Deterministic and Probabilistic Rounding Error Analysis for Mixed-Precision Arithmetic on Modern Computing Units

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bhola, Sahil, Duraisamy, Karthik
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917850912915456
author Bhola, Sahil
Duraisamy, Karthik
author_facet Bhola, Sahil
Duraisamy, Karthik
contents Modern computer architectures support low-precision arithmetic, which present opportunities for the adoption of mixed-precision algorithms to achieve high computational throughput and reduce energy consumption. As a growing number of scientific computations leverage specialized hardware accelerators, the risk of rounding errors increases, potentially compromising the reliability of models. This shift towards hardware-optimized, low-precision computations highlights the importance of rounding error analysis to ensure that performance gains do not come at the expense of accuracy, especially in high-stakes scientific applications. In this work, we conduct rounding error analysis on widely used operations such as fused multiply-add (FMA), mixed-precision FMA (MPFMA), and NVIDIA Tensor cores. We present a deterministic and probabilistic approach to quantifying the accumulated rounding errors. Numerical experiments are presented to perform the multiply and accumulate operation (MAC) and matrix-matrix multiplication using Tensor cores with random data. We show that probabilistic bounds produce tighter estimates by nearly an order of magnitude compared to deterministic ones for matrix-matrix multiplication.
format Preprint
id arxiv_https___arxiv_org_abs_2411_18747
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Deterministic and Probabilistic Rounding Error Analysis for Mixed-Precision Arithmetic on Modern Computing Units
Bhola, Sahil
Duraisamy, Karthik
Computation
Modern computer architectures support low-precision arithmetic, which present opportunities for the adoption of mixed-precision algorithms to achieve high computational throughput and reduce energy consumption. As a growing number of scientific computations leverage specialized hardware accelerators, the risk of rounding errors increases, potentially compromising the reliability of models. This shift towards hardware-optimized, low-precision computations highlights the importance of rounding error analysis to ensure that performance gains do not come at the expense of accuracy, especially in high-stakes scientific applications. In this work, we conduct rounding error analysis on widely used operations such as fused multiply-add (FMA), mixed-precision FMA (MPFMA), and NVIDIA Tensor cores. We present a deterministic and probabilistic approach to quantifying the accumulated rounding errors. Numerical experiments are presented to perform the multiply and accumulate operation (MAC) and matrix-matrix multiplication using Tensor cores with random data. We show that probabilistic bounds produce tighter estimates by nearly an order of magnitude compared to deterministic ones for matrix-matrix multiplication.
title Deterministic and Probabilistic Rounding Error Analysis for Mixed-Precision Arithmetic on Modern Computing Units
topic Computation
url https://arxiv.org/abs/2411.18747