FLOPs as a Discriminant for Dense Linear Algebra Algorithms

被引:0
|
作者
Lopez, Francisco [1 ]
Karlsson, Lars [1 ]
Bientinesi, Paolo [1 ]
机构
[1] Umea Univ, Umea, Sweden
关键词
linear algebra; algorithm selection; scientific computing; SET;
D O I
10.1145/3545008.3545072
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Expressions that involve matrices and vectors, known as linear algebra expressions, are commonly evaluated through a sequence of invocations to highly optimised kernels provided in libraries such as BLAS and LAPACK. A sequence of kernels represents an algorithm, and in general, because of associativity, algebraic identities, and multiple kernels, one expression can be evaluated via many different algorithms. These algorithms are all mathematically equivalent (i.e., in exact arithmetic, they all compute the same result), but often differ noticeably in terms of execution time. When faced with a decision, high-level languages, libraries, and tools such as Julia, Armadillo, and Linnea choose by selecting the algorithm that minimises the FLOP count. In this paper, we test the validity of the FLOP count as a discriminant for dense linear algebra algorithms, analysing "anomalies": problem instances for which the fastest algorithm does not perform the least number of FLOPs. To do so, we focused on relatively simple expressions and analysed when and why anomalies occurred. We found that anomalies exist and tend to cluster into large contiguous regions. For one expression anomalies were rare, whereas for the other they were abundant. We conclude that FLOPs is not a sufficiently dependable discriminant even when building algorithms with highly optimised kernels. Plus, most of the anomalies remained as such even after filtering out the inter-kernel cache effects. We conjecture that combining FLOP counts with kernel performance models will significantly improve our ability to choose optimal algorithms.
引用
收藏
页数:10
相关论文
共 50 条
  • [1] A Test for FLOPs as a Discriminant for Linear Algebra Algorithms
    Sankaran, Aravind
    Bientinesi, Paolo
    2022 IEEE 34TH INTERNATIONAL SYMPOSIUM ON COMPUTER ARCHITECTURE AND HIGH PERFORMANCE COMPUTING (SBAC-PAD 2022), 2022, : 221 - 230
  • [2] PARALLEL ALGORITHMS FOR DENSE LINEAR ALGEBRA COMPUTATIONS
    GALLIVAN, KA
    PLEMMONS, RJ
    SAMEH, AH
    SIAM REVIEW, 1990, 32 (01) : 54 - 135
  • [3] The science of deriving dense linear algebra algorithms
    Bientinesi, P
    Gunnels, JA
    Myers, ME
    Quintana-Orti, ES
    Van De Geijn, RA
    ACM TRANSACTIONS ON MATHEMATICAL SOFTWARE, 2005, 31 (01): : 1 - 26
  • [4] Design, Optimization, and Benchmarking of Dense Linear Algebra Algorithms on AMD GPUs
    Brown, Cade
    Abdelfattah, Ahmad
    Tomov, Stanimire
    Dongarra, Jack
    2020 IEEE HIGH PERFORMANCE EXTREME COMPUTING CONFERENCE (HPEC), 2020,
  • [5] IMPLEMENTING LINEAR ALGEBRA ALGORITHMS FOR DENSE MATRICES ON A VECTOR PIPELINE MACHINE
    DONGARRA, JJ
    GUSTAVSON, FG
    KARP, A
    SIAM REVIEW, 1984, 26 (01) : 91 - 112
  • [6] Performance and energy analysis of OpenMP runtime systems with dense linear algebra algorithms
    Ferreira Lima, Joao Vicente
    Rais, Issam
    Lefevre, Laurent
    Gautier, Thierry
    INTERNATIONAL JOURNAL OF HIGH PERFORMANCE COMPUTING APPLICATIONS, 2019, 33 (03): : 431 - 443
  • [7] Algorithm 979: Recursive Algorithms for Dense Linear Algebra-The ReLAPACK Collection
    Peise, Elmar
    Bientinesi, Paolo
    ACM TRANSACTIONS ON MATHEMATICAL SOFTWARE, 2017, 44 (02):
  • [8] Analysis of dynamically scheduled tile algorithms for dense linear algebra on multicore architectures
    Haidar, Azzam
    Ltaief, Hatem
    YarKhan, Asim
    Dongarra, Jack
    CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE, 2012, 24 (03): : 305 - 321
  • [9] IMPROVING PERFORMANCE OF LINEAR ALGEBRA ALGORITHMS FOR DENSE MATRICES, USING ALGORITHMIC PREFETCH
    AGARWAL, RC
    GUSTAVSON, FG
    ZUBAIR, M
    IBM JOURNAL OF RESEARCH AND DEVELOPMENT, 1994, 38 (03) : 265 - 275
  • [10] Novel data formats and algorithms for Dense Linear Algebra Computations: Minisymposium abstract
    Gustavson, Fred G.
    Wasniewski, Jerzy
    APPLIED PARALLEL COMPUTING: STATE OF THE ART IN SCIENTIFIC COMPUTING, 2007, 4699 : 520 - 520