21 Commits

Author SHA1 Message Date
Konstantin Zhuravlyov
f49ec0fc3f [AMDGPU] Do not emit isa info as code object metadata
- It was decided to expose this information through other means (rocr)

Differential Revision: https://reviews.llvm.org/D30970


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@298560 91177308-0d34-0410-b5e6-96231b3b80d8
2017-03-22 23:27:09 +00:00
Konstantin Zhuravlyov
93cb3da5a9 [AMDGPU] Emit kernel code properties as code object metadata
- These are not required for low level runtime

Differential Revision: https://reviews.llvm.org/D29949


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@298556 91177308-0d34-0410-b5e6-96231b3b80d8
2017-03-22 22:54:39 +00:00
Konstantin Zhuravlyov
1c4f1852fb [AMDGPU] Restructure code object metadata creation
- Rename runtime metadata -> code object metadata
  - Make metadata not flow
  - Switch enums to use ScalarEnumerationTraits
  - Cleanup and move AMDGPUCodeObjectMetadata.h to AMDGPU/MCTargetDesc
  - Introduce in-memory representation for attributes
  - Code object metadata streamer
  - Create metadata for isa and printf during EmitStartOfAsmFile
  - Create metadata for kernel during EmitFunctionBodyStart
  - Finalize and emit metadata to .note during EmitEndOfAsmFile
  - Other minor improvements/bug fixes

Differential Revision: https://reviews.llvm.org/D29948



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@298552 91177308-0d34-0410-b5e6-96231b3b80d8
2017-03-22 22:32:22 +00:00
Yaxun Liu
ab0e0e2181 Rename PT_NOTE namespace name used in AMDGPUPTNote.h
Patch by Guansong Zhang.

Differential Revision: https://reviews.llvm.org/D30750


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@297498 91177308-0d34-0410-b5e6-96231b3b80d8
2017-03-10 19:35:43 +00:00
Konstantin Zhuravlyov
9995ddddac [AMDGPU] Runtime metadata fixes:
- Verify that runtime metadata is actually valid runtime metadata when assembling, otherwise we could accept the following when assembling, but ocl runtime will reject it:
    .amdgpu_runtime_metadata
    { amd.MDVersion: [ 2, 1 ], amd.RandomUnknownKey, amd.IsaInfo: ...
  - Make IsaInfo optional, and always emit it.

Differential Revision: https://reviews.llvm.org/D30349


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@296324 91177308-0d34-0410-b5e6-96231b3b80d8
2017-02-27 07:55:17 +00:00
Matt Arsenault
dd3604df31 AMDGPU: Fix trailing whitespace
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@294694 91177308-0d34-0410-b5e6-96231b3b80d8
2017-02-10 02:42:31 +00:00
Konstantin Zhuravlyov
017228cd76 [AMDGPU] Add target information that is required by tools to metadata
Differential Revision: https://reviews.llvm.org/D28760#fb670e28


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@294449 91177308-0d34-0410-b5e6-96231b3b80d8
2017-02-08 14:05:23 +00:00
Benjamin Kramer
1fb85c6675 Apply clang-tidy's performance-unnecessary-value-param to LLVM.
With some minor manual fixes for using function_ref instead of
std::function. No functional change intended.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@291904 91177308-0d34-0410-b5e6-96231b3b80d8
2017-01-13 14:39:03 +00:00
Sam Kolton
a8a17674a4 AMDGPU: [AMDGPU] Assembler: add .hsa_code_object_metadata directive for functime metadata V2.0
Summary:
Added pair of directives .hsa_code_object_metadata/.end_hsa_code_object_metadata.
Between them user can put YAML string that would be directly put to the generated note. E.g.:
'''
.hsa_code_object_metadata
    {
        amd.MDVersion: [ 2, 0 ]
    }
.end_hsa_code_object_metadata
'''
Based on D25046

Reviewers: vpykhtin, nhaustov, yaxunl, tstellarAMD

Subscribers: arsenm, kzhuravl, wdng, nhaehnle, mgorny, tony-tye

Differential Revision: https://reviews.llvm.org/D27619

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@290097 91177308-0d34-0410-b5e6-96231b3b80d8
2016-12-19 11:43:15 +00:00
Yaxun Liu
d2fea82b59 AMDGPU: Emit runtime metadata version 2 as YAML
Differential Revision: https://reviews.llvm.org/D25046


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@289674 91177308-0d34-0410-b5e6-96231b3b80d8
2016-12-14 17:16:52 +00:00
Sam Kolton
45849f5ed4 [AMDGPU] TargetStreamer: Fix .note section name
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@286591 91177308-0d34-0410-b5e6-96231b3b80d8
2016-11-11 13:41:52 +00:00
Yaxun Liu
a2ee7d2991 AMDGPU: Emit runtime metadata as a note element in .note section
Currently runtime metadata is emitted as an ELF section with name .AMDGPU.runtime_metadata.

