high performance computing on graphics processing units: hgpu.org

hgpu.org » Performance

clpeak – peak performance of your opencl device

Krishnaraj Bhat

Source codes

Tags: ATI, Benchmarking, Computer science, nVidia, OpenCL, Package, Performance

January 23, 2014 by hgpu

Improving the Performance of CA-GMRES on Multicores with Multiple GPUs

Ichitaro Yamazaki, Hartwig Anzt, Stanimire Tomov, Mark Hoemmenx, Jack Dongarra

View

Download (PDF)

Tags: Computer science, CUDA, Linear Algebra, nVidia, Performance, Tesla M2090

January 18, 2014 by hgpu

Performance Engineering for a Medical Imaging Application on the Intel Xeon Phi Accelerator

Johannes Hofmann, Jan Treibig, Georg Hager, Gerhard Wellein

View

Download (PDF)

Tags: Benchmarking, Computed tomography, Computer science, CT, Image reconstruction, Intel Xeon Phi, Medicine, Performance

January 17, 2014 by hgpu

MRPB: Memory Request Prioritization for Massively Parallel Processors

Wenhao Jia, Kelly A. Shaw, Margaret Martonosi

View

Download (PDF)

Tags: Computer science, CUDA, GPGPU-sim, nVidia, Performance, Tesla C2050

January 16, 2014 by hgpu

Towards Portable Performance for Explicit Hydrodynamics Codes

A. C. Mallinson, D. A. Beckingsale, W. P. Gaudin, J. A. Herdman, S. A. Jarvis

View

Download (PDF)

Source codes

Tags: APU, ATI, ATI FirePro V7800, Computer science, Fluid dynamics, MPI, nVidia, OpenCL, Package, Performance, Tesla K20

January 14, 2014 by hgpu

Warp-Level Divergence in GPUs: Characterization, Impact, and Mitigation

Ping Xiang, Yi Yang, Huiyang Zhou

View

Download (PDF)

Tags: Computer science, CUDA, GPGPU-sim, nVidia, nVidia GeForce GTX 480, Performance

January 12, 2014 by hgpu

Conditional component composition for GPU-based systems

Usman Dastgeer, Christoph W. Kessler

View

Download (PDF)

Tags: Computer science, CUDA, nVidia, Performance, Tesla C2050

January 6, 2014 by hgpu

Accelerating Simulation Codes through the GeMTC Framework

Digvijay Singh Gahlot, Scott Krieder, Ioan Raicu

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, nVidia, nVidia GeForce GTX 480, Package, Performance

January 3, 2014 by hgpu

Efficiency analysis of a physical problem: Different parallel computational approaches for a dynamical integrator evolution

Adriana Gaudiani, Alejandro Soba, M. Florencia Carusela

View

Download (PDF)

Tags: Algorithms, Computer science, CUDA, MPI, nVidia, nVidia GeForce GTX 560 Ti, Performance

December 25, 2013 by hgpu

Adaptive Task Size Control on High Level Programming for GPU/CPU Work Sharing

Tetsuya Odajima, Taisuke Boku, Mitsuhisa Sato, Toshihiro Hanawa, Yuetsu Kodama, Raymond Namyst, Samuel Thibault, Olivier Aumage

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Heterogeneous systems, nVidia, Package, Performance, Task scheduling, Tesla M2090

December 25, 2013 by hgpu

Energy Auto-tuning using the Polyhedral Approach

Wei Wang, John Cavazos, Allan Porterfield

View

Download (PDF)

Tags: Computer science, Intel Xeon Phi, Performance

December 22, 2013 by hgpu

Tesla vs. Xeon Phi vs. Radeon A Compiler Writer’s Perspective

Brent Leback, Douglas Miles, Michael Wolfe

View

Download (PDF)

Tags: ATI, Compilers, Computer science, Intel Xeon Phi, nVidia, OpenCL, Performance, Tesla

December 18, 2013 by hgpu

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

MSCCL++: Rethinking GPU Communication Abstractions for Cutting-edge AI Applications

Benchmark compute shader of Unity against InteropUnityCUDA

InteropUnityCUDA: A Tool for Interoperability Between Unity and CUDA

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

* * *

high performance computing on graphics processing units: hgpu.org

clpeak – peak performance of your opencl device

Improving the Performance of CA-GMRES on Multicores with Multiple GPUs

Performance Engineering for a Medical Imaging Application on the Intel Xeon Phi Accelerator

MRPB: Memory Request Prioritization for Massively Parallel Processors

Towards Portable Performance for Explicit Hydrodynamics Codes

Warp-Level Divergence in GPUs: Characterization, Impact, and Mitigation

Conditional component composition for GPU-based systems

Accelerating Simulation Codes through the GeMTC Framework

Efficiency analysis of a physical problem: Different parallel computational approaches for a dynamical integrator evolution

Adaptive Task Size Control on High Level Programming for GPU/CPU Work Sharing

Energy Auto-tuning using the Polyhedral Approach

Tesla vs. Xeon Phi vs. Radeon A Compiler Writer’s Perspective

Recent source codes

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

Shamrock: Multi-GPU hydrodynamics for astrophysics

LLMPerf: GPU Performance Modeling meets Large Language Models

Most viewed papers (last 30 days)