NeuroScalar: A Deep Learning Framework for Fast, Accurate, and In-the-Wild Cycle-Level Performance Prediction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wadle, Shayne, Zhang, Yanxin, Singh, Vikas, Sankaralingam, Karthikeyan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916978917113856
author Wadle, Shayne
Zhang, Yanxin
Singh, Vikas
Sankaralingam, Karthikeyan
author_facet Wadle, Shayne
Zhang, Yanxin
Singh, Vikas
Sankaralingam, Karthikeyan
contents The evaluation of new microprocessor designs is constrained by slow, cycle-accurate simulators that rely on unrepresentative benchmark traces. This paper introduces a novel deep learning framework for high-fidelity, ``in-the-wild'' simulation on production hardware. Our core contribution is a DL model trained on microarchitecture-independent features to predict cycle-level performance for hypothetical processor designs. This unique approach allows the model to be deployed on existing silicon to evaluate future hardware. We propose a complete system featuring a lightweight hardware trace collector and a principled sampling strategy to minimize user impact. This system achieves a simulation speed of 5 MIPS on a commodity GPU, imposing a mere 0.1% performance overhead. Furthermore, our co-designed Neutrino on-chip accelerator improves performance by 85x over the GPU. We demonstrate that this framework enables accurate performance analysis and large-scale hardware A/B testing on a massive scale using real-world applications.
format Preprint
id arxiv_https___arxiv_org_abs_2509_22410
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle NeuroScalar: A Deep Learning Framework for Fast, Accurate, and In-the-Wild Cycle-Level Performance Prediction
Wadle, Shayne
Zhang, Yanxin
Singh, Vikas
Sankaralingam, Karthikeyan
Hardware Architecture
Machine Learning
The evaluation of new microprocessor designs is constrained by slow, cycle-accurate simulators that rely on unrepresentative benchmark traces. This paper introduces a novel deep learning framework for high-fidelity, ``in-the-wild'' simulation on production hardware. Our core contribution is a DL model trained on microarchitecture-independent features to predict cycle-level performance for hypothetical processor designs. This unique approach allows the model to be deployed on existing silicon to evaluate future hardware. We propose a complete system featuring a lightweight hardware trace collector and a principled sampling strategy to minimize user impact. This system achieves a simulation speed of 5 MIPS on a commodity GPU, imposing a mere 0.1% performance overhead. Furthermore, our co-designed Neutrino on-chip accelerator improves performance by 85x over the GPU. We demonstrate that this framework enables accurate performance analysis and large-scale hardware A/B testing on a massive scale using real-world applications.
title NeuroScalar: A Deep Learning Framework for Fast, Accurate, and In-the-Wild Cycle-Level Performance Prediction
topic Hardware Architecture
Machine Learning
url https://arxiv.org/abs/2509.22410