Predicting Execution Time of CUDA Kernel Using Static Analysis
Authors:
- Gargi AlavaniGAGargi Alavani
- Kajal VarmaKVKajal Varma
- Santonu SarkarSSSantonu Sarkar
- 1 December 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 948-955
Abstract
With the growing demand for performance-oriented problems, programmers routinely execute the embarrassing parallel part of the application (GPU kernels) in a GPU in order to achieve signi?cant speedup. These applications are becoming complex and long-running which makes it energy inef?cient. Anticipating its execution time can help the developers to ?x the inef?cient code before running it. In this paper, we propose an approach to predict the execution time of a GPU kernel without the need of executing it. We build an analytical model to predict the execution time of a GPU kernel by analyzing the intermediate PTX code of a CUDA kernel. Our experimental analysis of a set of benchmarks shows that for 45 applications the estimated execution time has the mean absolute error of 26.86% when compared to the actual execution time. Mean absolute error for benchmarks belonging to Dynamic programming dwarf is minimum, followed by Dense Linear Algebra benchmarks.Keywords
This publication has 8 references indexed in Scilit:
- A quantitative roofline model for GPU kernel performance estimation using micro-benchmarks and hardware metric profilingJournal of Parallel and Distributed Computing, 2017
- A comparison of GPU execution time prediction using machine learning and analytical modeling2016
- A Simple BSP-based Model to Predict Execution Time in GPU Applications2015
- A Survey of Methods for Analyzing and Improving GPU Energy EfficiencyACM Computing Surveys, 2014
- A view of the parallel computing landscapeCommunications of the ACM, 2009
- Rodinia: A benchmark suite for heterogeneous computing2009
- An analytical model for a GPU architecture with memory-level and thread-level parallelism awareness2009
- Analyzing CUDA workloads using a detailed GPU simulator2009