# Predicting the Performance of a Computing System with Deep Networks

## TL;DR

This paper explores using deep learning models to accurately predict hardware benchmark scores, addressing limitations of traditional benchmarking methods for hardware performance and energy consumption estimation.

## Contribution

It demonstrates the effectiveness of deep neural networks, including CNNs and ResNet-inspired models, in predicting SPEC 2017 benchmark scores for unseen hardware.

## Key findings

- Deep learning models achieve high R^2 scores (0.94-0.98) in predicting benchmark results.
- CNN-based models outperform fully-connected networks in accuracy.
- The approach enables performance prediction without extensive hardware benchmarking.

## Abstract

Predicting the performance and energy consumption of computing hardware is critical for many modern applications. This will inform procurement decisions, deployment decisions, and autonomic scaling. Existing approaches to understanding the performance of hardware largely focus around benchmarking -- leveraging standardised workloads which seek to be representative of an end-user's needs. Two key challenges are present; benchmark workloads may not be representative of an end-user's workload, and benchmark scores are not easily obtained for all hardware. Within this paper, we demonstrate the potential to build Deep Learning models to predict benchmark scores for unseen hardware. We undertake our evaluation with the openly available SPEC 2017 benchmark results. We evaluate three different networks, one fully-connected network along with two Convolutional Neural Networks (one bespoke and one ResNet inspired) and demonstrate impressive $R^2$ scores of 0.96, 0.98 and 0.94 respectively.