[llvm] d0231d2 - [LV] Fix LoopVectorize/X86/CostModel tests when regenerated with UTC. NFC (#209802)
via llvm-commits
llvm-commits at lists.llvm.org
Wed Jul 15 08:51:07 PDT 2026
Author: Luke Lau
Date: 2026-07-15T23:51:01+08:00
New Revision: d0231d2195976b5b091b8e55f4d4fd2b55875ee5
URL: https://github.com/llvm/llvm-project/commit/d0231d2195976b5b091b8e55f4d4fd2b55875ee5
DIFF: https://github.com/llvm/llvm-project/commit/d0231d2195976b5b091b8e55f4d4fd2b55875ee5.diff
LOG: [LV] Fix LoopVectorize/X86/CostModel tests when regenerated with UTC. NFC (#209802)
Some of the cost model tests were passing, but their UTC arguments
were outdated and CHECK lines disappeared when regenerating them.
- Add additional --filter lines for VPlan cost model CHECK lines,
which were manually written previously
- Update the --filter argument for the updated INTERLEAVE-GROUP print
output
- Regenerate strided-load-*.ll tests with UTC
- Pass -vplan-print-metadata=false for tests that were using
hand-written regexes in CHECK lines
Added:
Modified:
llvm/test/Transforms/LoopVectorize/X86/CostModel/gather-i16-with-i8-index.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/gather-i32-with-i8-index.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/gather-i64-with-i8-index.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/gather-i8-with-i8-index.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/handle-iptr-with-data-layout-to-not-assert.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f32-stride-2.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f32-stride-3.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f32-stride-4.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f32-stride-5.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f32-stride-6.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f32-stride-7.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f32-stride-8.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f64-stride-2.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f64-stride-3.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f64-stride-4.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f64-stride-5.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f64-stride-6.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f64-stride-7.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f64-stride-8.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-half.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i16-stride-2.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i16-stride-3.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i16-stride-4.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i16-stride-5.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i16-stride-6.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i16-stride-7.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i16-stride-8.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-2-indices-0u.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-2.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-3-indices-01u.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-3-indices-0uu.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-3.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-4-indices-012u.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-4-indices-01uu.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-4-indices-0uuu.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-4.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-5.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-6.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-7.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-8.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i64-stride-2.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i64-stride-3.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i64-stride-4.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i64-stride-5.