PPT-GPU: Scalable GPU Performance Modeling

Arafa, Yehia; Badawy, Abdel Hameed A.; Chennupati, Gopinath; Santhi, Nandakishore; Eidenbenz, Stephan Johannes

doi:10.1109/LCA.2019.2904497

Title: PPT-GPU: Scalable GPU Performance Modeling

Full Record
Other Related Research

Abstract

Performance modeling is a challenging problem due to the complexities of hardware architectures. In this paper, we present PPT-GPU, a scalable and accurate simulation framework that enables GPU code developers and architects to predict the performance of applications in a fast, and accurate manner on different GPU architectures. PPT-GPU is part of the open source project, Performance Prediction Toolkit (PPT) developed at the Los Alamos National Laboratory. We extend the old GPU model in PPT that predict the runtimes of computational physics codes to offer better prediction accuracy, for which, we add models for different memory hierarchies found in GPUs and latencies for different instructions. To further show the utility of PPT-GPU, we compare our model against real GPU device(s) and the widely used cycle-accurate simulator, GPGPU-Sim using different workloads from RODINIA and Parboil benchmarks. The results indicate that the predicted performance of PPT-GPU is within a 10% error compared to the real device(s). In addition, PPT-GPU is highly scalable, where it is up to 450x faster than GPGPU-Sim with more accurate results.

Authors:

Arafa, Yehia ^[1]; Badawy, Abdel Hameed A. ^[1];

^[2];

^[2]

New Mexico State Univ., Las Cruces, NM (United States)
Los Alamos National Lab. (LANL), Los Alamos, NM (United States)

Publication Date:: Tue Jan 01 00:00:00 EST 2019

Research Org.:: Los Alamos National Lab. (LANL), Los Alamos, NM (United States)

Sponsoring Org.:: USDOE Laboratory Directed Research and Development (LDRD) Program; USDOE National Nuclear Security Administration (NNSA)

OSTI Identifier:: 1504654

Report Number(s):: LA-UR-18-30853
Journal ID: ISSN 1556-6056

Grant/Contract Number:: 89233218CNA000001; AC52-06NA25396

Resource Type:: Accepted Manuscript

Journal Name:: IEEE Computer Architecture Letters

Additional Journal Information:: Journal Volume: 18; Journal Issue: 1; Journal ID: ISSN 1556-6056

Publisher:: IEEE

Country of Publication:: United States

Language:: English

Subject:: 97 MATHEMATICS AND COMPUTING; Computer Hardware; Computer Science

Citation Formats


                    Arafa, Yehia, Badawy, Abdel Hameed A., Chennupati, Gopinath, Santhi, Nandakishore, and Eidenbenz, Stephan Johannes. PPT-GPU: Scalable GPU Performance Modeling.  United States: N. p., 2019. 
Web.  doi:10.1109/LCA.2019.2904497.

Copy to clipboard


                    Arafa, Yehia, Badawy, Abdel Hameed A., Chennupati, Gopinath, Santhi, Nandakishore, & Eidenbenz, Stephan Johannes. PPT-GPU: Scalable GPU Performance Modeling.  United States.  https://doi.org/10.1109/LCA.2019.2904497

Copy to clipboard


                    Arafa, Yehia, Badawy, Abdel Hameed A., Chennupati, Gopinath, Santhi, Nandakishore, and Eidenbenz, Stephan Johannes. Tue .  
"PPT-GPU: Scalable GPU Performance Modeling".  United States.  https://doi.org/10.1109/LCA.2019.2904497.  https://www.osti.gov/servlets/purl/1504654.

Copy to clipboard


                    
@article{osti_1504654,

  title        = {PPT-GPU: Scalable GPU Performance Modeling},

  author       = {Arafa, Yehia and Badawy, Abdel Hameed A. and Chennupati, Gopinath and Santhi, Nandakishore and Eidenbenz, Stephan Johannes},

  abstractNote = {Performance modeling is a challenging problem due to the complexities of hardware architectures. In this paper, we present PPT-GPU, a scalable and accurate simulation framework that enables GPU code developers and architects to predict the performance of applications in a fast, and accurate manner on different GPU architectures. PPT-GPU is part of the open source project, Performance Prediction Toolkit (PPT) developed at the Los Alamos National Laboratory. We extend the old GPU model in PPT that predict the runtimes of computational physics codes to offer better prediction accuracy, for which, we add models for different memory hierarchies found in GPUs and latencies for different instructions. To further show the utility of PPT-GPU, we compare our model against real GPU device(s) and the widely used cycle-accurate simulator, GPGPU-Sim using different workloads from RODINIA and Parboil benchmarks. The results indicate that the predicted performance of PPT-GPU is within a 10% error compared to the real device(s). In addition, PPT-GPU is highly scalable, where it is up to 450x faster than GPGPU-Sim with more accurate results.},

  doi          = {10.1109/LCA.2019.2904497},

  journal      = {IEEE Computer Architecture Letters},

  number       = 1,

  volume       = 18,

  place        = {United States},

  year         = {Tue Jan 01 00:00:00 EST 2019},

  month        = {Tue Jan 01 00:00:00 EST 2019}

}

Copy to clipboard

Journal Article:

