Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Flush cache #246

Draft
wants to merge 30 commits into
base: master
Choose a base branch
from
Draft

Flush cache #246

wants to merge 30 commits into from

Commits on Feb 8, 2024

  1. Added RegisterObserver with common interface among backends

    @fjwillemsen
    fjwillemsen committed Feb 8, 2024
    Configuration menu
    Copy the full SHA
    81a68a4 View commit details
    Browse the repository at this point in the history

  2. Added test for RegisterObserver, added clause in case of mocktest

    @fjwillemsen
    fjwillemsen committed Feb 8, 2024
    Configuration menu
    Copy the full SHA
    943b3c4 View commit details
    Browse the repository at this point in the history

Commits on Feb 9, 2024

  1. Added useful error message in case Register Observer is not supported

    @fjwillemsen
    fjwillemsen committed Feb 9, 2024
    Configuration menu
    Copy the full SHA
    1681730 View commit details
    Browse the repository at this point in the history

  2. Added tests for Register Observer for OpenCL and HIP backends

    @fjwillemsen
    fjwillemsen committed Feb 9, 2024
    Configuration menu
    Copy the full SHA
    f153945 View commit details
    Browse the repository at this point in the history

Commits on Feb 12, 2024

  1. Added instruction for pointing cache directory elsewhere

    @fjwillemsen
    fjwillemsen committed Feb 12, 2024
    Configuration menu
    Copy the full SHA
    7bd7c2b View commit details
    Browse the repository at this point in the history

  2. Non-argument streams are now correctly passed in the CuPy and NVCUDA … 

    …backends
    @fjwillemsen
    fjwillemsen committed Feb 12, 2024
    Configuration menu
    Copy the full SHA
    9dea137 View commit details
    Browse the repository at this point in the history

Commits on Feb 15, 2024

  1. Fixed several issues pertaining to the setting of clocks, in particul… 

    …ar one where the memory clock would always be seen as not-equal due to a rounding error
    @fjwillemsen
    fjwillemsen committed Feb 15, 2024
    Configuration menu
    Copy the full SHA
    df54145 View commit details
    Browse the repository at this point in the history

  2. Time spent setting NVML parameters (clock & memory frequency, power) … 

    …goes to framework time instead of benchmark time
    @fjwillemsen
    fjwillemsen committed Feb 15, 2024
    Configuration menu
    Copy the full SHA
    4cc4a13 View commit details
    Browse the repository at this point in the history

  3. Time spent setting NVML parameters (clock & memory frequency, power) … 

    …goes to framework time instead of benchmark time
    @fjwillemsen
    fjwillemsen committed Feb 15, 2024
    Configuration menu
    Copy the full SHA
    e309bc1 View commit details
    Browse the repository at this point in the history

  4. Removed redundant print statement

    @fjwillemsen
    fjwillemsen authored Feb 15, 2024
    Configuration menu
    Copy the full SHA
    d6aac8b View commit details
    Browse the repository at this point in the history

Commits on Feb 28, 2024

  1. Added L2 cache size property to CUDA backends

    @fjwillemsen
    fjwillemsen committed Feb 28, 2024
    Configuration menu
    Copy the full SHA
    a020791 View commit details
    Browse the repository at this point in the history

  2. Added specification to CUPY compiler options

    @fjwillemsen
    fjwillemsen committed Feb 28, 2024
    Configuration menu
    Copy the full SHA
    6e6e5fb View commit details
    Browse the repository at this point in the history

  3. Added L2 cache size property to OpenCL, HIP and mocked PyCUDA backends

    @fjwillemsen
    fjwillemsen committed Feb 28, 2024
    Configuration menu
    Copy the full SHA
    f15338f View commit details
    Browse the repository at this point in the history

  4. Added function to check for compute capability validity, improved che… 

    …ck on gpu-architecture compiler option, added gpu-architecture auto-adding to CuPy
    @fjwillemsen
    fjwillemsen committed Feb 28, 2024
    Configuration menu
    Copy the full SHA
    00ac419 View commit details
    Browse the repository at this point in the history

