[NFC][AArch64] Specify aarch64 little-endian linux datalayout explicitly for cast.ll and arith-overflow.ll

[mingmingl]

Summary

These two tests stand out from a sweep study (D132889) to see how aarch64-little-endian linux data layout affects test results.

This is the pre-commit test for D132784

[mingmingl]

move target layout from opt option to IR, so that only one DL is needed per file (not one DL per RUN)

[mingmingl]

Add arith-overflow.ll into diffbase.

[fhahn]

LGTM, thanks!

[mingmingl]

thanks! Pushed https://github.com/llvm/llvm-project/commit/3785234b03c568cd135b18c79cd7606108b9d388.

Need to manually close this (uploaded commit message doesn't have differential revision link)

[dmgreen]

Thanks. This does sound good. It is probably worth doing it for all the other tests, as in D132889 even if they don't alter the costs.

[mingmingl]

In D132856#3760359, @dmgreen wrote:

Thanks. This does sound good. It is probably worth doing it for all the other tests, as in D132889 even if they don't alter the costs.

Adding them makes sense! Sent out D132889.

llvm/test/Analysis/CostModel/AArch64/arith-overflow.ll

 ; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
 ; RUN: opt -passes="print<cost-model>" 2>&1 -disable-output -mtriple=aarch64 < %s | FileCheck %s --check-prefix=RECIP
 ; RUN: opt -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=code-size -mtriple=aarch64 < %s | FileCheck %s --check-prefix=SIZE
 
+target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
+
 declare {i64, i1}              @llvm.sadd.with.overflow.i64(i64, i64)
 declare {<2 x i64>, <2 x i1>}  @llvm.sadd.with.overflow.v2i64(<2 x i64>, <2 x i64>)
 declare {<4 x i64>, <4 x i1>}  @llvm.sadd.with.overflow.v4i64(<4 x i64>, <4 x i64>)
 declare {<8 x i64>, <8 x i1>}  @llvm.sadd.with.overflow.v8i64(<8 x i64>, <8 x i64>)
 
 declare {i32, i1}               @llvm.sadd.with.overflow.i32(i32, i32)
 declare {<4 x i32>, <4 x i1>}   @llvm.sadd.with.overflow.v4i32(<4 x i32>, <4 x i32>)
 declare {<8 x i32>, <8 x i1>}   @llvm.sadd.with.overflow.v8i32(<8 x i32>, <8 x i32>)

 declare {i8, i1}                @llvm.smul.with.overflow.i8(i8, i8)
 declare {<16 x i8>, <16 x i1>}  @llvm.smul.with.overflow.v16i8(<16 x i8>, <16 x i8>)
 declare {<32 x i8>, <32 x i1>}  @llvm.smul.with.overflow.v32i8(<32 x i8>, <32 x i8>)
 declare {<64 x i8>, <64 x i1>}  @llvm.smul.with.overflow.v64i8(<64 x i8>, <64 x i8>)
 
 define i32 @smul(i32 %arg) {
 ; RECIP-LABEL: 'smul'
 ; RECIP-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call { i64, i1 } @llvm.smul.with.overflow.i64(i64 undef, i64 undef)
-; RECIP-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.smul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
-; RECIP-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.smul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
-; RECIP-NEXT:  Cost Model: Found an estimated cost of 88 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.smul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
+; RECIP-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.smul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
+; RECIP-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.smul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
+; RECIP-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.smul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call { i32, i1 } @llvm.smul.with.overflow.i32(i32 undef, i32 undef)
 ; RECIP-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.smul.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; RECIP-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.smul.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; RECIP-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.smul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; RECIP-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %I16 = call { i16, i1 } @llvm.smul.with.overflow.i16(i16 undef, i16 undef)
 ; RECIP-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.smul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; RECIP-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.smul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; RECIP-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.smul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; RECIP-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %I8 = call { i8, i1 } @llvm.smul.with.overflow.i8(i8 undef, i8 undef)
-; RECIP-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.smul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
-; RECIP-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.smul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
-; RECIP-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.smul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
+; RECIP-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.smul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
+; RECIP-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.smul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
+; RECIP-NEXT:  Cost Model: Found an estimated cost of 48 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.smul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; RECIP-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SIZE-LABEL: 'smul'
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call { i64, i1 } @llvm.smul.with.overflow.i64(i64 undef, i64 undef)
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.smul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.smul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.smul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call { i32, i1 } @llvm.smul.with.overflow.i32(i32 undef, i32 undef)

 declare {i8, i1}                @llvm.umul.with.overflow.i8(i8, i8)
 declare {<16 x i8>, <16 x i1>}  @llvm.umul.with.overflow.v16i8(<16 x i8>, <16 x i8>)
 declare {<32 x i8>, <32 x i1>}  @llvm.umul.with.overflow.v32i8(<32 x i8>, <32 x i8>)
 declare {<64 x i8>, <64 x i1>}  @llvm.umul.with.overflow.v64i8(<64 x i8>, <64 x i8>)
 