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i64-stride-6.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i64-stride-7.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i64-stride-8.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i8-stride-2.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i8-stride-3.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i8-stride-4.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i8-stride-5.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i8-stride-6.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i8-stride-7.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i8-stride-8.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f32-stride-2.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f32-stride-3.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f32-stride-4.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f32-stride-5.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f32-stride-6.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f32-stride-7.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f32-stride-8.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f64-stride-2.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f64-stride-3.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f64-stride-4.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f64-stride-5.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f64-stride-6.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f64-stride-7.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i16-stride-2.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i16-stride-3.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i16-stride-4.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i16-stride-5.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i16-stride-6.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i16-stride-7.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i16-stride-8.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i32-stride-2.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i32-stride-3.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i32-stride-4.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i32-stride-5.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i32-stride-6.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i32-stride-7.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i32-stride-8.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i64-stride-2.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i64-stride-3.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i64-stride-4.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i64-stride-5.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i64-stride-6.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i64-stride-7.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i64-stride-8.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i8-stride-2.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i8-stride-3.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i8-stride-4.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i8-stride-5.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i8-stride-6.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i8-stride-7.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i8-stride-8.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-gather-i32-with-i8-index.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-gather-i64-with-i8-index.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-interleaved-load-i16.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-interleaved-store-i16.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-load-i16.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-load-i32.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-load-i64.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-load-i8.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-store-i16.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-store-i32.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-store-i64.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-store-i8.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/strided-load-i16.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/strided-load-i32.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/strided-load-i64.ll
