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] [-c] [-i N] [-m]Option | Description |
|---|---|
-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) |
-m | --mask_interrupts | Optional. Enable interrupt masking. This flag clears the interrupt
enable flag in the core (using the x86 cli instruction), which masks hardware maskable interrupts. For more information about masking interrupts, see the Intel® 64 and IA-32 Architectures Software Developer’s Manual Volume 3A, Section 2.3, “SYSTEM FLAGS AND FIELDS IN THE EFLAGS REGISTER.” The interrupts are masked only for the duration of the pointer-chase task to avoid negative effects on overall system behavior. |
-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] [-c] [-i N] [-m]