[all-commits] [llvm/llvm-project] fc22de: [AMDGPU] Clarify calling conv about inactive lanes

[Sebastian Neubauer via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: fc22de82182e05794123be70df5dfe15600c02b4
      https://github.com/llvm/llvm-project/commit/fc22de82182e05794123be70df5dfe15600c02b4
  Author: Sebastian Neubauer <sebastian.neubauer at amd.com>
  Date:   2021-02-02 (Tue, 02 Feb 2021)

  Changed paths:
    M llvm/docs/AMDGPUUsage.rst

  Log Message:
  -----------
  [AMDGPU] Clarify calling conv about inactive lanes

So far, it was not specified what happens with the VGPRs of inactive
lanes when functions are called. This patch explicitely mentions that
the VGPR values of inactive lanes need to be preserved for all
registers.

This describes the current behavior, as only active lanes of registers
are saved to scratch. Also, as the multi-lane nature of VGPRs is not
properly modeled, we cannot determine the live VGPRs from inactive lanes
at calls. So we cannot save them, even if we intended to do so.

Differential Revision: https://reviews.llvm.org/D95610