Page MenuHomePhabricator
Feed Advanced Search

Mar 18 2019

tpr committed rGcfdfba996b08: [AMDGPU] Asm/disasm clamp modifier on vop3 int arithmetic (authored by tpr).
[AMDGPU] Asm/disasm clamp modifier on vop3 int arithmetic
Mar 18 2019, 12:36 PM
tpr committed rL356399: [AMDGPU] Asm/disasm clamp modifier on vop3 int arithmetic.
[AMDGPU] Asm/disasm clamp modifier on vop3 int arithmetic
Mar 18 2019, 12:36 PM
tpr closed D59267: [AMDGPU] Asm/disasm clamp modifier on vop3 int arithmetic.
Mar 18 2019, 12:36 PM · Restricted Project
tpr committed rG2e94f6e584d9: [AMDGPU] Asm/disasm v_cndmask_b32_e64 with abs/neg source modifiers (authored by tpr).
[AMDGPU] Asm/disasm v_cndmask_b32_e64 with abs/neg source modifiers
Mar 18 2019, 12:25 PM
tpr committed rL356398: [AMDGPU] Asm/disasm v_cndmask_b32_e64 with abs/neg source modifiers.
[AMDGPU] Asm/disasm v_cndmask_b32_e64 with abs/neg source modifiers
Mar 18 2019, 12:25 PM
tpr closed D59191: [AMDGPU] Asm/disasm v_cndmask_b32_e64 with abs/neg source modifiers.
Mar 18 2019, 12:24 PM · Restricted Project
tpr committed rG8723a5655172: [MsgPack][AMDGPU] Fix unflushed raw_string_ostream bugs on windows expensive… (authored by tpr).
[MsgPack][AMDGPU] Fix unflushed raw_string_ostream bugs on windows expensive…
Mar 18 2019, 12:01 PM
tpr committed rL356394: [MsgPack][AMDGPU] Fix unflushed raw_string_ostream bugs on windows expensive….
[MsgPack][AMDGPU] Fix unflushed raw_string_ostream bugs on windows expensive…
Mar 18 2019, 12:00 PM
tpr closed D59396: [MsgPack] Attempt to fix failure on windows expensive checks bot.
Mar 18 2019, 12:00 PM · Restricted Project
tpr added inline comments to D57027: [AMDGPU] Factored PAL metadata handling out into its own class.
Mar 18 2019, 8:56 AM · Restricted Project
tpr updated the diff for D57028: [AMDGPU] Added MsgPack format PAL metadata.

V2: Like the previous commit, no longer supports a method for LLPC to

call to write the PAL metadata into IR metadata. The plan now is
that LLPC will use MsgPackDocument and put the msgpack binary blob
into IR metadata itself.
Mar 18 2019, 8:55 AM · Restricted Project
tpr updated the diff for D57027: [AMDGPU] Factored PAL metadata handling out into its own class.

V2: Removed AMDGPUPALMetadata API used directly by LLPC. The plan now is

that LLPC will continue to put the PAL metadata binary blob
into IR metadata itself.
Mar 18 2019, 8:52 AM · Restricted Project

Mar 17 2019

tpr committed rGc4e128e2219b: [CodeGen] Defined MVTs v3i32, v3f32, v5i32, v5f32 (authored by tpr).
[CodeGen] Defined MVTs v3i32, v3f32, v5i32, v5f32
Mar 17 2019, 3:57 PM
tpr committed rL356351: [CodeGen] Defined MVTs v3i32, v3f32, v5i32, v5f32.
[CodeGen] Defined MVTs v3i32, v3f32, v5i32, v5f32
Mar 17 2019, 3:57 PM
tpr closed D58901: [CodeGen] Defined MVTs v3i32, v3f32, v5i32, v5f32.
Mar 17 2019, 3:56 PM · Restricted Project
tpr committed rGc302b9b5fe0e: [CodeGen] Prepare for introduction of v3 and v5 MVTs (authored by tpr).
[CodeGen] Prepare for introduction of v3 and v5 MVTs
Mar 17 2019, 2:42 PM
tpr committed rL356350: [CodeGen] Prepare for introduction of v3 and v5 MVTs.
[CodeGen] Prepare for introduction of v3 and v5 MVTs
Mar 17 2019, 2:42 PM
tpr closed D58899: [CodeGen] Prepare for introduction of v3 and v5 MVTs.
Mar 17 2019, 2:42 PM · Restricted Project
tpr committed rGe30aa6a13623: [AMDGPU] Prepare for introduction of v3 and v5 MVTs (authored by tpr).
[AMDGPU] Prepare for introduction of v3 and v5 MVTs
Mar 17 2019, 2:03 PM
tpr committed rL356342: [AMDGPU] Prepare for introduction of v3 and v5 MVTs.
[AMDGPU] Prepare for introduction of v3 and v5 MVTs
Mar 17 2019, 2:03 PM
tpr closed D58928: [AMDGPU] Prepare for introduction of v3 and v5 MVTs.
Mar 17 2019, 2:03 PM · Restricted Project
tpr committed rGd1477e989cef: [ARM] Fixed an assumption of power-of-2 vector MVT (authored by tpr).
[ARM] Fixed an assumption of power-of-2 vector MVT
Mar 17 2019, 1:48 PM
tpr committed rL356341: [ARM] Fixed an assumption of power-of-2 vector MVT.
[ARM] Fixed an assumption of power-of-2 vector MVT
Mar 17 2019, 1:47 PM
tpr closed D58927: [ARM] Fixed an assumption of power-of-2 vector MVT.
Mar 17 2019, 1:47 PM · Restricted Project

