Page MenuHomePhabricator

kzhuravl (Konstantin Zhuravlyov)
User

Projects

User does not belong to any projects.

User Details

User Since
Feb 16 2016, 12:13 PM (277 w, 4 d)

Recent Activity

Fri, Jun 4

kzhuravl committed rG4d9f8527dbfb: CUDA/HIP: Change device-use-host-var.cu's NOT "external" check to include… (authored by kzhuravl).
CUDA/HIP: Change device-use-host-var.cu's NOT "external" check to include…
Fri, Jun 4, 10:10 AM
kzhuravl closed D103658: CUDA/HIP: Change device-use-host-var.cu's NOT "external" check to include "addrspace".
Fri, Jun 4, 10:10 AM · Restricted Project

Thu, Jun 3

kzhuravl updated the diff for D103658: CUDA/HIP: Change device-use-host-var.cu's NOT "external" check to include "addrspace".

Address review feedback.

Thu, Jun 3, 5:24 PM · Restricted Project
kzhuravl requested review of D103658: CUDA/HIP: Change device-use-host-var.cu's NOT "external" check to include "addrspace".
Thu, Jun 3, 4:31 PM · Restricted Project

Thu, May 20

kzhuravl accepted D102859: [NFC][AMDGPU] Add documentation for AMD Instinct MI100 accelerator.
Thu, May 20, 11:55 AM · Restricted Project

Wed, May 19

kzhuravl closed D102708: AMDGPU/NFC: Replace EF_AMDGPU_MACH_AMDGCN_RESERVED_0X3E with EF_AMDGPU_MACH_AMDGCN_GFX1034.
Wed, May 19, 8:32 AM · Restricted Project

Tue, May 18

kzhuravl added inline comments to D102306: Add gfx1034.
Tue, May 18, 2:06 PM · Restricted Project, Restricted Project, Restricted Project
kzhuravl committed rG4e297dcd18da: AMDGPU/Docs: Remove reserved MACH 0x3E (it is no longer reserved), sort MACHs… (authored by kzhuravl).
AMDGPU/Docs: Remove reserved MACH 0x3E (it is no longer reserved), sort MACHs…
Tue, May 18, 1:58 PM
kzhuravl committed rG0f544be244e3: AMDGPU/NFC: Replace EF_AMDGPU_MACH_AMDGCN_RESERVED_0X3E with… (authored by kzhuravl).
AMDGPU/NFC: Replace EF_AMDGPU_MACH_AMDGCN_RESERVED_0X3E with…
Tue, May 18, 12:12 PM
kzhuravl closed D102708: AMDGPU/NFC: Replace EF_AMDGPU_MACH_AMDGCN_RESERVED_0X3E with EF_AMDGPU_MACH_AMDGCN_GFX1034.
Tue, May 18, 12:12 PM · Restricted Project
kzhuravl requested review of D102708: AMDGPU/NFC: Replace EF_AMDGPU_MACH_AMDGCN_RESERVED_0X3E with EF_AMDGPU_MACH_AMDGCN_GFX1034.
Tue, May 18, 11:32 AM · Restricted Project

Mon, May 17

kzhuravl updated subscribers of D102306: Add gfx1034.

Is there documentation for the mapping from product names to gfx numbers?

See the Processors section of https://llvm.org/docs/AMDGPUUsage.html

It appears to be missing some GPUs. None of WX series are listed, for example.

Mon, May 17, 8:49 AM · Restricted Project, Restricted Project, Restricted Project

Thu, May 13

kzhuravl accepted D102432: [AMDGPU] Add support for architected flat scratch.

LGTM, but please run clang-format, thanks!

Thu, May 13, 6:10 PM · Restricted Project

May 3 2021

kzhuravl added a comment to D101304: AMDGPU/llvm-readobj: Add missing tests for note parsing/displaying.

