high performance computing on graphics processing units: hgpu.org

hgpu.org » Applications » Computer science

Comparison of HPC Architectures for Computing All-Pairs Shortest Paths. Intel Xeon Phi KNL vs NVIDIA Pascal

Manuel Costanzo, Enzo Rucci, Ulises Costi, Franco Chichizola, Marcelo Naiouf

View

Download (PDF)

Source codes

Tags: Algorithms, All-Pairs Distance, Computer science, CUDA, HPC, Intel, Intel Xeon Phi, nVidia, nVidia GeForce GTX Titan X, Package

May 23, 2021 by hgpu

NPBench: A Benchmarking Suite for High-Performance NumPy

Alexandros Nikolaos Ziogas, Tal Ben-Nun, Timo Schneider, Torsten Hoefler

View

Download (PDF)

Source codes

Tags: Benchmarking, Computer science, CUDA, HPC, Linear Algebra, nVidia, Package, Performance, Python, Tesla V100

May 16, 2021 by hgpu

PeriPy – A High Performance OpenCL Peridynamics Package

B. Boys, T. J. Dodwell, M. Hobbs, M. Girolami

View

Download (PDF)

Source codes

Tags: Benchmarking, Computer science, Heterogeneous systems, nVidia, nVidia GeForce RTX 2080 Ti, OpenCL, Package, Python

May 16, 2021 by hgpu

Performance Evaluation and Improvements of the PoCL Open-Source OpenCL Implementation on Intel CPUs

Tobias Baumann, Matthias Noack, Thomas Steinke

View

Download (PDF)

Source codes

Tags: Benchmarking, Computer science, LLVM, OpenCL, Package, Video

May 9, 2021 by hgpu

Easy and Efficient Transformer: Scalable Inference Solution For large NLP mode

Gongzheng li, Yadong Xi, Jingzhen Ding, Duan Wang, Bai Liu, Changjie Fan, Xiaoxi Mao, Zeng Zhao

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, NLP, nVidia, nVidia GeForce RTX 2080 Ti, Package, Tesla A100

May 2, 2021 by hgpu

Ripple: Simplified Large-Scale Computation on Heterogeneous Architectures with Polymorphic Data Layout

Robert Clucas, Philip Blakely, Nikolaos Nikiforakis

View

Download (PDF)

Source codes

Tags: Algorithms, Computer science, CUDA, Heterogeneous systems, nVidia, Package, Tesla V100

April 25, 2021 by hgpu

CryptGPU: Fast Privacy-Preserving Machine Learning on the GPU

Sijun Tan, Brian Knott, Yuan Tian, David J. Wu

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Deep learning, Linear Algebra, Machine learning, Neural networks, nVidia, Package, PyTorch, Security, Tesla V100

April 25, 2021 by hgpu

SLATE port to AMD and Intel platforms

Ahmad Abdelfattah, Mohammed Al Farhan, Cade Brown, Mark Gates, Dalal Sukkari, Asim YarKhan, Jack Dongarra

View

Download (PDF)

Source codes

Tags: Computer science, CUBLAS, CUDA, Linear Algebra, nVidia, OpenCL, Package, SYCL

April 18, 2021 by hgpu

Efficient Large-Scale Language Model Training on GPU Clusters

Deepak Narayanan, Mohammad Shoeybi, Jared Casper, Patrick LeGresley, Mostofa Patwary, Vijay Korthikanti, Dmitri Vainbrand, Prethvi Kashinkunti, Julie Bernauer, Bryan Catanzaro, Amar Phanishayee, Matei Zaharia

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Data parallelism, Deep learning, GPU cluster, NLP, nVidia, nVidia DGX-A100, Package

April 18, 2021 by hgpu

Performance Monitoring of Multi-FPGA Systems

Arzhang Rafii

View

Download (PDF)

Source codes

Tags: Computer science, FPGA, Package, Performance, Thesis

April 11, 2021 by hgpu

Efficient Video Compression via Content-Adaptive Super-Resolution

Mehrdad Khani, Vibhaalakshmi Sivaraman, Mohammad Alizadeh

View

Download (PDF)

Source codes

Tags: Compression, Computer science, Deep learning, Neural networks, nVidia, Package, Tesla V100

April 11, 2021 by hgpu

Parallel Arbitrary-precision Integer Arithmetic

Davood Mohajerani

View

Download (PDF)

Source codes

Tags: Algorithms, Computer science, CUDA, nVidia, OpenCL, Package, Thesis

April 5, 2021 by hgpu

Data-efficient LLM Fine-tuning for Code Generation

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

DeepCompile: A Compiler-Driven Approach to Optimizing Distributed Deep Learning Training

Large Language Model Powered C-to-CUDA Code Translation: A Novel Auto-Parallelization Framework

GigaAPI: a user-space API that simplifies multi-GPU programming, bridging the gap between the capabilities of parallel GPU systems and the ability of developers to harness their full potential

GigaAPI for GPU Parallelization

Coccinelle: a C code transformation engine using SmPL for matches, refactorings, and bug fixing

Advances in Semantic Patching for HPC-oriented Refactorings with Coccinelle

DuoReduce: MLIR's benchmark

Hardware-Assisted Software Testing and Debugging for Heterogeneous Computing

See all packages

* * *

high performance computing on graphics processing units: hgpu.org

Packages

Comparison of HPC Architectures for Computing All-Pairs Shortest Paths. Intel Xeon Phi KNL vs NVIDIA Pascal

NPBench: A Benchmarking Suite for High-Performance NumPy

PeriPy – A High Performance OpenCL Peridynamics Package

Performance Evaluation and Improvements of the PoCL Open-Source OpenCL Implementation on Intel CPUs

Easy and Efficient Transformer: Scalable Inference Solution For large NLP mode

Ripple: Simplified Large-Scale Computation on Heterogeneous Architectures with Polymorphic Data Layout

CryptGPU: Fast Privacy-Preserving Machine Learning on the GPU

SLATE port to AMD and Intel platforms

Efficient Large-Scale Language Model Training on GPU Clusters

Performance Monitoring of Multi-FPGA Systems

Efficient Video Compression via Content-Adaptive Super-Resolution

Parallel Arbitrary-precision Integer Arithmetic

Recent source codes

PELSI: Power-Efficient Layer-Switched Inference

Ouroboros: Virtualized Queues for dynamic memory management

MSCCL++: A GPU-driven communication stack for scalable AI applications

Benchmark compute shader of Unity against InteropUnityCUDA

Data-efficient LLM Fine-tuning for Code Generation

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

Large Language Model Powered C-to-CUDA Code Translation: A Novel Auto-Parallelization Framework

GigaAPI: a user-space API that simplifies multi-GPU programming, bridging the gap between the capabilities of parallel GPU systems and the ability of developers to harness their full potential

Coccinelle: a C code transformation engine using SmPL for matches, refactorings, and bug fixing

DuoReduce: MLIR's benchmark

Most viewed papers (last 30 days)