high performance computing on graphics processing units: hgpu.org

Applications

hgpu.org » paper

SkePU 2: Flexible and Type-Safe Skeleton Programming for Heterogeneous Parallel Systems

August Ernstsson, Christoph Kessler

View

Download (PDF)

Source codes

Tags: Compilers, Computer science, CUDA, Heterogeneous systems, Intel Xeon Phi, nVidia, OpenCL, OpenMP, Package, Tesla K20

January 28, 2018 by hgpu

Revisiting Online Autotuning for Sparse-Matrix Vector Multiplication Kernels on Next-Generation Architectures

Simon Garcia De Gonzalo, Simon D. Hammond, Christian R. Trott, Wen-Mei Hwu

View

Download (PDF)

Tags: Auto-Tuning, Computer science, CUDA, Intel Xeon Phi, nVidia, Sparse matrix, Tesla K20, Tesla K40, Tesla K80, Tesla P100

January 28, 2018 by hgpu

Communication Architectures for Scalable GPU-centric Computing Systems

Benjamin Klenk

View

Download (PDF)

Tags: Algorithms, Benchmarking, Computer science, CUDA, Heterogeneous systems, nVidia, Tesla K20, Thesis

January 28, 2018 by hgpu

A Survey on Compiler Autotuning using Machine Learning

Amir H. Ashouri, William Killian, John Cavazos, Gianluca Palermo, Cristina Silvano

View

Download (PDF)

Tags: Auto-Tuning, Compilers, Computer science, Machine learning, Performance

January 28, 2018 by hgpu

Improving Communication Performance in GPU-Accelerated HPC Clusters

Iman Faraji

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, GPU cluster, MPI, nVidia, Package, Performance, Thesis

January 28, 2018 by hgpu

Scheduling Parallel Tasks under Multiple Resources: List Scheduling vs. Pack Scheduling

Hongyang Sun, Redouane Elghazi, Ana Gainaru, Guillaume Aupy, Padma Raghavan

View

Download (PDF)

Tags: Computer science, Intel Xeon Phi, Performance, Task scheduling

January 20, 2018 by hgpu

Comprehensive Optimization of Parametric Kernels for Graphics Processing Units

Xiaohui Chen, Marc Moreno-Maza, Jeeva Paudel, Ning Xie

View

Download (PDF)

Source codes

Tags: Code generation, Computer science, CUDA, LLVM, nVidia, Package, Performance, PTX, Symbolic Computation, Tesla M2050

January 20, 2018 by hgpu

SuperNeurons: Dynamic GPU Memory Management for Training Deep Neural Networks

Linnan Wang, Jinmian Ye, Yiyang Zhao, Wei Wu, Ang Li, Shuaiwen Leon Song, Zenglin Xu, Tim Kraska

View

Download (PDF)

Tags: Computer science, CUDA, Deep learning, Machine learning, Neural networks, nVidia, Tesla K40

January 20, 2018 by hgpu

Fast and Flexible GPU Accelerated Binding Free Energy Calculations within the AMBER Molecular Dynamics Package

Daniel J. Mermelstein, Charles Lin, Gard Nelson, Rachael Kretsch, J. Andrew McCammon, Ross C. Walker

View

Download (PDF)

Tags: Algorithms, Bioinformatics, Biology, CUDA, Molecular dynamics, nVidia, nVidia GeForce GTX 1080 Ti, nVidia GeForce GTX Titan X

January 20, 2018 by hgpu

Evaluation of Machine Learning Fameworks on Finis Terrae II

Andres Gomez Tato

View

Download (PDF)

Tags: Algorithms, Benchmarking, Computer science, CUDA, Deep learning, Machine learning, nVidia, Performance, Tesla K80

January 20, 2018 by hgpu

ImageCL: Language and source-to-source compiler for performance portability, load balancing, and scalability prediction on heterogeneous systems

Thomas L. Falch, Anne C. Elster

View

Download (PDF)

Source codes

Tags: ATI, ATI Radeon HD 7970, Compilers, Heterogeneous systems, Image processing, Machine learning, nVidia, nVidia GeForce GTX 960, OpenCL, Package, performance portability, Tesla K40

