[llvm] a2120f6 - [NFC][AMDGPU][CostModel] Add tests for AMDGPU cost model, part 2.
Daniil Fukalov via llvm-commits
llvm-commits at lists.llvm.org
Wed Dec 22 11:34:48 PST 2021
Author: Daniil Fukalov
Date: 2021-12-22T22:33:57+03:00
New Revision: a2120f6b449103f517e541abb77839a1e3e12272
URL: https://github.com/llvm/llvm-project/commit/a2120f6b449103f517e541abb77839a1e3e12272
DIFF: https://github.com/llvm/llvm-project/commit/a2120f6b449103f517e541abb77839a1e3e12272.diff
LOG: [NFC][AMDGPU][CostModel] Add tests for AMDGPU cost model, part 2.
Added:
llvm/test/Analysis/CostModel/AMDGPU/aggregates.ll
llvm/test/Analysis/CostModel/AMDGPU/arith-fp.ll
llvm/test/Analysis/CostModel/AMDGPU/arith-sminmax.ll
llvm/test/Analysis/CostModel/AMDGPU/arith-uminmax.ll
llvm/test/Analysis/CostModel/AMDGPU/cast.ll
llvm/test/Analysis/CostModel/AMDGPU/div.ll
llvm/test/Analysis/CostModel/AMDGPU/fptosi.ll
llvm/test/Analysis/CostModel/AMDGPU/fptoui.ll
llvm/test/Analysis/CostModel/AMDGPU/fround.ll
llvm/test/Analysis/CostModel/AMDGPU/gep.ll
llvm/test/Analysis/CostModel/AMDGPU/rem.ll
Modified:
Removed:
################################################################################
diff --git a/llvm/test/Analysis/CostModel/AMDGPU/aggregates.ll b/llvm/test/Analysis/CostModel/AMDGPU/aggregates.ll
new file mode 100644
index 000000000000..4f9a30bc8841
--- /dev/null
+++ b/llvm/test/Analysis/CostModel/AMDGPU/aggregates.ll
@@ -0,0 +1,47 @@
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
+; RUN: opt -cost-model -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx1010 < %s | FileCheck -check-prefixes=ALL %s
+; RUN: opt -cost-model -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx90a < %s | FileCheck -check-prefixes=ALL %s
+; RUN: opt -cost-model -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx900 < %s | FileCheck -check-prefixes=ALL %s
+; RUN: opt -cost-model -analyze -mtriple=amdgcn-unknown-amdhsa < %s | FileCheck -check-prefixes=ALL %s
+
+; RUN: opt -cost-model -cost-kind=code-size -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx1010 < %s | FileCheck -check-prefixes=ALL-SIZE %s
+; RUN: opt -cost-model -cost-kind=code-size -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx90a < %s | FileCheck -check-prefixes=ALL-SIZE %s
+; RUN: opt -cost-model -cost-kind=code-size -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx900 < %s | FileCheck -check-prefixes=ALL-SIZE %s
+; RUN: opt -cost-model -cost-kind=code-size -analyze -mtriple=amdgcn-unknown-amdhsa < %s | FileCheck -check-prefixes=ALL-SIZE %s
+; END.
+
+%T1 = type { i32, float, <4 x i1> }
+
+define void @extract_1() {
+; ALL-LABEL: 'extract_1'
+; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r0 = extractvalue { i32, i32 } undef, 0
+; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r1 = extractvalue { i32, i32 } undef, 1
+; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r2 = extractvalue { i32, i1 } undef, 0
+; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r3 = extractvalue { i32, i1 } undef, 1
+; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r4 = extractvalue { i32, float } undef, 1
+; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r5 = extractvalue { i32, [42 x i42] } undef, 1
+; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r6 = extractvalue { i32, <42 x i42> } undef, 1
+; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r7 = extractvalue { i32, %T1 } undef, 1
+; ALL-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret void
+;
+; ALL-SIZE-LABEL: 'extract_1'
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r0 = extractvalue { i32, i32 } undef, 0
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r1 = extractvalue { i32, i32 } undef, 1
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r2 = extractvalue { i32, i1 } undef, 0
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r3 = extractvalue { i32, i1 } undef, 1
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r4 = extractvalue { i32, float } undef, 1
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r5 = extractvalue { i32, [42 x i42] } undef, 1
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r6 = extractvalue { i32, <42 x i42> } undef, 1
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r7 = extractvalue { i32, %T1 } undef, 1
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
+;
+ %r0 = extractvalue {i32, i32} undef, 0
+ %r1 = extractvalue {i32, i32} undef, 1
+ %r2 = extractvalue {i32, i1} undef, 0
+ %r3 = extractvalue {i32, i1} undef, 1
+ %r4 = extractvalue {i32, float} undef, 1
+ %r5 = extractvalue {i32, [42 x i42]} undef, 1
+ %r6 = extractvalue {i32, <42 x i42>} undef, 1
+ %r7 = extractvalue {i32, %T1} undef, 1
+ ret void
+}
diff --git a/llvm/test/Analysis/CostModel/AMDGPU/arith-fp.ll b/llvm/test/Analysis/CostModel/AMDGPU/arith-fp.ll
new file mode 100644
index 000000000000..01913a7204a6
--- /dev/null
+++ b/llvm/test/Analysis/CostModel/AMDGPU/arith-fp.ll
@@ -0,0 +1,103 @@
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
+; RUN: opt -cost-model -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx1010 < %s | FileCheck -check-prefixes=ALL %s
+; RUN: opt -cost-model -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx90a < %s | FileCheck -check-prefixes=ALL %s
+; RUN: opt -cost-model -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx900 < %s | FileCheck -check-prefixes=ALL %s
+; RUN: opt -cost-model -analyze -mtriple=amdgcn-unknown-amdhsa < %s | FileCheck -check-prefixes=ALL %s
+
+; RUN: opt -cost-model -cost-kind=code-size -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx1010 < %s | FileCheck -check-prefixes=ALL-SIZE %s
+; RUN: opt -cost-model -cost-kind=code-size -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx90a < %s | FileCheck -check-prefixes=ALL-SIZE %s
+; RUN: opt -cost-model -cost-kind=code-size -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx900 < %s | FileCheck -check-prefixes=ALL-SIZE %s
+; RUN: opt -cost-model -cost-kind=code-size -analyze -mtriple=amdgcn-unknown-amdhsa < %s | FileCheck -check-prefixes=ALL-SIZE %s
+; END.
+
+define i32 @fcopysign(i32 %arg) {
+; ALL-LABEL: 'fcopysign'
+; ALL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.copysign.f32(float undef, float undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F32 = call <4 x float> @llvm.copysign.v4f32(<4 x float> undef, <4 x float> undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8F32 = call <8 x float> @llvm.copysign.v8f32(<8 x float> undef, <8 x float> undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16F32 = call <16 x float> @llvm.copysign.v16f32(<16 x float> undef, <16 x float> undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.copysign.f64(double undef, double undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = call <2 x double> @llvm.copysign.v2f64(<2 x double> undef, <2 x double> undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = call <4 x double> @llvm.copysign.v4f64(<4 x double> undef, <4 x double> undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = call <8 x double> @llvm.copysign.v8f64(<8 x double> undef, <8 x double> undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; ALL-SIZE-LABEL: 'fcopysign'
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.copysign.f32(float undef, float undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F32 = call <4 x float> @llvm.copysign.v4f32(<4 x float> undef, <4 x float> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8F32 = call <8 x float> @llvm.copysign.v8f32(<8 x float> undef, <8 x float> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16F32 = call <16 x float> @llvm.copysign.v16f32(<16 x float> undef, <16 x float> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.copysign.f64(double undef, double undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = call <2 x double> @llvm.copysign.v2f64(<2 x double> undef, <2 x double> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = call <4 x double> @llvm.copysign.v4f64(<4 x double> undef, <4 x double> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = call <8 x double> @llvm.copysign.v8f64(<8 x double> undef, <8 x double> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %F32 = call float @llvm.copysign.f32(float undef, float undef)
+ %V4F32 = call <4 x float> @llvm.copysign.v4f32(<4 x float> undef, <4 x float> undef)
+ %V8F32 = call <8 x float> @llvm.copysign.v8f32(<8 x float> undef, <8 x float> undef)
+ %V16F32 = call <16 x float> @llvm.copysign.v16f32(<16 x float> undef, <16 x float> undef)
+
+ %F64 = call double @llvm.copysign.f64(double undef, double undef)
+ %V2F64 = call <2 x double> @llvm.copysign.v2f64(<2 x double> undef, <2 x double> undef)
+ %V4F64 = call <4 x double> @llvm.copysign.v4f64(<4 x double> undef, <4 x double> undef)
+ %V8F64 = call <8 x double> @llvm.copysign.v8f64(<8 x double> undef, <8 x double> undef)
+
+ ret i32 undef
+}
+
+define i32 @fsqrt(i32 %arg) {
+; ALL-LABEL: 'fsqrt'
+; ALL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.sqrt.f32(float undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F32 = call <4 x float> @llvm.sqrt.v4f32(<4 x float> undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8F32 = call <8 x float> @llvm.sqrt.v8f32(<8 x float> undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16F32 = call <16 x float> @llvm.sqrt.v16f32(<16 x float> undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.sqrt.f64(double undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = call <2 x double> @llvm.sqrt.v2f64(<2 x double> undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = call <4 x double> @llvm.sqrt.v4f64(<4 x double> undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = call <8 x double> @llvm.sqrt.v8f64(<8 x double> undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; ALL-SIZE-LABEL: 'fsqrt'
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.sqrt.f32(float undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F32 = call <4 x float> @llvm.sqrt.v4f32(<4 x float> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8F32 = call <8 x float> @llvm.sqrt.v8f32(<8 x float> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16F32 = call <16 x float> @llvm.sqrt.v16f32(<16 x float> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.sqrt.f64(double undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = call <2 x double> @llvm.sqrt.v2f64(<2 x double> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = call <4 x double> @llvm.sqrt.v4f64(<4 x double> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = call <8 x double> @llvm.sqrt.v8f64(<8 x double> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %F32 = call float @llvm.sqrt.f32(float undef)
+ %V4F32 = call <4 x float> @llvm.sqrt.v4f32(<4 x float> undef)
+ %V8F32 = call <8 x float> @llvm.sqrt.v8f32(<8 x float> undef)
+ %V16F32 = call <16 x float> @llvm.sqrt.v16f32(<16 x float> undef)
+
+ %F64 = call double @llvm.sqrt.f64(double undef)
+ %V2F64 = call <2 x double> @llvm.sqrt.v2f64(<2 x double> undef)
+ %V4F64 = call <4 x double> @llvm.sqrt.v4f64(<4 x double> undef)
+ %V8F64 = call <8 x double> @llvm.sqrt.v8f64(<8 x double> undef)
+
+ ret i32 undef
+}
+
+declare float @llvm.copysign.f32(float, float)
+declare <4 x float> @llvm.copysign.v4f32(<4 x float>, <4 x float>)
+declare <8 x float> @llvm.copysign.v8f32(<8 x float>, <8 x float>)
+declare <16 x float> @llvm.copysign.v16f32(<16 x float>, <16 x float>)
+
+declare double @llvm.copysign.f64(double, double)
+declare <2 x double> @llvm.copysign.v2f64(<2 x double>, <2 x double>)
+declare <4 x double> @llvm.copysign.v4f64(<4 x double>, <4 x double>)
+declare <8 x double> @llvm.copysign.v8f64(<8 x double>, <8 x double>)
+
+declare float @llvm.sqrt.f32(float)
+declare <4 x float> @llvm.sqrt.v4f32(<4 x float>)
+declare <8 x float> @llvm.sqrt.v8f32(<8 x float>)
+declare <16 x float> @llvm.sqrt.v16f32(<16 x float>)
+
+declare double @llvm.sqrt.f64(double)
+declare <2 x double> @llvm.sqrt.v2f64(<2 x double>)
+declare <4 x double> @llvm.sqrt.v4f64(<4 x double>)
+declare <8 x double> @llvm.sqrt.v8f64(<8 x double>)
diff --git a/llvm/test/Analysis/CostModel/AMDGPU/arith-sminmax.ll b/llvm/test/Analysis/CostModel/AMDGPU/arith-sminmax.ll
new file mode 100644
index 000000000000..d75c38bfb342
--- /dev/null
+++ b/llvm/test/Analysis/CostModel/AMDGPU/arith-sminmax.ll
@@ -0,0 +1,273 @@
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
+; RUN: opt -cost-model -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx1010 < %s | FileCheck -check-prefixes=FAST %s
+; RUN: opt -cost-model -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx90a < %s | FileCheck -check-prefixes=FAST %s
+; RUN: opt -cost-model -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx900 < %s | FileCheck -check-prefixes=FAST %s
+; RUN: opt -cost-model -analyze -mtriple=amdgcn-unknown-amdhsa < %s | FileCheck -check-prefixes=SLOW %s
+
+; RUN: opt -cost-model -cost-kind=code-size -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx1010 < %s | FileCheck -check-prefixes=ALL-SIZE %s
+; RUN: opt -cost-model -cost-kind=code-size -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx90a < %s | FileCheck -check-prefixes=ALL-SIZE %s
+; RUN: opt -cost-model -cost-kind=code-size -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx900 < %s | FileCheck -check-prefixes=ALL-SIZE %s
+; RUN: opt -cost-model -cost-kind=code-size -analyze -mtriple=amdgcn-unknown-amdhsa < %s | FileCheck -check-prefixes=ALL-SIZE %s
+; END.
+
+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 <2 x i32> @llvm.smax.v2i32(<2 x i32>, <2 x 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 <2 x i16> @llvm.smax.v2i16(<2 x i16>, <2 x i16>)
+declare <4 x i16> @llvm.smax.v4i16(<4 x i16>, <4 x 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 <2 x i8> @llvm.smax.v2i8(<2 x i8>, <2 x i8>)
+declare <4 x i8> @llvm.smax.v4i8(<4 x i8>, <4 x i8>)
+declare <8 x i8> @llvm.smax.v8i8(<8 x i8>, <8 x 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) {
+; FAST-LABEL: 'smax'
+; FAST-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
+; FAST-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)
+; FAST-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)
+; FAST-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)
+; FAST-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I32 = call <2 x i32> @llvm.smax.v2i32(<2 x i32> undef, <2 x i32> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V2I16 = call <2 x i16> @llvm.smax.v2i16(<2 x i16> undef, <2 x i16> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V4I16 = call <4 x i16> @llvm.smax.v4i16(<4 x i16> undef, <4 x i16> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 62 for instruction: %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 126 for instruction: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V2I8 = call <2 x i8> @llvm.smax.v2i8(<2 x i8> undef, <2 x i8> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V4I8 = call <4 x i8> @llvm.smax.v4i8(<4 x i8> undef, <4 x i8> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V8I8 = call <8 x i8> @llvm.smax.v8i8(<8 x i8> undef, <8 x i8> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 256 for instruction: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; SLOW-LABEL: 'smax'
+; SLOW-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
+; SLOW-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)
+; SLOW-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)
+; SLOW-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)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I32 = call <2 x i32> @llvm.smax.v2i32(<2 x i32> undef, <2 x i32> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16I32 = call <16 x i32> @llvm.smax.v16i32(<16 x i32> undef, <16 x i32> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V2I16 = call <2 x i16> @llvm.smax.v2i16(<2 x i16> undef, <2 x i16> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V4I16 = call <4 x i16> @llvm.smax.v4i16(<4 x i16> undef, <4 x i16> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V16I16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V32I16 = call <32 x i16> @llvm.smax.v32i16(<32 x i16> undef, <32 x i16> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V2I8 = call <2 x i8> @llvm.smax.v2i8(<2 x i8> undef, <2 x i8> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V4I8 = call <4 x i8> @llvm.smax.v4i8(<4 x i8> undef, <4 x i8> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V8I8 = call <8 x i8> @llvm.smax.v8i8(<8 x i8> undef, <8 x i8> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V16I8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V32I8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 256 for instruction: %V64I8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; ALL-SIZE-LABEL: 'smax'
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
+; ALL-SIZE-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)
+; ALL-SIZE-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)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I64 = call <8 x i64> @llvm.smax.v8i64(<8 x i64> undef, <8 x i64> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I32 = call <2 x i32> @llvm.smax.v2i32(<2 x i32> undef, <2 x i32> undef)
+; ALL-SIZE-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)
+; ALL-SIZE-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)
+; ALL-SIZE-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)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I16 = call <2 x i16> @llvm.smax.v2i16(<2 x i16> undef, <2 x i16> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I16 = call <4 x i16> @llvm.smax.v4i16(<4 x i16> undef, <4 x i16> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
+; ALL-SIZE-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)
+; ALL-SIZE-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)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I8 = call <2 x i8> @llvm.smax.v2i8(<2 x i8> undef, <2 x i8> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I8 = call <4 x i8> @llvm.smax.v4i8(<4 x i8> undef, <4 x i8> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I8 = call <8 x i8> @llvm.smax.v8i8(<8 x i8> undef, <8 x i8> undef)
+; ALL-SIZE-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)
+; ALL-SIZE-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)
+; ALL-SIZE-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)
+; ALL-SIZE-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)
+ %V2I32 = call <2 x i32> @llvm.smax.v2i32(<2 x i32> undef, <2 x 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)
+ %V2I16 = call <2 x i16> @llvm.smax.v2i16(<2 x i16> undef, <2 x i16> undef)
+ %V4I16 = call <4 x i16> @llvm.smax.v4i16(<4 x i16> undef, <4 x 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)
+ %V2I8 = call <2 x i8> @llvm.smax.v2i8(<2 x i8> undef, <2 x i8> undef)
+ %V4I8 = call <4 x i8> @llvm.smax.v4i8(<4 x i8> undef, <4 x i8> undef)
+ %V8I8 = call <8 x i8> @llvm.smax.v8i8(<8 x i8> undef, <8 x 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 <2 x i32> @llvm.smin.v2i32(<2 x i32>, <2 x 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 <2 x i16> @llvm.smin.v2i16(<2 x i16>, <2 x i16>)
+declare <4 x i16> @llvm.smin.v4i16(<4 x i16>, <4 x 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 <2 x i8> @llvm.smin.v2i8(<2 x i8>, <2 x i8>)
+declare <4 x i8> @llvm.smin.v4i8(<4 x i8>, <4 x i8>)
+declare <8 x i8> @llvm.smin.v8i8(<8 x i8>, <8 x 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) {
+; FAST-LABEL: 'smin'
+; FAST-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
+; FAST-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)
+; FAST-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)
+; FAST-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)
+; FAST-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I32 = call <2 x i32> @llvm.smin.v2i32(<2 x i32> undef, <2 x i32> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V2I16 = call <2 x i16> @llvm.smin.v2i16(<2 x i16> undef, <2 x i16> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V4I16 = call <4 x i16> @llvm.smin.v4i16(<4 x i16> undef, <4 x i16> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 62 for instruction: %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 126 for instruction: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V2I8 = call <2 x i8> @llvm.smin.v2i8(<2 x i8> undef, <2 x i8> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V4I8 = call <4 x i8> @llvm.smin.v4i8(<4 x i8> undef, <4 x i8> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V8I8 = call <8 x i8> @llvm.smin.v8i8(<8 x i8> undef, <8 x i8> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 256 for instruction: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; SLOW-LABEL: 'smin'
+; SLOW-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
+; SLOW-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)
+; SLOW-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)
+; SLOW-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)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I32 = call <2 x i32> @llvm.smin.v2i32(<2 x i32> undef, <2 x i32> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4I32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8I32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16I32 = call <16 x i32> @llvm.smin.v16i32(<16 x i32> undef, <16 x i32> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V2I16 = call <2 x i16> @llvm.smin.v2i16(<2 x i16> undef, <2 x i16> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V4I16 = call <4 x i16> @llvm.smin.v4i16(<4 x i16> undef, <4 x i16> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V16I16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V32I16 = call <32 x i16> @llvm.smin.v32i16(<32 x i16> undef, <32 x i16> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V2I8 = call <2 x i8> @llvm.smin.v2i8(<2 x i8> undef, <2 x i8> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V4I8 = call <4 x i8> @llvm.smin.v4i8(<4 x i8> undef, <4 x i8> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V8I8 = call <8 x i8> @llvm.smin.v8i8(<8 x i8> undef, <8 x i8> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V16I8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V32I8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 256 for instruction: %V64I8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; ALL-SIZE-LABEL: 'smin'
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
+; ALL-SIZE-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)
+; ALL-SIZE-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)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I64 = call <8 x i64> @llvm.smin.v8i64(<8 x i64> undef, <8 x i64> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I32 = call <2 x i32> @llvm.smin.v2i32(<2 x i32> undef, <2 x i32> undef)
+; ALL-SIZE-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)
+; ALL-SIZE-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)
+; ALL-SIZE-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)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I16 = call <2 x i16> @llvm.smin.v2i16(<2 x i16> undef, <2 x i16> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I16 = call <4 x i16> @llvm.smin.v4i16(<4 x i16> undef, <4 x i16> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
+; ALL-SIZE-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)
+; ALL-SIZE-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)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I8 = call <2 x i8> @llvm.smin.v2i8(<2 x i8> undef, <2 x i8> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I8 = call <4 x i8> @llvm.smin.v4i8(<4 x i8> undef, <4 x i8> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I8 = call <8 x i8> @llvm.smin.v8i8(<8 x i8> undef, <8 x i8> undef)
+; ALL-SIZE-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)
+; ALL-SIZE-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)
+; ALL-SIZE-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)
+; ALL-SIZE-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)
+ %V2I32 = call <2 x i32> @llvm.smin.v2i32(<2 x i32> undef, <2 x 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)
+ %V2I16 = call <2 x i16> @llvm.smin.v2i16(<2 x i16> undef, <2 x i16> undef)
+ %V4I16 = call <4 x i16> @llvm.smin.v4i16(<4 x i16> undef, <4 x 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)
+ %V2I8 = call <2 x i8> @llvm.smin.v2i8(<2 x i8> undef, <2 x i8> undef)
+ %V4I8 = call <4 x i8> @llvm.smin.v4i8(<4 x i8> undef, <4 x i8> undef)
+ %V8I8 = call <8 x i8> @llvm.smin.v8i8(<8 x i8> undef, <8 x 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/AMDGPU/arith-uminmax.ll b/llvm/test/Analysis/CostModel/AMDGPU/arith-uminmax.ll
new file mode 100644
index 000000000000..f42a1a0990c2
--- /dev/null
+++ b/llvm/test/Analysis/CostModel/AMDGPU/arith-uminmax.ll
@@ -0,0 +1,273 @@
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
+; RUN: opt -cost-model -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx1010 < %s | FileCheck -check-prefixes=FAST %s
+; RUN: opt -cost-model -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx90a < %s | FileCheck -check-prefixes=FAST %s
+; RUN: opt -cost-model -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx900 < %s | FileCheck -check-prefixes=FAST %s
+; RUN: opt -cost-model -analyze -mtriple=amdgcn-unknown-amdhsa < %s | FileCheck -check-prefixes=SLOW %s
+
+; RUN: opt -cost-model -cost-kind=code-size -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx1010 < %s | FileCheck -check-prefixes=ALL-SIZE %s
+; RUN: opt -cost-model -cost-kind=code-size -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx90a < %s | FileCheck -check-prefixes=ALL-SIZE %s
+; RUN: opt -cost-model -cost-kind=code-size -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx900 < %s | FileCheck -check-prefixes=ALL-SIZE %s
+; RUN: opt -cost-model -cost-kind=code-size -analyze -mtriple=amdgcn-unknown-amdhsa < %s | FileCheck -check-prefixes=ALL-SIZE %s
+; END.
