PMEvo: Portable Inference of Port Mappings for Out-of-Order Processors by Evolutionary Optimization

被引:4
|
作者
Ritter, Fabian [1 ]
Hack, Sebastian [1 ]
机构
[1] Saarland Univ, Saarland Informat Campus, Saarbrucken, Germany
关键词
port mapping; evolutionary algorithm; processor reverse engineering;
D O I
10.1145/3385412.3385995
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
Achieving peak performance in a computer system requires optimizations in every layer of the system, be it hardware or software. A detailed understanding of the underlying hardware, and especially the processor, is crucial to optimize software. One key criterion for the performance of a processor is its ability to exploit instruction-level parallelism. This ability is determined by the port mapping of the processor, which describes the execution units of the processor for each instruction. Processor manufacturers usually do not share the port mappings of their microarchitectures. While approaches to automatically infer port mappings from experiments exist, they are based on processor-specific hardware performance counters that are not available on every platform. We present PMEvo, a framework to automatically infer port mappings solely based on the measurement of the execution time of short instruction sequences. PMEvo uses an evolutionary algorithm that evaluates the fitness of candidate mappings with an analytical throughput model formulated as a linear program. Our prototype implementation infers a port mapping for Intel's Skylake architecture that predicts measured instruction throughput with an accuracy that is competitive to existing work. Furthermore, it finds port mappings for AMD's Zen+ architecture and the ARM Cortex-A72 architecture, which are out of scope of existing techniques.
引用
收藏
页码:608 / 622
页数:15
相关论文
共 50 条
  • [1] Out-of-order commit processors
    Cristal, A
    Ortega, D
    Llosa, J
    Valero, M
    [J]. 10TH INTERNATIONAL SYMPOSIUM ON HIGH PERFORMANCE COMPUTER ARCHITECTURE, PROCEEDINGS, 2004, : 48 - 59
  • [2] Modeling out-of-order processors for WCET analysis
    Li, Xianfeng
    Roychoudhury, Abhik
    Mitra, Tulika
    [J]. REAL-TIME SYSTEMS, 2006, 34 (03) : 195 - 227
  • [3] Direct instruction wakeup for out-of-order processors
    Ramírez, MA
    Cristal, A
    Veidenbaum, AV
    Villa, L
    Valero, M
    [J]. INNOVATIVE ARCHITECTURE FOR FUTURE GENERATION HIGH-PERFORMANCE PROCESSORS AND SYSTEMS, PROCEEDINGS, 2004, : 2 - 9
  • [4] INTERRUPT HANDLING FOR OUT-OF-ORDER EXECUTION PROCESSORS
    TORNG, HC
    DAY, M
    [J]. IEEE TRANSACTIONS ON COMPUTERS, 1993, 42 (01) : 122 - 127
  • [5] Unrolling shape for out-of-order processors.
    Sato, H
    [J]. INNOVATIVE ARCHITECTURE FOR FUTURE GENERATION HIGH-PERFORMANCE PROCESSORS AND SYSTEMS, 2003, : 88 - 97
  • [6] Modeling out-of-order processors for WCET analysis
    Xianfeng Li
    Abhik Roychoudhury
    Tulika Mitra
    [J]. Real-Time Systems, 2006, 34 : 195 - 227
  • [7] A Novel Register Renaming Technique for Out-of-Order Processors
    Tabani, Hamid
    Arnau, Jose-Maria
    Tubella, Jordi
    Gonzalez, Antonio
    [J]. 2018 24TH IEEE INTERNATIONAL SYMPOSIUM ON HIGH PERFORMANCE COMPUTER ARCHITECTURE (HPCA), 2018, : 259 - 270
  • [8] Modeling out-of-order processors for software timing analysis
    Li, XF
    Roychoudhury, A
    Mitra, T
    [J]. 25TH IEEE INTERNATIONAL REAL-TIME SYSTEMS SYMPOSIUM, PROCEEDINGS, 2004, : 92 - 103
  • [9] A Mechanistic Performance Model for Superscalar Out-of-Order Processors
    Eyerman, Stijn
    Eeckhout, Lieven
    Karkhanis, Tejas
    Smith, James E.
    [J]. ACM TRANSACTIONS ON COMPUTER SYSTEMS, 2009, 27 (02):
  • [10] Dynamic MIPS Rate Stabilization in Out-of-Order Processors
    Suh, Jinho
    Dubois, Michel
    [J]. ISCA 2009: 36TH ANNUAL INTERNATIONAL SYMPOSIUM ON COMPUTER ARCHITECTURE, 2009, : 46 - 56