Mar 16 2019

tpr updated the diff for D58902: [AMDGPU] Support for v3i32/v3f32.

V5: Added vec3 to AMDGPUCallingConvention.td. Fixed call-return-types test for dwordx3 buffer/flat.
(I will add vec5 to AMDGPUCallingConvention.td in the vec5 change.)

Mar 16 2019, 11:55 AM · Restricted Project
tpr updated the diff for D58928: [AMDGPU] Prepare for introduction of v3 and v5 MVTs.

V5: Added vec3/vec5 non-shader arg and ret type test cases, including passing by stack.

Mar 16 2019, 11:49 AM · Restricted Project
tpr added inline comments to D58927: [ARM] Fixed an assumption of power-of-2 vector MVT.
Mar 16 2019, 6:09 AM · Restricted Project
tpr updated the diff for D58927: [ARM] Fixed an assumption of power-of-2 vector MVT.

V4: Properly addressed review comment.

Mar 16 2019, 6:09 AM · Restricted Project
tpr updated the diff for D59396: [MsgPack] Attempt to fix failure on windows expensive checks bot.

V3: Adjusted the MIR roundtrip fix to use scoping instead of explicit flush.

Mar 16 2019, 5:26 AM · Restricted Project
tpr added inline comments to D59396: [MsgPack] Attempt to fix failure on windows expensive checks bot.
Mar 16 2019, 5:18 AM · Restricted Project

Mar 15 2019

tpr added a reviewer for D59396: [MsgPack] Attempt to fix failure on windows expensive checks bot: arsenm.
Mar 15 2019, 2:19 AM · Restricted Project
tpr updated the diff for D59396: [MsgPack] Attempt to fix failure on windows expensive checks bot.

V2: Also fix the same bug in Matt's AMDGPU MIR roundtrip commit.

Mar 15 2019, 2:19 AM · Restricted Project

Mar 14 2019

tpr added reviewers for D59396: [MsgPack] Attempt to fix failure on windows expensive checks bot: gkistanova, scott.linder.
Mar 14 2019, 4:32 PM · Restricted Project
tpr created D59396: [MsgPack] Attempt to fix failure on windows expensive checks bot.
Mar 14 2019, 4:27 PM · Restricted Project
tpr added a reviewer for D59191: [AMDGPU] Asm/disasm v_cndmask_b32_e64 with abs/neg source modifiers: rampitec.
Mar 14 2019, 2:38 AM · Restricted Project
tpr added a reviewer for D59267: [AMDGPU] Asm/disasm clamp modifier on vop3 int arithmetic: rampitec.
Mar 14 2019, 2:37 AM · Restricted Project

