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

Cleanup CUDA, Reuse Memory, Add Serial Model, Cleaup Std Parallelism #202

Open
wants to merge 14 commits into
base: develop
Choose a base branch
from
Open

Cleanup CUDA, Reuse Memory, Add Serial Model, Cleaup Std Parallelism #202

wants to merge 14 commits into from

Commits on May 27, 2024

  1. Refactor CUDA memory allocation

    @gonzalobg
    gonzalobg committed May 27, 2024
    Configuration menu
    Copy the full SHA
    759f7b1 View commit details
    Browse the repository at this point in the history

Commits on May 30, 2024

  1. Refactor CUDA kernels and support block-stride loops

    @gonzalobg
    gonzalobg committed May 30, 2024
    Configuration menu
    Copy the full SHA
    293ed77 View commit details
    Browse the repository at this point in the history

  2. Bugfix: division by zero in solution-check for individual benchmarks

    @gonzalobg
    gonzalobg committed May 30, 2024
    Configuration menu
    Copy the full SHA
    13e870f View commit details
    Browse the repository at this point in the history

  3. Print order used

    @gonzalobg
    gonzalobg committed May 30, 2024
    Configuration menu
    Copy the full SHA
    46b6d41 View commit details
    Browse the repository at this point in the history

  4. Print device peak BW using NVML

    @gonzalobg
    gonzalobg committed May 30, 2024
    Configuration menu
    Copy the full SHA
    51231ac View commit details
    Browse the repository at this point in the history

  5. Capitalize order options for consistency with benchmarks

    @gonzalobg
    gonzalobg committed May 30, 2024
    Configuration menu
    Copy the full SHA
    321ba62 View commit details
    Browse the repository at this point in the history

Commits on Jun 4, 2024

  1. Move host-side allocation to benchmarks and reuse device with UVM 

    This commit puts benchmarks in control of allocating the host
memory used for verifying the results.

This enables benchmarks that use Unified Memory for the device
allocations, to avoid the host-side allocation and just pass
pointers to the device allocation to the benchmark driver.

Closes UoB-HPC#128 .
    @gonzalobg
    gonzalobg committed Jun 4, 2024
    Configuration menu
    Copy the full SHA
    616b3b2 View commit details
    Browse the repository at this point in the history

Commits on Jun 5, 2024

  1. Add serial model

    @tom91136 @gonzalobg
    tom91136 authored and gonzalobg committed Jun 5, 2024
    Configuration menu
    Copy the full SHA
    2929a6c View commit details
    Browse the repository at this point in the history

  2. Update Serial

    @gonzalobg
    gonzalobg committed Jun 5, 2024
    Configuration menu
    Copy the full SHA
    9ff46ec View commit details
    Browse the repository at this point in the history

  3. Merge C++ Standard Parallelism and SYCL2020 implementations

    @gonzalobg
    gonzalobg committed Jun 5, 2024
    Configuration menu
    Copy the full SHA
    b3786f6 View commit details
    Browse the repository at this point in the history

  4. Add support for AdaptiveCpp to C++ Standard Parallelism

    @gonzalobg
    gonzalobg committed Jun 5, 2024
    Configuration menu
    Copy the full SHA
    62a5051 View commit details
    Browse the repository at this point in the history

Commits on Aug 14, 2024

  1. Add support for hipstdpar

    @gsitaram @gonzalobg
    gsitaram authored and gonzalobg committed Aug 14, 2024
    Configuration menu
    Copy the full SHA
    6f0c2a1 View commit details
    Browse the repository at this point in the history

  2. Arm toolchains prefer -mcpu=native

    @gonzalobg
    gonzalobg committed Aug 14, 2024
    Configuration menu
    Copy the full SHA
    084ef3b View commit details
    Browse the repository at this point in the history

  3. Support NVHPC stdpar=multicore and AMDGPU interpose-alloc

    @gonzalobg
    gonzalobg committed Aug 14, 2024
    Configuration menu
    Copy the full SHA
    4cebcde View commit details
    Browse the repository at this point in the history