test/Analysis/CostModel/X86/arith-overflow.ll - llvm-project/llvm - Git at Google

 ; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
 ; RUN: opt < %s -cost-model -analyze -mtriple=x86_64-apple-macosx10.8.0 -mattr=+ssse3 | FileCheck %s --check-prefixes=SSSE3
 ; RUN: opt < %s -cost-model -analyze -mtriple=x86_64-apple-macosx10.8.0 -mattr=+sse4.2 | FileCheck %s --check-prefixes=SSE42
 ; RUN: opt < %s -cost-model -analyze -mtriple=x86_64-apple-macosx10.8.0 -mattr=+avx | FileCheck %s --check-prefixes=AVX1
 ; RUN: opt < %s -cost-model -analyze -mtriple=x86_64-apple-macosx10.8.0 -mattr=+avx2 | FileCheck %s --check-prefixes=AVX2
 ; RUN: opt < %s -cost-model -analyze -mtriple=x86_64-apple-macosx10.8.0 -mattr=+avx512f | FileCheck %s --check-prefixes=AVX512F
 ; RUN: opt < %s -cost-model -analyze -mtriple=x86_64-apple-macosx10.8.0 -mattr=+avx512f,+avx512bw | FileCheck %s --check-prefixes=AVX512BW
 ; RUN: opt < %s -cost-model -analyze -mtriple=x86_64-apple-macosx10.8.0 -mattr=+avx512f,+avx512dq | FileCheck %s --check-prefixes=AVX512DQ
 ;
 ; RUN: opt < %s -cost-model -analyze -mtriple=x86_64-apple-macosx10.8.0 -mcpu=slm | FileCheck %s --check-prefixes=SLM
 ; RUN: opt < %s -cost-model -analyze -mtriple=x86_64-apple-macosx10.8.0 -mcpu=goldmont | FileCheck %s --check-prefixes=GLM
 ; RUN: opt < %s -cost-model -analyze -mtriple=x86_64-apple-macosx10.8.0 -mcpu=btver2 | FileCheck %s --check-prefixes=BTVER2

 ;
 ; sadd.with.overflow
 ;

 declare {i64, i1}              @llvm.sadd.with.overflow.i64(i64, i64)
 declare {<2 x i64>, <2 x i1>}  @llvm.sadd.with.overflow.v2i64(<2 x i64>, <2 x i64>)
 declare {<4 x i64>, <4 x i1>}  @llvm.sadd.with.overflow.v4i64(<4 x i64>, <4 x i64>)
 declare {<8 x i64>, <8 x i1>}  @llvm.sadd.with.overflow.v8i64(<8 x i64>, <8 x i64>)

 declare {i32, i1}               @llvm.sadd.with.overflow.i32(i32, i32)
 declare {<4 x i32>, <4 x i1>}   @llvm.sadd.with.overflow.v4i32(<4 x i32>, <4 x i32>)
 declare {<8 x i32>, <8 x i1>}   @llvm.sadd.with.overflow.v8i32(<8 x i32>, <8 x i32>)
 declare {<16 x i32>, <16 x i1>} @llvm.sadd.with.overflow.v16i32(<16 x i32>, <16 x i32>)

 declare {i16, i1}               @llvm.sadd.with.overflow.i16(i16, i16)
 declare {<8 x i16>,  <8 x i1>}  @llvm.sadd.with.overflow.v8i16(<8 x i16>, <8 x i16>)
 declare {<16 x i16>, <16 x i1>} @llvm.sadd.with.overflow.v16i16(<16 x i16>, <16 x i16>)
 declare {<32 x i16>, <32 x i1>} @llvm.sadd.with.overflow.v32i16(<32 x i16>, <32 x i16>)

 declare {i8, i1}                @llvm.sadd.with.overflow.i8(i8, i8)
 declare {<16 x i8>, <16 x i1>}  @llvm.sadd.with.overflow.v16i8(<16 x i8>, <16 x i8>)
 declare {<32 x i8>, <32 x i1>}  @llvm.sadd.with.overflow.v32i8(<32 x i8>, <32 x i8>)
 declare {<64 x i8>, <64 x i1>}  @llvm.sadd.with.overflow.v64i8(<64 x i8>, <64 x i8>)

