User Guide

Contents

Disable Stacks Collection

To minimize collection overhead, you can disable collecting data distribution over stacks with the
--no-stacks
option, with the potential tradeoff of modeling accuracy. You have two ways to use the
--no-stacks
option:
  • Disable collecting data distribution over stacks
    . Run
    run_oa.py
    ,
    collect.py
    , or
    advixe-cl
    (with
    --collect=tripcounts
    ) with the
    --no-stacks
    option to minimize collection overhead. This may reduce modeling accuracy.
    If you collect data with
    collect.py
    or
    advixe-cl
    , you do not need to use this options with
    analyze.py
    , as it will be used automatically because the collection will not include callstack-attributed data.
  • Run data analysis without callstacks data
    . If you collected callstack-attributed data with
    collect.py
    or
    advixe-cl
    (with
    --collect=tripcounts
    ), but callstack attribution went wrong, disable using callstacks data for analysis with
    analyze.py
    to avoid using the wrong data. This is a possible fallback when data with stacks is broken.
    This reduces modeling accuracy.

Product and Performance Information

1

Intel's compilers may or may not optimize to the same degree for non-Intel microprocessors for optimizations that are not unique to Intel microprocessors. These optimizations include SSE2, SSE3, and SSSE3 instruction sets and other optimizations. Intel does not guarantee the availability, functionality, or effectiveness of any optimization on microprocessors not manufactured by Intel. Microprocessor-dependent optimizations in this product are intended for use with Intel microprocessors. Certain optimizations not specific to Intel microarchitecture are reserved for Intel microprocessors. Please refer to the applicable product User and Reference Guides for more information regarding the specific instruction sets covered by this notice.

Notice revision #20110804