Hi, llvm/test/tools/llvm-readobj/ELF/note-amd-valid-v3.s is failing for me.
/android0/llvm-project/llvm/build/bin/llvm-mc: error: : error: unable to get target for 'amdgcn-amd-amdhsa', see --version and --triple.
/android0/llvm-project/llvm/build/bin/llvm-readobj: error: '<stdin>': The file was not recognized as a valid object file
FileCheck error: '<stdin>' is empty.

May 3 2021, 6:48 AM · Restricted Project
kzhuravl added a comment to D101304: AMDGPU/llvm-readobj: Add missing tests for note parsing/displaying.

Hello,

The reland version of this patch for which I cannot find the differential of has broken LLVM::note-amd-valid-v2.test on PowerPC:

/home/buildbots/ppc64be-clang-test/clang-ppc64be/llvm/llvm/test/tools/llvm-readobj/ELF/note-amd-valid-v2.test:17:14: error: LLVM-NEXT: expected string not found in input
# LLVM-NEXT: AMD HSA Code Object Version: [Major: 2, Minor: 1]
             ^
<stdin>:15:68: note: scanning from here
 Type: NT_AMD_HSA_CODE_OBJECT_VERSION (AMD HSA Code Object Version)
                                                                   ^
<stdin>:16:2: note: possible intended match here
 AMD HSA Code Object Version: [Major: 33554432, Minor: 16777216]
 ^
Input file: <stdin>
Check file: /home/buildbots/ppc64be-clang-test/clang-ppc64be/llvm/llvm/test/tools/llvm-readobj/ELF/note-amd-valid-v2.test
-dump-input=help explains the following input dump.
Input was:
<<<<<<
           .
           .
           .
          10:  Offset: 0x40 
          11:  Size: 0x18 
          12:  Note { 
          13:  Owner: AMD 
          14:  Data size: 0x8 
          15:  Type: NT_AMD_HSA_CODE_OBJECT_VERSION (AMD HSA Code Object Version) 
next:17'0                                                                        X error: no match found
          16:  AMD HSA Code Object Version: [Major: 33554432, Minor: 16777216] 
next:17'0     ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
next:17'1      ?                                                                possible intended match

Seems like a small fix but if you could have a push for it soon that'd be great. Thanks! FYI @rksharma

Hi,

Reland patch fixed an issue if AMDGPU backend was not built, which was a one liner (I reverted original patch to not create the noise).

Seems like it is an endianness issue.

Unfortunately I don't have PowerPC, will adding these lines in note-amd-valid-v2.test mark it as XFAIL for you:

diff --git a/llvm/test/tools/llvm-readobj/ELF/note-amd-valid-v2.test b/llvm/test/tools/llvm-readobj/ELF/note-amd-valid-v2.test
index 688bbd50994c..f9cac212ce9f 100644
--- a/llvm/test/tools/llvm-readobj/ELF/note-amd-valid-v2.test
+++ b/llvm/test/tools/llvm-readobj/ELF/note-amd-valid-v2.test
@@ -1,6 +1,9 @@
 ## This test is checking the handling of valid note entries for AMDGPU code
 ## object v2.

+## Big endian not supported.
+# XFAIL: host-byteorder-big-endian
+
 # RUN: yaml2obj %s -o %t.o
 # RUN: llvm-readobj --notes %t.o | FileCheck %s --match-full-lines --check-prefix=LLVM
 # RUN: llvm-readelf --notes %t.o | FileCheck %s --match-full-lines --check-prefix=GNU

?

That would fix it yes, thank you!
Another possible solution would be to add a BE specific runline, but I'm not really familiar with the AMD test files so it's just a suggestion.

May 3 2021, 6:46 AM · Restricted Project
kzhuravl committed rG2055cc8ef4b9: AMDGPU: XFAIL LLVM::note-amd-valid-v2.test for big endian (authored by kzhuravl).
AMDGPU: XFAIL LLVM::note-amd-valid-v2.test for big endian
May 3 2021, 6:45 AM
kzhuravl added a comment to D101304: AMDGPU/llvm-readobj: Add missing tests for note parsing/displaying.

