high performance computing on graphics processing units: hgpu.org

Programming

hgpu.org » Programming » CUDA

Adaptivity in AdaptiveCpp: Optimizing Performance by Leveraging Runtime Information During JIT-Compilation

Aksel Alpay, Vincent Heuveline

View

Download (PDF)

Source codes

Tags: AMD Radeon Pro VII, ATI, Benchmarking, Computer science, CUDA, HIP, Intel UHD 630, nVidia, nVidia RTX A5000, Package, Performance, SYCL

October 19, 2025 by hgpu

Compiler and Runtime Systems for Generative AI Models

Zihao Ye

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Deep learning, Heterogeneous systems, Machine learning, nVidia, nVidia GeForce RTX 3070, nVidia H100, Package, Tesla V100

October 19, 2025 by hgpu

Neptune: Advanced ML Operator Fusion for Locality and Parallelism on GPUs

Yifan Zhao, Egan Johnson, Prasanth Chatarasi, Vikram Adve, Sasa Misailovic

View

Download (PDF)

Source codes

Tags: AMD Radeon Instinct MI300X, ATI, Computer science, CUDA, Deep learning, nVidia, nVidia A100, nVidia RTX A5000, nVidia RTX A6000, Package, Performance, ROCm

October 19, 2025 by hgpu

A Performance Portable Matrix Free Dense MTTKRP in GenTen

Gabriel Kosmacher, Eric T. Phipps, Sivasankaran Rajamanickam

View

Download (PDF)

Source codes

Tags: Algorithms, Computer science, CUDA, Kokkos, Mathematical Software, nVidia, nVidia H100, OpenMP, Package

October 19, 2025 by hgpu

ConCuR: Conciseness Makes State-of-the-Art Kernel Generation

Lingcheng Kong, Jiateng Wei, Hanzhang Shen, Huan Wang

View

Download (PDF)

Source codes

Tags: AI, Code generation, Computer science, CUDA, Deep learning, LLM, Machine learning, nVidia, Package

October 12, 2025 by hgpu

High-Performance Computing: from Optimization to Automation

Bérenger Bramas

View

Download (PDF)

Tags: AMD Radeon Instinct MI210, ATI, Computer science, CUDA, HIP, HPC, nVidia, nVidia A100, nVidia T600, Performance, Thesis

October 12, 2025 by hgpu

EvoEngineer: Mastering Automated CUDA Kernel Code Evolution with Large Language Models

Ping Guo, Chenyu Zhu, Siyuan Chen, Fei Liu, Xi Lin, Zhichao Lu, Qingfu Zhang

View

Download (PDF)

Tags: AI, Code generation, Computer science, CUDA, Deep learning, LLM, nVidia, nVidia GeForce RTX 4090, nVidia H100, PyTorch

October 12, 2025 by hgpu

VibeCodeHPC: An Agent-Based Iterative Prompting Auto-Tuner for HPC Code Generation Using LLMs

Shun-ichiro Hayashi, Koki Morita, Daichi Mukunoki, Tetsuya Hoshino, Takahiro Katagiri

View

Download (PDF)

Source codes

Tags: AI, Code generation, Computer science, CUDA, HPC, LLM, nVidia, OpenACC, OpenMP, Package, Tesla V100

October 5, 2025 by hgpu

Compile-Time Resource Safety for GPU APIs: A Low-Overhead Typestate Framework

Tihomir Thomas Bicanic

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, nVidia, nVidia GeForce RTX 3090, OpenCL, Package, Performance, Rust, Security

October 5, 2025 by hgpu

Opal: A Modular Framework for Optimizing Performance using Analytics and LLMs

Mohammad Zaeed, Tanzima Z. Islam, Vladimir Inđić

View

Download (PDF)

Tags: AI, AMD Radeon Instinct MI210, ATI, Computer science, CUDA, LLM, nVidia, nVidia H100, Performance, ROCm

October 5, 2025 by hgpu

TRUST: the HPC open-source CFD platform – from CPU to GPU

Elie Saikali∗ , Adrien Bruneton, Pierre Ledac, Remi Bourgeois

View

Download (PDF)

Source codes

Tags: AMD Radeon Instinct MI250A, AMD Radeon Instinct MI300A, ATI, cfd, CUDA, Fluid dynamics, HIP, MPI, Numerical simulation, nVidia, nVidia A100, OpenMP, Package

September 28, 2025 by hgpu

Towards GPU Parallelism Abstractions in Rust: A Case Study with Linear Pipelines

Leonardo Gibrowski Faé, Dalvan Griebler

View

Download (PDF)

Tags: Code generation, Computer science, CUDA, nVidia, nVidia GeForce RTX 3090, OpenCL, Rust, Tesla M40

September 28, 2025 by hgpu

KernelBenchX: A Comprehensive Benchmark for Evaluating LLM-Generated GPU Kernels

CuTile Benchmark Suite: Performance and Productivity Tradeoffs for GPU Kernel Programming on Blackwell Architecture

Evaluating CUDA Tile for AI Workloads on Hopper and Blackwell GPUs

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

See all packages

* * *

high performance computing on graphics processing units: hgpu.org

Programming

Adaptivity in AdaptiveCpp: Optimizing Performance by Leveraging Runtime Information During JIT-Compilation

Compiler and Runtime Systems for Generative AI Models

Neptune: Advanced ML Operator Fusion for Locality and Parallelism on GPUs

A Performance Portable Matrix Free Dense MTTKRP in GenTen

ConCuR: Conciseness Makes State-of-the-Art Kernel Generation

High-Performance Computing: from Optimization to Automation

EvoEngineer: Mastering Automated CUDA Kernel Code Evolution with Large Language Models

VibeCodeHPC: An Agent-Based Iterative Prompting Auto-Tuner for HPC Code Generation Using LLMs

Compile-Time Resource Safety for GPU APIs: A Low-Overhead Typestate Framework

Opal: A Modular Framework for Optimizing Performance using Analytics and LLMs

TRUST: the HPC open-source CFD platform – from CPU to GPU

Towards GPU Parallelism Abstractions in Rust: A Case Study with Linear Pipelines

Recent source codes

KernelBenchX: A Comprehensive Benchmark for Evaluating LLM-Generated GPU Kernels

CUDA Kernel Fusion Benchmarks

IntelliKit: Agent-first tooling for AMD hardware

DITRON: Distributed Compiler based on Triton for Parallel Systems

CuTile Benchmark Suite: Performance and Productivity Tradeoffs for GPU Kernel Programming on Blackwell Architecture

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

Most viewed papers (last 30 days)