Saved in:
Bibliographic Details
Main Authors: Sarda, Giuseppe M., Shah, Nimish, Bhattacharjee, Debjyoti, Debacker, Peter, Verhelst, Marian
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.11999
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913434169245696
author Sarda, Giuseppe M.
Shah, Nimish
Bhattacharjee, Debjyoti
Debacker, Peter
Verhelst, Marian
author_facet Sarda, Giuseppe M.
Shah, Nimish
Bhattacharjee, Debjyoti
Debacker, Peter
Verhelst, Marian
contents GPGPU execution analysis has always been tied to closed-source, proprietary benchmarking tools that provide high-level, non-exhaustive, and/or statistical information, preventing a thorough understanding of bottlenecks and optimization possibilities. Open-source hardware platforms offer opportunities to overcome such limits and co-optimize the full {hardware-mapping-algorithm} compute stack. Yet, so far, this has remained under-explored. In this work, we exploit micro-architecture parameter analysis to develop a hardware-aware, runtime mapping technique for OpenCL kernels on the open Vortex RISC-V GPGPU. Our method is based on trace observations and targets optimal hardware resource utilization to achieve superior performance and flexibility compared to hardware-agnostic mapping approaches. The technique was validated on different architectural GPU configurations across several OpenCL kernels. Overall, our approach significantly enhances the performance of the open-source Vortex GPGPU, contributing to unlocking its potential and usability.
format Preprint
id arxiv_https___arxiv_org_abs_2407_11999
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Optimising GPGPU Execution Through Runtime Micro-Architecture Parameter Analysis
Sarda, Giuseppe M.
Shah, Nimish
Bhattacharjee, Debjyoti
Debacker, Peter
Verhelst, Marian
Hardware Architecture
GPGPU execution analysis has always been tied to closed-source, proprietary benchmarking tools that provide high-level, non-exhaustive, and/or statistical information, preventing a thorough understanding of bottlenecks and optimization possibilities. Open-source hardware platforms offer opportunities to overcome such limits and co-optimize the full {hardware-mapping-algorithm} compute stack. Yet, so far, this has remained under-explored. In this work, we exploit micro-architecture parameter analysis to develop a hardware-aware, runtime mapping technique for OpenCL kernels on the open Vortex RISC-V GPGPU. Our method is based on trace observations and targets optimal hardware resource utilization to achieve superior performance and flexibility compared to hardware-agnostic mapping approaches. The technique was validated on different architectural GPU configurations across several OpenCL kernels. Overall, our approach significantly enhances the performance of the open-source Vortex GPGPU, contributing to unlocking its potential and usability.
title Optimising GPGPU Execution Through Runtime Micro-Architecture Parameter Analysis
topic Hardware Architecture
url https://arxiv.org/abs/2407.11999