Skip to content
This repository was archived by the owner on Mar 21, 2024. It is now read-only.
Permalink

Comparing changes

Choose two branches to see what’s changed or to start a new pull request. If you need to, you can also or learn more about diff comparisons.

Open a pull request

Create a new pull request by comparing changes across two branches. If you need to, you can also . Learn more about diff comparisons here.
base repository: NVIDIA/cub
Failed to load repositories. Confirm that selected base ref is valid, then try again.
Loading
base: 56dcb06d0cd7f923c373a27a7f9993722e0f50b4
Choose a base ref
...
head repository: NVIDIA/cub
Failed to load repositories. Confirm that selected head ref is valid, then try again.
Loading
compare: 4de961aee49c894e9c380d7c2f7e750016976f00
Choose a head ref
  • 7 commits
  • 63 files changed
  • 1 contributor

Commits on May 16, 2022

  1. Add libcu++ dependency.

    @alliepiper
    alliepiper committed May 16, 2022
    Configuration menu
    Copy the full SHA
    f42070e View commit details
    Browse the repository at this point in the history

  2. Remove checks for obsolete architectures.

    @alliepiper
    alliepiper committed May 16, 2022
    Configuration menu
    Copy the full SHA
    f9beaa5 View commit details
    Browse the repository at this point in the history

  3. Remove PTX arguments from compile-time contexts. 

    nvc++ will stop defining __NVCOMPILER_CUDA_ARCH__ soon, removing the
ability to determine the PTX arch at compile time.

This updates agents and collective algorithms to no longer require the
PTX_ARCH template parameter, and changes the CUB_WARP_SIZE(PTX_ARCH), etc
helpers to ignore their argument. These macros only differed on
obsolete arches and have no effect on currently supported architectures.
    @alliepiper
    alliepiper committed May 16, 2022
    Configuration menu
    Copy the full SHA
    5799e96 View commit details
    Browse the repository at this point in the history

  4. Use NV_IF_TARGET to select between host/device/sm implementations.

    @alliepiper
    alliepiper committed May 16, 2022
    Configuration menu
    Copy the full SHA
    c4299c4 View commit details
    Browse the repository at this point in the history

  5. Don't use host-only functions in host-device contexts. 

    This fixes the issue reported in #299. There's no
clear reason why this should use `RandomBits` unconditionally.
    @alliepiper
    alliepiper committed May 16, 2022
    Configuration menu
    Copy the full SHA
    476c1b8 View commit details
    Browse the repository at this point in the history

  6. Use Thrust's kernel launch helper in DispatchRadixSort.

    @alliepiper
    alliepiper committed May 16, 2022
    Configuration menu
    Copy the full SHA
    f4d61fb View commit details
    Browse the repository at this point in the history

  7. Skip large allocation tests that exceed device memory. 

    The merge sort test with pow2 >20 fails on GTX 1650. Detect
bad_alloc failures and skip those tests. Tests for smaller
problem sizes will still fail if there's a bad_alloc.
    @alliepiper
    alliepiper committed May 16, 2022
    Configuration menu
    Copy the full SHA
    4de961a View commit details
    Browse the repository at this point in the history
Loading