 define i32 @sadd(i32 %arg) {
 ; SSSE3-LABEL: 'sadd'
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call { i64, i1 } @llvm.sadd.with.overflow.i64(i64 undef, i64 undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.sadd.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 57 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.sadd.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 107 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.sadd.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call { i32, i1 } @llvm.sadd.with.overflow.i32(i32 undef, i32 undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.sadd.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.sadd.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.sadd.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call { i16, i1 } @llvm.sadd.with.overflow.i16(i16 undef, i16 undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.sadd.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.sadd.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.sadd.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call { i8, i1 } @llvm.sadd.with.overflow.i8(i8 undef, i8 undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.sadd.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.sadd.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.sadd.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSE42-LABEL: 'sadd'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call { i64, i1 } @llvm.sadd.with.overflow.i64(i64 undef, i64 undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.sadd.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.sadd.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.sadd.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call { i32, i1 } @llvm.sadd.with.overflow.i32(i32 undef, i32 undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.sadd.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.sadd.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.sadd.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call { i16, i1 } @llvm.sadd.with.overflow.i16(i16 undef, i16 undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.sadd.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.sadd.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.sadd.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call { i8, i1 } @llvm.sadd.with.overflow.i8(i8 undef, i8 undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.sadd.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.sadd.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.sadd.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX1-LABEL: 'sadd'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call { i64, i1 } @llvm.sadd.with.overflow.i64(i64 undef, i64 undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.sadd.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.sadd.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 35 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.sadd.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call { i32, i1 } @llvm.sadd.with.overflow.i32(i32 undef, i32 undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.sadd.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.sadd.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 35 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.sadd.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call { i16, i1 } @llvm.sadd.with.overflow.i16(i16 undef, i16 undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.sadd.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.sadd.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 39 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.sadd.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call { i8, i1 } @llvm.sadd.with.overflow.i8(i8 undef, i8 undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.sadd.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.sadd.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.sadd.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX2-LABEL: 'sadd'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call { i64, i1 } @llvm.sadd.with.overflow.i64(i64 undef, i64 undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.sadd.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.sadd.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.sadd.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call { i32, i1 } @llvm.sadd.with.overflow.i32(i32 undef, i32 undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.sadd.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.sadd.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.sadd.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call { i16, i1 } @llvm.sadd.with.overflow.i16(i16 undef, i16 undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.sadd.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.sadd.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.sadd.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call { i8, i1 } @llvm.sadd.with.overflow.i8(i8 undef, i8 undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.sadd.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.sadd.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.sadd.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512F-LABEL: 'sadd'
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call { i64, i1 } @llvm.sadd.with.overflow.i64(i64 undef, i64 undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.sadd.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.sadd.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.sadd.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call { i32, i1 } @llvm.sadd.with.overflow.i32(i32 undef, i32 undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.sadd.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.sadd.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 69 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.sadd.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call { i16, i1 } @llvm.sadd.with.overflow.i16(i16 undef, i16 undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.sadd.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 69 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.sadd.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 138 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.sadd.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call { i8, i1 } @llvm.sadd.with.overflow.i8(i8 undef, i8 undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 69 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.sadd.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 134 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.sadd.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 268 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.sadd.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512BW-LABEL: 'sadd'
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call { i64, i1 } @llvm.sadd.with.overflow.i64(i64 undef, i64 undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.sadd.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.sadd.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.sadd.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call { i32, i1 } @llvm.sadd.with.overflow.i32(i32 undef, i32 undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.sadd.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.sadd.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 69 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.sadd.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call { i16, i1 } @llvm.sadd.with.overflow.i16(i16 undef, i16 undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.sadd.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 69 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.sadd.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 133 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.sadd.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call { i8, i1 } @llvm.sadd.with.overflow.i8(i8 undef, i8 undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 69 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.sadd.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 133 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.sadd.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 261 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.sadd.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512DQ-LABEL: 'sadd'
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call { i64, i1 } @llvm.sadd.with.overflow.i64(i64 undef, i64 undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.sadd.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.sadd.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.sadd.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call { i32, i1 } @llvm.sadd.with.overflow.i32(i32 undef, i32 undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.sadd.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.sadd.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 69 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.sadd.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call { i16, i1 } @llvm.sadd.with.overflow.i16(i16 undef, i16 undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.sadd.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 69 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.sadd.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 138 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.sadd.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call { i8, i1 } @llvm.sadd.with.overflow.i8(i8 undef, i8 undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 69 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.sadd.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 134 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.sadd.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 268 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.sadd.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SLM-LABEL: 'sadd'
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call { i64, i1 } @llvm.sadd.with.overflow.i64(i64 undef, i64 undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.sadd.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.sadd.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 43 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.sadd.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call { i32, i1 } @llvm.sadd.with.overflow.i32(i32 undef, i32 undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.sadd.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.sadd.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.sadd.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call { i16, i1 } @llvm.sadd.with.overflow.i16(i16 undef, i16 undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.sadd.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.sadd.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.sadd.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call { i8, i1 } @llvm.sadd.with.overflow.i8(i8 undef, i8 undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.sadd.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.sadd.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.sadd.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; GLM-LABEL: 'sadd'
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call { i64, i1 } @llvm.sadd.with.overflow.i64(i64 undef, i64 undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.sadd.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.sadd.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.sadd.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call { i32, i1 } @llvm.sadd.with.overflow.i32(i32 undef, i32 undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.sadd.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.sadd.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.sadd.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call { i16, i1 } @llvm.sadd.with.overflow.i16(i16 undef, i16 undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.sadd.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.sadd.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.sadd.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call { i8, i1 } @llvm.sadd.with.overflow.i8(i8 undef, i8 undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.sadd.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.sadd.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.sadd.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; BTVER2-LABEL: 'sadd'
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call { i64, i1 } @llvm.sadd.with.overflow.i64(i64 undef, i64 undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.sadd.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.sadd.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 35 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.sadd.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call { i32, i1 } @llvm.sadd.with.overflow.i32(i32 undef, i32 undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.sadd.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.sadd.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 35 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.sadd.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call { i16, i1 } @llvm.sadd.with.overflow.i16(i16 undef, i16 undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.sadd.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.sadd.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 39 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.sadd.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call { i8, i1 } @llvm.sadd.with.overflow.i8(i8 undef, i8 undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.sadd.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.sadd.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.sadd.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %I64 = call {i64, i1} @llvm.sadd.with.overflow.i64(i64 undef, i64 undef)
   %V2I64 = call {<2 x i64>, <2 x i1>} @llvm.sadd.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
   %V4I64 = call {<4 x i64>, <4 x i1>} @llvm.sadd.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
   %V8I64 = call {<8 x i64>, <8 x i1>} @llvm.sadd.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)

   %I32 = call {i32, i1} @llvm.sadd.with.overflow.i32(i32 undef, i32 undef)
   %V4I32  = call {<4 x i32>, <4 x i1>}  @llvm.sadd.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
   %V8I32  = call {<8 x i32>, <8 x i1>}  @llvm.sadd.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
   %V16I32 = call {<16 x i32>, <16 x i1>} @llvm.sadd.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)

   %I16 = call {i16, i1} @llvm.sadd.with.overflow.i16(i16 undef, i16 undef)
   %V8I16  = call {<8 x i16>, <8 x i1>}  @llvm.sadd.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
   %V16I16 = call {<16 x i16>, <16 x i1>} @llvm.sadd.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
   %V32I16 = call {<32 x i16>, <32 x i1>} @llvm.sadd.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)

   %I8 = call {i8, i1} @llvm.sadd.with.overflow.i8(i8 undef, i8 undef)
   %V16I8 = call {<16 x i8>, <16 x i1>} @llvm.sadd.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
   %V32I8 = call {<32 x i8>, <32 x i1>} @llvm.sadd.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
   %V64I8 = call {<64 x i8>, <64 x i1>} @llvm.sadd.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)

   ret i32 undef
 }

 ;
 ; uadd.with.overflow
 ;

 declare {i64, i1}              @llvm.uadd.with.overflow.i64(i64, i64)
 declare {<2 x i64>, <2 x i1>}  @llvm.uadd.with.overflow.v2i64(<2 x i64>, <2 x i64>)
 declare {<4 x i64>, <4 x i1>}  @llvm.uadd.with.overflow.v4i64(<4 x i64>, <4 x i64>)
 declare {<8 x i64>, <8 x i1>}  @llvm.uadd.with.overflow.v8i64(<8 x i64>, <8 x i64>)

 declare {i32, i1}               @llvm.uadd.with.overflow.i32(i32, i32)
 declare {<4 x i32>, <4 x i1>}   @llvm.uadd.with.overflow.v4i32(<4 x i32>, <4 x i32>)
 declare {<8 x i32>, <8 x i1>}   @llvm.uadd.with.overflow.v8i32(<8 x i32>, <8 x i32>)
 declare {<16 x i32>, <16 x i1>} @llvm.uadd.with.overflow.v16i32(<16 x i32>, <16 x i32>)

 declare {i16, i1}               @llvm.uadd.with.overflow.i16(i16, i16)
 declare {<8 x i16>,  <8 x i1>}  @llvm.uadd.with.overflow.v8i16(<8 x i16>, <8 x i16>)
 declare {<16 x i16>, <16 x i1>} @llvm.uadd.with.overflow.v16i16(<16 x i16>, <16 x i16>)
 declare {<32 x i16>, <32 x i1>} @llvm.uadd.with.overflow.v32i16(<32 x i16>, <32 x i16>)

 declare {i8, i1}                @llvm.uadd.with.overflow.i8(i8, i8)
 declare {<16 x i8>, <16 x i1>}  @llvm.uadd.with.overflow.v16i8(<16 x i8>, <16 x i8>)
 declare {<32 x i8>, <32 x i1>}  @llvm.uadd.with.overflow.v32i8(<32 x i8>, <32 x i8>)
 declare {<64 x i8>, <64 x i1>}  @llvm.uadd.with.overflow.v64i8(<64 x i8>, <64 x i8>)

