The roofline model: A pedagogical tool for program analysis and optimization

Williams, Samuel; Patterson, David; Oliker, Leonid; Shalf, John; Yelick, Katherine

doi:10.1109/HOTCHIPS.2008.7476531

Title: The roofline model: A pedagogical tool for program analysis and optimization

Full Record
Other Related Research

Abstract

This article consists of a collection of slides from the authors' conference presentation. The Roofline model is a visually intuitive figure for kernel analysis and optimization. We believe undergraduates will find it useful in assessing performance and scalability limitations. It is easily extended to other architectural paradigms. It is easily extendable to other metrics: performance (sort, graphics, crypto..) bandwidth (L2, PCIe, ..). Furthermore, a performance counters could be used to generate a runtime-specific roofline that would greatly aide the optimization.

Authors:

Williams, Samuel ^[1]; Patterson, David ^[2]; Oliker, Leonid ^[1]; Shalf, John ^[3]; Yelick, Katherine ^[1]

Univ. of California, Berkeley, CA (United States); Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
Univ. of California, Berkeley, CA (United States)
Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)

Publication Date:: Fri Aug 01 00:00:00 EDT 2008

Research Org.:: Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)

Sponsoring Org.:: USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR)

OSTI Identifier:: 1379347

Grant/Contract Number:: AC02-05CH11231

Resource Type:: Accepted Manuscript

Journal Name:: IEEE Hot Chips Symposium

Additional Journal Information:: Journal Volume: 2008; Conference: Hot Chips 20 Symposium (HCS), Stanford, CA (United States), 24-26 Aug 2008; Journal ID: ISSN 2573-203X

Publisher:: IEEE

Country of Publication:: United States

Language:: English

Subject:: 97 MATHEMATICS AND COMPUTING

Citation Formats


                    Williams, Samuel, Patterson, David, Oliker, Leonid, Shalf, John, and Yelick, Katherine. The roofline model: A pedagogical tool for program analysis and optimization.  United States: N. p., 2008. 
Web.  doi:10.1109/HOTCHIPS.2008.7476531.

Copy to clipboard


                    Williams, Samuel, Patterson, David, Oliker, Leonid, Shalf, John, & Yelick, Katherine. The roofline model: A pedagogical tool for program analysis and optimization.  United States.  https://doi.org/10.1109/HOTCHIPS.2008.7476531

Copy to clipboard


                    Williams, Samuel, Patterson, David, Oliker, Leonid, Shalf, John, and Yelick, Katherine. Fri .  
"The roofline model: A pedagogical tool for program analysis and optimization".  United States.  https://doi.org/10.1109/HOTCHIPS.2008.7476531.  https://www.osti.gov/servlets/purl/1379347.

Copy to clipboard


                    
@article{osti_1379347,

  title        = {The roofline model: A pedagogical tool for program analysis and optimization},

  author       = {Williams, Samuel and Patterson, David and Oliker, Leonid and Shalf, John and Yelick, Katherine},

  abstractNote = {This article consists of a collection of slides from the authors' conference presentation. The Roofline model is a visually intuitive figure for kernel analysis and optimization. We believe undergraduates will find it useful in assessing performance and scalability limitations. It is easily extended to other architectural paradigms. It is easily extendable to other metrics: performance (sort, graphics, crypto..) bandwidth (L2, PCIe, ..). Furthermore, a performance counters could be used to generate a runtime-specific roofline that would greatly aide the optimization.},

  doi          = {10.1109/HOTCHIPS.2008.7476531},

  journal      = {IEEE Hot Chips Symposium},

  number       = ,

  volume       = 2008,

  place        = {United States},

  year         = {Fri Aug 01 00:00:00 EDT 2008},

  month        = {Fri Aug 01 00:00:00 EDT 2008}

}

Copy to clipboard

Journal Article:

Free Publicly Available Full Text

Accepted Manuscript (DOE)

Publisher's Version of Record

https://doi.org/10.1109/HOTCHIPS.2008.7476531

Other availability

Search WorldCat to find libraries that may hold this journal

Save / Share:

