[llvm] 168177a - [CostModel][X86] merge arithmetic integer min/max costs tests using -cost-kind=all (#131834)

via llvm-commits llvm-commits at lists.llvm.org
Tue Mar 18 10:08:57 PDT 2025


Author: Simon Pilgrim
Date: 2025-03-18T17:08:52Z
New Revision: 168177a0bd009269bec4d752b8096c63c492af76

URL: https://github.com/llvm/llvm-project/commit/168177a0bd009269bec4d752b8096c63c492af76
DIFF: https://github.com/llvm/llvm-project/commit/168177a0bd009269bec4d752b8096c63c492af76.diff

LOG: [CostModel][X86] merge arithmetic integer min/max costs tests using -cost-kind=all (#131834)

Added: 
    

Modified: 
    llvm/test/Analysis/CostModel/X86/arith-sminmax.ll
    llvm/test/Analysis/CostModel/X86/arith-uminmax.ll

Removed: 
    llvm/test/Analysis/CostModel/X86/arith-sminmax-codesize.ll
    llvm/test/Analysis/CostModel/X86/arith-sminmax-latency.ll
    llvm/test/Analysis/CostModel/X86/arith-sminmax-sizelatency.ll
    llvm/test/Analysis/CostModel/X86/arith-uminmax-codesize.ll
    llvm/test/Analysis/CostModel/X86/arith-uminmax-latency.ll
    llvm/test/Analysis/CostModel/X86/arith-uminmax-sizelatency.ll


################################################################################
diff  --git a/llvm/test/Analysis/CostModel/X86/arith-sminmax-codesize.ll b/llvm/test/Analysis/CostModel/X86/arith-sminmax-codesize.ll
deleted file mode 100644
index 00e2dbb1753d1..0000000000000
--- a/llvm/test/Analysis/CostModel/X86/arith-sminmax-codesize.ll
+++ /dev/null
@@ -1,401 +0,0 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=code-size -mattr=+sse2 | FileCheck %s -check-prefixes=SSE2
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=code-size -mattr=+ssse3 | FileCheck %s -check-prefixes=SSSE3
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=code-size -mattr=+sse4.2 | FileCheck %s -check-prefixes=SSE42
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=code-size -mattr=+avx | FileCheck %s -check-prefixes=AVX1
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=code-size -mattr=+avx2 | FileCheck %s -check-prefixes=AVX2
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=code-size -mattr=+avx512f | FileCheck %s -check-prefixes=AVX512F
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=code-size -mattr=+avx512vl,+avx512dq | FileCheck %s -check-prefixes=AVX512DQ
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=code-size -mattr=+avx512vl,+avx512bw | FileCheck %s -check-prefixes=AVX512BW
-
-declare i64        @llvm.smax.i64(i64, i64)
-declare <2 x i64>  @llvm.smax.v2i64(<2 x i64>, <2 x i64>)
-declare <4 x i64>  @llvm.smax.v4i64(<4 x i64>, <4 x i64>)
-declare <8 x i64>  @llvm.smax.v8i64(<8 x i64>, <8 x i64>)
-
-declare i32        @llvm.smax.i32(i32, i32)
-declare <4 x i32>  @llvm.smax.v4i32(<4 x i32>, <4 x i32>)
-declare <8 x i32>  @llvm.smax.v8i32(<8 x i32>, <8 x i32>)
-declare <16 x i32> @llvm.smax.v16i32(<16 x i32>, <16 x i32>)
-
-declare i16        @llvm.smax.i16(i16, i16)
-declare <8 x i16>  @llvm.smax.v8i16(<8 x i16>, <8 x i16>)
-declare <16 x i16> @llvm.smax.v16i16(<16 x i16>, <16 x i16>)
-declare <32 x i16> @llvm.smax.v32i16(<32 x i16>, <32 x i16>)
-
-declare i8         @llvm.smax.i8(i8,  i8)
-declare <16 x i8>  @llvm.smax.v16i8(<16 x i8>, <16 x i8>)
-declare <32 x i8>  @llvm.smax.v32i8(<32 x i8>, <32 x i8>)
-declare <64 x i8>  @llvm.smax.v64i8(<64 x i8>, <64 x i8>)
-
-define i32 @smax(i32 %arg) {
-; SSE2-LABEL: 'smax'
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %V4I64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V8I32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; SSSE3-LABEL: 'smax'
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %V4I64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V8I32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; SSE42-LABEL: 'smax'
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2I64 = call <2 x i64> @llvm.smax.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> @llvm.smax.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> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX1-LABEL: 'smax'
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V4I64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V8I32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX2-LABEL: 'smax'
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2I64 = call <2 x i64> @llvm.smax.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> @llvm.smax.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> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX512F-LABEL: 'smax'
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX512DQ-LABEL: 'smax'
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX512BW-LABEL: 'smax'
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-  %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
-  %V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
-  %V4I64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
-  %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
-
-  %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
-  %V4I32  = call <4 x i32>  @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
-  %V8I32  = call <8 x i32>  @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
-  %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
-
-  %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
-  %V8I16  = call <8 x i16>  @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
-  %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
-  %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
-
-  %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
-  %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
-  %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
-  %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
-
-  ret i32 undef
-}
-
-declare i64        @llvm.smin.i64(i64, i64)
-declare <2 x i64>  @llvm.smin.v2i64(<2 x i64>, <2 x i64>)
-declare <4 x i64>  @llvm.smin.v4i64(<4 x i64>, <4 x i64>)
-declare <8 x i64>  @llvm.smin.v8i64(<8 x i64>, <8 x i64>)
-
-declare i32        @llvm.smin.i32(i32, i32)
-declare <4 x i32>  @llvm.smin.v4i32(<4 x i32>, <4 x i32>)
-declare <8 x i32>  @llvm.smin.v8i32(<8 x i32>, <8 x i32>)
-declare <16 x i32> @llvm.smin.v16i32(<16 x i32>, <16 x i32>)
-
-declare i16        @llvm.smin.i16(i16, i16)
-declare <8 x i16>  @llvm.smin.v8i16(<8 x i16>, <8 x i16>)
-declare <16 x i16> @llvm.smin.v16i16(<16 x i16>, <16 x i16>)
-declare <32 x i16> @llvm.smin.v32i16(<32 x i16>, <32 x i16>)
-
-declare i8         @llvm.smin.i8(i8,  i8)
-declare <16 x i8>  @llvm.smin.v16i8(<16 x i8>, <16 x i8>)
-declare <32 x i8>  @llvm.smin.v32i8(<32 x i8>, <32 x i8>)
-declare <64 x i8>  @llvm.smin.v64i8(<64 x i8>, <64 x i8>)
-
-define i32 @smin(i32 %arg) {
-; SSE2-LABEL: 'smin'
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %V4I64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V8I32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; SSSE3-LABEL: 'smin'
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %V4I64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V8I32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; SSE42-LABEL: 'smin'
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2I64 = call <2 x i64> @llvm.smin.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> @llvm.smin.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> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX1-LABEL: 'smin'
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V4I64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V8I32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX2-LABEL: 'smin'
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2I64 = call <2 x i64> @llvm.smin.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> @llvm.smin.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> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX512F-LABEL: 'smin'
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX512DQ-LABEL: 'smin'
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX512BW-LABEL: 'smin'
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-  %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
-  %V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
-  %V4I64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
-  %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
-
-  %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
-  %V4I32  = call <4 x i32>  @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
-  %V8I32  = call <8 x i32>  @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
-  %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
-
-  %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
-  %V8I16  = call <8 x i16>  @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
-  %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
-  %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
-
-  %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
-  %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
-  %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
-  %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
-
-  ret i32 undef
-}

diff  --git a/llvm/test/Analysis/CostModel/X86/arith-sminmax-latency.ll b/llvm/test/Analysis/CostModel/X86/arith-sminmax-latency.ll
deleted file mode 100644
index e17fcdd34badf..0000000000000
--- a/llvm/test/Analysis/CostModel/X86/arith-sminmax-latency.ll
+++ /dev/null
@@ -1,401 +0,0 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=latency -mattr=+sse2 | FileCheck %s -check-prefixes=SSE2
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=latency -mattr=+ssse3 | FileCheck %s -check-prefixes=SSSE3
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=latency -mattr=+sse4.2 | FileCheck %s -check-prefixes=SSE42
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=latency -mattr=+avx | FileCheck %s -check-prefixes=AVX1
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=latency -mattr=+avx2 | FileCheck %s -check-prefixes=AVX2
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=latency -mattr=+avx512f | FileCheck %s -check-prefixes=AVX512F
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=latency -mattr=+avx512vl,+avx512dq | FileCheck %s -check-prefixes=AVX512DQ
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=latency -mattr=+avx512vl,+avx512bw | FileCheck %s -check-prefixes=AVX512BW
-
-declare i64        @llvm.smax.i64(i64, i64)
-declare <2 x i64>  @llvm.smax.v2i64(<2 x i64>, <2 x i64>)
-declare <4 x i64>  @llvm.smax.v4i64(<4 x i64>, <4 x i64>)
-declare <8 x i64>  @llvm.smax.v8i64(<8 x i64>, <8 x i64>)
-
-declare i32        @llvm.smax.i32(i32, i32)
-declare <4 x i32>  @llvm.smax.v4i32(<4 x i32>, <4 x i32>)
-declare <8 x i32>  @llvm.smax.v8i32(<8 x i32>, <8 x i32>)
-declare <16 x i32> @llvm.smax.v16i32(<16 x i32>, <16 x i32>)
-
-declare i16        @llvm.smax.i16(i16, i16)
-declare <8 x i16>  @llvm.smax.v8i16(<8 x i16>, <8 x i16>)
-declare <16 x i16> @llvm.smax.v16i16(<16 x i16>, <16 x i16>)
-declare <32 x i16> @llvm.smax.v32i16(<32 x i16>, <32 x i16>)
-
-declare i8         @llvm.smax.i8(i8,  i8)
-declare <16 x i8>  @llvm.smax.v16i8(<16 x i8>, <16 x i8>)
-declare <32 x i8>  @llvm.smax.v32i8(<32 x i8>, <32 x i8>)
-declare <64 x i8>  @llvm.smax.v64i8(<64 x i8>, <64 x i8>)
-
-define i32 @smax(i32 %arg) {
-; SSE2-LABEL: 'smax'
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V4I64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8I32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; SSSE3-LABEL: 'smax'
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V4I64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8I32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; SSE42-LABEL: 'smax'
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V4I64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX1-LABEL: 'smax'
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V4I64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V8I32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX2-LABEL: 'smax'
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2I64 = call <2 x i64> @llvm.smax.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> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX512F-LABEL: 'smax'
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V4I64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX512DQ-LABEL: 'smax'
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V4I64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX512BW-LABEL: 'smax'
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V4I64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-  %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
-  %V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
-  %V4I64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
-  %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
-
-  %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
-  %V4I32  = call <4 x i32>  @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
-  %V8I32  = call <8 x i32>  @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
-  %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
-
-  %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
-  %V8I16  = call <8 x i16>  @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
-  %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
-  %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
-
-  %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
-  %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
-  %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
-  %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
-
-  ret i32 undef
-}
-
-declare i64        @llvm.smin.i64(i64, i64)
-declare <2 x i64>  @llvm.smin.v2i64(<2 x i64>, <2 x i64>)
-declare <4 x i64>  @llvm.smin.v4i64(<4 x i64>, <4 x i64>)
-declare <8 x i64>  @llvm.smin.v8i64(<8 x i64>, <8 x i64>)
-
-declare i32        @llvm.smin.i32(i32, i32)
-declare <4 x i32>  @llvm.smin.v4i32(<4 x i32>, <4 x i32>)
-declare <8 x i32>  @llvm.smin.v8i32(<8 x i32>, <8 x i32>)
-declare <16 x i32> @llvm.smin.v16i32(<16 x i32>, <16 x i32>)
-
-declare i16        @llvm.smin.i16(i16, i16)
-declare <8 x i16>  @llvm.smin.v8i16(<8 x i16>, <8 x i16>)
-declare <16 x i16> @llvm.smin.v16i16(<16 x i16>, <16 x i16>)
-declare <32 x i16> @llvm.smin.v32i16(<32 x i16>, <32 x i16>)
-
-declare i8         @llvm.smin.i8(i8,  i8)
-declare <16 x i8>  @llvm.smin.v16i8(<16 x i8>, <16 x i8>)
-declare <32 x i8>  @llvm.smin.v32i8(<32 x i8>, <32 x i8>)
-declare <64 x i8>  @llvm.smin.v64i8(<64 x i8>, <64 x i8>)
-
-define i32 @smin(i32 %arg) {
-; SSE2-LABEL: 'smin'
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V4I64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8I32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; SSSE3-LABEL: 'smin'
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V4I64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8I32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; SSE42-LABEL: 'smin'
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V4I64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX1-LABEL: 'smin'
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V4I64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V8I32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX2-LABEL: 'smin'
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2I64 = call <2 x i64> @llvm.smin.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> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX512F-LABEL: 'smin'
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V4I64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX512DQ-LABEL: 'smin'
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V4I64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX512BW-LABEL: 'smin'
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V4I64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-  %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
-  %V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
-  %V4I64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
-  %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
-
-  %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
-  %V4I32  = call <4 x i32>  @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
-  %V8I32  = call <8 x i32>  @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
-  %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
-
-  %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
-  %V8I16  = call <8 x i16>  @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
-  %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
-  %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
-
-  %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
-  %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
-  %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
-  %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
-
-  ret i32 undef
-}