January 13, 2018 by hgpu

Graph Processing on GPUs: A Survey

Xuanhua Shi, Zhigao Zheng, Yongluan Zhou, Hai Jin, Ligang He, Bo Liu, Qiang-Sheng Hua

View

Download (PDF)

Tags: Computer science, CUDA, Graph theory, nVidia, OpenCL, survey

January 13, 2018 by hgpu

torchPDLP: Primal-Dual Linear Programming in PyTorch. In collaboration with AMD and IPAM

Accelerating a Linear Programming Algorithm on AMD GPUs

Benchmarks for Dissecting CPU-GPU Unified Physical Memory on AMD MI300A APUs

Dissecting CPU-GPU Unified Physical Memory on AMD MI300A APUs

kvcached: Elastic KV cache for dynamic GPU sharing and efficient multi-LLM inference

Towards Efficient and Practical GPU Multitasking in the Era of LLM

Bandicoot: C++ library for GPU accelerated linear algebra

Bandicoot: A Templated C++ Library for GPU Linear Algebra

Luthier: Bridging Auto-Tuning and Vendor Libraries for Efficient Deep Learning Inference

Fused Kernel Library (FKL)

The Fused Kernel Library: A C++ API to Develop Highly-Efficient GPU Libraries

GPUHammer: Rowhammer Attacks on GPU Memories are Practical

Block: Balance Loader of LLM Serving with Context, Knowledge and Predictive Scheduling

Block: Balancing Load in LLM Serving with Context, Knowledge and Predictive Scheduling

SIGMo: Scalable Isomorphism Graph Matching on GPUs

SIGMo: High-Throughput Batched Subgraph Isomorphism on GPUs for Molecular Matching

DGEMM without FP64 Arithmetic - using FP64 Emulation and FP8 Tensor Cores with Ozaki Scheme

DGEMM without FP64 Arithmetic – using FP64 Emulation and FP8 Tensor Cores with Ozaki Scheme

See all packages

* * *

high performance computing on graphics processing units: hgpu.org

Applications

SkePU 2: Flexible and Type-Safe Skeleton Programming for Heterogeneous Parallel Systems

Revisiting Online Autotuning for Sparse-Matrix Vector Multiplication Kernels on Next-Generation Architectures

Communication Architectures for Scalable GPU-centric Computing Systems

A Survey on Compiler Autotuning using Machine Learning

Improving Communication Performance in GPU-Accelerated HPC Clusters

Scheduling Parallel Tasks under Multiple Resources: List Scheduling vs. Pack Scheduling

Comprehensive Optimization of Parametric Kernels for Graphics Processing Units

SuperNeurons: Dynamic GPU Memory Management for Training Deep Neural Networks

Fast and Flexible GPU Accelerated Binding Free Energy Calculations within the AMBER Molecular Dynamics Package

Evaluation of Machine Learning Fameworks on Finis Terrae II

ImageCL: Language and source-to-source compiler for performance portability, load balancing, and scalability prediction on heterogeneous systems

Graph Processing on GPUs: A Survey

Recent source codes

torchPDLP: Primal-Dual Linear Programming in PyTorch. In collaboration with AMD and IPAM

Benchmarks for Dissecting CPU-GPU Unified Physical Memory on AMD MI300A APUs

kvcached: Elastic KV cache for dynamic GPU sharing and efficient multi-LLM inference

Bandicoot: C++ library for GPU accelerated linear algebra

Luthier: Bridging Auto-Tuning and Vendor Libraries for Efficient Deep Learning Inference

Fused Kernel Library (FKL)

GPUHammer: Rowhammer Attacks on GPU Memories are Practical

Block: Balance Loader of LLM Serving with Context, Knowledge and Predictive Scheduling

SIGMo: Scalable Isomorphism Graph Matching on GPUs

DGEMM without FP64 Arithmetic - using FP64 Emulation and FP8 Tensor Cores with Ozaki Scheme

Most viewed papers (last 30 days)