llvm/test/Transforms/LoopVectorize/X86/CostModel/strided-load-i8.ll
Removed:
################################################################################
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/gather-i16-with-i8-index.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/gather-i16-with-i8-index.ll
index 8cf210ad4f2c8..1ac8f11262064 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/gather-i16-with-i8-index.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/gather-i16-with-i8-index.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF [0-9]+ For instruction:\s*%valB = load i16, ptr %inB, align 2"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF [0-9]+ For instruction:\s*%valB = load i16, ptr %inB, align 2" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: .* ir<%valB> = load"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=SSE
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse4.2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=SSE
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=AVX1
@@ -18,43 +18,43 @@ target triple = "x86_64-unknown-linux-gnu"
define void @test() {
; SSE-LABEL: 'test'
; SSE: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i16, ptr %inB, align 2
-; SSE: Cost of 24 for VF 2: {{.*}}ir<%valB> = load
-; SSE: Cost of 48 for VF 4: {{.*}}ir<%valB> = load
-; SSE: Cost of 96 for VF 8: {{.*}}ir<%valB> = load
-; SSE: Cost of 192 for VF 16: {{.*}}ir<%valB> = load
+; SSE: Cost of 24 for VF 2: REPLICATE ir<%valB> = load ir<%inB>
+; SSE: Cost of 48 for VF 4: REPLICATE ir<%valB> = load ir<%inB>
+; SSE: Cost of 96 for VF 8: REPLICATE ir<%valB> = load ir<%inB>
+; SSE: Cost of 192 for VF 16: REPLICATE ir<%valB> = load ir<%inB>
;
; AVX1-LABEL: 'test'
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i16, ptr %inB, align 2
-; AVX1: Cost of 24 for VF 2: {{.*}}ir<%valB> = load
-; AVX1: Cost of 48 for VF 4: {{.*}}ir<%valB> = load
-; AVX1: Cost of 96 for VF 8: {{.*}}ir<%valB> = load
-; AVX1: Cost of 193 for VF 16: {{.*}}ir<%valB> = load
-; AVX1: Cost of 386 for VF 32: {{.*}}ir<%valB> = load
+; AVX1: Cost of 24 for VF 2: REPLICATE ir<%valB> = load ir<%inB>
+; AVX1: Cost of 48 for VF 4: REPLICATE ir<%valB> = load ir<%inB>
+; AVX1: Cost of 96 for VF 8: REPLICATE ir<%valB> = load ir<%inB>
+; AVX1: Cost of 193 for VF 16: REPLICATE ir<%valB> = load ir<%inB>
+; AVX1: Cost of 386 for VF 32: REPLICATE ir<%valB> = load ir<%inB>
;
; AVX2-SLOWGATHER-LABEL: 'test'
; AVX2-SLOWGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i16, ptr %inB, align 2
-; AVX2-SLOWGATHER: Cost of 4 for VF 2: {{.*}}ir<%valB> = load
-; AVX2-SLOWGATHER: Cost of 8 for VF 4: {{.*}}ir<%valB> = load
-; AVX2-SLOWGATHER: Cost of 16 for VF 8: {{.*}}ir<%valB> = load
-; AVX2-SLOWGATHER: Cost of 33 for VF 16: {{.*}}ir<%valB> = load
-; AVX2-SLOWGATHER: Cost of 66 for VF 32: {{.*}}ir<%valB> = load
+; AVX2-SLOWGATHER: Cost of 4 for VF 2: REPLICATE ir<%valB> = load ir<%inB>
+; AVX2-SLOWGATHER: Cost of 8 for VF 4: REPLICATE ir<%valB> = load ir<%inB>
+; AVX2-SLOWGATHER: Cost of 16 for VF 8: REPLICATE ir<%valB> = load ir<%inB>
+; AVX2-SLOWGATHER: Cost of 33 for VF 16: REPLICATE ir<%valB> = load ir<%inB>
+; AVX2-SLOWGATHER: Cost of 66 for VF 32: REPLICATE ir<%valB> = load ir<%inB>
;
; AVX2-FASTGATHER-LABEL: 'test'
; AVX2-FASTGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i16, ptr %inB, align 2
-; AVX2-FASTGATHER: Cost of 6 for VF 2: {{.*}}ir<%valB> = load
-; AVX2-FASTGATHER: Cost of 13 for VF 4: {{.*}}ir<%valB> = load
-; AVX2-FASTGATHER: Cost of 26 for VF 8: {{.*}}ir<%valB> = load
