projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 33f02de) | patch
[X86] Replace avx512f integer mul reduction builtins with generic builtin
authorSimon Pilgrim <llvm-dev@redking.me.uk>
Mon, 9 May 2022 13:10:17 +0000 (14:10 +0100)
committerSimon Pilgrim <llvm-dev@redking.me.uk>
Mon, 9 May 2022 13:10:28 +0000 (14:10 +0100)
commitec6024d0811b3116e0a29481b01179d5081a3b92
tree0d3ded5283619ff0662ab3ce507fe936ad0f8b80tree | snapshot
parent33f02de5df4d66ee704fbe282bcae7eb0c8e9493commit | diff
[X86] Replace avx512f integer mul reduction builtins with generic builtin

D117829 added the generic "__builtin_reduce_mul" which we can use to replace the x86 specific integer mul reduction builtins - internally these were mapping to the same intrinsic already so there are no test changes required.

Differential Revision: https://reviews.llvm.org/D125222
clang/include/clang/Basic/BuiltinsX86.def diff | blob | history
clang/lib/CodeGen/CGBuiltin.cpp diff | blob | history
clang/lib/Headers/avx512fintrin.h diff | blob | history
Domain: System / Toolchain;