However there is a standard way to convey vendor specific information about how to run an ELF binary, which is called vendor-specific note element (http://www.netbsd.org/docs/kernel/elf-notes.html).

This patch lets AMDGPU backend emits runtime metadata as a note element in .note section.

Differential Revision: https://reviews.llvm.org/D25781


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@286502 91177308-0d34-0410-b5e6-96231b3b80d8
2016-11-10 21:18:49 +00:00
Konstantin Zhuravlyov
37962abba1 [AMDGPU] Make note record name a static const member of target streamer
Differential Revision: https://reviews.llvm.org/D25746


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@284760 91177308-0d34-0410-b5e6-96231b3b80d8
2016-10-20 18:22:36 +00:00
Konstantin Zhuravlyov
18560f1ee0 [AMDGPU] Mark .note section SHF_ALLOC so lld creates a segment for it
Differential Revision: https://reviews.llvm.org/D25694


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@284435 91177308-0d34-0410-b5e6-96231b3b80d8
2016-10-17 22:40:15 +00:00
Sam Kolton
442deaa85b [AMDGPU] Assembler: rename amd_kernel_code_t asm names according to spec
Summary:
Also removed duplicate code from AMDGPUTargetAsmStreamer.
This change only change how amd_kernel_code_t is parsed and printed. No variable names are changed.

Reviewers: vpykhtin, tstellarAMD

Subscribers: arsenm, wdng, nhaehnle

Differential Revision: https://reviews.llvm.org/D24296

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@281028 91177308-0d34-0410-b5e6-96231b3b80d8
2016-09-09 10:08:02 +00:00
Tom Stellard
66eb4d17bb AMDGPU/SI: Add support for AMD code object version 2.
Summary:
Version 2 is now the default.  If you want to emit version 1, use
the amdgcn--amdhsa-amdcov1 triple.

Reviewers: arsenm, kzhuravl

Subscribers: arsenm, llvm-commits

Differential Revision: http://reviews.llvm.org/D19283

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@268647 91177308-0d34-0410-b5e6-96231b3b80d8
2016-05-05 17:03:33 +00:00
Tom Stellard
27cbe8f717 AMDGPU/SI: Correctly emit agent global segment variables when targeting HSA
Differential Revision: http://reviews.llvm.org/D14508

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@254540 91177308-0d34-0410-b5e6-96231b3b80d8
2015-12-02 19:47:57 +00:00
Tom Stellard
65cad952e4 AMDGPU/SI: Emit HSA kernels with symbol type STT_AMDGPU_HSA_KERNEL
Reviewers: arsenm

Subscribers: arsenm, llvm-commits

Differential Revision: http://reviews.llvm.org/D13804

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@252291 91177308-0d34-0410-b5e6-96231b3b80d8
2015-11-06 11:45:14 +00:00
Tom Stellard
1566e71dbd AMDGPU/SI: Use .hsatext section instead of .text for HSA
Reviewers: arsenm, grosbach, rafael

Subscribers: arsenm, llvm-commits

Differential Revision: http://reviews.llvm.org/D12424

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@248619 91177308-0d34-0410-b5e6-96231b3b80d8
2015-09-25 21:41:28 +00:00
Tom Stellard
4a888086a4 AMDGPU/SI: Update amd_kernel_code_t definition and add assembler support
Reviewers: arsenm

Subscribers: llvm-commits

Differential Revision: http://reviews.llvm.org/D10772

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@240839 91177308-0d34-0410-b5e6-96231b3b80d8
2015-06-26 21:58:31 +00:00
Tom Stellard
ac1a45e511 AMDGPU/SI: Add hsa code object directives
Reviewers: arsenm

Subscribers: llvm-commits

Differential Revision: http://reviews.llvm.org/D10757

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@240831 91177308-0d34-0410-b5e6-96231b3b80d8
2015-06-26 21:15:07 +00:00