 define i32 @umul(i32 %arg) {
 ; RECIP-LABEL: 'umul'
 ; RECIP-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 undef, i64 undef)
-; RECIP-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.umul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
-; RECIP-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.umul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
-; RECIP-NEXT:  Cost Model: Found an estimated cost of 84 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.umul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
+; RECIP-NEXT:  Cost Model: Found an estimated cost of 17 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.umul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
+; RECIP-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.umul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
+; RECIP-NEXT:  Cost Model: Found an estimated cost of 68 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.umul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; RECIP-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call { i32, i1 } @llvm.umul.with.overflow.i32(i32 undef, i32 undef)
 ; RECIP-NEXT:  Cost Model: Found an estimated cost of 35 for instruction: %V4I32 = call { <4 x i32>, <4 x i1> } @llvm.umul.with.overflow.v4i32(<4 x i32> undef, <4 x i32> undef)
 ; RECIP-NEXT:  Cost Model: Found an estimated cost of 70 for instruction: %V8I32 = call { <8 x i32>, <8 x i1> } @llvm.umul.with.overflow.v8i32(<8 x i32> undef, <8 x i32> undef)
 ; RECIP-NEXT:  Cost Model: Found an estimated cost of 140 for instruction: %V16I32 = call { <16 x i32>, <16 x i1> } @llvm.umul.with.overflow.v16i32(<16 x i32> undef, <16 x i32> undef)
 ; RECIP-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I16 = call { i16, i1 } @llvm.umul.with.overflow.i16(i16 undef, i16 undef)
 ; RECIP-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V8I16 = call { <8 x i16>, <8 x i1> } @llvm.umul.with.overflow.v8i16(<8 x i16> undef, <8 x i16> undef)
 ; RECIP-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %V16I16 = call { <16 x i16>, <16 x i1> } @llvm.umul.with.overflow.v16i16(<16 x i16> undef, <16 x i16> undef)
 ; RECIP-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %V32I16 = call { <32 x i16>, <32 x i1> } @llvm.umul.with.overflow.v32i16(<32 x i16> undef, <32 x i16> undef)
 ; RECIP-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %I8 = call { i8, i1 } @llvm.umul.with.overflow.i8(i8 undef, i8 undef)
-; RECIP-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.umul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
-; RECIP-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.umul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
-; RECIP-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.umul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
+; RECIP-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %V16I8 = call { <16 x i8>, <16 x i1> } @llvm.umul.with.overflow.v16i8(<16 x i8> undef, <16 x i8> undef)
+; RECIP-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %V32I8 = call { <32 x i8>, <32 x i1> } @llvm.umul.with.overflow.v32i8(<32 x i8> undef, <32 x i8> undef)
+; RECIP-NEXT:  Cost Model: Found an estimated cost of 44 for instruction: %V64I8 = call { <64 x i8>, <64 x i1> } @llvm.umul.with.overflow.v64i8(<64 x i8> undef, <64 x i8> undef)
 ; RECIP-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; SIZE-LABEL: 'umul'
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %I64 = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 undef, i64 undef)
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2I64 = call { <2 x i64>, <2 x i1> } @llvm.umul.with.overflow.v2i64(<2 x i64> undef, <2 x i64> undef)
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V4I64 = call { <4 x i64>, <4 x i1> } @llvm.umul.with.overflow.v4i64(<4 x i64> undef, <4 x i64> undef)
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V8I64 = call { <8 x i64>, <8 x i1> } @llvm.umul.with.overflow.v8i64(<8 x i64> undef, <8 x i64> undef)
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %I32 = call { i32, i1 } @llvm.umul.with.overflow.i32(i32 undef, i32 undef)

llvm/test/Analysis/CostModel/AArch64/cast.ll

 ; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
 ; RUN: opt -passes="print<cost-model>" 2>&1 -disable-output -mtriple=aarch64-none-linux-gnueabi %s | FileCheck --check-prefixes=CHECK,CHECK-NOFP16 %s
 ; RUN: opt -passes="print<cost-model>" 2>&1 -disable-output -mtriple=aarch64-none-linux-gnueabi -mattr=+fullfp16 %s | FileCheck --check-prefixes=CHECK,CHECK-FP16 %s
 
+target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
+
 define void @ext() {
 ; CHECK-LABEL: 'ext'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %r0 = sext i1 undef to i8
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %r1 = zext i1 undef to i8
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %r2 = sext i1 undef to i16
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %r3 = zext i1 undef to i16
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %r4 = sext i1 undef to i32
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %r5 = zext i1 undef to i32