diff  --git a/llvm/test/Analysis/CostModel/X86/arith-sminmax-sizelatency.ll b/llvm/test/Analysis/CostModel/X86/arith-sminmax-sizelatency.ll
deleted file mode 100644
index 085039701799d..0000000000000
--- a/llvm/test/Analysis/CostModel/X86/arith-sminmax-sizelatency.ll
+++ /dev/null
@@ -1,401 +0,0 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=size-latency -mattr=+sse2 | FileCheck %s -check-prefixes=SSE2
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=size-latency -mattr=+ssse3 | FileCheck %s -check-prefixes=SSSE3
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=size-latency -mattr=+sse4.2 | FileCheck %s -check-prefixes=SSE42
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=size-latency -mattr=+avx | FileCheck %s -check-prefixes=AVX1
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=size-latency -mattr=+avx2 | FileCheck %s -check-prefixes=AVX2
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=size-latency -mattr=+avx512f | FileCheck %s -check-prefixes=AVX512F
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=size-latency -mattr=+avx512vl,+avx512dq | FileCheck %s -check-prefixes=AVX512DQ
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=size-latency -mattr=+avx512vl,+avx512bw | FileCheck %s -check-prefixes=AVX512BW
-
-declare i64        @llvm.smax.i64(i64, i64)
-declare <2 x i64>  @llvm.smax.v2i64(<2 x i64>, <2 x i64>)
-declare <4 x i64>  @llvm.smax.v4i64(<4 x i64>, <4 x i64>)
-declare <8 x i64>  @llvm.smax.v8i64(<8 x i64>, <8 x i64>)
-
-declare i32        @llvm.smax.i32(i32, i32)
-declare <4 x i32>  @llvm.smax.v4i32(<4 x i32>, <4 x i32>)
-declare <8 x i32>  @llvm.smax.v8i32(<8 x i32>, <8 x i32>)
-declare <16 x i32> @llvm.smax.v16i32(<16 x i32>, <16 x i32>)
-
-declare i16        @llvm.smax.i16(i16, i16)
-declare <8 x i16>  @llvm.smax.v8i16(<8 x i16>, <8 x i16>)
-declare <16 x i16> @llvm.smax.v16i16(<16 x i16>, <16 x i16>)
-declare <32 x i16> @llvm.smax.v32i16(<32 x i16>, <32 x i16>)
-
-declare i8         @llvm.smax.i8(i8,  i8)
-declare <16 x i8>  @llvm.smax.v16i8(<16 x i8>, <16 x i8>)
-declare <32 x i8>  @llvm.smax.v32i8(<32 x i8>, <32 x i8>)
-declare <64 x i8>  @llvm.smax.v64i8(<64 x i8>, <64 x i8>)
-
-define i32 @smax(i32 %arg) {
-; SSE2-LABEL: 'smax'
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %V4I64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V8I32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; SSSE3-LABEL: 'smax'
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %V4I64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V8I32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; SSE42-LABEL: 'smax'
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V4I64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX1-LABEL: 'smax'
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V4I64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V8I32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX2-LABEL: 'smax'
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V4I64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.smax.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> @llvm.smax.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> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smax.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> @llvm.smax.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> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.smax.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> @llvm.smax.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> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX512F-LABEL: 'smax'
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.smax.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> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smax.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> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.smax.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> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX512DQ-LABEL: 'smax'
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.smax.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> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smax.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> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.smax.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> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX512BW-LABEL: 'smax'
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.smax.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> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smax.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> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.smax.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> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-  %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
-  %V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
-  %V4I64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
-  %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
-
-  %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
-  %V4I32  = call <4 x i32>  @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
-  %V8I32  = call <8 x i32>  @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
-  %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
-
-  %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
-  %V8I16  = call <8 x i16>  @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
-  %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
-  %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
-
-  %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
-  %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
-  %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
-  %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
-
-  ret i32 undef
-}
-
-declare i64        @llvm.smin.i64(i64, i64)
-declare <2 x i64>  @llvm.smin.v2i64(<2 x i64>, <2 x i64>)
-declare <4 x i64>  @llvm.smin.v4i64(<4 x i64>, <4 x i64>)
-declare <8 x i64>  @llvm.smin.v8i64(<8 x i64>, <8 x i64>)
-
-declare i32        @llvm.smin.i32(i32, i32)
-declare <4 x i32>  @llvm.smin.v4i32(<4 x i32>, <4 x i32>)
-declare <8 x i32>  @llvm.smin.v8i32(<8 x i32>, <8 x i32>)
-declare <16 x i32> @llvm.smin.v16i32(<16 x i32>, <16 x i32>)
-
-declare i16        @llvm.smin.i16(i16, i16)
-declare <8 x i16>  @llvm.smin.v8i16(<8 x i16>, <8 x i16>)
-declare <16 x i16> @llvm.smin.v16i16(<16 x i16>, <16 x i16>)
-declare <32 x i16> @llvm.smin.v32i16(<32 x i16>, <32 x i16>)
-
-declare i8         @llvm.smin.i8(i8,  i8)
-declare <16 x i8>  @llvm.smin.v16i8(<16 x i8>, <16 x i8>)
-declare <32 x i8>  @llvm.smin.v32i8(<32 x i8>, <32 x i8>)
-declare <64 x i8>  @llvm.smin.v64i8(<64 x i8>, <64 x i8>)
-
-define i32 @smin(i32 %arg) {
-; SSE2-LABEL: 'smin'
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %V4I64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V8I32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; SSSE3-LABEL: 'smin'
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %V4I64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V8I32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; SSE42-LABEL: 'smin'
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V4I64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX1-LABEL: 'smin'
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V4I64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V8I32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX2-LABEL: 'smin'
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V4I64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.smin.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> @llvm.smin.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> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smin.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> @llvm.smin.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> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.smin.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> @llvm.smin.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> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX512F-LABEL: 'smin'
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.smin.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> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smin.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> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.smin.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> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX512DQ-LABEL: 'smin'
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.smin.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> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smin.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> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.smin.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> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX512BW-LABEL: 'smin'
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.smin.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> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smin.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> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.smin.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> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-  %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
-  %V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
-  %V4I64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
-  %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
-
-  %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
-  %V4I32  = call <4 x i32>  @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
-  %V8I32  = call <8 x i32>  @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
-  %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
-
-  %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
-  %V8I16  = call <8 x i16>  @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
-  %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
-  %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
-
-  %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
-  %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
-  %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
-  %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
-
-  ret i32 undef
-}

diff  --git a/llvm/test/Analysis/CostModel/X86/arith-sminmax.ll b/llvm/test/Analysis/CostModel/X86/arith-sminmax.ll
index 0810255fd082d..25e0f5a62247d 100644
--- a/llvm/test/Analysis/CostModel/X86/arith-sminmax.ll
+++ b/llvm/test/Analysis/CostModel/X86/arith-sminmax.ll
@@ -1,12 +1,12 @@
 ; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -mattr=+sse2 | FileCheck %s -check-prefixes=SSE2
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -mattr=+ssse3 | FileCheck %s -check-prefixes=SSSE3
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -mattr=+sse4.2 | FileCheck %s -check-prefixes=SSE42
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -mattr=+avx | FileCheck %s -check-prefixes=AVX1
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -mattr=+avx2 | FileCheck %s -check-prefixes=AVX2
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -mattr=+avx512f | FileCheck %s -check-prefixes=AVX512F
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -mattr=+avx512vl,+avx512dq | FileCheck %s -check-prefixes=AVX512DQ
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -mattr=+avx512vl,+avx512bw | FileCheck %s -check-prefixes=AVX512BW
+; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=all -mattr=+sse2 | FileCheck %s -check-prefixes=SSE2
+; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=all -mattr=+ssse3 | FileCheck %s -check-prefixes=SSSE3
+; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=all -mattr=+sse4.2 | FileCheck %s -check-prefixes=SSE42
+; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=all -mattr=+avx | FileCheck %s -check-prefixes=AVX1
+; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=all -mattr=+avx2 | FileCheck %s -check-prefixes=AVX2
+; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=all -mattr=+avx512f | FileCheck %s -check-prefixes=AVX512F
+; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=all -mattr=+avx512vl,+avx512dq | FileCheck %s -check-prefixes=AVX512DQ
+; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=all -mattr=+avx512vl,+avx512bw | FileCheck %s -check-prefixes=AVX512BW
 
 declare i64        @llvm.smax.i64(i64, i64)
 declare <2 x i64>  @llvm.smax.v2i64(<2 x i64>, <2 x i64>)
@@ -30,156 +30,156 @@ declare <64 x i8>  @llvm.smax.v64i8(<64 x i8>, <64 x i8>)
 