-; AVX2-FASTGATHER: Cost of 53 for VF 16: {{.*}}ir<%valB> = load
-; AVX2-FASTGATHER: Cost of 106 for VF 32: {{.*}}ir<%valB> = load
+; AVX2-FASTGATHER: Cost of 6 for VF 2: REPLICATE ir<%valB> = load ir<%inB>
+; AVX2-FASTGATHER: Cost of 13 for VF 4: REPLICATE ir<%valB> = load ir<%inB>
+; AVX2-FASTGATHER: Cost of 26 for VF 8: REPLICATE ir<%valB> = load ir<%inB>
+; AVX2-FASTGATHER: Cost of 53 for VF 16: REPLICATE ir<%valB> = load ir<%inB>
+; AVX2-FASTGATHER: Cost of 106 for VF 32: REPLICATE ir<%valB> = load ir<%inB>
;
; AVX512-LABEL: 'test'
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i16, ptr %inB, align 2
-; AVX512: Cost of 6 for VF 2: {{.*}}ir<%valB> = load
-; AVX512: Cost of 13 for VF 4: {{.*}}ir<%valB> = load
-; AVX512: Cost of 27 for VF 8: {{.*}}ir<%valB> = load
-; AVX512: Cost of 55 for VF 16: {{.*}}ir<%valB> = load
-; AVX512: Cost of 111 for VF 32: {{.*}}ir<%valB> = load
-; AVX512: Cost of 222 for VF 64: {{.*}}ir<%valB> = load
+; AVX512: Cost of 6 for VF 2: REPLICATE ir<%valB> = load ir<%inB>
+; AVX512: Cost of 13 for VF 4: REPLICATE ir<%valB> = load ir<%inB>
+; AVX512: Cost of 27 for VF 8: REPLICATE ir<%valB> = load ir<%inB>
+; AVX512: Cost of 55 for VF 16: REPLICATE ir<%valB> = load ir<%inB>
+; AVX512: Cost of 111 for VF 32: REPLICATE ir<%valB> = load ir<%inB>
+; AVX512: Cost of 222 for VF 64: REPLICATE ir<%valB> = load ir<%inB>
;
entry:
br label %for.body
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/gather-i32-with-i8-index.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/gather-i32-with-i8-index.ll
index a44654e157a49..2d5a30019bacd 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/gather-i32-with-i8-index.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/gather-i32-with-i8-index.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF [0-9]+ For instruction:\s*%valB = load i32, ptr %inB, align 4"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF [0-9]+ For instruction:\s*%valB = load i32, ptr %inB, align 4" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: .* ir<%valB> = load"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse4.2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=SSE42
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=AVX1
@@ -18,50 +18,50 @@ target triple = "x86_64-unknown-linux-gnu"
define void @test() {
; SSE2-LABEL: 'test'
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i32, ptr %inB, align 4
-; SSE2: Cost of 25 for VF 2: {{.*}}ir<%valB> = load
-; SSE2: Cost of 51 for VF 4: {{.*}}ir<%valB> = load
-; SSE2: Cost of 102 for VF 8: {{.*}}ir<%valB> = load
-; SSE2: Cost of 204 for VF 16: {{.*}}ir<%valB> = load
+; SSE2: Cost of 25 for VF 2: REPLICATE ir<%valB> = load ir<%inB>
+; SSE2: Cost of 51 for VF 4: REPLICATE ir<%valB> = load ir<%inB>
+; SSE2: Cost of 102 for VF 8: REPLICATE ir<%valB> = load ir<%inB>
+; SSE2: Cost of 204 for VF 16: REPLICATE ir<%valB> = load ir<%inB>
;
; SSE42-LABEL: 'test'
; SSE42: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i32, ptr %inB, align 4
-; SSE42: Cost of 24 for VF 2: {{.*}}ir<%valB> = load
-; SSE42: Cost of 48 for VF 4: {{.*}}ir<%valB> = load
-; SSE42: Cost of 96 for VF 8: {{.*}}ir<%valB> = load
-; SSE42: Cost of 192 for VF 16: {{.*}}ir<%valB> = load
+; SSE42: Cost of 24 for VF 2: REPLICATE ir<%valB> = load ir<%inB>
+; SSE42: Cost of 48 for VF 4: REPLICATE ir<%valB> = load ir<%inB>
+; SSE42: Cost of 96 for VF 8: REPLICATE ir<%valB> = load ir<%inB>
+; SSE42: Cost of 192 for VF 16: REPLICATE ir<%valB> = load ir<%inB>
;
; AVX1-LABEL: 'test'
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i32, ptr %inB, align 4
-; AVX1: Cost of 24 for VF 2: {{.*}}ir<%valB> = load
-; AVX1: Cost of 48 for VF 4: {{.*}}ir<%valB> = load
-; AVX1: Cost of 97 for VF 8: {{.*}}ir<%valB> = load
-; AVX1: Cost of 194 for VF 16: {{.*}}ir<%valB> = load
-; AVX1: Cost of 388 for VF 32: {{.*}}ir<%valB> = load
+; AVX1: Cost of 24 for VF 2: REPLICATE ir<%valB> = load ir<%inB>
