high performance computing on graphics processing units: hgpu.org

hgpu.org » Operating systems

TimeGraph: GPU scheduling for real-time multi-tasking environments

Shinpei Kato, Karthik Lakshmanan, Ragunathan Rajkumar, Yutaka Ishikawa

View

Download (PDF)

Source codes

Tags: Benchmarking, Computer science, nVidia, nVidia GeForce 9800 GT, nVidia GeForce GTX 285, nVidia GeForce GTX 480, OpenGL, Operating systems, Package, Real-time graphics, Task scheduling

September 11, 2011 by hgpu

KAdvice: infering synchronization patterns from an existing codebase

Alexander Schmidt, Andreas Polze

Tags: Computer science, Operating systems

September 9, 2011 by hgpu

Pegasus: coordinated scheduling for virtualized accelerator-based systems

Vishakha Gupta, Karsten Schwan, Niraj Tolia, Vanish Talwar, Parthasarathy Ranganathan

View

Download (PDF)

Tags: Computer science, CUDA, Heterogeneous systems, nVidia, nVidia GeForce 9800 GTX, Operating systems, Task scheduling, Virtualization

September 7, 2011 by hgpu

Operating systems must support GPU abstractions

Christopher J. Rossbach, Jon Currey, Emmett Witchel

View

Download (PDF)

Tags: Computer science, nVidia, nVidia GeForce GT 230, Operating systems

September 7, 2011 by hgpu

Resource Sharing in GPU-Accelerated Windowing Systems

Shinpei Kato, Karthik Lakshmanan, Yutaka Ishikawa, Ragunathan (Raj) Rajkumar

View

Download (PDF)

Tags: Computer science, nVidia, nVidia GeForce 9500 GT, OpenGL, Operating systems, Rendering

June 22, 2011 by hgpu

GPU-based X server on top of EGL and openVG

Dongkyun Jeong, Kamalneet Singh, Namin Kim, Soochan Lim

Tags: Computer science, Energy-efficient computing, Operating systems

May 16, 2011 by hgpu

The multikernel: a new OS architecture for scalable multicore systems

Andrew Baumann, Paul Barham, Pierre E. Dagand, Tim Harris, Rebecca Isaacs, Simon Peter, Timothy Roscoe, Adrian Schüpbach, Akhilesh Singhania

View

Download (PDF)

Tags: Computer science, Operating systems

November 27, 2010 by hgpu

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

Agentic Code Optimization via Compiler-LLM Cooperation

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

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

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

LLMQ: Efficient Lower-Precision LLM Training for Consumer GPUs

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

* * *

high performance computing on graphics processing units: hgpu.org

TimeGraph: GPU scheduling for real-time multi-tasking environments

KAdvice: infering synchronization patterns from an existing codebase

Pegasus: coordinated scheduling for virtualized accelerator-based systems

Operating systems must support GPU abstractions

Resource Sharing in GPU-Accelerated Windowing Systems

GPU-based X server on top of EGL and openVG

The multikernel: a new OS architecture for scalable multicore systems

Recent source codes

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

Device Virtual Machine (DVM)

Agentic Code Optimization via Compiler-LLM Cooperation

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

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

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

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

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)