 define i32 @uadd(i32 %arg) {
 ; SSSE3-LABEL: 'uadd'
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call { i64, i1 } @llvm.uadd.with.overflow.i64(i64 undef, i64 undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.uadd.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.uadd.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.uadd.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call { i32, i1 } @llvm.uadd.with.overflow.i32(i32 undef, i32 undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.uadd.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.uadd.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.uadd.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call { i16, i1 } @llvm.uadd.with.overflow.i16(i16 undef, i16 undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.uadd.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.uadd.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.uadd.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call { i8, i1 } @llvm.uadd.with.overflow.i8(i8 undef, i8 undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.uadd.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.uadd.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.uadd.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSE42-LABEL: 'uadd'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call { i64, i1 } @llvm.uadd.with.overflow.i64(i64 undef, i64 undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.uadd.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.uadd.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.uadd.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call { i32, i1 } @llvm.uadd.with.overflow.i32(i32 undef, i32 undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.uadd.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.uadd.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.uadd.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call { i16, i1 } @llvm.uadd.with.overflow.i16(i16 undef, i16 undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.uadd.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.uadd.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.uadd.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call { i8, i1 } @llvm.uadd.with.overflow.i8(i8 undef, i8 undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.uadd.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.uadd.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.uadd.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX1-LABEL: 'uadd'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call { i64, i1 } @llvm.uadd.with.overflow.i64(i64 undef, i64 undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.uadd.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.uadd.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.uadd.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call { i32, i1 } @llvm.uadd.with.overflow.i32(i32 undef, i32 undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.uadd.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.uadd.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.uadd.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call { i16, i1 } @llvm.uadd.with.overflow.i16(i16 undef, i16 undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.uadd.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.uadd.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.uadd.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call { i8, i1 } @llvm.uadd.with.overflow.i8(i8 undef, i8 undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.uadd.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.uadd.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.uadd.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX2-LABEL: 'uadd'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call { i64, i1 } @llvm.uadd.with.overflow.i64(i64 undef, i64 undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.uadd.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.uadd.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.uadd.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call { i32, i1 } @llvm.uadd.with.overflow.i32(i32 undef, i32 undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.uadd.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.uadd.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.uadd.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call { i16, i1 } @llvm.uadd.with.overflow.i16(i16 undef, i16 undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.uadd.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.uadd.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.uadd.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call { i8, i1 } @llvm.uadd.with.overflow.i8(i8 undef, i8 undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.uadd.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.uadd.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.uadd.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512F-LABEL: 'uadd'
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call { i64, i1 } @llvm.uadd.with.overflow.i64(i64 undef, i64 undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.uadd.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.uadd.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.uadd.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call { i32, i1 } @llvm.uadd.with.overflow.i32(i32 undef, i32 undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.uadd.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.uadd.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.uadd.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call { i16, i1 } @llvm.uadd.with.overflow.i16(i16 undef, i16 undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.uadd.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.uadd.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.uadd.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call { i8, i1 } @llvm.uadd.with.overflow.i8(i8 undef, i8 undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.uadd.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.uadd.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.uadd.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512BW-LABEL: 'uadd'
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call { i64, i1 } @llvm.uadd.with.overflow.i64(i64 undef, i64 undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.uadd.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.uadd.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.uadd.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call { i32, i1 } @llvm.uadd.with.overflow.i32(i32 undef, i32 undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.uadd.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.uadd.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.uadd.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call { i16, i1 } @llvm.uadd.with.overflow.i16(i16 undef, i16 undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.uadd.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.uadd.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.uadd.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call { i8, i1 } @llvm.uadd.with.overflow.i8(i8 undef, i8 undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.uadd.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.uadd.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.uadd.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512DQ-LABEL: 'uadd'
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call { i64, i1 } @llvm.uadd.with.overflow.i64(i64 undef, i64 undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.uadd.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.uadd.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.uadd.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call { i32, i1 } @llvm.uadd.with.overflow.i32(i32 undef, i32 undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.uadd.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.uadd.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.uadd.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call { i16, i1 } @llvm.uadd.with.overflow.i16(i16 undef, i16 undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.uadd.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.uadd.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.uadd.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call { i8, i1 } @llvm.uadd.with.overflow.i8(i8 undef, i8 undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.uadd.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.uadd.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.uadd.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SLM-LABEL: 'uadd'
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call { i64, i1 } @llvm.uadd.with.overflow.i64(i64 undef, i64 undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.uadd.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.uadd.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.uadd.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call { i32, i1 } @llvm.uadd.with.overflow.i32(i32 undef, i32 undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.uadd.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.uadd.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.uadd.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call { i16, i1 } @llvm.uadd.with.overflow.i16(i16 undef, i16 undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.uadd.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.uadd.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.uadd.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call { i8, i1 } @llvm.uadd.with.overflow.i8(i8 undef, i8 undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.uadd.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.uadd.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.uadd.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; GLM-LABEL: 'uadd'
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call { i64, i1 } @llvm.uadd.with.overflow.i64(i64 undef, i64 undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.uadd.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.uadd.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.uadd.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call { i32, i1 } @llvm.uadd.with.overflow.i32(i32 undef, i32 undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.uadd.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.uadd.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.uadd.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call { i16, i1 } @llvm.uadd.with.overflow.i16(i16 undef, i16 undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.uadd.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.uadd.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.uadd.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call { i8, i1 } @llvm.uadd.with.overflow.i8(i8 undef, i8 undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.uadd.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.uadd.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.uadd.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; BTVER2-LABEL: 'uadd'
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call { i64, i1 } @llvm.uadd.with.overflow.i64(i64 undef, i64 undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.uadd.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.uadd.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.uadd.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call { i32, i1 } @llvm.uadd.with.overflow.i32(i32 undef, i32 undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.uadd.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.uadd.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.uadd.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call { i16, i1 } @llvm.uadd.with.overflow.i16(i16 undef, i16 undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.uadd.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.uadd.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.uadd.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call { i8, i1 } @llvm.uadd.with.overflow.i8(i8 undef, i8 undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.uadd.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.uadd.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.uadd.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %I64 = call {i64, i1} @llvm.uadd.with.overflow.i64(i64 undef, i64 undef)
   %V2I64 = call {<2 x i64>, <2 x i1>} @llvm.uadd.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
   %V4I64 = call {<4 x i64>, <4 x i1>} @llvm.uadd.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
   %V8I64 = call {<8 x i64>, <8 x i1>} @llvm.uadd.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)

   %I32 = call {i32, i1} @llvm.uadd.with.overflow.i32(i32 undef, i32 undef)
   %V4I32  = call {<4 x i32>, <4 x i1>}  @llvm.uadd.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
   %V8I32  = call {<8 x i32>, <8 x i1>}  @llvm.uadd.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
   %V16I32 = call {<16 x i32>, <16 x i1>} @llvm.uadd.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)

   %I16 = call {i16, i1} @llvm.uadd.with.overflow.i16(i16 undef, i16 undef)
   %V8I16  = call {<8 x i16>, <8 x i1>}  @llvm.uadd.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
   %V16I16 = call {<16 x i16>, <16 x i1>} @llvm.uadd.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
   %V32I16 = call {<32 x i16>, <32 x i1>} @llvm.uadd.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)

