aboutsummaryrefslogtreecommitdiff
path: root/llvm/lib/CodeGen/TargetLoweringObjectFileImpl.cpp
diff options
context:
space:
mode:
authorAndrew Savonichev <andrew.savonichev@gmail.com>2022-04-10 22:33:48 +0300
committerAndrew Savonichev <andrew.savonichev@gmail.com>2022-04-14 17:07:53 +0300
commitb6183a57a10b03bdad83e4bef02990673c155011 (patch)
treeb3d02d89b705c4a8d4e2688507176981dbc8e603 /llvm/lib/CodeGen/TargetLoweringObjectFileImpl.cpp
parent32949401a86aea1cfc0a04bef566c2af30c82e39 (diff)
downloadllvm-b6183a57a10b03bdad83e4bef02990673c155011.zip
llvm-b6183a57a10b03bdad83e4bef02990673c155011.tar.gz
llvm-b6183a57a10b03bdad83e4bef02990673c155011.tar.bz2
[NVPTX] Fix barrier.ll LIT test
The second parameter should be a multiple of the warp size (32). PTX ISA spec, s9.7.12.1. Parallel Synchronization and Communication Instructions: bar, barrier barrier.sync{.aligned} a{, b}; Operand b specifies the number of threads participating in the barrier. If no thread count is specified, all threads in the CTA participate in the barrier. When specifying a thread count, the value must be a multiple of the warp size. Differential Revision: https://reviews.llvm.org/D123470
Diffstat (limited to 'llvm/lib/CodeGen/TargetLoweringObjectFileImpl.cpp')
0 files changed, 0 insertions, 0 deletions