+
+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 <2 x i32> @llvm.umax.v2i32(<2 x i32>, <2 x 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 <2 x i16> @llvm.umax.v2i16(<2 x i16>, <2 x i16>)
+declare <4 x i16> @llvm.umax.v4i16(<4 x i16>, <4 x 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 <2 x i8> @llvm.umax.v2i8(<2 x i8>, <2 x i8>)
+declare <4 x i8> @llvm.umax.v4i8(<4 x i8>, <4 x i8>)
+declare <8 x i8> @llvm.umax.v8i8(<8 x i8>, <8 x 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) {
+; FAST-LABEL: 'umax'
+; FAST-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I64 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
+; FAST-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)
+; FAST-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)
+; FAST-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)
+; FAST-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I32 = call <2 x i32> @llvm.umax.v2i32(<2 x i32> undef, <2 x i32> undef)
+; FAST-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)
+; FAST-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)
+; FAST-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)
+; FAST-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V2I16 = call <2 x i16> @llvm.umax.v2i16(<2 x i16> undef, <2 x i16> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V4I16 = call <4 x i16> @llvm.umax.v4i16(<4 x i16> undef, <4 x i16> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %V8I16 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 62 for instruction: %V16I16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 126 for instruction: %V32I16 = call <32 x i16> @llvm.umax.v32i16(<32 x i16> undef, <32 x i16> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.umax.i8(i8 undef, i8 undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V2I8 = call <2 x i8> @llvm.umax.v2i8(<2 x i8> undef, <2 x i8> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V4I8 = call <4 x i8> @llvm.umax.v4i8(<4 x i8> undef, <4 x i8> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V8I8 = call <8 x i8> @llvm.umax.v8i8(<8 x i8> undef, <8 x i8> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V16I8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V32I8 = call <32 x i8> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 256 for instruction: %V64I8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; SLOW-LABEL: 'umax'
+; SLOW-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I64 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
+; SLOW-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)
+; SLOW-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)
+; SLOW-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)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I32 = call <2 x i32> @llvm.umax.v2i32(<2 x i32> undef, <2 x i32> undef)
+; SLOW-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)
+; SLOW-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)
+; SLOW-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)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V2I16 = call <2 x i16> @llvm.umax.v2i16(<2 x i16> undef, <2 x i16> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V4I16 = call <4 x i16> @llvm.umax.v4i16(<4 x i16> undef, <4 x i16> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V8I16 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V16I16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V32I16 = call <32 x i16> @llvm.umax.v32i16(<32 x i16> undef, <32 x i16> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.umax.i8(i8 undef, i8 undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V2I8 = call <2 x i8> @llvm.umax.v2i8(<2 x i8> undef, <2 x i8> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V4I8 = call <4 x i8> @llvm.umax.v4i8(<4 x i8> undef, <4 x i8> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V8I8 = call <8 x i8> @llvm.umax.v8i8(<8 x i8> undef, <8 x i8> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V16I8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V32I8 = call <32 x i8> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 256 for instruction: %V64I8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; ALL-SIZE-LABEL: 'umax'
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I64 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
+; ALL-SIZE-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)
+; ALL-SIZE-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)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I64 = call <8 x i64> @llvm.umax.v8i64(<8 x i64> undef, <8 x i64> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I32 = call <2 x i32> @llvm.umax.v2i32(<2 x i32> undef, <2 x i32> undef)
+; ALL-SIZE-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)
+; ALL-SIZE-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)
+; ALL-SIZE-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)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I16 = call <2 x i16> @llvm.umax.v2i16(<2 x i16> undef, <2 x i16> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I16 = call <4 x i16> @llvm.umax.v4i16(<4 x i16> undef, <4 x i16> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
+; ALL-SIZE-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)
+; ALL-SIZE-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)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.umax.i8(i8 undef, i8 undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I8 = call <2 x i8> @llvm.umax.v2i8(<2 x i8> undef, <2 x i8> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I8 = call <4 x i8> @llvm.umax.v4i8(<4 x i8> undef, <4 x i8> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I8 = call <8 x i8> @llvm.umax.v8i8(<8 x i8> undef, <8 x i8> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
+; ALL-SIZE-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)
+; ALL-SIZE-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)
+; ALL-SIZE-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)
+ %V2I32 = call <2 x i32> @llvm.umax.v2i32(<2 x i32> undef, <2 x 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)
+ %V2I16 = call <2 x i16> @llvm.umax.v2i16(<2 x i16> undef, <2 x i16> undef)
+ %V4I16 = call <4 x i16> @llvm.umax.v4i16(<4 x i16> undef, <4 x 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)
+ %V2I8 = call <2 x i8> @llvm.umax.v2i8(<2 x i8> undef, <2 x i8> undef)
+ %V4I8 = call <4 x i8> @llvm.umax.v4i8(<4 x i8> undef, <4 x i8> undef)
+ %V8I8 = call <8 x i8> @llvm.umax.v8i8(<8 x i8> undef, <8 x 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 <2 x i32> @llvm.umin.v2i32(<2 x i32>, <2 x 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 <2 x i16> @llvm.umin.v2i16(<2 x i16>, <2 x i16>)
+declare <4 x i16> @llvm.umin.v4i16(<4 x i16>, <4 x 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 <2 x i8> @llvm.umin.v2i8(<2 x i8>, <2 x i8>)
+declare <4 x i8> @llvm.umin.v4i8(<4 x i8>, <4 x i8>)
+declare <8 x i8> @llvm.umin.v8i8(<8 x i8>, <8 x 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) {
+; FAST-LABEL: 'umin'
+; FAST-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I64 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
+; FAST-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)
+; FAST-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)
+; FAST-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)
+; FAST-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I32 = call <2 x i32> @llvm.umin.v2i32(<2 x i32> undef, <2 x i32> undef)
+; FAST-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)
+; FAST-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)
+; FAST-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)
+; FAST-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V2I16 = call <2 x i16> @llvm.umin.v2i16(<2 x i16> undef, <2 x i16> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V4I16 = call <4 x i16> @llvm.umin.v4i16(<4 x i16> undef, <4 x i16> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %V8I16 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 62 for instruction: %V16I16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 126 for instruction: %V32I16 = call <32 x i16> @llvm.umin.v32i16(<32 x i16> undef, <32 x i16> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.umin.i8(i8 undef, i8 undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V2I8 = call <2 x i8> @llvm.umin.v2i8(<2 x i8> undef, <2 x i8> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V4I8 = call <4 x i8> @llvm.umin.v4i8(<4 x i8> undef, <4 x i8> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V8I8 = call <8 x i8> @llvm.umin.v8i8(<8 x i8> undef, <8 x i8> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V16I8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V32I8 = call <32 x i8> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 256 for instruction: %V64I8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; SLOW-LABEL: 'umin'
+; SLOW-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I64 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
+; SLOW-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)
+; SLOW-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)
+; SLOW-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)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I32 = call <2 x i32> @llvm.umin.v2i32(<2 x i32> undef, <2 x i32> undef)
+; SLOW-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)
+; SLOW-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)
+; SLOW-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)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V2I16 = call <2 x i16> @llvm.umin.v2i16(<2 x i16> undef, <2 x i16> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V4I16 = call <4 x i16> @llvm.umin.v4i16(<4 x i16> undef, <4 x i16> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V8I16 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V16I16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V32I16 = call <32 x i16> @llvm.umin.v32i16(<32 x i16> undef, <32 x i16> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.umin.i8(i8 undef, i8 undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V2I8 = call <2 x i8> @llvm.umin.v2i8(<2 x i8> undef, <2 x i8> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V4I8 = call <4 x i8> @llvm.umin.v4i8(<4 x i8> undef, <4 x i8> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V8I8 = call <8 x i8> @llvm.umin.v8i8(<8 x i8> undef, <8 x i8> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V16I8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V32I8 = call <32 x i8> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 256 for instruction: %V64I8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; ALL-SIZE-LABEL: 'umin'
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I64 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
+; ALL-SIZE-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)
+; ALL-SIZE-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)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I64 = call <8 x i64> @llvm.umin.v8i64(<8 x i64> undef, <8 x i64> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I32 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I32 = call <2 x i32> @llvm.umin.v2i32(<2 x i32> undef, <2 x i32> undef)
+; ALL-SIZE-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)
+; ALL-SIZE-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)
+; ALL-SIZE-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)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I16 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I16 = call <2 x i16> @llvm.umin.v2i16(<2 x i16> undef, <2 x i16> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I16 = call <4 x i16> @llvm.umin.v4i16(<4 x i16> undef, <4 x i16> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I16 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
+; ALL-SIZE-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)
+; ALL-SIZE-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)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %I8 = call i8 @llvm.umin.i8(i8 undef, i8 undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I8 = call <2 x i8> @llvm.umin.v2i8(<2 x i8> undef, <2 x i8> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4I8 = call <4 x i8> @llvm.umin.v4i8(<4 x i8> undef, <4 x i8> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8I8 = call <8 x i8> @llvm.umin.v8i8(<8 x i8> undef, <8 x i8> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16I8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
+; ALL-SIZE-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)
+; ALL-SIZE-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)
+; ALL-SIZE-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)
+ %V2I32 = call <2 x i32> @llvm.umin.v2i32(<2 x i32> undef, <2 x 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)
+ %V2I16 = call <2 x i16> @llvm.umin.v2i16(<2 x i16> undef, <2 x i16> undef)
+ %V4I16 = call <4 x i16> @llvm.umin.v4i16(<4 x i16> undef, <4 x 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)
+ %V2I8 = call <2 x i8> @llvm.umin.v2i8(<2 x i8> undef, <2 x i8> undef)
+ %V4I8 = call <4 x i8> @llvm.umin.v4i8(<4 x i8> undef, <4 x i8> undef)
+ %V8I8 = call <8 x i8> @llvm.umin.v8i8(<8 x i8> undef, <8 x 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/AMDGPU/cast.ll b/llvm/test/Analysis/CostModel/AMDGPU/cast.ll
new file mode 100644
index 000000000000..308dd4c40a10
--- /dev/null
+++ b/llvm/test/Analysis/CostModel/AMDGPU/cast.ll
@@ -0,0 +1,449 @@
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
+; RUN: opt -cost-model -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx1010 < %s | FileCheck -check-prefixes=ALL,FAST %s
+; RUN: opt -cost-model -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx90a < %s | FileCheck -check-prefixes=ALL,FAST %s
+; RUN: opt -cost-model -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx900 < %s | FileCheck -check-prefixes=ALL,FAST %s
+; RUN: opt -cost-model -analyze -mtriple=amdgcn-unknown-amdhsa < %s | FileCheck -check-prefixes=ALL,SLOW %s
+
+; RUN: opt -cost-model -cost-kind=code-size -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx1010 < %s | FileCheck -check-prefixes=ALL-SIZE,FAST-SIZE %s
+; RUN: opt -cost-model -cost-kind=code-size -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx90a < %s | FileCheck -check-prefixes=ALL-SIZE,FAST-SIZE %s
+; RUN: opt -cost-model -cost-kind=code-size -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx900 < %s | FileCheck -check-prefixes=ALL-SIZE,FAST-SIZE %s
+; RUN: opt -cost-model -cost-kind=code-size -analyze -mtriple=amdgcn-unknown-amdhsa < %s | FileCheck -check-prefixes=ALL-SIZE,SLOW-SIZE %s
+; END.
+
+define i32 @add(i32 %arg) {
+ ; -- Same size registeres --
+; ALL-LABEL: 'add'
+; ALL-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %A = zext <4 x i1> undef to <4 x i32>
+; ALL-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %B = sext <4 x i1> undef to <4 x i32>
+; ALL-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %C = trunc <4 x i32> undef to <4 x i1>
+; ALL-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %D = zext <8 x i1> undef to <8 x i32>
+; ALL-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %E = sext <8 x i1> undef to <8 x i32>
+; ALL-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %F = trunc <8 x i32> undef to <8 x i1>
+; ALL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %G = zext i1 undef to i32
+; ALL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %H = trunc i32 undef to i1
+; ALL-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; ALL-SIZE-LABEL: 'add'
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %A = zext <4 x i1> undef to <4 x i32>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %B = sext <4 x i1> undef to <4 x i32>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %C = trunc <4 x i32> undef to <4 x i1>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %D = zext <8 x i1> undef to <8 x i32>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %E = sext <8 x i1> undef to <8 x i32>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %F = trunc <8 x i32> undef to <8 x i1>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %G = zext i1 undef to i32
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %H = trunc i32 undef to i1
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %A = zext <4 x i1> undef to <4 x i32>
+ %B = sext <4 x i1> undef to <4 x i32>
+ %C = trunc <4 x i32> undef to <4 x i1>
+
+ ; -- Different size registers --
+ %D = zext <8 x i1> undef to <8 x i32>
+ %E = sext <8 x i1> undef to <8 x i32>
+ %F = trunc <8 x i32> undef to <8 x i1>
+
+ ; -- scalars --
+ %G = zext i1 undef to i32
+ %H = trunc i32 undef to i1
+
+ ret i32 undef
+}
+
+define i32 @zext_sext(<8 x i1> %in) {
+; FAST-LABEL: 'zext_sext'
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %Z = zext <8 x i1> %in to <8 x i32>
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %S = sext <8 x i1> %in to <8 x i32>
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %A1 = zext <16 x i8> undef to <16 x i16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %A2 = sext <16 x i8> undef to <16 x i16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %A = sext <8 x i16> undef to <8 x i32>
+; FAST-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %B = zext <8 x i16> undef to <8 x i32>
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %C = sext <4 x i32> undef to <4 x i64>
+; FAST-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %C.v8i8.z = zext <8 x i8> undef to <8 x i32>
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %C.v8i8.s = sext <8 x i8> undef to <8 x i32>
+; FAST-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %C.v4i16.z = zext <4 x i16> undef to <4 x i64>
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %C.v4i16.s = sext <4 x i16> undef to <4 x i64>
+; FAST-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %C.v4i8.z = zext <4 x i8> undef to <4 x i64>
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %C.v4i8.s = sext <4 x i8> undef to <4 x i64>
+; FAST-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %D = zext <4 x i32> undef to <4 x i64>
+; FAST-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %D1 = zext <8 x i32> undef to <8 x i64>
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %D2 = sext <8 x i32> undef to <8 x i64>
+; FAST-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %D3 = zext <16 x i16> undef to <16 x i32>
+; FAST-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %D4 = zext <16 x i8> undef to <16 x i32>
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %D5 = zext <16 x i1> undef to <16 x i32>
+; FAST-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %E = trunc <4 x i64> undef to <4 x i32>
+; FAST-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %F = trunc <8 x i32> undef to <8 x i16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %F1 = trunc <16 x i16> undef to <16 x i8>
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %F2 = trunc <8 x i32> undef to <8 x i8>
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %F3 = trunc <4 x i64> undef to <4 x i8>
+; FAST-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %G = trunc <8 x i64> undef to <8 x i32>
+; FAST-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %G1 = trunc <16 x i32> undef to <16 x i16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %G2 = trunc <16 x i32> undef to <16 x i8>
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; SLOW-LABEL: 'zext_sext'
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %Z = zext <8 x i1> %in to <8 x i32>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %S = sext <8 x i1> %in to <8 x i32>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %A1 = zext <16 x i8> undef to <16 x i16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %A2 = sext <16 x i8> undef to <16 x i16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %A = sext <8 x i16> undef to <8 x i32>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %B = zext <8 x i16> undef to <8 x i32>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %C = sext <4 x i32> undef to <4 x i64>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %C.v8i8.z = zext <8 x i8> undef to <8 x i32>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %C.v8i8.s = sext <8 x i8> undef to <8 x i32>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %C.v4i16.z = zext <4 x i16> undef to <4 x i64>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %C.v4i16.s = sext <4 x i16> undef to <4 x i64>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %C.v4i8.z = zext <4 x i8> undef to <4 x i64>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %C.v4i8.s = sext <4 x i8> undef to <4 x i64>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %D = zext <4 x i32> undef to <4 x i64>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %D1 = zext <8 x i32> undef to <8 x i64>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %D2 = sext <8 x i32> undef to <8 x i64>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %D3 = zext <16 x i16> undef to <16 x i32>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %D4 = zext <16 x i8> undef to <16 x i32>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %D5 = zext <16 x i1> undef to <16 x i32>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %E = trunc <4 x i64> undef to <4 x i32>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %F = trunc <8 x i32> undef to <8 x i16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %F1 = trunc <16 x i16> undef to <16 x i8>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %F2 = trunc <8 x i32> undef to <8 x i8>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %F3 = trunc <4 x i64> undef to <4 x i8>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %G = trunc <8 x i64> undef to <8 x i32>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %G1 = trunc <16 x i32> undef to <16 x i16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %G2 = trunc <16 x i32> undef to <16 x i8>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; FAST-SIZE-LABEL: 'zext_sext'
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %Z = zext <8 x i1> %in to <8 x i32>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %S = sext <8 x i1> %in to <8 x i32>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %A1 = zext <16 x i8> undef to <16 x i16>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %A2 = sext <16 x i8> undef to <16 x i16>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %A = sext <8 x i16> undef to <8 x i32>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %B = zext <8 x i16> undef to <8 x i32>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %C = sext <4 x i32> undef to <4 x i64>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %C.v8i8.z = zext <8 x i8> undef to <8 x i32>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %C.v8i8.s = sext <8 x i8> undef to <8 x i32>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %C.v4i16.z = zext <4 x i16> undef to <4 x i64>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %C.v4i16.s = sext <4 x i16> undef to <4 x i64>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %C.v4i8.z = zext <4 x i8> undef to <4 x i64>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %C.v4i8.s = sext <4 x i8> undef to <4 x i64>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %D = zext <4 x i32> undef to <4 x i64>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %D1 = zext <8 x i32> undef to <8 x i64>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %D2 = sext <8 x i32> undef to <8 x i64>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %D3 = zext <16 x i16> undef to <16 x i32>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %D4 = zext <16 x i8> undef to <16 x i32>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %D5 = zext <16 x i1> undef to <16 x i32>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %E = trunc <4 x i64> undef to <4 x i32>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %F = trunc <8 x i32> undef to <8 x i16>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %F1 = trunc <16 x i16> undef to <16 x i8>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %F2 = trunc <8 x i32> undef to <8 x i8>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %F3 = trunc <4 x i64> undef to <4 x i8>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %G = trunc <8 x i64> undef to <8 x i32>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %G1 = trunc <16 x i32> undef to <16 x i16>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %G2 = trunc <16 x i32> undef to <16 x i8>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; SLOW-SIZE-LABEL: 'zext_sext'
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %Z = zext <8 x i1> %in to <8 x i32>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %S = sext <8 x i1> %in to <8 x i32>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %A1 = zext <16 x i8> undef to <16 x i16>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %A2 = sext <16 x i8> undef to <16 x i16>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %A = sext <8 x i16> undef to <8 x i32>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %B = zext <8 x i16> undef to <8 x i32>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %C = sext <4 x i32> undef to <4 x i64>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %C.v8i8.z = zext <8 x i8> undef to <8 x i32>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %C.v8i8.s = sext <8 x i8> undef to <8 x i32>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %C.v4i16.z = zext <4 x i16> undef to <4 x i64>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %C.v4i16.s = sext <4 x i16> undef to <4 x i64>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %C.v4i8.z = zext <4 x i8> undef to <4 x i64>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %C.v4i8.s = sext <4 x i8> undef to <4 x i64>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %D = zext <4 x i32> undef to <4 x i64>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %D1 = zext <8 x i32> undef to <8 x i64>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %D2 = sext <8 x i32> undef to <8 x i64>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %D3 = zext <16 x i16> undef to <16 x i32>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %D4 = zext <16 x i8> undef to <16 x i32>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %D5 = zext <16 x i1> undef to <16 x i32>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %E = trunc <4 x i64> undef to <4 x i32>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %F = trunc <8 x i32> undef to <8 x i16>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %F1 = trunc <16 x i16> undef to <16 x i8>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %F2 = trunc <8 x i32> undef to <8 x i8>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %F3 = trunc <4 x i64> undef to <4 x i8>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %G = trunc <8 x i64> undef to <8 x i32>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %G1 = trunc <16 x i32> undef to <16 x i16>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %G2 = trunc <16 x i32> undef to <16 x i8>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %Z = zext <8 x i1> %in to <8 x i32>
+ %S = sext <8 x i1> %in to <8 x i32>
+
+ %A1 = zext <16 x i8> undef to <16 x i16>
+ %A2 = sext <16 x i8> undef to <16 x i16>
+ %A = sext <8 x i16> undef to <8 x i32>
+ %B = zext <8 x i16> undef to <8 x i32>
+ %C = sext <4 x i32> undef to <4 x i64>
+
+ %C.v8i8.z = zext <8 x i8> undef to <8 x i32>
+ %C.v8i8.s = sext <8 x i8> undef to <8 x i32>
+ %C.v4i16.z = zext <4 x i16> undef to <4 x i64>
+ %C.v4i16.s = sext <4 x i16> undef to <4 x i64>
+
+ %C.v4i8.z = zext <4 x i8> undef to <4 x i64>
+ %C.v4i8.s = sext <4 x i8> undef to <4 x i64>
+
+ %D = zext <4 x i32> undef to <4 x i64>
+
+ %D1 = zext <8 x i32> undef to <8 x i64>
+
+ %D2 = sext <8 x i32> undef to <8 x i64>
+
+ %D3 = zext <16 x i16> undef to <16 x i32>
+ %D4 = zext <16 x i8> undef to <16 x i32>
+ %D5 = zext <16 x i1> undef to <16 x i32>
+
+ %E = trunc <4 x i64> undef to <4 x i32>
+ %F = trunc <8 x i32> undef to <8 x i16>
+ %F1 = trunc <16 x i16> undef to <16 x i8>
+ %F2 = trunc <8 x i32> undef to <8 x i8>
+ %F3 = trunc <4 x i64> undef to <4 x i8>
+
+ %G = trunc <8 x i64> undef to <8 x i32>
+ %G1 = trunc <16 x i32> undef to <16 x i16>
+ %G2 = trunc <16 x i32> undef to <16 x i8>
+ ret i32 undef
+}
+
+define i32 @masks8(<8 x i1> %in) {
+; ALL-LABEL: 'masks8'
+; ALL-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %Z = zext <8 x i1> %in to <8 x i32>
+; ALL-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %S = sext <8 x i1> %in to <8 x i32>
+; ALL-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; ALL-SIZE-LABEL: 'masks8'
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %Z = zext <8 x i1> %in to <8 x i32>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %S = sext <8 x i1> %in to <8 x i32>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %Z = zext <8 x i1> %in to <8 x i32>
+ %S = sext <8 x i1> %in to <8 x i32>
+ ret i32 undef
+}
+
+define i32 @masks4(<4 x i1> %in) {
+; ALL-LABEL: 'masks4'
+; ALL-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %Z = zext <4 x i1> %in to <4 x i64>
+; ALL-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %S = sext <4 x i1> %in to <4 x i64>
+; ALL-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; ALL-SIZE-LABEL: 'masks4'
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %Z = zext <4 x i1> %in to <4 x i64>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %S = sext <4 x i1> %in to <4 x i64>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %Z = zext <4 x i1> %in to <4 x i64>
+ %S = sext <4 x i1> %in to <4 x i64>
+ ret i32 undef
+}
+
+define void @sitofp4(<4 x i1> %a, <4 x i8> %b, <4 x i16> %c, <4 x i32> %d) {
+; FAST-LABEL: 'sitofp4'
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %A1 = sitofp <4 x i1> %a to <4 x float>
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %A2 = sitofp <4 x i1> %a to <4 x double>
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %B1 = sitofp <4 x i8> %b to <4 x float>
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %B2 = sitofp <4 x i8> %b to <4 x double>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %C1 = sitofp <4 x i16> %c to <4 x float>
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %C2 = sitofp <4 x i16> %c to <4 x double>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %D1 = sitofp <4 x i32> %d to <4 x float>
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %D2 = sitofp <4 x i32> %d to <4 x double>
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret void
+;
+; SLOW-LABEL: 'sitofp4'
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %A1 = sitofp <4 x i1> %a to <4 x float>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %A2 = sitofp <4 x i1> %a to <4 x double>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %B1 = sitofp <4 x i8> %b to <4 x float>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %B2 = sitofp <4 x i8> %b to <4 x double>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %C1 = sitofp <4 x i16> %c to <4 x float>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %C2 = sitofp <4 x i16> %c to <4 x double>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %D1 = sitofp <4 x i32> %d to <4 x float>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %D2 = sitofp <4 x i32> %d to <4 x double>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret void
+;
+; FAST-SIZE-LABEL: 'sitofp4'
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %A1 = sitofp <4 x i1> %a to <4 x float>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %A2 = sitofp <4 x i1> %a to <4 x double>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %B1 = sitofp <4 x i8> %b to <4 x float>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %B2 = sitofp <4 x i8> %b to <4 x double>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %C1 = sitofp <4 x i16> %c to <4 x float>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %C2 = sitofp <4 x i16> %c to <4 x double>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %D1 = sitofp <4 x i32> %d to <4 x float>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %D2 = sitofp <4 x i32> %d to <4 x double>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
+;
+; SLOW-SIZE-LABEL: 'sitofp4'
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %A1 = sitofp <4 x i1> %a to <4 x float>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %A2 = sitofp <4 x i1> %a to <4 x double>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %B1 = sitofp <4 x i8> %b to <4 x float>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %B2 = sitofp <4 x i8> %b to <4 x double>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %C1 = sitofp <4 x i16> %c to <4 x float>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %C2 = sitofp <4 x i16> %c to <4 x double>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %D1 = sitofp <4 x i32> %d to <4 x float>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %D2 = sitofp <4 x i32> %d to <4 x double>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
+;
+ %A1 = sitofp <4 x i1> %a to <4 x float>
+ %A2 = sitofp <4 x i1> %a to <4 x double>
+ %B1 = sitofp <4 x i8> %b to <4 x float>
+ %B2 = sitofp <4 x i8> %b to <4 x double>
+ %C1 = sitofp <4 x i16> %c to <4 x float>
+ %C2 = sitofp <4 x i16> %c to <4 x double>
+ %D1 = sitofp <4 x i32> %d to <4 x float>
+ %D2 = sitofp <4 x i32> %d to <4 x double>
+ ret void
+}
+
+define void @sitofp8(<8 x i1> %a, <8 x i8> %b, <8 x i16> %c, <8 x i32> %d) {
+; FAST-LABEL: 'sitofp8'
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %A1 = sitofp <8 x i1> %a to <8 x float>
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %B1 = sitofp <8 x i8> %b to <8 x float>
+; FAST-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %C1 = sitofp <8 x i16> %c to <8 x float>
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %D1 = sitofp <8 x i32> %d to <8 x float>
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret void
+;
+; SLOW-LABEL: 'sitofp8'
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %A1 = sitofp <8 x i1> %a to <8 x float>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %B1 = sitofp <8 x i8> %b to <8 x float>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %C1 = sitofp <8 x i16> %c to <8 x float>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %D1 = sitofp <8 x i32> %d to <8 x float>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret void
+;
+; FAST-SIZE-LABEL: 'sitofp8'
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %A1 = sitofp <8 x i1> %a to <8 x float>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %B1 = sitofp <8 x i8> %b to <8 x float>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %C1 = sitofp <8 x i16> %c to <8 x float>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %D1 = sitofp <8 x i32> %d to <8 x float>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
+;
+; SLOW-SIZE-LABEL: 'sitofp8'
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %A1 = sitofp <8 x i1> %a to <8 x float>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %B1 = sitofp <8 x i8> %b to <8 x float>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %C1 = sitofp <8 x i16> %c to <8 x float>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %D1 = sitofp <8 x i32> %d to <8 x float>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
+;
+ %A1 = sitofp <8 x i1> %a to <8 x float>
+ %B1 = sitofp <8 x i8> %b to <8 x float>
+ %C1 = sitofp <8 x i16> %c to <8 x float>
+ %D1 = sitofp <8 x i32> %d to <8 x float>
+ ret void
+}
+
+define void @uitofp4(<4 x i1> %a, <4 x i8> %b, <4 x i16> %c, <4 x i32> %d) {
+; FAST-LABEL: 'uitofp4'
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %A1 = uitofp <4 x i1> %a to <4 x float>
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %A2 = uitofp <4 x i1> %a to <4 x double>
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %B1 = uitofp <4 x i8> %b to <4 x float>
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %B2 = uitofp <4 x i8> %b to <4 x double>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %C1 = uitofp <4 x i16> %c to <4 x float>
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %C2 = uitofp <4 x i16> %c to <4 x double>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %D1 = uitofp <4 x i32> %d to <4 x float>
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %D2 = uitofp <4 x i32> %d to <4 x double>
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret void
+;
+; SLOW-LABEL: 'uitofp4'
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %A1 = uitofp <4 x i1> %a to <4 x float>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %A2 = uitofp <4 x i1> %a to <4 x double>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %B1 = uitofp <4 x i8> %b to <4 x float>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %B2 = uitofp <4 x i8> %b to <4 x double>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %C1 = uitofp <4 x i16> %c to <4 x float>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %C2 = uitofp <4 x i16> %c to <4 x double>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %D1 = uitofp <4 x i32> %d to <4 x float>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %D2 = uitofp <4 x i32> %d to <4 x double>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret void
+;
+; FAST-SIZE-LABEL: 'uitofp4'
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %A1 = uitofp <4 x i1> %a to <4 x float>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %A2 = uitofp <4 x i1> %a to <4 x double>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %B1 = uitofp <4 x i8> %b to <4 x float>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %B2 = uitofp <4 x i8> %b to <4 x double>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %C1 = uitofp <4 x i16> %c to <4 x float>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %C2 = uitofp <4 x i16> %c to <4 x double>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %D1 = uitofp <4 x i32> %d to <4 x float>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %D2 = uitofp <4 x i32> %d to <4 x double>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
+;
+; SLOW-SIZE-LABEL: 'uitofp4'
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %A1 = uitofp <4 x i1> %a to <4 x float>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %A2 = uitofp <4 x i1> %a to <4 x double>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %B1 = uitofp <4 x i8> %b to <4 x float>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %B2 = uitofp <4 x i8> %b to <4 x double>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %C1 = uitofp <4 x i16> %c to <4 x float>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %C2 = uitofp <4 x i16> %c to <4 x double>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %D1 = uitofp <4 x i32> %d to <4 x float>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %D2 = uitofp <4 x i32> %d to <4 x double>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
+;
+ %A1 = uitofp <4 x i1> %a to <4 x float>
+ %A2 = uitofp <4 x i1> %a to <4 x double>
+ %B1 = uitofp <4 x i8> %b to <4 x float>
+ %B2 = uitofp <4 x i8> %b to <4 x double>
+ %C1 = uitofp <4 x i16> %c to <4 x float>
+ %C2 = uitofp <4 x i16> %c to <4 x double>
+ %D1 = uitofp <4 x i32> %d to <4 x float>
+ %D2 = uitofp <4 x i32> %d to <4 x double>
+ ret void
+}
+
+define void @uitofp8(<8 x i1> %a, <8 x i8> %b, <8 x i16> %c, <8 x i32> %d) {
+; FAST-LABEL: 'uitofp8'
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %A1 = uitofp <8 x i1> %a to <8 x float>
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %B1 = uitofp <8 x i8> %b to <8 x float>
+; FAST-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %C1 = uitofp <8 x i16> %c to <8 x float>
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %D1 = uitofp <8 x i32> %d to <8 x float>
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret void
+;
+; SLOW-LABEL: 'uitofp8'
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %A1 = uitofp <8 x i1> %a to <8 x float>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %B1 = uitofp <8 x i8> %b to <8 x float>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %C1 = uitofp <8 x i16> %c to <8 x float>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %D1 = uitofp <8 x i32> %d to <8 x float>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret void
+;
+; FAST-SIZE-LABEL: 'uitofp8'
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %A1 = uitofp <8 x i1> %a to <8 x float>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %B1 = uitofp <8 x i8> %b to <8 x float>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %C1 = uitofp <8 x i16> %c to <8 x float>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %D1 = uitofp <8 x i32> %d to <8 x float>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
+;
+; SLOW-SIZE-LABEL: 'uitofp8'
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %A1 = uitofp <8 x i1> %a to <8 x float>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %B1 = uitofp <8 x i8> %b to <8 x float>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %C1 = uitofp <8 x i16> %c to <8 x float>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %D1 = uitofp <8 x i32> %d to <8 x float>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
+;
+ %A1 = uitofp <8 x i1> %a to <8 x float>
+ %B1 = uitofp <8 x i8> %b to <8 x float>
+ %C1 = uitofp <8 x i16> %c to <8 x float>
+ %D1 = uitofp <8 x i32> %d to <8 x float>
+ ret void
+}
+
+define void @fp_conv(<8 x float> %a, <16 x float>%b, <4 x float> %c) {
+; ALL-LABEL: 'fp_conv'
+; ALL-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %A1 = fpext <4 x float> %c to <4 x double>
+; ALL-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %A2 = fpext <8 x float> %a to <8 x double>
+; ALL-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %A3 = fptrunc <4 x double> undef to <4 x float>
+; ALL-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %A4 = fptrunc <8 x double> undef to <8 x float>
+; ALL-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret void
+;
+; ALL-SIZE-LABEL: 'fp_conv'
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %A1 = fpext <4 x float> %c to <4 x double>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %A2 = fpext <8 x float> %a to <8 x double>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %A3 = fptrunc <4 x double> undef to <4 x float>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %A4 = fptrunc <8 x double> undef to <8 x float>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
+;
+ %A1 = fpext <4 x float> %c to <4 x double>
+ %A2 = fpext <8 x float> %a to <8 x double>
+ %A3 = fptrunc <4 x double> undef to <4 x float>
+ %A4 = fptrunc <8 x double> undef to <8 x float>
+ ret void
+}
diff --git a/llvm/test/Analysis/CostModel/AMDGPU/div.ll b/llvm/test/Analysis/CostModel/AMDGPU/div.ll
new file mode 100644
index 000000000000..7114b81025be
--- /dev/null
+++ b/llvm/test/Analysis/CostModel/AMDGPU/div.ll
@@ -0,0 +1,1145 @@
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
+; RUN: opt -cost-model -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx1010 < %s | FileCheck -check-prefixes=FAST %s
+; RUN: opt -cost-model -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx90a < %s | FileCheck -check-prefixes=FAST %s
+; RUN: opt -cost-model -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx900 < %s | FileCheck -check-prefixes=FAST %s
+; RUN: opt -cost-model -analyze -mtriple=amdgcn-unknown-amdhsa < %s | FileCheck -check-prefixes=SLOW %s
+
+; RUN: opt -cost-model -cost-kind=code-size -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx1010 < %s | FileCheck -check-prefixes=ALL-SIZE %s
+; RUN: opt -cost-model -cost-kind=code-size -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx90a < %s | FileCheck -check-prefixes=ALL-SIZE %s
+; RUN: opt -cost-model -cost-kind=code-size -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx900 < %s | FileCheck -check-prefixes=ALL-SIZE %s
+; RUN: opt -cost-model -cost-kind=code-size -analyze -mtriple=amdgcn-unknown-amdhsa < %s | FileCheck -check-prefixes=ALL-SIZE %s
+; END.