Hello,

The reland version of this patch for which I cannot find the differential of has broken LLVM::note-amd-valid-v2.test on PowerPC:

/home/buildbots/ppc64be-clang-test/clang-ppc64be/llvm/llvm/test/tools/llvm-readobj/ELF/note-amd-valid-v2.test:17:14: error: LLVM-NEXT: expected string not found in input
# LLVM-NEXT: AMD HSA Code Object Version: [Major: 2, Minor: 1]
             ^
<stdin>:15:68: note: scanning from here
 Type: NT_AMD_HSA_CODE_OBJECT_VERSION (AMD HSA Code Object Version)
                                                                   ^
<stdin>:16:2: note: possible intended match here
 AMD HSA Code Object Version: [Major: 33554432, Minor: 16777216]
 ^
Input file: <stdin>
Check file: /home/buildbots/ppc64be-clang-test/clang-ppc64be/llvm/llvm/test/tools/llvm-readobj/ELF/note-amd-valid-v2.test
-dump-input=help explains the following input dump.
Input was:
<<<<<<
           .
           .
           .
          10:  Offset: 0x40 
          11:  Size: 0x18 
          12:  Note { 
          13:  Owner: AMD 
          14:  Data size: 0x8 
          15:  Type: NT_AMD_HSA_CODE_OBJECT_VERSION (AMD HSA Code Object Version) 
next:17'0                                                                        X error: no match found
          16:  AMD HSA Code Object Version: [Major: 33554432, Minor: 16777216] 
next:17'0     ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
next:17'1      ?                                                                possible intended match

Seems like a small fix but if you could have a push for it soon that'd be great. Thanks! FYI @rksharma

May 3 2021, 6:11 AM · Restricted Project

May 2 2021

kzhuravl added a reverting change for rG54aad6365951: Revert "AMDGPU/llvm-readobj: Add missing tests for note parsing/displaying": rG94aaf3ddd96f: Reland "AMDGPU/llvm-readobj: Add missing tests for note parsing/displaying".
May 2 2021, 7:56 PM
kzhuravl committed rG94aaf3ddd96f: Reland "AMDGPU/llvm-readobj: Add missing tests for note parsing/displaying" (authored by kzhuravl).
Reland "AMDGPU/llvm-readobj: Add missing tests for note parsing/displaying"
May 2 2021, 7:56 PM

Apr 30 2021

kzhuravl added a reverting change for D101304: AMDGPU/llvm-readobj: Add missing tests for note parsing/displaying: rG54aad6365951: Revert "AMDGPU/llvm-readobj: Add missing tests for note parsing/displaying".
Apr 30 2021, 11:46 AM · Restricted Project
kzhuravl added a reverting change for rGc9c4676a458b: AMDGPU/llvm-readobj: Add missing tests for note parsing/displaying: rG54aad6365951: Revert "AMDGPU/llvm-readobj: Add missing tests for note parsing/displaying".
Apr 30 2021, 11:46 AM
kzhuravl committed rG54aad6365951: Revert "AMDGPU/llvm-readobj: Add missing tests for note parsing/displaying" (authored by kzhuravl).
Revert "AMDGPU/llvm-readobj: Add missing tests for note parsing/displaying"
Apr 30 2021, 11:46 AM
kzhuravl added a comment to D101304: AMDGPU/llvm-readobj: Add missing tests for note parsing/displaying.

I have reverted the change while I am testing the fix.

Apr 30 2021, 11:46 AM · Restricted Project
kzhuravl added a comment to D101304: AMDGPU/llvm-readobj: Add missing tests for note parsing/displaying.

Thanks, I am working on a fix.

Apr 30 2021, 11:29 AM · Restricted Project
kzhuravl committed rGc9c4676a458b: AMDGPU/llvm-readobj: Add missing tests for note parsing/displaying (authored by kzhuravl).
AMDGPU/llvm-readobj: Add missing tests for note parsing/displaying
Apr 30 2021, 8:19 AM
kzhuravl closed D101304: AMDGPU/llvm-readobj: Add missing tests for note parsing/displaying.
Apr 30 2021, 8:19 AM · Restricted Project
kzhuravl added a comment to D101304: AMDGPU/llvm-readobj: Add missing tests for note parsing/displaying.

