llvm-project

Commit Graph

Author	SHA1	Message	Date
Matt Arsenault	627bb31a28	AMDGPU/GlobalISel: Avoid illegal vector exts for add/sub/mul When expanding scalar packed operations, we should not introduce illegal vector casts LegalizerHelper introduces. We're not in a legalizer context, and there's no RegBankSelect apply or legalize worklist.	2020-03-09 23:42:17 -04:00
Matt Arsenault	ed72bcae34	AMDGPU/GlobalISel: Fix mishandling SGPR v2s16 add/sub/mul We weren't considering the packed case correctly, and this was passing through to the selector. The selector only checked the size, so this would incorrectly compile to a single 32-bit scalar add. As usual, the LegalizerHelper is somewhat awkward to use from applyMappingImpl. I think this is the first place we've needed multi-step legalization here though.	2020-03-09 22:51:54 -04:00

Author

SHA1

Message

Date

Matt Arsenault

627bb31a28

AMDGPU/GlobalISel: Avoid illegal vector exts for add/sub/mul

When expanding scalar packed operations, we should not introduce
illegal vector casts LegalizerHelper introduces. We're not in a
legalizer context, and there's no RegBankSelect apply or legalize
worklist.

2020-03-09 23:42:17 -04:00

Matt Arsenault

ed72bcae34

AMDGPU/GlobalISel: Fix mishandling SGPR v2s16 add/sub/mul

We weren't considering the packed case correctly, and this was passing
through to the selector. The selector only checked the size, so this
would incorrectly compile to a single 32-bit scalar add.

As usual, the LegalizerHelper is somewhat awkward to use from
applyMappingImpl. I think this is the first place we've needed
multi-step legalization here though.

2020-03-09 22:51:54 -04:00

2 Commits