+; AVX1: Cost of 48 for VF 4: REPLICATE ir<%valB> = load ir<%inB>
+; AVX1: Cost of 97 for VF 8: REPLICATE ir<%valB> = load ir<%inB>
+; AVX1: Cost of 194 for VF 16: REPLICATE ir<%valB> = load ir<%inB>
+; AVX1: Cost of 388 for VF 32: REPLICATE ir<%valB> = load ir<%inB>
;
; AVX2-SLOWGATHER-LABEL: 'test'
; AVX2-SLOWGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i32, ptr %inB, align 4
-; AVX2-SLOWGATHER: Cost of 4 for VF 2: {{.*}}ir<%valB> = load
-; AVX2-SLOWGATHER: Cost of 8 for VF 4: {{.*}}ir<%valB> = load
-; AVX2-SLOWGATHER: Cost of 17 for VF 8: {{.*}}ir<%valB> = load
-; AVX2-SLOWGATHER: Cost of 34 for VF 16: {{.*}}ir<%valB> = load
-; AVX2-SLOWGATHER: Cost of 68 for VF 32: {{.*}}ir<%valB> = load
+; AVX2-SLOWGATHER: Cost of 4 for VF 2: REPLICATE ir<%valB> = load ir<%inB>
+; AVX2-SLOWGATHER: Cost of 8 for VF 4: REPLICATE ir<%valB> = load ir<%inB>
+; AVX2-SLOWGATHER: Cost of 17 for VF 8: REPLICATE ir<%valB> = load ir<%inB>
+; AVX2-SLOWGATHER: Cost of 34 for VF 16: REPLICATE ir<%valB> = load ir<%inB>
+; AVX2-SLOWGATHER: Cost of 68 for VF 32: REPLICATE ir<%valB> = load ir<%inB>
;
; AVX2-FASTGATHER-LABEL: 'test'
; AVX2-FASTGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i32, ptr %inB, align 4
-; AVX2-FASTGATHER: Cost of 4 for VF 2: {{.*}}ir<%valB> = load
-; AVX2-FASTGATHER: Cost of 6 for VF 4: {{.*}}ir<%valB> = load
-; AVX2-FASTGATHER: Cost of 12 for VF 8: {{.*}}ir<%valB> = load
-; AVX2-FASTGATHER: Cost of 24 for VF 16: {{.*}}ir<%valB> = load
-; AVX2-FASTGATHER: Cost of 48 for VF 32: {{.*}}ir<%valB> = load
+; AVX2-FASTGATHER: Cost of 4 for VF 2: WIDEN ir<%valB> = load ir<%inB>
+; AVX2-FASTGATHER: Cost of 6 for VF 4: WIDEN ir<%valB> = load ir<%inB>
+; AVX2-FASTGATHER: Cost of 12 for VF 8: WIDEN ir<%valB> = load ir<%inB>
+; AVX2-FASTGATHER: Cost of 24 for VF 16: WIDEN ir<%valB> = load ir<%inB>
+; AVX2-FASTGATHER: Cost of 48 for VF 32: WIDEN ir<%valB> = load ir<%inB>
;
; AVX512-LABEL: 'test'
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i32, ptr %inB, align 4
-; AVX512: Cost of 6 for VF 2: {{.*}}ir<%valB> = load
-; AVX512: Cost of 13 for VF 4: {{.*}}ir<%valB> = load
-; AVX512: Cost of 10 for VF 8: {{.*}}ir<%valB> = load
-; AVX512: Cost of 18 for VF 16: {{.*}}ir<%valB> = load
-; AVX512: Cost of 36 for VF 32: {{.*}}ir<%valB> = load
-; AVX512: Cost of 72 for VF 64: {{.*}}ir<%valB> = load
+; AVX512: Cost of 6 for VF 2: REPLICATE ir<%valB> = load ir<%inB>
+; AVX512: Cost of 13 for VF 4: REPLICATE ir<%valB> = load ir<%inB>
+; AVX512: Cost of 10 for VF 8: WIDEN ir<%valB> = load ir<%inB>
+; AVX512: Cost of 18 for VF 16: WIDEN ir<%valB> = load ir<%inB>
+; AVX512: Cost of 36 for VF 32: WIDEN ir<%valB> = load ir<%inB>
+; AVX512: Cost of 72 for VF 64: WIDEN ir<%valB> = load ir<%inB>
;
entry:
br label %for.body
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/gather-i64-with-i8-index.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/gather-i64-with-i8-index.ll
index 7040087e4b400..ce5828a46eea7 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/gather-i64-with-i8-index.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/gather-i64-with-i8-index.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF [0-9]+ For instruction:\s*%valB = load i64, ptr %inB, align 8"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF [0-9]+ For instruction:\s*%valB = load i64, ptr %inB, align 8" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: .* ir<%valB> = load"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse4.2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=SSE42
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=AVX1
@@ -18,50 +18,50 @@ target triple = "x86_64-unknown-linux-gnu"
define void @test() {
; SSE2-LABEL: 'test'
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i64, ptr %inB, align 8
-; SSE2: Cost of 25 for VF 2: {{.*}}ir<%valB> = load
-; SSE2: Cost of 50 for VF 4: {{.*}}ir<%valB> = load
-; SSE2: Cost of 100 for VF 8: {{.*}}ir<%valB> = load