+
+define i32 @sdiv() {
+; FAST-LABEL: 'sdiv'
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = sdiv i64 undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i64 = sdiv <2 x i64> undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = sdiv <4 x i64> undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i64 = sdiv <8 x i64> undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = sdiv i32 undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = sdiv <4 x i32> undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i32 = sdiv <8 x i32> undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i32 = sdiv <16 x i32> undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = sdiv i16 undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V8i16 = sdiv <8 x i16> undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %V16i16 = sdiv <16 x i16> undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %V32i16 = sdiv <32 x i16> undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = sdiv i8 undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i8 = sdiv <16 x i8> undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V32i8 = sdiv <32 x i8> undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V64i8 = sdiv <64 x i8> undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; SLOW-LABEL: 'sdiv'
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = sdiv i64 undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i64 = sdiv <2 x i64> undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = sdiv <4 x i64> undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i64 = sdiv <8 x i64> undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = sdiv i32 undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = sdiv <4 x i32> undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i32 = sdiv <8 x i32> undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i32 = sdiv <16 x i32> undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = sdiv i16 undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8i16 = sdiv <8 x i16> undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16i16 = sdiv <16 x i16> undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32i16 = sdiv <32 x i16> undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = sdiv i8 undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16i8 = sdiv <16 x i8> undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32i8 = sdiv <32 x i8> undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V64i8 = sdiv <64 x i8> undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; ALL-SIZE-LABEL: 'sdiv'
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = sdiv i64 undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2i64 = sdiv <2 x i64> undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = sdiv <4 x i64> undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i64 = sdiv <8 x i64> undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I32 = sdiv i32 undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = sdiv <4 x i32> undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i32 = sdiv <8 x i32> undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i32 = sdiv <16 x i32> undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = sdiv i16 undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i16 = sdiv <8 x i16> undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i16 = sdiv <16 x i16> undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i16 = sdiv <32 x i16> undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = sdiv i8 undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i8 = sdiv <16 x i8> undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i8 = sdiv <32 x i8> undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V64i8 = sdiv <64 x i8> undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %I64 = sdiv i64 undef, undef
+ %V2i64 = sdiv <2 x i64> undef, undef
+ %V4i64 = sdiv <4 x i64> undef, undef
+ %V8i64 = sdiv <8 x i64> undef, undef
+
+ %I32 = sdiv i32 undef, undef
+ %V4i32 = sdiv <4 x i32> undef, undef
+ %V8i32 = sdiv <8 x i32> undef, undef
+ %V16i32 = sdiv <16 x i32> undef, undef
+
+ %I16 = sdiv i16 undef, undef
+ %V8i16 = sdiv <8 x i16> undef, undef
+ %V16i16 = sdiv <16 x i16> undef, undef
+ %V32i16 = sdiv <32 x i16> undef, undef
+
+ %I8 = sdiv i8 undef, undef
+ %V16i8 = sdiv <16 x i8> undef, undef
+ %V32i8 = sdiv <32 x i8> undef, undef
+ %V64i8 = sdiv <64 x i8> undef, undef
+
+ ret i32 undef
+}
+
+define i32 @udiv() {
+; FAST-LABEL: 'udiv'
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = udiv i64 undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i64 = udiv <2 x i64> undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = udiv <4 x i64> undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i64 = udiv <8 x i64> undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = udiv i32 undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = udiv <4 x i32> undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i32 = udiv <8 x i32> undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i32 = udiv <16 x i32> undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = udiv i16 undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V8i16 = udiv <8 x i16> undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %V16i16 = udiv <16 x i16> undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %V32i16 = udiv <32 x i16> undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = udiv i8 undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i8 = udiv <16 x i8> undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V32i8 = udiv <32 x i8> undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V64i8 = udiv <64 x i8> undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; SLOW-LABEL: 'udiv'
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = udiv i64 undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i64 = udiv <2 x i64> undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = udiv <4 x i64> undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i64 = udiv <8 x i64> undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = udiv i32 undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = udiv <4 x i32> undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i32 = udiv <8 x i32> undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i32 = udiv <16 x i32> undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = udiv i16 undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8i16 = udiv <8 x i16> undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16i16 = udiv <16 x i16> undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32i16 = udiv <32 x i16> undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = udiv i8 undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16i8 = udiv <16 x i8> undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32i8 = udiv <32 x i8> undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V64i8 = udiv <64 x i8> undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; ALL-SIZE-LABEL: 'udiv'
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = udiv i64 undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2i64 = udiv <2 x i64> undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = udiv <4 x i64> undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i64 = udiv <8 x i64> undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I32 = udiv i32 undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = udiv <4 x i32> undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i32 = udiv <8 x i32> undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i32 = udiv <16 x i32> undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = udiv i16 undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i16 = udiv <8 x i16> undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i16 = udiv <16 x i16> undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i16 = udiv <32 x i16> undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = udiv i8 undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i8 = udiv <16 x i8> undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i8 = udiv <32 x i8> undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V64i8 = udiv <64 x i8> undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %I64 = udiv i64 undef, undef
+ %V2i64 = udiv <2 x i64> undef, undef
+ %V4i64 = udiv <4 x i64> undef, undef
+ %V8i64 = udiv <8 x i64> undef, undef
+
+ %I32 = udiv i32 undef, undef
+ %V4i32 = udiv <4 x i32> undef, undef
+ %V8i32 = udiv <8 x i32> undef, undef
+ %V16i32 = udiv <16 x i32> undef, undef
+
+ %I16 = udiv i16 undef, undef
+ %V8i16 = udiv <8 x i16> undef, undef
+ %V16i16 = udiv <16 x i16> undef, undef
+ %V32i16 = udiv <32 x i16> undef, undef
+
+ %I8 = udiv i8 undef, undef
+ %V16i8 = udiv <16 x i8> undef, undef
+ %V32i8 = udiv <32 x i8> undef, undef
+ %V64i8 = udiv <64 x i8> undef, undef
+
+ ret i32 undef
+}
+
+define i32 @sdiv_const() {
+; FAST-LABEL: 'sdiv_const'
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = sdiv i64 undef, 7
+; FAST-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i64 = sdiv <2 x i64> undef, <i64 6, i64 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = sdiv <4 x i64> undef, <i64 4, i64 5, i64 6, i64 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i64 = sdiv <8 x i64> undef, <i64 4, i64 5, i64 6, i64 7, i64 8, i64 9, i64 10, i64 11>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = sdiv i32 undef, 7
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = sdiv <4 x i32> undef, <i32 4, i32 5, i32 6, i32 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i32 = sdiv <8 x i32> undef, <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11>
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i32 = sdiv <16 x i32> undef, <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = sdiv i16 undef, 7
+; FAST-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V8i16 = sdiv <8 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11>
+; FAST-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %V16i16 = sdiv <16 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19>
+; FAST-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %V32i16 = sdiv <32 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19, i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = sdiv i8 undef, 7
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i8 = sdiv <16 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+; FAST-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V32i8 = sdiv <32 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+; FAST-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V64i8 = sdiv <64 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; SLOW-LABEL: 'sdiv_const'
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = sdiv i64 undef, 7
+; SLOW-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i64 = sdiv <2 x i64> undef, <i64 6, i64 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = sdiv <4 x i64> undef, <i64 4, i64 5, i64 6, i64 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i64 = sdiv <8 x i64> undef, <i64 4, i64 5, i64 6, i64 7, i64 8, i64 9, i64 10, i64 11>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = sdiv i32 undef, 7
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = sdiv <4 x i32> undef, <i32 4, i32 5, i32 6, i32 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i32 = sdiv <8 x i32> undef, <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i32 = sdiv <16 x i32> undef, <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = sdiv i16 undef, 7
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8i16 = sdiv <8 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16i16 = sdiv <16 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32i16 = sdiv <32 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19, i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = sdiv i8 undef, 7
+; SLOW-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16i8 = sdiv <16 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32i8 = sdiv <32 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V64i8 = sdiv <64 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; ALL-SIZE-LABEL: 'sdiv_const'
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = sdiv i64 undef, 7
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2i64 = sdiv <2 x i64> undef, <i64 6, i64 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = sdiv <4 x i64> undef, <i64 4, i64 5, i64 6, i64 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i64 = sdiv <8 x i64> undef, <i64 4, i64 5, i64 6, i64 7, i64 8, i64 9, i64 10, i64 11>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I32 = sdiv i32 undef, 7
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = sdiv <4 x i32> undef, <i32 4, i32 5, i32 6, i32 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i32 = sdiv <8 x i32> undef, <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i32 = sdiv <16 x i32> undef, <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = sdiv i16 undef, 7
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i16 = sdiv <8 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i16 = sdiv <16 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i16 = sdiv <32 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19, i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = sdiv i8 undef, 7
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i8 = sdiv <16 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i8 = sdiv <32 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V64i8 = sdiv <64 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %I64 = sdiv i64 undef, 7
+ %V2i64 = sdiv <2 x i64> undef, <i64 6, i64 7>
+ %V4i64 = sdiv <4 x i64> undef, <i64 4, i64 5, i64 6, i64 7>
+ %V8i64 = sdiv <8 x i64> undef, <i64 4, i64 5, i64 6, i64 7, i64 8, i64 9, i64 10, i64 11>
+
+ %I32 = sdiv i32 undef, 7
+ %V4i32 = sdiv <4 x i32> undef, <i32 4, i32 5, i32 6, i32 7>
+ %V8i32 = sdiv <8 x i32> undef, <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11>
+ %V16i32 = sdiv <16 x i32> undef, <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19>
+
+ %I16 = sdiv i16 undef, 7
+ %V8i16 = sdiv <8 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11>
+ %V16i16 = sdiv <16 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19>
+ %V32i16 = sdiv <32 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19, i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19>
+
+ %I8 = sdiv i8 undef, 7
+ %V16i8 = sdiv <16 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+ %V32i8 = sdiv <32 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+ %V64i8 = sdiv <64 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+
+ ret i32 undef
+}
+
+define i32 @udiv_const() {
+; FAST-LABEL: 'udiv_const'
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = udiv i64 undef, 7
+; FAST-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i64 = udiv <2 x i64> undef, <i64 6, i64 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = udiv <4 x i64> undef, <i64 4, i64 5, i64 6, i64 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i64 = udiv <8 x i64> undef, <i64 4, i64 5, i64 6, i64 7, i64 8, i64 9, i64 10, i64 11>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = udiv i32 undef, 7
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = udiv <4 x i32> undef, <i32 4, i32 5, i32 6, i32 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i32 = udiv <8 x i32> undef, <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11>
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i32 = udiv <16 x i32> undef, <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = udiv i16 undef, 7
+; FAST-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V8i16 = udiv <8 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11>
+; FAST-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %V16i16 = udiv <16 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19>
+; FAST-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %V32i16 = udiv <32 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19, i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = udiv i8 undef, 7
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i8 = udiv <16 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+; FAST-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V32i8 = udiv <32 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+; FAST-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V64i8 = udiv <64 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; SLOW-LABEL: 'udiv_const'
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = udiv i64 undef, 7
+; SLOW-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i64 = udiv <2 x i64> undef, <i64 6, i64 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = udiv <4 x i64> undef, <i64 4, i64 5, i64 6, i64 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i64 = udiv <8 x i64> undef, <i64 4, i64 5, i64 6, i64 7, i64 8, i64 9, i64 10, i64 11>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = udiv i32 undef, 7
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = udiv <4 x i32> undef, <i32 4, i32 5, i32 6, i32 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i32 = udiv <8 x i32> undef, <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i32 = udiv <16 x i32> undef, <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = udiv i16 undef, 7
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8i16 = udiv <8 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16i16 = udiv <16 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32i16 = udiv <32 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19, i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = udiv i8 undef, 7
+; SLOW-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16i8 = udiv <16 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32i8 = udiv <32 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V64i8 = udiv <64 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; ALL-SIZE-LABEL: 'udiv_const'
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = udiv i64 undef, 7
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2i64 = udiv <2 x i64> undef, <i64 6, i64 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = udiv <4 x i64> undef, <i64 4, i64 5, i64 6, i64 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i64 = udiv <8 x i64> undef, <i64 4, i64 5, i64 6, i64 7, i64 8, i64 9, i64 10, i64 11>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I32 = udiv i32 undef, 7
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = udiv <4 x i32> undef, <i32 4, i32 5, i32 6, i32 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i32 = udiv <8 x i32> undef, <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i32 = udiv <16 x i32> undef, <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = udiv i16 undef, 7
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i16 = udiv <8 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i16 = udiv <16 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i16 = udiv <32 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19, i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = udiv i8 undef, 7
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i8 = udiv <16 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i8 = udiv <32 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V64i8 = udiv <64 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %I64 = udiv i64 undef, 7
+ %V2i64 = udiv <2 x i64> undef, <i64 6, i64 7>
+ %V4i64 = udiv <4 x i64> undef, <i64 4, i64 5, i64 6, i64 7>
+ %V8i64 = udiv <8 x i64> undef, <i64 4, i64 5, i64 6, i64 7, i64 8, i64 9, i64 10, i64 11>
+
+ %I32 = udiv i32 undef, 7
+ %V4i32 = udiv <4 x i32> undef, <i32 4, i32 5, i32 6, i32 7>
+ %V8i32 = udiv <8 x i32> undef, <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11>
+ %V16i32 = udiv <16 x i32> undef, <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19>
+
+ %I16 = udiv i16 undef, 7
+ %V8i16 = udiv <8 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11>
+ %V16i16 = udiv <16 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19>
+ %V32i16 = udiv <32 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19, i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19>
+
+ %I8 = udiv i8 undef, 7
+ %V16i8 = udiv <16 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+ %V32i8 = udiv <32 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+ %V64i8 = udiv <64 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+
+ ret i32 undef
+}
+
+define i32 @sdiv_uniformconst() {
+; FAST-LABEL: 'sdiv_uniformconst'
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = sdiv i64 undef, 7
+; FAST-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i64 = sdiv <2 x i64> undef, <i64 7, i64 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = sdiv <4 x i64> undef, <i64 7, i64 7, i64 7, i64 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i64 = sdiv <8 x i64> undef, <i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = sdiv i32 undef, 7
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = sdiv <4 x i32> undef, <i32 7, i32 7, i32 7, i32 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i32 = sdiv <8 x i32> undef, <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i32 = sdiv <16 x i32> undef, <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = sdiv i16 undef, 7
+; FAST-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V8i16 = sdiv <8 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %V16i16 = sdiv <16 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %V32i16 = sdiv <32 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = sdiv i8 undef, 7
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i8 = sdiv <16 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V32i8 = sdiv <32 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V64i8 = sdiv <64 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; SLOW-LABEL: 'sdiv_uniformconst'
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = sdiv i64 undef, 7
+; SLOW-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i64 = sdiv <2 x i64> undef, <i64 7, i64 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = sdiv <4 x i64> undef, <i64 7, i64 7, i64 7, i64 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i64 = sdiv <8 x i64> undef, <i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = sdiv i32 undef, 7
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = sdiv <4 x i32> undef, <i32 7, i32 7, i32 7, i32 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i32 = sdiv <8 x i32> undef, <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i32 = sdiv <16 x i32> undef, <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = sdiv i16 undef, 7
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8i16 = sdiv <8 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16i16 = sdiv <16 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32i16 = sdiv <32 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = sdiv i8 undef, 7
+; SLOW-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16i8 = sdiv <16 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32i8 = sdiv <32 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V64i8 = sdiv <64 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; ALL-SIZE-LABEL: 'sdiv_uniformconst'
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = sdiv i64 undef, 7
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2i64 = sdiv <2 x i64> undef, <i64 7, i64 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = sdiv <4 x i64> undef, <i64 7, i64 7, i64 7, i64 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i64 = sdiv <8 x i64> undef, <i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I32 = sdiv i32 undef, 7
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = sdiv <4 x i32> undef, <i32 7, i32 7, i32 7, i32 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i32 = sdiv <8 x i32> undef, <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i32 = sdiv <16 x i32> undef, <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = sdiv i16 undef, 7
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i16 = sdiv <8 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i16 = sdiv <16 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i16 = sdiv <32 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = sdiv i8 undef, 7
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i8 = sdiv <16 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i8 = sdiv <32 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V64i8 = sdiv <64 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %I64 = sdiv i64 undef, 7
+ %V2i64 = sdiv <2 x i64> undef, <i64 7, i64 7>
+ %V4i64 = sdiv <4 x i64> undef, <i64 7, i64 7, i64 7, i64 7>
+ %V8i64 = sdiv <8 x i64> undef, <i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7>
+
+ %I32 = sdiv i32 undef, 7
+ %V4i32 = sdiv <4 x i32> undef, <i32 7, i32 7, i32 7, i32 7>
+ %V8i32 = sdiv <8 x i32> undef, <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
+ %V16i32 = sdiv <16 x i32> undef, <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
+
+ %I16 = sdiv i16 undef, 7
+ %V8i16 = sdiv <8 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+ %V16i16 = sdiv <16 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+ %V32i16 = sdiv <32 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+
+ %I8 = sdiv i8 undef, 7
+ %V16i8 = sdiv <16 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+ %V32i8 = sdiv <32 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+ %V64i8 = sdiv <64 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+
+ ret i32 undef
+}
+
+define i32 @udiv_uniformconst() {
+; FAST-LABEL: 'udiv_uniformconst'
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = udiv i64 undef, 7
+; FAST-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i64 = udiv <2 x i64> undef, <i64 7, i64 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = udiv <4 x i64> undef, <i64 7, i64 7, i64 7, i64 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i64 = udiv <8 x i64> undef, <i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = udiv i32 undef, 7
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = udiv <4 x i32> undef, <i32 7, i32 7, i32 7, i32 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i32 = udiv <8 x i32> undef, <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i32 = udiv <16 x i32> undef, <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = udiv i16 undef, 7
+; FAST-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V8i16 = udiv <8 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %V16i16 = udiv <16 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %V32i16 = udiv <32 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = udiv i8 undef, 7
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i8 = udiv <16 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V32i8 = udiv <32 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V64i8 = udiv <64 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; SLOW-LABEL: 'udiv_uniformconst'
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = udiv i64 undef, 7
+; SLOW-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i64 = udiv <2 x i64> undef, <i64 7, i64 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = udiv <4 x i64> undef, <i64 7, i64 7, i64 7, i64 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i64 = udiv <8 x i64> undef, <i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = udiv i32 undef, 7
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = udiv <4 x i32> undef, <i32 7, i32 7, i32 7, i32 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i32 = udiv <8 x i32> undef, <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i32 = udiv <16 x i32> undef, <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = udiv i16 undef, 7
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8i16 = udiv <8 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16i16 = udiv <16 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32i16 = udiv <32 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = udiv i8 undef, 7
+; SLOW-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16i8 = udiv <16 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32i8 = udiv <32 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V64i8 = udiv <64 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; ALL-SIZE-LABEL: 'udiv_uniformconst'
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = udiv i64 undef, 7
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2i64 = udiv <2 x i64> undef, <i64 7, i64 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = udiv <4 x i64> undef, <i64 7, i64 7, i64 7, i64 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i64 = udiv <8 x i64> undef, <i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I32 = udiv i32 undef, 7
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = udiv <4 x i32> undef, <i32 7, i32 7, i32 7, i32 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i32 = udiv <8 x i32> undef, <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i32 = udiv <16 x i32> undef, <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = udiv i16 undef, 7
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i16 = udiv <8 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i16 = udiv <16 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i16 = udiv <32 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = udiv i8 undef, 7
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i8 = udiv <16 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i8 = udiv <32 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V64i8 = udiv <64 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %I64 = udiv i64 undef, 7
+ %V2i64 = udiv <2 x i64> undef, <i64 7, i64 7>
+ %V4i64 = udiv <4 x i64> undef, <i64 7, i64 7, i64 7, i64 7>
+ %V8i64 = udiv <8 x i64> undef, <i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7>
+
+ %I32 = udiv i32 undef, 7
+ %V4i32 = udiv <4 x i32> undef, <i32 7, i32 7, i32 7, i32 7>
+ %V8i32 = udiv <8 x i32> undef, <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
+ %V16i32 = udiv <16 x i32> undef, <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
+
+ %I16 = udiv i16 undef, 7
+ %V8i16 = udiv <8 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+ %V16i16 = udiv <16 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+ %V32i16 = udiv <32 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+
+ %I8 = udiv i8 undef, 7
+ %V16i8 = udiv <16 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+ %V32i8 = udiv <32 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+ %V64i8 = udiv <64 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+
+ ret i32 undef
+}
+
+define i32 @sdiv_constpow2() {
+; FAST-LABEL: 'sdiv_constpow2'
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = sdiv i64 undef, 16
+; FAST-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i64 = sdiv <2 x i64> undef, <i64 8, i64 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = sdiv <4 x i64> undef, <i64 2, i64 4, i64 8, i64 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i64 = sdiv <8 x i64> undef, <i64 2, i64 4, i64 8, i64 16, i64 32, i64 64, i64 128, i64 256>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = sdiv i32 undef, 16
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = sdiv <4 x i32> undef, <i32 2, i32 4, i32 8, i32 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i32 = sdiv <8 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256>
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i32 = sdiv <16 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256, i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = sdiv i16 undef, 16
+; FAST-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V8i16 = sdiv <8 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+; FAST-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %V16i16 = sdiv <16 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+; FAST-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %V32i16 = sdiv <32 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = sdiv i8 undef, 16
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i8 = sdiv <16 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V32i8 = sdiv <32 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V64i8 = sdiv <64 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; SLOW-LABEL: 'sdiv_constpow2'
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = sdiv i64 undef, 16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i64 = sdiv <2 x i64> undef, <i64 8, i64 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = sdiv <4 x i64> undef, <i64 2, i64 4, i64 8, i64 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i64 = sdiv <8 x i64> undef, <i64 2, i64 4, i64 8, i64 16, i64 32, i64 64, i64 128, i64 256>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = sdiv i32 undef, 16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = sdiv <4 x i32> undef, <i32 2, i32 4, i32 8, i32 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i32 = sdiv <8 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i32 = sdiv <16 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256, i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = sdiv i16 undef, 16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8i16 = sdiv <8 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16i16 = sdiv <16 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32i16 = sdiv <32 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = sdiv i8 undef, 16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16i8 = sdiv <16 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32i8 = sdiv <32 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V64i8 = sdiv <64 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; ALL-SIZE-LABEL: 'sdiv_constpow2'
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = sdiv i64 undef, 16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2i64 = sdiv <2 x i64> undef, <i64 8, i64 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = sdiv <4 x i64> undef, <i64 2, i64 4, i64 8, i64 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i64 = sdiv <8 x i64> undef, <i64 2, i64 4, i64 8, i64 16, i64 32, i64 64, i64 128, i64 256>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I32 = sdiv i32 undef, 16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = sdiv <4 x i32> undef, <i32 2, i32 4, i32 8, i32 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i32 = sdiv <8 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i32 = sdiv <16 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256, i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = sdiv i16 undef, 16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i16 = sdiv <8 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i16 = sdiv <16 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i16 = sdiv <32 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = sdiv i8 undef, 16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i8 = sdiv <16 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i8 = sdiv <32 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V64i8 = sdiv <64 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %I64 = sdiv i64 undef, 16
+ %V2i64 = sdiv <2 x i64> undef, <i64 8, i64 16>
+ %V4i64 = sdiv <4 x i64> undef, <i64 2, i64 4, i64 8, i64 16>
+ %V8i64 = sdiv <8 x i64> undef, <i64 2, i64 4, i64 8, i64 16, i64 32, i64 64, i64 128, i64 256>
+
+ %I32 = sdiv i32 undef, 16
+ %V4i32 = sdiv <4 x i32> undef, <i32 2, i32 4, i32 8, i32 16>
+ %V8i32 = sdiv <8 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256>
+ %V16i32 = sdiv <16 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256, i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256>
+
+ %I16 = sdiv i16 undef, 16
+ %V8i16 = sdiv <8 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+ %V16i16 = sdiv <16 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+ %V32i16 = sdiv <32 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+
+ %I8 = sdiv i8 undef, 16
+ %V16i8 = sdiv <16 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+ %V32i8 = sdiv <32 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+ %V64i8 = sdiv <64 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+
+ ret i32 undef
+}
+
+define i32 @udiv_constpow2() {
+; FAST-LABEL: 'udiv_constpow2'
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = udiv i64 undef, 16
+; FAST-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i64 = udiv <2 x i64> undef, <i64 8, i64 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = udiv <4 x i64> undef, <i64 2, i64 4, i64 8, i64 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i64 = udiv <8 x i64> undef, <i64 2, i64 4, i64 8, i64 16, i64 32, i64 64, i64 128, i64 256>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = udiv i32 undef, 16
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = udiv <4 x i32> undef, <i32 2, i32 4, i32 8, i32 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i32 = udiv <8 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256>
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i32 = udiv <16 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256, i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = udiv i16 undef, 16