 define i32 @smax(i32 %arg) {
 ; SSE2-LABEL: 'smax'
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8I32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+; SSE2-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:3 SizeLat:3 for: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
+; SSE2-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:15 Lat:8 SizeLat:15 for: %V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
+; SSE2-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:30 Lat:16 SizeLat:30 for: %V4I64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
+; SSE2-NEXT:  Cost Model: Found costs of RThru:16 CodeSize:60 Lat:32 SizeLat:60 for: %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
+; SSE2-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:2 SizeLat:3 for: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
+; SSE2-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:5 Lat:4 SizeLat:5 for: %V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
+; SSE2-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:10 Lat:8 SizeLat:10 for: %V8I32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
+; SSE2-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:20 Lat:16 SizeLat:20 for: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
+; SSE2-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
+; SSE2-NEXT:  Cost Model: Found costs of 1 for: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
+; SSE2-NEXT:  Cost Model: Found costs of 2 for: %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
+; SSE2-NEXT:  Cost Model: Found costs of 4 for: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
+; SSE2-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
+; SSE2-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:5 Lat:4 SizeLat:5 for: %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
+; SSE2-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:10 Lat:8 SizeLat:10 for: %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
+; SSE2-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:20 Lat:16 SizeLat:20 for: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
+; SSE2-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
 ;
 ; SSSE3-LABEL: 'smax'
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call <4 x i32> @llvm.smax.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> @llvm.smax.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> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call <16 x i8> @llvm.smax.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> @llvm.smax.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> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:3 SizeLat:3 for: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:15 Lat:8 SizeLat:15 for: %V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:30 Lat:16 SizeLat:30 for: %V4I64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:16 CodeSize:60 Lat:32 SizeLat:60 for: %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:2 SizeLat:3 for: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:5 Lat:4 SizeLat:5 for: %V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:10 Lat:8 SizeLat:10 for: %V8I32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:20 Lat:16 SizeLat:20 for: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
+; SSSE3-NEXT:  Cost Model: Found costs of 1 for: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
+; SSSE3-NEXT:  Cost Model: Found costs of 2 for: %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
+; SSSE3-NEXT:  Cost Model: Found costs of 4 for: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:5 Lat:4 SizeLat:5 for: %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:10 Lat:8 SizeLat:10 for: %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:20 Lat:16 SizeLat:20 for: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
 ;
 ; SSE42-LABEL: 'smax'
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V4I64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+; SSE42-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:3 SizeLat:3 for: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
+; SSE42-NEXT:  Cost Model: Found costs of RThru:3 CodeSize:2 Lat:7 SizeLat:3 for: %V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
+; SSE42-NEXT:  Cost Model: Found costs of RThru:6 CodeSize:4 Lat:14 SizeLat:6 for: %V4I64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
+; SSE42-NEXT:  Cost Model: Found costs of RThru:12 CodeSize:8 Lat:28 SizeLat:12 for: %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
+; SSE42-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:2 SizeLat:3 for: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
+; SSE42-NEXT:  Cost Model: Found costs of 1 for: %V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
+; SSE42-NEXT:  Cost Model: Found costs of 2 for: %V8I32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
+; SSE42-NEXT:  Cost Model: Found costs of 4 for: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
+; SSE42-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
+; SSE42-NEXT:  Cost Model: Found costs of 1 for: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
+; SSE42-NEXT:  Cost Model: Found costs of 2 for: %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
+; SSE42-NEXT:  Cost Model: Found costs of 4 for: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
+; SSE42-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
+; SSE42-NEXT:  Cost Model: Found costs of 1 for: %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
+; SSE42-NEXT:  Cost Model: Found costs of 2 for: %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
+; SSE42-NEXT:  Cost Model: Found costs of 4 for: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
+; SSE42-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
 ;
 ; AVX1-LABEL: 'smax'
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V4I64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8I32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+; AVX1-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:3 SizeLat:3 for: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
+; AVX1-NEXT:  Cost Model: Found costs of RThru:3 CodeSize:2 Lat:7 SizeLat:4 for: %V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
+; AVX1-NEXT:  Cost Model: Found costs of RThru:6 CodeSize:6 Lat:9 SizeLat:12 for: %V4I64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
+; AVX1-NEXT:  Cost Model: Found costs of RThru:12 CodeSize:12 Lat:18 SizeLat:24 for: %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
+; AVX1-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:2 SizeLat:3 for: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
+; AVX1-NEXT:  Cost Model: Found costs of 1 for: %V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
+; AVX1-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:5 Lat:6 SizeLat:6 for: %V8I32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
+; AVX1-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:10 Lat:12 SizeLat:12 for: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
+; AVX1-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
+; AVX1-NEXT:  Cost Model: Found costs of 1 for: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
+; AVX1-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:5 Lat:6 SizeLat:6 for: %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
+; AVX1-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:10 Lat:12 SizeLat:12 for: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
+; AVX1-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
+; AVX1-NEXT:  Cost Model: Found costs of 1 for: %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
+; AVX1-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:5 Lat:6 SizeLat:6 for: %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
+; AVX1-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:10 Lat:12 SizeLat:12 for: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
+; AVX1-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
 ;
 ; AVX2-LABEL: 'smax'
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2I64 = call <2 x i64> @llvm.smax.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> @llvm.smax.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> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+; AVX2-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:3 SizeLat:3 for: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
+; AVX2-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:2 Lat:7 SizeLat:3 for: %V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
+; AVX2-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:2 Lat:7 SizeLat:3 for: %V4I64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
+; AVX2-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:4 Lat:14 SizeLat:6 for: %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
+; AVX2-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:2 SizeLat:3 for: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
+; AVX2-NEXT:  Cost Model: Found costs of 1 for: %V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
+; AVX2-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V8I32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
+; AVX2-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:2 Lat:2 SizeLat:4 for: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
+; AVX2-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
+; AVX2-NEXT:  Cost Model: Found costs of 1 for: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
+; AVX2-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
+; AVX2-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:2 Lat:2 SizeLat:4 for: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
+; AVX2-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
+; AVX2-NEXT:  Cost Model: Found costs of 1 for: %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
+; AVX2-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
+; AVX2-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:2 Lat:2 SizeLat:4 for: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
+; AVX2-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
 ;
 ; AVX512F-LABEL: 'smax'
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+; AVX512F-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:3 SizeLat:3 for: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
+; AVX512F-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
+; AVX512F-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V4I64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
+; AVX512F-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
+; AVX512F-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:2 SizeLat:3 for: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
+; AVX512F-NEXT:  Cost Model: Found costs of 1 for: %V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
+; AVX512F-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V8I32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
+; AVX512F-NEXT:  Cost Model: Found costs of 1 for: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
+; AVX512F-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
+; AVX512F-NEXT:  Cost Model: Found costs of 1 for: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
+; AVX512F-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
+; AVX512F-NEXT:  Cost Model: Found costs of RThru:3 CodeSize:5 Lat:7 SizeLat:5 for: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
+; AVX512F-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
+; AVX512F-NEXT:  Cost Model: Found costs of 1 for: %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
+; AVX512F-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
+; AVX512F-NEXT:  Cost Model: Found costs of RThru:3 CodeSize:5 Lat:7 SizeLat:5 for: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
+; AVX512F-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
 ;
 ; AVX512DQ-LABEL: 'smax'
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+; AVX512DQ-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:3 SizeLat:3 for: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V4I64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:2 SizeLat:3 for: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of 1 for: %V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V8I32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of 1 for: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of 1 for: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of RThru:3 CodeSize:5 Lat:7 SizeLat:5 for: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of 1 for: %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of RThru:3 CodeSize:5 Lat:7 SizeLat:5 for: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
 ;
 ; AVX512BW-LABEL: 'smax'
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+; AVX512BW-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:3 SizeLat:3 for: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V4I64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:2 SizeLat:3 for: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of 1 for: %V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V8I32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of 1 for: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of 1 for: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of 1 for: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of 1 for: %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of 1 for: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
 ;
   %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
   %V2I64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
@@ -226,156 +226,156 @@ declare <64 x i8>  @llvm.smin.v64i8(<64 x i8>, <64 x i8>)
 
 define i32 @smin(i32 %arg) {
 ; SSE2-LABEL: 'smin'
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8I32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+; SSE2-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:3 SizeLat:3 for: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
+; SSE2-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:15 Lat:8 SizeLat:15 for: %V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
+; SSE2-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:30 Lat:16 SizeLat:30 for: %V4I64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
+; SSE2-NEXT:  Cost Model: Found costs of RThru:16 CodeSize:60 Lat:32 SizeLat:60 for: %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
+; SSE2-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:2 SizeLat:3 for: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
+; SSE2-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:5 Lat:4 SizeLat:5 for: %V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
+; SSE2-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:10 Lat:8 SizeLat:10 for: %V8I32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
+; SSE2-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:20 Lat:16 SizeLat:20 for: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
+; SSE2-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
+; SSE2-NEXT:  Cost Model: Found costs of 1 for: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
+; SSE2-NEXT:  Cost Model: Found costs of 2 for: %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
+; SSE2-NEXT:  Cost Model: Found costs of 4 for: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
+; SSE2-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
+; SSE2-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:5 Lat:4 SizeLat:5 for: %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
+; SSE2-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:10 Lat:8 SizeLat:10 for: %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
+; SSE2-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:20 Lat:16 SizeLat:20 for: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
+; SSE2-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
 ;
 ; SSSE3-LABEL: 'smin'
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call <4 x i32> @llvm.smin.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> @llvm.smin.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> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call <16 x i8> @llvm.smin.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> @llvm.smin.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> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:3 SizeLat:3 for: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:15 Lat:8 SizeLat:15 for: %V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:30 Lat:16 SizeLat:30 for: %V4I64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:16 CodeSize:60 Lat:32 SizeLat:60 for: %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:2 SizeLat:3 for: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:5 Lat:4 SizeLat:5 for: %V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:10 Lat:8 SizeLat:10 for: %V8I32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:20 Lat:16 SizeLat:20 for: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
+; SSSE3-NEXT:  Cost Model: Found costs of 1 for: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
+; SSSE3-NEXT:  Cost Model: Found costs of 2 for: %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
+; SSSE3-NEXT:  Cost Model: Found costs of 4 for: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:5 Lat:4 SizeLat:5 for: %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:10 Lat:8 SizeLat:10 for: %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:20 Lat:16 SizeLat:20 for: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
 ;
 ; SSE42-LABEL: 'smin'
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V4I64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+; SSE42-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:3 SizeLat:3 for: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
+; SSE42-NEXT:  Cost Model: Found costs of RThru:3 CodeSize:2 Lat:7 SizeLat:3 for: %V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
+; SSE42-NEXT:  Cost Model: Found costs of RThru:6 CodeSize:4 Lat:14 SizeLat:6 for: %V4I64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
+; SSE42-NEXT:  Cost Model: Found costs of RThru:12 CodeSize:8 Lat:28 SizeLat:12 for: %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
+; SSE42-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:2 SizeLat:3 for: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
+; SSE42-NEXT:  Cost Model: Found costs of 1 for: %V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
+; SSE42-NEXT:  Cost Model: Found costs of 2 for: %V8I32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
+; SSE42-NEXT:  Cost Model: Found costs of 4 for: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
+; SSE42-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
+; SSE42-NEXT:  Cost Model: Found costs of 1 for: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
+; SSE42-NEXT:  Cost Model: Found costs of 2 for: %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
+; SSE42-NEXT:  Cost Model: Found costs of 4 for: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
+; SSE42-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
+; SSE42-NEXT:  Cost Model: Found costs of 1 for: %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
+; SSE42-NEXT:  Cost Model: Found costs of 2 for: %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
+; SSE42-NEXT:  Cost Model: Found costs of 4 for: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
+; SSE42-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
 ;
 ; AVX1-LABEL: 'smin'
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V4I64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8I32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+; AVX1-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:3 SizeLat:3 for: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
+; AVX1-NEXT:  Cost Model: Found costs of RThru:3 CodeSize:2 Lat:7 SizeLat:3 for: %V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
+; AVX1-NEXT:  Cost Model: Found costs of RThru:6 CodeSize:6 Lat:9 SizeLat:12 for: %V4I64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
+; AVX1-NEXT:  Cost Model: Found costs of RThru:12 CodeSize:12 Lat:18 SizeLat:24 for: %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
+; AVX1-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:2 SizeLat:3 for: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
+; AVX1-NEXT:  Cost Model: Found costs of 1 for: %V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
+; AVX1-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:5 Lat:6 SizeLat:6 for: %V8I32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
+; AVX1-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:10 Lat:12 SizeLat:12 for: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
+; AVX1-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
+; AVX1-NEXT:  Cost Model: Found costs of 1 for: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
+; AVX1-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:5 Lat:6 SizeLat:6 for: %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
+; AVX1-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:10 Lat:12 SizeLat:12 for: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
+; AVX1-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
+; AVX1-NEXT:  Cost Model: Found costs of 1 for: %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
+; AVX1-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:5 Lat:6 SizeLat:6 for: %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
+; AVX1-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:10 Lat:12 SizeLat:12 for: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
+; AVX1-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
 ;
 ; AVX2-LABEL: 'smin'
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2I64 = call <2 x i64> @llvm.smin.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> @llvm.smin.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> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+; AVX2-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:3 SizeLat:3 for: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
+; AVX2-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:2 Lat:7 SizeLat:3 for: %V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
+; AVX2-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:2 Lat:7 SizeLat:3 for: %V4I64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
+; AVX2-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:4 Lat:14 SizeLat:6 for: %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
+; AVX2-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:2 SizeLat:3 for: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
+; AVX2-NEXT:  Cost Model: Found costs of 1 for: %V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
+; AVX2-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V8I32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
+; AVX2-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:2 Lat:2 SizeLat:4 for: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
+; AVX2-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
+; AVX2-NEXT:  Cost Model: Found costs of 1 for: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
+; AVX2-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
+; AVX2-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:2 Lat:2 SizeLat:4 for: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
+; AVX2-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
+; AVX2-NEXT:  Cost Model: Found costs of 1 for: %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
+; AVX2-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
+; AVX2-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:2 Lat:2 SizeLat:4 for: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
+; AVX2-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
 ;
 ; AVX512F-LABEL: 'smin'
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+; AVX512F-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:3 SizeLat:3 for: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
+; AVX512F-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
+; AVX512F-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V4I64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
+; AVX512F-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
+; AVX512F-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:2 SizeLat:3 for: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
+; AVX512F-NEXT:  Cost Model: Found costs of 1 for: %V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
+; AVX512F-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V8I32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
+; AVX512F-NEXT:  Cost Model: Found costs of 1 for: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
+; AVX512F-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
+; AVX512F-NEXT:  Cost Model: Found costs of 1 for: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
+; AVX512F-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
+; AVX512F-NEXT:  Cost Model: Found costs of RThru:3 CodeSize:5 Lat:7 SizeLat:5 for: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
+; AVX512F-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
+; AVX512F-NEXT:  Cost Model: Found costs of 1 for: %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
+; AVX512F-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
+; AVX512F-NEXT:  Cost Model: Found costs of RThru:3 CodeSize:5 Lat:7 SizeLat:5 for: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
+; AVX512F-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
 ;
 ; AVX512DQ-LABEL: 'smin'
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+; AVX512DQ-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:3 SizeLat:3 for: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V4I64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:2 SizeLat:3 for: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of 1 for: %V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V8I32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of 1 for: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of 1 for: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of RThru:3 CodeSize:5 Lat:7 SizeLat:5 for: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of 1 for: %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of RThru:3 CodeSize:5 Lat:7 SizeLat:5 for: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
 ;
 ; AVX512BW-LABEL: 'smin'
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+; AVX512BW-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:3 SizeLat:3 for: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V4I64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:2 SizeLat:3 for: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of 1 for: %V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V8I32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of 1 for: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of 1 for: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of 1 for: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of 1 for: %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of 1 for: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
 ;
   %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
   %V2I64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)

