high performance computing on graphics processing units: hgpu.org

hgpu.org » Computer sceince

CUDA-LLM: LLMs Can Write Efficient CUDA Kernels

Wentao Chen, Jiace Zhu, Qi Fan, Yehan Ma, An Zou

View

Tags: Artificial intelligence, Code generation, Computer sceince, CUDA, LLM, nVidia, nVidia GeForce GTX 1660, nVidia GeForce RTX 3090 Ti

June 15, 2025 by hgpu

WiLLM: An Open Wireless LLM Communication System

WiLLM: An Open Wireless LLM Communication System

Vcc: the Vulkan Clang Compiler

No More Shading Languages: Compiling C++ to Vulkan Shaders

hpcbench: A set of benchmarking utilities for biomolecular simulation tools

Engineering Supercomputing Platforms for Biomolecular Applications

HPCTransCompile: An AI Compiler Generated Dataset for High-Performance CUDA Transpilation and LLM Preliminary Exploration

HPCTransCompile: An AI Compiler Generated Dataset for High-Performance CUDA Transpilation and LLM Preliminary Exploration

chemtrain: Training Molecular Dynamics Potentials in JAX

chemtrain-deploy: A parallel and scalable framework for machine learning potentials in million-atom MD simulations

microSYCL: SYCL micro-benchmarks repository

Exploring SYCL as a Portability Layer for High-Performance Computing on CPUs

XaaS containers

Acceleration as a Service (XaaS) Source Containers

CASS: Cuda-Amd aSSembly

CASS: Nvidia to AMD Transpilation with Data, Models, and Benchmark

Cluser of smartphones for edge computing application using TensorFlow

Low-cost edge computing using upcycled smartphones

SYCL Container

Exploring SYCL for batched kernels with memory allocations

See all packages

* * *

* * *

HGPU group © 2010-2025 hgpu.org

All rights belong to the respective authors

Login | Sitemap | Feedback | Policy

Contact us:

contact@hpgu.org