Developer Guide

  • 2021.2
  • 06/11/2021
  • Public
Contents

Launch the Cache Configurator

When you launch the cache configurator, it reads the current cache configuration and displays it on the console.
The following steps assume a host-target setup.
To launch the cache configurator:
  1. From your host system, connect to the target system:
    ssh <user>@<target>
  2. In the SSH session
    , disable the real-time configuration manager (RTCM) before using the cache configurator. You can disable RTCM with the following commands:
    For systems running the PR1 release of the Yocto Project*-based BSP for Intel Atom® x6000E Series processors, run:
    /usr/share/tcc_tools/scripts/setup_ssram_v1/control_rtcm.sh disable reboot
    For other systems, run:
    /usr/share/tcc_tools/scripts/setup_ssram/control_rtcm.sh disable reboot
  3. On the host system
    , source the environment file to set up environment variables:
    source ~/intel/oneapi/setvars.sh
  4. Go to the
    tools
    directory:
    cd ${TCC_TOOLS_PATH}
  5. If you have not done so, modify the sample environment file to enable the host to connect to the target system via SSH when running the cache configurator. This command example uses nano, but you can use any text editor.
    nano demo/environment/sample_environment_uefi.json
    Modify the following fields:
    Field Name
    Description
    “hostname”
    Replace
    ...
    with the IP address or hostname of the target system.
    “username”
    Replace
    ...
    with
    root
    for customer reference boards.
    The field should look like this:
    "username": "root"
    This field contains the username to connect to the target system via SSH.
    “password”
    Replace
    ...
    with the password to connect to the target system via SSH.
    If the SSH connection does not need a password or if you have created an SSH key and installed an SSH key on the target system, leave the password field empty as shown below:
    "password": ""
    All other fields
    Leave all other fields as is. These fields enable you to further customize the behavior of the tool.
  6. Save and close the file.
  7. Run the tool, where
    --environment
    is the path to your environment file.
    Note:
    If you decide to copy the environment file to another location on your host system, be sure to change the relative paths in the environment file or replace them with full paths.
    ./tcc_cache_configurator.py --environment ./demo/environment/sample_environment_uefi.json
First, the tool displays the current software SRAM allocation. On the tool’s first execution, you may see an already allocated software SRAM. This is because the
tcc_setup_ssram.sh
script executed in the Get Started Guide applies a preset configuration. The configuration may vary by platform.
In the following example, the system has one software SRAM buffer. The maximum access latency of the buffer is 159 nanoseconds, the buffer is in L3 cache, the buffer is available to applications running on CPU cores 0, 1, 2 and 3, and the buffer size is 1,048,576 bytes.
You can choose to add a buffer, delete a buffer, or change the way the cache is partitioned among caching agents.
Checking the platform's current real-time configuration for maximum tolerable buffer access latency, buffer size, etc. For more information on these parameters see the Intel® TCC Tools Developer Guide At any time, you can press (Ctrl + C) to exit the application or press (U) to cancel current operation and return to the main screen Connected. ******************************************************************************** Here is an initial configuration you currently have on the system CURRENT BUFFERS ALLOCATED: 1 BUFFER 0 LATENCY(ns): 159 CACHE LEVEL: 3 CPU CORE: [0, 1, 2, 3] BUFFER SIZE(bytes): 1048576 Would you like to add (A) or delete (D) a cache allocation? Or would you like to change the way the configuration is partitioned? (P)
Intel recommends starting with Select a Cache Partitioning Preset.

Product and Performance Information

1

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