high performance computing on graphics processing units: hgpu.org

hgpu.org » Performance

Enabling OS Research by Inferring Interactions in the Black-Box GPU Stack

Konstantinos Menychtas, Kai Shen, Michael L. Scott

View

Tags: Computer science, CUDA, nVidia, nVidia GeForce GTX 275, nVidia GeForce GTX 670, nVidia Quadro NVS 295, Performance

May 25, 2013 by hgpu

OpenCL Performance Evaluation on Modern Multi Core CPUs

Joo Hwan Lee, Kaushik Patel, Nimit Nigania, Hyojong Kim, Hyesoon Kim

View

Download (PDF)

Tags: Computer science, Heterogeneous systems, nVidia, nVidia GeForce GTX 580, OpenCL, Performance

May 25, 2013 by hgpu

GEMTC: GPU Enabled Many-Task Computing

Scott Krieder, Ioan Raicu

View

Download (PDF)

Tags: Computer science, CUDA, nVidia, nVidia GeForce GTX 670, Performance

May 25, 2013 by hgpu

Sequential Consistency for Heterogeneous-Race-Free: Programmer-centric Memory Models for Heterogeneous Platforms

Derek R. Hower, Bradford M. Beckmann, Benedict R. Gaster, Blake A. Hechtman, Mark D. Hill, Steven K. Reinhardt, David A. Wood

View

Download (PDF)

Tags: Computer science, CUDA, Heterogeneous systems, Memory model, nVidia, OpenCL, Performance

May 23, 2013 by hgpu

Evaluating the Performance of Legacy Applications on Emerging Parallel Architectures

Simon John Pennycook

View

Download (PDF)

Source codes

Tags: Algorithms, ATI, ATI FirePro V7800, Benchmarking, Computer science, CUDA, MPI, nVidia, nVidia GeForce 8400 GS, nVidia GeForce 9800 GT, nVidia GeForce GTX 680, OpenCL, Performance, Tesla C1060, Tesla C2050, Thesis

May 21, 2013 by hgpu

An Investigation of the Performance Portability of OpenCL

S.J. Pennycook, S.D. Hammond, S.A. Wright, J.A. Herdman, I. Miller, S.A. Jarvis

View

Download (PDF)

Source codes

Tags: ATI, ATI FirePro V7800, Benchmarking, Computer science, CUDA, Fortran, MPI, nVidia, OpenCL, Package, Performance, Tesla C1060, Tesla C2050

May 21, 2013 by hgpu

Exploiting Uniform Vector Instructions for GPGPU Performance, Energy Efficiency, and Opportunistic Reliability Enhancement

Ping Xiang, Yi Yang, Mike Mantor, Norm Rubin, Lisa R. Hsu, Huiyang Zhou

View

Download (PDF)

Tags: Computer science, GPGPU-sim, nVidia, nVidia GeForce GTX 285, nVidia GeForce GTX 480, Performance

May 19, 2013 by hgpu

Parallel Zonal Summations of Large-Scale Species Occurrence Data on Hybrid CPU-GPU Systems

Jianting Zhang, Simin You

View

Download (PDF)

Tags: CUDA, Data parallelism, Earth and Space Sciences, Filtering, Geoscience, nVidia, nVidia Quadro FX 6000, Performance

May 19, 2013 by hgpu

Performance Evaluation of CPU-GPU communication Depending on the Characteristic of Co-Located Workloads

Dongyou Seo, Shin-gyu Kim, Hyeonsang Eom, Heon Y. Yeom

View

Download (PDF)

Tags: CUDA, nVidia, nVidia GeForce GTX 580, Performance

May 17, 2013 by hgpu

GPUWattch: Enabling Energy Optimizations in GPGPUs

Jingwen Leng, Tayler Hetherington, Ahmed ElTantawy, Syed Gilani, Nam Sung Kim, Tor M. Aamodt, Vijay Janapa Reddi

View

Download (PDF)

Tags: Computer science, CUDA, GPGPU-sim, nVidia, nVidia GeForce GTX 480, nVidia Quadro FX 5600, Performance

May 4, 2013 by hgpu

Impact of Warp Formation on GPU Performance

Hong Jun Choi, Dong Oh Son, Cheol Hong Kim

View

Download (PDF)

Tags: Computer science, GPGPU-sim, nVidia, Performance

May 3, 2013 by hgpu

OpenMP performance analysis for many-core platforms with non-uniform memory access

Pablo Gonzalez de Aledo Marugan, Javier Gonzalez Bayon, Pablo Sanchez Espeso, Juan Casal Martin

View

Download (PDF)

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

May 2, 2013 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

Enabling OS Research by Inferring Interactions in the Black-Box GPU Stack

OpenCL Performance Evaluation on Modern Multi Core CPUs

GEMTC: GPU Enabled Many-Task Computing

Sequential Consistency for Heterogeneous-Race-Free: Programmer-centric Memory Models for Heterogeneous Platforms

Evaluating the Performance of Legacy Applications on Emerging Parallel Architectures

An Investigation of the Performance Portability of OpenCL

Exploiting Uniform Vector Instructions for GPGPU Performance, Energy Efficiency, and Opportunistic Reliability Enhancement

Parallel Zonal Summations of Large-Scale Species Occurrence Data on Hybrid CPU-GPU Systems

Performance Evaluation of CPU-GPU communication Depending on the Characteristic of Co-Located Workloads

GPUWattch: Enabling Energy Optimizations in GPGPUs

Impact of Warp Formation on GPU Performance

OpenMP performance analysis for many-core platforms with non-uniform memory access

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)