diff  --git a/llvm/test/Analysis/CostModel/X86/arith-uminmax-codesize.ll b/llvm/test/Analysis/CostModel/X86/arith-uminmax-codesize.ll
deleted file mode 100644
index a1e35425ca670..0000000000000
--- a/llvm/test/Analysis/CostModel/X86/arith-uminmax-codesize.ll
+++ /dev/null
@@ -1,401 +0,0 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=code-size -mattr=+sse2 | FileCheck %s -check-prefixes=SSE2
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=code-size -mattr=+ssse3 | FileCheck %s -check-prefixes=SSSE3
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=code-size -mattr=+sse4.2 | FileCheck %s -check-prefixes=SSE42
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=code-size -mattr=+avx | FileCheck %s -check-prefixes=AVX1
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=code-size -mattr=+avx2 | FileCheck %s -check-prefixes=AVX2
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=code-size -mattr=+avx512f | FileCheck %s -check-prefixes=AVX512F
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=code-size -mattr=+avx512vl,+avx512dq | FileCheck %s -check-prefixes=AVX512DQ
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=code-size -mattr=+avx512vl,+avx512bw | FileCheck %s -check-prefixes=AVX512BW
-
-declare i64        @llvm.umax.i64(i64, i64)
-declare <2 x i64>  @llvm.umax.v2i64(<2 x i64>, <2 x i64>)
-declare <4 x i64>  @llvm.umax.v4i64(<4 x i64>, <4 x i64>)
-declare <8 x i64>  @llvm.umax.v8i64(<8 x i64>, <8 x i64>)
-
-declare i32        @llvm.umax.i32(i32, i32)
-declare <4 x i32>  @llvm.umax.v4i32(<4 x i32>, <4 x i32>)
-declare <8 x i32>  @llvm.umax.v8i32(<8 x i32>, <8 x i32>)
-declare <16 x i32> @llvm.umax.v16i32(<16 x i32>, <16 x i32>)
-
-declare i16        @llvm.umax.i16(i16, i16)
-declare <8 x i16>  @llvm.umax.v8i16(<8 x i16>, <8 x i16>)
-declare <16 x i16> @llvm.umax.v16i16(<16 x i16>, <16 x i16>)
-declare <32 x i16> @llvm.umax.v32i16(<32 x i16>, <32 x i16>)
-
-declare i8         @llvm.umax.i8(i8,  i8)
-declare <16 x i8>  @llvm.umax.v16i8(<16 x i8>, <16 x i8>)
-declare <32 x i8>  @llvm.umax.v32i8(<32 x i8>, <32 x i8>)
-declare <64 x i8>  @llvm.umax.v64i8(<64 x i8>, <64 x i8>)
-
-define i32 @umax(i32 %arg) {
-; SSE2-LABEL: 'umax'
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I64 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V2I64 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %V4I64 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %V8I64 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I32 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I32 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16I32 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V8I16 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V16I16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V32I16 = call <32 x i16> @llvm.umax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.umax.i8(i8 undef, i8 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = call <32 x i8> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V64I8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; SSSE3-LABEL: 'umax'
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I64 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V2I64 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %V4I64 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %V8I64 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I32 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I32 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16I32 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V8I16 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V16I16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V32I16 = call <32 x i16> @llvm.umax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.umax.i8(i8 undef, i8 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = call <32 x i8> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V64I8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; SSE42-LABEL: 'umax'
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I64 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2I64 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V4I64 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V8I64 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.umax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.umax.i8(i8 undef, i8 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = call <32 x i8> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V64I8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX1-LABEL: 'umax'
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I64 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2I64 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V4I64 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V8I64 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V8I32 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V16I32 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V16I16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32I16 = call <32 x i16> @llvm.umax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.umax.i8(i8 undef, i8 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V32I8 = call <32 x i8> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V64I8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX2-LABEL: 'umax'
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I64 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2I64 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4I64 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V8I64 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I32 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I16 = call <32 x i16> @llvm.umax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.umax.i8(i8 undef, i8 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = call <32 x i8> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V64I8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX512F-LABEL: 'umax'
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I64 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I64 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I64 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V32I16 = call <32 x i16> @llvm.umax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.umax.i8(i8 undef, i8 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = call <32 x i8> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V64I8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX512DQ-LABEL: 'umax'
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I64 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I64 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I64 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V32I16 = call <32 x i16> @llvm.umax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.umax.i8(i8 undef, i8 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = call <32 x i8> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V64I8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX512BW-LABEL: 'umax'
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I64 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I64 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I64 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I16 = call <32 x i16> @llvm.umax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.umax.i8(i8 undef, i8 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = call <32 x i8> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V64I8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-  %I64 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
-  %V2I64 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
-  %V4I64 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
-  %V8I64 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
-
-  %I32 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
-  %V4I32  = call <4 x i32>  @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef)
-  %V8I32  = call <8 x i32>  @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
-  %V16I32 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
-
-  %I16 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
-  %V8I16  = call <8 x i16>  @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
-  %V16I16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
-  %V32I16 = call <32 x i16> @llvm.umax.v32i16(<32 x i16> undef, <32 x i16> undef)
-
-  %I8 = call i8 @llvm.umax.i8(i8 undef, i8 undef)
-  %V16I8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
-  %V32I8 = call <32 x i8> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef)
-  %V64I8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
-
-  ret i32 undef
-}
-
-declare i64        @llvm.umin.i64(i64, i64)
-declare <2 x i64>  @llvm.umin.v2i64(<2 x i64>, <2 x i64>)
-declare <4 x i64>  @llvm.umin.v4i64(<4 x i64>, <4 x i64>)
-declare <8 x i64>  @llvm.umin.v8i64(<8 x i64>, <8 x i64>)
-
-declare i32        @llvm.umin.i32(i32, i32)
-declare <4 x i32>  @llvm.umin.v4i32(<4 x i32>, <4 x i32>)
-declare <8 x i32>  @llvm.umin.v8i32(<8 x i32>, <8 x i32>)
-declare <16 x i32> @llvm.umin.v16i32(<16 x i32>, <16 x i32>)
-
-declare i16        @llvm.umin.i16(i16, i16)
-declare <8 x i16>  @llvm.umin.v8i16(<8 x i16>, <8 x i16>)
-declare <16 x i16> @llvm.umin.v16i16(<16 x i16>, <16 x i16>)
-declare <32 x i16> @llvm.umin.v32i16(<32 x i16>, <32 x i16>)
-
-declare i8         @llvm.umin.i8(i8,  i8)
-declare <16 x i8>  @llvm.umin.v16i8(<16 x i8>, <16 x i8>)
-declare <32 x i8>  @llvm.umin.v32i8(<32 x i8>, <32 x i8>)
-declare <64 x i8>  @llvm.umin.v64i8(<64 x i8>, <64 x i8>)
-
-define i32 @umin(i32 %arg) {
-; SSE2-LABEL: 'umin'
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I64 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V2I64 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %V4I64 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %V8I64 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I32 = call <4 x i32> @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I32 = call <8 x i32> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16I32 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V8I16 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V16I16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V32I16 = call <32 x i16> @llvm.umin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.umin.i8(i8 undef, i8 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = call <32 x i8> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V64I8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; SSSE3-LABEL: 'umin'
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I64 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V2I64 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %V4I64 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %V8I64 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I32 = call <4 x i32> @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I32 = call <8 x i32> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16I32 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V8I16 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V16I16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V32I16 = call <32 x i16> @llvm.umin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.umin.i8(i8 undef, i8 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = call <32 x i8> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V64I8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; SSE42-LABEL: 'umin'
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I64 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2I64 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V4I64 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V8I64 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.umin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.umin.i8(i8 undef, i8 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = call <32 x i8> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V64I8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX1-LABEL: 'umin'
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I64 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2I64 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V4I64 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V8I64 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V8I32 = call <8 x i32> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V16I32 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V16I16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V32I16 = call <32 x i16> @llvm.umin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.umin.i8(i8 undef, i8 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V32I8 = call <32 x i8> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V64I8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX2-LABEL: 'umin'
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I64 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V2I64 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4I64 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V8I64 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = call <8 x i32> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I32 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I16 = call <32 x i16> @llvm.umin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.umin.i8(i8 undef, i8 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = call <32 x i8> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V64I8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX512F-LABEL: 'umin'
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I64 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I64 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I64 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = call <8 x i32> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V32I16 = call <32 x i16> @llvm.umin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.umin.i8(i8 undef, i8 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = call <32 x i8> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V64I8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX512DQ-LABEL: 'umin'
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I64 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I64 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I64 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = call <8 x i32> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V32I16 = call <32 x i16> @llvm.umin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.umin.i8(i8 undef, i8 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = call <32 x i8> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V64I8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX512BW-LABEL: 'umin'
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I64 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I64 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I64 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = call <8 x i32> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I16 = call <32 x i16> @llvm.umin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.umin.i8(i8 undef, i8 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = call <32 x i8> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V64I8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-  %I64 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
-  %V2I64 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
-  %V4I64 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
-  %V8I64 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
-
-  %I32 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
-  %V4I32  = call <4 x i32>  @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef)
-  %V8I32  = call <8 x i32>  @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
-  %V16I32 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
-
-  %I16 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
-  %V8I16  = call <8 x i16>  @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
-  %V16I16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
-  %V32I16 = call <32 x i16> @llvm.umin.v32i16(<32 x i16> undef, <32 x i16> undef)
-
-  %I8 = call i8 @llvm.umin.i8(i8 undef, i8 undef)
-  %V16I8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
-  %V32I8 = call <32 x i8> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef)
-  %V64I8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
-
-  ret i32 undef
-}

