This is an archive of the discontinued LLVM Phabricator instance.

Differential D81247

Fix a typo in AMDGPU docs
ClosedPublic

Authored by madhur13490 on Jun 5 2020, 3:24 AM.

Details

Reviewers
t-tye
arsenm
Commits
rGbca413b036bf: Fix a typo in AMDGPU docs

Diff Detail

Event Timeline

madhur13490 created this revision.Jun 5 2020, 3:24 AM
Herald added a project: Restricted Project. · View Herald TranscriptJun 5 2020, 3:24 AM
Herald added subscribers: llvm-commits, kerbowa, tpr and 6 others. · View Herald Transcript
Harbormaster failed remote builds in B59213: Diff 268729!Jun 5 2020, 4:22 AM
arsenm accepted this revision.Jun 5 2020, 6:08 AM
This revision is now accepted and ready to land.Jun 5 2020, 6:08 AM
Closed by commit rGbca413b036bf: Fix a typo in AMDGPU docs (authored by madhur13490). · Explain WhyJun 5 2020, 6:37 AM
This revision was automatically updated to reflect the committed changes.

Revision Contents

PathSize
llvm/
docs/
2 lines

Diff 268774

llvm/docs/AMDGPUUsage.rst

  • This file is larger than 256 KB, so syntax highlighting is disabled by default.
Show First 20 Lines • Show All 3,845 Lines • ▼ Show 20 Lines
2. Work-group Id registers X, Y, Z are set by ADC which supports any 2. Work-group Id registers X, Y, Z are set by ADC which supports any
combination including none. combination including none.
3. Scratch Wavefront Offset is set by SPI in a per wavefront basis which is why 3. Scratch Wavefront Offset is set by SPI in a per wavefront basis which is why
its value cannot be included with the flat scratch init value which is per its value cannot be included with the flat scratch init value which is per
queue. queue.
4. The VGPRs are set by SPI which only supports specifying either (X), (X, Y) 4. The VGPRs are set by SPI which only supports specifying either (X), (X, Y)
or (X, Y, Z). or (X, Y, Z).
Flat Scratch register pair are adjacent SGRRs so they can be moved as a 64-bit Flat Scratch register pair are adjacent SGPRs so they can be moved as a 64-bit
value to the hardware required SGPRn-3 and SGPRn-4 respectively. value to the hardware required SGPRn-3 and SGPRn-4 respectively.
The global segment can be accessed either using buffer instructions (GFX6 which The global segment can be accessed either using buffer instructions (GFX6 which
has V# 64-bit address support), flat instructions (GFX7-GFX10), or global has V# 64-bit address support), flat instructions (GFX7-GFX10), or global
instructions (GFX9-GFX10). instructions (GFX9-GFX10).
If buffer operations are used, then the compiler can generate a V# with the If buffer operations are used, then the compiler can generate a V# with the
following properties: following properties:
▲ Show 20 Lines • Show All 3,970 Lines • Show Last 20 Lines