high performance computing on graphics processing units: hgpu.org

Manuel López-Martínez, Germán Díaz-Flórez, Santiago Villagrana-Barraza, Luis O. Solís-Sánchez, Héctor A. Guerrero-Osuna, Genaro M. Soto-Zarazúa, Carlos A. Olvera-Olvera

View

Download (PDF)

Tags: CUDA, Deep learning, Distributed computing, HPC, Image processing, Neural networks, nVidia, nVidia GeForce GTX 1050 Ti

June 4, 2023 by hgpu

Implementation Techniques for SPMD Kernels on CPUs

Joachim Meyer, Aksel Alpay, Sebastian Hack, Holger Fröning, Vincent Heuveline

View

Download (PDF)

Source codes

Tags: Compilers, Computer science, CUDA, Heterogeneous systems, nVidia, OpenCL, Package, performance portability

June 4, 2023 by hgpu

Genomics-GPU: A Benchmark Suite for GPU-accelerated Genome Analysis

Zhuren Liu, Shouzhe Zhang, Justin Garrigus, Hui Zhao

View

Download (PDF)

Source codes

Tags: Benchmarking, Bioinformatics, Biology, Computer science, CUDA, Genomics, nVidia, nVidia GeForce RTX 3070, Package

May 28, 2023 by hgpu

Experiences Migrating CUDA to SYCL: A Molecular Docking Case Study

Leonardo Solis-Vasquez, Edward Mascarenhas, Andreas Koch

View

Download (PDF)

Source codes

Tags: Chemistry, Computer science, CUDA, molecular docking, nVidia, nVidia A100, oneAPI, Package, SYCL

May 28, 2023 by hgpu

PyTorch Hyperparameter Tuning – A Tutorial for spotPython

Thomas Bartz-Beielstein

View

Download (PDF)

Source codes

Tags: Computer science, Deep learning, Package, Python, PyTorch, Tutorial

May 28, 2023 by hgpu

Communication-minimizing Asynchronous Tensor Parallelism

Siddharth Singh, Zack Sating, Abhinav Bhatele

View

Download (PDF)

Tags: Computer science, CUDA, GPU cluster, Neural networks, nVidia, nVidia A100

May 28, 2023 by hgpu

ACRoBat: Optimizing Auto-batching of Dynamic Deep Learning at Compile Time

Pratik Fegade, Tianqi Chen, Phillip B. Gibbons, Todd C. Mowry

View

Download (PDF)

Tags: Code generation, Computer science, CUDA, Deep learning, nVidia, nVidia GeForce RTX 3070

May 28, 2023 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

Accelerating 128-bit Floating-Point Matrix Multiplication on FPGAs

Hybrid CPU/GPU/APU accelerated query, insert, update and erase operations in hash tables with string keys

GPU-Acceleration of Tensor Renormalization with PyTorch using CUDA

Compiler Technologies in Deep Learning Co-Design: A Survey

A High-Performance Computing Cluster for Distributed Deep Learning: A Practical Case of Weed Classification Using Convolutional Neural Network Models

Implementation Techniques for SPMD Kernels on CPUs

Genomics-GPU: A Benchmark Suite for GPU-accelerated Genome Analysis

Experiences Migrating CUDA to SYCL: A Molecular Docking Case Study

PyTorch Hyperparameter Tuning – A Tutorial for spotPython

Communication-minimizing Asynchronous Tensor Parallelism

ACRoBat: Optimizing Auto-batching of Dynamic Deep Learning at Compile Time

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)