high performance computing on graphics processing units: hgpu.org

Programming

hgpu.org » Programming » CUDA

MSREP: A Fast yet Light Sparse Matrix Framework for Multi-GPU Systems

Jieyang Chen, Chenhao Xie, Jesun S Firoz, Jiajia Li, Shuaiwen Leon Song, Kevin Barker, Mark Raugas, Ang Li

View

Download (PDF)

Tags: Computer science, CUDA, Linear Algebra, nVidia, nVidia DGX-1, OpenMP, Sparse matrix, Tesla V100

October 2, 2022 by hgpu

Exploiting dynamic sparse matrices for performance portable linear algebra operations

Chris Stylianou, Michele Weiland

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Heterogeneous systems, HPC, Linear Algebra, MPI, nVidia, OpenMP, Package, Sparse matrix, Tesla V100

October 2, 2022 by hgpu

Direct GPU Compilation and Execution for Host Applications with OpenMP Parallelism

Shilei Tian, Joseph Huber, Konstantinos Parasyris, Barbara Chapman, Johannes Doefert

View

Download (PDF)

Tags: Computer science, CUDA, LLVM, nVidia, nVidia A100, OpenMP, Portability

September 11, 2022 by hgpu

EnergonAI: An Inference System for 10-100 Billion Parameter Transformer Models

Jiangsu Du, Ziming Liu, Jiarui Fang, Shenggui Li, Yongbin Li, Yutong Lu, Yang You

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Deep learning, Heterogeneous systems, NLP, nVidia, nVidia A100, Package

September 11, 2022 by hgpu

Sgap: Towards Efficient Sparse Tensor Algebra Compilation for GPU

Genghan Zhang, Yuetong Zhao, Yanting Tao, Zhongming Yu, Guohao Dai, Sitao Huang, Yuan Wen, Pavlos Petoumenos, Yu Wang

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Matrix multiplication, nVidia, nVidia GeForce RTX 2080, nVidia GeForce RTX 3090, Package, Sparse matrix, Tesla V100

September 11, 2022 by hgpu

GGArray: A Dynamically Growable GPU Array

Enzo meneses, Cristóbal A. Navarro, Héctor Ferrada

View

Download (PDF)

Tags: Algorithms, Computer science, CUDA, Memory, nVidia, nVidia A100, nVidia Titan RTX

September 4, 2022 by hgpu

Understanding the Power of Evolutionary Computation for GPU Code Optimization

Jhe-Yu Liou, Muaaz Awan, Steven Hofmeyr, Stephanie Forrest, Carole-Jean Wu

View

Download (PDF)

Source codes

Tags: Bioinformatics, Biology, Computer science, CUDA, Evolutionary Computations, Neural and Evolutionary Computing, nVidia, nVidia GeForce GTX 1080 Ti, Package, performance portability, Sequence alignment, Tesla P100, Tesla V100

September 4, 2022 by hgpu

Towards Understanding and Mitigating Memory-Access Challenges in Computing Systems

Mohammad K. Dashti

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Deep learning, Heterogeneous systems, Memory model, nVidia, nVidia GeForce RTX 2070, nVidia Jetson TK1, OpenCL, Package, Thesis

August 28, 2022 by hgpu

Fully Concurrent GPU Data Structures

Muhammad Abdelghaffar Awad

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Data Structures and Algorithms, nVidia, nVidia GeForce GTX Titan V, Package, Tesla V100

August 28, 2022 by hgpu

LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale

Tim Dettmers, Mike Lewis, Younes Belkada, Luke Zettlemoyer

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Deep learning, Machine learning, Matrix multiplication, nVidia, nVidia A40, Package, PyTorch

August 21, 2022 by hgpu

Optimization of GPU workloads using natural language processing based on deep learning techniques

Petros Vavaroutsos

View

Download (PDF)

Tags: ATI, ATI Radeon HD 7970, Computer science, CUDA, Deep learning, Machine learning, Neural networks, nVidia, nVidia GeForce GTX 970, OpenCL, Thesis

August 21, 2022 by hgpu

A Container-Based Workflow for Distributed Training of Deep Learning Algorithms in HPC Clusters

Jose González-Abad, Álvaro López García, Valentin Y. Kozlov

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Deep learning, HPC, nVidia, nVidia GeForce GTX 980 Ti, Package, Tesla V100

August 7, 2022 by hgpu

tritonBLAS: A Lightweight Triton-based General Matrix Multiplication (GEMM) Library

tritonBLAS: Triton-based Analytical Approach for GEMM Kernel Parameter Selection

hls4ml: Machine learning on FPGAs using HLS

hls4ml: A Flexible, Open-Source Platform for Deep Learning Acceleration on Reconfigurable Hardware

ThunderKittens: Tile primitives for speedy kernels

ParallelKittens: Systematic and Practical Simplification of Multi-GPU AI Kernels

NVIDIA Nemotron Parse 1.1

Iris: AMD RAD's multi-GPU Triton-based framework for seamless multi-GPU programming

Iris: First-Class Multi-GPU Programming Experience in Triton

HipKittens: Fast and Furious AMD Kernels

CudaForge: An Agent Framework with Hardware Feedback for CUDA Kernel Optimization

See all packages

* * *

high performance computing on graphics processing units: hgpu.org

Programming

MSREP: A Fast yet Light Sparse Matrix Framework for Multi-GPU Systems

Exploiting dynamic sparse matrices for performance portable linear algebra operations

Direct GPU Compilation and Execution for Host Applications with OpenMP Parallelism

EnergonAI: An Inference System for 10-100 Billion Parameter Transformer Models

Sgap: Towards Efficient Sparse Tensor Algebra Compilation for GPU

GGArray: A Dynamically Growable GPU Array

Understanding the Power of Evolutionary Computation for GPU Code Optimization

Towards Understanding and Mitigating Memory-Access Challenges in Computing Systems

Fully Concurrent GPU Data Structures

LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale

Optimization of GPU workloads using natural language processing based on deep learning techniques

A Container-Based Workflow for Distributed Training of Deep Learning Algorithms in HPC Clusters

Recent source codes

tritonBLAS: A Lightweight Triton-based General Matrix Multiplication (GEMM) Library

hls4ml: Machine learning on FPGAs using HLS

ThunderKittens: Tile primitives for speedy kernels

NVIDIA Nemotron Parse 1.1

Iris: AMD RAD's multi-GPU Triton-based framework for seamless multi-GPU programming

HipKittens: Fast and Furious AMD Kernels

Fortran xDSL dialects

mt4g: Memory Topology 4 GPUs

Falcon: GPU-Based Floating-point Adaptive Lossless Compression

CudaForge: An Agent Framework with Hardware Feedback for CUDA Kernel Optimization

Most viewed papers (last 30 days)