+; FAST-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V8i16 = udiv <8 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+; FAST-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %V16i16 = udiv <16 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+; FAST-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %V32i16 = udiv <32 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = udiv i8 undef, 16
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i8 = udiv <16 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V32i8 = udiv <32 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V64i8 = udiv <64 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; SLOW-LABEL: 'udiv_constpow2'
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = udiv i64 undef, 16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i64 = udiv <2 x i64> undef, <i64 8, i64 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = udiv <4 x i64> undef, <i64 2, i64 4, i64 8, i64 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i64 = udiv <8 x i64> undef, <i64 2, i64 4, i64 8, i64 16, i64 32, i64 64, i64 128, i64 256>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = udiv i32 undef, 16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = udiv <4 x i32> undef, <i32 2, i32 4, i32 8, i32 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i32 = udiv <8 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i32 = udiv <16 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256, i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = udiv i16 undef, 16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8i16 = udiv <8 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16i16 = udiv <16 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32i16 = udiv <32 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = udiv i8 undef, 16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16i8 = udiv <16 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32i8 = udiv <32 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V64i8 = udiv <64 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; ALL-SIZE-LABEL: 'udiv_constpow2'
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = udiv i64 undef, 16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2i64 = udiv <2 x i64> undef, <i64 8, i64 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = udiv <4 x i64> undef, <i64 2, i64 4, i64 8, i64 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i64 = udiv <8 x i64> undef, <i64 2, i64 4, i64 8, i64 16, i64 32, i64 64, i64 128, i64 256>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I32 = udiv i32 undef, 16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = udiv <4 x i32> undef, <i32 2, i32 4, i32 8, i32 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i32 = udiv <8 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i32 = udiv <16 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256, i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = udiv i16 undef, 16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i16 = udiv <8 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i16 = udiv <16 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i16 = udiv <32 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = udiv i8 undef, 16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i8 = udiv <16 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i8 = udiv <32 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V64i8 = udiv <64 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %I64 = udiv i64 undef, 16
+ %V2i64 = udiv <2 x i64> undef, <i64 8, i64 16>
+ %V4i64 = udiv <4 x i64> undef, <i64 2, i64 4, i64 8, i64 16>
+ %V8i64 = udiv <8 x i64> undef, <i64 2, i64 4, i64 8, i64 16, i64 32, i64 64, i64 128, i64 256>
+
+ %I32 = udiv i32 undef, 16
+ %V4i32 = udiv <4 x i32> undef, <i32 2, i32 4, i32 8, i32 16>
+ %V8i32 = udiv <8 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256>
+ %V16i32 = udiv <16 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256, i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256>
+
+ %I16 = udiv i16 undef, 16
+ %V8i16 = udiv <8 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+ %V16i16 = udiv <16 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+ %V32i16 = udiv <32 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+
+ %I8 = udiv i8 undef, 16
+ %V16i8 = udiv <16 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+ %V32i8 = udiv <32 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+ %V64i8 = udiv <64 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+
+ ret i32 undef
+}
+
+define i32 @sdiv_uniformconstpow2() {
+; FAST-LABEL: 'sdiv_uniformconstpow2'
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = sdiv i64 undef, 16
+; FAST-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i64 = sdiv <2 x i64> undef, <i64 16, i64 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = sdiv <4 x i64> undef, <i64 16, i64 16, i64 16, i64 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i64 = sdiv <8 x i64> undef, <i64 16, i64 16, i64 16, i64 16, i64 16, i64 16, i64 16, i64 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = sdiv i32 undef, 16
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = sdiv <4 x i32> undef, <i32 16, i32 16, i32 16, i32 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i32 = sdiv <8 x i32> undef, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i32 = sdiv <16 x i32> undef, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = sdiv i16 undef, 16
+; FAST-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V8i16 = sdiv <8 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %V16i16 = sdiv <16 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %V32i16 = sdiv <32 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = sdiv i8 undef, 16
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i8 = sdiv <16 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V32i8 = sdiv <32 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V64i8 = sdiv <64 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; SLOW-LABEL: 'sdiv_uniformconstpow2'
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = sdiv i64 undef, 16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i64 = sdiv <2 x i64> undef, <i64 16, i64 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = sdiv <4 x i64> undef, <i64 16, i64 16, i64 16, i64 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i64 = sdiv <8 x i64> undef, <i64 16, i64 16, i64 16, i64 16, i64 16, i64 16, i64 16, i64 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = sdiv i32 undef, 16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = sdiv <4 x i32> undef, <i32 16, i32 16, i32 16, i32 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i32 = sdiv <8 x i32> undef, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i32 = sdiv <16 x i32> undef, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = sdiv i16 undef, 16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8i16 = sdiv <8 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16i16 = sdiv <16 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32i16 = sdiv <32 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = sdiv i8 undef, 16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16i8 = sdiv <16 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32i8 = sdiv <32 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V64i8 = sdiv <64 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; ALL-SIZE-LABEL: 'sdiv_uniformconstpow2'
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = sdiv i64 undef, 16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2i64 = sdiv <2 x i64> undef, <i64 16, i64 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = sdiv <4 x i64> undef, <i64 16, i64 16, i64 16, i64 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i64 = sdiv <8 x i64> undef, <i64 16, i64 16, i64 16, i64 16, i64 16, i64 16, i64 16, i64 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I32 = sdiv i32 undef, 16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = sdiv <4 x i32> undef, <i32 16, i32 16, i32 16, i32 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i32 = sdiv <8 x i32> undef, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i32 = sdiv <16 x i32> undef, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = sdiv i16 undef, 16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i16 = sdiv <8 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i16 = sdiv <16 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i16 = sdiv <32 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = sdiv i8 undef, 16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i8 = sdiv <16 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i8 = sdiv <32 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V64i8 = sdiv <64 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %I64 = sdiv i64 undef, 16
+ %V2i64 = sdiv <2 x i64> undef, <i64 16, i64 16>
+ %V4i64 = sdiv <4 x i64> undef, <i64 16, i64 16, i64 16, i64 16>
+ %V8i64 = sdiv <8 x i64> undef, <i64 16, i64 16, i64 16, i64 16, i64 16, i64 16, i64 16, i64 16>
+
+ %I32 = sdiv i32 undef, 16
+ %V4i32 = sdiv <4 x i32> undef, <i32 16, i32 16, i32 16, i32 16>
+ %V8i32 = sdiv <8 x i32> undef, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
+ %V16i32 = sdiv <16 x i32> undef, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
+
+ %I16 = sdiv i16 undef, 16
+ %V8i16 = sdiv <8 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+ %V16i16 = sdiv <16 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+ %V32i16 = sdiv <32 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+
+ %I8 = sdiv i8 undef, 16
+ %V16i8 = sdiv <16 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+ %V32i8 = sdiv <32 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+ %V64i8 = sdiv <64 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+
+ ret i32 undef
+}
+
+define i32 @udiv_uniformconstpow2() {
+; FAST-LABEL: 'udiv_uniformconstpow2'
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = udiv i64 undef, 16
+; FAST-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i64 = udiv <2 x i64> undef, <i64 16, i64 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = udiv <4 x i64> undef, <i64 16, i64 16, i64 16, i64 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i64 = udiv <8 x i64> undef, <i64 16, i64 16, i64 16, i64 16, i64 16, i64 16, i64 16, i64 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = udiv i32 undef, 16
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = udiv <4 x i32> undef, <i32 16, i32 16, i32 16, i32 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i32 = udiv <8 x i32> undef, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i32 = udiv <16 x i32> undef, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = udiv i16 undef, 16
+; FAST-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V8i16 = udiv <8 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %V16i16 = udiv <16 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %V32i16 = udiv <32 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = udiv i8 undef, 16
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i8 = udiv <16 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V32i8 = udiv <32 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V64i8 = udiv <64 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; SLOW-LABEL: 'udiv_uniformconstpow2'
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = udiv i64 undef, 16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i64 = udiv <2 x i64> undef, <i64 16, i64 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = udiv <4 x i64> undef, <i64 16, i64 16, i64 16, i64 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i64 = udiv <8 x i64> undef, <i64 16, i64 16, i64 16, i64 16, i64 16, i64 16, i64 16, i64 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = udiv i32 undef, 16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = udiv <4 x i32> undef, <i32 16, i32 16, i32 16, i32 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i32 = udiv <8 x i32> undef, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i32 = udiv <16 x i32> undef, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = udiv i16 undef, 16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8i16 = udiv <8 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16i16 = udiv <16 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32i16 = udiv <32 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = udiv i8 undef, 16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16i8 = udiv <16 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32i8 = udiv <32 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V64i8 = udiv <64 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; ALL-SIZE-LABEL: 'udiv_uniformconstpow2'
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = udiv i64 undef, 16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2i64 = udiv <2 x i64> undef, <i64 16, i64 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = udiv <4 x i64> undef, <i64 16, i64 16, i64 16, i64 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i64 = udiv <8 x i64> undef, <i64 16, i64 16, i64 16, i64 16, i64 16, i64 16, i64 16, i64 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I32 = udiv i32 undef, 16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = udiv <4 x i32> undef, <i32 16, i32 16, i32 16, i32 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i32 = udiv <8 x i32> undef, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i32 = udiv <16 x i32> undef, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = udiv i16 undef, 16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i16 = udiv <8 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i16 = udiv <16 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i16 = udiv <32 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = udiv i8 undef, 16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i8 = udiv <16 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i8 = udiv <32 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V64i8 = udiv <64 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %I64 = udiv i64 undef, 16
+ %V2i64 = udiv <2 x i64> undef, <i64 16, i64 16>
+ %V4i64 = udiv <4 x i64> undef, <i64 16, i64 16, i64 16, i64 16>
+ %V8i64 = udiv <8 x i64> undef, <i64 16, i64 16, i64 16, i64 16, i64 16, i64 16, i64 16, i64 16>
+
+ %I32 = udiv i32 undef, 16
+ %V4i32 = udiv <4 x i32> undef, <i32 16, i32 16, i32 16, i32 16>
+ %V8i32 = udiv <8 x i32> undef, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
+ %V16i32 = udiv <16 x i32> undef, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
+
+ %I16 = udiv i16 undef, 16
+ %V8i16 = udiv <8 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+ %V16i16 = udiv <16 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+ %V32i16 = udiv <32 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+
+ %I8 = udiv i8 undef, 16
+ %V16i8 = udiv <16 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+ %V32i8 = udiv <32 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+ %V64i8 = udiv <64 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+
+ ret i32 undef
+}
+
+define i32 @sdiv_constnegpow2() {
+; FAST-LABEL: 'sdiv_constnegpow2'
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = sdiv i64 undef, -16
+; FAST-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i64 = sdiv <2 x i64> undef, <i64 -8, i64 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = sdiv <4 x i64> undef, <i64 -2, i64 -4, i64 -8, i64 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i64 = sdiv <8 x i64> undef, <i64 -2, i64 -4, i64 -8, i64 -16, i64 -32, i64 -64, i64 -128, i64 -256>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = sdiv i32 undef, -16
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = sdiv <4 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i32 = sdiv <8 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256>
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i32 = sdiv <16 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256, i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = sdiv i16 undef, -16
+; FAST-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V8i16 = sdiv <8 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+; FAST-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %V16i16 = sdiv <16 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+; FAST-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %V32i16 = sdiv <32 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = sdiv i8 undef, -16
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i8 = sdiv <16 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V32i8 = sdiv <32 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V64i8 = sdiv <64 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; SLOW-LABEL: 'sdiv_constnegpow2'
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = sdiv i64 undef, -16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i64 = sdiv <2 x i64> undef, <i64 -8, i64 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = sdiv <4 x i64> undef, <i64 -2, i64 -4, i64 -8, i64 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i64 = sdiv <8 x i64> undef, <i64 -2, i64 -4, i64 -8, i64 -16, i64 -32, i64 -64, i64 -128, i64 -256>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = sdiv i32 undef, -16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = sdiv <4 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i32 = sdiv <8 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i32 = sdiv <16 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256, i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = sdiv i16 undef, -16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8i16 = sdiv <8 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16i16 = sdiv <16 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32i16 = sdiv <32 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = sdiv i8 undef, -16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16i8 = sdiv <16 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32i8 = sdiv <32 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V64i8 = sdiv <64 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; ALL-SIZE-LABEL: 'sdiv_constnegpow2'
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = sdiv i64 undef, -16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2i64 = sdiv <2 x i64> undef, <i64 -8, i64 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = sdiv <4 x i64> undef, <i64 -2, i64 -4, i64 -8, i64 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i64 = sdiv <8 x i64> undef, <i64 -2, i64 -4, i64 -8, i64 -16, i64 -32, i64 -64, i64 -128, i64 -256>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I32 = sdiv i32 undef, -16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = sdiv <4 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i32 = sdiv <8 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i32 = sdiv <16 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256, i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = sdiv i16 undef, -16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i16 = sdiv <8 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i16 = sdiv <16 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i16 = sdiv <32 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = sdiv i8 undef, -16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i8 = sdiv <16 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i8 = sdiv <32 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V64i8 = sdiv <64 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %I64 = sdiv i64 undef, -16
+ %V2i64 = sdiv <2 x i64> undef, <i64 -8, i64 -16>
+ %V4i64 = sdiv <4 x i64> undef, <i64 -2, i64 -4, i64 -8, i64 -16>
+ %V8i64 = sdiv <8 x i64> undef, <i64 -2, i64 -4, i64 -8, i64 -16, i64 -32, i64 -64, i64 -128, i64 -256>
+
+ %I32 = sdiv i32 undef, -16
+ %V4i32 = sdiv <4 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16>
+ %V8i32 = sdiv <8 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256>
+ %V16i32 = sdiv <16 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256, i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256>
+
+ %I16 = sdiv i16 undef, -16
+ %V8i16 = sdiv <8 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+ %V16i16 = sdiv <16 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+ %V32i16 = sdiv <32 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+
+ %I8 = sdiv i8 undef, -16
+ %V16i8 = sdiv <16 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+ %V32i8 = sdiv <32 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+ %V64i8 = sdiv <64 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+
+ ret i32 undef
+}
+
+define i32 @udiv_constnegpow2() {
+; FAST-LABEL: 'udiv_constnegpow2'
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = udiv i64 undef, -16
+; FAST-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i64 = udiv <2 x i64> undef, <i64 -8, i64 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = udiv <4 x i64> undef, <i64 -2, i64 -4, i64 -8, i64 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i64 = udiv <8 x i64> undef, <i64 -2, i64 -4, i64 -8, i64 -16, i64 -32, i64 -64, i64 -128, i64 -256>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = udiv i32 undef, -16
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = udiv <4 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i32 = udiv <8 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256>
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i32 = udiv <16 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256, i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = udiv i16 undef, -16
+; FAST-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V8i16 = udiv <8 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+; FAST-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %V16i16 = udiv <16 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+; FAST-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %V32i16 = udiv <32 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = udiv i8 undef, -16
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i8 = udiv <16 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V32i8 = udiv <32 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V64i8 = udiv <64 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; SLOW-LABEL: 'udiv_constnegpow2'
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = udiv i64 undef, -16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i64 = udiv <2 x i64> undef, <i64 -8, i64 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = udiv <4 x i64> undef, <i64 -2, i64 -4, i64 -8, i64 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i64 = udiv <8 x i64> undef, <i64 -2, i64 -4, i64 -8, i64 -16, i64 -32, i64 -64, i64 -128, i64 -256>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = udiv i32 undef, -16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = udiv <4 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i32 = udiv <8 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i32 = udiv <16 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256, i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = udiv i16 undef, -16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8i16 = udiv <8 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16i16 = udiv <16 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32i16 = udiv <32 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = udiv i8 undef, -16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16i8 = udiv <16 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32i8 = udiv <32 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V64i8 = udiv <64 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; ALL-SIZE-LABEL: 'udiv_constnegpow2'
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = udiv i64 undef, -16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2i64 = udiv <2 x i64> undef, <i64 -8, i64 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = udiv <4 x i64> undef, <i64 -2, i64 -4, i64 -8, i64 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i64 = udiv <8 x i64> undef, <i64 -2, i64 -4, i64 -8, i64 -16, i64 -32, i64 -64, i64 -128, i64 -256>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I32 = udiv i32 undef, -16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = udiv <4 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i32 = udiv <8 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i32 = udiv <16 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256, i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = udiv i16 undef, -16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i16 = udiv <8 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i16 = udiv <16 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i16 = udiv <32 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = udiv i8 undef, -16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i8 = udiv <16 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i8 = udiv <32 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V64i8 = udiv <64 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %I64 = udiv i64 undef, -16
+ %V2i64 = udiv <2 x i64> undef, <i64 -8, i64 -16>
+ %V4i64 = udiv <4 x i64> undef, <i64 -2, i64 -4, i64 -8, i64 -16>
+ %V8i64 = udiv <8 x i64> undef, <i64 -2, i64 -4, i64 -8, i64 -16, i64 -32, i64 -64, i64 -128, i64 -256>
+
+ %I32 = udiv i32 undef, -16
+ %V4i32 = udiv <4 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16>
+ %V8i32 = udiv <8 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256>
+ %V16i32 = udiv <16 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256, i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256>
+
+ %I16 = udiv i16 undef, -16
+ %V8i16 = udiv <8 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+ %V16i16 = udiv <16 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+ %V32i16 = udiv <32 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+
+ %I8 = udiv i8 undef, -16
+ %V16i8 = udiv <16 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+ %V32i8 = udiv <32 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+ %V64i8 = udiv <64 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+
+ ret i32 undef
+}
+
+define i32 @sdiv_uniformconstnegpow2() {
+; FAST-LABEL: 'sdiv_uniformconstnegpow2'
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = sdiv i64 undef, -16
+; FAST-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i64 = sdiv <2 x i64> undef, <i64 -16, i64 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = sdiv <4 x i64> undef, <i64 -16, i64 -16, i64 -16, i64 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i64 = sdiv <8 x i64> undef, <i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = sdiv i32 undef, -16
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = sdiv <4 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i32 = sdiv <8 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i32 = sdiv <16 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = sdiv i16 undef, -16
+; FAST-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V8i16 = sdiv <8 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %V16i16 = sdiv <16 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %V32i16 = sdiv <32 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = sdiv i8 undef, -16
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i8 = sdiv <16 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V32i8 = sdiv <32 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V64i8 = sdiv <64 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; SLOW-LABEL: 'sdiv_uniformconstnegpow2'
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = sdiv i64 undef, -16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i64 = sdiv <2 x i64> undef, <i64 -16, i64 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = sdiv <4 x i64> undef, <i64 -16, i64 -16, i64 -16, i64 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i64 = sdiv <8 x i64> undef, <i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = sdiv i32 undef, -16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = sdiv <4 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i32 = sdiv <8 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i32 = sdiv <16 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = sdiv i16 undef, -16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8i16 = sdiv <8 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16i16 = sdiv <16 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32i16 = sdiv <32 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = sdiv i8 undef, -16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16i8 = sdiv <16 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32i8 = sdiv <32 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V64i8 = sdiv <64 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; ALL-SIZE-LABEL: 'sdiv_uniformconstnegpow2'
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = sdiv i64 undef, -16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2i64 = sdiv <2 x i64> undef, <i64 -16, i64 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = sdiv <4 x i64> undef, <i64 -16, i64 -16, i64 -16, i64 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i64 = sdiv <8 x i64> undef, <i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I32 = sdiv i32 undef, -16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = sdiv <4 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i32 = sdiv <8 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i32 = sdiv <16 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = sdiv i16 undef, -16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i16 = sdiv <8 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i16 = sdiv <16 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i16 = sdiv <32 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = sdiv i8 undef, -16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i8 = sdiv <16 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i8 = sdiv <32 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V64i8 = sdiv <64 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %I64 = sdiv i64 undef, -16
+ %V2i64 = sdiv <2 x i64> undef, <i64 -16, i64 -16>
+ %V4i64 = sdiv <4 x i64> undef, <i64 -16, i64 -16, i64 -16, i64 -16>
+ %V8i64 = sdiv <8 x i64> undef, <i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16>
+
+ %I32 = sdiv i32 undef, -16
+ %V4i32 = sdiv <4 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16>
+ %V8i32 = sdiv <8 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16>
+ %V16i32 = sdiv <16 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16>
+
+ %I16 = sdiv i16 undef, -16
+ %V8i16 = sdiv <8 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+ %V16i16 = sdiv <16 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+ %V32i16 = sdiv <32 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+
+ %I8 = sdiv i8 undef, -16
+ %V16i8 = sdiv <16 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+ %V32i8 = sdiv <32 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+ %V64i8 = sdiv <64 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+
+ ret i32 undef
+}
+
+define i32 @udiv_uniformconstnegpow2() {
+; FAST-LABEL: 'udiv_uniformconstnegpow2'
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = udiv i64 undef, -16
+; FAST-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i64 = udiv <2 x i64> undef, <i64 -16, i64 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = udiv <4 x i64> undef, <i64 -16, i64 -16, i64 -16, i64 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i64 = udiv <8 x i64> undef, <i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = udiv i32 undef, -16
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = udiv <4 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i32 = udiv <8 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i32 = udiv <16 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = udiv i16 undef, -16
+; FAST-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V8i16 = udiv <8 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %V16i16 = udiv <16 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %V32i16 = udiv <32 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = udiv i8 undef, -16
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i8 = udiv <16 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V32i8 = udiv <32 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V64i8 = udiv <64 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; SLOW-LABEL: 'udiv_uniformconstnegpow2'
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = udiv i64 undef, -16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2i64 = udiv <2 x i64> undef, <i64 -16, i64 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = udiv <4 x i64> undef, <i64 -16, i64 -16, i64 -16, i64 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i64 = udiv <8 x i64> undef, <i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = udiv i32 undef, -16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = udiv <4 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8i32 = udiv <8 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i32 = udiv <16 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = udiv i16 undef, -16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8i16 = udiv <8 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16i16 = udiv <16 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32i16 = udiv <32 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = udiv i8 undef, -16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16i8 = udiv <16 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V32i8 = udiv <32 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V64i8 = udiv <64 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; ALL-SIZE-LABEL: 'udiv_uniformconstnegpow2'
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = udiv i64 undef, -16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2i64 = udiv <2 x i64> undef, <i64 -16, i64 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = udiv <4 x i64> undef, <i64 -16, i64 -16, i64 -16, i64 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i64 = udiv <8 x i64> undef, <i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I32 = udiv i32 undef, -16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = udiv <4 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i32 = udiv <8 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i32 = udiv <16 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = udiv i16 undef, -16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i16 = udiv <8 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i16 = udiv <16 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i16 = udiv <32 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = udiv i8 undef, -16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i8 = udiv <16 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i8 = udiv <32 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V64i8 = udiv <64 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %I64 = udiv i64 undef, -16
+ %V2i64 = udiv <2 x i64> undef, <i64 -16, i64 -16>
+ %V4i64 = udiv <4 x i64> undef, <i64 -16, i64 -16, i64 -16, i64 -16>
+ %V8i64 = udiv <8 x i64> undef, <i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16>
+
+ %I32 = udiv i32 undef, -16
+ %V4i32 = udiv <4 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16>
+ %V8i32 = udiv <8 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16>
+ %V16i32 = udiv <16 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16>
+
+ %I16 = udiv i16 undef, -16
+ %V8i16 = udiv <8 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+ %V16i16 = udiv <16 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+ %V32i16 = udiv <32 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+
+ %I8 = udiv i8 undef, -16
+ %V16i8 = udiv <16 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+ %V32i8 = udiv <32 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+ %V64i8 = udiv <64 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+
+ ret i32 undef
+}
diff --git a/llvm/test/Analysis/CostModel/AMDGPU/fptosi.ll b/llvm/test/Analysis/CostModel/AMDGPU/fptosi.ll
new file mode 100644
index 000000000000..3c24d6cdcd28
--- /dev/null
+++ b/llvm/test/Analysis/CostModel/AMDGPU/fptosi.ll
@@ -0,0 +1,259 @@
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
+; RUN: opt -cost-model -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx1010 < %s | FileCheck -check-prefixes=ALL,FAST %s
+; RUN: opt -cost-model -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx90a < %s | FileCheck -check-prefixes=ALL,FAST %s
+; RUN: opt -cost-model -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx900 < %s | FileCheck -check-prefixes=ALL,FAST %s
+; RUN: opt -cost-model -analyze -mtriple=amdgcn-unknown-amdhsa < %s | FileCheck -check-prefixes=ALL,SLOW %s
+
+; RUN: opt -cost-model -cost-kind=code-size -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx1010 < %s | FileCheck -check-prefixes=ALL-SIZE,FAST-SIZE %s
+; RUN: opt -cost-model -cost-kind=code-size -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx90a < %s | FileCheck -check-prefixes=ALL-SIZE,FAST-SIZE %s
+; RUN: opt -cost-model -cost-kind=code-size -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx900 < %s | FileCheck -check-prefixes=ALL-SIZE,FAST-SIZE %s
+; RUN: opt -cost-model -cost-kind=code-size -analyze -mtriple=amdgcn-unknown-amdhsa < %s | FileCheck -check-prefixes=ALL-SIZE,SLOW-SIZE %s
+; END.
