Warp level parallelism

hgpu.org » Warp level parallelism

Harnessing Aspect Oriented Programming on GPU: Application to Warp-Level Parallelism (WLP)

Jonathan Passerat-Palmbach, Pierre Schweitzer, Jonathan Caux, Pridi Siregar, Claude Mazel, David Hill

View

Download (PDF)

Tags: Computer science, CUDA, nVidia, Stochastic simulation, Tesla C2050, Warp level parallelism

January 19, 2015 by hgpu

Advanced Trends of Heterogeneous Computing with CPU-GPU Integration: Comparative Study

Ishan Rajani, G Nanda Gopal

View

Download (PDF)

Tags: AMD FireStream 9270, ATI, Computer science, CUDA, Distributed computing, Heterogeneous systems, nVidia, OpenCL, Tesla C2050, Warp level parallelism

January 26, 2013 by hgpu

Warp-Level Parallelism: Enabling Multiple Replications In Parallel on GPU

Jonathan Passerat-Palmbach, Jonathan Caux, Pridi Siregar, Claude Mazel, D.R.C.Hill

View

Download (PDF)

Tags: Benchmarking, Computer science, CUDA, nVidia, Stochastic simulation, Tesla C2050, Warp level parallelism

December 21, 2011 by hgpu

Memory-level and Thread-level Parallelism Aware GPU Architecture Performance Analytical Model

Sunpyo Hong, Hyesoon Kim

View

Download (PDF)

Tags: Analytical model, Benchmarking, Computer science, CUDA, Memory level parallelism, nVidia, nVidia Quadro FX 5600, Warp level parallelism

December 15, 2011 by hgpu

Improving GPU Performance via Large Warps and Two-Level Warp Scheduling

Veynu Narasiman, Chang Joo Lee, Michael Shebanow, Rustam Miftakhutdinov, Onur Mutlu, Yale N. Patt

View

Download (PDF)

Tags: Computer science, CUDA, nVidia, Performance, Warp level parallelism

November 11, 2011 by hgpu

Dynamic warp formation: Efficient MIMD control flow on SIMD graphics hardware

Wilson W. L. Fung, Ivan Sham, George Yuan, Tor M. Aamodt

View

Download (PDF)

Tags: Computer science, CUDA, Hardware Architecture, nVidia, nVidia GeForce 8800 GTX, Performance, Warp level parallelism

April 19, 2011 by hgpu

An analytical model for a GPU architecture with memory-level and thread-level parallelism awareness

Sunpyo Hong, Hyesoon Kim

View

Download (PDF)

Tags: Analytical model, Computer science, CUDA, Memory level parallelism, nVidia, nVidia GeForce 8800 GT, nVidia GeForce 8800 GTX, nVidia Quadro FX 5600, Warp level parallelism

October 29, 2010 by hgpu

Over-synchronization in GPU Programs

profile_util: simple C++ library to report memory, timing, thread affinity

Profile Util library: A quick and easy way to get MPI, OpenMP and GPU runtime information

MaC: Mamba CPU performance predictor

MambaCPU: Enhanced Correlation Mining with State Space Models for CPU Performance Prediction

Mixed-precision finite element kernels

Mixed-precision finite element kernels and assembly: Rounding error analysis and hardware acceleration

SHMT: The Simultaneous and Heterogenous Multithreading project

General-Purpose Computing on Tensor Processors

Superpipeline: A Universal Approach for Reducing GPU Memory Usage in Large Models

EnergyUCB-Bandit

Online Energy Optimization in GPUs: A Multi-Armed Bandit Approach

See all packages

* * *

high performance computing on graphics processing units: hgpu.org

Harnessing Aspect Oriented Programming on GPU: Application to Warp-Level Parallelism (WLP)

Advanced Trends of Heterogeneous Computing with CPU-GPU Integration: Comparative Study

Warp-Level Parallelism: Enabling Multiple Replications In Parallel on GPU

Memory-level and Thread-level Parallelism Aware GPU Architecture Performance Analytical Model

Improving GPU Performance via Large Warps and Two-Level Warp Scheduling

Dynamic warp formation: Efficient MIMD control flow on SIMD graphics hardware

An analytical model for a GPU architecture with memory-level and thread-level parallelism awareness

Recent source codes

Kokkidio: Kokkos+Eigen - write fast, readable multi-platform code

LLaMA-Inference-Bench

MATAR

Over-synchronization in GPU Programs

profile_util: simple C++ library to report memory, timing, thread affinity

MaC: Mamba CPU performance predictor

Mixed-precision finite element kernels

SHMT: The Simultaneous and Heterogenous Multithreading project

Superpipeline: A Universal Approach for Reducing GPU Memory Usage in Large Models

EnergyUCB-Bandit

Most viewed papers (last 30 days)