   %I8 = call {i8, i1} @llvm.uadd.with.overflow.i8(i8 undef, i8 undef)
   %V16I8 = call {<16 x i8>, <16 x i1>} @llvm.uadd.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
   %V32I8 = call {<32 x i8>, <32 x i1>} @llvm.uadd.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
   %V64I8 = call {<64 x i8>, <64 x i1>} @llvm.uadd.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)

   ret i32 undef
 }

 ;
 ; ssub.with.overflow
 ;

 declare {i64, i1}              @llvm.ssub.with.overflow.i64(i64, i64)
 declare {<2 x i64>, <2 x i1>}  @llvm.ssub.with.overflow.v2i64(<2 x i64>, <2 x i64>)
 declare {<4 x i64>, <4 x i1>}  @llvm.ssub.with.overflow.v4i64(<4 x i64>, <4 x i64>)
 declare {<8 x i64>, <8 x i1>}  @llvm.ssub.with.overflow.v8i64(<8 x i64>, <8 x i64>)

 declare {i32, i1}               @llvm.ssub.with.overflow.i32(i32, i32)
 declare {<4 x i32>, <4 x i1>}   @llvm.ssub.with.overflow.v4i32(<4 x i32>, <4 x i32>)
 declare {<8 x i32>, <8 x i1>}   @llvm.ssub.with.overflow.v8i32(<8 x i32>, <8 x i32>)
 declare {<16 x i32>, <16 x i1>} @llvm.ssub.with.overflow.v16i32(<16 x i32>, <16 x i32>)

 declare {i16, i1}               @llvm.ssub.with.overflow.i16(i16, i16)
 declare {<8 x i16>,  <8 x i1>}  @llvm.ssub.with.overflow.v8i16(<8 x i16>, <8 x i16>)
 declare {<16 x i16>, <16 x i1>} @llvm.ssub.with.overflow.v16i16(<16 x i16>, <16 x i16>)
 declare {<32 x i16>, <32 x i1>} @llvm.ssub.with.overflow.v32i16(<32 x i16>, <32 x i16>)

 declare {i8, i1}                @llvm.ssub.with.overflow.i8(i8, i8)
 declare {<16 x i8>, <16 x i1>}  @llvm.ssub.with.overflow.v16i8(<16 x i8>, <16 x i8>)
 declare {<32 x i8>, <32 x i1>}  @llvm.ssub.with.overflow.v32i8(<32 x i8>, <32 x i8>)
 declare {<64 x i8>, <64 x i1>}  @llvm.ssub.with.overflow.v64i8(<64 x i8>, <64 x i8>)

 define i32 @ssub(i32 %arg) {
 ; SSSE3-LABEL: 'ssub'
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call { i64, i1 } @llvm.ssub.with.overflow.i64(i64 undef, i64 undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.ssub.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 57 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.ssub.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 107 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.ssub.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call { i32, i1 } @llvm.ssub.with.overflow.i32(i32 undef, i32 undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.ssub.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.ssub.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.ssub.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call { i16, i1 } @llvm.ssub.with.overflow.i16(i16 undef, i16 undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.ssub.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.ssub.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.ssub.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call { i8, i1 } @llvm.ssub.with.overflow.i8(i8 undef, i8 undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.ssub.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.ssub.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.ssub.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSE42-LABEL: 'ssub'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call { i64, i1 } @llvm.ssub.with.overflow.i64(i64 undef, i64 undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.ssub.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.ssub.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.ssub.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call { i32, i1 } @llvm.ssub.with.overflow.i32(i32 undef, i32 undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.ssub.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.ssub.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.ssub.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call { i16, i1 } @llvm.ssub.with.overflow.i16(i16 undef, i16 undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.ssub.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.ssub.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.ssub.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call { i8, i1 } @llvm.ssub.with.overflow.i8(i8 undef, i8 undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.ssub.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.ssub.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.ssub.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX1-LABEL: 'ssub'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call { i64, i1 } @llvm.ssub.with.overflow.i64(i64 undef, i64 undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.ssub.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.ssub.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 35 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.ssub.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call { i32, i1 } @llvm.ssub.with.overflow.i32(i32 undef, i32 undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.ssub.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.ssub.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 35 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.ssub.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call { i16, i1 } @llvm.ssub.with.overflow.i16(i16 undef, i16 undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.ssub.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.ssub.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 39 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.ssub.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call { i8, i1 } @llvm.ssub.with.overflow.i8(i8 undef, i8 undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.ssub.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.ssub.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.ssub.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX2-LABEL: 'ssub'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call { i64, i1 } @llvm.ssub.with.overflow.i64(i64 undef, i64 undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.ssub.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.ssub.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.ssub.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call { i32, i1 } @llvm.ssub.with.overflow.i32(i32 undef, i32 undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.ssub.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.ssub.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.ssub.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call { i16, i1 } @llvm.ssub.with.overflow.i16(i16 undef, i16 undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.ssub.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.ssub.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.ssub.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call { i8, i1 } @llvm.ssub.with.overflow.i8(i8 undef, i8 undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.ssub.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.ssub.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.ssub.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512F-LABEL: 'ssub'
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call { i64, i1 } @llvm.ssub.with.overflow.i64(i64 undef, i64 undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.ssub.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.ssub.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.ssub.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call { i32, i1 } @llvm.ssub.with.overflow.i32(i32 undef, i32 undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.ssub.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.ssub.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 69 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.ssub.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call { i16, i1 } @llvm.ssub.with.overflow.i16(i16 undef, i16 undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.ssub.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 69 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.ssub.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 138 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.ssub.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call { i8, i1 } @llvm.ssub.with.overflow.i8(i8 undef, i8 undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 69 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.ssub.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 134 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.ssub.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 268 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.ssub.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512BW-LABEL: 'ssub'
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call { i64, i1 } @llvm.ssub.with.overflow.i64(i64 undef, i64 undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.ssub.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.ssub.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.ssub.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call { i32, i1 } @llvm.ssub.with.overflow.i32(i32 undef, i32 undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.ssub.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.ssub.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 69 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.ssub.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call { i16, i1 } @llvm.ssub.with.overflow.i16(i16 undef, i16 undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.ssub.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 69 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.ssub.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 133 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.ssub.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call { i8, i1 } @llvm.ssub.with.overflow.i8(i8 undef, i8 undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 69 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.ssub.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 133 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.ssub.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 261 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.ssub.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512DQ-LABEL: 'ssub'
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call { i64, i1 } @llvm.ssub.with.overflow.i64(i64 undef, i64 undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.ssub.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.ssub.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.ssub.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call { i32, i1 } @llvm.ssub.with.overflow.i32(i32 undef, i32 undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.ssub.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.ssub.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 69 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.ssub.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call { i16, i1 } @llvm.ssub.with.overflow.i16(i16 undef, i16 undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 37 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.ssub.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 69 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.ssub.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 138 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.ssub.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call { i8, i1 } @llvm.ssub.with.overflow.i8(i8 undef, i8 undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 69 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.ssub.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 134 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.ssub.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 268 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.ssub.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SLM-LABEL: 'ssub'
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call { i64, i1 } @llvm.ssub.with.overflow.i64(i64 undef, i64 undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 13 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.ssub.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.ssub.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 43 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.ssub.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call { i32, i1 } @llvm.ssub.with.overflow.i32(i32 undef, i32 undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.ssub.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.ssub.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.ssub.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call { i16, i1 } @llvm.ssub.with.overflow.i16(i16 undef, i16 undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.ssub.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.ssub.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.ssub.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call { i8, i1 } @llvm.ssub.with.overflow.i8(i8 undef, i8 undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.ssub.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.ssub.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.ssub.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; GLM-LABEL: 'ssub'
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call { i64, i1 } @llvm.ssub.with.overflow.i64(i64 undef, i64 undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.ssub.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.ssub.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.ssub.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call { i32, i1 } @llvm.ssub.with.overflow.i32(i32 undef, i32 undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.ssub.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.ssub.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.ssub.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call { i16, i1 } @llvm.ssub.with.overflow.i16(i16 undef, i16 undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.ssub.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.ssub.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.ssub.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call { i8, i1 } @llvm.ssub.with.overflow.i8(i8 undef, i8 undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.ssub.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.ssub.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.ssub.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; BTVER2-LABEL: 'ssub'
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call { i64, i1 } @llvm.ssub.with.overflow.i64(i64 undef, i64 undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.ssub.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.ssub.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 35 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.ssub.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call { i32, i1 } @llvm.ssub.with.overflow.i32(i32 undef, i32 undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.ssub.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.ssub.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 35 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.ssub.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call { i16, i1 } @llvm.ssub.with.overflow.i16(i16 undef, i16 undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.ssub.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.ssub.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 39 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.ssub.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call { i8, i1 } @llvm.ssub.with.overflow.i8(i8 undef, i8 undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.ssub.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.ssub.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.ssub.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %I64 = call {i64, i1} @llvm.ssub.with.overflow.i64(i64 undef, i64 undef)
   %V2I64 = call {<2 x i64>, <2 x i1>} @llvm.ssub.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
   %V4I64 = call {<4 x i64>, <4 x i1>} @llvm.ssub.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
   %V8I64 = call {<8 x i64>, <8 x i1>} @llvm.ssub.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)

