rtaylor (Ryan Taylor)
User

Projects

User does not belong to any projects.

User Details

User Since
Jan 9 2018, 7:56 AM (40 w, 5 d)

Recent Activity

Aug 28 2018

rtaylor added a comment to D50575: [AMDGPU] Add support for a16 modifier for gfx9.

Thanks for the changes.

Sorry to be a stickler about this, but the formatting of the odd gradients check in lowerImage is still wrong, please adjust this according to clang-format-diff before you commit.

No need to re-upload here, the rest of the changes looks good to me.

Aug 28 2018, 10:45 AM

Aug 27 2018

rtaylor updated the diff for D50575: [AMDGPU] Add support for a16 modifier for gfx9.

Realized that I had updated clang-format runs of of SIISelLowering.h/.cpp and this caused a lot of re-formatting.

Aug 27 2018, 8:22 AM

Aug 23 2018

rtaylor updated the diff for D50575: [AMDGPU] Add support for a16 modifier for gfx9.

Made suggested changes.

Aug 23 2018, 4:12 PM

Aug 17 2018

rtaylor added a comment to D50575: [AMDGPU] Add support for a16 modifier for gfx9.

Ping.

Aug 17 2018, 7:38 AM

Aug 14 2018

rtaylor added a reviewer for D50575: [AMDGPU] Add support for a16 modifier for gfx9: arsenm.
Aug 14 2018, 11:30 AM
rtaylor updated the diff for D50575: [AMDGPU] Add support for a16 modifier for gfx9.

Made changes according to suggestions. Reduced redundancy and simplified code structure.

Aug 14 2018, 9:26 AM

Aug 13 2018

rtaylor added inline comments to D50575: [AMDGPU] Add support for a16 modifier for gfx9.
Aug 13 2018, 4:33 PM
rtaylor added inline comments to D50575: [AMDGPU] Add support for a16 modifier for gfx9.
Aug 13 2018, 6:06 AM

Aug 10 2018

rtaylor retitled D50575: [AMDGPU] Add support for a16 modifier for gfx9 from [AMDGPU] Add support for a16 modifiear for gfx9 to [AMDGPU] Add support for a16 modifier for gfx9.
Aug 10 2018, 11:07 AM
rtaylor added reviewers for D50575: [AMDGPU] Add support for a16 modifier for gfx9: nhaehnle, tpr, dstuttard, timcorringham.
Aug 10 2018, 11:06 AM
rtaylor created D50575: [AMDGPU] Add support for a16 modifier for gfx9.
Aug 10 2018, 11:05 AM

Jul 30 2018

rtaylor updated the diff for D49483: [AMDGPU] Optimize _L image intrinsic to _LZ when lod is zero.

Added gather4 test cases.
Added 'isNegative' to _L to _LZ check to include <= 0.0

Jul 30 2018, 7:42 AM

Jul 25 2018

rtaylor added a comment to D49483: [AMDGPU] Optimize _L image intrinsic to _LZ when lod is zero.

Ping.

Jul 25 2018, 8:20 AM

Jul 18 2018

rtaylor added a comment to D49483: [AMDGPU] Optimize _L image intrinsic to _LZ when lod is zero.

Should this be done in an IR pass instead?

Jul 18 2018, 8:30 AM
rtaylor added reviewers for D49483: [AMDGPU] Optimize _L image intrinsic to _LZ when lod is zero: nhaehnle, arsenm, tpr, dstuttard.
Jul 18 2018, 7:00 AM
rtaylor created D49483: [AMDGPU] Optimize _L image intrinsic to _LZ when lod is zero.
Jul 18 2018, 6:59 AM

Jun 29 2018

rtaylor updated the diff for D48772: [AMDGPU] Add VALU to V_INTERP Instructions.

Adding GCN-NEXT in test case

Jun 29 2018, 10:59 AM
rtaylor updated the diff for D48772: [AMDGPU] Add VALU to V_INTERP Instructions.

Removed empty line insert in SIInstructions.td

Jun 29 2018, 10:43 AM
rtaylor updated the diff for D48772: [AMDGPU] Add VALU to V_INTERP Instructions.

Changed VALU to be set in base instruction class.

Jun 29 2018, 10:41 AM
rtaylor updated the diff for D48772: [AMDGPU] Add VALU to V_INTERP Instructions.

Moved VALU=1 to the base instruction defs.

Jun 29 2018, 8:53 AM
rtaylor added reviewers for D48772: [AMDGPU] Add VALU to V_INTERP Instructions: tpr, dstuttard, arsenm, nhaehnle.
Jun 29 2018, 7:27 AM
rtaylor created D48772: [AMDGPU] Add VALU to V_INTERP Instructions.
Jun 29 2018, 7:25 AM