-; SSE2: Cost of 200 for VF 16: {{.*}}ir<%valB> = load
+; SSE2: Cost of 25 for VF 2: REPLICATE ir<%valB> = load ir<%inB>
+; SSE2: Cost of 50 for VF 4: REPLICATE ir<%valB> = load ir<%inB>
+; SSE2: Cost of 100 for VF 8: REPLICATE ir<%valB> = load ir<%inB>
+; SSE2: Cost of 200 for VF 16: REPLICATE ir<%valB> = load ir<%inB>
;
; SSE42-LABEL: 'test'
; SSE42: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i64, ptr %inB, align 8
-; SSE42: Cost of 24 for VF 2: {{.*}}ir<%valB> = load
-; SSE42: Cost of 48 for VF 4: {{.*}}ir<%valB> = load
-; SSE42: Cost of 96 for VF 8: {{.*}}ir<%valB> = load
-; SSE42: Cost of 192 for VF 16: {{.*}}ir<%valB> = load
+; SSE42: Cost of 24 for VF 2: REPLICATE ir<%valB> = load ir<%inB>
+; SSE42: Cost of 48 for VF 4: REPLICATE ir<%valB> = load ir<%inB>
+; SSE42: Cost of 96 for VF 8: REPLICATE ir<%valB> = load ir<%inB>
+; SSE42: Cost of 192 for VF 16: REPLICATE ir<%valB> = load ir<%inB>
;
; AVX1-LABEL: 'test'
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i64, ptr %inB, align 8
-; AVX1: Cost of 24 for VF 2: {{.*}}ir<%valB> = load
-; AVX1: Cost of 49 for VF 4: {{.*}}ir<%valB> = load
-; AVX1: Cost of 98 for VF 8: {{.*}}ir<%valB> = load
-; AVX1: Cost of 196 for VF 16: {{.*}}ir<%valB> = load
-; AVX1: Cost of 392 for VF 32: {{.*}}ir<%valB> = load
+; AVX1: Cost of 24 for VF 2: REPLICATE ir<%valB> = load ir<%inB>
+; AVX1: Cost of 49 for VF 4: REPLICATE ir<%valB> = load ir<%inB>
+; AVX1: Cost of 98 for VF 8: REPLICATE ir<%valB> = load ir<%inB>
+; AVX1: Cost of 196 for VF 16: REPLICATE ir<%valB> = load ir<%inB>
+; AVX1: Cost of 392 for VF 32: REPLICATE ir<%valB> = load ir<%inB>
;
; AVX2-SLOWGATHER-LABEL: 'test'
; AVX2-SLOWGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i64, ptr %inB, align 8
-; AVX2-SLOWGATHER: Cost of 4 for VF 2: {{.*}}ir<%valB> = load
-; AVX2-SLOWGATHER: Cost of 9 for VF 4: {{.*}}ir<%valB> = load
-; AVX2-SLOWGATHER: Cost of 18 for VF 8: {{.*}}ir<%valB> = load
-; AVX2-SLOWGATHER: Cost of 36 for VF 16: {{.*}}ir<%valB> = load
-; AVX2-SLOWGATHER: Cost of 72 for VF 32: {{.*}}ir<%valB> = load
+; AVX2-SLOWGATHER: Cost of 4 for VF 2: REPLICATE ir<%valB> = load ir<%inB>
+; AVX2-SLOWGATHER: Cost of 9 for VF 4: REPLICATE ir<%valB> = load ir<%inB>
+; AVX2-SLOWGATHER: Cost of 18 for VF 8: REPLICATE ir<%valB> = load ir<%inB>
+; AVX2-SLOWGATHER: Cost of 36 for VF 16: REPLICATE ir<%valB> = load ir<%inB>
+; AVX2-SLOWGATHER: Cost of 72 for VF 32: REPLICATE ir<%valB> = load ir<%inB>
;
; AVX2-FASTGATHER-LABEL: 'test'
; AVX2-FASTGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i64, ptr %inB, align 8
-; AVX2-FASTGATHER: Cost of 4 for VF 2: {{.*}}ir<%valB> = load
-; AVX2-FASTGATHER: Cost of 6 for VF 4: {{.*}}ir<%valB> = load
-; AVX2-FASTGATHER: Cost of 12 for VF 8: {{.*}}ir<%valB> = load
-; AVX2-FASTGATHER: Cost of 24 for VF 16: {{.*}}ir<%valB> = load
-; AVX2-FASTGATHER: Cost of 48 for VF 32: {{.*}}ir<%valB> = load
+; AVX2-FASTGATHER: Cost of 4 for VF 2: WIDEN ir<%valB> = load ir<%inB>
+; AVX2-FASTGATHER: Cost of 6 for VF 4: WIDEN ir<%valB> = load ir<%inB>
+; AVX2-FASTGATHER: Cost of 12 for VF 8: WIDEN ir<%valB> = load ir<%inB>
+; AVX2-FASTGATHER: Cost of 24 for VF 16: WIDEN ir<%valB> = load ir<%inB>
+; AVX2-FASTGATHER: Cost of 48 for VF 32: WIDEN ir<%valB> = load ir<%inB>
;
; AVX512-LABEL: 'test'
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i64, ptr %inB, align 8
-; AVX512: Cost of 6 for VF 2: {{.*}}ir<%valB> = load
-; AVX512: Cost of 14 for VF 4: {{.*}}ir<%valB> = load
-; AVX512: Cost of 10 for VF 8: {{.*}}ir<%valB> = load
-; AVX512: Cost of 20 for VF 16: {{.*}}ir<%valB> = load
-; AVX512: Cost of 40 for VF 32: {{.*}}ir<%valB> = load
-; AVX512: Cost of 80 for VF 64: {{.*}}ir<%valB> = load
+; AVX512: Cost of 6 for VF 2: REPLICATE ir<%valB> = load ir<%inB>
+; AVX512: Cost of 14 for VF 4: REPLICATE ir<%valB> = load ir<%inB>
+; AVX512: Cost of 10 for VF 8: WIDEN ir<%valB> = load ir<%inB>
+; AVX512: Cost of 20 for VF 16: WIDEN ir<%valB> = load ir<%inB>