diff  --git a/llvm/test/Analysis/CostModel/X86/arith-uminmax-latency.ll b/llvm/test/Analysis/CostModel/X86/arith-uminmax-latency.ll
deleted file mode 100644
index 7e77653aa15cf..0000000000000
--- a/llvm/test/Analysis/CostModel/X86/arith-uminmax-latency.ll
+++ /dev/null
@@ -1,401 +0,0 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=latency -mattr=+sse2 | FileCheck %s -check-prefixes=SSE2
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=latency -mattr=+ssse3 | FileCheck %s -check-prefixes=SSSE3
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=latency -mattr=+sse4.2 | FileCheck %s -check-prefixes=SSE42
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=latency -mattr=+avx | FileCheck %s -check-prefixes=AVX1
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=latency -mattr=+avx2 | FileCheck %s -check-prefixes=AVX2
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=latency -mattr=+avx512f | FileCheck %s -check-prefixes=AVX512F
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=latency -mattr=+avx512vl,+avx512dq | FileCheck %s -check-prefixes=AVX512DQ
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=latency -mattr=+avx512vl,+avx512bw | FileCheck %s -check-prefixes=AVX512BW
-
-declare i64        @llvm.umax.i64(i64, i64)
-declare <2 x i64>  @llvm.umax.v2i64(<2 x i64>, <2 x i64>)
-declare <4 x i64>  @llvm.umax.v4i64(<4 x i64>, <4 x i64>)
-declare <8 x i64>  @llvm.umax.v8i64(<8 x i64>, <8 x i64>)
-
-declare i32        @llvm.umax.i32(i32, i32)
-declare <4 x i32>  @llvm.umax.v4i32(<4 x i32>, <4 x i32>)
-declare <8 x i32>  @llvm.umax.v8i32(<8 x i32>, <8 x i32>)
-declare <16 x i32> @llvm.umax.v16i32(<16 x i32>, <16 x i32>)
-
-declare i16        @llvm.umax.i16(i16, i16)
-declare <8 x i16>  @llvm.umax.v8i16(<8 x i16>, <8 x i16>)
-declare <16 x i16> @llvm.umax.v16i16(<16 x i16>, <16 x i16>)
-declare <32 x i16> @llvm.umax.v32i16(<32 x i16>, <32 x i16>)
-
-declare i8         @llvm.umax.i8(i8,  i8)
-declare <16 x i8>  @llvm.umax.v16i8(<16 x i8>, <16 x i8>)
-declare <32 x i8>  @llvm.umax.v32i8(<32 x i8>, <32 x i8>)
-declare <64 x i8>  @llvm.umax.v64i8(<64 x i8>, <64 x i8>)
-
-define i32 @umax(i32 %arg) {
-; SSE2-LABEL: 'umax'
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V2I64 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V4I64 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V8I64 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4I32 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V8I32 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V16I32 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V8I16 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V16I16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V32I16 = call <32 x i16> @llvm.umax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.umax.i8(i8 undef, i8 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = call <32 x i8> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V64I8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; SSSE3-LABEL: 'umax'
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V2I64 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V4I64 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V8I64 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4I32 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V8I32 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V16I32 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V8I16 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V16I16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V32I16 = call <32 x i16> @llvm.umax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.umax.i8(i8 undef, i8 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = call <32 x i8> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V64I8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; SSE42-LABEL: 'umax'
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V2I64 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V4I64 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: %V8I64 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.umax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.umax.i8(i8 undef, i8 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = call <32 x i8> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V64I8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX1-LABEL: 'umax'
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V2I64 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V4I64 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V8I64 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V8I32 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V16I32 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V16I16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V32I16 = call <32 x i16> @llvm.umax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.umax.i8(i8 undef, i8 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V32I8 = call <32 x i8> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V64I8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX2-LABEL: 'umax'
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V2I64 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I64 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I64 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I32 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I16 = call <32 x i16> @llvm.umax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.umax.i8(i8 undef, i8 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = call <32 x i8> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V64I8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX512F-LABEL: 'umax'
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2I64 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V4I64 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V8I64 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V32I16 = call <32 x i16> @llvm.umax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.umax.i8(i8 undef, i8 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = call <32 x i8> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V64I8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX512DQ-LABEL: 'umax'
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2I64 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V4I64 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V8I64 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V32I16 = call <32 x i16> @llvm.umax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.umax.i8(i8 undef, i8 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = call <32 x i8> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V64I8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX512BW-LABEL: 'umax'
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2I64 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V4I64 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V8I64 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I16 = call <32 x i16> @llvm.umax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.umax.i8(i8 undef, i8 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = call <32 x i8> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V64I8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-  %I64 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
-  %V2I64 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
-  %V4I64 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
-  %V8I64 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
-
-  %I32 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
-  %V4I32  = call <4 x i32>  @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef)
-  %V8I32  = call <8 x i32>  @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
-  %V16I32 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
-
-  %I16 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
-  %V8I16  = call <8 x i16>  @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
-  %V16I16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
-  %V32I16 = call <32 x i16> @llvm.umax.v32i16(<32 x i16> undef, <32 x i16> undef)
-
-  %I8 = call i8 @llvm.umax.i8(i8 undef, i8 undef)
-  %V16I8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
-  %V32I8 = call <32 x i8> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef)
-  %V64I8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
-
-  ret i32 undef
-}
-
-declare i64        @llvm.umin.i64(i64, i64)
-declare <2 x i64>  @llvm.umin.v2i64(<2 x i64>, <2 x i64>)
-declare <4 x i64>  @llvm.umin.v4i64(<4 x i64>, <4 x i64>)
-declare <8 x i64>  @llvm.umin.v8i64(<8 x i64>, <8 x i64>)
-
-declare i32        @llvm.umin.i32(i32, i32)
-declare <4 x i32>  @llvm.umin.v4i32(<4 x i32>, <4 x i32>)
-declare <8 x i32>  @llvm.umin.v8i32(<8 x i32>, <8 x i32>)
-declare <16 x i32> @llvm.umin.v16i32(<16 x i32>, <16 x i32>)
-
-declare i16        @llvm.umin.i16(i16, i16)
-declare <8 x i16>  @llvm.umin.v8i16(<8 x i16>, <8 x i16>)
-declare <16 x i16> @llvm.umin.v16i16(<16 x i16>, <16 x i16>)
-declare <32 x i16> @llvm.umin.v32i16(<32 x i16>, <32 x i16>)
-
-declare i8         @llvm.umin.i8(i8,  i8)
-declare <16 x i8>  @llvm.umin.v16i8(<16 x i8>, <16 x i8>)
-declare <32 x i8>  @llvm.umin.v32i8(<32 x i8>, <32 x i8>)
-declare <64 x i8>  @llvm.umin.v64i8(<64 x i8>, <64 x i8>)
-
-define i32 @umin(i32 %arg) {
-; SSE2-LABEL: 'umin'
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V2I64 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V4I64 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V8I64 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4I32 = call <4 x i32> @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V8I32 = call <8 x i32> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V16I32 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V8I16 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V16I16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V32I16 = call <32 x i16> @llvm.umin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.umin.i8(i8 undef, i8 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = call <32 x i8> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V64I8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; SSSE3-LABEL: 'umin'
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V2I64 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V4I64 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V8I64 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V4I32 = call <4 x i32> @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V8I32 = call <8 x i32> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V16I32 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V8I16 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V16I16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V32I16 = call <32 x i16> @llvm.umin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.umin.i8(i8 undef, i8 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = call <32 x i8> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V64I8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; SSE42-LABEL: 'umin'
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V2I64 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V4I64 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: %V8I64 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.umin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.umin.i8(i8 undef, i8 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = call <32 x i8> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V64I8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX1-LABEL: 'umin'
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V2I64 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %V4I64 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %V8I64 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V8I32 = call <8 x i32> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V16I32 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V16I16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V32I16 = call <32 x i16> @llvm.umin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.umin.i8(i8 undef, i8 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V32I8 = call <32 x i8> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V64I8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX2-LABEL: 'umin'
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V2I64 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I64 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I64 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = call <8 x i32> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I32 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I16 = call <32 x i16> @llvm.umin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.umin.i8(i8 undef, i8 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = call <32 x i8> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V64I8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX512F-LABEL: 'umin'
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2I64 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V4I64 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V8I64 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = call <8 x i32> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V32I16 = call <32 x i16> @llvm.umin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.umin.i8(i8 undef, i8 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = call <32 x i8> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V64I8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX512DQ-LABEL: 'umin'
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2I64 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V4I64 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V8I64 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = call <8 x i32> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V32I16 = call <32 x i16> @llvm.umin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.umin.i8(i8 undef, i8 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = call <32 x i8> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V64I8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX512BW-LABEL: 'umin'
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V2I64 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V4I64 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V8I64 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = call <8 x i32> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I16 = call <32 x i16> @llvm.umin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.umin.i8(i8 undef, i8 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = call <32 x i8> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V64I8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-  %I64 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
-  %V2I64 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
-  %V4I64 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
-  %V8I64 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
-
-  %I32 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
-  %V4I32  = call <4 x i32>  @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef)
-  %V8I32  = call <8 x i32>  @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
-  %V16I32 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
-
-  %I16 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
-  %V8I16  = call <8 x i16>  @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
-  %V16I16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
-  %V32I16 = call <32 x i16> @llvm.umin.v32i16(<32 x i16> undef, <32 x i16> undef)
-
-  %I8 = call i8 @llvm.umin.i8(i8 undef, i8 undef)
-  %V16I8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
-  %V32I8 = call <32 x i8> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef)
-  %V64I8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
-
-  ret i32 undef
-}