   %I32 = call {i32, i1} @llvm.ssub.with.overflow.i32(i32 undef, i32 undef)
   %V4I32  = call {<4 x i32>, <4 x i1>}  @llvm.ssub.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
   %V8I32  = call {<8 x i32>, <8 x i1>}  @llvm.ssub.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
   %V16I32 = call {<16 x i32>, <16 x i1>} @llvm.ssub.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)

   %I16 = call {i16, i1} @llvm.ssub.with.overflow.i16(i16 undef, i16 undef)
   %V8I16  = call {<8 x i16>, <8 x i1>}  @llvm.ssub.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
   %V16I16 = call {<16 x i16>, <16 x i1>} @llvm.ssub.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
   %V32I16 = call {<32 x i16>, <32 x i1>} @llvm.ssub.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)

   %I8 = call {i8, i1} @llvm.ssub.with.overflow.i8(i8 undef, i8 undef)
   %V16I8 = call {<16 x i8>, <16 x i1>} @llvm.ssub.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
   %V32I8 = call {<32 x i8>, <32 x i1>} @llvm.ssub.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
   %V64I8 = call {<64 x i8>, <64 x i1>} @llvm.ssub.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)

   ret i32 undef
 }

 ;
 ; usub.with.overflow
 ;

 declare {i64, i1}              @llvm.usub.with.overflow.i64(i64, i64)
 declare {<2 x i64>, <2 x i1>}  @llvm.usub.with.overflow.v2i64(<2 x i64>, <2 x i64>)
 declare {<4 x i64>, <4 x i1>}  @llvm.usub.with.overflow.v4i64(<4 x i64>, <4 x i64>)
 declare {<8 x i64>, <8 x i1>}  @llvm.usub.with.overflow.v8i64(<8 x i64>, <8 x i64>)

 declare {i32, i1}               @llvm.usub.with.overflow.i32(i32, i32)
 declare {<4 x i32>, <4 x i1>}   @llvm.usub.with.overflow.v4i32(<4 x i32>, <4 x i32>)
 declare {<8 x i32>, <8 x i1>}   @llvm.usub.with.overflow.v8i32(<8 x i32>, <8 x i32>)
 declare {<16 x i32>, <16 x i1>} @llvm.usub.with.overflow.v16i32(<16 x i32>, <16 x i32>)

 declare {i16, i1}               @llvm.usub.with.overflow.i16(i16, i16)
 declare {<8 x i16>,  <8 x i1>}  @llvm.usub.with.overflow.v8i16(<8 x i16>, <8 x i16>)
 declare {<16 x i16>, <16 x i1>} @llvm.usub.with.overflow.v16i16(<16 x i16>, <16 x i16>)
 declare {<32 x i16>, <32 x i1>} @llvm.usub.with.overflow.v32i16(<32 x i16>, <32 x i16>)

 declare {i8, i1}                @llvm.usub.with.overflow.i8(i8, i8)
 declare {<16 x i8>, <16 x i1>}  @llvm.usub.with.overflow.v16i8(<16 x i8>, <16 x i8>)
 declare {<32 x i8>, <32 x i1>}  @llvm.usub.with.overflow.v32i8(<32 x i8>, <32 x i8>)
 declare {<64 x i8>, <64 x i1>}  @llvm.usub.with.overflow.v64i8(<64 x i8>, <64 x i8>)

 define i32 @usub(i32 %arg) {
 ; SSSE3-LABEL: 'usub'
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call { i64, i1 } @llvm.usub.with.overflow.i64(i64 undef, i64 undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.usub.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.usub.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.usub.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call { i32, i1 } @llvm.usub.with.overflow.i32(i32 undef, i32 undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.usub.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.usub.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.usub.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call { i16, i1 } @llvm.usub.with.overflow.i16(i16 undef, i16 undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.usub.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.usub.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.usub.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call { i8, i1 } @llvm.usub.with.overflow.i8(i8 undef, i8 undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.usub.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.usub.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.usub.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSE42-LABEL: 'usub'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call { i64, i1 } @llvm.usub.with.overflow.i64(i64 undef, i64 undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.usub.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.usub.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.usub.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call { i32, i1 } @llvm.usub.with.overflow.i32(i32 undef, i32 undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.usub.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.usub.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.usub.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call { i16, i1 } @llvm.usub.with.overflow.i16(i16 undef, i16 undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.usub.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.usub.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.usub.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call { i8, i1 } @llvm.usub.with.overflow.i8(i8 undef, i8 undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.usub.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.usub.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.usub.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX1-LABEL: 'usub'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call { i64, i1 } @llvm.usub.with.overflow.i64(i64 undef, i64 undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.usub.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.usub.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.usub.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call { i32, i1 } @llvm.usub.with.overflow.i32(i32 undef, i32 undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.usub.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.usub.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.usub.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call { i16, i1 } @llvm.usub.with.overflow.i16(i16 undef, i16 undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.usub.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.usub.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.usub.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call { i8, i1 } @llvm.usub.with.overflow.i8(i8 undef, i8 undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.usub.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.usub.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.usub.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX2-LABEL: 'usub'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call { i64, i1 } @llvm.usub.with.overflow.i64(i64 undef, i64 undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.usub.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.usub.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.usub.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call { i32, i1 } @llvm.usub.with.overflow.i32(i32 undef, i32 undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.usub.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.usub.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.usub.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call { i16, i1 } @llvm.usub.with.overflow.i16(i16 undef, i16 undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.usub.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.usub.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.usub.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call { i8, i1 } @llvm.usub.with.overflow.i8(i8 undef, i8 undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.usub.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.usub.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.usub.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512F-LABEL: 'usub'
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call { i64, i1 } @llvm.usub.with.overflow.i64(i64 undef, i64 undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.usub.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.usub.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.usub.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call { i32, i1 } @llvm.usub.with.overflow.i32(i32 undef, i32 undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.usub.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.usub.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.usub.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call { i16, i1 } @llvm.usub.with.overflow.i16(i16 undef, i16 undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.usub.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.usub.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.usub.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call { i8, i1 } @llvm.usub.with.overflow.i8(i8 undef, i8 undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.usub.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.usub.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.usub.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512BW-LABEL: 'usub'
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call { i64, i1 } @llvm.usub.with.overflow.i64(i64 undef, i64 undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.usub.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.usub.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.usub.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call { i32, i1 } @llvm.usub.with.overflow.i32(i32 undef, i32 undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.usub.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.usub.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.usub.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call { i16, i1 } @llvm.usub.with.overflow.i16(i16 undef, i16 undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.usub.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.usub.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.usub.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call { i8, i1 } @llvm.usub.with.overflow.i8(i8 undef, i8 undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.usub.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.usub.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.usub.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512DQ-LABEL: 'usub'
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call { i64, i1 } @llvm.usub.with.overflow.i64(i64 undef, i64 undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.usub.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.usub.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.usub.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call { i32, i1 } @llvm.usub.with.overflow.i32(i32 undef, i32 undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.usub.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.usub.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.usub.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call { i16, i1 } @llvm.usub.with.overflow.i16(i16 undef, i16 undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.usub.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.usub.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.usub.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call { i8, i1 } @llvm.usub.with.overflow.i8(i8 undef, i8 undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.usub.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.usub.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.usub.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SLM-LABEL: 'usub'
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call { i64, i1 } @llvm.usub.with.overflow.i64(i64 undef, i64 undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.usub.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.usub.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.usub.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call { i32, i1 } @llvm.usub.with.overflow.i32(i32 undef, i32 undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.usub.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.usub.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.usub.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call { i16, i1 } @llvm.usub.with.overflow.i16(i16 undef, i16 undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.usub.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.usub.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.usub.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call { i8, i1 } @llvm.usub.with.overflow.i8(i8 undef, i8 undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.usub.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.usub.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.usub.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; GLM-LABEL: 'usub'
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call { i64, i1 } @llvm.usub.with.overflow.i64(i64 undef, i64 undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.usub.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.usub.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.usub.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call { i32, i1 } @llvm.usub.with.overflow.i32(i32 undef, i32 undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.usub.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.usub.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.usub.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call { i16, i1 } @llvm.usub.with.overflow.i16(i16 undef, i16 undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.usub.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.usub.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.usub.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call { i8, i1 } @llvm.usub.with.overflow.i8(i8 undef, i8 undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.usub.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.usub.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.usub.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; BTVER2-LABEL: 'usub'
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call { i64, i1 } @llvm.usub.with.overflow.i64(i64 undef, i64 undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.usub.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.usub.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.usub.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call { i32, i1 } @llvm.usub.with.overflow.i32(i32 undef, i32 undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.usub.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.usub.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.usub.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call { i16, i1 } @llvm.usub.with.overflow.i16(i16 undef, i16 undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.usub.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.usub.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.usub.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call { i8, i1 } @llvm.usub.with.overflow.i8(i8 undef, i8 undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.usub.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.usub.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.usub.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %I64 = call {i64, i1} @llvm.usub.with.overflow.i64(i64 undef, i64 undef)
   %V2I64 = call {<2 x i64>, <2 x i1>} @llvm.usub.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
   %V4I64 = call {<4 x i64>, <4 x i1>} @llvm.usub.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
   %V8I64 = call {<8 x i64>, <8 x i1>} @llvm.usub.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)

