projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: cb30590) | patch
[X86] Make CMPXCHG16B feature imply CMPXCHG8B feature.
authorCraig Topper <craig.topper@intel.com>
Thu, 8 Aug 2019 18:11:17 +0000 (18:11 +0000)
committerCraig Topper <craig.topper@intel.com>
Thu, 8 Aug 2019 18:11:17 +0000 (18:11 +0000)
commit9d55e2c85e6636898f58487aea8832d858e7e682
tree6b413fbc4458c003160997cdf6cf1734bbf4a728tree | snapshot
parentcb30590da10ba80a133222588efedab7e5fc9bddcommit | diff
[X86] Make CMPXCHG16B feature imply CMPXCHG8B feature.

This fixes znver1 so that it properly enables CMPXHG8B. We can
probably remove explicit CMPXCHG8B from CPUs that also have
CMPXCHG16B, but keeping this simple to allow cherry pick to 9.0.

Fixes PR42935.

llvm-svn: 368324
llvm/lib/Target/X86/X86.td diff | blob | history
llvm/test/CodeGen/X86/cmpxchg8b.ll diff | blob | history
Domain: System / Toolchain;