10 Commits

Author SHA1 Message Date
Jay Foad
8871c3c562 [AMDGPU] Regenerate MIR checks. NFC. 2022-06-27 12:15:29 +01:00
Carl Ritson
5df2af8b0e [AMDGPU] Merge SIRemoveShortExecBranches into SIPreEmitPeephole
SIRemoveShortExecBranches is an optimisation so fits well in the
context of SIPreEmitPeephole.

Test changes relate to early termination from kills which have now
been lowered prior to considering branches for removal.
As these use s_cbranch the execz skips are now retained instead.
Currently either behaviour is valid as kill with EXEC=0 is a nop;
however, if early termination is used differently in future then
the new behaviour is the correct one.

Reviewed By: foad

Differential Revision: https://reviews.llvm.org/D98917
2021-03-20 11:26:42 +09:00
Ruiling Song
f0ccdde3c9 [AMDGPU] Remove SI_MASK_BRANCH
This is already deprecated, so remove code working on this.
Also update the tests by using S_CBRANCH_EXECZ instead of SI_MASK_BRANCH.

Reviewed By: foad

Differential Revision: https://reviews.llvm.org/D97545
2021-03-09 09:13:23 +08:00
Jay Foad
7a79921edd [AMDGPU] Remove gds operand from ds_gws_* MachineInstrs
The operand value was always 1 (except in some bad MIR tests) so it was
redundant.

Differential Revision: https://reviews.llvm.org/D90378
2020-10-29 15:04:23 +00:00
cdevadas
e53a9d96e6 Resubmit: [AMDGPU] Invert the handling of skip insertion.
The current implementation of skip insertion (SIInsertSkip) makes it a
mandatory pass required for correctness. Initially, the idea was to
have an optional pass. This patch inserts the s_cbranch_execz upfront
during SILowerControlFlow to skip over the sections of code when no
lanes are active. Later, SIRemoveShortExecBranches removes the skips
for short branches, unless there is a sideeffect and the skip branch is
really necessary.

This new pass will replace the handling of skip insertion in the
existing SIInsertSkip Pass.

Differential revision: https://reviews.llvm.org/D68092
2020-01-22 13:18:32 +09:00
Nicolai Hähnle
a80291ce10 Revert "[AMDGPU] Invert the handling of skip insertion."
This reverts commit 0dc6c249bffac9f23a605ce4e42a84341da3ddbd.

The commit is reported to cause a regression in piglit/bin/glsl-vs-loop for
Mesa.
2020-01-21 09:17:25 +01:00
cdevadas
0dc6c249bf [AMDGPU] Invert the handling of skip insertion.
The current implementation of skip insertion (SIInsertSkip) makes it a
mandatory pass required for correctness. Initially, the idea was to
have an optional pass. This patch inserts the s_cbranch_execz upfront
during SILowerControlFlow to skip over the sections of code when no
lanes are active. Later, SIRemoveShortExecBranches removes the skips
for short branches, unless there is a sideeffect and the skip branch is
really necessary.

This new pass will replace the handling of skip insertion in the
existing SIInsertSkip Pass.

Differential revision: https://reviews.llvm.org/D68092
2020-01-15 15:18:16 +05:30
Matt Arsenault
4d55d024be Reapply "AMDGPU: Add ds_gws_init / ds_gws_barrier intrinsics"
This reapplies r363678, using the correct chain for the CopyToReg for
v0. glueCopyToM0 counterintuitively changes the operands of the
original node.

llvm-svn: 363870
2019-06-19 19:55:27 +00:00
Simon Pilgrim
128ce93c60 Revert rL363678 : AMDGPU: Add ds_gws_init / ds_gws_barrier intrinsics
There may or may not be additional work to handle this correctly on
SI/CI.
........
Breaks EXPENSIVE_CHECKS buildbots - http://lab.llvm.org:8011/builders/llvm-clang-x86_64-expensive-checks-win/builds/78/

llvm-svn: 363797
2019-06-19 13:00:54 +00:00
Matt Arsenault
8d35dcd703 AMDGPU: Add ds_gws_init / ds_gws_barrier intrinsics
There may or may not be additional work to handle this correctly on
SI/CI.

llvm-svn: 363678
2019-06-18 13:19:57 +00:00