Mar 13 2019

tpr committed rG49454e236f52: [MsgPack] Removed MsgPackTypes (authored by tpr).
[MsgPack] Removed MsgPackTypes
Mar 13 2019, 11:57 AM
tpr committed rL356082: [MsgPack] Removed MsgPackTypes.
[MsgPack] Removed MsgPackTypes
Mar 13 2019, 11:55 AM
tpr closed D57025: [MsgPack] Removed MsgPackTypes.
Mar 13 2019, 11:55 AM · Restricted Project
tpr committed rGed0b9af9973e: [AMDGPU] Switched HSA metadata to use MsgPackDocument (authored by tpr).
[AMDGPU] Switched HSA metadata to use MsgPackDocument
Mar 13 2019, 11:55 AM
tpr committed rL356081: [AMDGPU] Switched HSA metadata to use MsgPackDocument.
[AMDGPU] Switched HSA metadata to use MsgPackDocument
Mar 13 2019, 11:54 AM
tpr closed D57024: [AMDGPU] Switched HSA metadata to use MsgPackDocument.
Mar 13 2019, 11:54 AM · Restricted Project
tpr committed rG4ced8de17c5f: [MsgPack] New MsgPackDocument class (authored by tpr).
[MsgPack] New MsgPackDocument class
Mar 13 2019, 11:54 AM
tpr committed rL356080: [MsgPack] New MsgPackDocument class.
[MsgPack] New MsgPackDocument class
Mar 13 2019, 11:54 AM
tpr closed D57023: [MsgPack] New MsgPackDocument class.
Mar 13 2019, 11:54 AM · Restricted Project
tpr updated the diff for D58928: [AMDGPU] Prepare for introduction of v3 and v5 MVTs.

V4: Added vec3/vec5 shader arg test cases.

Mar 13 2019, 10:40 AM · Restricted Project
tpr updated the diff for D58902: [AMDGPU] Support for v3i32/v3f32.

V4: Fixed vec3 in sign_extend test.

Mar 13 2019, 3:45 AM · Restricted Project
tpr added inline comments to D58927: [ARM] Fixed an assumption of power-of-2 vector MVT.
Mar 13 2019, 2:58 AM · Restricted Project
tpr updated the diff for D58927: [ARM] Fixed an assumption of power-of-2 vector MVT.

V3: Addressed review comment.

Mar 13 2019, 2:58 AM · Restricted Project

Mar 12 2019

tpr updated the diff for D59267: [AMDGPU] Asm/disasm clamp modifier on vop3 int arithmetic.

V2: Addressed review comment: Commented extra clamp bit operands.

Mar 12 2019, 2:06 PM · Restricted Project
tpr added reviewers for D59267: [AMDGPU] Asm/disasm clamp modifier on vop3 int arithmetic: vpykhtin, kzhuravl, scott.linder, arsenm.
Mar 12 2019, 10:37 AM · Restricted Project
tpr created D59267: [AMDGPU] Asm/disasm clamp modifier on vop3 int arithmetic.
Mar 12 2019, 10:35 AM · Restricted Project

Mar 11 2019

tpr added a comment to D59191: [AMDGPU] Asm/disasm v_cndmask_b32_e64 with abs/neg source modifiers.

The answer I have got from the HW team is that you can use abs and neg modifiers on f32 data in v_cndmask_b32, v_mov_b32 and v_movrel*_b32.

Mar 11 2019, 10:39 AM · Restricted Project
tpr updated the diff for D58902: [AMDGPU] Support for v3i32/v3f32.

V3: Added multi-dword vgpr spill test, inc vec3 and vec5.

Mar 11 2019, 7:12 AM · Restricted Project
tpr added reviewers for D58905: [AMDGPU] Use three- and five-dword result type in image ops: rampitec, arsenm.

Ping.

Mar 11 2019, 5:44 AM · Restricted Project
tpr added a comment to D58927: [ARM] Fixed an assumption of power-of-2 vector MVT.

Hi Tim,

It seems to me that this could use a test-case that fails without this fix.

Mar 11 2019, 5:44 AM · Restricted Project
tpr updated the diff for D58928: [AMDGPU] Prepare for introduction of v3 and v5 MVTs.

V3: Fixed new cost tests so they work with and without legal v3/v5
types. Added v5i64/v5f64 kernarg test cases as suggested by Matt.

Mar 11 2019, 5:08 AM · Restricted Project
tpr added a comment to D58928: [AMDGPU] Prepare for introduction of v3 and v5 MVTs.

Could also use the vector tests for the shader arguments

Mar 11 2019, 4:48 AM · Restricted Project
tpr added a comment to D59191: [AMDGPU] Asm/disasm v_cndmask_b32_e64 with abs/neg source modifiers.

I'll double check.

