high performance computing on graphics processing units: hgpu.org

hgpu.org » Performance

Implementing the Himeno benchmark with CUDA on GPU clusters

Everett H. Phillips, Massimiliano Fatica

Tags: Benchmarking, Computer science, CUDA, GPU cluster, nVidia, Performance, Tesla C1060

March 16, 2011 by hgpu

Patterns of Inefficient Performance Behavior in GPU Applications

Dominic Eschweiler, Daniel Becker, Felix Wolf

View

Download (PDF)

Tags: Computer science, CUDA, nVidia, nVidia GeForce GTX 480, Optimization, Performance, Tesla T10

March 16, 2011 by hgpu

General-purpose molecular dynamics simulations on GPU-based clusters

Christian R. Trott, Lars Winterfeld, Paul S. Crozier

View

Download (PDF)

Source codes

Tags: Computational Physics, Condensed matter, CUDA, GPU cluster, Materials Science, Molecular dynamics, MPI, nVidia, nVidia GeForce GTX 280, nVidia GeForce GTX 295, Package, Performance, Physics, Tesla C1060, Tesla S1070

March 8, 2011 by hgpu

Non-blocking programming on multi-core graphics processors: (extended asbtract)

Phuong Hoai Ha, Philippas Tsigas, Otto J. Anshus

View

Download (PDF)

Tags: Computer science, CUDA, Memory model, nVidia, nVidia GeForce 8800 GTX, Performance, Programming techniques

March 7, 2011 by hgpu

Performance study of mapping irregular computations on GPUs

Steven Solomon, Parimala Thulasiraman

View

Download (PDF)

Tags: Computer science, CUDA, nVidia, nVidia GeForce GTX 260, Performance, Presentation

March 6, 2011 by hgpu

Tuned and asynchronous stencil kernels for CPU/GPU systems (thesis)

Sundaresan Venkatasubramanian

View

Download (PDF)

Tags: Computer science, CUDA, nVidia, nVidia Quadro FX 570, Performance, Tesla C1060, Tesla C870, Thesis

March 6, 2011 by hgpu

Speculative Execution on Multi-GPU Systems

Gregory Diamos, Sudhakar Yalamanchili

View

Download (PDF)

Tags: Computer science, CUDA, GPU cluster, nVidia, nVidia GeForce 9800 GX2, Optimization, Performance, Tesla S870

March 6, 2011 by hgpu

Task management for irregular-parallel workloads on the GPU

Stanley Tzeng, Anjul Patney, John D. Owens

View

Download (PDF)

Tags: Computer science, CUDA, nVidia, nVidia GeForce GTX 280, Optimization, Performance, Presentation, Task scheduling

March 6, 2011 by hgpu

Dynamic load balancing on single- and multi-GPU systems

Long Chen, Oreste Villa, Sriram Krishnamoorthy, Guang R. Gao

View

Download (PDF)

Tags: Computer science, CUDA, nVidia, Optimization, Performance, Task scheduling, Tesla C1060

March 6, 2011 by hgpu

Parallel Computing: The Elephant in the Room

Patrick H. Madden

View

Download (PDF)

Tags: Algorithms, Computer science, Performance, Review

March 5, 2011 by hgpu

Inter-Block GPU Communication via Fast Barrier Synchronization

Shucai Xiao, Wu-chun Feng

View

Download (PDF)

Tags: Algorithms, Computer science, CUDA, FFT, nVidia, nVidia GeForce GTX 280, Performance, Sorting

March 5, 2011 by hgpu

Real-Time Multiprocessor Systems with GPUs

Glenn A. Elliott and James H. Anderson

View

Download (PDF)

Tags: Computer science, CUDA, nVidia, nVidia GeForce GTX 285, Performance, Task scheduling

March 3, 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

Implementing the Himeno benchmark with CUDA on GPU clusters

Patterns of Inefficient Performance Behavior in GPU Applications

General-purpose molecular dynamics simulations on GPU-based clusters

Non-blocking programming on multi-core graphics processors: (extended asbtract)

Performance study of mapping irregular computations on GPUs

Tuned and asynchronous stencil kernels for CPU/GPU systems (thesis)

Speculative Execution on Multi-GPU Systems

Task management for irregular-parallel workloads on the GPU

Dynamic load balancing on single- and multi-GPU systems

Parallel Computing: The Elephant in the Room

Inter-Block GPU Communication via Fast Barrier Synchronization

Real-Time Multiprocessor Systems with GPUs

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)