high performance computing on graphics processing units: hgpu.org

Dong He, Supun Nakandala, Dalitso Banda, Rathijit Sen, Karla Saur, Kwanghyun Park, Carlo Curino, Jesús Camacho-Rodríguez, Konstantinos Karanasos, Matteo Interlandi

View

Download (PDF)

Source codes

Tags: Benchmarking, Cloud, Computer science, CUDA, Databases, Machine learning, nVidia, Package, Tesla P100

March 6, 2022 by hgpu

FastFold: Reducing AlphaFold Training Time from 11 Days to 67 Hours

Shenggan Cheng, Ruidong Wu, Zhongming Yu, Binrui Li, Xiwen Zhang, Jian Peng, Yang You

View

Download (PDF)

Source codes

Tags: Biology, Computer science, CUDA, Machine learning, nVidia, nVidia A100, Package

March 6, 2022 by hgpu

Enabling On-Device Smartphone GPU based Training: Lessons Learned

Anish Das, Young D. Kwon, Jagmohan Chauhan, Cecilia Mascolo

View

Download (PDF)

Tags: Computer science, Deep learning, Neural networks, OpenCL

March 6, 2022 by hgpu

A ML-based resource utilization OpenCL GPU-kernel fusion model

Usman Ahmed, Jerry Chun-Wei Lin, Gautam Srivastava

View

Download (PDF)

Tags: Computer science, Data parallelism, HPC, Machine learning, nVidia, nVidia GeForce GT 740 M, nVidia GeForce GTX 760, OpenCL

February 20, 2022 by hgpu

gLBM: A GPU enabled Lattice Boltzmann Method Library

Aaron Bray, Rachel B. Clipp, M. Umar Qureshi, Sorin Mitran, Andinet Enquobahrie

View

Download (PDF)

Source codes

Tags: cfd, CUDA, Fluid dynamics, Lattice Boltzmann model, nVidia, Package

February 20, 2022 by hgpu

A Comprehensive Benchmark of Deep Learning Libraries on Mobile Devices

Qiyang Zhang, Xiang Li, Xiangying Che, Xiao Ma, Ao Zhou, Mengwei Xu, Shangguang Wang, Yun Ma, Xuanzhe Liu

View

Download (PDF)

Source codes

Tags: ARM, Benchmarking, Computer science, Deep learning, OpenCL, OpenGL, Vulkan

February 20, 2022 by hgpu

Heuristic Adaptability to Input Dynamics for SpMM on GPUs

Guohao Dai, Guyue Huang, Shang Yang, Zhongming Yu, Hengrui Zhang, Yufei Ding, Yuan Xie, Huazhong Yang, Yu Wang

View

Download (PDF)

Source codes

Tags: Algorithms, CUDA, Matrix multiplication, Neural networks, nVidia, nVidia GeForce RTX 2080, nVidia GeForce RTX 3090, Package, Sparse matrix, Tesla V100

February 20, 2022 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

Programming

DISTAL: The Distributed Tensor Algebra Compiler

Benchmarking a Proof-of-Concept Performance Portable SYCL-based Fast Fourier Transformation Library

HipBone: A performance-portable GPU-accelerated C++ version of the NekBone benchmark

Integrating SkePU’s algorithmic skeletons with GPI on a cluster

Romou: Rapidly Generate High-Performance Tensor Kernels for Mobile GPUs

FastFold: Reducing AlphaFold Training Time from 11 Days to 67 Hours

Enabling On-Device Smartphone GPU based Training: Lessons Learned

A ML-based resource utilization OpenCL GPU-kernel fusion model

gLBM: A GPU enabled Lattice Boltzmann Method Library

A Comprehensive Benchmark of Deep Learning Libraries on Mobile Devices

Heuristic Adaptability to Input Dynamics for SpMM on GPUs

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)