An Automated Tool for Analysis and Tuning of GPU-Accelerated Code in HPC Applications
- 1 July 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Parallel and Distributed Systems
- Vol. 33 (4) , 854-865
Abstract
The US Department of Energy’s fastest supercomputers and forthcoming exascale systems employ Graphics Processing Units (GPUs) to increase the computational performance of compute nodes. However, the complexity of GPU architectures makes tailoring sophisticated applications to achieve high performance on GPU-accelerated systems a major challenge. At best, prior performance tools for GPU code only provide coarse-grained tuning advice at the kernel level. In this article, we describe GPA, a performance advisor that suggests potential code optimizations at a hierarchy of levels, including individual lines, loops, and functions. To gather the fine-grained measurements needed to produce such insights, GPA uses instruction sampling and binary instrumentation to monitor execution of GPU code. At the time of this writing, GPU instruction sampling is only available on NVIDIA GPUs. To understand performance losses, GPA uses data flow analysis to approximately attribute measured instruction stalls back to their causes. GPA then analyzes patterns of stalls using information about a program’s structure and the GPU architecture to identify optimization strategies that address inefficiencies observed. GPA then employs detailed performance models to estimate the potential speedup that each optimization might provide. Experiments with benchmarks and applications show that GPA provides useful advice for tuning GPU code. We applied GPA to analyze and tune a collection of codes on NVIDIA V100 and A100 GPUs. GPA suggested optimizations that it estimates will accelerate performance across the set of codes by a geometric mean of 1.21×. Applying these optimizations suggested by GPA accelerated these codes by a geometric mean of 1.19×.Keywords
Funding Information
- Exascale Computing (17-SC-20-SC)
- U.S. Department of Energy
- National Nuclear Security Administration
- Lawrence Livermore National Laboratory (B639429)
- ExxonMobil Graduate Fellowship
This publication has 19 references indexed in Scilit:
- Fast Computational GPU Design with GT-Pin2015
- Flexible software profiling of GPU architecturesACM SIGARCH Computer Architecture News, 2015
- CQA: A code quality analyzer tool at binary level2014
- BerkeleyGW: A massively parallel computer package for the calculation of the quasiparticle and optical properties of materials and nanostructuresComputer Physics Communications, 2012
- High-Order Curvilinear Finite Element Methods for Lagrangian HydrodynamicsSIAM Journal on Scientific Computing, 2012
- HPCTOOLKIT: tools for performance analysis of optimized parallel programsConcurrency and Computation: Practice and Experience, 2009
- The Tau Parallel Performance SystemThe International Journal of High Performance Computing Applications, 2006
- ProfileMe: hardware support for instruction-level profiling on out-of-order processors2002
- NAMD: Biomolecular Simulation on Thousands of Processors2002
- Intraprocedural static slicing of binary executables1997