+
+define i32 @fptosi_double_i64(i32 %arg) {
+; ALL-LABEL: 'fptosi_double_i64'
+; ALL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = fptosi double undef to i64
+; ALL-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I64 = fptosi <2 x double> undef to <2 x i64>
+; ALL-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I64 = fptosi <4 x double> undef to <4 x i64>
+; ALL-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I64 = fptosi <8 x double> undef to <8 x i64>
+; ALL-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; ALL-SIZE-LABEL: 'fptosi_double_i64'
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = fptosi double undef to i64
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I64 = fptosi <2 x double> undef to <2 x i64>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I64 = fptosi <4 x double> undef to <4 x i64>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I64 = fptosi <8 x double> undef to <8 x i64>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %I64 = fptosi double undef to i64
+ %V2I64 = fptosi <2 x double> undef to <2 x i64>
+ %V4I64 = fptosi <4 x double> undef to <4 x i64>
+ %V8I64 = fptosi <8 x double> undef to <8 x i64>
+ ret i32 undef
+}
+
+define i32 @fptosi_double_i32(i32 %arg) {
+; ALL-LABEL: 'fptosi_double_i32'
+; ALL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = fptosi double undef to i32
+; ALL-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I32 = fptosi <2 x double> undef to <2 x i32>
+; ALL-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I32 = fptosi <4 x double> undef to <4 x i32>
+; ALL-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I32 = fptosi <8 x double> undef to <8 x i32>
+; ALL-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; ALL-SIZE-LABEL: 'fptosi_double_i32'
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = fptosi double undef to i32
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I32 = fptosi <2 x double> undef to <2 x i32>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I32 = fptosi <4 x double> undef to <4 x i32>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I32 = fptosi <8 x double> undef to <8 x i32>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %I32 = fptosi double undef to i32
+ %V2I32 = fptosi <2 x double> undef to <2 x i32>
+ %V4I32 = fptosi <4 x double> undef to <4 x i32>
+ %V8I32 = fptosi <8 x double> undef to <8 x i32>
+ ret i32 undef
+}
+
+define i32 @fptosi_double_i16(i32 %arg) {
+; FAST-LABEL: 'fptosi_double_i16'
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = fptosi double undef to i16
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I16 = fptosi <2 x double> undef to <2 x i16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4I16 = fptosi <4 x double> undef to <4 x i16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V8I16 = fptosi <8 x double> undef to <8 x i16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; SLOW-LABEL: 'fptosi_double_i16'
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = fptosi double undef to i16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I16 = fptosi <2 x double> undef to <2 x i16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I16 = fptosi <4 x double> undef to <4 x i16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I16 = fptosi <8 x double> undef to <8 x i16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; FAST-SIZE-LABEL: 'fptosi_double_i16'
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = fptosi double undef to i16
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I16 = fptosi <2 x double> undef to <2 x i16>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4I16 = fptosi <4 x double> undef to <4 x i16>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V8I16 = fptosi <8 x double> undef to <8 x i16>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; SLOW-SIZE-LABEL: 'fptosi_double_i16'
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = fptosi double undef to i16
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I16 = fptosi <2 x double> undef to <2 x i16>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I16 = fptosi <4 x double> undef to <4 x i16>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I16 = fptosi <8 x double> undef to <8 x i16>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %I16 = fptosi double undef to i16
+ %V2I16 = fptosi <2 x double> undef to <2 x i16>
+ %V4I16 = fptosi <4 x double> undef to <4 x i16>
+ %V8I16 = fptosi <8 x double> undef to <8 x i16>
+ ret i32 undef
+}
+
+define i32 @fptosi_double_i8(i32 %arg) {
+; FAST-LABEL: 'fptosi_double_i8'
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = fptosi double undef to i8
+; FAST-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V2I8 = fptosi <2 x double> undef to <2 x i8>
+; FAST-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V4I8 = fptosi <4 x double> undef to <4 x i8>
+; FAST-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V8I8 = fptosi <8 x double> undef to <8 x i8>
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; SLOW-LABEL: 'fptosi_double_i8'
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = fptosi double undef to i8
+; SLOW-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I8 = fptosi <2 x double> undef to <2 x i8>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I8 = fptosi <4 x double> undef to <4 x i8>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I8 = fptosi <8 x double> undef to <8 x i8>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; FAST-SIZE-LABEL: 'fptosi_double_i8'
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = fptosi double undef to i8
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V2I8 = fptosi <2 x double> undef to <2 x i8>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V4I8 = fptosi <4 x double> undef to <4 x i8>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V8I8 = fptosi <8 x double> undef to <8 x i8>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; SLOW-SIZE-LABEL: 'fptosi_double_i8'
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = fptosi double undef to i8
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I8 = fptosi <2 x double> undef to <2 x i8>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I8 = fptosi <4 x double> undef to <4 x i8>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I8 = fptosi <8 x double> undef to <8 x i8>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %I8 = fptosi double undef to i8
+ %V2I8 = fptosi <2 x double> undef to <2 x i8>
+ %V4I8 = fptosi <4 x double> undef to <4 x i8>
+ %V8I8 = fptosi <8 x double> undef to <8 x i8>
+ ret i32 undef
+}
+
+define i32 @fptosi_float_i64(i32 %arg) {
+; ALL-LABEL: 'fptosi_float_i64'
+; ALL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = fptosi float undef to i64
+; ALL-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I64 = fptosi <2 x float> undef to <2 x i64>
+; ALL-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I64 = fptosi <4 x float> undef to <4 x i64>
+; ALL-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I64 = fptosi <8 x float> undef to <8 x i64>
+; ALL-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16I64 = fptosi <16 x float> undef to <16 x i64>
+; ALL-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; ALL-SIZE-LABEL: 'fptosi_float_i64'
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = fptosi float undef to i64
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I64 = fptosi <2 x float> undef to <2 x i64>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I64 = fptosi <4 x float> undef to <4 x i64>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I64 = fptosi <8 x float> undef to <8 x i64>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16I64 = fptosi <16 x float> undef to <16 x i64>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %I64 = fptosi float undef to i64
+ %V2I64 = fptosi <2 x float> undef to <2 x i64>
+ %V4I64 = fptosi <4 x float> undef to <4 x i64>
+ %V8I64 = fptosi <8 x float> undef to <8 x i64>
+ %V16I64 = fptosi <16 x float> undef to <16 x i64>
+ ret i32 undef
+}
+
+define i32 @fptosi_float_i32(i32 %arg) {
+; ALL-LABEL: 'fptosi_float_i32'
+; ALL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = fptosi float undef to i32
+; ALL-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I32 = fptosi <2 x float> undef to <2 x i32>
+; ALL-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I32 = fptosi <4 x float> undef to <4 x i32>
+; ALL-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I32 = fptosi <8 x float> undef to <8 x i32>
+; ALL-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16I32 = fptosi <16 x float> undef to <16 x i32>
+; ALL-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; ALL-SIZE-LABEL: 'fptosi_float_i32'
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = fptosi float undef to i32
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I32 = fptosi <2 x float> undef to <2 x i32>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I32 = fptosi <4 x float> undef to <4 x i32>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I32 = fptosi <8 x float> undef to <8 x i32>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16I32 = fptosi <16 x float> undef to <16 x i32>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %I32 = fptosi float undef to i32
+ %V2I32 = fptosi <2 x float> undef to <2 x i32>
+ %V4I32 = fptosi <4 x float> undef to <4 x i32>
+ %V8I32 = fptosi <8 x float> undef to <8 x i32>
+ %V16I32 = fptosi <16 x float> undef to <16 x i32>
+ ret i32 undef
+}
+
+define i32 @fptosi_float_i16(i32 %arg) {
+; FAST-LABEL: 'fptosi_float_i16'
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = fptosi float undef to i16
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I16 = fptosi <2 x float> undef to <2 x i16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4I16 = fptosi <4 x float> undef to <4 x i16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V8I16 = fptosi <8 x float> undef to <8 x i16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V16I16 = fptosi <16 x float> undef to <16 x i16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; SLOW-LABEL: 'fptosi_float_i16'
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = fptosi float undef to i16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I16 = fptosi <2 x float> undef to <2 x i16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I16 = fptosi <4 x float> undef to <4 x i16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I16 = fptosi <8 x float> undef to <8 x i16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16I16 = fptosi <16 x float> undef to <16 x i16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; FAST-SIZE-LABEL: 'fptosi_float_i16'
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = fptosi float undef to i16
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I16 = fptosi <2 x float> undef to <2 x i16>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4I16 = fptosi <4 x float> undef to <4 x i16>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V8I16 = fptosi <8 x float> undef to <8 x i16>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V16I16 = fptosi <16 x float> undef to <16 x i16>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; SLOW-SIZE-LABEL: 'fptosi_float_i16'
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = fptosi float undef to i16
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I16 = fptosi <2 x float> undef to <2 x i16>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I16 = fptosi <4 x float> undef to <4 x i16>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I16 = fptosi <8 x float> undef to <8 x i16>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16I16 = fptosi <16 x float> undef to <16 x i16>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %I16 = fptosi float undef to i16
+ %V2I16 = fptosi <2 x float> undef to <2 x i16>
+ %V4I16 = fptosi <4 x float> undef to <4 x i16>
+ %V8I16 = fptosi <8 x float> undef to <8 x i16>
+ %V16I16 = fptosi <16 x float> undef to <16 x i16>
+ ret i32 undef
+}
+
+define i32 @fptosi_float_i8(i32 %arg) {
+; FAST-LABEL: 'fptosi_float_i8'
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = fptosi float undef to i8
+; FAST-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V2I8 = fptosi <2 x float> undef to <2 x i8>
+; FAST-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V4I8 = fptosi <4 x float> undef to <4 x i8>
+; FAST-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V8I8 = fptosi <8 x float> undef to <8 x i8>
+; FAST-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V16I8 = fptosi <16 x float> undef to <16 x i8>
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; SLOW-LABEL: 'fptosi_float_i8'
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = fptosi float undef to i8
+; SLOW-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I8 = fptosi <2 x float> undef to <2 x i8>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I8 = fptosi <4 x float> undef to <4 x i8>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I8 = fptosi <8 x float> undef to <8 x i8>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16I8 = fptosi <16 x float> undef to <16 x i8>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; FAST-SIZE-LABEL: 'fptosi_float_i8'
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = fptosi float undef to i8
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V2I8 = fptosi <2 x float> undef to <2 x i8>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V4I8 = fptosi <4 x float> undef to <4 x i8>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V8I8 = fptosi <8 x float> undef to <8 x i8>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V16I8 = fptosi <16 x float> undef to <16 x i8>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; SLOW-SIZE-LABEL: 'fptosi_float_i8'
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = fptosi float undef to i8
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I8 = fptosi <2 x float> undef to <2 x i8>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I8 = fptosi <4 x float> undef to <4 x i8>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I8 = fptosi <8 x float> undef to <8 x i8>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16I8 = fptosi <16 x float> undef to <16 x i8>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %I8 = fptosi float undef to i8
+ %V2I8 = fptosi <2 x float> undef to <2 x i8>
+ %V4I8 = fptosi <4 x float> undef to <4 x i8>
+ %V8I8 = fptosi <8 x float> undef to <8 x i8>
+ %V16I8 = fptosi <16 x float> undef to <16 x i8>
+ ret i32 undef
+}
diff --git a/llvm/test/Analysis/CostModel/AMDGPU/fptoui.ll b/llvm/test/Analysis/CostModel/AMDGPU/fptoui.ll
new file mode 100644
index 000000000000..e2f75a9f302c
--- /dev/null
+++ b/llvm/test/Analysis/CostModel/AMDGPU/fptoui.ll
@@ -0,0 +1,259 @@
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
+; RUN: opt -cost-model -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx1010 < %s | FileCheck -check-prefixes=ALL,FAST %s
+; RUN: opt -cost-model -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx90a < %s | FileCheck -check-prefixes=ALL,FAST %s
+; RUN: opt -cost-model -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx900 < %s | FileCheck -check-prefixes=ALL,FAST %s
+; RUN: opt -cost-model -analyze -mtriple=amdgcn-unknown-amdhsa < %s | FileCheck -check-prefixes=ALL,SLOW %s
+
+; RUN: opt -cost-model -cost-kind=code-size -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx1010 < %s | FileCheck -check-prefixes=ALL-SIZE,FAST-SIZE %s
+; RUN: opt -cost-model -cost-kind=code-size -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx90a < %s | FileCheck -check-prefixes=ALL-SIZE,FAST-SIZE %s
+; RUN: opt -cost-model -cost-kind=code-size -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx900 < %s | FileCheck -check-prefixes=ALL-SIZE,FAST-SIZE %s
+; RUN: opt -cost-model -cost-kind=code-size -analyze -mtriple=amdgcn-unknown-amdhsa < %s | FileCheck -check-prefixes=ALL-SIZE,SLOW-SIZE %s
+; END.
+
+define i32 @fptoui_double_i64(i32 %arg) {
+; ALL-LABEL: 'fptoui_double_i64'
+; ALL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = fptoui double undef to i64
+; ALL-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I64 = fptoui <2 x double> undef to <2 x i64>
+; ALL-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I64 = fptoui <4 x double> undef to <4 x i64>
+; ALL-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I64 = fptoui <8 x double> undef to <8 x i64>
+; ALL-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; ALL-SIZE-LABEL: 'fptoui_double_i64'
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = fptoui double undef to i64
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I64 = fptoui <2 x double> undef to <2 x i64>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I64 = fptoui <4 x double> undef to <4 x i64>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I64 = fptoui <8 x double> undef to <8 x i64>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %I64 = fptoui double undef to i64
+ %V2I64 = fptoui <2 x double> undef to <2 x i64>
+ %V4I64 = fptoui <4 x double> undef to <4 x i64>
+ %V8I64 = fptoui <8 x double> undef to <8 x i64>
+ ret i32 undef
+}
+
+define i32 @fptoui_double_i32(i32 %arg) {
+; ALL-LABEL: 'fptoui_double_i32'
+; ALL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = fptoui double undef to i32
+; ALL-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I32 = fptoui <2 x double> undef to <2 x i32>
+; ALL-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I32 = fptoui <4 x double> undef to <4 x i32>
+; ALL-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I32 = fptoui <8 x double> undef to <8 x i32>
+; ALL-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; ALL-SIZE-LABEL: 'fptoui_double_i32'
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = fptoui double undef to i32
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I32 = fptoui <2 x double> undef to <2 x i32>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I32 = fptoui <4 x double> undef to <4 x i32>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I32 = fptoui <8 x double> undef to <8 x i32>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %I32 = fptoui double undef to i32
+ %V2I32 = fptoui <2 x double> undef to <2 x i32>
+ %V4I32 = fptoui <4 x double> undef to <4 x i32>
+ %V8I32 = fptoui <8 x double> undef to <8 x i32>
+ ret i32 undef
+}
+
+define i32 @fptoui_double_i16(i32 %arg) {
+; FAST-LABEL: 'fptoui_double_i16'
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = fptoui double undef to i16
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I16 = fptoui <2 x double> undef to <2 x i16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4I16 = fptoui <4 x double> undef to <4 x i16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V8I16 = fptoui <8 x double> undef to <8 x i16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; SLOW-LABEL: 'fptoui_double_i16'
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = fptoui double undef to i16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I16 = fptoui <2 x double> undef to <2 x i16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I16 = fptoui <4 x double> undef to <4 x i16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I16 = fptoui <8 x double> undef to <8 x i16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; FAST-SIZE-LABEL: 'fptoui_double_i16'
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = fptoui double undef to i16
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I16 = fptoui <2 x double> undef to <2 x i16>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4I16 = fptoui <4 x double> undef to <4 x i16>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V8I16 = fptoui <8 x double> undef to <8 x i16>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; SLOW-SIZE-LABEL: 'fptoui_double_i16'
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = fptoui double undef to i16
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I16 = fptoui <2 x double> undef to <2 x i16>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I16 = fptoui <4 x double> undef to <4 x i16>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I16 = fptoui <8 x double> undef to <8 x i16>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %I16 = fptoui double undef to i16
+ %V2I16 = fptoui <2 x double> undef to <2 x i16>
+ %V4I16 = fptoui <4 x double> undef to <4 x i16>
+ %V8I16 = fptoui <8 x double> undef to <8 x i16>
+ ret i32 undef
+}
+
+define i32 @fptoui_double_i8(i32 %arg) {
+; FAST-LABEL: 'fptoui_double_i8'
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = fptoui double undef to i8
+; FAST-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V2I8 = fptoui <2 x double> undef to <2 x i8>
+; FAST-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V4I8 = fptoui <4 x double> undef to <4 x i8>
+; FAST-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V8I8 = fptoui <8 x double> undef to <8 x i8>
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; SLOW-LABEL: 'fptoui_double_i8'
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = fptoui double undef to i8
+; SLOW-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I8 = fptoui <2 x double> undef to <2 x i8>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I8 = fptoui <4 x double> undef to <4 x i8>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I8 = fptoui <8 x double> undef to <8 x i8>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; FAST-SIZE-LABEL: 'fptoui_double_i8'
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = fptoui double undef to i8
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V2I8 = fptoui <2 x double> undef to <2 x i8>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V4I8 = fptoui <4 x double> undef to <4 x i8>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V8I8 = fptoui <8 x double> undef to <8 x i8>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; SLOW-SIZE-LABEL: 'fptoui_double_i8'
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = fptoui double undef to i8
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I8 = fptoui <2 x double> undef to <2 x i8>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I8 = fptoui <4 x double> undef to <4 x i8>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I8 = fptoui <8 x double> undef to <8 x i8>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %I8 = fptoui double undef to i8
+ %V2I8 = fptoui <2 x double> undef to <2 x i8>
+ %V4I8 = fptoui <4 x double> undef to <4 x i8>
+ %V8I8 = fptoui <8 x double> undef to <8 x i8>
+ ret i32 undef
+}
+
+define i32 @fptoui_float_i64(i32 %arg) {
+; ALL-LABEL: 'fptoui_float_i64'
+; ALL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = fptoui float undef to i64
+; ALL-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I64 = fptoui <2 x float> undef to <2 x i64>
+; ALL-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I64 = fptoui <4 x float> undef to <4 x i64>
+; ALL-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I64 = fptoui <8 x float> undef to <8 x i64>
+; ALL-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16I64 = fptoui <16 x float> undef to <16 x i64>
+; ALL-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; ALL-SIZE-LABEL: 'fptoui_float_i64'
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I64 = fptoui float undef to i64
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I64 = fptoui <2 x float> undef to <2 x i64>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I64 = fptoui <4 x float> undef to <4 x i64>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I64 = fptoui <8 x float> undef to <8 x i64>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16I64 = fptoui <16 x float> undef to <16 x i64>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %I64 = fptoui float undef to i64
+ %V2I64 = fptoui <2 x float> undef to <2 x i64>
+ %V4I64 = fptoui <4 x float> undef to <4 x i64>
+ %V8I64 = fptoui <8 x float> undef to <8 x i64>
+ %V16I64 = fptoui <16 x float> undef to <16 x i64>
+ ret i32 undef
+}
+
+define i32 @fptoui_float_i32(i32 %arg) {
+; ALL-LABEL: 'fptoui_float_i32'
+; ALL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = fptoui float undef to i32
+; ALL-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I32 = fptoui <2 x float> undef to <2 x i32>
+; ALL-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I32 = fptoui <4 x float> undef to <4 x i32>
+; ALL-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I32 = fptoui <8 x float> undef to <8 x i32>
+; ALL-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16I32 = fptoui <16 x float> undef to <16 x i32>
+; ALL-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; ALL-SIZE-LABEL: 'fptoui_float_i32'
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I32 = fptoui float undef to i32
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I32 = fptoui <2 x float> undef to <2 x i32>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I32 = fptoui <4 x float> undef to <4 x i32>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I32 = fptoui <8 x float> undef to <8 x i32>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16I32 = fptoui <16 x float> undef to <16 x i32>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %I32 = fptoui float undef to i32
+ %V2I32 = fptoui <2 x float> undef to <2 x i32>
+ %V4I32 = fptoui <4 x float> undef to <4 x i32>
+ %V8I32 = fptoui <8 x float> undef to <8 x i32>
+ %V16I32 = fptoui <16 x float> undef to <16 x i32>
+ ret i32 undef
+}
+
+define i32 @fptoui_float_i16(i32 %arg) {
+; FAST-LABEL: 'fptoui_float_i16'
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = fptoui float undef to i16
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I16 = fptoui <2 x float> undef to <2 x i16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4I16 = fptoui <4 x float> undef to <4 x i16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V8I16 = fptoui <8 x float> undef to <8 x i16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V16I16 = fptoui <16 x float> undef to <16 x i16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; SLOW-LABEL: 'fptoui_float_i16'
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = fptoui float undef to i16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I16 = fptoui <2 x float> undef to <2 x i16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I16 = fptoui <4 x float> undef to <4 x i16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I16 = fptoui <8 x float> undef to <8 x i16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16I16 = fptoui <16 x float> undef to <16 x i16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; FAST-SIZE-LABEL: 'fptoui_float_i16'
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = fptoui float undef to i16
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2I16 = fptoui <2 x float> undef to <2 x i16>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V4I16 = fptoui <4 x float> undef to <4 x i16>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V8I16 = fptoui <8 x float> undef to <8 x i16>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 40 for instruction: %V16I16 = fptoui <16 x float> undef to <16 x i16>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; SLOW-SIZE-LABEL: 'fptoui_float_i16'
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = fptoui float undef to i16
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I16 = fptoui <2 x float> undef to <2 x i16>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I16 = fptoui <4 x float> undef to <4 x i16>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I16 = fptoui <8 x float> undef to <8 x i16>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16I16 = fptoui <16 x float> undef to <16 x i16>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %I16 = fptoui float undef to i16
+ %V2I16 = fptoui <2 x float> undef to <2 x i16>
+ %V4I16 = fptoui <4 x float> undef to <4 x i16>
+ %V8I16 = fptoui <8 x float> undef to <8 x i16>
+ %V16I16 = fptoui <16 x float> undef to <16 x i16>
+ ret i32 undef
+}
+
+define i32 @fptoui_float_i8(i32 %arg) {
+; FAST-LABEL: 'fptoui_float_i8'
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = fptoui float undef to i8
+; FAST-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V2I8 = fptoui <2 x float> undef to <2 x i8>
+; FAST-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V4I8 = fptoui <4 x float> undef to <4 x i8>
+; FAST-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V8I8 = fptoui <8 x float> undef to <8 x i8>
+; FAST-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V16I8 = fptoui <16 x float> undef to <16 x i8>
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; SLOW-LABEL: 'fptoui_float_i8'
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = fptoui float undef to i8
+; SLOW-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I8 = fptoui <2 x float> undef to <2 x i8>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I8 = fptoui <4 x float> undef to <4 x i8>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I8 = fptoui <8 x float> undef to <8 x i8>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16I8 = fptoui <16 x float> undef to <16 x i8>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; FAST-SIZE-LABEL: 'fptoui_float_i8'
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = fptoui float undef to i8
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V2I8 = fptoui <2 x float> undef to <2 x i8>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V4I8 = fptoui <4 x float> undef to <4 x i8>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V8I8 = fptoui <8 x float> undef to <8 x i8>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V16I8 = fptoui <16 x float> undef to <16 x i8>
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; SLOW-SIZE-LABEL: 'fptoui_float_i8'
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = fptoui float undef to i8
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2I8 = fptoui <2 x float> undef to <2 x i8>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4I8 = fptoui <4 x float> undef to <4 x i8>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8I8 = fptoui <8 x float> undef to <8 x i8>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16I8 = fptoui <16 x float> undef to <16 x i8>
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %I8 = fptoui float undef to i8
+ %V2I8 = fptoui <2 x float> undef to <2 x i8>
+ %V4I8 = fptoui <4 x float> undef to <4 x i8>
+ %V8I8 = fptoui <8 x float> undef to <8 x i8>
+ %V16I8 = fptoui <16 x float> undef to <16 x i8>
+ ret i32 undef
+}
diff --git a/llvm/test/Analysis/CostModel/AMDGPU/fround.ll b/llvm/test/Analysis/CostModel/AMDGPU/fround.ll
new file mode 100644
index 000000000000..fec0bd737304
--- /dev/null
+++ b/llvm/test/Analysis/CostModel/AMDGPU/fround.ll
@@ -0,0 +1,307 @@
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
+; RUN: opt -cost-model -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx1010 < %s | FileCheck -check-prefixes=ALL,FAST %s
+; RUN: opt -cost-model -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx90a < %s | FileCheck -check-prefixes=ALL,FAST %s
+; RUN: opt -cost-model -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx900 < %s | FileCheck -check-prefixes=ALL,FAST %s
+; RUN: opt -cost-model -analyze -mtriple=amdgcn-unknown-amdhsa < %s | FileCheck -check-prefixes=ALL,SLOW %s
+
+; RUN: opt -cost-model -cost-kind=code-size -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx1010 < %s | FileCheck -check-prefixes=ALL-SIZE,FAST-SIZE %s
+; RUN: opt -cost-model -cost-kind=code-size -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx90a < %s | FileCheck -check-prefixes=ALL-SIZE,FAST-SIZE %s
+; RUN: opt -cost-model -cost-kind=code-size -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx900 < %s | FileCheck -check-prefixes=ALL-SIZE,FAST-SIZE %s
+; RUN: opt -cost-model -cost-kind=code-size -analyze -mtriple=amdgcn-unknown-amdhsa < %s | FileCheck -check-prefixes=ALL-SIZE,SLOW-SIZE %s
+; END.
