Name
Abstract | ||
|---|---|---|
This paper introduces a predictive modeling framework to estimate the performance of GPUs during pre-silicon design. Early-stage performance prediction is useful when simulation times impede development by rendering driver performance validation, API conformance testing and design space explorations infeasible. Our approach builds a Random Forest regression model to analyze DirectX 3D workload behavior when executed by a software rasterizer, which we have extended with a workload characterizer to collect further performance information via program counters. In addition to regression models, this work produces detailed feature rankings which can provide valuable architectural insight, and accurate performance estimates for an Intel integrated Skylake generation GPU. Our models achieve reasonable out-of-sample-error rates of 14%, with an average simulation speedup of 327x.
|
Year | DOI | Venue |
|---|---|---|
2017 | 10.1145/3126557 | ACM Trans. Embedded Comput. Syst. |
Keywords | Field | DocType |
GPU simulation, predictive model, random forest regression | Computer science,Workload,Conformance testing,DirectX,Real-time computing,Software,Random forest,Rendering (computer graphics),Performance prediction,Speedup | Journal |
Volume | Issue | ISSN |
16 | 5 | 1539-9087 |
Citations | PageRank | References |
0 | 0.34 | 15 |
Authors | ||
5 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Kenneth O'Neal | 1 | 13 | 2.58 |
| Philip Brisk | 2 | 80 | 10.05 |
| Ahmed Abousamra | 3 | 55 | 4.46 |
| Zack Waters | 4 | 0 | 0.34 |
| Emily Shriver | 5 | 5 | 2.69 |