Mar 11 2019, 2:22 AM · Restricted Project

Mar 10 2019

tpr added reviewers for D59191: [AMDGPU] Asm/disasm v_cndmask_b32_e64 with abs/neg source modifiers: vpykhtin, kzhuravl, scott.linder, arsenm.
Mar 10 2019, 1:16 PM · Restricted Project
tpr created D59191: [AMDGPU] Asm/disasm v_cndmask_b32_e64 with abs/neg source modifiers.
Mar 10 2019, 1:12 PM · Restricted Project

Mar 8 2019

tpr added reviewers for D58927: [ARM] Fixed an assumption of power-of-2 vector MVT: dnsampaio, RKSimon.
Mar 8 2019, 12:42 AM · Restricted Project
tpr added a reviewer for D58901: [CodeGen] Defined MVTs v3i32, v3f32, v5i32, v5f32: craig.topper.
Mar 8 2019, 12:39 AM · Restricted Project

Mar 6 2019

tpr updated the diff for D58899: [CodeGen] Prepare for introduction of v3 and v5 MVTs.

V3: Addressed review comment by widening illegal odd vectors in a
different way.

Mar 6 2019, 1:33 PM · Restricted Project
tpr updated the diff for D58903: [AMDGPU] Added v5i32 and v5f32 register classes.

V2: Fixed missing part of change, including defaulting v5 operations to
expand. Fixed broken v5f32 select. Fixed reg class priorities.
Fixed spilling and asm constraints, and added sgpr spill test.

Mar 6 2019, 1:28 PM · Restricted Project
tpr added a comment to D58902: [AMDGPU] Support for v3i32/v3f32.

Actually I only have a vec3 spilling test for sgprs. I didn't see any multi-dword vgpr spill tests.

Mar 6 2019, 12:47 PM · Restricted Project
tpr updated the diff for D58902: [AMDGPU] Support for v3i32/v3f32.

V2: Fixed broken v3f32 select.

Fixed reg class priorities.
Updated a fragile test.
Addressed review comments on DL::getIdxType.
Fixed vec3 sgpr inline asm constraint.
Added vec3 sgpr spill test.
Mar 6 2019, 12:46 PM · Restricted Project
tpr added a comment to D58902: [AMDGPU] Support for v3i32/v3f32.

Needs a test for the 96-bit spills. An -O0 test case with a value live across a block should work

Mar 6 2019, 11:49 AM · Restricted Project
tpr added inline comments to D58902: [AMDGPU] Support for v3i32/v3f32.
Mar 6 2019, 10:57 AM · Restricted Project
tpr added a comment to D58902: [AMDGPU] Support for v3i32/v3f32.
In D58902#1418275, @tpr wrote:

What about flat and segmented memory operations?

Flat dwordx3 is supported, as shown by some test changes. What is segmented memory?

Segmented flat, like global_load.

Mar 6 2019, 4:00 AM · Restricted Project

Mar 5 2019

tpr added inline comments to D58902: [AMDGPU] Support for v3i32/v3f32.
Mar 5 2019, 10:39 AM · Restricted Project
tpr added a comment to D58902: [AMDGPU] Support for v3i32/v3f32.

What about flat and segmented memory operations?

Mar 5 2019, 5:35 AM · Restricted Project
tpr updated the diff for D58928: [AMDGPU] Prepare for introduction of v3 and v5 MVTs.

V2: Addressed Stas's review comment about empty block.

Mar 5 2019, 3:27 AM · Restricted Project

Mar 4 2019

tpr added inline comments to D58899: [CodeGen] Prepare for introduction of v3 and v5 MVTs.
Mar 4 2019, 3:24 PM · Restricted Project
tpr added a child revision for D58928: [AMDGPU] Prepare for introduction of v3 and v5 MVTs: D58901: [CodeGen] Defined MVTs v3i32, v3f32, v5i32, v5f32.
Mar 4 2019, 3:24 PM · Restricted Project
tpr added a parent revision for D58901: [CodeGen] Defined MVTs v3i32, v3f32, v5i32, v5f32: D58928: [AMDGPU] Prepare for introduction of v3 and v5 MVTs.
Mar 4 2019, 3:24 PM · Restricted Project
tpr added reviewers for D58928: [AMDGPU] Prepare for introduction of v3 and v5 MVTs: arsenm, rampitec.
Mar 4 2019, 3:24 PM · Restricted Project
tpr added a parent revision for D58901: [CodeGen] Defined MVTs v3i32, v3f32, v5i32, v5f32: D58927: [ARM] Fixed an assumption of power-of-2 vector MVT.
Mar 4 2019, 3:19 PM · Restricted Project
tpr added a child revision for D58927: [ARM] Fixed an assumption of power-of-2 vector MVT: D58901: [CodeGen] Defined MVTs v3i32, v3f32, v5i32, v5f32.
Mar 4 2019, 3:19 PM · Restricted Project
tpr added reviewers for D58927: [ARM] Fixed an assumption of power-of-2 vector MVT: efriedma, echristo.
Mar 4 2019, 3:19 PM · Restricted Project
tpr updated the diff for D58899: [CodeGen] Prepare for introduction of v3 and v5 MVTs.

