high performance computing on graphics processing units: hgpu.org

hgpu.org » PTX

Enhancing productivity and performance portability of OpenCL applications on heterogeneous systems using runtime optimizations

Thibaut Lutz

View

Download (PDF)

Tags: Computer science, nVidia, nVidia GeForce GTX 780, OpenCL, Performance, performance portability, PTX, Thesis

March 8, 2016 by hgpu

Programming GPUs with C++14 and Just-In-Time Compilation

Michael Haidl, Bastian Hagedorn, Sergei Gorlatch

View

Download (PDF)

Tags: Compilers, Computer science, CUDA, Intel Xeon Phi, LLVM, nVidia, OpenCL, PTX, Tesla K20

February 10, 2016 by hgpu

Adaptive and Transparent Cache Bypassing for GPUs

Ang Li, Gert-Jan van den Braak, Akash Kumar, Henk Corporaal

View

Download (PDF)

Tags: Benchmarking, cache, Computer science, Memory, nVidia, nVidia GeForce GTX 460, nVidia GeForce GTX 570, nVidia GeForce GTX 690, nVidia GeForce GTX 750 Ti, nVidia GeForce GTX 980, Performance, PTX, Tesla K40, Tesla K80

September 24, 2015 by hgpu

Optimizing OpenCL Local Work Group Size With Machine Learning

Markus Schlafli

View

Download (PDF)

Tags: ATI, ATI Radeon HD 7850, Computer science, Machine learning, OpenCL, Performance, PTX

August 18, 2015 by hgpu

Fine-Grained Synchronizations and Dataflow Programming on GPUs

Ang Li, Gert-Jan van den Braak, Henk Corporaa, Akash Kumar

View

Download (PDF)

Tags: Computer science, CUDA, nVidia, nVidia GeForce GTX 570, Performance, PTX

May 3, 2015 by hgpu

Flexible Software Profiling of GPU Architectures

Mark Stephenson, Siva Kumar Sastry Hari, Yunsup Lee, Eiman Ebrahimi, Daniel R. Johnson, David Nellans, Mike O'Connor, Stephen W. Keckler

View

Download (PDF)

Tags: Computer science, CUDA, Design space exploration, nVidia, PTX, Tesla K10, Tesla K20, Tesla K40

April 25, 2015 by hgpu

Verification of Producer-Consumer Synchronization in GPU Programs

Rahul Sharma, Michael Bauer, Alex Aiken

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, nVidia, Package, PTX

April 20, 2015 by hgpu

PTX2Kernel: Converting PTX Code into Compilable Kernels

Qiankun Dong, Tao Li, Shuai Zhang, Xiaofan Jiao, Jiabing Leng

View

Download (PDF)

Tags: Computer science, CUDA, Matrix multiplication, nVidia, nVidia GeForce GTX 480, PTX, Tesla K40

March 22, 2015 by hgpu

Characterizing and Enhancing Global Memory Data Coalescing on GPUs

Naznin Fauzia, Louis-Noel Pouchet, P. Sadayappan

View

Download (PDF)

Tags: Computer science, CUDA, Memory, nVidia, Performance, PTX, Tesla K20

February 2, 2015 by hgpu

GPU concurrency: Weak behaviours and programming assumptions

Jade Alglave, Mark Batty, Alastair F. Donaldson, Ganesh Gopalakrishnan, Jeroen Ketema, Daniel Poetzl, Tyler Sorensen, John Wickerson

View

Download (PDF)

Tags: ATI, ATI Radeon HD 6570, ATI Radeon HD 7970, Computer science, Memory, nVidia, nVidia GeForce GTX 280, nVidia GeForce GTX 540 M, nVidia GeForce GTX 660, nVidia GeForce GTX 750, nVidia GeForce GTX Titan, OpenCL, Performance, PTX, Tesla C2075

January 21, 2015 by hgpu

Thorough Evaluation of GPU Shared Memory Load and Store Instructions

Satoshi Okamoto, Yasuaki Ito, Koji Nakano, Jacir L. Bordim

View

Download (PDF)

Tags: Benchmarking, Computer science, CUDA, nVidia, nVidia GeForce GTX 780 Ti, Performance, PTX

January 13, 2015 by hgpu

Analysis and Optimization Techniques for Massively Parallel Processors

Wenhao Jia

View

Download (PDF)

Tags: Algorithms, ATI, ATI Radeon HD 7970, Computer science, CUDA, Heterogeneous systems, nVidia, OpenCL, PTX, Tesla C2070, Thesis, Virtualization

December 15, 2014 by hgpu

MATLAB Tensor Core models

Accurate Models of NVIDIA Tensor Cores

TritonForge: Transform PyTorch Operations into Optimized GPU Kernels with LLMs

TritonForge: Profiling-Guided Framework for Automated Triton Kernel Optimization

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

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

tritonBLAS: A Lightweight Triton-based General Matrix Multiplication (GEMM) Library

tritonBLAS: Triton-based Analytical Approach for GEMM Kernel Parameter Selection

hls4ml: Machine learning on FPGAs using HLS

hls4ml: A Flexible, Open-Source Platform for Deep Learning Acceleration on Reconfigurable Hardware

NVIDIA Nemotron Parse 1.1

ThunderKittens: Tile primitives for speedy kernels

ParallelKittens: Systematic and Practical Simplification of Multi-GPU AI Kernels

Iris: AMD RAD's multi-GPU Triton-based framework for seamless multi-GPU programming

Iris: First-Class Multi-GPU Programming Experience in Triton

HipKittens: Fast and Furious AMD Kernels

Fortran xDSL dialects

An MLIR pipeline for offloading Fortran to FPGAs via OpenMP

See all packages

* * *

high performance computing on graphics processing units: hgpu.org

Enhancing productivity and performance portability of OpenCL applications on heterogeneous systems using runtime optimizations

Programming GPUs with C++14 and Just-In-Time Compilation

Adaptive and Transparent Cache Bypassing for GPUs

Optimizing OpenCL Local Work Group Size With Machine Learning

Fine-Grained Synchronizations and Dataflow Programming on GPUs

Flexible Software Profiling of GPU Architectures

Verification of Producer-Consumer Synchronization in GPU Programs

PTX2Kernel: Converting PTX Code into Compilable Kernels

Characterizing and Enhancing Global Memory Data Coalescing on GPUs

GPU concurrency: Weak behaviours and programming assumptions

Thorough Evaluation of GPU Shared Memory Load and Store Instructions

Analysis and Optimization Techniques for Massively Parallel Processors

Recent source codes

MATLAB Tensor Core models

TritonForge: Transform PyTorch Operations into Optimized GPU Kernels with LLMs

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

tritonBLAS: A Lightweight Triton-based General Matrix Multiplication (GEMM) Library

hls4ml: Machine learning on FPGAs using HLS

NVIDIA Nemotron Parse 1.1

ThunderKittens: Tile primitives for speedy kernels

Iris: AMD RAD's multi-GPU Triton-based framework for seamless multi-GPU programming

HipKittens: Fast and Furious AMD Kernels

Fortran xDSL dialects

Most viewed papers (last 30 days)