high performance computing on graphics processing units: hgpu.org

hgpu.org » Heterogeneous systems

Accelerating GPU Programs by Reducing Irregular Control Flow and Memory Access

Tomohiro Okuyama

View

Tags: Algorithms, Biophysics, CUDA, Differential equations, Heterogeneous systems, nVidia, ODEs, Ordinary differential equations, Physics, Tesla C2070, Thesis

June 18, 2013 by hgpu

Auto-Tunning of Data Communication on Heterogeneous Systems

Marc Jorda, Ivan Tanasic, Javier Cabezas, Lluis Vilanova, Isaac Gelado, Nacho Navarro

View

Download (PDF)

Tags: Computer science, CUDA, Heterogeneous systems, nVidia, Performance, Tesla C2050, Tesla C2070, Tesla M2090

June 17, 2013 by hgpu

An Analysis of Conventional and Heterogeneous Workloads on Production Supercomputing Resources

Jonathan Allen Berkhahn

View

Download (PDF)

Tags: Cloud, Computer science, CUDA, Heterogeneous systems, nVidia, Tesla M2050, Tesla S2050

June 13, 2013 by hgpu

A MapReduce Framework for Heterogeneous Computing Architectures

Marwa Khamis Elteir

View

Download (PDF)

Tags: Computer science, CUDA, Heterogeneous systems, MapReduce, nVidia, OpenCL, Tesla C2050, Tesla M2050, Thesis

June 6, 2013 by hgpu

Parallel Acceleration on Manycore Systems and Its Performance Analysis: OpenCL Case Study

Rafael Alejandro Vejarano, Phuong Thi Yen, Jeong-Gun Lee

View

Download (PDF)

Tags: Computer science, Heterogeneous systems, Matrix multiplication, nVidia, nVidia GeForce GTX 460, OpenCL, Performance

June 4, 2013 by hgpu

Task scheduling in hybrid CPU-GPU systems

Martin Krulis, Zbynek Falt, David Bednarek, Jakub Yaghob

View

Download (PDF)

Tags: Computer science, Heterogeneous systems, nVidia, nVidia GeForce GTX 580, OpenCL, Operating systems, Task scheduling, Tesla M2090

June 2, 2013 by hgpu

From Experiment to Design – Fault Characterization and Detection in Parallel Computer Systems Using Computational Accelerators

Keun Soo Yim

View

Download (PDF)

Tags: Computer science, CUDA, Fault tolerance, Heterogeneous systems, MPI, nVidia, Tesla S1070, Thesis

May 30, 2013 by hgpu

Performance Portability in Accelerated Parallel Kernels

John A. Stratton, Hee-Seok Kim, Thoman B. Jablin, Wen-Mei W. Hwu

View

Download (PDF)

Tags: Computer science, Heterogeneous systems, OpenCL, OpenMP, Performance

May 27, 2013 by hgpu

Scaling Radio Astronomy Signal Correlation on Heterogeneous Supercomputers Using Various Data Distribution Methodologies

Ruonan Wang, Christopher Harris

View

Download (PDF)

Tags: Astrophysics, GPU cluster, Heterogeneous systems, Instrumentation and Methods for Astrophysics, nVidia, OpenCL, Signal processing, Tesla C2075

May 27, 2013 by hgpu

On-Demand Generating and Scheduling Optimised Parallel Applications on Heterogeneous Platforms

K. A. Hawick, D. P. Playne

View

Download (PDF)

Tags: Code generation, Computer science, CUDA, Heterogeneous systems, nVidia, nVidia GeForce GTX 260, nVidia GeForce GTX 580, nVidia GeForce GTX 680, Software Engineering

May 25, 2013 by hgpu

OpenCL Performance Evaluation on Modern Multi Core CPUs

Joo Hwan Lee, Kaushik Patel, Nimit Nigania, Hyojong Kim, Hyesoon Kim

View

Download (PDF)

Tags: Computer science, Heterogeneous systems, nVidia, nVidia GeForce GTX 580, OpenCL, Performance

May 25, 2013 by hgpu

Quantifying the Energy Efficiency of FFT on Heterogeneous Platforms

Yash Ukidave, Amir Kavyan Ziabari, Perhaad Mistry, Gunar Schirner, David Kaeli

View

Download (PDF)

Tags: ATI, ATI Radeon HD 7770, FFT, Heterogeneous systems, nVidia, nVidia GeForce GTX 480, OpenCL, Signal processing

May 25, 2013 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

Accelerating GPU Programs by Reducing Irregular Control Flow and Memory Access

Auto-Tunning of Data Communication on Heterogeneous Systems

A MapReduce Framework for Heterogeneous Computing Architectures

Parallel Acceleration on Manycore Systems and Its Performance Analysis: OpenCL Case Study

Task scheduling in hybrid CPU-GPU systems

From Experiment to Design – Fault Characterization and Detection in Parallel Computer Systems Using Computational Accelerators

Performance Portability in Accelerated Parallel Kernels

Scaling Radio Astronomy Signal Correlation on Heterogeneous Supercomputers Using Various Data Distribution Methodologies

On-Demand Generating and Scheduling Optimised Parallel Applications on Heterogeneous Platforms

OpenCL Performance Evaluation on Modern Multi Core CPUs

Quantifying the Energy Efficiency of FFT on Heterogeneous Platforms

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)