high performance computing on graphics processing units: hgpu.org

Tal Kadosh, Niranjan Hasabnis, Vy A. Vo, Nadav Schneider, Neva Krien, Mihai Capota, Abdul Wasay, Nesreen Ahmed, Ted Willke, Guy Tamir, Yuval Pinter, Timothy Mattson, Gal Oren

View

Download (PDF)

Source codes

Tags: AI, Code generation, Computer science, Heterogeneous systems, HPC, nVidia, nVidia A40, OpenMP, Package, Python

January 7, 2024 by hgpu

An Autonomous Data Language

Tom T.P. Franken, Thomas Neele, Jan Friso Groote

View

Download (PDF)

Tags: Code generation, Computer science, CUDA, nVidia, OpenCL, Programming Languages

January 7, 2024 by hgpu

CuPBoP-AMD: Extending CUDA to AMD Platforms

Jun Chen, Xule Zhou, Hyesoon Kim

View

Download (PDF)

Source codes

Tags: AMD Radeon Instinct MI210, ATI, Code generation, Computer science, CUDA, HIP, nVidia, OpenCL, Package

December 3, 2023 by hgpu

Performance portability evaluation of blocked stencil computations on GPUs

Oscar Antepara, Hans Johansen, Samuel Williams, Tuowen Zhao, Samantha Hirsch, Priya Goyal, Mary Hall

View

Download (PDF)

Source codes

Tags: AMD Radeon Instinct MI250X, ATI, Code generation, Computer science, CUDA, HIP, nVidia, nVidia A100, Package, performance portability, Stencil computation, SYCL

October 29, 2023 by hgpu

* * *

high performance computing on graphics processing units: hgpu.org

Optimized Code Generation for Parallel and Polyhedral Loop Nests using MLIR

Automatic Generation of OpenCL Code through Polyhedral Compilation with LLM

A Comparison of OpenCL, CUDA, and HIP as Compilation Targets for a Functional Array Language

Automated C/C++ Program Repair for High-Level Synthesis via Large Language Models

APPy: Annotated Parallelism for Python on GPUs

DeepSeek-Coder: When the Large Language Model Meets Programming – The Rise of Code Intelligence

swCUDA: Auto parallel code translation framework from CUDA to ATHREAD for new generation sunway supercomputer

Code Generation for a Variety of Accelerators for a Graph DSL

Domain-Specific Code Language Models: Unraveling the Potential for HPC Codes and Tasks

An Autonomous Data Language

CuPBoP-AMD: Extending CUDA to AMD Platforms

Performance portability evaluation of blocked stencil computations on GPUs

Recent source codes

Mixed-precision finite element kernels

SHMT: The Simultaneous and Heterogenous Multithreading project

EnergyUCB-Bandit

Superpipeline: A Universal Approach for Reducing GPU Memory Usage in Large Models

Faial: finds bugs in CUDA kernels

Effects of OpenCL-Based Parallelization Methods on Explicit Numerical Methods to Solve the Heat Equation

Intel® SHMEM: Device initiated shared memory based communication library

miniLB: Lattice Botlzmann miniapp w/SYCL

AFOCL

2domination

Most viewed papers (last 30 days)