high performance computing on graphics processing units: hgpu.org

hgpu.org » Performance

Dissecting the NVIDIA Hopper Architecture through Microbenchmarking and Multiple Level Analysis

Weile Luo, Ruibo Fan, Zeyu Li, Dayou Du, Hongyuan Liu, Qiang Wang, Xiaowen Chu

View

Tags: Benchmarking, Computer science, CUDA, Hardware Architecture, nVidia, nVidia A100, nVidia GeForce RTX 4090, nVidia H800, Performance, PTX

January 27, 2025 by hgpu

Boosting Performance of Iterative Applications on GPUs: Kernel Batching with CUDA Graphs

Jonah Ekelund, Stefano Markidis, Ivy Peng

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, FDTD, HIP, nVidia, nVidia A100, nVidia H100, Package, Performance

January 20, 2025 by hgpu

Debunking the CUDA Myth Towards GPU-based AI Systems

Yunjae Lee, Juntaek Lim, Jehyeon Bang, Eunyeong Cho, Huijong Jeong, Taesu Kim, Hyungjun Kim, Joonhyung Lee, Jinseop Im, Ranggi Hwang, Se Jung Kwon, Dongsoo Lee, Minsoo Rhu

View

Download (PDF)

Tags: AI, Benchmarking, Computer science, CUDA, Intel, Intel Gaudi-2, nVidia, nVidia A100, Performance

January 6, 2025 by hgpu

Reproducible Study and Performance Analysis of GPU Programming Paradigms: OpenACC vs. CUDA in Key Linear Algebra Computations

Ezhilmathi Krishnasamy, Pascal Bouvry

View

Download (PDF)

Source codes

Tags: BLAS, Computer science, CUDA, Differential equations, HPC, Linear Algebra, Matrix multiplication, nVidia, nVidia A100, OpenACC, Package, Partial differential equations, PDEs, Performance

December 24, 2024 by hgpu

Towards Performance-Aware Allocation for Accelerated Machine Learning on GPU-SSD Systems

Ayush Gundawar, Euijun Chung, Hyesoon Kim

View

Download (PDF)

Tags: Computer science, Hardware Architecture, Machine learning, Performance

December 15, 2024 by hgpu

Automating Energy-Efficient GPU Kernel Generation: A Fast Search-Based Compilation Approach

Yijia Zhang, Zhihong Gou, Shijie Cao, Weigang Feng, Sicheng Zhang, Guohao Dai, Ningyi Xu

View

Download (PDF)

Tags: Computer science, CUDA, Energy-efficient computing, Machine learning, Neural networks, nVidia, nVidia A100, nVidia GeForce RTX 4090, Performance

December 8, 2024 by hgpu

Hardware Accelerators for Artificial Intelligence

S M Mojahidul Ahsan, Anurag Dhungel, Mrittika Chowdhury, Md Sakib Hasan, Tamzidul Hoque

View

Download (PDF)

Tags: AI, Computer science, Hardware Architecture, Performance, survey

December 1, 2024 by hgpu

Understanding GEMM Performance and Energy on NVIDIA Ada Lovelace: A Machine Learning-Based Analytical Approach

Xiaoteng (Frank) Liu, Pavly Halim

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Energy-efficient computing, GEMM, Machine learning, Matrix multiplication, nVidia, nVidia GeForce RTX 4070, Package, Performance

December 1, 2024 by hgpu

Performance portability via C++ PSTL, SYCL, OpenMP, and HIP: the Gaia AVU-GSR case study

Giulio Malenza, Valentina Cesare, Marco Edoardo Santimaria, Robert Birke, Alberto Vecchiato, Ugo Becciani, Marco Aldinucci

View

Download (PDF)

Source codes

Tags: AMD Radeon Instinct MI250X, Astrophysics, ATI, Computer science, CUDA, HIP, HPC, nVidia, nVidia A100, nVidia H100, nVidia V100, OpenMP, Package, Performance, performance portability, SYCL, Tesla T4

November 24, 2024 by hgpu

GPUVM: GPU-driven Unified Virtual Memory

Nurlan Nazaraliyev, Elaheh Sadredini, Nael Abu-Ghazaleh

View

Download (PDF)

Tags: Computer science, CUDA, Memory, nVidia, Operating systems, Performance, Tesla V100

November 17, 2024 by hgpu

Context Parallelism for Scalable Million-Token Inference

Amy (Jie) Yang, Jingyi Yang, Aya Ibrahim, Xinfeng Xie, Bangsheng Tang, Grigory Sizov, Jeremy Reizenstein, Jongsoo Park, Jianyu Huang

View

Download (PDF)

Tags: Artificial intelligence, Benchmarking, Computer science, LLM, nVidia, nVidia H100, Performance

November 17, 2024 by hgpu

The Rewriting of DataRaceBench Benchmark for OpenCL Program Validations

Chia-Chen Hsu, Chun-Lin Huang, Chao-Lin Lee, Jenq-Kuen Lee, Pei-Hung Lin

View

Download (PDF)

Tags: Benchmarking, Computer science, LLVM, OpenCL, Performance

November 17, 2024 by hgpu

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

Shamrock: Multi-GPU hydrodynamics for astrophysics

The Shamrock code: I- Smoothed Particle Hydrodynamics on GPUs

LLMPerf: GPU Performance Modeling meets Large Language Models

Hercules: A Compiler for Productive Programming of Heterogeneous Systems

* * *

high performance computing on graphics processing units: hgpu.org

Dissecting the NVIDIA Hopper Architecture through Microbenchmarking and Multiple Level Analysis

Boosting Performance of Iterative Applications on GPUs: Kernel Batching with CUDA Graphs

Debunking the CUDA Myth Towards GPU-based AI Systems

Reproducible Study and Performance Analysis of GPU Programming Paradigms: OpenACC vs. CUDA in Key Linear Algebra Computations

Towards Performance-Aware Allocation for Accelerated Machine Learning on GPU-SSD Systems

Automating Energy-Efficient GPU Kernel Generation: A Fast Search-Based Compilation Approach

Hardware Accelerators for Artificial Intelligence

Understanding GEMM Performance and Energy on NVIDIA Ada Lovelace: A Machine Learning-Based Analytical Approach

Performance portability via C++ PSTL, SYCL, OpenMP, and HIP: the Gaia AVU-GSR case study

GPUVM: GPU-driven Unified Virtual Memory

Context Parallelism for Scalable Million-Token Inference

The Rewriting of DataRaceBench Benchmark for OpenCL Program Validations

Recent source codes

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

Hercules: A Compiler for Productive Programming of Heterogeneous Systems

Celerity Runtime: High-level C++ for Accelerator Clusters

wgpy: WebGL accelerated numpy-compatible array library for web browser

Microbenchmarking OpenMP target offload with Catch2

SUperman: Highly Efficient Permanent Computation Library

TransCL: An Automatic CUDA-to-OpenCL Programs Transformation Framework

Most viewed papers (last 30 days)