Export Metadata

Save to My Library

Similar Records in DOE PAGES and OSTI.GOV collections:

Hierarchical Roofline analysis for GPUs: Accelerating performance optimization for the NERSC‐9 Perlmutter system

Journal Article Yang, Charlene ; Kurth, Thorsten ; Williams, Samuel - Concurrency and Computation. Practice and Experience

Summary The Roofline performance model provides an intuitive and insightful approach to identifying performance bottlenecks and guiding performance optimization. In preparation for the next‐generation supercomputer Perlmutter at NERSC, this paper presents a methodology to construct a hierarchical Roofline on NVIDIA GPUs and extends it to support reduced precision and Tensor Cores. The hierarchical Roofline incorporates L1, L2, device memory, and system memory bandwidths into one single figure, and it offers more profound insights into performance analysis than the traditional DRAM‐only Roofline. We use our Roofline methodology to analyze three proxy applications: GPP from BerkeleyGW, HPGMG from AMReX, and conv2d frommore »« less
Cited by 29
https://doi.org/10.1002/cpe.5547
Roofline Analysis in the Intel® Advisor to Deliver Optimized Performance for applications on Intel® Xeon Phi™ Processor

Conference Koskela, Tuomas S. ; Lobet, Mathieu ; Deslippe, Jack ; ...

In this session we show, in two case studies, how the roofline feature of Intel Advisor has been utilized to optimize the performance of kernels of the XGC1 and PICSAR codes in preparation for Intel Knights Landing architecture. The impact of the implemented optimizations and the benefits of using the automatic roofline feature of Intel Advisor to study performance of large applications will be presented. This demonstrates an effective optimization strategy that has enabled these science applications to achieve up to 4.6 times speed-up and prepare for future exascale architectures. # Goal/Relevance of Session The roofline model [1,2] is amore »« less
Full Text Available
The Roofline Model

Book Williams, Samuel W.

The Roofline model is a visually intuitive performance model constructed using bound and bottleneck analysis. It is designed to drive programmers towards an intuitive understanding of performance on modern computer architectures. As such, it not only provides programmers with realistic performance expectations, but also enumerates the potential impediments to performance. Knowledge of these bottlenecks drives programmers to implement particular classes of optimizations. This chapter will focus on architecture-oriented roofline models as opposed to using performance counters to generate a roofline model.
https://doi.org/10.1201/b10509-10

Full Text Available
Roofline model toolkit: A practical tool for architectural and program analysis

Conference Lo, Yu Jung ; Williams, Samuel ; Van Straalen, Brian ; ...

We present preliminary results of the Roofline Toolkit for multicore, many core, and accelerated architectures. This paper focuses on the processor architecture characterization engine, a collection of portable instrumented micro benchmarks implemented with Message Passing Interface (MPI), and OpenMP used to express thread-level parallelism. These benchmarks are specialized to quantify the behavior of different architectural features. Compared to previous work on performance characterization, these microbenchmarks focus on capturing the performance of each level of the memory hierarchy, along with thread-level parallelism, instruction-level parallelism and explicit SIMD parallelism, measured in the context of the compilers and run-time environments. We also measuremore »« less
https://doi.org/10.1007/978-3-319-17248-4_7

Full Text Available
Data Locality Enhancement of Dynamic Simulations for Exascale Computing (Final Report)

Technical Report Shen, Xipeng

The development of modern processors exhibits two trends that complicate the optimizations of modern software. The first is the increasing sensitivity of processors' throughput to irregularities in computation. With more processors produced through a massive integration of simple cores, future systems will increasingly favor regular data-level parallel computations, but deviate from the needs of applications with complex patterns. Some evidences are already shown on Graphic Processing Units (GPU): Irregular data accesses (e.g., indirect references A[D[i]]) and conditional branches are limiting many GPU applications' performance at a level an order of magnitude lower than the peak of GPU. The second hardwaremore »« less
https://doi.org/10.2172/1576175

Full Text Available

Similar Records