 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %r26 = trunc i64 undef to i1
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %r27 = trunc i64 undef to i8
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %r28 = trunc i64 undef to i16
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %r29 = trunc i64 undef to i32
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s2i8i16 = trunc <2 x i16> undef to <2 x i8>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s2i8i32 = trunc <2 x i32> undef to <2 x i8>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %s2i8i64 = trunc <2 x i64> undef to <2 x i8>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s2i16i32 = trunc <2 x i32> undef to <2 x i16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %s2i16i64 = trunc <2 x i64> undef to <2 x i16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %s2i32i64 = trunc <2 x i64> undef to <2 x i32>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s2i16i64 = trunc <2 x i64> undef to <2 x i16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s2i32i64 = trunc <2 x i64> undef to <2 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s4i8i16 = trunc <4 x i16> undef to <4 x i8>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %s4i8i32 = trunc <4 x i32> undef to <4 x i8>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %s4i8i64 = trunc <4 x i64> undef to <4 x i8>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s4i8i32 = trunc <4 x i32> undef to <4 x i8>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s4i8i64 = trunc <4 x i64> undef to <4 x i8>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %s4i16i32 = trunc <4 x i32> undef to <4 x i16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %s4i16i64 = trunc <4 x i64> undef to <4 x i16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s4i16i64 = trunc <4 x i64> undef to <4 x i16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s4i32i64 = trunc <4 x i64> undef to <4 x i32>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %s8i8i16 = trunc <8 x i16> undef to <8 x i8>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s8i8i16 = trunc <8 x i16> undef to <8 x i8>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %s8i8i32 = trunc <8 x i32> undef to <8 x i8>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %s8i8i64 = trunc <8 x i64> undef to <8 x i8>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s8i8i64 = trunc <8 x i64> undef to <8 x i8>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %s8i16i32 = trunc <8 x i32> undef to <8 x i16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %s8i16i64 = trunc <8 x i64> undef to <8 x i16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %s8i16i64 = trunc <8 x i64> undef to <8 x i16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s8i32i64 = trunc <8 x i64> undef to <8 x i32>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %s16i8i16 = trunc <16 x i16> undef to <16 x i8>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %s16i8i16 = trunc <16 x i16> undef to <16 x i8>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %s16i8i32 = trunc <16 x i32> undef to <16 x i8>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %s16i8i64 = trunc <16 x i64> undef to <16 x i8>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %s16i8i64 = trunc <16 x i64> undef to <16 x i8>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %s16i16i32 = trunc <16 x i32> undef to <16 x i16>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %s16i16i64 = trunc <16 x i64> undef to <16 x i16>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %s16i16i64 = trunc <16 x i64> undef to <16 x i16>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s16i32i64 = trunc <16 x i64> undef to <16 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %r8 = trunc i8 undef to i1
   %r15 = trunc i16 undef to i1
   %r16 = trunc i16 undef to i8
   %r21 = trunc i32 undef to i1
   %r22 = trunc i32 undef to i8

 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r0 = sext i8 %a to i16
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r1 = sext i8 %a to i32
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r2 = sext i8 %a to i64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r3 = sext i16 %b to i32
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r4 = sext i16 %b to i64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r5 = sext i32 %c to i64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i16 %r0, i16* undef, align 2
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i32 %r1, i32* undef, align 4
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i64 %r2, i64* undef, align 4
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i64 %r2, i64* undef, align 8
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i32 %r3, i32* undef, align 4
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i64 %r4, i64* undef, align 4
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i64 %r5, i64* undef, align 4
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i64 %r4, i64* undef, align 8
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i64 %r5, i64* undef, align 8
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r6 = zext i8 %a to i16
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r7 = zext i8 %a to i32
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %r8 = zext i8 %a to i64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r9 = zext i16 %b to i32
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %r10 = zext i16 %b to i64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %r11 = zext i32 %c to i64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i16 %r6, i16* undef, align 2
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i32 %r7, i32* undef, align 4
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i64 %r8, i64* undef, align 4
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i64 %r8, i64* undef, align 8
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i32 %r9, i32* undef, align 4
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i64 %r10, i64* undef, align 4
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i64 %r11, i64* undef, align 4
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i64 %r10, i64* undef, align 8
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i64 %r11, i64* undef, align 8
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %r12 = trunc i64 %d to i32
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %r13 = trunc i64 %d to i16
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %r14 = trunc i64 %d to i8
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %r15 = trunc i32 %c to i16
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %r16 = trunc i32 %c to i8
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %r17 = trunc i16 %b to i8
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %tie.trunc.8 = add i8 %r14, %r16
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %tie.trunc.8.1 = add i8 %tie.trunc.8, %r17

 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r21 = sext i1 %e to i64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r22 = zext i1 %e to i8
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r23 = zext i1 %e to i16
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r24 = zext i1 %e to i32
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %r25 = zext i1 %e to i64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i8 %r18, i8* undef, align 1
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i16 %r19, i16* undef, align 2
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i32 %r20, i32* undef, align 4
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i64 %r21, i64* undef, align 4
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i64 %r21, i64* undef, align 8
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i8 %r22, i8* undef, align 1
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i16 %r23, i16* undef, align 2
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i32 %r24, i32* undef, align 4
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i64 %r25, i64* undef, align 4
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i64 %r25, i64* undef, align 8
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r12
 ;
   %r0 = sext i8 %a to i16
   %r1 = sext i8 %a to i32
   %r2 = sext i8 %a to i64
   %r3 = sext i16 %b to i32
   %r4 = sext i16 %b to i64
   %r5 = sext i32 %c to i64