high performance computing on graphics processing units: hgpu.org

Applications

hgpu.org » paper

UniCoder: Unified Visual-to-Code Generation via Symbolic Rewards and Reference-Guided Code Optimization

Yaozhi Zheng, Yilei Jiang, Manyuan Zhang, Yuxuan Wan, Kaituo Feng, Tianshuo Peng, Bo Zhang, Xiangyu Yue

View

Download (PDF)

Source codes

Tags: Code generation, Computer science, Heterogeneous systems, nVidia, nVidia A100, Package

July 13, 2026 by hgpu

Real FP4 Tensor-Core Code in Pure Rust on a Gaming GPU – with NVIDIA’s Own Compiler

Carter Richardson

View

Download (PDF)

Tags: Computer science, CUDA, nVidia, nVidia GeForce RTX 5070 Ti, PTX, Rust

July 13, 2026 by hgpu

Enhancing the Performance Analysis of NCCL GPU Collectives

Jurij Cerar

View

Download (PDF)

Tags: Computer science, CUDA, nVidia, nVidia H100, Performance, Tesla T4, Thesis

July 13, 2026 by hgpu

CuFuzz: An API-Knowledge-Graph Coverage-Driven Fuzzing Framework for CUDA Libraries

Ximing Fan, Yong Fang, Peng Jia, Yang Liu, Yijia Xu, Xi Peng, Yuhao Zhou

View

Download (PDF)

Source codes

Tags: Computer science, CUBLAS, CUDA, FFT, LLM, nVidia, Package, Security

July 13, 2026 by hgpu

Augmenting LLM Code Translation with Compiler Analysis for C to Triton Kernel Generation

Xiao Qin, Chunwei Xia, Zheng Wang

View

Download (PDF)

Tags: Computer science, CUDA, LLM, nVidia, nVidia GeForce RTX 3090, Triton

July 13, 2026 by hgpu

AutoPass: Evidence-Guided LLM Agents for Compiler Performance Tuning

Zepeng Li, Jie Ren, Zhanyong Tang, Jie Zheng, Zheng Wang

View

Download (PDF)

Source codes

Tags: Code generation, Computer science, LLM, Package

June 28, 2026 by hgpu

SpecGen: Accelerating Agentic Kernel Optimization with Speculative Generation

Jihu Guo, Sitian Lu, Tenghui Ma, Wei Gao, Zhisheng Ye, Xingcheng Zhang, Dahua Lin

View

Download (PDF)

Tags: Code generation, Computer science, CUDA, nVidia, nVidia H200

June 28, 2026 by hgpu

Optimizing CUDA like a Human: Micro-Profiling Tools as Expert Surrogates for LLM-Based GPU Kernel Optimization

Jiading Gai, Shuai Zhang, Kaj Bostrom, Jin Huang, Vihang Patil, Haoyang Fang, Bernie Wang, Huzefa Rangwala, George Karypis

View

Download (PDF)

Tags: Code generation, Computer science, CUDA, LLM, nVidia, nVidia A100, Triton

June 28, 2026 by hgpu

Probe-and-Refine Tuning of Repository Guidance for Coding Agents

Asa Shepard, Jeannie Albrecht

View

Download (PDF)

Source codes

Tags: Code generation, Computer science, LLM, Package

June 28, 2026 by hgpu

The Correctness Illusion in LLM-Generated GPU Kernels

Dipankar Sarkar

View

Download (PDF)

Tags: Benchmarking, Code generation, Computer science, CUDA, LLM, nVidia, nVidia A10, nVidia A100, nVidia GeForce RTX 3060, nVidia H100, nVidia L40s, Triton

June 28, 2026 by hgpu

daVinci-kernel: Co-Evolving Skill Selection, Summarization, and Utilization via RL for GPU Kernel Optimization

Dayuan Fu, Mohan Jiang, Tongyu Wang, Dian Yang, Jiarui Hu, Liming Liu, Jinlong Hou, Pengfei Li

View

Download (PDF)

Tags: Computer science, CUDA, LLM, Triton

June 17, 2026 by hgpu

Leveraging AI Ecosystem for Portable and Sustainable GPU Kernels in HPC

Yanbo Zhao, Zhaonan Meng, Sai Krishna Teja Varma Manthena, Xu Liu, Ajay Panyala, Jiajia Li

View

Download (PDF)

Tags: AMD, AMD Radeon Instinct MI300X, Computer science, DSL, HPC, nVidia, nVidia GeForce RTX 4090, nVidia H100, PTX, Python, ROCm, Triton

June 17, 2026 by hgpu

UniCoder: Unified Visual-to-Code Generation via Symbolic Rewards and Reference-Guided Code Optimization

CuFuzz: An API-Knowledge-Graph Coverage-Driven Fuzzing Framework for CUDA Libraries

AutoPass: Evidence-Guided LLM Agents for Compiler Performance Tuning

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

CUDA Kernel Fusion Benchmarks

Analyzing the Impact of Kernel Fusion on GPU Tensor Operation Performance: A Systematic Performance Study

IntelliKit: Agent-first tooling for AMD hardware

Kerncap: Automated Kernel Extraction and Isolation for AMD GPUs

DITRON: Distributed Compiler based on Triton for Parallel Systems

DITRON: Distributed Multi-level Tiling Compiler for Parallel Tensor Programs

See all packages

* * *

high performance computing on graphics processing units: hgpu.org

Applications

UniCoder: Unified Visual-to-Code Generation via Symbolic Rewards and Reference-Guided Code Optimization

Real FP4 Tensor-Core Code in Pure Rust on a Gaming GPU – with NVIDIA’s Own Compiler

Enhancing the Performance Analysis of NCCL GPU Collectives

CuFuzz: An API-Knowledge-Graph Coverage-Driven Fuzzing Framework for CUDA Libraries

Augmenting LLM Code Translation with Compiler Analysis for C to Triton Kernel Generation

AutoPass: Evidence-Guided LLM Agents for Compiler Performance Tuning

SpecGen: Accelerating Agentic Kernel Optimization with Speculative Generation

Optimizing CUDA like a Human: Micro-Profiling Tools as Expert Surrogates for LLM-Based GPU Kernel Optimization

Probe-and-Refine Tuning of Repository Guidance for Coding Agents

The Correctness Illusion in LLM-Generated GPU Kernels

daVinci-kernel: Co-Evolving Skill Selection, Summarization, and Utilization via RL for GPU Kernel Optimization

Leveraging AI Ecosystem for Portable and Sustainable GPU Kernels in HPC

Recent source codes

UniCoder: Unified Visual-to-Code Generation via Symbolic Rewards and Reference-Guided Code Optimization

CuFuzz: An API-Knowledge-Graph Coverage-Driven Fuzzing Framework for CUDA Libraries

AutoPass: Evidence-Guided LLM Agents for Compiler Performance Tuning

Probe-and-Refine Tuning of Repository Guidance for AI Coding Agents

CUDAnalyst (CUDA + Analyst)

CodegenBench

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

Most viewed papers (last 30 days)