+
+define i32 @ceil(i32 %arg) {
+; FAST-LABEL: 'ceil'
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.ceil.f32(float undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F32 = call <4 x float> @llvm.ceil.v4f32(<4 x float> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8F32 = call <8 x float> @llvm.ceil.v8f32(<8 x float> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16F32 = call <16 x float> @llvm.ceil.v16f32(<16 x float> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.ceil.f64(double undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = call <2 x double> @llvm.ceil.v2f64(<2 x double> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = call <4 x double> @llvm.ceil.v4f64(<4 x double> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = call <8 x double> @llvm.ceil.v8f64(<8 x double> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; SLOW-LABEL: 'ceil'
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.ceil.f32(float undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F32 = call <4 x float> @llvm.ceil.v4f32(<4 x float> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8F32 = call <8 x float> @llvm.ceil.v8f32(<8 x float> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16F32 = call <16 x float> @llvm.ceil.v16f32(<16 x float> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F64 = call double @llvm.ceil.f64(double undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x double> @llvm.ceil.v2f64(<2 x double> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x double> @llvm.ceil.v4f64(<4 x double> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = call <8 x double> @llvm.ceil.v8f64(<8 x double> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; FAST-SIZE-LABEL: 'ceil'
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.ceil.f32(float undef)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F32 = call <4 x float> @llvm.ceil.v4f32(<4 x float> undef)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8F32 = call <8 x float> @llvm.ceil.v8f32(<8 x float> undef)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16F32 = call <16 x float> @llvm.ceil.v16f32(<16 x float> undef)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.ceil.f64(double undef)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = call <2 x double> @llvm.ceil.v2f64(<2 x double> undef)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = call <4 x double> @llvm.ceil.v4f64(<4 x double> undef)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = call <8 x double> @llvm.ceil.v8f64(<8 x double> undef)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; SLOW-SIZE-LABEL: 'ceil'
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.ceil.f32(float undef)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F32 = call <4 x float> @llvm.ceil.v4f32(<4 x float> undef)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8F32 = call <8 x float> @llvm.ceil.v8f32(<8 x float> undef)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16F32 = call <16 x float> @llvm.ceil.v16f32(<16 x float> undef)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F64 = call double @llvm.ceil.f64(double undef)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x double> @llvm.ceil.v2f64(<2 x double> undef)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x double> @llvm.ceil.v4f64(<4 x double> undef)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = call <8 x double> @llvm.ceil.v8f64(<8 x double> undef)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %F32 = call float @llvm.ceil.f32(float undef)
+ %V4F32 = call <4 x float> @llvm.ceil.v4f32(<4 x float> undef)
+ %V8F32 = call <8 x float> @llvm.ceil.v8f32(<8 x float> undef)
+ %V16F32 = call <16 x float> @llvm.ceil.v16f32(<16 x float> undef)
+
+ %F64 = call double @llvm.ceil.f64(double undef)
+ %V2F64 = call <2 x double> @llvm.ceil.v2f64(<2 x double> undef)
+ %V4F64 = call <4 x double> @llvm.ceil.v4f64(<4 x double> undef)
+ %V8F64 = call <8 x double> @llvm.ceil.v8f64(<8 x double> undef)
+
+ ret i32 undef
+}
+
+define i32 @floor(i32 %arg) {
+; ALL-LABEL: 'floor'
+; ALL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.floor.f32(float undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F32 = call <4 x float> @llvm.floor.v4f32(<4 x float> undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8F32 = call <8 x float> @llvm.floor.v8f32(<8 x float> undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16F32 = call <16 x float> @llvm.floor.v16f32(<16 x float> undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.floor.f64(double undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = call <2 x double> @llvm.floor.v2f64(<2 x double> undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = call <4 x double> @llvm.floor.v4f64(<4 x double> undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = call <8 x double> @llvm.floor.v8f64(<8 x double> undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; ALL-SIZE-LABEL: 'floor'
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.floor.f32(float undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F32 = call <4 x float> @llvm.floor.v4f32(<4 x float> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8F32 = call <8 x float> @llvm.floor.v8f32(<8 x float> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16F32 = call <16 x float> @llvm.floor.v16f32(<16 x float> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.floor.f64(double undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = call <2 x double> @llvm.floor.v2f64(<2 x double> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = call <4 x double> @llvm.floor.v4f64(<4 x double> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = call <8 x double> @llvm.floor.v8f64(<8 x double> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %F32 = call float @llvm.floor.f32(float undef)
+ %V4F32 = call <4 x float> @llvm.floor.v4f32(<4 x float> undef)
+ %V8F32 = call <8 x float> @llvm.floor.v8f32(<8 x float> undef)
+ %V16F32 = call <16 x float> @llvm.floor.v16f32(<16 x float> undef)
+
+ %F64 = call double @llvm.floor.f64(double undef)
+ %V2F64 = call <2 x double> @llvm.floor.v2f64(<2 x double> undef)
+ %V4F64 = call <4 x double> @llvm.floor.v4f64(<4 x double> undef)
+ %V8F64 = call <8 x double> @llvm.floor.v8f64(<8 x double> undef)
+
+ ret i32 undef
+}
+
+define i32 @nearbyint(i32 %arg) {
+; ALL-LABEL: 'nearbyint'
+; ALL-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F32 = call float @llvm.nearbyint.f32(float undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4F32 = call <4 x float> @llvm.nearbyint.v4f32(<4 x float> undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8F32 = call <8 x float> @llvm.nearbyint.v8f32(<8 x float> undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16F32 = call <16 x float> @llvm.nearbyint.v16f32(<16 x float> undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F64 = call double @llvm.nearbyint.f64(double undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x double> @llvm.nearbyint.v2f64(<2 x double> undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x double> @llvm.nearbyint.v4f64(<4 x double> undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = call <8 x double> @llvm.nearbyint.v8f64(<8 x double> undef)
+; ALL-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; ALL-SIZE-LABEL: 'nearbyint'
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F32 = call float @llvm.nearbyint.f32(float undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4F32 = call <4 x float> @llvm.nearbyint.v4f32(<4 x float> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8F32 = call <8 x float> @llvm.nearbyint.v8f32(<8 x float> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V16F32 = call <16 x float> @llvm.nearbyint.v16f32(<16 x float> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F64 = call double @llvm.nearbyint.f64(double undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x double> @llvm.nearbyint.v2f64(<2 x double> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x double> @llvm.nearbyint.v4f64(<4 x double> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = call <8 x double> @llvm.nearbyint.v8f64(<8 x double> undef)
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %F32 = call float @llvm.nearbyint.f32(float undef)
+ %V4F32 = call <4 x float> @llvm.nearbyint.v4f32(<4 x float> undef)
+ %V8F32 = call <8 x float> @llvm.nearbyint.v8f32(<8 x float> undef)
+ %V16F32 = call <16 x float> @llvm.nearbyint.v16f32(<16 x float> undef)
+
+ %F64 = call double @llvm.nearbyint.f64(double undef)
+ %V2F64 = call <2 x double> @llvm.nearbyint.v2f64(<2 x double> undef)
+ %V4F64 = call <4 x double> @llvm.nearbyint.v4f64(<4 x double> undef)
+ %V8F64 = call <8 x double> @llvm.nearbyint.v8f64(<8 x double> undef)
+
+ ret i32 undef
+}
+
+define i32 @rint(i32 %arg) {
+; FAST-LABEL: 'rint'
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.rint.f32(float undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F32 = call <4 x float> @llvm.rint.v4f32(<4 x float> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8F32 = call <8 x float> @llvm.rint.v8f32(<8 x float> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16F32 = call <16 x float> @llvm.rint.v16f32(<16 x float> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.rint.f64(double undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = call <2 x double> @llvm.rint.v2f64(<2 x double> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = call <4 x double> @llvm.rint.v4f64(<4 x double> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = call <8 x double> @llvm.rint.v8f64(<8 x double> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; SLOW-LABEL: 'rint'
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.rint.f32(float undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F32 = call <4 x float> @llvm.rint.v4f32(<4 x float> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8F32 = call <8 x float> @llvm.rint.v8f32(<8 x float> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16F32 = call <16 x float> @llvm.rint.v16f32(<16 x float> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F64 = call double @llvm.rint.f64(double undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x double> @llvm.rint.v2f64(<2 x double> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x double> @llvm.rint.v4f64(<4 x double> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = call <8 x double> @llvm.rint.v8f64(<8 x double> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; FAST-SIZE-LABEL: 'rint'
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.rint.f32(float undef)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F32 = call <4 x float> @llvm.rint.v4f32(<4 x float> undef)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8F32 = call <8 x float> @llvm.rint.v8f32(<8 x float> undef)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16F32 = call <16 x float> @llvm.rint.v16f32(<16 x float> undef)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.rint.f64(double undef)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = call <2 x double> @llvm.rint.v2f64(<2 x double> undef)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = call <4 x double> @llvm.rint.v4f64(<4 x double> undef)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = call <8 x double> @llvm.rint.v8f64(<8 x double> undef)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; SLOW-SIZE-LABEL: 'rint'
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.rint.f32(float undef)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F32 = call <4 x float> @llvm.rint.v4f32(<4 x float> undef)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8F32 = call <8 x float> @llvm.rint.v8f32(<8 x float> undef)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16F32 = call <16 x float> @llvm.rint.v16f32(<16 x float> undef)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F64 = call double @llvm.rint.f64(double undef)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x double> @llvm.rint.v2f64(<2 x double> undef)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x double> @llvm.rint.v4f64(<4 x double> undef)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = call <8 x double> @llvm.rint.v8f64(<8 x double> undef)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %F32 = call float @llvm.rint.f32(float undef)
+ %V4F32 = call <4 x float> @llvm.rint.v4f32(<4 x float> undef)
+ %V8F32 = call <8 x float> @llvm.rint.v8f32(<8 x float> undef)
+ %V16F32 = call <16 x float> @llvm.rint.v16f32(<16 x float> undef)
+
+ %F64 = call double @llvm.rint.f64(double undef)
+ %V2F64 = call <2 x double> @llvm.rint.v2f64(<2 x double> undef)
+ %V4F64 = call <4 x double> @llvm.rint.v4f64(<4 x double> undef)
+ %V8F64 = call <8 x double> @llvm.rint.v8f64(<8 x double> undef)
+
+ ret i32 undef
+}
+
+define i32 @trunc(i32 %arg) {
+; FAST-LABEL: 'trunc'
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.trunc.f32(float undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F32 = call <4 x float> @llvm.trunc.v4f32(<4 x float> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8F32 = call <8 x float> @llvm.trunc.v8f32(<8 x float> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16F32 = call <16 x float> @llvm.trunc.v16f32(<16 x float> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.trunc.f64(double undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = call <2 x double> @llvm.trunc.v2f64(<2 x double> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = call <4 x double> @llvm.trunc.v4f64(<4 x double> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = call <8 x double> @llvm.trunc.v8f64(<8 x double> undef)
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; SLOW-LABEL: 'trunc'
+; SLOW-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.trunc.f32(float undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F32 = call <4 x float> @llvm.trunc.v4f32(<4 x float> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8F32 = call <8 x float> @llvm.trunc.v8f32(<8 x float> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16F32 = call <16 x float> @llvm.trunc.v16f32(<16 x float> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F64 = call double @llvm.trunc.f64(double undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x double> @llvm.trunc.v2f64(<2 x double> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x double> @llvm.trunc.v4f64(<4 x double> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = call <8 x double> @llvm.trunc.v8f64(<8 x double> undef)
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; FAST-SIZE-LABEL: 'trunc'
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.trunc.f32(float undef)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F32 = call <4 x float> @llvm.trunc.v4f32(<4 x float> undef)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8F32 = call <8 x float> @llvm.trunc.v8f32(<8 x float> undef)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16F32 = call <16 x float> @llvm.trunc.v16f32(<16 x float> undef)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.trunc.f64(double undef)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F64 = call <2 x double> @llvm.trunc.v2f64(<2 x double> undef)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F64 = call <4 x double> @llvm.trunc.v4f64(<4 x double> undef)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8F64 = call <8 x double> @llvm.trunc.v8f64(<8 x double> undef)
+; FAST-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+; SLOW-SIZE-LABEL: 'trunc'
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.trunc.f32(float undef)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4F32 = call <4 x float> @llvm.trunc.v4f32(<4 x float> undef)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V8F32 = call <8 x float> @llvm.trunc.v8f32(<8 x float> undef)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16F32 = call <16 x float> @llvm.trunc.v16f32(<16 x float> undef)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F64 = call double @llvm.trunc.f64(double undef)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2F64 = call <2 x double> @llvm.trunc.v2f64(<2 x double> undef)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4F64 = call <4 x double> @llvm.trunc.v4f64(<4 x double> undef)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8F64 = call <8 x double> @llvm.trunc.v8f64(<8 x double> undef)
+; SLOW-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %F32 = call float @llvm.trunc.f32(float undef)
+ %V4F32 = call <4 x float> @llvm.trunc.v4f32(<4 x float> undef)
+ %V8F32 = call <8 x float> @llvm.trunc.v8f32(<8 x float> undef)
+ %V16F32 = call <16 x float> @llvm.trunc.v16f32(<16 x float> undef)
+
+ %F64 = call double @llvm.trunc.f64(double undef)
+ %V2F64 = call <2 x double> @llvm.trunc.v2f64(<2 x double> undef)
+ %V4F64 = call <4 x double> @llvm.trunc.v4f64(<4 x double> undef)
+ %V8F64 = call <8 x double> @llvm.trunc.v8f64(<8 x double> undef)
+
+ ret i32 undef
+}
+
+declare float @llvm.ceil.f32(float)
+declare <4 x float> @llvm.ceil.v4f32(<4 x float>)
+declare <8 x float> @llvm.ceil.v8f32(<8 x float>)
+declare <16 x float> @llvm.ceil.v16f32(<16 x float>)
+
+declare double @llvm.ceil.f64(double)
+declare <2 x double> @llvm.ceil.v2f64(<2 x double>)
+declare <4 x double> @llvm.ceil.v4f64(<4 x double>)
+declare <8 x double> @llvm.ceil.v8f64(<8 x double>)
+
+declare float @llvm.floor.f32(float)
+declare <4 x float> @llvm.floor.v4f32(<4 x float>)
+declare <8 x float> @llvm.floor.v8f32(<8 x float>)
+declare <16 x float> @llvm.floor.v16f32(<16 x float>)
+
+declare double @llvm.floor.f64(double)
+declare <2 x double> @llvm.floor.v2f64(<2 x double>)
+declare <4 x double> @llvm.floor.v4f64(<4 x double>)
+declare <8 x double> @llvm.floor.v8f64(<8 x double>)
+
+declare float @llvm.nearbyint.f32(float)
+declare <4 x float> @llvm.nearbyint.v4f32(<4 x float>)
+declare <8 x float> @llvm.nearbyint.v8f32(<8 x float>)
+declare <16 x float> @llvm.nearbyint.v16f32(<16 x float>)
+
+declare double @llvm.nearbyint.f64(double)
+declare <2 x double> @llvm.nearbyint.v2f64(<2 x double>)
+declare <4 x double> @llvm.nearbyint.v4f64(<4 x double>)
+declare <8 x double> @llvm.nearbyint.v8f64(<8 x double>)
+
+declare float @llvm.rint.f32(float)
+declare <4 x float> @llvm.rint.v4f32(<4 x float>)
+declare <8 x float> @llvm.rint.v8f32(<8 x float>)
+declare <16 x float> @llvm.rint.v16f32(<16 x float>)
+
+declare double @llvm.rint.f64(double)
+declare <2 x double> @llvm.rint.v2f64(<2 x double>)
+declare <4 x double> @llvm.rint.v4f64(<4 x double>)
+declare <8 x double> @llvm.rint.v8f64(<8 x double>)
+
+declare float @llvm.trunc.f32(float)
+declare <4 x float> @llvm.trunc.v4f32(<4 x float>)
+declare <8 x float> @llvm.trunc.v8f32(<8 x float>)
+declare <16 x float> @llvm.trunc.v16f32(<16 x float>)
+
+declare double @llvm.trunc.f64(double)
+declare <2 x double> @llvm.trunc.v2f64(<2 x double>)
+declare <4 x double> @llvm.trunc.v4f64(<4 x double>)
+declare <8 x double> @llvm.trunc.v8f64(<8 x double>)
diff --git a/llvm/test/Analysis/CostModel/AMDGPU/gep.ll b/llvm/test/Analysis/CostModel/AMDGPU/gep.ll
new file mode 100644
index 000000000000..da60908299be
--- /dev/null
+++ b/llvm/test/Analysis/CostModel/AMDGPU/gep.ll
@@ -0,0 +1,73 @@
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
+; RUN: opt -cost-model -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx1010 < %s | FileCheck -check-prefixes=ALL %s
+; RUN: opt -cost-model -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx90a < %s | FileCheck -check-prefixes=ALL %s
+; RUN: opt -cost-model -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx900 < %s | FileCheck -check-prefixes=ALL %s
+; RUN: opt -cost-model -analyze -mtriple=amdgcn-unknown-amdhsa < %s | FileCheck -check-prefixes=ALL %s
+
+; RUN: opt -cost-model -cost-kind=code-size -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx1010 < %s | FileCheck -check-prefixes=ALL-SIZE %s
+; RUN: opt -cost-model -cost-kind=code-size -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx90a < %s | FileCheck -check-prefixes=ALL-SIZE %s
+; RUN: opt -cost-model -cost-kind=code-size -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx900 < %s | FileCheck -check-prefixes=ALL-SIZE %s
+; RUN: opt -cost-model -cost-kind=code-size -analyze -mtriple=amdgcn-unknown-amdhsa < %s | FileCheck -check-prefixes=ALL-SIZE %s
+; END.
+
+define void @test_geps() {
+; ALL-LABEL: 'test_geps'
+; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %a0 = getelementptr inbounds i8, i8* undef, i32 0
+; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %a1 = getelementptr inbounds i16, i16* undef, i32 0
+; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %a2 = getelementptr inbounds i32, i32* undef, i32 0
+; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %a3 = getelementptr inbounds i64, i64* undef, i32 0
+; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %a4 = getelementptr inbounds float, float* undef, i32 0
+; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %a5 = getelementptr inbounds double, double* undef, i32 0
+; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %a7 = getelementptr inbounds <4 x i8>, <4 x i8>* undef, i32 0
+; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %a8 = getelementptr inbounds <4 x i16>, <4 x i16>* undef, i32 0
+; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %a9 = getelementptr inbounds <4 x i32>, <4 x i32>* undef, i32 0
+; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %a10 = getelementptr inbounds <4 x i64>, <4 x i64>* undef, i32 0
+; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %a11 = getelementptr inbounds <4 x float>, <4 x float>* undef, i32 0
+; ALL-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %a12 = getelementptr inbounds <4 x double>, <4 x double>* undef, i32 0
+; ALL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %giant_gep0 = getelementptr inbounds i8, i8* undef, i64 9223372036854775807
+; ALL-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %giant_gep1 = getelementptr inbounds i8, i8* undef, i128 295147905179352825855
+; ALL-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret void
+;
+; ALL-SIZE-LABEL: 'test_geps'
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %a0 = getelementptr inbounds i8, i8* undef, i32 0
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %a1 = getelementptr inbounds i16, i16* undef, i32 0
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %a2 = getelementptr inbounds i32, i32* undef, i32 0
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %a3 = getelementptr inbounds i64, i64* undef, i32 0
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %a4 = getelementptr inbounds float, float* undef, i32 0
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %a5 = getelementptr inbounds double, double* undef, i32 0
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %a7 = getelementptr inbounds <4 x i8>, <4 x i8>* undef, i32 0
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %a8 = getelementptr inbounds <4 x i16>, <4 x i16>* undef, i32 0
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %a9 = getelementptr inbounds <4 x i32>, <4 x i32>* undef, i32 0
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %a10 = getelementptr inbounds <4 x i64>, <4 x i64>* undef, i32 0
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %a11 = getelementptr inbounds <4 x float>, <4 x float>* undef, i32 0
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %a12 = getelementptr inbounds <4 x double>, <4 x double>* undef, i32 0
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %giant_gep0 = getelementptr inbounds i8, i8* undef, i64 9223372036854775807
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %giant_gep1 = getelementptr inbounds i8, i8* undef, i128 295147905179352825855
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret void
+;
+ %a0 = getelementptr inbounds i8, i8* undef, i32 0
+ %a1 = getelementptr inbounds i16, i16* undef, i32 0
+ %a2 = getelementptr inbounds i32, i32* undef, i32 0
+ %a3 = getelementptr inbounds i64, i64* undef, i32 0
+
+ %a4 = getelementptr inbounds float, float* undef, i32 0
+ %a5 = getelementptr inbounds double, double* undef, i32 0
+
+ %a7 = getelementptr inbounds <4 x i8>, <4 x i8>* undef, i32 0
+ %a8 = getelementptr inbounds <4 x i16>, <4 x i16>* undef, i32 0
+ %a9 = getelementptr inbounds <4 x i32>, <4 x i32>* undef, i32 0
+ %a10 = getelementptr inbounds <4 x i64>, <4 x i64>* undef, i32 0
+ %a11 = getelementptr inbounds <4 x float>, <4 x float>* undef, i32 0
+ %a12 = getelementptr inbounds <4 x double>, <4 x double>* undef, i32 0
+
+ ; Check that we handle outlandishly large GEPs properly. This is unlikely to
+ ; be a valid pointer, but LLVM still generates GEPs like this sometimes in
+ ; dead code.
+ ; This GEP has index INT64_MAX, which is cost 1.
+ %giant_gep0 = getelementptr inbounds i8, i8* undef, i64 9223372036854775807
+
+ ; This GEP index wraps around to -1, which is cost 0.
+ %giant_gep1 = getelementptr inbounds i8, i8* undef, i128 295147905179352825855
+
+ ret void
+}
diff --git a/llvm/test/Analysis/CostModel/AMDGPU/rem.ll b/llvm/test/Analysis/CostModel/AMDGPU/rem.ll
new file mode 100644
index 000000000000..a2d38d2314bd
--- /dev/null
+++ b/llvm/test/Analysis/CostModel/AMDGPU/rem.ll
@@ -0,0 +1,1145 @@
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
+; RUN: opt -cost-model -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx1010 < %s | FileCheck -check-prefixes=FAST %s
+; RUN: opt -cost-model -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx90a < %s | FileCheck -check-prefixes=FAST %s
+; RUN: opt -cost-model -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx900 < %s | FileCheck -check-prefixes=FAST %s
+; RUN: opt -cost-model -analyze -mtriple=amdgcn-unknown-amdhsa < %s | FileCheck -check-prefixes=SLOW %s
+
+; RUN: opt -cost-model -cost-kind=code-size -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx1010 < %s | FileCheck -check-prefixes=ALL-SIZE %s
+; RUN: opt -cost-model -cost-kind=code-size -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx90a < %s | FileCheck -check-prefixes=ALL-SIZE %s
+; RUN: opt -cost-model -cost-kind=code-size -analyze -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx900 < %s | FileCheck -check-prefixes=ALL-SIZE %s
+; RUN: opt -cost-model -cost-kind=code-size -analyze -mtriple=amdgcn-unknown-amdhsa < %s | FileCheck -check-prefixes=ALL-SIZE %s
+; END.
