Developer Guide

  • 2021.3
  • 11/18/2021
  • Public
Contents

Command-Line Options

Running the cache allocation sample with the
-h
option yields the following usage message:
Usage: tcc_cache_allocation_sample -l N [--sleep N | --stress | --nostress] [-p N] [-c] [-i N]
Option
Description
-p | --cpuid N
Specify the requested core. Default: 3.
-l | --latency N
Required. Specify the maximum tolerable latency for a single cache line access in N nanoseconds.
--sleep N |--stress |--nostress
Optional. Select one of these options:
--sleep N
Period between iterations in N nanoseconds. Select this option when you want to run your own noisy neighbor.
--stress
Run the sample’s provided noisy neighbor on core 3 (default).
--nostress
Do not run the sample’s provided noisy neighbor and run workload iterations continuously without sleep in between.
-c | --collect
Optional. Enable measurement result collection if INTEL_LIBITTNOTIFY64 was not set via environment.
-i | --iterations N
Optional. Execute N iterations of the main loop to gather more precise timing statistics. (default: 100)
-h | --help
Optional. Print command-line help.
An alternative to
-c | --collect
is to use the
INTEL_LIBITTNOTIFY64
environment variable to set the collector library.
Usage: INTEL_LIBITTNOTIFY64=libtcc_collector.so tcc_cache_allocation_sample -l N [--sleep N | --stress | --nostress] [-p N] [-c] [-i N]

Product and Performance Information

1

Performance varies by use, configuration and other factors. Learn more at www.Intel.com/PerformanceIndex.