diff  --git a/llvm/test/Analysis/CostModel/X86/arith-uminmax-sizelatency.ll b/llvm/test/Analysis/CostModel/X86/arith-uminmax-sizelatency.ll
deleted file mode 100644
index 0ee8f427787c8..0000000000000
--- a/llvm/test/Analysis/CostModel/X86/arith-uminmax-sizelatency.ll
+++ /dev/null
@@ -1,401 +0,0 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=size-latency -mattr=+sse2 | FileCheck %s -check-prefixes=SSE2
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=size-latency -mattr=+ssse3 | FileCheck %s -check-prefixes=SSSE3
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=size-latency -mattr=+sse4.2 | FileCheck %s -check-prefixes=SSE42
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=size-latency -mattr=+avx | FileCheck %s -check-prefixes=AVX1
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=size-latency -mattr=+avx2 | FileCheck %s -check-prefixes=AVX2
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=size-latency -mattr=+avx512f | FileCheck %s -check-prefixes=AVX512F
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=size-latency -mattr=+avx512vl,+avx512dq | FileCheck %s -check-prefixes=AVX512DQ
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=size-latency -mattr=+avx512vl,+avx512bw | FileCheck %s -check-prefixes=AVX512BW
-
-declare i64        @llvm.umax.i64(i64, i64)
-declare <2 x i64>  @llvm.umax.v2i64(<2 x i64>, <2 x i64>)
-declare <4 x i64>  @llvm.umax.v4i64(<4 x i64>, <4 x i64>)
-declare <8 x i64>  @llvm.umax.v8i64(<8 x i64>, <8 x i64>)
-
-declare i32        @llvm.umax.i32(i32, i32)
-declare <4 x i32>  @llvm.umax.v4i32(<4 x i32>, <4 x i32>)
-declare <8 x i32>  @llvm.umax.v8i32(<8 x i32>, <8 x i32>)
-declare <16 x i32> @llvm.umax.v16i32(<16 x i32>, <16 x i32>)
-
-declare i16        @llvm.umax.i16(i16, i16)
-declare <8 x i16>  @llvm.umax.v8i16(<8 x i16>, <8 x i16>)
-declare <16 x i16> @llvm.umax.v16i16(<16 x i16>, <16 x i16>)
-declare <32 x i16> @llvm.umax.v32i16(<32 x i16>, <32 x i16>)
-
-declare i8         @llvm.umax.i8(i8,  i8)
-declare <16 x i8>  @llvm.umax.v16i8(<16 x i8>, <16 x i8>)
-declare <32 x i8>  @llvm.umax.v32i8(<32 x i8>, <32 x i8>)
-declare <64 x i8>  @llvm.umax.v64i8(<64 x i8>, <64 x i8>)
-
-define i32 @umax(i32 %arg) {
-; SSE2-LABEL: 'umax'
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V2I64 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %V4I64 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %V8I64 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I32 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I32 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16I32 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V8I16 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V16I16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V32I16 = call <32 x i16> @llvm.umax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.umax.i8(i8 undef, i8 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = call <32 x i8> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V64I8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; SSSE3-LABEL: 'umax'
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V2I64 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %V4I64 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %V8I64 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I32 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I32 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16I32 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V8I16 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V16I16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V32I16 = call <32 x i16> @llvm.umax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.umax.i8(i8 undef, i8 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = call <32 x i8> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V64I8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; SSE42-LABEL: 'umax'
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2I64 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V4I64 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V8I64 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.umax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.umax.i8(i8 undef, i8 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = call <32 x i8> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V64I8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX1-LABEL: 'umax'
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2I64 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V4I64 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %V8I64 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V8I32 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V16I32 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V16I16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V32I16 = call <32 x i16> @llvm.umax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.umax.i8(i8 undef, i8 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V32I8 = call <32 x i8> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V64I8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX2-LABEL: 'umax'
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2I64 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I64 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I64 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.umax.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> @llvm.umax.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> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umax.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> @llvm.umax.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> @llvm.umax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.umax.i8(i8 undef, i8 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umax.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> @llvm.umax.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> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX512F-LABEL: 'umax'
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I64 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I64 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.umax.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> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umax.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> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V32I16 = call <32 x i16> @llvm.umax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.umax.i8(i8 undef, i8 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umax.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> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V64I8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX512DQ-LABEL: 'umax'
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I64 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I64 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.umax.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> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umax.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> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V32I16 = call <32 x i16> @llvm.umax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.umax.i8(i8 undef, i8 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umax.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> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V64I8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX512BW-LABEL: 'umax'
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I64 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I64 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.umax.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> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umax.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> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I16 = call <32 x i16> @llvm.umax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.umax.i8(i8 undef, i8 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umax.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> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V64I8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-  %I64 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
-  %V2I64 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
-  %V4I64 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
-  %V8I64 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
-
-  %I32 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
-  %V4I32  = call <4 x i32>  @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef)
-  %V8I32  = call <8 x i32>  @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
-  %V16I32 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
-
-  %I16 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
-  %V8I16  = call <8 x i16>  @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
-  %V16I16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
-  %V32I16 = call <32 x i16> @llvm.umax.v32i16(<32 x i16> undef, <32 x i16> undef)
-
-  %I8 = call i8 @llvm.umax.i8(i8 undef, i8 undef)
-  %V16I8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
-  %V32I8 = call <32 x i8> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef)
-  %V64I8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
-
-  ret i32 undef
-}
-
-declare i64        @llvm.umin.i64(i64, i64)
-declare <2 x i64>  @llvm.umin.v2i64(<2 x i64>, <2 x i64>)
-declare <4 x i64>  @llvm.umin.v4i64(<4 x i64>, <4 x i64>)
-declare <8 x i64>  @llvm.umin.v8i64(<8 x i64>, <8 x i64>)
-
-declare i32        @llvm.umin.i32(i32, i32)
-declare <4 x i32>  @llvm.umin.v4i32(<4 x i32>, <4 x i32>)
-declare <8 x i32>  @llvm.umin.v8i32(<8 x i32>, <8 x i32>)
-declare <16 x i32> @llvm.umin.v16i32(<16 x i32>, <16 x i32>)
-
-declare i16        @llvm.umin.i16(i16, i16)
-declare <8 x i16>  @llvm.umin.v8i16(<8 x i16>, <8 x i16>)
-declare <16 x i16> @llvm.umin.v16i16(<16 x i16>, <16 x i16>)
-declare <32 x i16> @llvm.umin.v32i16(<32 x i16>, <32 x i16>)
-
-declare i8         @llvm.umin.i8(i8,  i8)
-declare <16 x i8>  @llvm.umin.v16i8(<16 x i8>, <16 x i8>)
-declare <32 x i8>  @llvm.umin.v32i8(<32 x i8>, <32 x i8>)
-declare <64 x i8>  @llvm.umin.v64i8(<64 x i8>, <64 x i8>)
-
-define i32 @umin(i32 %arg) {
-; SSE2-LABEL: 'umin'
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V2I64 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %V4I64 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %V8I64 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I32 = call <4 x i32> @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I32 = call <8 x i32> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16I32 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V8I16 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V16I16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V32I16 = call <32 x i16> @llvm.umin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.umin.i8(i8 undef, i8 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = call <32 x i8> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V64I8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; SSSE3-LABEL: 'umin'
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V2I64 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %V4I64 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %V8I64 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I32 = call <4 x i32> @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I32 = call <8 x i32> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16I32 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V8I16 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V16I16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V32I16 = call <32 x i16> @llvm.umin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.umin.i8(i8 undef, i8 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = call <32 x i8> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V64I8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; SSE42-LABEL: 'umin'
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2I64 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %V4I64 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %V8I64 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.umin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.umin.i8(i8 undef, i8 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = call <32 x i8> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V64I8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX1-LABEL: 'umin'
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2I64 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V4I64 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %V8I64 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V8I32 = call <8 x i32> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V16I32 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V16I16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V32I16 = call <32 x i16> @llvm.umin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.umin.i8(i8 undef, i8 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V32I8 = call <32 x i8> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V64I8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX2-LABEL: 'umin'
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2I64 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I64 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I64 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.umin.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> @llvm.umin.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> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umin.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> @llvm.umin.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> @llvm.umin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.umin.i8(i8 undef, i8 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umin.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> @llvm.umin.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> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX512F-LABEL: 'umin'
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I64 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I64 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.umin.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> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umin.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> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V32I16 = call <32 x i16> @llvm.umin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.umin.i8(i8 undef, i8 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umin.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> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V64I8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX512DQ-LABEL: 'umin'
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I64 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I64 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.umin.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> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umin.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> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V32I16 = call <32 x i16> @llvm.umin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.umin.i8(i8 undef, i8 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umin.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> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V64I8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-; AVX512BW-LABEL: 'umin'
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I64 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I64 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I32 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.umin.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> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umin.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> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I16 = call <32 x i16> @llvm.umin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call i8 @llvm.umin.i8(i8 undef, i8 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umin.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> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V64I8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
-;
-  %I64 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
-  %V2I64 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
-  %V4I64 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
-  %V8I64 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
-
-  %I32 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
-  %V4I32  = call <4 x i32>  @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef)
-  %V8I32  = call <8 x i32>  @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
-  %V16I32 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
-
-  %I16 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
-  %V8I16  = call <8 x i16>  @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
-  %V16I16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
-  %V32I16 = call <32 x i16> @llvm.umin.v32i16(<32 x i16> undef, <32 x i16> undef)
-
-  %I8 = call i8 @llvm.umin.i8(i8 undef, i8 undef)
-  %V16I8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
-  %V32I8 = call <32 x i8> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef)
-  %V64I8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
-
-  ret i32 undef
-}

diff  --git a/llvm/test/Analysis/CostModel/X86/arith-uminmax.ll b/llvm/test/Analysis/CostModel/X86/arith-uminmax.ll
index e233a7a30041e..7fc6fcf91cc7c 100644
--- a/llvm/test/Analysis/CostModel/X86/arith-uminmax.ll
+++ b/llvm/test/Analysis/CostModel/X86/arith-uminmax.ll
@@ -1,12 +1,12 @@
 ; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -mattr=+sse2 | FileCheck %s -check-prefixes=SSE2
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -mattr=+ssse3 | FileCheck %s -check-prefixes=SSSE3
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -mattr=+sse4.2 | FileCheck %s -check-prefixes=SSE42
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -mattr=+avx | FileCheck %s -check-prefixes=AVX1
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -mattr=+avx2 | FileCheck %s -check-prefixes=AVX2
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -mattr=+avx512f | FileCheck %s -check-prefixes=AVX512F
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -mattr=+avx512vl,+avx512dq | FileCheck %s -check-prefixes=AVX512DQ
-; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -mattr=+avx512vl,+avx512bw | FileCheck %s -check-prefixes=AVX512BW
+; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=all -mattr=+sse2 | FileCheck %s -check-prefixes=SSE2
+; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=all -mattr=+ssse3 | FileCheck %s -check-prefixes=SSSE3
+; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=all -mattr=+sse4.2 | FileCheck %s -check-prefixes=SSE42
+; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=all -mattr=+avx | FileCheck %s -check-prefixes=AVX1
+; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=all -mattr=+avx2 | FileCheck %s -check-prefixes=AVX2
+; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=all -mattr=+avx512f | FileCheck %s -check-prefixes=AVX512F
+; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=all -mattr=+avx512vl,+avx512dq | FileCheck %s -check-prefixes=AVX512DQ
+; RUN: opt < %s -mtriple=x86_64-- -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=all -mattr=+avx512vl,+avx512bw | FileCheck %s -check-prefixes=AVX512BW
 
 declare i64        @llvm.umax.i64(i64, i64)
 declare <2 x i64>  @llvm.umax.v2i64(<2 x i64>, <2 x i64>)
@@ -30,156 +30,156 @@ declare <64 x i8>  @llvm.umax.v64i8(<64 x i8>, <64 x i8>)
 
