high performance computing on graphics processing units: hgpu.org

hgpu.org » nVidia GeForce RTX 4090

CuTeGen: An LLM-Based Agentic Framework for Generation and Optimization of High-Performance GPU Kernels using CuTe

Tara Saba, Anne Ouyang, Xujie Si, Fan Long

View

Download (PDF)

Tags: Computer science, CUDA, Machine learning, Matrix multiplication, nVidia, nVidia GeForce RTX 4090

April 13, 2026 by hgpu

LLMQ: Efficient Lower-Precision LLM Training for Consumer GPUs

Erik Schultheis, Dan Alistarh

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, LLM, nVidia, nVidia GeForce RTX 4090, nVidia GeForce RTX 5060 Ti, nVidia L40s, Package

March 22, 2026 by hgpu

Triton-Sanitizer: A Fast and Device-Agnostic Memory Sanitizer for Triton with Rich Diagnostic Context

Hao Wu, Qidong Zhao, Songqing Chen, Yang Chen, Yueming Hao, Tony CW Liu, Sijia Chen, Adnan Aziz, Keren Zhou

View

Download (PDF)

Source codes

Tags: AMD, AMD Radeon Instinct MI250X, Computer science, Deep learning, nVidia, nVidia GeForce RTX 4090, ROCm, Triton

March 22, 2026 by hgpu

An Efficient Heterogeneous Co-Design for Fine-Tuning on a Single GPU

Ruijia Yang, Zeyi Wen

View

Download (PDF)

Tags: AMD, AMD Radeon RX 7900 XT, Computer science, Heterogeneous systems, nVidia, nVidia A100, nVidia GeForce RTX 4090, Triton

March 18, 2026 by hgpu

Making LLMs Optimize Multi-Scenario CUDA Kernels Like Experts

Yuxuan Han, Meng-Hao Guo, Zhengning Liu, Wenguang Chen, Shi-Min Hu

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Machine learning, nVidia, nVidia GeForce RTX 4090, Package

March 15, 2026 by hgpu

CUDABench: Benchmarking LLMs for Text-to-CUDA Generation

Jiace Zhu, Wentao Chen, Qi Fan, Zhixing Ren, Junying Wu, Xing Zhe Chai, Chotiwit Rungrueangwutthinon, Yehan Ma, An Zou

View

Download (PDF)

Source codes

Tags: Benchmarking, Computer science, CUDA, LLM, nVidia, nVidia A40, nVidia GeForce RTX 4090, Package

March 4, 2026 by hgpu

KernelBand: Boosting LLM-based Kernel Optimization with a Hierarchical and Hardware-aware Multi-armed Bandit

Dezhi Ran, Shuxiao Xie, Mingfang Ji, Ziyue Hua, Mengzhou Wu, Yuan Cao, Yuzhe Guo, Yu Hao, Linyi Li, Yitao Hu, Tao Xie

View

Download (PDF)

Tags: Code generation, Computer science, CUDA, LLM, nVidia, nVidia A100, nVidia GeForce RTX 4090, Triton

November 30, 2025 by hgpu

CudaForge: An Agent Framework with Hardware Feedback for CUDA Kernel Optimization

Zijian Zhang, Rong Wang, Shiyang Li, Yuebo Luo, Mingyi Hong, Caiwen Ding

View

Download (PDF)

Source codes

Tags: Code generation, Computer science, CUDA, nVidia, nVidia A100, nVidia GeForce RTX 3090, nVidia GeForce RTX 4090, nVidia RTX 6000 Ada, Package, Performance

November 9, 2025 by hgpu

Characterizing the Performance of Parallel Data-Compression Algorithms across Compilers and GPUs

Brandon Alexander Burtchell, Martin Burtscher

View

Download (PDF)

Source codes

Tags: Algorithms, Compilers, Compression, Computer science, CUDA, HIP, nVidia, nVidia GeForce GTX Titan V, nVidia GeForce RTX 3080 Ti, nVidia GeForce RTX 4090, Package

November 9, 2025 by hgpu

Interleaved Learning and Exploration: A Self-Adaptive Fuzz Testing Framework for MLIR

Zeyu Sun, Jingjing Liang, Weiyi Wang, Chenyao Suo, Junjie Chen, Fanjiang Xu

View

Download (PDF)

Source codes

Tags: Computer science, Neural networks, nVidia, nVidia GeForce RTX 4090, OpenCL, Package, Software Engineering

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

The Fused Kernel Library: A C++ API to Develop Highly-Efficient GPU Libraries

Oscar Amoros, Albert Andaluz, Johnny Nunez, Antonio J. Pena

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, nVidia, nVidia GeForce RTX 4090, Package, Performance

August 17, 2025 by hgpu

Agentic Code Optimization via Compiler-LLM Cooperation

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

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

SOL-ExecBench: Speed-of-Light Benchmarking for Real-World GPU Kernels Against Hardware Limits

Triton-Sanitizer: A Fast and Device-Agnostic Memory Sanitizer for Triton with Rich Diagnostic Context

* * *

high performance computing on graphics processing units: hgpu.org

CuTeGen: An LLM-Based Agentic Framework for Generation and Optimization of High-Performance GPU Kernels using CuTe

LLMQ: Efficient Lower-Precision LLM Training for Consumer GPUs

Triton-Sanitizer: A Fast and Device-Agnostic Memory Sanitizer for Triton with Rich Diagnostic Context

An Efficient Heterogeneous Co-Design for Fine-Tuning on a Single GPU

Making LLMs Optimize Multi-Scenario CUDA Kernels Like Experts

CUDABench: Benchmarking LLMs for Text-to-CUDA Generation

KernelBand: Boosting LLM-based Kernel Optimization with a Hierarchical and Hardware-aware Multi-armed Bandit

CudaForge: An Agent Framework with Hardware Feedback for CUDA Kernel Optimization

Characterizing the Performance of Parallel Data-Compression Algorithms across Compilers and GPUs

Interleaved Learning and Exploration: A Self-Adaptive Fuzz Testing Framework for MLIR

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

The Fused Kernel Library: A C++ API to Develop Highly-Efficient GPU Libraries

Recent source codes

Agentic Code Optimization via Compiler-LLM Cooperation

MegaTrain: Full Precision Training of 100B+ Parameter Large Language Models on a Single GPU

Device Virtual Machine (DVM)

AutoKernel: Autoresearch for GPU kernels. Give it any PyTorch model, go to sleep, wake up to optimized Triton kernels

SOL-ExecBench: Speed-of-Light Benchmarking for Real-World GPU Kernels Against Hardware Limits

Triton-Sanitizer: A Fast and Device-Agnostic Memory Sanitizer for Triton with Rich Diagnostic Context

LLM.Q: Quantized LLM training in pure CUDA/C++

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)