Saved in:
Bibliographic Details
Main Authors: Popovici, Doru Thom, Vega, Mario, Ioannou, Angelos, Chaix, Fabien, Mosuli, Dania, Reasoner, Blair, Nguyen, Tan, Yang, Xiaokun, Shalf, John
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.09774
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908534744023040
author Popovici, Doru Thom
Vega, Mario
Ioannou, Angelos
Chaix, Fabien
Mosuli, Dania
Reasoner, Blair
Nguyen, Tan
Yang, Xiaokun
Shalf, John
author_facet Popovici, Doru Thom
Vega, Mario
Ioannou, Angelos
Chaix, Fabien
Mosuli, Dania
Reasoner, Blair
Nguyen, Tan
Yang, Xiaokun
Shalf, John
contents Developing efficient hardware accelerators for mathematical kernels used in scientific applications and machine learning has traditionally been a labor-intensive task. These accelerators typically require low-level programming in Verilog or other hardware description languages, along with significant manual optimization effort. Recently, to alleviate this challenge, high-level hardware design tools like Chisel and High-Level Synthesis have emerged. However, as with any compiler, some of the generated hardware may be suboptimal compared to expert-crafted designs. Understanding where these inefficiencies arise is crucial, as it provides valuable insights for both users and tool developers. In this paper, we propose a methodology to hierarchically decompose mathematical kernels - such as Fourier transforms, matrix multiplication, and QR factorization - into a set of common building blocks or primitives. Then the primitives are implemented in the different programming environments, and the larger algorithms get assembled. Furthermore, we employ an automatic approach to investigate the achievable frequency and required resources. Performing this experimentation at each level will provide fairer comparisons between designs and offer guidance for both tool developers and hardware designers to adopt better practices.
format Preprint
id arxiv_https___arxiv_org_abs_2509_09774
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards An Approach to Identify Divergences in Hardware Designs for HPC Workloads
Popovici, Doru Thom
Vega, Mario
Ioannou, Angelos
Chaix, Fabien
Mosuli, Dania
Reasoner, Blair
Nguyen, Tan
Yang, Xiaokun
Shalf, John
Hardware Architecture
Developing efficient hardware accelerators for mathematical kernels used in scientific applications and machine learning has traditionally been a labor-intensive task. These accelerators typically require low-level programming in Verilog or other hardware description languages, along with significant manual optimization effort. Recently, to alleviate this challenge, high-level hardware design tools like Chisel and High-Level Synthesis have emerged. However, as with any compiler, some of the generated hardware may be suboptimal compared to expert-crafted designs. Understanding where these inefficiencies arise is crucial, as it provides valuable insights for both users and tool developers. In this paper, we propose a methodology to hierarchically decompose mathematical kernels - such as Fourier transforms, matrix multiplication, and QR factorization - into a set of common building blocks or primitives. Then the primitives are implemented in the different programming environments, and the larger algorithms get assembled. Furthermore, we employ an automatic approach to investigate the achievable frequency and required resources. Performing this experimentation at each level will provide fairer comparisons between designs and offer guidance for both tool developers and hardware designers to adopt better practices.
title Towards An Approach to Identify Divergences in Hardware Designs for HPC Workloads
topic Hardware Architecture
url https://arxiv.org/abs/2509.09774