 define i32 @umax(i32 %arg) {
 ; SSE2-LABEL: 'umax'
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2I64 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I64 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I64 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8I32 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16I32 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.umax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.umax.i8(i8 undef, i8 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = call <32 x i8> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V64I8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+; SSE2-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:3 SizeLat:3 for: %I64 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
+; SSE2-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:15 Lat:8 SizeLat:15 for: %V2I64 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
+; SSE2-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:30 Lat:16 SizeLat:30 for: %V4I64 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
+; SSE2-NEXT:  Cost Model: Found costs of RThru:16 CodeSize:60 Lat:32 SizeLat:60 for: %V8I64 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
+; SSE2-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:2 SizeLat:3 for: %I32 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
+; SSE2-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:8 Lat:5 SizeLat:8 for: %V4I32 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef)
+; SSE2-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:16 Lat:10 SizeLat:16 for: %V8I32 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
+; SSE2-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:32 Lat:20 SizeLat:32 for: %V16I32 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
+; SSE2-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I16 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
+; SSE2-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:3 Lat:3 SizeLat:3 for: %V8I16 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
+; SSE2-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:6 Lat:6 SizeLat:6 for: %V16I16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
+; SSE2-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:12 Lat:12 SizeLat:12 for: %V32I16 = call <32 x i16> @llvm.umax.v32i16(<32 x i16> undef, <32 x i16> undef)
+; SSE2-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I8 = call i8 @llvm.umax.i8(i8 undef, i8 undef)
+; SSE2-NEXT:  Cost Model: Found costs of 1 for: %V16I8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
+; SSE2-NEXT:  Cost Model: Found costs of 2 for: %V32I8 = call <32 x i8> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef)
+; SSE2-NEXT:  Cost Model: Found costs of 4 for: %V64I8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
+; SSE2-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
 ;
 ; SSSE3-LABEL: 'umax'
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2I64 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I64 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I64 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call <4 x i32> @llvm.umax.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> @llvm.umax.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> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.umax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.umax.i8(i8 undef, i8 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = call <32 x i8> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V64I8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:3 SizeLat:3 for: %I64 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:15 Lat:8 SizeLat:15 for: %V2I64 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:30 Lat:16 SizeLat:30 for: %V4I64 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:16 CodeSize:60 Lat:32 SizeLat:60 for: %V8I64 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:2 SizeLat:3 for: %I32 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:8 Lat:5 SizeLat:8 for: %V4I32 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef)
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:16 Lat:10 SizeLat:16 for: %V8I32 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:32 Lat:20 SizeLat:32 for: %V16I32 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I16 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:3 Lat:3 SizeLat:3 for: %V8I16 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:6 Lat:6 SizeLat:6 for: %V16I16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:12 Lat:12 SizeLat:12 for: %V32I16 = call <32 x i16> @llvm.umax.v32i16(<32 x i16> undef, <32 x i16> undef)
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I8 = call i8 @llvm.umax.i8(i8 undef, i8 undef)
+; SSSE3-NEXT:  Cost Model: Found costs of 1 for: %V16I8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
+; SSSE3-NEXT:  Cost Model: Found costs of 2 for: %V32I8 = call <32 x i8> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef)
+; SSSE3-NEXT:  Cost Model: Found costs of 4 for: %V64I8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
 ;
 ; SSE42-LABEL: 'umax'
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2I64 = call <2 x i64> @llvm.umax.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> @llvm.umax.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> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.umax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.umax.i8(i8 undef, i8 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = call <32 x i8> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V64I8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+; SSE42-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:3 SizeLat:3 for: %I64 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
+; SSE42-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:6 Lat:11 SizeLat:7 for: %V2I64 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
+; SSE42-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:12 Lat:22 SizeLat:14 for: %V4I64 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
+; SSE42-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:24 Lat:44 SizeLat:28 for: %V8I64 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
+; SSE42-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:2 SizeLat:3 for: %I32 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
+; SSE42-NEXT:  Cost Model: Found costs of 1 for: %V4I32 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef)
+; SSE42-NEXT:  Cost Model: Found costs of 2 for: %V8I32 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
+; SSE42-NEXT:  Cost Model: Found costs of 4 for: %V16I32 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
+; SSE42-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I16 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
+; SSE42-NEXT:  Cost Model: Found costs of 1 for: %V8I16 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
+; SSE42-NEXT:  Cost Model: Found costs of 2 for: %V16I16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
+; SSE42-NEXT:  Cost Model: Found costs of 4 for: %V32I16 = call <32 x i16> @llvm.umax.v32i16(<32 x i16> undef, <32 x i16> undef)
+; SSE42-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I8 = call i8 @llvm.umax.i8(i8 undef, i8 undef)
+; SSE42-NEXT:  Cost Model: Found costs of 1 for: %V16I8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
+; SSE42-NEXT:  Cost Model: Found costs of 2 for: %V32I8 = call <32 x i8> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef)
+; SSE42-NEXT:  Cost Model: Found costs of 4 for: %V64I8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
+; SSE42-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
 ;
 ; AVX1-LABEL: 'umax'
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2I64 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V4I64 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %V8I64 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8I32 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16I32 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = call <32 x i16> @llvm.umax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.umax.i8(i8 undef, i8 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I8 = call <32 x i8> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V64I8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+; AVX1-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:3 SizeLat:3 for: %I64 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
+; AVX1-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:5 Lat:8 SizeLat:7 for: %V2I64 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
+; AVX1-NEXT:  Cost Model: Found costs of RThru:9 CodeSize:11 Lat:10 SizeLat:17 for: %V4I64 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
+; AVX1-NEXT:  Cost Model: Found costs of RThru:18 CodeSize:22 Lat:20 SizeLat:34 for: %V8I64 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
+; AVX1-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:2 SizeLat:3 for: %I32 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
+; AVX1-NEXT:  Cost Model: Found costs of 1 for: %V4I32 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef)
+; AVX1-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:5 Lat:6 SizeLat:6 for: %V8I32 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
+; AVX1-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:10 Lat:12 SizeLat:12 for: %V16I32 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
+; AVX1-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I16 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
+; AVX1-NEXT:  Cost Model: Found costs of 1 for: %V8I16 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
+; AVX1-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:5 Lat:6 SizeLat:6 for: %V16I16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
+; AVX1-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:10 Lat:12 SizeLat:12 for: %V32I16 = call <32 x i16> @llvm.umax.v32i16(<32 x i16> undef, <32 x i16> undef)
+; AVX1-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I8 = call i8 @llvm.umax.i8(i8 undef, i8 undef)
+; AVX1-NEXT:  Cost Model: Found costs of 1 for: %V16I8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
+; AVX1-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:5 Lat:6 SizeLat:6 for: %V32I8 = call <32 x i8> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef)
+; AVX1-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:10 Lat:12 SizeLat:12 for: %V64I8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
+; AVX1-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
 ;
 ; AVX2-LABEL: 'umax'
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2I64 = call <2 x i64> @llvm.umax.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> @llvm.umax.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> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I32 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I16 = call <32 x i16> @llvm.umax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.umax.i8(i8 undef, i8 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = call <32 x i8> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V64I8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+; AVX2-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:3 SizeLat:3 for: %I64 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
+; AVX2-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:5 Lat:8 SizeLat:6 for: %V2I64 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
+; AVX2-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:5 Lat:8 SizeLat:8 for: %V4I64 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
+; AVX2-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:10 Lat:16 SizeLat:16 for: %V8I64 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
+; AVX2-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:2 SizeLat:3 for: %I32 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
+; AVX2-NEXT:  Cost Model: Found costs of 1 for: %V4I32 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef)
+; AVX2-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V8I32 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
+; AVX2-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:2 Lat:2 SizeLat:4 for: %V16I32 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
+; AVX2-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I16 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
+; AVX2-NEXT:  Cost Model: Found costs of 1 for: %V8I16 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
+; AVX2-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V16I16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
+; AVX2-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:2 Lat:2 SizeLat:4 for: %V32I16 = call <32 x i16> @llvm.umax.v32i16(<32 x i16> undef, <32 x i16> undef)
+; AVX2-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I8 = call i8 @llvm.umax.i8(i8 undef, i8 undef)
+; AVX2-NEXT:  Cost Model: Found costs of 1 for: %V16I8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
+; AVX2-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V32I8 = call <32 x i8> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef)
+; AVX2-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:2 Lat:2 SizeLat:4 for: %V64I8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
+; AVX2-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
 ;
 ; AVX512F-LABEL: 'umax'
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I64 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I64 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V32I16 = call <32 x i16> @llvm.umax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.umax.i8(i8 undef, i8 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = call <32 x i8> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V64I8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+; AVX512F-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:3 SizeLat:3 for: %I64 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
+; AVX512F-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V2I64 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
+; AVX512F-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V4I64 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
+; AVX512F-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V8I64 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
+; AVX512F-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:2 SizeLat:3 for: %I32 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
+; AVX512F-NEXT:  Cost Model: Found costs of 1 for: %V4I32 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef)
+; AVX512F-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V8I32 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
+; AVX512F-NEXT:  Cost Model: Found costs of 1 for: %V16I32 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
+; AVX512F-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I16 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
+; AVX512F-NEXT:  Cost Model: Found costs of 1 for: %V8I16 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
+; AVX512F-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V16I16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
+; AVX512F-NEXT:  Cost Model: Found costs of RThru:3 CodeSize:5 Lat:7 SizeLat:5 for: %V32I16 = call <32 x i16> @llvm.umax.v32i16(<32 x i16> undef, <32 x i16> undef)
+; AVX512F-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I8 = call i8 @llvm.umax.i8(i8 undef, i8 undef)
+; AVX512F-NEXT:  Cost Model: Found costs of 1 for: %V16I8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
+; AVX512F-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V32I8 = call <32 x i8> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef)
+; AVX512F-NEXT:  Cost Model: Found costs of RThru:3 CodeSize:5 Lat:7 SizeLat:5 for: %V64I8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
+; AVX512F-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
 ;
 ; AVX512DQ-LABEL: 'umax'
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I64 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I64 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V32I16 = call <32 x i16> @llvm.umax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.umax.i8(i8 undef, i8 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = call <32 x i8> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V64I8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+; AVX512DQ-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:3 SizeLat:3 for: %I64 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V2I64 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V4I64 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V8I64 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:2 SizeLat:3 for: %I32 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of 1 for: %V4I32 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V8I32 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of 1 for: %V16I32 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I16 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of 1 for: %V8I16 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V16I16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of RThru:3 CodeSize:5 Lat:7 SizeLat:5 for: %V32I16 = call <32 x i16> @llvm.umax.v32i16(<32 x i16> undef, <32 x i16> undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I8 = call i8 @llvm.umax.i8(i8 undef, i8 undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of 1 for: %V16I8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V32I8 = call <32 x i8> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of RThru:3 CodeSize:5 Lat:7 SizeLat:5 for: %V64I8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
 ;
 ; AVX512BW-LABEL: 'umax'
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I64 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I64 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I16 = call <32 x i16> @llvm.umax.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.umax.i8(i8 undef, i8 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = call <32 x i8> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V64I8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+; AVX512BW-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:3 SizeLat:3 for: %I64 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V2I64 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V4I64 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V8I64 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:2 SizeLat:3 for: %I32 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of 1 for: %V4I32 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V8I32 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of 1 for: %V16I32 = call <16 x i32> @llvm.umax.v16i32(<16 x i32> undef, <16 x i32> undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I16 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of 1 for: %V8I16 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V16I16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of 1 for: %V32I16 = call <32 x i16> @llvm.umax.v32i16(<32 x i16> undef, <32 x i16> undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I8 = call i8 @llvm.umax.i8(i8 undef, i8 undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of 1 for: %V16I8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V32I8 = call <32 x i8> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of 1 for: %V64I8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
 ;
   %I64 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
   %V2I64 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
@@ -226,156 +226,156 @@ declare <64 x i8>  @llvm.umin.v64i8(<64 x i8>, <64 x i8>)
 