Free Publicly Available Full Text

Accepted Manuscript (DOE)

Publisher's Version of Record

https://doi.org/10.1109/LCA.2019.2904497

Other availability

Search WorldCat to find libraries that may hold this journal

Citation Metrics:

Cited by: 22 works

Citation information provided by
Web of Science

Save / Share:

Export Metadata

Save to My Library

Similar Records in DOE PAGES and OSTI.GOV collections:

A performance model for GPUs with caches

Journal Article Dao, Thanh Tuan ; Kim, Jungwon ; Seo, Sangmin ; ... - IEEE Transactions on Parallel and Distributed Systems

To exploit the abundant computational power of the world's fastest supercomputers, an even workload distribution to the typically heterogeneous compute devices is necessary. While relatively accurate performance models exist for conventional CPUs, accurate performance estimation models for modern GPUs do not exist. This paper presents two accurate models for modern GPUs: a sampling-based linear model, and a model based on machine-learning (ML) techniques which improves the accuracy of the linear model and is applicable to modern GPUs with and without caches. We first construct the sampling-based linear model to predict the runtime of an arbitrary OpenCL kernel. Based on anmore »« less
Cited by 25
https://doi.org/10.1109/TPDS.2014.2333526

Full Text Available
Scalable molecular dynamics on CPU and GPU architectures with NAMD

Journal Article Phillips, James C ; Hardy, David J ; Maia, Julio D.C. ; ... - Journal of Chemical Physics

NAMD is a molecular dynamics program designed for high-performance simulations of very large biological objects on CPU- and GPU-based architectures. NAMD offers scalable performance on petascale parallel supercomputers consisting of hundreds of thousands of cores, as well as on inexpensive commodity clusters commonly found in academic environments. It is written in C++ and leans on Charm++ parallel objects for optimal performance on low-latency architectures. NAMD is a versatile, multipurpose code that gathers state-of-the-art algorithms to carry out simulations in apt thermodynamic ensembles, using the widely popular CHARMM, AMBER, OPLS, and GROMOS biomolecular force fields. Here, we review the main featuresmore »« less
https://doi.org/10.1063/5.0014475
Machine Learning-enabled Scalable Performance Prediction of Scientific Codes

Journal Article Chennupati, Gopinath ; Santhi, Nandakishore ; Romero, Phillip R. ; ... - ACM Transactions on Modeling and Computer Simulation

Hardware architectures become increasingly complex as the compute capabilities grow to exascale. Here, we present the Analytical Memory Model with Pipelines (AMMP) of the Performance Prediction Toolkit (PPT). PPT-AMMP takes high-level source code and hardware architecture parameters as input and predicts runtime of that code on the target hardware platform, which is defined in the input parameters. PPT-AMMP transforms the code to an (architecture-independent) intermediate representation, then (i) analyzes the basic block structure of the code, (ii) processes architecture-independent virtual memory access patterns that it uses to build memory reuse distance distribution models for each basic block, and (iii) runsmore »« less
https://doi.org/10.1145/3450264

Full Text Available
Scalable Deep Learning-Based Microarchitecture Simulation on GPUs

Conference Li, Lingda ; Pandey, Santosh ; Li, L ; ...

Cycle-accurate microarchitecture simulators are essential tools for designers to architect, estimate, optimize, and manufacture new processors that meet specific design expectations. However, conventional simulators based on discrete-event methods often require an exceedingly long time-to-solution for the simulation of applications and architectures at full complexity and scale. Given the excitement around wielding the machine learning (ML) hammer to tackle various architecture problems, there have been attempts to employ ML to perform architecture simulations, such as Ithemal and SimNet. However, the direct application of existing ML approaches to architecture simulation may be even slower due to overwhelming memory traffic and stringent sequentialmore »« less
https://doi.org/10.1109/SC41404.2022.00084

Full Text Available
Fast and Scalable Sparse Triangular Solver for Multi-GPU Based HPC Architectures

Conference Xie, Chenhao ; Chen, Jieyang ; Firoz, Jesun S. ; ...

Designing efficient and scalable sparse linear algebra kernels on modern multi-GPU based HPC systems is a daunting task due to significant irregular memory references and workload imbalance across the GPUs. This is particularly the case for \textit{Sparse Triangular Solver (SpTRSV)} which introduces additional two-dimensional computation dependencies among subsequent computation steps. Dependency information is exchanged and shared among GPUs, thus warrant for efficient memory allocation, data partitioning, and workload distribution as well as fine-grained communication and synchronization support. In this work, we demonstrate that directly adopting unified memory can adversely affect the performance of SpTRSV on multi-GPU architectures, despite linking viamore »« less
https://doi.org/10.1145/3472456.3472478

Similar Records