high performance computing on graphics processing units: hgpu.org

Jacob Kahn, Vineel Pratap, Tatiana Likhomanenko, Qiantong Xu, Awni Hannun, Jeff Cai, Paden Tomasello, Ann Lee, Edouard Grave, Gilad Avidov, Benoit Steiner, Vitaliy Liptchinsky, Gabriel Synnaeve, Ronan Collobert

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Machine learning, nVidia, Package, Tesla V100

February 6, 2022 by hgpu

SZx: an Ultra-fast Error-bounded Lossy Compressor for Scientific Datasets

Xiaodong Yu, Sheng Di, Kai Zhao, jiannan Tian, Dingwen Tao, Xin Liang, Franck Cappello

View

Download (PDF)

Tags: Algorithms, Compression, Computer science, CUDA, nVidia, nVidia A100, Tesla V100

February 6, 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

Applications

Enabling On-Device Smartphone GPU based Training: Lessons Learned

gLBM: A GPU enabled Lattice Boltzmann Method Library

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

Lightning: Scaling the GPU Programming Model Beyond a Single GPU

A Comprehensive Benchmark of Deep Learning Libraries on Mobile Devices

Electrical-Level Attacks on CPUs, FPGAs, and GPUs: Survey and Implications in the Heterogeneous Era

Pattern-based Programming Abstractions for Heterogeneous Parallel Computing

The Ecological Footprint of Neural Machine Translation Systems

Improving Loop Parallelization by a Combination of Static and Dynamic Analyses in HLS

FC_ACCEL: Enabling Efficient, Low-Latency and Flexible Inference in DNN Fully Connected Layers, using Optimized Checkerboard Block matrix decomposition, fast scheduling, and a resource efficient 1D PE array with a custom HBM2 memory subsystem

Flashlight: Enabling Innovation in Tools for Machine Learning

SZx: an Ultra-fast Error-bounded Lossy Compressor for Scientific Datasets

Recent source codes

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

LLaMA-Inference-Bench

MATAR