high performance computing on graphics processing units: hgpu.org

hgpu.org » Performance

The Feasibility of Using OpenCL Instead of OpenMP for Parallel CPU Programming

Kamran Karimi

View

Download (PDF)

Tags: ATI, Computer science, OpenCL, OpenMP, Performance

March 25, 2015 by hgpu

Raising the Bar for Using GPUs in Software Packet Processing

Anuj Kalia, Dong Zhou, Michael Kaminsky, David G. Andersen

View

Download (PDF)

Tags: Computer science, CUDA, nVidia, nVidia GeForce GTX 650 Ti, nVidia GeForce GTX 980, Performance, Tesla K20

March 22, 2015 by hgpu

CSR5: An Efficient Storage Format for Cross-Platform Sparse Matrix-Vector Multiplication

Weifeng Liu, Brian Vinter

View

Download (PDF)

Source codes

Tags: Algorithms, AMD Radeon R9 290X, Benchmarking, Computer science, CUDA, Intel Xeon Phi, Mathematical Software, nVidia, nVidia GeForce GTX 980, OpenCL, Package, Performance, Sparse matrix

March 20, 2015 by hgpu

The More We Share, The More We Have: Improving GPU performance through Register Sharing

Vishwesh Jatala, Jayvant Anantpur, Amey Karkare

View

Download (PDF)

Tags: Computer science, CUDA, GPGPU-sim, Hardware Architecture, nVidia, Performance

March 20, 2015 by hgpu

An Empirical Performance Evaluation of GPU-Enabled Graph-Processing Systems

Yong Guo, Ana Lucia Varbanescu, Alexandru Iosup, Dick Epema

View

Download (PDF)

Tags: Computer science, CUDA, nVidia, nVidia GeForce GTX 480, nVidia GeForce GTX 580, Performance, Tesla K20

March 8, 2015 by hgpu

HPerf: A Lightweight Profiler for Task Distribution on CPU+GPU Platforms

Joo Hwan Lee, Nimit Nigania, Hyesoon Kim, Bevin Brett

View

Download (PDF)

Tags: Computer science, Heterogeneous systems, nVidia, nVidia Quadro 2000, OpenCL, Performance

March 8, 2015 by hgpu

Stochastic Gradient Descent on GPUs

Rashid Kaleem, Sreepathi Pai, Keshav Pingali

View

Download (PDF)

Tags: Algorithms, Computer science, Machine learning, nVidia, OpenCL, Performance, Tesla K40

February 22, 2015 by hgpu

Comparison of SPMV performance on matrices with different matrix format using CUSP, cuSPARSE and ViennaCL

Ang Li, Hammad Mazhar, Radu Serban, Dan Negrut

View

Download (PDF)

Tags: Computer science, CUDA, Linear Algebra, nVidia, OpenCL, Performance, Python, Sparse matrix, Tesla K20

February 22, 2015 by hgpu

Patterns and Rewrite Rules for Systematic Code Generation (From High-Level Functional Patterns to High-Performance OpenCL Code)

Michel Steuwer, Christian Fensch, Christophe Dubach

View

Download (PDF)

Tags: ATI, ATI Radeon HD 7970, Code generation, Computer science, nVidia, nVidia GeForce GTX 480, OpenCL, Performance, Programming Languages

February 10, 2015 by hgpu

Comparison of OpenCL performance on different platforms using VexCL and Blaze

Hammad Mazhar, Dan Negrut

View

Download (PDF)

Tags: AMD Radeon R7 260, ATI, Benchmarking, Computer science, Intel Xeon Phi, nVidia, nVidia GeForce GTX 680, nVidia GeForce GTX 770, OpenCL, Performance, Sparse matrix, Tesla K20

February 6, 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

Different Optimization Strategies and Performance Evaluation of Reduction on Multicore CUDA Architecture

Chhaya Patel

View

Download (PDF)

Tags: Algorithms, Computer science, CUDA, nVidia, nVidia GeForce GTX 480, Performance

January 30, 2015 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

The Feasibility of Using OpenCL Instead of OpenMP for Parallel CPU Programming

Raising the Bar for Using GPUs in Software Packet Processing

CSR5: An Efficient Storage Format for Cross-Platform Sparse Matrix-Vector Multiplication

The More We Share, The More We Have: Improving GPU performance through Register Sharing

An Empirical Performance Evaluation of GPU-Enabled Graph-Processing Systems

HPerf: A Lightweight Profiler for Task Distribution on CPU+GPU Platforms

Stochastic Gradient Descent on GPUs

Comparison of SPMV performance on matrices with different matrix format using CUSP, cuSPARSE and ViennaCL

Patterns and Rewrite Rules for Systematic Code Generation (From High-Level Functional Patterns to High-Performance OpenCL Code)

Comparison of OpenCL performance on different platforms using VexCL and Blaze

Characterizing and Enhancing Global Memory Data Coalescing on GPUs

Different Optimization Strategies and Performance Evaluation of Reduction on Multicore CUDA Architecture

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)