@jhenderson , do you have any additional comments?

Apr 30 2021, 6:55 AM · Restricted Project

Apr 29 2021

kzhuravl added a comment to D101304: AMDGPU/llvm-readobj: Add missing tests for note parsing/displaying.

+ @t-tye to maybe look at note tests...

Apr 29 2021, 1:24 PM · Restricted Project
kzhuravl added a reviewer for D101304: AMDGPU/llvm-readobj: Add missing tests for note parsing/displaying: t-tye.
Apr 29 2021, 1:24 PM · Restricted Project
kzhuravl updated the diff for D101304: AMDGPU/llvm-readobj: Add missing tests for note parsing/displaying.

clang-format.

Apr 29 2021, 12:04 PM · Restricted Project

Apr 28 2021

kzhuravl updated the diff for D101304: AMDGPU/llvm-readobj: Add missing tests for note parsing/displaying.

Address review feedback.

Apr 28 2021, 7:05 AM · Restricted Project

Apr 27 2021

kzhuravl updated the diff for D101304: AMDGPU/llvm-readobj: Add missing tests for note parsing/displaying.

Address review feedback.

Apr 27 2021, 10:02 AM · Restricted Project
kzhuravl added inline comments to D101304: AMDGPU/llvm-readobj: Add missing tests for note parsing/displaying.
Apr 27 2021, 10:02 AM · Restricted Project

Apr 26 2021

kzhuravl added a comment to D95638: AMDGPU: Add target id and code object v4 support.

https://reviews.llvm.org/D101304

Apr 26 2021, 9:17 AM · Restricted Project
kzhuravl added a comment to D101304: AMDGPU/llvm-readobj: Add missing tests for note parsing/displaying.

I believe this testing covers all cases (both valid and invalid) of note parsing/displaying for llvm-readobj

Apr 26 2021, 9:16 AM · Restricted Project
kzhuravl requested review of D101304: AMDGPU/llvm-readobj: Add missing tests for note parsing/displaying.
Apr 26 2021, 9:15 AM · Restricted Project
kzhuravl added a comment to D95638: AMDGPU: Add target id and code object v4 support.

@kzhuravl, are my comments going to be addressed?

Apr 26 2021, 6:35 AM · Restricted Project

Apr 16 2021

kzhuravl accepted D100679: [AMDGPU] Enforce that gfx802/803/805 do not support XNACK.

Thanks, this matches docs and TD file in AMDGPU backend.

Apr 16 2021, 12:33 PM · Restricted Project

Apr 15 2021

kzhuravl accepted D100589: [AMDGPU] Add new EmitDstSel field to VOPPofile. NFC..
Apr 15 2021, 12:03 PM · Restricted Project
kzhuravl accepted D100409: [AMDGPU] Factor out predicate FmaakFmamkF32Insts.

LGTM

Apr 15 2021, 11:52 AM · Restricted Project

Apr 8 2021

kzhuravl committed rG4fae63c612a7: AMDGPU: Add gfx90c support to code object v2 for backwards compatibility (authored by kzhuravl).
AMDGPU: Add gfx90c support to code object v2 for backwards compatibility
Apr 8 2021, 1:55 PM
kzhuravl closed D100126: AMDGPU: Add gfx90c support to code object v2 for backwards compatibility.
Apr 8 2021, 1:55 PM · Restricted Project
kzhuravl accepted D100072: [AMDGPU] Allow -amdgpu-unsafe-fp-atomics to ignore denorm mode.

LGTM

Apr 8 2021, 12:37 PM · Restricted Project, Restricted Project
kzhuravl updated the diff for D100126: AMDGPU: Add gfx90c support to code object v2 for backwards compatibility.

Address review feedback.