  5. Added a flush kernel to clear the L2 cache between runs

    @fjwillemsen
    fjwillemsen committed Feb 28, 2024
    Configuration menu
    Copy the full SHA
    55ab074 View commit details
    Browse the repository at this point in the history

  6. Added a flush kernel to clear the L2 cache between runs

    @fjwillemsen
    fjwillemsen committed Feb 28, 2024
    Configuration menu
    Copy the full SHA
    e106bae View commit details
    Browse the repository at this point in the history

Commits on Feb 29, 2024

  1. Made function for scaling the compute capability to a valid one, adde… 

    …d tests for this function, removed setting --gpu-architecture for CuPy as it is already set internally
    @fjwillemsen
    fjwillemsen committed Feb 29, 2024
    Configuration menu
    Copy the full SHA
    0cb5e3a View commit details
    Browse the repository at this point in the history

Commits on Mar 1, 2024

  1. Applied suggestions from comments by @csbnw

    @fjwillemsen
    fjwillemsen committed Mar 1, 2024
    2 Configuration menu
    Copy the full SHA
    b682506 View commit details
    Browse the repository at this point in the history

  2. Removed redundant comments / printing

    @fjwillemsen
    fjwillemsen committed Mar 1, 2024
    Configuration menu
    Copy the full SHA
    da907b1 View commit details
    Browse the repository at this point in the history

  3. Added L2 cache size information to backends

    @fjwillemsen
    fjwillemsen committed Mar 1, 2024
    Configuration menu
    Copy the full SHA
    2396bdf View commit details
    Browse the repository at this point in the history

  4. Added L2 flush kernel

    @fjwillemsen
    fjwillemsen committed Mar 1, 2024
    Configuration menu
    Copy the full SHA
    eced775 View commit details
    Browse the repository at this point in the history

  5. Switched to new attempt for flushing L2 using memset

    @fjwillemsen
    fjwillemsen committed Mar 1, 2024
    Configuration menu
    Copy the full SHA
    143889f View commit details
    Browse the repository at this point in the history

  6. Added implementation of allocate numpy array function

    @fjwillemsen
    fjwillemsen committed Mar 1, 2024
    Configuration menu
    Copy the full SHA
    651eea7 View commit details
    Browse the repository at this point in the history

Commits on Mar 2, 2024

  1. Added new flush L2 cache method using memset

    @fjwillemsen
    fjwillemsen committed Mar 2, 2024
    Configuration menu
    Copy the full SHA
    7d8d48f View commit details
    Browse the repository at this point in the history

Commits on Mar 4, 2024

  1. Added a standard method for freeing memory from the GPU

    @fjwillemsen
    fjwillemsen committed Mar 4, 2024
    Configuration menu
    Copy the full SHA
    9911f4c View commit details
    Browse the repository at this point in the history

  2. Circumvented an issue where list.remove(val) was not properly impleme… 

    …nted by CuPy, and attempt free of previous allocation after checking if flush is possible
    @fjwillemsen
    fjwillemsen committed Mar 4, 2024
    Configuration menu
    Copy the full SHA
    47c2cca View commit details
    Browse the repository at this point in the history

Commits on Mar 7, 2024

  1. Added the ability to recopy array arguments with every kernel launch,… 

    … added interfacing for flushing L2 and recopying arguments
    @fjwillemsen
    fjwillemsen committed Mar 7, 2024
    Configuration menu
    Copy the full SHA
    157ca41 View commit details
    Browse the repository at this point in the history

  2. Renamed to for clarity, added check

    @fjwillemsen
    fjwillemsen committed Mar 7, 2024
    Configuration menu
    Copy the full SHA
    98afa60 View commit details
    Browse the repository at this point in the history

Commits on Apr 12, 2024

  1. Improved getting L2 cache size

    @fjwillemsen
    fjwillemsen committed Apr 12, 2024
    Configuration menu
    Copy the full SHA
    cfecdc5 View commit details
    Browse the repository at this point in the history

  2. Small improvements to flushing arrays

    @fjwillemsen
    fjwillemsen committed Apr 12, 2024
    Configuration menu
    Copy the full SHA
    108e14c View commit details
    Browse the repository at this point in the history