high performance computing on graphics processing units: hgpu.org

hgpu.org » nVidia

CUDA-L2: Surpassing cuBLAS Performance for Matrix Multiplication through Reinforcement Learning

Songqiao Su, Xiaofei Sun, Xiaoya Li, Albert Wang, Jiwei Li, Chris Shum

View

Download (PDF)

Source codes

Tags: Computer science, CUBLAS, CUDA, Matrix multiplication, nVidia, nVidia A100, Package

December 21, 2025 by hgpu

Beyond Code Pairs: Dialogue-Based Data Generation for LLM Code Translation

Le Chen1, Nuo Xu, Winson Chen, Bin Lei, Pei-Hung Lin, Dunzhi Zhou, Rajeev Thakur, Caiwen Ding, Ali Jannesari, Chunhua Liao

View

Download (PDF)

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

December 21, 2025 by hgpu

cuPilot: A Strategy-Coordinated Multi-agent Framework for CUDA Kernel Evolution

Jinwu Chen, Qidie Wu, Bin Li, Lin Ma, Xin Si, Yang Hu, Shouyi Yin, Jun Yang

View

Download (PDF)

Source codes

Tags: AI, Code generation, Computer science, CUDA, nVidia, nVidia A100, Package, PyTorch

December 21, 2025 by hgpu

ML Inference Scheduling with Predictable Latency

Haidong Zhao, Nikolaos Georgantas

View

Download (PDF)

Tags: Computer science, Machine learning, nVidia, nVidia L4, Task scheduling

December 21, 2025 by hgpu

PystachIO: Efficient Distributed GPU Query Processing with PyTorch over Fast Networks & Fast Storage

Jigao Luo, Nils Boeschen, Muhammad El-Hindi, Carsten Binnig

View

Download (PDF)

Tags: Computer science, CUDA, Databases, GPU cluster, nVidia, nVidia A100, nVidia DGX-1, PyTorch

December 21, 2025 by hgpu

Accurate Models of NVIDIA Tensor Cores

Faizan A. Khattak, Mantas Mikaitis

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Matrix multiplication, nVidia, nVidia B200, nVidia H100, nVidia V100, Package

December 15, 2025 by hgpu

TritonForge: Profiling-Guided Framework for Automated Triton Kernel Optimization

Haonan Li, Keyu Man, Partha Kanuparthy, Hanning Chen, Wei Sun, Sreen Tallam, Chenguang Zhu, Kevin Zhu, Zhiyun Qian

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, LLM, Machine learning, nVidia, nVidia H100, Package, PyTorch, Triton

December 15, 2025 by hgpu

Hybrid Learning and Optimization-Based Dynamic Scheduling for DL Workloads on Heterogeneous GPU Clusters

Shruti Dongare, Redwan Ibne Seraj Khan, Hadeel Albahar, Nannan Zhao, Diego Melendez Maita, Ali R. Butt

View

Download (PDF)

Source codes

Tags: Computer science, Deep learning, GPU cluster, nVidia, nVidia H100, Package, Task scheduling

December 15, 2025 by hgpu

Accelerating Molecular Simulations with Triton: Fused GPU Kernels for TensorNet Neural Potentials

Manpreet Singh

View

Download (PDF)

Tags: Biology, Chemistry, CUDA, Molecular dynamics, nVidia, nVidia A100, PyTorch, Triton

December 15, 2025 by hgpu

Microbenchmarking NVIDIA’s Blackwell Architecture: An in-depth Architectural Analysis

Aaron Jarmusch, Sunita Chandrasekaran

View

Download (PDF)

Tags: Benchmarking, Computer science, CUDA, HPC, Machine learning, nVidia, nVidia B200, nVidia H200, PTX

December 7, 2025 by hgpu

Decoupled Triton: A Block-Level Decoupled Language for Writing and Exploring Efficient Machine-Learning Kernels

Quinn Leo Pham

View

Download (PDF)

Tags: Compilers, Computer science, Machine learning, nVidia, nVidia RTX 5000 Ada, PyTorch, Thesis, Triton

December 7, 2025 by hgpu

QiMeng-Kernel: Macro-Thinking Micro-Coding Paradigm for LLM-Based High-Performance GPU Kernel Generation

Xinguo Zhu, Shaohui Peng, Jiaming Guo, Yunji Chen, Qi Guo, Yuanbo Wen, Hang Qin, Ruizhi Chen, Qirui Zhou, Ke Gao, Yanjun Wu, Chen Zhao, Ling Li

View

Download (PDF)

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

November 30, 2025 by hgpu

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

pytest-gpu-proof: A Simple Pytest Extension for Local GPU Code Testing

pytest-gpu-proof: Enabling Cloud-CPU Continuous Integration for GPU Code with Local GPU Attestation

Accelerating the Mitigation of LLM Inference Nondeterminism Across GPU Architectures

AutoTuneBench: Trustworthy Measurement for Agent Auto-Tuning of LLM Serving Engines

nvsass-disassembler

Automated Instruction Encoding Synthesis for Modern GPU ISA Compression

PrefixBench-H100: Characterizing Prefix Reuse and Time-to-First-Token in H100 LLM Serving

EinsummableV3 - graph-based computation with tensor operations support

Every Kernel Is a Join: Automatic Multi-GPU Parallelism for AI Computations in Einsummable

MaxKernel: Intelligent TPU Kernel Engineering Agents

MaxKernel: Agentic Kernel Generation for TPUs

See all packages

* * *

high performance computing on graphics processing units: hgpu.org

CUDA-L2: Surpassing cuBLAS Performance for Matrix Multiplication through Reinforcement Learning

Beyond Code Pairs: Dialogue-Based Data Generation for LLM Code Translation

cuPilot: A Strategy-Coordinated Multi-agent Framework for CUDA Kernel Evolution

ML Inference Scheduling with Predictable Latency

PystachIO: Efficient Distributed GPU Query Processing with PyTorch over Fast Networks & Fast Storage

Accurate Models of NVIDIA Tensor Cores

TritonForge: Profiling-Guided Framework for Automated Triton Kernel Optimization

Hybrid Learning and Optimization-Based Dynamic Scheduling for DL Workloads on Heterogeneous GPU Clusters

Accelerating Molecular Simulations with Triton: Fused GPU Kernels for TensorNet Neural Potentials

Microbenchmarking NVIDIA’s Blackwell Architecture: An in-depth Architectural Analysis

Decoupled Triton: A Block-Level Decoupled Language for Writing and Exploring Efficient Machine-Learning Kernels

QiMeng-Kernel: Macro-Thinking Micro-Coding Paradigm for LLM-Based High-Performance GPU Kernel Generation

Recent source codes

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

Introduction to Computer Vision

ACT: Accelerator Compiler Toolkit

pytest-gpu-proof: A Simple Pytest Extension for Local GPU Code Testing

Accelerating the Mitigation of LLM Inference Nondeterminism Across GPU Architectures

AutoTuneBench: Trustworthy Measurement for Agent Auto-Tuning of LLM Serving Engines

nvsass-disassembler

PrefixBench-H100: Characterizing Prefix Reuse and Time-to-First-Token in H100 LLM Serving

EinsummableV3 - graph-based computation with tensor operations support

MaxKernel: Intelligent TPU Kernel Engineering Agents

Most viewed papers (last 30 days)