diff options
| author | Craig Topper <craig.topper@intel.com> | 2017-09-24 19:30:55 +0000 |
|---|---|---|
| committer | Craig Topper <craig.topper@intel.com> | 2017-09-24 19:30:55 +0000 |
| commit | 47e14ead54d229aa8ac5436594e91bfb8943230e (patch) | |
| tree | af3e6fd7ea023e76bb0aaa5498a51874ffb92047 /llvm/lib/Target/X86/X86ISelLowering.h | |
| parent | 4ffd90c50444d98784f65698f54d386d27289c90 (diff) | |
| download | bcm5719-llvm-47e14ead54d229aa8ac5436594e91bfb8943230e.tar.gz bcm5719-llvm-47e14ead54d229aa8ac5436594e91bfb8943230e.zip | |
[X86] Make IFMA instructions during isel so we can fold broadcast loads.
This required changing the ISD opcode for these instructions to have the commutable operands first and the addend last. This way tablegen can autogenerate the additional patterns for us.
llvm-svn: 314083
Diffstat (limited to 'llvm/lib/Target/X86/X86ISelLowering.h')
| -rw-r--r-- | llvm/lib/Target/X86/X86ISelLowering.h | 4 |
1 files changed, 4 insertions, 0 deletions
diff --git a/llvm/lib/Target/X86/X86ISelLowering.h b/llvm/lib/Target/X86/X86ISelLowering.h index a1ae1613c73..a0fc4c8a29c 100644 --- a/llvm/lib/Target/X86/X86ISelLowering.h +++ b/llvm/lib/Target/X86/X86ISelLowering.h @@ -467,6 +467,10 @@ namespace llvm { // Multiply and Add Packed Integers. VPMADDUBSW, VPMADDWD, + + // AVX512IFMA multiply and add. + // NOTE: These are different than the instruction and perform + // op0 x op1 + op2. VPMADD52L, VPMADD52H, // FMA nodes. |
