Efficient architectural design space exploration via predictive modeling
Authors:
Open Access
- 30 January 2008
- journal article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Architecture and Code Optimization
- Vol. 4 (4) , 1-34
Abstract
Efficiently exploring exponential-size architectural design spaces with many interacting parameters remains an open problem: the sheer number of experiments required renders detailed simulation intractable. We attack this via an automated approach that builds accurate predictive models. We simulate sampled points, using results to teach our models the function describing relationships among design parameters. The models can be queried and are very fast, enabling efficient design tradeoff discovery. We validate our approach via two uniprocessor sensitivity studies, predicting IPC with only 1--2% error. In an experimental study using the approach, training on 1% of a 250-K-point CMP design space allows our models to predict performance with only 4--5% error. Our predictive modeling combines well with techniques that reduce the time taken by each simulation experiment, achieving net time savings of three-four orders of magnitude.Keywords
This publication has 31 references indexed in Scilit:
- A Predictive Performance Model for Superscalar Processors40th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO 2007), 2006
- Efficiently exploring architectural design spaces via predictive modeling2006
- An Approach to Performance Prediction for Parallel ApplicationsLecture Notes in Computer Science, 2005
- BLRL: Accurate and Efficient Warmup for Sampled Processor SimulationThe Computer Journal, 2005
- Maximizing CMP throughput with mediocre cores2005
- Interaction cost and shotgun profilingACM Transactions on Architecture and Code Optimization, 2004
- Statistical simulation: Adding efficiency to the computer designer's toolboxIEEE Micro, 2003
- A case for studying DRAM issues at the system levelIEEE Micro, 2003
- Applying neural networks to computer system performance tuning2002
- The Elements of Statistical Learning2001