high performance computing on graphics processing units: hgpu.org

Applications

hgpu.org » Applications

Automatic BLAS Offloading on Unified Memory Architecture: A Study on NVIDIA Grace-Hopper

Junjie Li, Yinzhi Wang, Xiao Liang, Hang Liu

View

Download (PDF)

Tags: BLAS, Chemistry, CUDA, nVidia, nVidia GH200, nVidia H100, Performance, Physics

May 5, 2024 by hgpu

Software Optimization and Orchestration for Heterogeneous and Distributed Architectures

Francesco Lumpp

View

Download (PDF)

Tags: Computer science, Heterogeneous systems, nVidia, nVidia Jetson AGX Xavier, nVidia Jetson TX2, Performance, Thesis

April 21, 2024 by hgpu

SimSYCL: A SYCL Implementation Targeting Development, Debugging, Simulation and Conformance

Peter Thoman, Fabian Knorr, Luigi Crisci

View

Download (PDF)

Source codes

Tags: Computer science, HPC, Package, Performance, SYCL

April 21, 2024 by hgpu

Efficient Approaches for GEMM Acceleration on Leading AI-Optimized FPGAs

Endri Taka, Dimitrios Gourounas, Andreas Gerstlauer, Diana Marculescu, Aman Arora

View

Download (PDF)

Tags: AI, Computer science, Deep learning, FPGA, GEMM, Matrix multiplication

April 21, 2024 by hgpu

Python-Based Quantum Chemistry Calculations with GPU Acceleration

Xiaojie Wu, Qiming Sun, Zhichen Pu, Tianze Zheng, Wenzhi Ma, Wen Yan, Xia Yu, Zhengxiao Wu, Mian Huo, Xiang Li, Weiluo Ren, Sheng Gong, Yumin Zhang, Weihao Gao

View

Download (PDF)

Source codes

Tags: Chemical Physics, Chemistry, Computational Physics, CUDA, nVidia, nVidia A100, Package, Python, Quantum Physics

April 21, 2024 by hgpu

Communication-Efficient Large-Scale Distributed Deep Learning: A Comprehensive Survey

Feng Liang, Zhen Zhang, Haifeng Lu, Victor C. M. Leung, Yanyi Guo, Xiping Hu

View

Download (PDF)

Tags: Computer science, CUDA, Deep learning, Heterogeneous systems, nVidia, nVidia A100, survey, Task scheduling

April 21, 2024 by hgpu

A Systematic Literature Survey of Sparse Matrix-Vector Multiplication

Jianhua Gao, Bingjie Liu, Weixing Ji, Hua Huang

View

Download (PDF)

Tags: Computer science, FPGA, Heterogeneous systems, Linear Algebra, Machine learning, Overview, Sparse matrix

April 14, 2024 by hgpu

OpenMP offload at the Exascale using Intel GPU Max 1550: evaluation of STREAmS compressible solver

Francesco Salvadore, Giacomo Rossi, Srikanth Sathyanarayana, Matteo Bernardini

View

Download (PDF)

Tags: AMD Radeon Instinct MI250X, ATI, Benchmarking, cfd, Compression, Fluid dynamics, Intel, Intel Data Center GPU Max 1550, nVidia, nVidia A100, OpenMP

April 14, 2024 by hgpu

Balancing Tracking Granularity and Parallelism in Many-Task Systems: The Horizons Approach

Peter Thoman, Philip Salzmann

View

Download (PDF)

Source codes

Tags: Benchmarking, Computer science, GPU cluster, HPC, nVidia, nVidia V100, Package, SYCL

April 14, 2024 by hgpu

QArray: a GPU-accelerated constant capacitance model simulator for large quantum dot arrays

Barnaby van Straaten, Joseph Hickie, Lucas Schorling, Jonas Schuff, Federico Fedele, Natalia Ares

View

Download (PDF)

Source codes

Tags: Condensed matter, Machine learning, Mesoscale and Nanoscale Physics, nVidia, nVidia GeForce GTX 1080 Ti, Package, Physics, Python, Rust

April 14, 2024 by hgpu

High Performance Privacy Preserving AI

Jayavanth Shenoy, Patrick Grinaway, Shriphani Palakodety

View

Download (PDF)

Tags: AI, Artificial intelligence, Book, Computer science, Neural networks, Security

April 14, 2024 by hgpu

94% on CIFAR-10 in 3.29 Seconds on a Single GPU

Keller Jordan

View

Download (PDF)

Source codes

Tags: Computer science, Computer vision, Image processing, Machine learning, nVidia

April 7, 2024 by hgpu

MegaTrain: Full Precision Training of 100B+ Parameter Large Language Models on a Single GPU

Device Virtual Machine (DVM)

DVM: Real-Time Kernel Generation for Dynamic AI Models

Agentic Code Optimization via Compiler-LLM Cooperation

AutoKernel: Autoresearch for GPU kernels. Give it any PyTorch model, go to sleep, wake up to optimized Triton kernels

AutoKernel: Autonomous GPU Kernel Optimization via Iterative Agent-Driven Search

Triton-Sanitizer: A Fast and Device-Agnostic Memory Sanitizer for Triton with Rich Diagnostic Context

LLM.Q: Quantized LLM training in pure CUDA/C++

LLMQ: Efficient Lower-Precision LLM Training for Consumer GPUs

SOL-ExecBench: Speed-of-Light Benchmarking for Real-World GPU Kernels Against Hardware Limits

* * *

high performance computing on graphics processing units: hgpu.org

Applications

Automatic BLAS Offloading on Unified Memory Architecture: A Study on NVIDIA Grace-Hopper

Software Optimization and Orchestration for Heterogeneous and Distributed Architectures

SimSYCL: A SYCL Implementation Targeting Development, Debugging, Simulation and Conformance

Efficient Approaches for GEMM Acceleration on Leading AI-Optimized FPGAs

Python-Based Quantum Chemistry Calculations with GPU Acceleration

Communication-Efficient Large-Scale Distributed Deep Learning: A Comprehensive Survey

A Systematic Literature Survey of Sparse Matrix-Vector Multiplication

OpenMP offload at the Exascale using Intel GPU Max 1550: evaluation of STREAmS compressible solver

Balancing Tracking Granularity and Parallelism in Many-Task Systems: The Horizons Approach

QArray: a GPU-accelerated constant capacitance model simulator for large quantum dot arrays

High Performance Privacy Preserving AI

94% on CIFAR-10 in 3.29 Seconds on a Single GPU

Recent source codes

MegaTrain: Full Precision Training of 100B+ Parameter Large Language Models on a Single GPU

Device Virtual Machine (DVM)

Agentic Code Optimization via Compiler-LLM Cooperation

AutoKernel: Autoresearch for GPU kernels. Give it any PyTorch model, go to sleep, wake up to optimized Triton kernels

Triton-Sanitizer: A Fast and Device-Agnostic Memory Sanitizer for Triton with Rich Diagnostic Context

LLM.Q: Quantized LLM training in pure CUDA/C++

SOL-ExecBench: Speed-of-Light Benchmarking for Real-World GPU Kernels Against Hardware Limits

True 4-Bit Quantized CNN Training on CPU

cuFuzz: A GPU-oriented coverage-guided fuzzer for userland CUDA application

KernelSkill: A Multi-Agent Framework for GPU Kernel Optimization

Most viewed papers (last 30 days)