+
+define i32 @srem() {
+; FAST-LABEL: 'srem'
+; FAST-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %I64 = srem i64 undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V2i64 = srem <2 x i64> undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 92 for instruction: %V4i64 = srem <4 x i64> undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 184 for instruction: %V8i64 = srem <8 x i64> undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I32 = srem i32 undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V4i32 = srem <4 x i32> undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V8i32 = srem <8 x i32> undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V16i32 = srem <16 x i32> undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = srem i16 undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V8i16 = srem <8 x i16> undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %V16i16 = srem <16 x i16> undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %V32i16 = srem <32 x i16> undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = srem i8 undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i8 = srem <16 x i8> undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V32i8 = srem <32 x i8> undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V64i8 = srem <64 x i8> undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; SLOW-LABEL: 'srem'
+; SLOW-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %I64 = srem i64 undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V2i64 = srem <2 x i64> undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 92 for instruction: %V4i64 = srem <4 x i64> undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 184 for instruction: %V8i64 = srem <8 x i64> undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I32 = srem i32 undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V4i32 = srem <4 x i32> undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V8i32 = srem <8 x i32> undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V16i32 = srem <16 x i32> undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I16 = srem i16 undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V8i16 = srem <8 x i16> undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V16i16 = srem <16 x i16> undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 266 for instruction: %V32i16 = srem <32 x i16> undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I8 = srem i8 undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V16i8 = srem <16 x i8> undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 256 for instruction: %V32i8 = srem <32 x i8> undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 522 for instruction: %V64i8 = srem <64 x i8> undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; ALL-SIZE-LABEL: 'srem'
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = srem i64 undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2i64 = srem <2 x i64> undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = srem <4 x i64> undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i64 = srem <8 x i64> undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I32 = srem i32 undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = srem <4 x i32> undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i32 = srem <8 x i32> undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i32 = srem <16 x i32> undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = srem i16 undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i16 = srem <8 x i16> undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i16 = srem <16 x i16> undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i16 = srem <32 x i16> undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = srem i8 undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i8 = srem <16 x i8> undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i8 = srem <32 x i8> undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V64i8 = srem <64 x i8> undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %I64 = srem i64 undef, undef
+ %V2i64 = srem <2 x i64> undef, undef
+ %V4i64 = srem <4 x i64> undef, undef
+ %V8i64 = srem <8 x i64> undef, undef
+
+ %I32 = srem i32 undef, undef
+ %V4i32 = srem <4 x i32> undef, undef
+ %V8i32 = srem <8 x i32> undef, undef
+ %V16i32 = srem <16 x i32> undef, undef
+
+ %I16 = srem i16 undef, undef
+ %V8i16 = srem <8 x i16> undef, undef
+ %V16i16 = srem <16 x i16> undef, undef
+ %V32i16 = srem <32 x i16> undef, undef
+
+ %I8 = srem i8 undef, undef
+ %V16i8 = srem <16 x i8> undef, undef
+ %V32i8 = srem <32 x i8> undef, undef
+ %V64i8 = srem <64 x i8> undef, undef
+
+ ret i32 undef
+}
+
+define i32 @urem() {
+; FAST-LABEL: 'urem'
+; FAST-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %I64 = urem i64 undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V2i64 = urem <2 x i64> undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 92 for instruction: %V4i64 = urem <4 x i64> undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 184 for instruction: %V8i64 = urem <8 x i64> undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I32 = urem i32 undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V4i32 = urem <4 x i32> undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V8i32 = urem <8 x i32> undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V16i32 = urem <16 x i32> undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = urem i16 undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V8i16 = urem <8 x i16> undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %V16i16 = urem <16 x i16> undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %V32i16 = urem <32 x i16> undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = urem i8 undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i8 = urem <16 x i8> undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V32i8 = urem <32 x i8> undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V64i8 = urem <64 x i8> undef, undef
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; SLOW-LABEL: 'urem'
+; SLOW-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %I64 = urem i64 undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V2i64 = urem <2 x i64> undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 92 for instruction: %V4i64 = urem <4 x i64> undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 184 for instruction: %V8i64 = urem <8 x i64> undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I32 = urem i32 undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V4i32 = urem <4 x i32> undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V8i32 = urem <8 x i32> undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V16i32 = urem <16 x i32> undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I16 = urem i16 undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V8i16 = urem <8 x i16> undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V16i16 = urem <16 x i16> undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 266 for instruction: %V32i16 = urem <32 x i16> undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I8 = urem i8 undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V16i8 = urem <16 x i8> undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 256 for instruction: %V32i8 = urem <32 x i8> undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 522 for instruction: %V64i8 = urem <64 x i8> undef, undef
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; ALL-SIZE-LABEL: 'urem'
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = urem i64 undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2i64 = urem <2 x i64> undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = urem <4 x i64> undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i64 = urem <8 x i64> undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I32 = urem i32 undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = urem <4 x i32> undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i32 = urem <8 x i32> undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i32 = urem <16 x i32> undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = urem i16 undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i16 = urem <8 x i16> undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i16 = urem <16 x i16> undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i16 = urem <32 x i16> undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = urem i8 undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i8 = urem <16 x i8> undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i8 = urem <32 x i8> undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V64i8 = urem <64 x i8> undef, undef
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %I64 = urem i64 undef, undef
+ %V2i64 = urem <2 x i64> undef, undef
+ %V4i64 = urem <4 x i64> undef, undef
+ %V8i64 = urem <8 x i64> undef, undef
+
+ %I32 = urem i32 undef, undef
+ %V4i32 = urem <4 x i32> undef, undef
+ %V8i32 = urem <8 x i32> undef, undef
+ %V16i32 = urem <16 x i32> undef, undef
+
+ %I16 = urem i16 undef, undef
+ %V8i16 = urem <8 x i16> undef, undef
+ %V16i16 = urem <16 x i16> undef, undef
+ %V32i16 = urem <32 x i16> undef, undef
+
+ %I8 = urem i8 undef, undef
+ %V16i8 = urem <16 x i8> undef, undef
+ %V32i8 = urem <32 x i8> undef, undef
+ %V64i8 = urem <64 x i8> undef, undef
+
+ ret i32 undef
+}
+
+define i32 @srem_const() {
+; FAST-LABEL: 'srem_const'
+; FAST-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %I64 = srem i64 undef, 7
+; FAST-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V2i64 = srem <2 x i64> undef, <i64 6, i64 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 92 for instruction: %V4i64 = srem <4 x i64> undef, <i64 4, i64 5, i64 6, i64 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 184 for instruction: %V8i64 = srem <8 x i64> undef, <i64 4, i64 5, i64 6, i64 7, i64 8, i64 9, i64 10, i64 11>
+; FAST-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I32 = srem i32 undef, 7
+; FAST-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V4i32 = srem <4 x i32> undef, <i32 4, i32 5, i32 6, i32 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V8i32 = srem <8 x i32> undef, <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11>
+; FAST-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V16i32 = srem <16 x i32> undef, <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = srem i16 undef, 7
+; FAST-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V8i16 = srem <8 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11>
+; FAST-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %V16i16 = srem <16 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19>
+; FAST-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %V32i16 = srem <32 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19, i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = srem i8 undef, 7
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i8 = srem <16 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+; FAST-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V32i8 = srem <32 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+; FAST-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V64i8 = srem <64 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; SLOW-LABEL: 'srem_const'
+; SLOW-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %I64 = srem i64 undef, 7
+; SLOW-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V2i64 = srem <2 x i64> undef, <i64 6, i64 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 92 for instruction: %V4i64 = srem <4 x i64> undef, <i64 4, i64 5, i64 6, i64 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 184 for instruction: %V8i64 = srem <8 x i64> undef, <i64 4, i64 5, i64 6, i64 7, i64 8, i64 9, i64 10, i64 11>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I32 = srem i32 undef, 7
+; SLOW-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V4i32 = srem <4 x i32> undef, <i32 4, i32 5, i32 6, i32 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V8i32 = srem <8 x i32> undef, <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V16i32 = srem <16 x i32> undef, <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I16 = srem i16 undef, 7
+; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V8i16 = srem <8 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V16i16 = srem <16 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 266 for instruction: %V32i16 = srem <32 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19, i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I8 = srem i8 undef, 7
+; SLOW-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V16i8 = srem <16 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 256 for instruction: %V32i8 = srem <32 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 522 for instruction: %V64i8 = srem <64 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; ALL-SIZE-LABEL: 'srem_const'
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = srem i64 undef, 7
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2i64 = srem <2 x i64> undef, <i64 6, i64 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = srem <4 x i64> undef, <i64 4, i64 5, i64 6, i64 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i64 = srem <8 x i64> undef, <i64 4, i64 5, i64 6, i64 7, i64 8, i64 9, i64 10, i64 11>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I32 = srem i32 undef, 7
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = srem <4 x i32> undef, <i32 4, i32 5, i32 6, i32 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i32 = srem <8 x i32> undef, <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i32 = srem <16 x i32> undef, <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = srem i16 undef, 7
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i16 = srem <8 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i16 = srem <16 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i16 = srem <32 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19, i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = srem i8 undef, 7
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i8 = srem <16 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i8 = srem <32 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V64i8 = srem <64 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %I64 = srem i64 undef, 7
+ %V2i64 = srem <2 x i64> undef, <i64 6, i64 7>
+ %V4i64 = srem <4 x i64> undef, <i64 4, i64 5, i64 6, i64 7>
+ %V8i64 = srem <8 x i64> undef, <i64 4, i64 5, i64 6, i64 7, i64 8, i64 9, i64 10, i64 11>
+
+ %I32 = srem i32 undef, 7
+ %V4i32 = srem <4 x i32> undef, <i32 4, i32 5, i32 6, i32 7>
+ %V8i32 = srem <8 x i32> undef, <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11>
+ %V16i32 = srem <16 x i32> undef, <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19>
+
+ %I16 = srem i16 undef, 7
+ %V8i16 = srem <8 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11>
+ %V16i16 = srem <16 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19>
+ %V32i16 = srem <32 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19, i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19>
+
+ %I8 = srem i8 undef, 7
+ %V16i8 = srem <16 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+ %V32i8 = srem <32 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+ %V64i8 = srem <64 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+
+ ret i32 undef
+}
+
+define i32 @urem_const() {
+; FAST-LABEL: 'urem_const'
+; FAST-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %I64 = urem i64 undef, 7
+; FAST-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V2i64 = urem <2 x i64> undef, <i64 6, i64 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 92 for instruction: %V4i64 = urem <4 x i64> undef, <i64 4, i64 5, i64 6, i64 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 184 for instruction: %V8i64 = urem <8 x i64> undef, <i64 4, i64 5, i64 6, i64 7, i64 8, i64 9, i64 10, i64 11>
+; FAST-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I32 = urem i32 undef, 7
+; FAST-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V4i32 = urem <4 x i32> undef, <i32 4, i32 5, i32 6, i32 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V8i32 = urem <8 x i32> undef, <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11>
+; FAST-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V16i32 = urem <16 x i32> undef, <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = urem i16 undef, 7
+; FAST-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V8i16 = urem <8 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11>
+; FAST-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %V16i16 = urem <16 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19>
+; FAST-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %V32i16 = urem <32 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19, i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = urem i8 undef, 7
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i8 = urem <16 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+; FAST-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V32i8 = urem <32 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+; FAST-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V64i8 = urem <64 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; SLOW-LABEL: 'urem_const'
+; SLOW-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %I64 = urem i64 undef, 7
+; SLOW-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V2i64 = urem <2 x i64> undef, <i64 6, i64 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 92 for instruction: %V4i64 = urem <4 x i64> undef, <i64 4, i64 5, i64 6, i64 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 184 for instruction: %V8i64 = urem <8 x i64> undef, <i64 4, i64 5, i64 6, i64 7, i64 8, i64 9, i64 10, i64 11>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I32 = urem i32 undef, 7
+; SLOW-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V4i32 = urem <4 x i32> undef, <i32 4, i32 5, i32 6, i32 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V8i32 = urem <8 x i32> undef, <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V16i32 = urem <16 x i32> undef, <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I16 = urem i16 undef, 7
+; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V8i16 = urem <8 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V16i16 = urem <16 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 266 for instruction: %V32i16 = urem <32 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19, i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I8 = urem i8 undef, 7
+; SLOW-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V16i8 = urem <16 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 256 for instruction: %V32i8 = urem <32 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 522 for instruction: %V64i8 = urem <64 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; ALL-SIZE-LABEL: 'urem_const'
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = urem i64 undef, 7
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2i64 = urem <2 x i64> undef, <i64 6, i64 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = urem <4 x i64> undef, <i64 4, i64 5, i64 6, i64 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i64 = urem <8 x i64> undef, <i64 4, i64 5, i64 6, i64 7, i64 8, i64 9, i64 10, i64 11>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I32 = urem i32 undef, 7
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = urem <4 x i32> undef, <i32 4, i32 5, i32 6, i32 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i32 = urem <8 x i32> undef, <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i32 = urem <16 x i32> undef, <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = urem i16 undef, 7
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i16 = urem <8 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i16 = urem <16 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i16 = urem <32 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19, i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = urem i8 undef, 7
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i8 = urem <16 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i8 = urem <32 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V64i8 = urem <64 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %I64 = urem i64 undef, 7
+ %V2i64 = urem <2 x i64> undef, <i64 6, i64 7>
+ %V4i64 = urem <4 x i64> undef, <i64 4, i64 5, i64 6, i64 7>
+ %V8i64 = urem <8 x i64> undef, <i64 4, i64 5, i64 6, i64 7, i64 8, i64 9, i64 10, i64 11>
+
+ %I32 = urem i32 undef, 7
+ %V4i32 = urem <4 x i32> undef, <i32 4, i32 5, i32 6, i32 7>
+ %V8i32 = urem <8 x i32> undef, <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11>
+ %V16i32 = urem <16 x i32> undef, <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19>
+
+ %I16 = urem i16 undef, 7
+ %V8i16 = urem <8 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11>
+ %V16i16 = urem <16 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19>
+ %V32i16 = urem <32 x i16> undef, <i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19, i16 4, i16 5, i16 6, i16 7, i16 8, i16 9, i16 10, i16 11, i16 12, i16 13, i16 14, i16 15, i16 16, i16 17, i16 18, i16 19>
+
+ %I8 = urem i8 undef, 7
+ %V16i8 = urem <16 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+ %V32i8 = urem <32 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+ %V64i8 = urem <64 x i8> undef, <i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16, i8 17, i8 18, i8 19>
+
+ ret i32 undef
+}
+
+define i32 @srem_uniformconst() {
+; FAST-LABEL: 'srem_uniformconst'
+; FAST-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %I64 = srem i64 undef, 7
+; FAST-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V2i64 = srem <2 x i64> undef, <i64 7, i64 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 92 for instruction: %V4i64 = srem <4 x i64> undef, <i64 7, i64 7, i64 7, i64 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 184 for instruction: %V8i64 = srem <8 x i64> undef, <i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I32 = srem i32 undef, 7
+; FAST-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V4i32 = srem <4 x i32> undef, <i32 7, i32 7, i32 7, i32 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V8i32 = srem <8 x i32> undef, <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V16i32 = srem <16 x i32> undef, <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = srem i16 undef, 7
+; FAST-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V8i16 = srem <8 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %V16i16 = srem <16 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %V32i16 = srem <32 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = srem i8 undef, 7
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i8 = srem <16 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V32i8 = srem <32 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V64i8 = srem <64 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; SLOW-LABEL: 'srem_uniformconst'
+; SLOW-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %I64 = srem i64 undef, 7
+; SLOW-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V2i64 = srem <2 x i64> undef, <i64 7, i64 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 92 for instruction: %V4i64 = srem <4 x i64> undef, <i64 7, i64 7, i64 7, i64 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 184 for instruction: %V8i64 = srem <8 x i64> undef, <i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I32 = srem i32 undef, 7
+; SLOW-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V4i32 = srem <4 x i32> undef, <i32 7, i32 7, i32 7, i32 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V8i32 = srem <8 x i32> undef, <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V16i32 = srem <16 x i32> undef, <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I16 = srem i16 undef, 7
+; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V8i16 = srem <8 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V16i16 = srem <16 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 266 for instruction: %V32i16 = srem <32 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I8 = srem i8 undef, 7
+; SLOW-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V16i8 = srem <16 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 256 for instruction: %V32i8 = srem <32 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 522 for instruction: %V64i8 = srem <64 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; ALL-SIZE-LABEL: 'srem_uniformconst'
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = srem i64 undef, 7
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2i64 = srem <2 x i64> undef, <i64 7, i64 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = srem <4 x i64> undef, <i64 7, i64 7, i64 7, i64 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i64 = srem <8 x i64> undef, <i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I32 = srem i32 undef, 7
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = srem <4 x i32> undef, <i32 7, i32 7, i32 7, i32 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i32 = srem <8 x i32> undef, <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i32 = srem <16 x i32> undef, <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = srem i16 undef, 7
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i16 = srem <8 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i16 = srem <16 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i16 = srem <32 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = srem i8 undef, 7
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i8 = srem <16 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i8 = srem <32 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V64i8 = srem <64 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %I64 = srem i64 undef, 7
+ %V2i64 = srem <2 x i64> undef, <i64 7, i64 7>
+ %V4i64 = srem <4 x i64> undef, <i64 7, i64 7, i64 7, i64 7>
+ %V8i64 = srem <8 x i64> undef, <i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7>
+
+ %I32 = srem i32 undef, 7
+ %V4i32 = srem <4 x i32> undef, <i32 7, i32 7, i32 7, i32 7>
+ %V8i32 = srem <8 x i32> undef, <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
+ %V16i32 = srem <16 x i32> undef, <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
+
+ %I16 = srem i16 undef, 7
+ %V8i16 = srem <8 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+ %V16i16 = srem <16 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+ %V32i16 = srem <32 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+
+ %I8 = srem i8 undef, 7
+ %V16i8 = srem <16 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+ %V32i8 = srem <32 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+ %V64i8 = srem <64 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+
+ ret i32 undef
+}
+
+define i32 @urem_uniformconst() {
+; FAST-LABEL: 'urem_uniformconst'
+; FAST-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %I64 = urem i64 undef, 7
+; FAST-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V2i64 = urem <2 x i64> undef, <i64 7, i64 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 92 for instruction: %V4i64 = urem <4 x i64> undef, <i64 7, i64 7, i64 7, i64 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 184 for instruction: %V8i64 = urem <8 x i64> undef, <i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I32 = urem i32 undef, 7
+; FAST-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V4i32 = urem <4 x i32> undef, <i32 7, i32 7, i32 7, i32 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V8i32 = urem <8 x i32> undef, <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V16i32 = urem <16 x i32> undef, <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = urem i16 undef, 7
+; FAST-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V8i16 = urem <8 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %V16i16 = urem <16 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %V32i16 = urem <32 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = urem i8 undef, 7
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i8 = urem <16 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V32i8 = urem <32 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V64i8 = urem <64 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; SLOW-LABEL: 'urem_uniformconst'
+; SLOW-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %I64 = urem i64 undef, 7
+; SLOW-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V2i64 = urem <2 x i64> undef, <i64 7, i64 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 92 for instruction: %V4i64 = urem <4 x i64> undef, <i64 7, i64 7, i64 7, i64 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 184 for instruction: %V8i64 = urem <8 x i64> undef, <i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I32 = urem i32 undef, 7
+; SLOW-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V4i32 = urem <4 x i32> undef, <i32 7, i32 7, i32 7, i32 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V8i32 = urem <8 x i32> undef, <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V16i32 = urem <16 x i32> undef, <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I16 = urem i16 undef, 7
+; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V8i16 = urem <8 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V16i16 = urem <16 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 266 for instruction: %V32i16 = urem <32 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I8 = urem i8 undef, 7
+; SLOW-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V16i8 = urem <16 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 256 for instruction: %V32i8 = urem <32 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 522 for instruction: %V64i8 = urem <64 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; ALL-SIZE-LABEL: 'urem_uniformconst'
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = urem i64 undef, 7
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2i64 = urem <2 x i64> undef, <i64 7, i64 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = urem <4 x i64> undef, <i64 7, i64 7, i64 7, i64 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i64 = urem <8 x i64> undef, <i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I32 = urem i32 undef, 7
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = urem <4 x i32> undef, <i32 7, i32 7, i32 7, i32 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i32 = urem <8 x i32> undef, <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i32 = urem <16 x i32> undef, <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = urem i16 undef, 7
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i16 = urem <8 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i16 = urem <16 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i16 = urem <32 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = urem i8 undef, 7
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i8 = urem <16 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i8 = urem <32 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V64i8 = urem <64 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %I64 = urem i64 undef, 7
+ %V2i64 = urem <2 x i64> undef, <i64 7, i64 7>
+ %V4i64 = urem <4 x i64> undef, <i64 7, i64 7, i64 7, i64 7>
+ %V8i64 = urem <8 x i64> undef, <i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7, i64 7>
+
+ %I32 = urem i32 undef, 7
+ %V4i32 = urem <4 x i32> undef, <i32 7, i32 7, i32 7, i32 7>
+ %V8i32 = urem <8 x i32> undef, <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
+ %V16i32 = urem <16 x i32> undef, <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
+
+ %I16 = urem i16 undef, 7
+ %V8i16 = urem <8 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+ %V16i16 = urem <16 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+ %V32i16 = urem <32 x i16> undef, <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>
+
+ %I8 = urem i8 undef, 7
+ %V16i8 = urem <16 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+ %V32i8 = urem <32 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+ %V64i8 = urem <64 x i8> undef, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
+
+ ret i32 undef
+}
+
+define i32 @srem_constpow2() {
+; FAST-LABEL: 'srem_constpow2'
+; FAST-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %I64 = srem i64 undef, 16
+; FAST-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V2i64 = srem <2 x i64> undef, <i64 8, i64 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 92 for instruction: %V4i64 = srem <4 x i64> undef, <i64 2, i64 4, i64 8, i64 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 184 for instruction: %V8i64 = srem <8 x i64> undef, <i64 2, i64 4, i64 8, i64 16, i64 32, i64 64, i64 128, i64 256>
+; FAST-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I32 = srem i32 undef, 16
+; FAST-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V4i32 = srem <4 x i32> undef, <i32 2, i32 4, i32 8, i32 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V8i32 = srem <8 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256>
+; FAST-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V16i32 = srem <16 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256, i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = srem i16 undef, 16
+; FAST-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V8i16 = srem <8 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+; FAST-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %V16i16 = srem <16 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+; FAST-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %V32i16 = srem <32 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = srem i8 undef, 16
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i8 = srem <16 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V32i8 = srem <32 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V64i8 = srem <64 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; SLOW-LABEL: 'srem_constpow2'
+; SLOW-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %I64 = srem i64 undef, 16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V2i64 = srem <2 x i64> undef, <i64 8, i64 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 92 for instruction: %V4i64 = srem <4 x i64> undef, <i64 2, i64 4, i64 8, i64 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 184 for instruction: %V8i64 = srem <8 x i64> undef, <i64 2, i64 4, i64 8, i64 16, i64 32, i64 64, i64 128, i64 256>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I32 = srem i32 undef, 16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V4i32 = srem <4 x i32> undef, <i32 2, i32 4, i32 8, i32 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V8i32 = srem <8 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V16i32 = srem <16 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256, i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I16 = srem i16 undef, 16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V8i16 = srem <8 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V16i16 = srem <16 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 266 for instruction: %V32i16 = srem <32 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I8 = srem i8 undef, 16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V16i8 = srem <16 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 256 for instruction: %V32i8 = srem <32 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 522 for instruction: %V64i8 = srem <64 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; ALL-SIZE-LABEL: 'srem_constpow2'
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = srem i64 undef, 16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2i64 = srem <2 x i64> undef, <i64 8, i64 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = srem <4 x i64> undef, <i64 2, i64 4, i64 8, i64 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i64 = srem <8 x i64> undef, <i64 2, i64 4, i64 8, i64 16, i64 32, i64 64, i64 128, i64 256>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I32 = srem i32 undef, 16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = srem <4 x i32> undef, <i32 2, i32 4, i32 8, i32 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i32 = srem <8 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i32 = srem <16 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256, i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = srem i16 undef, 16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i16 = srem <8 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i16 = srem <16 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i16 = srem <32 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = srem i8 undef, 16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i8 = srem <16 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i8 = srem <32 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V64i8 = srem <64 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %I64 = srem i64 undef, 16
+ %V2i64 = srem <2 x i64> undef, <i64 8, i64 16>
+ %V4i64 = srem <4 x i64> undef, <i64 2, i64 4, i64 8, i64 16>
+ %V8i64 = srem <8 x i64> undef, <i64 2, i64 4, i64 8, i64 16, i64 32, i64 64, i64 128, i64 256>
+
+ %I32 = srem i32 undef, 16
+ %V4i32 = srem <4 x i32> undef, <i32 2, i32 4, i32 8, i32 16>
+ %V8i32 = srem <8 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256>
+ %V16i32 = srem <16 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256, i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256>
+
+ %I16 = srem i16 undef, 16
+ %V8i16 = srem <8 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+ %V16i16 = srem <16 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+ %V32i16 = srem <32 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+
+ %I8 = srem i8 undef, 16
+ %V16i8 = srem <16 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+ %V32i8 = srem <32 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+ %V64i8 = srem <64 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+
+ ret i32 undef
+}
+
+define i32 @urem_constpow2() {
+; FAST-LABEL: 'urem_constpow2'
+; FAST-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %I64 = urem i64 undef, 16
+; FAST-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V2i64 = urem <2 x i64> undef, <i64 8, i64 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 92 for instruction: %V4i64 = urem <4 x i64> undef, <i64 2, i64 4, i64 8, i64 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 184 for instruction: %V8i64 = urem <8 x i64> undef, <i64 2, i64 4, i64 8, i64 16, i64 32, i64 64, i64 128, i64 256>
+; FAST-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I32 = urem i32 undef, 16
+; FAST-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V4i32 = urem <4 x i32> undef, <i32 2, i32 4, i32 8, i32 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V8i32 = urem <8 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256>
