high performance computing on graphics processing units: hgpu.org

Aashaka Shah, Abhinav Jangda, Binyang Li, Caio Rocha, Changho Hwang, Jithin Jose, Madan Musuvathi, Olli Saarikivi, Peng Cheng, Qinghua Zhou, Roshan Dathathri, Saeed Maleki, Ziyue Yang

View

Download (PDF)

Source codes

Tags: AI, AMD Radeon Instinct MI300X, ATI, Computer science, CUDA, Heterogeneous systems, HIP, nVidia, nVidia A100, nVidia H100, Package

April 27, 2025 by hgpu

Data-efficient LLM Fine-tuning for Code Generation

Weijie Lv, Xuan Xia, Sheng-Jun Huang

View

Download (PDF)

Source codes

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

April 27, 2025 by hgpu

LithOS: An Operating System for Efficient Machine Learning on GPUs

Patrick H. Coppock, Brian Zhang, Eliot H. Solomon, Vasilis Kypriotis, Leon Yang, Bikash Sharma, Dan Schatzberg, Todd C. Mowry, Dimitrios Skarlatos

View

Download (PDF)

Tags: Computer science, CUDA, Machine learning, nVidia, nVidia A100, nVidia H100, Operating systems

April 27, 2025 by hgpu

DeepCompile: A Compiler-Driven Approach to Optimizing Distributed Deep Learning Training

Masahiro Tanaka, Du Li, Umesh Chand, Ali Zafar, Haiying Shen, Olatunji Ruwase

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Deep learning, Distributed computing, nVidia, nVidia H100, Package, Prefetch

April 27, 2025 by hgpu

Kernel Library for LLM Serving

Compiler and Runtime Systems for Generative AI Models

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

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

Genten: Software for Generalized Tensor Decompositions by Sandia National Laboratories

A Performance Portable Matrix Free Dense MTTKRP in GenTen

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

Pinocchio: PINpointing Orbit Crossing Collapsed Hierarchical Objects

Accelerating cosmological simulations on GPUs: a portable approach using OpenMP

KernelCoder: trained on a curated dataset of reasoning traces and CUDA kernel pairs

ConCuR: Conciseness Makes State-of-the-Art Kernel Generation

VibeCodeHPC - Multi Agentic Vibe Coding for HPC

VibeCodeHPC: An Agent-Based Iterative Prompting Auto-Tuner for HPC Code Generation Using LLMs

Compile-Time Resource Safety for GPU APIs: A Low-Overhead Typestate Framework

exa-AMD: Exascale Accelerated Materials Discovery

exa-AMD: An Exascale-Ready Framework for Accelerating the Discovery and Design of Functional Materials

See all packages

* * *

high performance computing on graphics processing units: hgpu.org

Applications

GPU Performance Portability needs Autotuning

Exploration of Cryptocurrency Mining-Specific GPUs in AI Applications: A Case Study of CMP 170HX

LIFT: LLM-Based Pragma Insertion for HLS via GNN Supervised Fine-Tuning

Mìmir: A real-time interactive visualization library for CUDA programs

Scaling On-Device GPU Inference for Large Generative Models

Efficient deep learning inference on end devices

Dynamic Memory Management on GPUs with SYCL

InteropUnityCUDA: A Tool for Interoperability Between Unity and CUDA

MSCCL++: Rethinking GPU Communication Abstractions for Cutting-edge AI Applications

Data-efficient LLM Fine-tuning for Code Generation

LithOS: An Operating System for Efficient Machine Learning on GPUs

DeepCompile: A Compiler-Driven Approach to Optimizing Distributed Deep Learning Training

Recent source codes

Kernel Library for LLM Serving

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

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

Genten: Software for Generalized Tensor Decompositions by Sandia National Laboratories

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

Pinocchio: PINpointing Orbit Crossing Collapsed Hierarchical Objects

KernelCoder: trained on a curated dataset of reasoning traces and CUDA kernel pairs

VibeCodeHPC - Multi Agentic Vibe Coding for HPC

Compile-Time Resource Safety for GPU APIs: A Low-Overhead Typestate Framework

exa-AMD: Exascale Accelerated Materials Discovery

Most viewed papers (last 30 days)