Apr 8 2021, 12:06 PM · Restricted Project
kzhuravl requested review of D100126: AMDGPU: Add gfx90c support to code object v2 for backwards compatibility.
Apr 8 2021, 10:05 AM · Restricted Project

Apr 6 2021

kzhuravl committed rG844012940e17: AMDGPU: Add isBranch=1 to SOPP branch instructions (authored by kzhuravl).
AMDGPU: Add isBranch=1 to SOPP branch instructions
Apr 6 2021, 7:59 AM
kzhuravl closed D99955: AMDGPU: Add isBranch=1 to SOPP branch instructions.
Apr 6 2021, 7:59 AM · Restricted Project
kzhuravl added reviewers for D99955: AMDGPU: Add isBranch=1 to SOPP branch instructions: Joe_Nash, arsenm.
Apr 6 2021, 7:13 AM · Restricted Project
kzhuravl requested review of D99955: AMDGPU: Add isBranch=1 to SOPP branch instructions.
Apr 6 2021, 7:12 AM · Restricted Project

Mar 24 2021

kzhuravl committed rG4f2830313353: AMDGPU/LLD: Add target id and code object v4 support to linker (authored by kzhuravl).
AMDGPU/LLD: Add target id and code object v4 support to linker
Mar 24 2021, 10:41 AM
kzhuravl closed D95811: AMDGPU/LLD: Add target id and code object v4 support to linker.
Mar 24 2021, 10:41 AM · Restricted Project
kzhuravl committed rGf4ace6373747: AMDGPU: Add target id and code object v4 support (authored by kzhuravl).
AMDGPU: Add target id and code object v4 support
Mar 24 2021, 8:54 AM
kzhuravl closed D95638: AMDGPU: Add target id and code object v4 support.
Mar 24 2021, 8:54 AM · Restricted Project

Mar 22 2021

kzhuravl accepted D99122: [AMDGPU] Reserve ELF code.

Thanks.

Mar 22 2021, 8:48 PM · Restricted Project
kzhuravl requested changes to D99122: [AMDGPU] Reserve ELF code.

you also should add reserved number to docs.

Mar 22 2021, 4:16 PM · Restricted Project
kzhuravl added a comment to D99122: [AMDGPU] Reserve ELF code.

probably update the title to reflect there is more than one change in the commit?

Mar 22 2021, 4:14 PM · Restricted Project

Mar 18 2021

kzhuravl accepted D98731: [AMDGPU] Support SCC on buffer atomics.

LGTM

Mar 18 2021, 9:54 AM · Restricted Project

Mar 16 2021

kzhuravl added a comment to D95638: AMDGPU: Add target id and code object v4 support.

ping.

Mar 16 2021, 7:44 PM · Restricted Project

Mar 11 2021

kzhuravl accepted D96469: [AMDGPU] Use single cache policy operand.

Not sure if @arsenm has any additional comments, but it LGTM. Should simplify further merges downstream drastically, thanks!

Mar 11 2021, 5:36 PM · Restricted Project

Mar 9 2021

kzhuravl accepted D98221: [AMDGPU] Disable SCC bit on fp atomics.

LGTM, thanks.

Mar 9 2021, 3:42 PM · Restricted Project
kzhuravl added inline comments to D98221: [AMDGPU] Disable SCC bit on fp atomics.
Mar 9 2021, 3:10 PM · Restricted Project
kzhuravl added a comment to D95638: AMDGPU: Add target id and code object v4 support.

ping.

Mar 9 2021, 12:02 PM · Restricted Project

Mar 4 2021

kzhuravl updated the diff for D95638: AMDGPU: Add target id and code object v4 support.

Rebase and address review feedback.

Mar 4 2021, 12:06 PM · Restricted Project
kzhuravl added inline comments to D95638: AMDGPU: Add target id and code object v4 support.
Mar 4 2021, 12:03 PM · Restricted Project

Mar 3 2021

kzhuravl added a comment to D95638: AMDGPU: Add target id and code object v4 support.

ping.

Mar 3 2021, 4:42 AM · Restricted Project

Feb 27 2021

kzhuravl accepted D97598: [NFC][AMDGPU] Document the AMDGPU target feature defaults.