   %I32 = call {i32, i1} @llvm.usub.with.overflow.i32(i32 undef, i32 undef)
   %V4I32  = call {<4 x i32>, <4 x i1>}  @llvm.usub.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
   %V8I32  = call {<8 x i32>, <8 x i1>}  @llvm.usub.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
   %V16I32 = call {<16 x i32>, <16 x i1>} @llvm.usub.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)

   %I16 = call {i16, i1} @llvm.usub.with.overflow.i16(i16 undef, i16 undef)
   %V8I16  = call {<8 x i16>, <8 x i1>}  @llvm.usub.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
   %V16I16 = call {<16 x i16>, <16 x i1>} @llvm.usub.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
   %V32I16 = call {<32 x i16>, <32 x i1>} @llvm.usub.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)

   %I8 = call {i8, i1} @llvm.usub.with.overflow.i8(i8 undef, i8 undef)
   %V16I8 = call {<16 x i8>, <16 x i1>} @llvm.usub.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
   %V32I8 = call {<32 x i8>, <32 x i1>} @llvm.usub.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
   %V64I8 = call {<64 x i8>, <64 x i1>} @llvm.usub.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)

   ret i32 undef
 }

 ;
 ; smul.with.overflow
 ;

 declare {i64, i1}              @llvm.smul.with.overflow.i64(i64, i64)
 declare {<2 x i64>, <2 x i1>}  @llvm.smul.with.overflow.v2i64(<2 x i64>, <2 x i64>)
 declare {<4 x i64>, <4 x i1>}  @llvm.smul.with.overflow.v4i64(<4 x i64>, <4 x i64>)
 declare {<8 x i64>, <8 x i1>}  @llvm.smul.with.overflow.v8i64(<8 x i64>, <8 x i64>)

 declare {i32, i1}               @llvm.smul.with.overflow.i32(i32, i32)
 declare {<4 x i32>, <4 x i1>}   @llvm.smul.with.overflow.v4i32(<4 x i32>, <4 x i32>)
 declare {<8 x i32>, <8 x i1>}   @llvm.smul.with.overflow.v8i32(<8 x i32>, <8 x i32>)
 declare {<16 x i32>, <16 x i1>} @llvm.smul.with.overflow.v16i32(<16 x i32>, <16 x i32>)

 declare {i16, i1}               @llvm.smul.with.overflow.i16(i16, i16)
 declare {<8 x i16>,  <8 x i1>}  @llvm.smul.with.overflow.v8i16(<8 x i16>, <8 x i16>)
 declare {<16 x i16>, <16 x i1>} @llvm.smul.with.overflow.v16i16(<16 x i16>, <16 x i16>)
 declare {<32 x i16>, <32 x i1>} @llvm.smul.with.overflow.v32i16(<32 x i16>, <32 x i16>)

 declare {i8, i1}                @llvm.smul.with.overflow.i8(i8, i8)
 declare {<16 x i8>, <16 x i1>}  @llvm.smul.with.overflow.v16i8(<16 x i8>, <16 x i8>)
 declare {<32 x i8>, <32 x i1>}  @llvm.smul.with.overflow.v32i8(<32 x i8>, <32 x i8>)
 declare {<64 x i8>, <64 x i1>}  @llvm.smul.with.overflow.v64i8(<64 x i8>, <64 x i8>)

