Instruction Roofline: An insightful visual performance model for GPUs
- 1 September 2021
- journal article
- research article
- Published by Wiley in Concurrency and Computation: Practice and Experience
- Vol. 34 (20) , e6591
Abstract
The Roofline performance model provides an intuitive approach to identify performance bottlenecks and guide performance optimization. However, the classic FLOP‐centric approach is inappropriate for the emerging applications that perform more integer operations than floating point operations. In this article, we reintroduce our Instruction Roofline Model on NVIDIA GPUs and expand our evaluation of it. The Instruction Roofline incorporates instructions and memory transactions across all memory hierarchies together, and provides more performance insights than the FLOP‐oriented Roofline Model, that is, instruction throughput, stride memory access patterns, bank conflicts, and thread predication. We use our Instruction Roofline methodology to analyze eight proxy applications: HPGMG from AMReX, Matrix Transpose benchmarks, ADEPT from MetaHipMer's sequence alignment phase, EXTENSION from MetaHipMer's local assembly phase, CUSP, cuSPARSE, cudaTensorCoreGemm, and cuBLAS. We demonstrate the ability of our methodology to understand various aspects of performance and performance bottlenecks on NVIDIA GPUs and motivate code optimizations.Keywords
This publication has 9 references indexed in Scilit:
- ADEPT: a domain independent sequence alignment strategy for gpu architecturesBMC Bioinformatics, 2020
- Terabase-scale metagenome coassembly with MetaHipMerScientific Reports, 2020
- An Instruction Roofline Model for GPUs2019
- A Novel Multi-level Integrated Roofline Model Approach for Performance Characterization2018
- Applying the Roofline Performance Model to the Intel Xeon Phi Knights Landing Processor2016
- merAligner: A Fully Parallel Sequence Aligner2015
- SSW Library: An SIMD Smith-Waterman C/C++ Library for Use in Genomic ApplicationsPLOS ONE, 2013
- Cache-aware Roofline model: Upgrading the loftIEEE Computer Architecture Letters, 2013
- RooflineCommunications of the ACM, 2009