossy compression is critical to the success of extreme-scale scientific research because of ever-increasing volumes of data produced by today's high-performance computing (HPC) applications. Not only can error-controlled lossy compressors significantly reduce the I…
While GPU utilization allows one to speed up computations to the orders of magnitude, memory management remains the bottleneck making it often a challenge to achieve the desired performance. Hence, different memory optimizations are leveraged to make memory being used more effect…
Latent Dirichlet Allocation (LDA) is a statistical approach for topic modeling with a wide range of applications. In spite of the significance, we observe very few attempts from system track to improve LDA, let alone the algorithm and system codesigned efforts. To this end, we pr…
The performance of many parallel applications has failed to scale as fast as successive generations of hardware on which these applications execute. To understand the cause of scalability losses, experts use performance tools to monitor and analyze application behavior. Profiles …
A finite-state machine (FSM) is a key component for many important applications, such as Huffman decoding, regular expression matching and HTML tokenization. Due to its inherent dependencies and unpredictable memory access pattern, FSM computations are considered to be extremely …
The use of futures can generate arbitrary dependences in the computation, making it difficult to detect races efficiently. Algorithms proposed by prior work to detect races on programs with futures all have to execute the program sequentially. We propose F-Order, the first known …
In this paper, we present an optimized implementation for single-precision Winograd convolution on NVIDIA Volta and Turing GPUs. Compared with the state-of-the-art Winograd convolution in cuDNN 7.6.1, our implementation achieves up to 2.13X speedup on Volta V100 and up to 2.65X s…
To support performance measurement and analysis of GPU-accelerated applications, we extended the HPCToolkit performance tools with several novel features. To support efficient monitoring of accelerated applications, HPCToolkit employs a new wait-free data structure to coordinate …
As one of the most important data structures used in algorithm design and programming, balanced search trees are widely used in real-world applications for organizing data. Answering the challenges thrown up by modern large-volume and ever-changing data, it is important to consid…
Over the past decade, many programming languages and systems for parallel-computing have been developed, e.g., Fork/Join and Habanero Java, Parallel Haskell, Parallel ML, and X10. Although these systems raise the level of abstraction for writing parallel codes, performance contin…
This paper is the first to specify blockchains as a composition of abstract data types all together with a hierarchy of consistency criteria that formally characterizes the histories admissible for distributed programs that use them. The paper presents as well some results on imp…
We engineer a GPU implementation of a B-Tree that supports concurrent queries (point, range, and successor) and updates (insertions and deletions). Our B-tree outperforms the state of the art, a GPU log-structured merge tree (LSM) and a GPU sorted array. In particular, point and …
Open nesting allows replacing the automatic detection of conflicting memory accesses used in transactional memory (TM) with programmer-specified higher-level conflict detection. Higher-level conflict detection allows removing conflicts of commuting operations where the automatic …
With the rapid change of computing architectures, and variety of programming models; the ability to develop performance portable applications has become of great importance. This is particularly true in large production codes where developing and maintaining hardware specific ver…
Non-volatile memory (NVM) promises persistent main memory that remains correct despite loss of power. Since caches are expected to remain volatile, concurrent algorithms must be redesigned to ensure a consistent state after a system crash, and to continue the execution upon recov…
In this tutorial participants learn how to build their own parallel programming language features by developing them as language extensions in the ableC [4] extensible C compiler framework. By implementing new parallel programming abstractions as language extensions one can build…
Asynchronous task-based programming models are gaining popularity to address programmability and performance challenges in high performance computing. One of the main attractions of these models and runtimes is their potential to automatically expose and exploit overlap of comput…
Scale-out has become the standard answer to data analysis, machine learning and many other fields. Contrary to common belief, scale-up machines can outperform scale-out clusters for a considerable portion of tasks. However, those scale-up machines are not economical and may not b…
This paper develops an operational semantics for a release-acquire fragment of the C11 memory model with relaxed accesses. We show that the semantics is both sound and complete with respect to the axiomatic model of Batty et al. The semantics relies on a per-thread notion of obse…