projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 73777b4) | patch
[AMDGPU] use scalar shift for SALU users in frame index elimination
authoralex-t <alexander.timofeev@amd.com>
Tue, 22 Mar 2022 12:13:15 +0000 (13:13 +0100)
committeralex-t <alexander.timofeev@amd.com>
Tue, 22 Mar 2022 12:16:24 +0000 (13:16 +0100)
commit7636c9a9297d82559a342d2c18a1205d7d7715c6
treef282b8203b0eaa7c2e4cbdbbbf7eed9a03692ef3tree | snapshot
parent73777b4c35a390617cce0f6b4516e98fe5a88df1commit | diff
[AMDGPU] use scalar shift for SALU users in frame index elimination

In the frame index lowering we have to insert shift and add
instructions to adjust stack object access.  We need to take care of the stack
object user kind and use scalar shift/add for scalar users.

Reviewed By: rampitec

Differential Revision: https://reviews.llvm.org/D121524
llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp diff | blob | history
Domain: System / Toolchain;