Commit Graph

10 Commits

Author SHA1 Message Date
Stanislav Mekhanoshin a8d9d50762 [AMDGPU] gfx90a support
Differential Revision: https://reviews.llvm.org/D96906
2021-02-17 16:01:32 -08:00
Joe Nash 314e29ed2b [AMDGPU] Add _e64 suffix to VOP3 Insts
Previously, instructions which could be
expressed as VOP3 in addition to another
encoding had a _e64 suffix on the tablegen
record name, while those
only available as VOP3 did not. With this
patch, all VOP3s will have the _e64 suffix.
The assembly does not change, only  the mir.

Reviewed By: foad

Differential Revision: https://reviews.llvm.org/D94341

Change-Id: Ia8ec8890d47f8f94bbbdac43745b4e9dd2b03423
2021-01-12 18:33:18 -05:00
Matt Arsenault ce16b6835b AMDGPU: Don't kill super-register with overlapping copy
This would end up killing part of the result super-register, resulting
in a verifier error on a later use of the overlapping registers.  We
could add kills of any non-aliasing registers, but we should be moving
away from relying on kill flags.
2020-10-16 09:34:35 -04:00
Matt Arsenault e56e9022bc AMDGPU: Fix liveness errors when copying AGPR tuples
Avoid recursively calling copyPhysReg for AGPR handling. This was
dropping the necessary super register implicit defs to avoid liveness
verifier errors.
2020-07-30 18:13:04 -04:00
Matt Arsenault 6c5b635e95 AMDGPU: Add a few more missing test for AGPR tuple copying 2020-07-16 15:53:11 -04:00
Matt Arsenault 10382285ac AMDGPU: Add missing tests for copyPhysReg AGPR tuples 2020-07-16 15:27:57 -04:00
Pushpinder Singh e1a31f52cd [AMDGPU] Control num waves per EU for implicit work-group size
Summary:
If amdgpu-flat-work-group-size is not specified in LLVM IR, the backend
uses default value of 1024. For this, minimum waves per EU should be 4.
However, backend is still setting minimum value to 1 instead of calculated
value. This is not observed normally as frontend always provide
amdgpu-flat-work-group-size attribute.

Reviewers: rampitec, b-sumner, sameerds, msearles

Reviewed By: rampitec

Subscribers: qcolombet, arsenm, kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, hiraditya, kerbowa, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D81991
2020-07-01 22:53:52 -04:00
Matt Arsenault a230f1db3f AMDGPU: Fix missing tracksRegLiveness in tests
I have no idea why this is considered optional, or why it's not the
default. Also add uses of the copied registers for more useful
liveness testing.
2020-07-01 18:58:59 -04:00
Matt Arsenault ba3bafe46a AMDGPU: Convert AGPR copy test to generated checks 2020-07-01 13:59:13 -04:00
Stanislav Mekhanoshin e67cc380a8 [AMDGPU] gfx908 mfma support
Differential Revision: https://reviews.llvm.org/D64584

llvm-svn: 365824
2019-07-11 21:19:33 +00:00