[X86][AVX] Fixed v16i16/v32i8 ADD/SUB costs on AVX1 subtargets
Add explicit v16i16/v32i8 ADD/SUB costs, matching the costs of v4i64/v8i32 - they were missing for some reason.
This has side effects on the LV max bandwidth tests (AVX1 now prefers 128-bit vectors vs AVX2 which still prefers 256-bit)
llvm-svn: 286832
diff --git a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
index 7029a02..5b3091e 100644
--- a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
+++ b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
@@ -526,6 +526,10 @@
// Two ops + 1 extract + 1 insert = 4.
{ ISD::MUL, MVT::v16i16, 4 },
{ ISD::MUL, MVT::v8i32, 4 },
+ { ISD::SUB, MVT::v32i8, 4 },
+ { ISD::ADD, MVT::v32i8, 4 },
+ { ISD::SUB, MVT::v16i16, 4 },
+ { ISD::ADD, MVT::v16i16, 4 },
{ ISD::SUB, MVT::v8i32, 4 },
{ ISD::ADD, MVT::v8i32, 4 },
{ ISD::SUB, MVT::v4i64, 4 },