high performance computing on graphics processing units: hgpu.org

hgpu.org » Performance

Lessons Learned Migrating CUDA to SYCL: A HEP Case Study with ROOT RDataFrame

Jolly Chen, Monica Dessole, Ana Lucia Varbanescu

View

Download (PDF)

Source codes

Tags: CUDA, HEP, nVidia, nVidia Quadro RTX 4000, OpenCL, Package, Performance, Physics, SYCL

January 28, 2024 by hgpu

Minuet: Accelerating 3D Sparse Convolutions on GPUs

Jiacheng Yang, Christina Giannoula, Jun Wu, Mostafa Elhoushi, James Gleeson, Gennady Pekhimenko

View

Download (PDF)

Source codes

Tags: Cloud, Computer science, CUDA, Matrix multiplication, nVidia, nVidia GeForce RTX 2070, nVidia GeForce RTX 2080 Ti, nVidia GeForce RTX 3090, Package, Performance, PyTorch, Tesla A100

January 21, 2024 by hgpu

Preliminary report: Initial evaluation of StdPar implementations on AMD GPUs for HPC

Wei-Chen Lin, Simon McIntosh-Smith, Tom Deakin

View

Download (PDF)

Tags: AMD Radeon Instinct MI100, AMD Radeon VII, Computer science, Heterogeneous systems, HIP, nVidia, OpenCL, Performance, SYCL

January 14, 2024 by hgpu

Optimization of Ported CFD Kernels on Intel Data Center GPU Max 1550 using oneAPI ESIMD

Mohammad Zubair, Aaron Walden, Gabriel Nastac, Eric Nielsen, Christoph Bauinger, Xiao Zhu

View

Download (PDF)

Tags: cfd, CUDA, Fluid dynamics, Intel, Intel Data Center GPU Max 1550, nVidia, nVidia A100, oneAPI, Performance, SYCL

December 31, 2023 by hgpu

Experiences Building an MLIR-based SYCL Compiler

Ettore Tiotto, Víctor Pérez, Whitney Tsang, Lukas Sommer, Julian Oppermann, Victor Lomüller, Mehdi Goli, James Brodman

View

Download (PDF)

Tags: Compilers, Computer science, Heterogeneous systems, Performance, Programming Languages, SYCL

December 24, 2023 by hgpu

Comparative Performance and Scalability Analysis of GPU-accelerated Database Operations

Carl Andersson, Jonathan Nilsson

View

Download (PDF)

Tags: Benchmarking, Computer science, CUDA, Databases, nVidia, nVidia A10, nVidia M60, Performance, Tesla T4, Thesis

December 24, 2023 by hgpu

Precision and Performance Analysis of C Standard Math Library Functions on GPUs

Anton Rydahl, Joseph Huber, Ethan Luis McDonough, Johannes Doerfert

View

Download (PDF)

Tags: AMD Radeon Instinct MI250X, AMD Radeon Instinct Mi50, ATI, Benchmarking, Compilers, Computer science, CUDA, HIP, Numerical Analysis, OpenMP, Performance, Tesla A100, Tesla V100

December 18, 2023 by hgpu

Application Performance Profiling on Intel GPUs with Oneprof and Onetrace

Mariam Umar, Maxwell Jong

View

Download (PDF)

Source codes

Tags: Computer science, Intel, Intel Data Center GPU Max 1550, OpenCL, OpenMP, Package, Performance

December 18, 2023 by hgpu

GenVectorX: A performance-portable SYCL library for Lorentz Vectors operations

Monica Dessole, Jolly Chen, Axel Naumann

View

Download (PDF)

Source codes

Tags: CUDA, nVidia, nVidia A100, nVidia GeForce RTX 3060, nVidia L4, oneAPI, Package, Performance, Physics, SYCL

December 10, 2023 by hgpu

Testing and Mutation Testing for GPU Kernels

Yujie Liu

View

Download (PDF)

Source codes

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

December 3, 2023 by hgpu

On the Three P’s of Parallel Programming for Heterogeneous Computing: Performance, Productivity, and Portability

Atharva Gondhalekar, Wu-chun Feng

View

Download (PDF)

Tags: Computer science, FPGA, Heterogeneous systems, HLS, nVidia, nVidia GeForce RTX 3090, oneAPI, OpenCL, Performance, performance portability, SYCL

November 12, 2023 by hgpu

An approach to performance portability through generic programming

Andreas Hadjigeorgiou, Christodoulos Stylianou, Michele Weiland, Dirk Jacob Verschuur, Jacob Finkenrath

View

Download (PDF)

Source codes

Tags: AMD Radeon Instinct MI100, ATI, Benchmarking, Computer science, CUDA, HIP, HPC, nVidia, OpenMP, Package, Performance, performance portability, Portability, Tesla V100

November 12, 2023 by hgpu

gpu_tracker: Context manager and CLI that tracks the computational-resource-usage of a code block or shell command, particularly the GPU usage

gpu_tracker: Python package for tracking and profiling GPU utilization in both desktop and high-performance computing environments

LOOPer: a polyhedral compiler for expressing fast and portable data parallel algorithms

LOOPer: A Learned Automatic Code Optimizer For Polyhedral Compilers

OpenMC Monte Carlo Code

Performance Portable Monte Carlo Particle Transport on Intel, NVIDIA, and AMD GPUs

Polygeist: C/C++ frontend for MLIR

Retargeting and Respecializing GPU Workloads for Performance Portability

Parallel Gaussian process with kernel approximation in CUDA

Optical flow algorithms for SYCL

SYCL in the edge: performance and energy evaluation for heterogeneous acceleration

OpenMP5-Offload-OpenMC-Intel-PVC

Distributed OpenMP Offloading of OpenMC on Intel GPU MAX Accelerators

See all packages

* * *

high performance computing on graphics processing units: hgpu.org

Lessons Learned Migrating CUDA to SYCL: A HEP Case Study with ROOT RDataFrame

Preliminary report: Initial evaluation of StdPar implementations on AMD GPUs for HPC

Optimization of Ported CFD Kernels on Intel Data Center GPU Max 1550 using oneAPI ESIMD

Experiences Building an MLIR-based SYCL Compiler

Comparative Performance and Scalability Analysis of GPU-accelerated Database Operations

Precision and Performance Analysis of C Standard Math Library Functions on GPUs

Application Performance Profiling on Intel GPUs with Oneprof and Onetrace

GenVectorX: A performance-portable SYCL library for Lorentz Vectors operations

Testing and Mutation Testing for GPU Kernels

On the Three P’s of Parallel Programming for Heterogeneous Computing: Performance, Productivity, and Portability

An approach to performance portability through generic programming

Recent source codes

QArray

Celerity: High-level C++ for Accelerator Clusters

CIFAR-10 Airbench: 94% on CIFAR-10 in 3.29 second

gpu_tracker: Context manager and CLI that tracks the computational-resource-usage of a code block or shell command, particularly the GPU usage

LOOPer: a polyhedral compiler for expressing fast and portable data parallel algorithms

OpenMC Monte Carlo Code

Polygeist: C/C++ frontend for MLIR

Parallel Gaussian process with kernel approximation in CUDA

Optical flow algorithms for SYCL

OpenMP5-Offload-OpenMC-Intel-PVC

Most viewed papers (last 30 days)