 define i32 @smul(i32 %arg) {
 ; SSSE3-LABEL: 'smul'
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I64 = call { i64, i1 } @llvm.smul.with.overflow.i64(i64 undef, i64 undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.smul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 58 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.smul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 116 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.smul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call { i32, i1 } @llvm.smul.with.overflow.i32(i32 undef, i32 undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.smul.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 62 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.smul.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 124 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.smul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call { i16, i1 } @llvm.smul.with.overflow.i16(i16 undef, i16 undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.smul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 62 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.smul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 124 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.smul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call { i8, i1 } @llvm.smul.with.overflow.i8(i8 undef, i8 undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.smul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.smul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 84 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.smul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSE42-LABEL: 'smul'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I64 = call { i64, i1 } @llvm.smul.with.overflow.i64(i64 undef, i64 undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.smul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.smul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 88 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.smul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call { i32, i1 } @llvm.smul.with.overflow.i32(i32 undef, i32 undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.smul.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 58 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.smul.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 116 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.smul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call { i16, i1 } @llvm.smul.with.overflow.i16(i16 undef, i16 undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.smul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.smul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 68 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.smul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call { i8, i1 } @llvm.smul.with.overflow.i8(i8 undef, i8 undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.smul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 38 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.smul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 76 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.smul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX1-LABEL: 'smul'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I64 = call { i64, i1 } @llvm.smul.with.overflow.i64(i64 undef, i64 undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.smul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 54 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.smul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 108 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.smul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call { i32, i1 } @llvm.smul.with.overflow.i32(i32 undef, i32 undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.smul.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.smul.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.smul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call { i16, i1 } @llvm.smul.with.overflow.i16(i16 undef, i16 undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.smul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.smul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.smul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call { i8, i1 } @llvm.smul.with.overflow.i8(i8 undef, i8 undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.smul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.smul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.smul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX2-LABEL: 'smul'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I64 = call { i64, i1 } @llvm.smul.with.overflow.i64(i64 undef, i64 undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.smul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.smul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 84 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.smul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call { i32, i1 } @llvm.smul.with.overflow.i32(i32 undef, i32 undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.smul.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.smul.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 62 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.smul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call { i16, i1 } @llvm.smul.with.overflow.i16(i16 undef, i16 undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.smul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.smul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 50 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.smul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call { i8, i1 } @llvm.smul.with.overflow.i8(i8 undef, i8 undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.smul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.smul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 66 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.smul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512F-LABEL: 'smul'
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I64 = call { i64, i1 } @llvm.smul.with.overflow.i64(i64 undef, i64 undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.smul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 39 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.smul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 79 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.smul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call { i32, i1 } @llvm.smul.with.overflow.i32(i32 undef, i32 undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.smul.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.smul.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.smul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call { i16, i1 } @llvm.smul.with.overflow.i16(i16 undef, i16 undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.smul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.smul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.smul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call { i8, i1 } @llvm.smul.with.overflow.i8(i8 undef, i8 undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.smul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.smul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 66 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.smul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512BW-LABEL: 'smul'
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I64 = call { i64, i1 } @llvm.smul.with.overflow.i64(i64 undef, i64 undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.smul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 39 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.smul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 79 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.smul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call { i32, i1 } @llvm.smul.with.overflow.i32(i32 undef, i32 undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.smul.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.smul.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.smul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call { i16, i1 } @llvm.smul.with.overflow.i16(i16 undef, i16 undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.smul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.smul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.smul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call { i8, i1 } @llvm.smul.with.overflow.i8(i8 undef, i8 undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.smul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.smul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.smul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512DQ-LABEL: 'smul'
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I64 = call { i64, i1 } @llvm.smul.with.overflow.i64(i64 undef, i64 undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.smul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 39 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.smul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 79 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.smul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call { i32, i1 } @llvm.smul.with.overflow.i32(i32 undef, i32 undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.smul.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.smul.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.smul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call { i16, i1 } @llvm.smul.with.overflow.i16(i16 undef, i16 undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.smul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.smul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.smul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call { i8, i1 } @llvm.smul.with.overflow.i8(i8 undef, i8 undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.smul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.smul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 66 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.smul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SLM-LABEL: 'smul'
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I64 = call { i64, i1 } @llvm.smul.with.overflow.i64(i64 undef, i64 undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.smul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.smul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 92 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.smul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call { i32, i1 } @llvm.smul.with.overflow.i32(i32 undef, i32 undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 47 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.smul.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 94 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.smul.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 188 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.smul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call { i16, i1 } @llvm.smul.with.overflow.i16(i16 undef, i16 undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 35 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.smul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 70 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.smul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 140 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.smul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call { i8, i1 } @llvm.smul.with.overflow.i8(i8 undef, i8 undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.smul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.smul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 84 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.smul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; GLM-LABEL: 'smul'
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I64 = call { i64, i1 } @llvm.smul.with.overflow.i64(i64 undef, i64 undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.smul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.smul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 88 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.smul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call { i32, i1 } @llvm.smul.with.overflow.i32(i32 undef, i32 undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.smul.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 58 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.smul.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 116 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.smul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call { i16, i1 } @llvm.smul.with.overflow.i16(i16 undef, i16 undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.smul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.smul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 68 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.smul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call { i8, i1 } @llvm.smul.with.overflow.i8(i8 undef, i8 undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.smul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 38 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.smul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 76 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.smul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; BTVER2-LABEL: 'smul'
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I64 = call { i64, i1 } @llvm.smul.with.overflow.i64(i64 undef, i64 undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.smul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 54 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.smul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 108 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.smul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call { i32, i1 } @llvm.smul.with.overflow.i32(i32 undef, i32 undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.smul.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.smul.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.smul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call { i16, i1 } @llvm.smul.with.overflow.i16(i16 undef, i16 undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.smul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.smul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.smul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call { i8, i1 } @llvm.smul.with.overflow.i8(i8 undef, i8 undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.smul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.smul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 128 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.smul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %I64 = call {i64, i1} @llvm.smul.with.overflow.i64(i64 undef, i64 undef)
   %V2I64 = call {<2 x i64>, <2 x i1>} @llvm.smul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
   %V4I64 = call {<4 x i64>, <4 x i1>} @llvm.smul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
   %V8I64 = call {<8 x i64>, <8 x i1>} @llvm.smul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)

   %I32 = call {i32, i1} @llvm.smul.with.overflow.i32(i32 undef, i32 undef)
   %V4I32  = call {<4 x i32>, <4 x i1>}  @llvm.smul.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
   %V8I32  = call {<8 x i32>, <8 x i1>}  @llvm.smul.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
   %V16I32 = call {<16 x i32>, <16 x i1>} @llvm.smul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)

   %I16 = call {i16, i1} @llvm.smul.with.overflow.i16(i16 undef, i16 undef)
   %V8I16  = call {<8 x i16>, <8 x i1>}  @llvm.smul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
   %V16I16 = call {<16 x i16>, <16 x i1>} @llvm.smul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
   %V32I16 = call {<32 x i16>, <32 x i1>} @llvm.smul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)

   %I8 = call {i8, i1} @llvm.smul.with.overflow.i8(i8 undef, i8 undef)
   %V16I8 = call {<16 x i8>, <16 x i1>} @llvm.smul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
   %V32I8 = call {<32 x i8>, <32 x i1>} @llvm.smul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
   %V64I8 = call {<64 x i8>, <64 x i1>} @llvm.smul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)

   ret i32 undef
 }

 ;
 ; umul.with.overflow
 ;

 declare {i64, i1}              @llvm.umul.with.overflow.i64(i64, i64)
 declare {<2 x i64>, <2 x i1>}  @llvm.umul.with.overflow.v2i64(<2 x i64>, <2 x i64>)
 declare {<4 x i64>, <4 x i1>}  @llvm.umul.with.overflow.v4i64(<4 x i64>, <4 x i64>)
 declare {<8 x i64>, <8 x i1>}  @llvm.umul.with.overflow.v8i64(<8 x i64>, <8 x i64>)

 declare {i32, i1}               @llvm.umul.with.overflow.i32(i32, i32)
 declare {<4 x i32>, <4 x i1>}   @llvm.umul.with.overflow.v4i32(<4 x i32>, <4 x i32>)
 declare {<8 x i32>, <8 x i1>}   @llvm.umul.with.overflow.v8i32(<8 x i32>, <8 x i32>)
 declare {<16 x i32>, <16 x i1>} @llvm.umul.with.overflow.v16i32(<16 x i32>, <16 x i32>)

 declare {i16, i1}               @llvm.umul.with.overflow.i16(i16, i16)
 declare {<8 x i16>,  <8 x i1>}  @llvm.umul.with.overflow.v8i16(<8 x i16>, <8 x i16>)
 declare {<16 x i16>, <16 x i1>} @llvm.umul.with.overflow.v16i16(<16 x i16>, <16 x i16>)
 declare {<32 x i16>, <32 x i1>} @llvm.umul.with.overflow.v32i16(<32 x i16>, <32 x i16>)

