This is an archive of the discontinued LLVM Phabricator instance.

Differential D97386

update AMDGPU _Float16 support in clang doc
ClosedPublic

Authored by yaxunl on Feb 24 2021, 7:28 AM.

Details

Reviewers
foad
arsenm
rampitec
Commits
rG392fd3f1bf9f: update AMDGPU _Float16 support in clang doc

Diff Detail

Unit TestsFailed

TimeTest
1,160 msx64 debian > UBSan-AddressSanitizer-lld-x86_64.TestCases/Misc::coverage-levels.cpp
2,400 msx64 debian > UBSan-AddressSanitizer-x86_64.TestCases/Misc::coverage-levels.cpp
1,130 msx64 debian > UBSan-MemorySanitizer-lld-x86_64.TestCases/Misc::coverage-levels.cpp
2,250 msx64 debian > UBSan-MemorySanitizer-x86_64.TestCases/Misc::coverage-levels.cpp
1,090 msx64 debian > UBSan-Standalone-lld-x86_64.TestCases/Misc::coverage-levels.cpp
View Full Test Results (6 Failed)

Event Timeline

yaxunl created this revision.Feb 24 2021, 7:28 AM
Herald added subscribers: t-tye, tpr, dstuttard, kzhuravl. · View Herald TranscriptFeb 24 2021, 7:28 AM
yaxunl requested review of this revision.Feb 24 2021, 7:28 AM
Herald added a subscriber: wdng. · View Herald TranscriptFeb 24 2021, 7:28 AM
Harbormaster completed remote builds in B90610: Diff 326088.Feb 24 2021, 8:56 AM
arsenm accepted this revision.Feb 24 2021, 12:07 PM
This revision is now accepted and ready to land.Feb 24 2021, 12:07 PM
This revision was landed with ongoing or failed builds.Feb 24 2021, 4:47 PM
Closed by commit rG392fd3f1bf9f: update AMDGPU _Float16 support in clang doc (authored by yaxunl). · Explain Why
This revision was automatically updated to reflect the committed changes.
yaxunl added a commit: rG392fd3f1bf9f: update AMDGPU _Float16 support in clang doc.
Herald added a project: Restricted Project. · View Herald TranscriptFeb 24 2021, 4:47 PM

Revision Contents

PathSize
clang/
docs/
1 line

Diff 326088

clang/docs/LanguageExtensions.rst

Show First 20 Lines • Show All 518 Lines • ▼ Show 20 Lines
``_Float16`` and ``__bf16``. These types are supported in all language modes. ``_Float16`` and ``__bf16``. These types are supported in all language modes.
``__fp16`` is supported on every target, as it is purely a storage format; see below. ``__fp16`` is supported on every target, as it is purely a storage format; see below.
``_Float16`` is currently only supported on the following targets, with further ``_Float16`` is currently only supported on the following targets, with further
targets pending ABI standardization: targets pending ABI standardization:
* 32-bit ARM * 32-bit ARM
* 64-bit ARM (AArch64) * 64-bit ARM (AArch64)
* AMDGPU
* SPIR * SPIR
``_Float16`` will be supported on more targets as they define ABIs for it. ``_Float16`` will be supported on more targets as they define ABIs for it.
``__bf16`` is purely a storage format; it is currently only supported on the following targets: ``__bf16`` is purely a storage format; it is currently only supported on the following targets:
* 32-bit ARM * 32-bit ARM
* 64-bit ARM (AArch64) * 64-bit ARM (AArch64)
▲ Show 20 Lines • Show All 3,255 Lines • Show Last 20 Lines