[all-commits] [llvm/llvm-project] 727573: [CUDA/NVPTX] Improve handling of memcpy for -Os co...

[Artem Belevich via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 72757343fa866b7bfcbaa67edad895297c8cb2c5
      https://github.com/llvm/llvm-project/commit/72757343fa866b7bfcbaa67edad895297c8cb2c5
  Author: Artem Belevich <tra at google.com>
  Date:   2023-08-18 (Fri, 18 Aug 2023)

  Changed paths:
    A clang/test/CodeGenCUDA/memcpy-libcall.cu
    M llvm/lib/Target/NVPTX/NVPTXISelLowering.cpp

  Log Message:
  -----------
  [CUDA/NVPTX] Improve handling of memcpy for -Os compilations.

We had some instances when LLVM would not inline fixed-count memcpy and ended up
attempting to lower it a a libcall, which would not work on NVPTX as there's no
standard library to call.

The patch relaxes the threshold used for -Os compilation so we're always allowed
to inline memory copy functions.

Differential Revision: https://reviews.llvm.org/D158226