V2: Moved ARM and AMDGPU changes out to their own commits.

Mar 4 2019, 3:17 PM · Restricted Project
tpr created D58928: [AMDGPU] Prepare for introduction of v3 and v5 MVTs.
Mar 4 2019, 3:17 PM · Restricted Project
tpr created D58927: [ARM] Fixed an assumption of power-of-2 vector MVT.
Mar 4 2019, 3:17 PM · Restricted Project
tpr added inline comments to D58899: [CodeGen] Prepare for introduction of v3 and v5 MVTs.
Mar 4 2019, 11:59 AM · Restricted Project
tpr added reviewers for D58905: [AMDGPU] Use three- and five-dword result type in image ops: nhaehnle, dstuttard.
Mar 4 2019, 8:13 AM · Restricted Project
tpr added reviewers for D58904: [AMDGPU] Implemented dwordx3 variants of buffer/tbuffer load/store intrinsics: arsenm, rampitec, nhaehnle.
Mar 4 2019, 8:13 AM · Restricted Project
tpr added reviewers for D58903: [AMDGPU] Added v5i32 and v5f32 register classes: arsenm, rampitec, nhaehnle.
Mar 4 2019, 8:13 AM · Restricted Project
tpr added reviewers for D58902: [AMDGPU] Support for v3i32/v3f32: arsenm, rampitec, nhaehnle.
Mar 4 2019, 8:10 AM · Restricted Project
tpr added inline comments to D58904: [AMDGPU] Implemented dwordx3 variants of buffer/tbuffer load/store intrinsics.
Mar 4 2019, 8:08 AM · Restricted Project
tpr added reviewers for D58899: [CodeGen] Prepare for introduction of v3 and v5 MVTs: craig.topper, arsenm, efriedma, echristo.
Mar 4 2019, 7:40 AM · Restricted Project
tpr added a parent revision for D58906: InstCombineSimplifyDemanded: Allow v3 results for amdgcn buffer and image intrinsics: D58905: [AMDGPU] Use three- and five-dword result type in image ops.
Mar 4 2019, 7:31 AM · Restricted Project
tpr added a child revision for D58905: [AMDGPU] Use three- and five-dword result type in image ops: D58906: InstCombineSimplifyDemanded: Allow v3 results for amdgcn buffer and image intrinsics.
Mar 4 2019, 7:31 AM · Restricted Project
tpr added a child revision for D58903: [AMDGPU] Added v5i32 and v5f32 register classes: D58905: [AMDGPU] Use three- and five-dword result type in image ops.
Mar 4 2019, 7:30 AM · Restricted Project
tpr added a parent revision for D58905: [AMDGPU] Use three- and five-dword result type in image ops: D58903: [AMDGPU] Added v5i32 and v5f32 register classes.
Mar 4 2019, 7:30 AM · Restricted Project
tpr added a child revision for D58902: [AMDGPU] Support for v3i32/v3f32: D58904: [AMDGPU] Implemented dwordx3 variants of buffer/tbuffer load/store intrinsics.
Mar 4 2019, 7:30 AM · Restricted Project
tpr added a parent revision for D58904: [AMDGPU] Implemented dwordx3 variants of buffer/tbuffer load/store intrinsics: D58902: [AMDGPU] Support for v3i32/v3f32.
Mar 4 2019, 7:30 AM · Restricted Project
tpr added a child revision for D58902: [AMDGPU] Support for v3i32/v3f32: D58903: [AMDGPU] Added v5i32 and v5f32 register classes.
Mar 4 2019, 7:29 AM · Restricted Project
tpr added a parent revision for D58903: [AMDGPU] Added v5i32 and v5f32 register classes: D58902: [AMDGPU] Support for v3i32/v3f32.
Mar 4 2019, 7:29 AM · Restricted Project
tpr added a parent revision for D58902: [AMDGPU] Support for v3i32/v3f32: D58901: [CodeGen] Defined MVTs v3i32, v3f32, v5i32, v5f32.
Mar 4 2019, 7:27 AM · Restricted Project
tpr added a child revision for D58901: [CodeGen] Defined MVTs v3i32, v3f32, v5i32, v5f32: D58902: [AMDGPU] Support for v3i32/v3f32.
Mar 4 2019, 7:27 AM · Restricted Project