LGTM

Feb 27 2021, 10:14 AM · Restricted Project

Feb 25 2021

kzhuravl accepted D97420: [AMDGPU] require s-memtime-inst for __builtin_amdgcn_s_memtime.

LGTM

Feb 25 2021, 7:41 AM · Restricted Project

Feb 24 2021

kzhuravl added inline comments to D97392: [amdgpu] Atomic should be source of divergence..
Feb 24 2021, 11:14 AM · Restricted Project
kzhuravl accepted D97377: [AMDGPU] Add a bit more gfx90a test coverage.

Thanks!

Feb 24 2021, 7:58 AM · Restricted Project
kzhuravl added a comment to D95619: [AMDGPU] Add more PAL metadata register names.

I am not familiar with graphics side much, but is there any reason to not use COMPUTE_PGM_RSRC* registers from https://github.com/llvm/llvm-project/blob/main/llvm/include/llvm/Support/AMDHSAKernelDescriptor.h#L130 ?

Feb 24 2021, 7:55 AM · Restricted Project
kzhuravl added inline comments to D97069: [clang] SimpleMFlag helper in Options.td.
Feb 24 2021, 6:50 AM · Restricted Project

Feb 23 2021

kzhuravl added a comment to D95638: AMDGPU: Add target id and code object v4 support.

ping.

Feb 23 2021, 4:16 PM · Restricted Project

Feb 19 2021

kzhuravl added a comment to D97069: [clang] SimpleMFlag helper in Options.td.

If folks are ok with this approach, we probably will need to update other targets' *m* flags (e.g. -m[no-]unimplemented_simd128, -m[no-]fix_cortex_a53_835769, etc.)

Feb 19 2021, 11:27 AM · Restricted Project

Feb 18 2021

kzhuravl added inline comments to D96906: [AMDGPU] gfx90a support.
Feb 18 2021, 6:20 PM · Restricted Project, Restricted Project
kzhuravl updated the diff for D95638: AMDGPU: Add target id and code object v4 support.

Rebase.

Feb 18 2021, 6:02 PM · Restricted Project
kzhuravl committed rG71d1f785a5a6: AMDGPU/ELF: Sort MACHs by value and add missing reserved MACHs (authored by kzhuravl).
AMDGPU/ELF: Sort MACHs by value and add missing reserved MACHs
Feb 18 2021, 5:47 PM
kzhuravl closed D97010: AMDGPU/ELF: Sort MACHs by value and add missing reserved MACHs.
Feb 18 2021, 5:46 PM · Restricted Project
kzhuravl added inline comments to D96906: [AMDGPU] gfx90a support.
Feb 18 2021, 5:39 PM · Restricted Project, Restricted Project
kzhuravl added inline comments to D96906: [AMDGPU] gfx90a support.
Feb 18 2021, 5:37 PM · Restricted Project, Restricted Project
kzhuravl added inline comments to D96906: [AMDGPU] gfx90a support.
Feb 18 2021, 5:26 PM · Restricted Project, Restricted Project
kzhuravl added inline comments to D96906: [AMDGPU] gfx90a support.
Feb 18 2021, 5:24 PM · Restricted Project, Restricted Project
kzhuravl added inline comments to D96906: [AMDGPU] gfx90a support.
Feb 18 2021, 5:20 PM · Restricted Project, Restricted Project
kzhuravl added inline comments to D96906: [AMDGPU] gfx90a support.
Feb 18 2021, 5:05 PM · Restricted Project, Restricted Project
kzhuravl updated the diff for D97010: AMDGPU/ELF: Sort MACHs by value and add missing reserved MACHs.

Update docs.

Feb 18 2021, 5:02 PM · Restricted Project
kzhuravl requested review of D97010: AMDGPU/ELF: Sort MACHs by value and add missing reserved MACHs.
Feb 18 2021, 5:00 PM · Restricted Project
kzhuravl updated the diff for D95638: AMDGPU: Add target id and code object v4 support.

Address @rampitec 's comments.

Feb 18 2021, 1:51 PM · Restricted Project
kzhuravl added a comment to D96906: [AMDGPU] gfx90a support.

