high performance computing on graphics processing units: hgpu.org

hgpu.org » Linear Algebra

Performance Optimization of Deep Learning Sparse Matrix Kernels on Intel Max Series GPU

Mohammad Zubair, Christoph Bauinger

View

Tags: Computer science, CUDA, Deep learning, Intel, Intel Data Center GPU Max 1550, Linear Algebra, Machine learning, Mathematical Software, Matrix multiplication, nVidia, nVidia V100, Sparse matrix, SYCL

November 5, 2023 by hgpu

Bandicoot: C++ Library for GPU Linear Algebra and Scientific Computing

Ryan R. Curtin, Marcus Edel, Conrad Sanderson

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Linear Algebra, nVidia, nVidia GeForce RTX 2080 Ti, OpenCL, Package, Programming techniques

July 30, 2023 by hgpu

Improving the Performance, Portability, and Productivity of Hardware Accelerators

Pablo Antonio Martínez Sánchez

View

Download (PDF)

Tags: Computer science, CUDA, Heterogeneous systems, Linear Algebra, Matrix multiplication, Neural networks, nVidia, nVidia GeForce RTX 2080, nVidia GeForce RTX 2080 Ti, Performance, performance portability, Thesis

July 16, 2023 by hgpu

DGEMM on Integer Matrix Multiplication Unit

Hiroyuki Ootomo, Katsuhisa Ozaki, Rio Yokota

View

Download (PDF)

Source codes

Tags: Computer science, CUBLAS, CUDA, Deep learning, Linear Algebra, Machine learning, Matrix multiplication, nVidia, nVidia A100, nVidia Jetson AGX Orin, nVidia RTX 6000 Ada, nVidia Titan RTX, Package

June 25, 2023 by hgpu

Improving Energy Efficiency of Basic Linear Algebra Routines on Heterogeneous Systems with Multiple GPUs

Hadi Zamani Sabzi

View

Download (PDF)

Tags: Algorithms, Computer science, CUDA, Energy-efficient computing, Factorization, Heterogeneous systems, Linear Algebra, Matrix multiplication, nVidia, nVidia GeForce GTX 1660, nVidia GeForce GTX 980, Thesis

May 21, 2023 by hgpu

Anatomy of High-Performance GEMM with Online Fault Tolerance on GPUs

Shixun Wu, Yujia Zhai, Jinyang Liu, Jiajun Huang, Zizhe Jian, Bryan M. Wong, Zizhong Chen

View

Download (PDF)

Source codes

Tags: Code generation, Computer science, CUDA, GEMM, Linear Algebra, Matrix multiplication, nVidia, nVidia A100, Package, Performance, Reliability, Tesla T4

May 7, 2023 by hgpu

Optimizing High-Performance Linpack for Exascale Accelerated Architectures

Noel Chalmers, Jakub Kurzak, Damon McDougall, Paul T. Bauman

View

Download (PDF)

Source codes

Tags: AMD Radeon Instinct MI250X, ATI, Benchmarking, Computer science, Factorization, HIP, Linear Algebra, MPI, Package, Performance

April 23, 2023 by hgpu

PopSparse: Accelerated block sparse matrix multiplication on IPU

Zhiyi Li, Douglas Orr, Valeriu Ohan, Godfrey Da costa, Tom Murray, Adam Sanders, Deniz Beker, Dominic Masters

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Deep learning, Linear Algebra, Machine learning, Matrix multiplication, nVidia, nVidia A100, Package, Sparse matrix

April 2, 2023 by hgpu

Harmonic CUDA: Asynchronous Programming on GPUs

Jonathan Wapman, Sean Treichler, Serban D. Porumbescu, John D. Owens

View

Download (PDF)

Tags: Computer science, CUDA, GEMM, Linear Algebra, Matrix multiplication, nVidia, nVidia A100

March 5, 2023 by hgpu

Auto-SpMV: Automated Optimizing SpMV Kernels on GPU

Mina Ashoury, Mohammad Loni, Farshad Khunjush, Masoud Daneshtalab

View

Download (PDF)

Tags: Computer science, CUDA, Energy efficiency, Linear Algebra, nVidia, nVidia GeForce GTX 1080, nVidia GeForce GTX 1650, Sparse matrix

February 26, 2023 by hgpu

Extending MAGMA Portability with OneAPI

Anna Fortenberry, Stanimire Tomov

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Heterogeneous systems, Linear Algebra, Matrix multiplication, nVidia, nVidia GeForce RTX 3060, oneAPI, Package, performance portability

December 25, 2022 by hgpu

GPU Load Balancing

Muhammad Osama

View

Download (PDF)

Source codes

Tags: Algorithms, Computer science, CUDA, Linear Algebra, load balancing, Matrix multiplication, nVidia, nVidia A100, Package, Sparse, Thesis

December 25, 2022 by hgpu

Creating a Dataset for High-Performance Computing Code Translation using LLMs: A Bridge Between OpenMP Fortran and C+

CHARM-SYCL: New Unified Programming Environment for Multiple Accelerator Types

AFOCL: Portable OpenCL Programming of FPGAs via Automated Built-in Kernel Management

pp-template: Template for Performance-Portable code development, targeting HOST-DEVICE computer architectures

An approach to performance portability through generic programming

Redco: A Lightweight Tool to Automate Distributed Training

Redco: A Lightweight Tool to Automate Distributed Training of LLMs on Any GPU/TPUs

OpenRAND: Reproducible Random Number For Parallel Computations

OpenRAND: A Performance Portable, Reproducible Random Number Generation Library for Parallel Computations

See all packages

* * *

high performance computing on graphics processing units: hgpu.org

Performance Optimization of Deep Learning Sparse Matrix Kernels on Intel Max Series GPU

Bandicoot: C++ Library for GPU Linear Algebra and Scientific Computing

Improving the Performance, Portability, and Productivity of Hardware Accelerators

DGEMM on Integer Matrix Multiplication Unit

Improving Energy Efficiency of Basic Linear Algebra Routines on Heterogeneous Systems with Multiple GPUs

Anatomy of High-Performance GEMM with Online Fault Tolerance on GPUs

Optimizing High-Performance Linpack for Exascale Accelerated Architectures

PopSparse: Accelerated block sparse matrix multiplication on IPU

Harmonic CUDA: Asynchronous Programming on GPUs

Auto-SpMV: Automated Optimizing SpMV Kernels on GPU

Extending MAGMA Portability with OneAPI

GPU Load Balancing

Recent source codes

miniBUDE: A BUDE virtual-screening benchmark, in many programming models

gossip: Efficient Communication Primitives for Multi-GPU Systems

GT4Py: GridTools for Python

AUCMEDI: a framework for Automated Classification of Medical Images

Creating a Dataset for High-Performance Computing Code Translation using LLMs: A Bridge Between OpenMP Fortran and C+

CHARM-SYCL: New Unified Programming Environment for Multiple Accelerator Types

AFOCL: Portable OpenCL Programming of FPGAs via Automated Built-in Kernel Management

pp-template: Template for Performance-Portable code development, targeting HOST-DEVICE computer architectures

Redco: A Lightweight Tool to Automate Distributed Training

OpenRAND: Reproducible Random Number For Parallel Computations

Most viewed papers (last 30 days)