+; FAST-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V16i32 = urem <16 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256, i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = urem i16 undef, 16
+; FAST-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V8i16 = urem <8 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+; FAST-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %V16i16 = urem <16 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+; FAST-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %V32i16 = urem <32 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = urem i8 undef, 16
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i8 = urem <16 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V32i8 = urem <32 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V64i8 = urem <64 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; SLOW-LABEL: 'urem_constpow2'
+; SLOW-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %I64 = urem i64 undef, 16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V2i64 = urem <2 x i64> undef, <i64 8, i64 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 92 for instruction: %V4i64 = urem <4 x i64> undef, <i64 2, i64 4, i64 8, i64 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 184 for instruction: %V8i64 = urem <8 x i64> undef, <i64 2, i64 4, i64 8, i64 16, i64 32, i64 64, i64 128, i64 256>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I32 = urem i32 undef, 16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V4i32 = urem <4 x i32> undef, <i32 2, i32 4, i32 8, i32 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V8i32 = urem <8 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V16i32 = urem <16 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256, i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I16 = urem i16 undef, 16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V8i16 = urem <8 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V16i16 = urem <16 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 266 for instruction: %V32i16 = urem <32 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I8 = urem i8 undef, 16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V16i8 = urem <16 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 256 for instruction: %V32i8 = urem <32 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 522 for instruction: %V64i8 = urem <64 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; ALL-SIZE-LABEL: 'urem_constpow2'
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = urem i64 undef, 16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2i64 = urem <2 x i64> undef, <i64 8, i64 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = urem <4 x i64> undef, <i64 2, i64 4, i64 8, i64 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i64 = urem <8 x i64> undef, <i64 2, i64 4, i64 8, i64 16, i64 32, i64 64, i64 128, i64 256>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I32 = urem i32 undef, 16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = urem <4 x i32> undef, <i32 2, i32 4, i32 8, i32 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i32 = urem <8 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i32 = urem <16 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256, i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = urem i16 undef, 16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i16 = urem <8 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i16 = urem <16 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i16 = urem <32 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = urem i8 undef, 16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i8 = urem <16 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i8 = urem <32 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V64i8 = urem <64 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %I64 = urem i64 undef, 16
+ %V2i64 = urem <2 x i64> undef, <i64 8, i64 16>
+ %V4i64 = urem <4 x i64> undef, <i64 2, i64 4, i64 8, i64 16>
+ %V8i64 = urem <8 x i64> undef, <i64 2, i64 4, i64 8, i64 16, i64 32, i64 64, i64 128, i64 256>
+
+ %I32 = urem i32 undef, 16
+ %V4i32 = urem <4 x i32> undef, <i32 2, i32 4, i32 8, i32 16>
+ %V8i32 = urem <8 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256>
+ %V16i32 = urem <16 x i32> undef, <i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256, i32 2, i32 4, i32 8, i32 16, i32 32, i32 64, i32 128, i32 256>
+
+ %I16 = urem i16 undef, 16
+ %V8i16 = urem <8 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+ %V16i16 = urem <16 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+ %V32i16 = urem <32 x i16> undef, <i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256, i16 2, i16 4, i16 8, i16 16, i16 32, i16 64, i16 128, i16 256>
+
+ %I8 = urem i8 undef, 16
+ %V16i8 = urem <16 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+ %V32i8 = urem <32 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+ %V64i8 = urem <64 x i8> undef, <i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16, i8 2, i8 4, i8 8, i8 16>
+
+ ret i32 undef
+}
+
+define i32 @srem_uniformconstpow2() {
+; FAST-LABEL: 'srem_uniformconstpow2'
+; FAST-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %I64 = srem i64 undef, 16
+; FAST-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V2i64 = srem <2 x i64> undef, <i64 16, i64 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 92 for instruction: %V4i64 = srem <4 x i64> undef, <i64 16, i64 16, i64 16, i64 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 184 for instruction: %V8i64 = srem <8 x i64> undef, <i64 16, i64 16, i64 16, i64 16, i64 16, i64 16, i64 16, i64 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I32 = srem i32 undef, 16
+; FAST-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V4i32 = srem <4 x i32> undef, <i32 16, i32 16, i32 16, i32 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V8i32 = srem <8 x i32> undef, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V16i32 = srem <16 x i32> undef, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = srem i16 undef, 16
+; FAST-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V8i16 = srem <8 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %V16i16 = srem <16 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %V32i16 = srem <32 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = srem i8 undef, 16
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i8 = srem <16 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V32i8 = srem <32 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V64i8 = srem <64 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; SLOW-LABEL: 'srem_uniformconstpow2'
+; SLOW-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %I64 = srem i64 undef, 16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V2i64 = srem <2 x i64> undef, <i64 16, i64 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 92 for instruction: %V4i64 = srem <4 x i64> undef, <i64 16, i64 16, i64 16, i64 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 184 for instruction: %V8i64 = srem <8 x i64> undef, <i64 16, i64 16, i64 16, i64 16, i64 16, i64 16, i64 16, i64 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I32 = srem i32 undef, 16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V4i32 = srem <4 x i32> undef, <i32 16, i32 16, i32 16, i32 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V8i32 = srem <8 x i32> undef, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V16i32 = srem <16 x i32> undef, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I16 = srem i16 undef, 16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V8i16 = srem <8 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V16i16 = srem <16 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 266 for instruction: %V32i16 = srem <32 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I8 = srem i8 undef, 16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V16i8 = srem <16 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 256 for instruction: %V32i8 = srem <32 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 522 for instruction: %V64i8 = srem <64 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; ALL-SIZE-LABEL: 'srem_uniformconstpow2'
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = srem i64 undef, 16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2i64 = srem <2 x i64> undef, <i64 16, i64 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = srem <4 x i64> undef, <i64 16, i64 16, i64 16, i64 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i64 = srem <8 x i64> undef, <i64 16, i64 16, i64 16, i64 16, i64 16, i64 16, i64 16, i64 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I32 = srem i32 undef, 16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = srem <4 x i32> undef, <i32 16, i32 16, i32 16, i32 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i32 = srem <8 x i32> undef, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i32 = srem <16 x i32> undef, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = srem i16 undef, 16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i16 = srem <8 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i16 = srem <16 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i16 = srem <32 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = srem i8 undef, 16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i8 = srem <16 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i8 = srem <32 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V64i8 = srem <64 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %I64 = srem i64 undef, 16
+ %V2i64 = srem <2 x i64> undef, <i64 16, i64 16>
+ %V4i64 = srem <4 x i64> undef, <i64 16, i64 16, i64 16, i64 16>
+ %V8i64 = srem <8 x i64> undef, <i64 16, i64 16, i64 16, i64 16, i64 16, i64 16, i64 16, i64 16>
+
+ %I32 = srem i32 undef, 16
+ %V4i32 = srem <4 x i32> undef, <i32 16, i32 16, i32 16, i32 16>
+ %V8i32 = srem <8 x i32> undef, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
+ %V16i32 = srem <16 x i32> undef, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
+
+ %I16 = srem i16 undef, 16
+ %V8i16 = srem <8 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+ %V16i16 = srem <16 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+ %V32i16 = srem <32 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+
+ %I8 = srem i8 undef, 16
+ %V16i8 = srem <16 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+ %V32i8 = srem <32 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+ %V64i8 = srem <64 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+
+ ret i32 undef
+}
+
+define i32 @urem_uniformconstpow2() {
+; FAST-LABEL: 'urem_uniformconstpow2'
+; FAST-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %I64 = urem i64 undef, 16
+; FAST-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V2i64 = urem <2 x i64> undef, <i64 16, i64 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 92 for instruction: %V4i64 = urem <4 x i64> undef, <i64 16, i64 16, i64 16, i64 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 184 for instruction: %V8i64 = urem <8 x i64> undef, <i64 16, i64 16, i64 16, i64 16, i64 16, i64 16, i64 16, i64 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I32 = urem i32 undef, 16
+; FAST-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V4i32 = urem <4 x i32> undef, <i32 16, i32 16, i32 16, i32 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V8i32 = urem <8 x i32> undef, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V16i32 = urem <16 x i32> undef, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = urem i16 undef, 16
+; FAST-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V8i16 = urem <8 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %V16i16 = urem <16 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %V32i16 = urem <32 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = urem i8 undef, 16
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i8 = urem <16 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V32i8 = urem <32 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V64i8 = urem <64 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; SLOW-LABEL: 'urem_uniformconstpow2'
+; SLOW-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %I64 = urem i64 undef, 16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V2i64 = urem <2 x i64> undef, <i64 16, i64 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 92 for instruction: %V4i64 = urem <4 x i64> undef, <i64 16, i64 16, i64 16, i64 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 184 for instruction: %V8i64 = urem <8 x i64> undef, <i64 16, i64 16, i64 16, i64 16, i64 16, i64 16, i64 16, i64 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I32 = urem i32 undef, 16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V4i32 = urem <4 x i32> undef, <i32 16, i32 16, i32 16, i32 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V8i32 = urem <8 x i32> undef, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V16i32 = urem <16 x i32> undef, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I16 = urem i16 undef, 16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V8i16 = urem <8 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V16i16 = urem <16 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 266 for instruction: %V32i16 = urem <32 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I8 = urem i8 undef, 16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V16i8 = urem <16 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 256 for instruction: %V32i8 = urem <32 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 522 for instruction: %V64i8 = urem <64 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; ALL-SIZE-LABEL: 'urem_uniformconstpow2'
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = urem i64 undef, 16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2i64 = urem <2 x i64> undef, <i64 16, i64 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = urem <4 x i64> undef, <i64 16, i64 16, i64 16, i64 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i64 = urem <8 x i64> undef, <i64 16, i64 16, i64 16, i64 16, i64 16, i64 16, i64 16, i64 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I32 = urem i32 undef, 16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = urem <4 x i32> undef, <i32 16, i32 16, i32 16, i32 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i32 = urem <8 x i32> undef, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i32 = urem <16 x i32> undef, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = urem i16 undef, 16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i16 = urem <8 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i16 = urem <16 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i16 = urem <32 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = urem i8 undef, 16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i8 = urem <16 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i8 = urem <32 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V64i8 = urem <64 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %I64 = urem i64 undef, 16
+ %V2i64 = urem <2 x i64> undef, <i64 16, i64 16>
+ %V4i64 = urem <4 x i64> undef, <i64 16, i64 16, i64 16, i64 16>
+ %V8i64 = urem <8 x i64> undef, <i64 16, i64 16, i64 16, i64 16, i64 16, i64 16, i64 16, i64 16>
+
+ %I32 = urem i32 undef, 16
+ %V4i32 = urem <4 x i32> undef, <i32 16, i32 16, i32 16, i32 16>
+ %V8i32 = urem <8 x i32> undef, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
+ %V16i32 = urem <16 x i32> undef, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
+
+ %I16 = urem i16 undef, 16
+ %V8i16 = urem <8 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+ %V16i16 = urem <16 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+ %V32i16 = urem <32 x i16> undef, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+
+ %I8 = urem i8 undef, 16
+ %V16i8 = urem <16 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+ %V32i8 = urem <32 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+ %V64i8 = urem <64 x i8> undef, <i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16, i8 16>
+
+ ret i32 undef
+}
+
+define i32 @srem_constnegpow2() {
+; FAST-LABEL: 'srem_constnegpow2'
+; FAST-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %I64 = srem i64 undef, -16
+; FAST-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V2i64 = srem <2 x i64> undef, <i64 -8, i64 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 92 for instruction: %V4i64 = srem <4 x i64> undef, <i64 -2, i64 -4, i64 -8, i64 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 184 for instruction: %V8i64 = srem <8 x i64> undef, <i64 -2, i64 -4, i64 -8, i64 -16, i64 -32, i64 -64, i64 -128, i64 -256>
+; FAST-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I32 = srem i32 undef, -16
+; FAST-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V4i32 = srem <4 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V8i32 = srem <8 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256>
+; FAST-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V16i32 = srem <16 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256, i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = srem i16 undef, -16
+; FAST-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V8i16 = srem <8 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+; FAST-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %V16i16 = srem <16 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+; FAST-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %V32i16 = srem <32 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = srem i8 undef, -16
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i8 = srem <16 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V32i8 = srem <32 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V64i8 = srem <64 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; SLOW-LABEL: 'srem_constnegpow2'
+; SLOW-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %I64 = srem i64 undef, -16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V2i64 = srem <2 x i64> undef, <i64 -8, i64 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 92 for instruction: %V4i64 = srem <4 x i64> undef, <i64 -2, i64 -4, i64 -8, i64 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 184 for instruction: %V8i64 = srem <8 x i64> undef, <i64 -2, i64 -4, i64 -8, i64 -16, i64 -32, i64 -64, i64 -128, i64 -256>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I32 = srem i32 undef, -16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V4i32 = srem <4 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V8i32 = srem <8 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V16i32 = srem <16 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256, i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I16 = srem i16 undef, -16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V8i16 = srem <8 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V16i16 = srem <16 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 266 for instruction: %V32i16 = srem <32 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I8 = srem i8 undef, -16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V16i8 = srem <16 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 256 for instruction: %V32i8 = srem <32 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 522 for instruction: %V64i8 = srem <64 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; ALL-SIZE-LABEL: 'srem_constnegpow2'
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = srem i64 undef, -16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2i64 = srem <2 x i64> undef, <i64 -8, i64 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = srem <4 x i64> undef, <i64 -2, i64 -4, i64 -8, i64 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i64 = srem <8 x i64> undef, <i64 -2, i64 -4, i64 -8, i64 -16, i64 -32, i64 -64, i64 -128, i64 -256>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I32 = srem i32 undef, -16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = srem <4 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i32 = srem <8 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i32 = srem <16 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256, i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = srem i16 undef, -16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i16 = srem <8 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i16 = srem <16 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i16 = srem <32 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = srem i8 undef, -16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i8 = srem <16 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i8 = srem <32 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V64i8 = srem <64 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %I64 = srem i64 undef, -16
+ %V2i64 = srem <2 x i64> undef, <i64 -8, i64 -16>
+ %V4i64 = srem <4 x i64> undef, <i64 -2, i64 -4, i64 -8, i64 -16>
+ %V8i64 = srem <8 x i64> undef, <i64 -2, i64 -4, i64 -8, i64 -16, i64 -32, i64 -64, i64 -128, i64 -256>
+
+ %I32 = srem i32 undef, -16
+ %V4i32 = srem <4 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16>
+ %V8i32 = srem <8 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256>
+ %V16i32 = srem <16 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256, i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256>
+
+ %I16 = srem i16 undef, -16
+ %V8i16 = srem <8 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+ %V16i16 = srem <16 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+ %V32i16 = srem <32 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+
+ %I8 = srem i8 undef, -16
+ %V16i8 = srem <16 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+ %V32i8 = srem <32 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+ %V64i8 = srem <64 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+
+ ret i32 undef
+}
+
+define i32 @urem_constnegpow2() {
+; FAST-LABEL: 'urem_constnegpow2'
+; FAST-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %I64 = urem i64 undef, -16
+; FAST-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V2i64 = urem <2 x i64> undef, <i64 -8, i64 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 92 for instruction: %V4i64 = urem <4 x i64> undef, <i64 -2, i64 -4, i64 -8, i64 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 184 for instruction: %V8i64 = urem <8 x i64> undef, <i64 -2, i64 -4, i64 -8, i64 -16, i64 -32, i64 -64, i64 -128, i64 -256>
+; FAST-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I32 = urem i32 undef, -16
+; FAST-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V4i32 = urem <4 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V8i32 = urem <8 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256>
+; FAST-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V16i32 = urem <16 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256, i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = urem i16 undef, -16
+; FAST-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V8i16 = urem <8 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+; FAST-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %V16i16 = urem <16 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+; FAST-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %V32i16 = urem <32 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = urem i8 undef, -16
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i8 = urem <16 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V32i8 = urem <32 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V64i8 = urem <64 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; SLOW-LABEL: 'urem_constnegpow2'
+; SLOW-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %I64 = urem i64 undef, -16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V2i64 = urem <2 x i64> undef, <i64 -8, i64 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 92 for instruction: %V4i64 = urem <4 x i64> undef, <i64 -2, i64 -4, i64 -8, i64 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 184 for instruction: %V8i64 = urem <8 x i64> undef, <i64 -2, i64 -4, i64 -8, i64 -16, i64 -32, i64 -64, i64 -128, i64 -256>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I32 = urem i32 undef, -16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V4i32 = urem <4 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V8i32 = urem <8 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V16i32 = urem <16 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256, i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I16 = urem i16 undef, -16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V8i16 = urem <8 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V16i16 = urem <16 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 266 for instruction: %V32i16 = urem <32 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I8 = urem i8 undef, -16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V16i8 = urem <16 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 256 for instruction: %V32i8 = urem <32 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 522 for instruction: %V64i8 = urem <64 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; ALL-SIZE-LABEL: 'urem_constnegpow2'
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = urem i64 undef, -16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2i64 = urem <2 x i64> undef, <i64 -8, i64 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = urem <4 x i64> undef, <i64 -2, i64 -4, i64 -8, i64 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i64 = urem <8 x i64> undef, <i64 -2, i64 -4, i64 -8, i64 -16, i64 -32, i64 -64, i64 -128, i64 -256>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I32 = urem i32 undef, -16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = urem <4 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i32 = urem <8 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i32 = urem <16 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256, i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = urem i16 undef, -16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i16 = urem <8 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i16 = urem <16 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i16 = urem <32 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = urem i8 undef, -16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i8 = urem <16 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i8 = urem <32 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V64i8 = urem <64 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %I64 = urem i64 undef, -16
+ %V2i64 = urem <2 x i64> undef, <i64 -8, i64 -16>
+ %V4i64 = urem <4 x i64> undef, <i64 -2, i64 -4, i64 -8, i64 -16>
+ %V8i64 = urem <8 x i64> undef, <i64 -2, i64 -4, i64 -8, i64 -16, i64 -32, i64 -64, i64 -128, i64 -256>
+
+ %I32 = urem i32 undef, -16
+ %V4i32 = urem <4 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16>
+ %V8i32 = urem <8 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256>
+ %V16i32 = urem <16 x i32> undef, <i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256, i32 -2, i32 -4, i32 -8, i32 -16, i32 -32, i32 -64, i32 -128, i32 -256>
+
+ %I16 = urem i16 undef, -16
+ %V8i16 = urem <8 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+ %V16i16 = urem <16 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+ %V32i16 = urem <32 x i16> undef, <i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256, i16 -2, i16 -4, i16 -8, i16 -16, i16 -32, i16 -64, i16 -128, i16 -256>
+
+ %I8 = urem i8 undef, -16
+ %V16i8 = urem <16 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+ %V32i8 = urem <32 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+ %V64i8 = urem <64 x i8> undef, <i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16, i8 -2, i8 -4, i8 -8, i8 -16>
+
+ ret i32 undef
+}
+
+define i32 @srem_uniformconstnegpow2() {
+; FAST-LABEL: 'srem_uniformconstnegpow2'
+; FAST-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %I64 = srem i64 undef, -16
+; FAST-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V2i64 = srem <2 x i64> undef, <i64 -16, i64 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 92 for instruction: %V4i64 = srem <4 x i64> undef, <i64 -16, i64 -16, i64 -16, i64 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 184 for instruction: %V8i64 = srem <8 x i64> undef, <i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I32 = srem i32 undef, -16
+; FAST-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V4i32 = srem <4 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V8i32 = srem <8 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V16i32 = srem <16 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = srem i16 undef, -16
+; FAST-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V8i16 = srem <8 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %V16i16 = srem <16 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %V32i16 = srem <32 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = srem i8 undef, -16
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i8 = srem <16 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V32i8 = srem <32 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V64i8 = srem <64 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; SLOW-LABEL: 'srem_uniformconstnegpow2'
+; SLOW-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %I64 = srem i64 undef, -16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V2i64 = srem <2 x i64> undef, <i64 -16, i64 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 92 for instruction: %V4i64 = srem <4 x i64> undef, <i64 -16, i64 -16, i64 -16, i64 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 184 for instruction: %V8i64 = srem <8 x i64> undef, <i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I32 = srem i32 undef, -16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V4i32 = srem <4 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V8i32 = srem <8 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V16i32 = srem <16 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I16 = srem i16 undef, -16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V8i16 = srem <8 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V16i16 = srem <16 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 266 for instruction: %V32i16 = srem <32 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I8 = srem i8 undef, -16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V16i8 = srem <16 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 256 for instruction: %V32i8 = srem <32 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 522 for instruction: %V64i8 = srem <64 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; ALL-SIZE-LABEL: 'srem_uniformconstnegpow2'
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = srem i64 undef, -16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2i64 = srem <2 x i64> undef, <i64 -16, i64 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = srem <4 x i64> undef, <i64 -16, i64 -16, i64 -16, i64 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i64 = srem <8 x i64> undef, <i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I32 = srem i32 undef, -16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = srem <4 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i32 = srem <8 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i32 = srem <16 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = srem i16 undef, -16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i16 = srem <8 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i16 = srem <16 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i16 = srem <32 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = srem i8 undef, -16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i8 = srem <16 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i8 = srem <32 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V64i8 = srem <64 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %I64 = srem i64 undef, -16
+ %V2i64 = srem <2 x i64> undef, <i64 -16, i64 -16>
+ %V4i64 = srem <4 x i64> undef, <i64 -16, i64 -16, i64 -16, i64 -16>
+ %V8i64 = srem <8 x i64> undef, <i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16>
+
+ %I32 = srem i32 undef, -16
+ %V4i32 = srem <4 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16>
+ %V8i32 = srem <8 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16>
+ %V16i32 = srem <16 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16>
+
+ %I16 = srem i16 undef, -16
+ %V8i16 = srem <8 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+ %V16i16 = srem <16 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+ %V32i16 = srem <32 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+
+ %I8 = srem i8 undef, -16
+ %V16i8 = srem <16 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+ %V32i8 = srem <32 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+ %V64i8 = srem <64 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+
+ ret i32 undef
+}
+
+define i32 @urem_uniformconstnegpow2() {
+; FAST-LABEL: 'urem_uniformconstnegpow2'
+; FAST-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %I64 = urem i64 undef, -16
+; FAST-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V2i64 = urem <2 x i64> undef, <i64 -16, i64 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 92 for instruction: %V4i64 = urem <4 x i64> undef, <i64 -16, i64 -16, i64 -16, i64 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 184 for instruction: %V8i64 = urem <8 x i64> undef, <i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I32 = urem i32 undef, -16
+; FAST-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V4i32 = urem <4 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V8i32 = urem <8 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V16i32 = urem <16 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I16 = urem i16 undef, -16
+; FAST-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V8i16 = urem <8 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 31 for instruction: %V16i16 = urem <16 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %V32i16 = urem <32 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %I8 = urem i8 undef, -16
+; FAST-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V16i8 = urem <16 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 32 for instruction: %V32i8 = urem <32 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V64i8 = urem <64 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+; FAST-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; SLOW-LABEL: 'urem_uniformconstnegpow2'
+; SLOW-NEXT: Cost Model: Found an estimated cost of 23 for instruction: %I64 = urem i64 undef, -16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 46 for instruction: %V2i64 = urem <2 x i64> undef, <i64 -16, i64 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 92 for instruction: %V4i64 = urem <4 x i64> undef, <i64 -16, i64 -16, i64 -16, i64 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 184 for instruction: %V8i64 = urem <8 x i64> undef, <i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I32 = urem i32 undef, -16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V4i32 = urem <4 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V8i32 = urem <8 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V16i32 = urem <16 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I16 = urem i16 undef, -16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 64 for instruction: %V8i16 = urem <8 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V16i16 = urem <16 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 266 for instruction: %V32i16 = urem <32 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %I8 = urem i8 undef, -16
+; SLOW-NEXT: Cost Model: Found an estimated cost of 128 for instruction: %V16i8 = urem <16 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 256 for instruction: %V32i8 = urem <32 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 522 for instruction: %V64i8 = urem <64 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+; SLOW-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
+;
+; ALL-SIZE-LABEL: 'urem_uniformconstnegpow2'
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I64 = urem i64 undef, -16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2i64 = urem <2 x i64> undef, <i64 -16, i64 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i64 = urem <4 x i64> undef, <i64 -16, i64 -16, i64 -16, i64 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i64 = urem <8 x i64> undef, <i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I32 = urem i32 undef, -16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4i32 = urem <4 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i32 = urem <8 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i32 = urem <16 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I16 = urem i16 undef, -16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8i16 = urem <8 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i16 = urem <16 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i16 = urem <32 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %I8 = urem i8 undef, -16
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16i8 = urem <16 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V32i8 = urem <32 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V64i8 = urem <64 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+; ALL-SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
+;
+ %I64 = urem i64 undef, -16
+ %V2i64 = urem <2 x i64> undef, <i64 -16, i64 -16>
+ %V4i64 = urem <4 x i64> undef, <i64 -16, i64 -16, i64 -16, i64 -16>
+ %V8i64 = urem <8 x i64> undef, <i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16, i64 -16>
+
+ %I32 = urem i32 undef, -16
+ %V4i32 = urem <4 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16>
+ %V8i32 = urem <8 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16>
+ %V16i32 = urem <16 x i32> undef, <i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16, i32 -16>
+
+ %I16 = urem i16 undef, -16
+ %V8i16 = urem <8 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+ %V16i16 = urem <16 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+ %V32i16 = urem <32 x i16> undef, <i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16, i16 -16>
+
+ %I8 = urem i8 undef, -16
+ %V16i8 = urem <16 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+ %V32i8 = urem <32 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+ %V64i8 = urem <64 x i8> undef, <i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16, i8 -16>
+
+ ret i32 undef
+}
More information about the llvm-commits
mailing list