The point is that nobody upstream even got a chance to chime in.

Feb 18 2021, 1:49 PM · Restricted Project, Restricted Project
kzhuravl accepted D96989: [AMDGPU] Correct gfx90c feature list.

LGTM

Feb 18 2021, 12:38 PM · Restricted Project
kzhuravl added a comment to D96989: [AMDGPU] Correct gfx90c feature list.

Looks like we have forced FeatureXNACK and forgot FeatureMadMacF32Insts.

Feb 18 2021, 12:38 PM · Restricted Project
kzhuravl updated the diff for D95638: AMDGPU: Add target id and code object v4 support.

Address review feedback.

Feb 18 2021, 12:31 PM · Restricted Project
kzhuravl added a comment to D95638: AMDGPU: Add target id and code object v4 support.

I've only looked at the llvm-readobj stuff: there are a very large number of changes to that tool in this change, but no direct testing (i.e. tests under llvm\test\llvm-readobj) that has been changed. I'm guessing it's not all covered by existing direct testing of the tool?

It is not covered by the direct testing of the tool (no tests in llvm\test\llvm-readobj), but has a very good coverage in llvm/test/CodeGen/AMDGPU.

Usually we have testing for llvm-readobj behaviour in test/tools/llvm-readobj, so that it can be kept independent of other testing, and so that changes in other areas don't impact test coverage for llvm-readobj. It also makes it easier to keep the tests focused on individual features. For example, what testing is there for EM_AMDGPU objects with an unrecognised ABI Version, or other aspects of that switch?

Feb 18 2021, 12:30 PM · Restricted Project
kzhuravl committed rG622652bf735c: AMDGPU: Fix checks in llvm.amdgcn.workitem.id.ll (authored by kzhuravl).
AMDGPU: Fix checks in llvm.amdgcn.workitem.id.ll
Feb 18 2021, 8:56 AM
kzhuravl closed D96967: AMDGPU: Fix checks in llvm.amdgcn.workitem.id.ll.
Feb 18 2021, 8:56 AM · Restricted Project
kzhuravl added inline comments to D96906: [AMDGPU] gfx90a support.
Feb 18 2021, 8:49 AM · Restricted Project, Restricted Project
kzhuravl requested review of D96967: AMDGPU: Fix checks in llvm.amdgcn.workitem.id.ll.
Feb 18 2021, 8:48 AM · Restricted Project

Feb 17 2021

kzhuravl added a comment to D95638: AMDGPU: Add target id and code object v4 support.

I've only looked at the llvm-readobj stuff: there are a very large number of changes to that tool in this change, but no direct testing (i.e. tests under llvm\test\llvm-readobj) that has been changed. I'm guessing it's not all covered by existing direct testing of the tool?

It is not covered by the direct testing of the tool (no tests in llvm\test\llvm-readobj), but has a very good coverage in llvm/test/CodeGen/AMDGPU.

Usually we have testing for llvm-readobj behaviour in test/tools/llvm-readobj, so that it can be kept independent of other testing, and so that changes in other areas don't impact test coverage for llvm-readobj. It also makes it easier to keep the tests focused on individual features. For example, what testing is there for EM_AMDGPU objects with an unrecognised ABI Version, or other aspects of that switch?

Feb 17 2021, 6:10 PM · Restricted Project
kzhuravl accepted D96906: [AMDGPU] gfx90a support.

LGTM

Feb 17 2021, 3:59 PM · Restricted Project, Restricted Project
kzhuravl abandoned D96728: AMDGPU: Update backend-resource-limit-diagnostics.cl test to not use -emit-codegen-only option.
Feb 17 2021, 11:35 AM

Feb 15 2021

kzhuravl updated the diff for D95638: AMDGPU: Add target id and code object v4 support.

Rebase and remove streamer check in AMDGPUAsmPrinter.cpp

Feb 15 2021, 12:27 PM · Restricted Project
kzhuravl added inline comments to D95638: AMDGPU: Add target id and code object v4 support.
Feb 15 2021, 12:26 PM · Restricted Project