high performance computing on graphics processing units: hgpu.org

Luigi Nardi, Bruno Bodin, M. Zeeshan Zia, John Mawer, Andy Nisbet, Paul H. J. Kelly, Andrew J. Davison, Mikel Lujan, Michael F. P. O'Boyle, Graham Riley, Nigel Topham, Steve Furber

View

Download (PDF)

Tags: Algorithms, ARM, Benchmarking, Computer science, Computer vision, CUDA, nVidia, nVidia GeForce GTX Titan, OpenCL, Performance

October 10, 2014 by hgpu

FDTD on Distributed Heterogeneous Multi-GPU Systems

Eirik Myklebost

View

Download (PDF)

Tags: Algorithms, Benchmarking, Cluster computing, CUDA, Electrodynamics, FDTD, Finite-difference time-domain, Heterogeneous systems, MPI, nVidia, nVidia GeForce GTX 280, nVidia GeForce GTX 470, nVidia GeForce GTX 760, Physics, Tesla K20, Thesis, Ultrasound

October 10, 2014 by hgpu

NAS Parallel Benchmarks for GPGPUs using a Directive-based Programming Model

Rengan Xu, Xiaonan Tian, Sunita Chandrasekaran, Yonghong Yan, Barbara Chapman

View

Download (PDF)

Tags: Benchmarking, Computer science, CUDA, MPI, nVidia, OpenACC, Tesla K20

September 28, 2014 by hgpu

Scalability Analysis of Parallel Algorithms on GPU Clusters

Fengshun Lu, Yufei Pang, Fukang Yin

View

Download (PDF)

Tags: Algorithms, Benchmarking, Computer science, CUDA, GPU cluster, nVidia, Tesla M2050

September 25, 2014 by hgpu

Performance analysis of a 240 thread tournament level MCTS Go program on the Intel Xeon Phi

Ali Mirsoleimani, Aske Plaat, Jos Vermaseren, Jaap van den Herik

View

Download (PDF)

Tags: Artificial intelligence, Benchmarking, Computer science, Intel Xeon Phi, Performance

September 16, 2014 by hgpu

Estimating GPU Speedups for Programs Without Writing a Single Line of GPU Code

Newsha Ardalani, Karthikeyan Sankaralingam, Xiaojin Zhu

View

Download (PDF)

Tags: Benchmarking, Computer science, CUDA, Heterogeneous systems, nVidia, nVidia GeForce GTX 480, nVidia GeForce GTX 660 Ti, OpenCL, Performance, Tesla K20

August 23, 2014 by hgpu

Practical Symbolic Race Checking of GPU Programs

Peng Li, Guodong Li, Ganesh Gopalakrishnan

View

Download (PDF)

Source codes

Tags: Benchmarking, Computer science, CUDA, nVidia, Package, Performance

August 19, 2014 by hgpu

AutoDock-GPU: AutoDock for GPUs and other accelerators

Architecting Tensor Core-Based Reductions for Irregular Molecular Docking Kernels

NCCLX: collective communication framework

Collective Communication for 100k+ GPUs

Tutoring LLM into a Better CUDA Optimizer

Kernel Library for LLM Serving

Compiler and Runtime Systems for Generative AI Models

Adaptivity in AdaptiveCpp: Optimizing Performance by Leveraging Runtime Information During JIT-Compilation

Neptune: Advanced ML Operator Fusion for Locality and Parallelism on GPUs

Genten: Software for Generalized Tensor Decompositions by Sandia National Laboratories

A Performance Portable Matrix Free Dense MTTKRP in GenTen

Interleaved Learning and Exploration: A Self-Adaptive Fuzz Testing Framework for MLIR

Pinocchio: PINpointing Orbit Crossing Collapsed Hierarchical Objects

Accelerating cosmological simulations on GPUs: a portable approach using OpenMP

KernelCoder: trained on a curated dataset of reasoning traces and CUDA kernel pairs

ConCuR: Conciseness Makes State-of-the-Art Kernel Generation

See all packages

* * *

high performance computing on graphics processing units: hgpu.org

Automatic Tuning of Local Memory Use on GPGPUs

A CUDA implementation of the High Performance Conjugate Gradient benchmark

Scalable Verification Techniques for Data-Parallel Programs

A Performance Comparison of Sort and Scan Libraries for GPUs

Leo: A Profile-Driven Dynamic Optimization Framework for GPU Applications

Introducing SLAMBench, a performance and accuracy benchmarking methodology for SLAM

FDTD on Distributed Heterogeneous Multi-GPU Systems

NAS Parallel Benchmarks for GPGPUs using a Directive-based Programming Model

Scalability Analysis of Parallel Algorithms on GPU Clusters

Performance analysis of a 240 thread tournament level MCTS Go program on the Intel Xeon Phi

Estimating GPU Speedups for Programs Without Writing a Single Line of GPU Code

Practical Symbolic Race Checking of GPU Programs

Recent source codes

AutoDock-GPU: AutoDock for GPUs and other accelerators

NCCLX: collective communication framework

Tutoring LLM into a Better CUDA Optimizer

Kernel Library for LLM Serving

Adaptivity in AdaptiveCpp: Optimizing Performance by Leveraging Runtime Information During JIT-Compilation

Neptune: Advanced ML Operator Fusion for Locality and Parallelism on GPUs

Genten: Software for Generalized Tensor Decompositions by Sandia National Laboratories

Interleaved Learning and Exploration: A Self-Adaptive Fuzz Testing Framework for MLIR

Pinocchio: PINpointing Orbit Crossing Collapsed Hierarchical Objects

KernelCoder: trained on a curated dataset of reasoning traces and CUDA kernel pairs

Most viewed papers (last 30 days)