high performance computing on graphics processing units: hgpu.org

hgpu.org » ATI

HipKittens: Fast and Furious AMD Kernels

William Hu, Drew Wadsworth, Sean Siddens, Stanley Winata, Daniel Y. Fu, Ryann Swann, Muhammad Osama, Christopher Ré, Simran Arora

View

Download (PDF)

Source codes

Tags: AMD Radeon Instinct MI355X, ATI, Computer science, nVidia, nVidia B200, Package, Performance

November 16, 2025 by hgpu

MT4G: A Tool for Reliable Auto-Discovery of NVIDIA and AMD GPU Compute and Memory Topologies

Stepan Vanecek, Manuel Walter Mussbacher, Dominik Groessler, Urvij Saroliya, Martin Schulz

View

Download (PDF)

Source codes

Tags: AMD Radeon Instinct MI100, AMD Radeon Instinct MI210, AMD Radeon Instinct MI300X, ATI, Benchmarking, Computer science, CUDA, HIP, nVidia, nVidia A100, nVidia GeForce RTX 2080, nVidia H100, nVidia Quadro P 6000, nVidia V100, Package, PTX

November 16, 2025 by hgpu

AMD MI300X GPU Performance Analysis

Chandrish Ambati, Trung Diep

View

Download (PDF)

Tags: AMD Radeon Instinct MI300X, ATI, Benchmarking, Computer science, CUDA, HIP, nVidia, nVidia H100, Performance

November 9, 2025 by hgpu

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

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

Accelerating cosmological simulations on GPUs: a portable approach using OpenMP

M. D. Lepinzan, G. Lacopo, D. Goz, G. Taffoni, P. Monaco, P. J. Elahi, U. Varetto, M. Cytowski

View

Download (PDF)

Source codes

Tags: AMD Radeon Instinct MI250X, Astrophysics, ATI, Benchmarking, Heterogeneous systems, HIP, HPC, Instrumentation and Methods for Astrophysics, nVidia, nVidia A100, OpenMP, 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

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

Mojo: MLIR-Based Performance-Portable HPC Science Kernels on GPUs for the Python Ecosystem

William F. Godoy, Tatiana Melnichenko, Pedro Valero-Lara, Wael Elwasif, Philip Fackler, Rafael Ferreira Da Silva, Keita Teranishi, Jeffrey S. Vetter

View

Download (PDF)

Source codes

Tags: AI, AMD Radeon Instinct MI300A, ATI, Compilers, Computer science, CUDA, HIP, HPC, nVidia, nVidia H100, Package, Python, ROCm

September 28, 2025 by hgpu

Harnessing Batched BLAS/LAPACK Kernels on GPUs for Parallel Solutions of Block Tridiagonal Systems

David Jin, Alexis Montoison, Sungho Shin

View

Download (PDF)

Source codes

Tags: AMD Radeon Instinct MI300X, ATI, Benchmarking, BLAS, Computer science, CUDA, Factorization, Julia, nVidia, nVidia H200, Package, ROCm

September 7, 2025 by hgpu

Accelerating a Linear Programming Algorithm on AMD GPUs

Xiyan Hu, Titus Parker, Connor Phillips, Yifa Yu

View

Download (PDF)

Source codes

Tags: AMD Radeon Instinct MI210, AMD Radeon Instinct MI325X, ATI, Computer science, HIP, nVidia, nVidia A100, Package, Performance, PyTorch, ROCm, Thesis

August 31, 2025 by hgpu

Qwen3-235B @ 1M tokens on AMD MI355X

CHUNDER: Enabling Million-Token Qwen3 Serving on AMD ROCm

CUDA++ for the NVIDIA DGX Spark

Reverse Engineering the CUDA Software Stack: A Clean-Room GPU Machine-Code Toolchain for the NVIDIA GB10

ATTUNE: Agentic Throughput Tuning for LLM Training

HPCAgent-Bench: A Framework for Sound Benchmarking of Code-Optimizing Agents, Harnesses, and Skills

Brian2 Atlas

A Unified Intermediate Representation and Execution Architecture for Heterogeneous and Distributed Neural Simulation

AgentGarten: Code Worlds for Evolving Agents

KernelLens: Automated Triton-to-C++ Compiler for Enterprise Inference Runtimes

KernelLens: Deploying Triton Kernels to C++ Inference Engines

KernelZero: Co-Evolving Proposer and Coder for Continuously Improved GPU Kernel Generation

Introduction to Computer Vision

ACT: Accelerator Compiler Toolkit

Automatically Generating ML Compiler Backends from Tensor Accelerator ISA Descriptions

See all packages

* * *

high performance computing on graphics processing units: hgpu.org

HipKittens: Fast and Furious AMD Kernels

MT4G: A Tool for Reliable Auto-Discovery of NVIDIA and AMD GPU Compute and Memory Topologies

AMD MI300X GPU Performance Analysis

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

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

Accelerating cosmological simulations on GPUs: a portable approach using OpenMP

High-Performance Computing: from Optimization to Automation

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

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

Mojo: MLIR-Based Performance-Portable HPC Science Kernels on GPUs for the Python Ecosystem

Harnessing Batched BLAS/LAPACK Kernels on GPUs for Parallel Solutions of Block Tridiagonal Systems

Accelerating a Linear Programming Algorithm on AMD GPUs

Recent source codes

Qwen3-235B @ 1M tokens on AMD MI355X

CUDA++ for the NVIDIA DGX Spark

ATTUNE: Agentic Throughput Tuning for LLM Training

HPCAgent-Bench: A Framework for Sound Benchmarking of Code-Optimizing Agents, Harnesses, and Skills

Brian2 Atlas

AgentGarten: Code Worlds for Evolving Agents

KernelLens: Automated Triton-to-C++ Compiler for Enterprise Inference Runtimes

KernelZero: Co-Evolving Proposer and Coder for Continuously Improved GPU Kernel Generation

Introduction to Computer Vision

ACT: Accelerator Compiler Toolkit

Most viewed papers (last 30 days)