high performance computing on graphics processing units: hgpu.org

hgpu.org » Performance

Towards metaprogramming for parallel systems on a chip

Lee Howes, Anton Lokhmotov, Alastair F. Donaldson, Paul H.J. Kell

View

Download (PDF)

Tags: Computer science, CUDA, nVidia, nVidia GeForce GTX 280, Performance, Programming techniques

August 22, 2011 by hgpu

Top ten ways to make formal methods for HPC practical

Ganesh Gopalakrishnan, Robert M. Kirby

View

Download (PDF)

Tags: Computer science, CUDA, MPI, nVidia, OpenCL, OpenMP, Performance

August 22, 2011 by hgpu

Reusable software components for accelerator-based clusters

M. Mustafa Rafique, Ali R. Butt, Eli Tilevich

View

Download (PDF)

Tags: Computer science, CUDA, Heterogeneous systems, nVidia, nVidia GeForce 9600 M GT, Performance, Playstation

August 22, 2011 by hgpu

Accelerating Haskell array codes with multicore GPUs

Manuel M.T. Chakravarty, Gabriele Keller, Sean Lee, Trevor L. McDonell, Vinod Grover

View

Download (PDF)

Tags: Code generation, Computer science, CUBLAS, CUDA, Data parallelism, nVidia, Performance, Programming Languages, Tesla T10

August 22, 2011 by hgpu

Mind the gap!: bridging the dichotomy of design and implementation

Donna Kaminskyj Long, Liam Kiemele, Celina Gibbs, Andrew Brownsword, Yvonne Coady

View

Download (PDF)

Tags: Computer science, Linear Algebra, OpenCL, Performance, Presentation, Programming techniques

August 21, 2011 by hgpu

Reducing data access latency in SDSM systems using runtime optimizations

Javier Bueno, Xavier Martorell, Juan Jose Costa, Toni Cortes, Eduard Ayguade, Guansong Zhang, Christopher Barton, Raul Silvera

View

Download (PDF)

Tags: Computer science, Distributed data structures, OpenCL, OpenMP, Performance, Programming Languages

August 21, 2011 by hgpu

A new method for GPU based irregular reductions and its application to k-means clustering

Balaji Dhanasekaran, Norman Rubin

View

Download (PDF)

Tags: Algorithms, ATI, ATI Radeon HD 5870, Computer science, Data mining, Heterogeneous systems, OpenCL, Performance, Programming techniques

August 21, 2011 by hgpu

Multi- and many-core data mining with adaptive sparse grids

Alexander Heinecke, Dirk Pfluger

View

Download (PDF)

Tags: Algorithms, Computer science, Data mining, Mathematical Software, nVidia, nVidia GeForce GTX 470, OpenCL, Performance, Presentation

August 21, 2011 by hgpu

Sponge: portable stream programming on graphics engines

Amir H. Hormati, Mehrzad Samadi, Mark Woh, Trevor Mudge, Scott Mahlke

View

Download (PDF)

Tags: Compilers, Computer science, CUDA, nVidia, nVidia GeForce GTX 285, Optimization, Performance, Programming Languages

August 21, 2011 by hgpu

Breaking the GPU programming barrier with the auto-parallelising SAC compiler

Jing Guo, Jeyarajan Thiyagalingam, Sven-Bodo Scholz

Tags: Algorithms, Compilers, Computer science, CUDA, nVidia, Performance, Programming Languages

August 21, 2011 by hgpu

Parallel 3D multigrid methods on the STI cell BE architecture

Fabian Oboril, Jan-Philipp Weiss, Vincent Heuveline

View

Download (PDF)

Tags: Cell processor, Computer science, nVidia, nVidia GeForce GTX 280, OpenCL, Performance

August 20, 2011 by hgpu

A balanced programming model for emerging heterogeneous multicore systems

Wei Liu, Brian Lewis, Xiaocheng Zhou, Hu Chen, Ying Gao, Shoumeng Yan, Sai Luo, Bratin Saha

View

Download (PDF)

Tags: Computer science, Heterogeneous systems, Larrabee, OpenCL, Performance

August 19, 2011 by hgpu

Data-efficient LLM Fine-tuning for Code Generation

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

DeepCompile: A Compiler-Driven Approach to Optimizing Distributed Deep Learning Training

Large Language Model Powered C-to-CUDA Code Translation: A Novel Auto-Parallelization Framework

GigaAPI: a user-space API that simplifies multi-GPU programming, bridging the gap between the capabilities of parallel GPU systems and the ability of developers to harness their full potential

GigaAPI for GPU Parallelization

Coccinelle: a C code transformation engine using SmPL for matches, refactorings, and bug fixing

Advances in Semantic Patching for HPC-oriented Refactorings with Coccinelle

DuoReduce: MLIR's benchmark

Hardware-Assisted Software Testing and Debugging for Heterogeneous Computing

See all packages

* * *

high performance computing on graphics processing units: hgpu.org

Towards metaprogramming for parallel systems on a chip

Top ten ways to make formal methods for HPC practical

Reusable software components for accelerator-based clusters

Accelerating Haskell array codes with multicore GPUs

Mind the gap!: bridging the dichotomy of design and implementation

Reducing data access latency in SDSM systems using runtime optimizations

A new method for GPU based irregular reductions and its application to k-means clustering

Multi- and many-core data mining with adaptive sparse grids

Sponge: portable stream programming on graphics engines

Breaking the GPU programming barrier with the auto-parallelising SAC compiler

Parallel 3D multigrid methods on the STI cell BE architecture

A balanced programming model for emerging heterogeneous multicore systems

Recent source codes

PELSI: Power-Efficient Layer-Switched Inference

Ouroboros: Virtualized Queues for dynamic memory management

MSCCL++: A GPU-driven communication stack for scalable AI applications

Benchmark compute shader of Unity against InteropUnityCUDA

Data-efficient LLM Fine-tuning for Code Generation

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

Large Language Model Powered C-to-CUDA Code Translation: A Novel Auto-Parallelization Framework

GigaAPI: a user-space API that simplifies multi-GPU programming, bridging the gap between the capabilities of parallel GPU systems and the ability of developers to harness their full potential

Coccinelle: a C code transformation engine using SmPL for matches, refactorings, and bug fixing

DuoReduce: MLIR's benchmark

Most viewed papers (last 30 days)