 define i32 @umin(i32 %arg) {
 ; SSE2-LABEL: 'umin'
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2I64 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I64 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I64 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call <4 x i32> @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8I32 = call <8 x i32> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16I32 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.umin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.umin.i8(i8 undef, i8 undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = call <32 x i8> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V64I8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+; SSE2-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:3 SizeLat:3 for: %I64 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
+; SSE2-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:15 Lat:8 SizeLat:15 for: %V2I64 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
+; SSE2-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:30 Lat:16 SizeLat:30 for: %V4I64 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
+; SSE2-NEXT:  Cost Model: Found costs of RThru:16 CodeSize:60 Lat:32 SizeLat:60 for: %V8I64 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
+; SSE2-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:2 SizeLat:3 for: %I32 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
+; SSE2-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:8 Lat:5 SizeLat:8 for: %V4I32 = call <4 x i32> @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef)
+; SSE2-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:16 Lat:10 SizeLat:16 for: %V8I32 = call <8 x i32> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
+; SSE2-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:32 Lat:20 SizeLat:32 for: %V16I32 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
+; SSE2-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I16 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
+; SSE2-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:3 Lat:3 SizeLat:3 for: %V8I16 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
+; SSE2-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:6 Lat:6 SizeLat:6 for: %V16I16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
+; SSE2-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:12 Lat:12 SizeLat:12 for: %V32I16 = call <32 x i16> @llvm.umin.v32i16(<32 x i16> undef, <32 x i16> undef)
+; SSE2-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I8 = call i8 @llvm.umin.i8(i8 undef, i8 undef)
+; SSE2-NEXT:  Cost Model: Found costs of 1 for: %V16I8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
+; SSE2-NEXT:  Cost Model: Found costs of 2 for: %V32I8 = call <32 x i8> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef)
+; SSE2-NEXT:  Cost Model: Found costs of 4 for: %V64I8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
+; SSE2-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
 ;
 ; SSSE3-LABEL: 'umin'
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2I64 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I64 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I64 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4I32 = call <4 x i32> @llvm.umin.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> @llvm.umin.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> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.umin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.umin.i8(i8 undef, i8 undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = call <32 x i8> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V64I8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; SSSE3-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:3 SizeLat:3 for: %I64 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:15 Lat:8 SizeLat:15 for: %V2I64 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:30 Lat:16 SizeLat:30 for: %V4I64 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:16 CodeSize:60 Lat:32 SizeLat:60 for: %V8I64 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:2 SizeLat:3 for: %I32 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:8 Lat:5 SizeLat:8 for: %V4I32 = call <4 x i32> @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef)
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:16 Lat:10 SizeLat:16 for: %V8I32 = call <8 x i32> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:32 Lat:20 SizeLat:32 for: %V16I32 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I16 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:3 Lat:3 SizeLat:3 for: %V8I16 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:6 Lat:6 SizeLat:6 for: %V16I16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:12 Lat:12 SizeLat:12 for: %V32I16 = call <32 x i16> @llvm.umin.v32i16(<32 x i16> undef, <32 x i16> undef)
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I8 = call i8 @llvm.umin.i8(i8 undef, i8 undef)
+; SSSE3-NEXT:  Cost Model: Found costs of 1 for: %V16I8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
+; SSSE3-NEXT:  Cost Model: Found costs of 2 for: %V32I8 = call <32 x i8> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef)
+; SSSE3-NEXT:  Cost Model: Found costs of 4 for: %V64I8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
+; SSSE3-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
 ;
 ; SSE42-LABEL: 'umin'
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2I64 = call <2 x i64> @llvm.umin.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> @llvm.umin.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> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8I32 = call <8 x i32> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16I32 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I16 = call <32 x i16> @llvm.umin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.umin.i8(i8 undef, i8 undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I8 = call <32 x i8> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V64I8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+; SSE42-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:3 SizeLat:3 for: %I64 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
+; SSE42-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:6 Lat:11 SizeLat:7 for: %V2I64 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
+; SSE42-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:12 Lat:22 SizeLat:14 for: %V4I64 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
+; SSE42-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:24 Lat:44 SizeLat:28 for: %V8I64 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
+; SSE42-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:2 SizeLat:3 for: %I32 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
+; SSE42-NEXT:  Cost Model: Found costs of 1 for: %V4I32 = call <4 x i32> @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef)
+; SSE42-NEXT:  Cost Model: Found costs of 2 for: %V8I32 = call <8 x i32> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
+; SSE42-NEXT:  Cost Model: Found costs of 4 for: %V16I32 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
+; SSE42-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I16 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
+; SSE42-NEXT:  Cost Model: Found costs of 1 for: %V8I16 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
+; SSE42-NEXT:  Cost Model: Found costs of 2 for: %V16I16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
+; SSE42-NEXT:  Cost Model: Found costs of 4 for: %V32I16 = call <32 x i16> @llvm.umin.v32i16(<32 x i16> undef, <32 x i16> undef)
+; SSE42-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I8 = call i8 @llvm.umin.i8(i8 undef, i8 undef)
+; SSE42-NEXT:  Cost Model: Found costs of 1 for: %V16I8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
+; SSE42-NEXT:  Cost Model: Found costs of 2 for: %V32I8 = call <32 x i8> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef)
+; SSE42-NEXT:  Cost Model: Found costs of 4 for: %V64I8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
+; SSE42-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
 ;
 ; AVX1-LABEL: 'umin'
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2I64 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V4I64 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %V8I64 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V8I32 = call <8 x i32> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V16I32 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V16I16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V32I16 = call <32 x i16> @llvm.umin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.umin.i8(i8 undef, i8 undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V32I8 = call <32 x i8> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V64I8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+; AVX1-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:3 SizeLat:3 for: %I64 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
+; AVX1-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:5 Lat:8 SizeLat:7 for: %V2I64 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
+; AVX1-NEXT:  Cost Model: Found costs of RThru:9 CodeSize:11 Lat:10 SizeLat:17 for: %V4I64 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
+; AVX1-NEXT:  Cost Model: Found costs of RThru:18 CodeSize:22 Lat:20 SizeLat:34 for: %V8I64 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
+; AVX1-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:2 SizeLat:3 for: %I32 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
+; AVX1-NEXT:  Cost Model: Found costs of 1 for: %V4I32 = call <4 x i32> @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef)
+; AVX1-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:5 Lat:6 SizeLat:6 for: %V8I32 = call <8 x i32> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
+; AVX1-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:10 Lat:12 SizeLat:12 for: %V16I32 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
+; AVX1-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I16 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
+; AVX1-NEXT:  Cost Model: Found costs of 1 for: %V8I16 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
+; AVX1-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:5 Lat:6 SizeLat:6 for: %V16I16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
+; AVX1-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:10 Lat:12 SizeLat:12 for: %V32I16 = call <32 x i16> @llvm.umin.v32i16(<32 x i16> undef, <32 x i16> undef)
+; AVX1-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I8 = call i8 @llvm.umin.i8(i8 undef, i8 undef)
+; AVX1-NEXT:  Cost Model: Found costs of 1 for: %V16I8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
+; AVX1-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:5 Lat:6 SizeLat:6 for: %V32I8 = call <32 x i8> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef)
+; AVX1-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:10 Lat:12 SizeLat:12 for: %V64I8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
+; AVX1-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
 ;
 ; AVX2-LABEL: 'umin'
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2I64 = call <2 x i64> @llvm.umin.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> @llvm.umin.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> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = call <8 x i32> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16I32 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V32I16 = call <32 x i16> @llvm.umin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.umin.i8(i8 undef, i8 undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = call <32 x i8> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V64I8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+; AVX2-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:3 SizeLat:3 for: %I64 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
+; AVX2-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:5 Lat:8 SizeLat:6 for: %V2I64 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
+; AVX2-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:5 Lat:8 SizeLat:8 for: %V4I64 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
+; AVX2-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:10 Lat:16 SizeLat:16 for: %V8I64 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
+; AVX2-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:2 SizeLat:3 for: %I32 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
+; AVX2-NEXT:  Cost Model: Found costs of 1 for: %V4I32 = call <4 x i32> @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef)
+; AVX2-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V8I32 = call <8 x i32> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
+; AVX2-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:2 Lat:2 SizeLat:4 for: %V16I32 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
+; AVX2-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I16 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
+; AVX2-NEXT:  Cost Model: Found costs of 1 for: %V8I16 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
+; AVX2-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V16I16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
+; AVX2-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:2 Lat:2 SizeLat:4 for: %V32I16 = call <32 x i16> @llvm.umin.v32i16(<32 x i16> undef, <32 x i16> undef)
+; AVX2-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I8 = call i8 @llvm.umin.i8(i8 undef, i8 undef)
+; AVX2-NEXT:  Cost Model: Found costs of 1 for: %V16I8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
+; AVX2-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V32I8 = call <32 x i8> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef)
+; AVX2-NEXT:  Cost Model: Found costs of RThru:2 CodeSize:2 Lat:2 SizeLat:4 for: %V64I8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
+; AVX2-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
 ;
 ; AVX512F-LABEL: 'umin'
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I64 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I64 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = call <8 x i32> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V32I16 = call <32 x i16> @llvm.umin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.umin.i8(i8 undef, i8 undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = call <32 x i8> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V64I8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX512F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+; AVX512F-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:3 SizeLat:3 for: %I64 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
+; AVX512F-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V2I64 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
+; AVX512F-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V4I64 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
+; AVX512F-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V8I64 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
+; AVX512F-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:2 SizeLat:3 for: %I32 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
+; AVX512F-NEXT:  Cost Model: Found costs of 1 for: %V4I32 = call <4 x i32> @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef)
+; AVX512F-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V8I32 = call <8 x i32> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
+; AVX512F-NEXT:  Cost Model: Found costs of 1 for: %V16I32 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
+; AVX512F-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I16 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
+; AVX512F-NEXT:  Cost Model: Found costs of 1 for: %V8I16 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
+; AVX512F-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V16I16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
+; AVX512F-NEXT:  Cost Model: Found costs of RThru:3 CodeSize:5 Lat:7 SizeLat:5 for: %V32I16 = call <32 x i16> @llvm.umin.v32i16(<32 x i16> undef, <32 x i16> undef)
+; AVX512F-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I8 = call i8 @llvm.umin.i8(i8 undef, i8 undef)
+; AVX512F-NEXT:  Cost Model: Found costs of 1 for: %V16I8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
+; AVX512F-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V32I8 = call <32 x i8> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef)
+; AVX512F-NEXT:  Cost Model: Found costs of RThru:3 CodeSize:5 Lat:7 SizeLat:5 for: %V64I8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
+; AVX512F-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
 ;
 ; AVX512DQ-LABEL: 'umin'
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I64 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I64 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = call <8 x i32> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V32I16 = call <32 x i16> @llvm.umin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.umin.i8(i8 undef, i8 undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = call <32 x i8> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V64I8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX512DQ-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+; AVX512DQ-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:3 SizeLat:3 for: %I64 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V2I64 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V4I64 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V8I64 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:2 SizeLat:3 for: %I32 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of 1 for: %V4I32 = call <4 x i32> @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V8I32 = call <8 x i32> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of 1 for: %V16I32 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I16 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of 1 for: %V8I16 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V16I16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of RThru:3 CodeSize:5 Lat:7 SizeLat:5 for: %V32I16 = call <32 x i16> @llvm.umin.v32i16(<32 x i16> undef, <32 x i16> undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I8 = call i8 @llvm.umin.i8(i8 undef, i8 undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of 1 for: %V16I8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V32I8 = call <32 x i8> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of RThru:3 CodeSize:5 Lat:7 SizeLat:5 for: %V64I8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
+; AVX512DQ-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
 ;
 ; AVX512BW-LABEL: 'umin'
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I64 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2I64 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I64 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I64 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I32 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4I32 = call <4 x i32> @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I32 = call <8 x i32> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I32 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I16 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8I16 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I16 = call <32 x i16> @llvm.umin.v32i16(<32 x i16> undef, <32 x i16> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %I8 = call i8 @llvm.umin.i8(i8 undef, i8 undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16I8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32I8 = call <32 x i8> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V64I8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
-; AVX512BW-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
+; AVX512BW-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:3 SizeLat:3 for: %I64 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V2I64 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V4I64 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V8I64 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:2 SizeLat:3 for: %I32 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of 1 for: %V4I32 = call <4 x i32> @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V8I32 = call <8 x i32> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of 1 for: %V16I32 = call <16 x i32> @llvm.umin.v16i32(<16 x i32> undef, <16 x i32> undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I16 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of 1 for: %V8I16 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V16I16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of 1 for: %V32I16 = call <32 x i16> @llvm.umin.v32i16(<32 x i16> undef, <32 x i16> undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:2 Lat:4 SizeLat:4 for: %I8 = call i8 @llvm.umin.i8(i8 undef, i8 undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of 1 for: %V16I8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of RThru:1 CodeSize:1 Lat:1 SizeLat:2 for: %V32I8 = call <32 x i8> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of 1 for: %V64I8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
+; AVX512BW-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
 ;
   %I64 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
   %V2I64 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)


        


More information about the llvm-commits mailing list