 declare {i8, i1}                @llvm.umul.with.overflow.i8(i8, i8)
 declare {<16 x i8>, <16 x i1>}  @llvm.umul.with.overflow.v16i8(<16 x i8>, <16 x i8>)
 declare {<32 x i8>, <32 x i1>}  @llvm.umul.with.overflow.v32i8(<32 x i8>, <32 x i8>)
 declare {<64 x i8>, <64 x i1>}  @llvm.umul.with.overflow.v64i8(<64 x i8>, <64 x i8>)

 define i32 @umul(i32 %arg) {
 ; SSSE3-LABEL: 'umul'
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I64 = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 undef, i64 undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 25 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.umul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 50 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.umul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 100 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.umul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call { i32, i1 } @llvm.umul.with.overflow.i32(i32 undef, i32 undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.umul.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.umul.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 120 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.umul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call { i16, i1 } @llvm.umul.with.overflow.i16(i16 undef, i16 undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.umul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.umul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 120 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.umul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call { i8, i1 } @llvm.umul.with.overflow.i8(i8 undef, i8 undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.umul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.umul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 68 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.umul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SSE42-LABEL: 'umul'
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I64 = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 undef, i64 undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.umul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.umul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.umul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call { i32, i1 } @llvm.umul.with.overflow.i32(i32 undef, i32 undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.umul.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.umul.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 112 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.umul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call { i16, i1 } @llvm.umul.with.overflow.i16(i16 undef, i16 undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.umul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.umul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.umul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call { i8, i1 } @llvm.umul.with.overflow.i8(i8 undef, i8 undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.umul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.umul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.umul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX1-LABEL: 'umul'
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I64 = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 undef, i64 undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.umul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.umul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 88 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.umul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call { i32, i1 } @llvm.umul.with.overflow.i32(i32 undef, i32 undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.umul.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 68 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.umul.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.umul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call { i16, i1 } @llvm.umul.with.overflow.i16(i16 undef, i16 undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.umul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.umul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.umul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call { i8, i1 } @llvm.umul.with.overflow.i8(i8 undef, i8 undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.umul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 54 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.umul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 108 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.umul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX2-LABEL: 'umul'
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I64 = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 undef, i64 undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.umul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 38 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.umul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 76 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.umul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call { i32, i1 } @llvm.umul.with.overflow.i32(i32 undef, i32 undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.umul.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.umul.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.umul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call { i16, i1 } @llvm.umul.with.overflow.i16(i16 undef, i16 undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.umul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.umul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.umul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call { i8, i1 } @llvm.umul.with.overflow.i8(i8 undef, i8 undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.umul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.umul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 58 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.umul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512F-LABEL: 'umul'
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I64 = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 undef, i64 undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.umul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 38 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.umul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 78 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.umul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call { i32, i1 } @llvm.umul.with.overflow.i32(i32 undef, i32 undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.umul.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.umul.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.umul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call { i16, i1 } @llvm.umul.with.overflow.i16(i16 undef, i16 undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.umul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.umul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.umul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call { i8, i1 } @llvm.umul.with.overflow.i8(i8 undef, i8 undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.umul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.umul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 58 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.umul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512BW-LABEL: 'umul'
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I64 = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 undef, i64 undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.umul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 38 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.umul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 78 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.umul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call { i32, i1 } @llvm.umul.with.overflow.i32(i32 undef, i32 undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.umul.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.umul.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.umul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call { i16, i1 } @llvm.umul.with.overflow.i16(i16 undef, i16 undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.umul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.umul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.umul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call { i8, i1 } @llvm.umul.with.overflow.i8(i8 undef, i8 undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.umul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.umul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.umul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; AVX512DQ-LABEL: 'umul'
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I64 = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 undef, i64 undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.umul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 38 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.umul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 78 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.umul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call { i32, i1 } @llvm.umul.with.overflow.i32(i32 undef, i32 undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.umul.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.umul.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.umul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call { i16, i1 } @llvm.umul.with.overflow.i16(i16 undef, i16 undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.umul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.umul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.umul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call { i8, i1 } @llvm.umul.with.overflow.i8(i8 undef, i8 undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.umul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 27 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.umul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 58 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.umul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SLM-LABEL: 'umul'
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I64 = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 undef, i64 undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.umul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 38 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.umul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 76 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.umul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call { i32, i1 } @llvm.umul.with.overflow.i32(i32 undef, i32 undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 46 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.umul.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 92 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.umul.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 184 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.umul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call { i16, i1 } @llvm.umul.with.overflow.i16(i16 undef, i16 undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.umul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 68 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.umul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.umul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call { i8, i1 } @llvm.umul.with.overflow.i8(i8 undef, i8 undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.umul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.umul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 68 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.umul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; SLM-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; GLM-LABEL: 'umul'
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I64 = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 undef, i64 undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.umul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.umul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.umul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call { i32, i1 } @llvm.umul.with.overflow.i32(i32 undef, i32 undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.umul.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 56 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.umul.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 112 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.umul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call { i16, i1 } @llvm.umul.with.overflow.i16(i16 undef, i16 undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.umul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.umul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.umul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call { i8, i1 } @llvm.umul.with.overflow.i8(i8 undef, i8 undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.umul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.umul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.umul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; GLM-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; BTVER2-LABEL: 'umul'
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I64 = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 undef, i64 undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.umul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.umul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 88 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.umul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call { i32, i1 } @llvm.umul.with.overflow.i32(i32 undef, i32 undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.umul.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 68 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.umul.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 136 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.umul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call { i16, i1 } @llvm.umul.with.overflow.i16(i16 undef, i16 undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.umul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.umul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.umul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call { i8, i1 } @llvm.umul.with.overflow.i8(i8 undef, i8 undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.umul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 54 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.umul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 108 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.umul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; BTVER2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
   %I64 = call {i64, i1} @llvm.umul.with.overflow.i64(i64 undef, i64 undef)
   %V2I64 = call {<2 x i64>, <2 x i1>} @llvm.umul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
   %V4I64 = call {<4 x i64>, <4 x i1>} @llvm.umul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
   %V8I64 = call {<8 x i64>, <8 x i1>} @llvm.umul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)

   %I32 = call {i32, i1} @llvm.umul.with.overflow.i32(i32 undef, i32 undef)
   %V4I32  = call {<4 x i32>, <4 x i1>}  @llvm.umul.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
   %V8I32  = call {<8 x i32>, <8 x i1>}  @llvm.umul.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
   %V16I32 = call {<16 x i32>, <16 x i1>} @llvm.umul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)

   %I16 = call {i16, i1} @llvm.umul.with.overflow.i16(i16 undef, i16 undef)
   %V8I16  = call {<8 x i16>, <8 x i1>}  @llvm.umul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
   %V16I16 = call {<16 x i16>, <16 x i1>} @llvm.umul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
   %V32I16 = call {<32 x i16>, <32 x i1>} @llvm.umul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)

   %I8 = call {i8, i1} @llvm.umul.with.overflow.i8(i8 undef, i8 undef)
   %V16I8 = call {<16 x i8>, <16 x i1>} @llvm.umul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
   %V32I8 = call {<32 x i8>, <32 x i1>} @llvm.umul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
   %V64I8 = call {<64 x i8>, <64 x i1>} @llvm.umul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)

   ret i32 undef
 }