+; AVX512: Cost of 40 for VF 32: WIDEN ir<%valB> = load ir<%inB>
+; AVX512: Cost of 80 for VF 64: WIDEN ir<%valB> = load ir<%inB>
;
entry:
br label %for.body
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/gather-i8-with-i8-index.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/gather-i8-with-i8-index.ll
index d51a6b341b8cf..d894cdb753bcd 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/gather-i8-with-i8-index.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/gather-i8-with-i8-index.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF [0-9]+ For instruction:\s*%valB = load i8, ptr %inB, align 1"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF [0-9]+ For instruction:\s*%valB = load i8, ptr %inB, align 1" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: .* ir<%valB> = load"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse4.2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=SSE42
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=AVX1
@@ -18,50 +18,50 @@ target triple = "x86_64-unknown-linux-gnu"
define void @test() {
; SSE2-LABEL: 'test'
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i8, ptr %inB, align 1
-; SSE2: Cost of 25 for VF 2: {{.*}}ir<%valB> = load
-; SSE2: Cost of 51 for VF 4: {{.*}}ir<%valB> = load
-; SSE2: Cost of 103 for VF 8: {{.*}}ir<%valB> = load
-; SSE2: Cost of 207 for VF 16: {{.*}}ir<%valB> = load
+; SSE2: Cost of 25 for VF 2: REPLICATE ir<%valB> = load ir<%inB>
+; SSE2: Cost of 51 for VF 4: REPLICATE ir<%valB> = load ir<%inB>
+; SSE2: Cost of 103 for VF 8: REPLICATE ir<%valB> = load ir<%inB>
+; SSE2: Cost of 207 for VF 16: REPLICATE ir<%valB> = load ir<%inB>
;
; SSE42-LABEL: 'test'
; SSE42: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i8, ptr %inB, align 1
-; SSE42: Cost of 24 for VF 2: {{.*}}ir<%valB> = load
-; SSE42: Cost of 48 for VF 4: {{.*}}ir<%valB> = load
-; SSE42: Cost of 96 for VF 8: {{.*}}ir<%valB> = load
-; SSE42: Cost of 192 for VF 16: {{.*}}ir<%valB> = load
+; SSE42: Cost of 24 for VF 2: REPLICATE ir<%valB> = load ir<%inB>
+; SSE42: Cost of 48 for VF 4: REPLICATE ir<%valB> = load ir<%inB>
+; SSE42: Cost of 96 for VF 8: REPLICATE ir<%valB> = load ir<%inB>
+; SSE42: Cost of 192 for VF 16: REPLICATE ir<%valB> = load ir<%inB>
;
; AVX1-LABEL: 'test'
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i8, ptr %inB, align 1
-; AVX1: Cost of 24 for VF 2: {{.*}}ir<%valB> = load
-; AVX1: Cost of 48 for VF 4: {{.*}}ir<%valB> = load
-; AVX1: Cost of 96 for VF 8: {{.*}}ir<%valB> = load
-; AVX1: Cost of 192 for VF 16: {{.*}}ir<%valB> = load
-; AVX1: Cost of 385 for VF 32: {{.*}}ir<%valB> = load
+; AVX1: Cost of 24 for VF 2: REPLICATE ir<%valB> = load ir<%inB>
+; AVX1: Cost of 48 for VF 4: REPLICATE ir<%valB> = load ir<%inB>
+; AVX1: Cost of 96 for VF 8: REPLICATE ir<%valB> = load ir<%inB>
+; AVX1: Cost of 192 for VF 16: REPLICATE ir<%valB> = load ir<%inB>
+; AVX1: Cost of 385 for VF 32: REPLICATE ir<%valB> = load ir<%inB>
;
; AVX2-SLOWGATHER-LABEL: 'test'
; AVX2-SLOWGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i8, ptr %inB, align 1
-; AVX2-SLOWGATHER: Cost of 4 for VF 2: {{.*}}ir<%valB> = load
-; AVX2-SLOWGATHER: Cost of 8 for VF 4: {{.*}}ir<%valB> = load
-; AVX2-SLOWGATHER: Cost of 16 for VF 8: {{.*}}ir<%valB> = load
-; AVX2-SLOWGATHER: Cost of 32 for VF 16: {{.*}}ir<%valB> = load
-; AVX2-SLOWGATHER: Cost of 65 for VF 32: {{.*}}ir<%valB> = load
+; AVX2-SLOWGATHER: Cost of 4 for VF 2: REPLICATE ir<%valB> = load ir<%inB>
+; AVX2-SLOWGATHER: Cost of 8 for VF 4: REPLICATE ir<%valB> = load ir<%inB>
+; AVX2-SLOWGATHER: Cost of 16 for VF 8: REPLICATE ir<%valB> = load ir<%inB>
+; AVX2-SLOWGATHER: Cost of 32 for VF 16: REPLICATE ir<%valB> = load ir<%inB>
+; AVX2-SLOWGATHER: Cost of 65 for VF 32: REPLICATE ir<%valB> = load ir<%inB>
;
; AVX2-FASTGATHER-LABEL: 'test'
; AVX2-FASTGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i8, ptr %inB, align 1
-; AVX2-FASTGATHER: Cost of 6 for VF 2: {{.*}}ir<%valB> = load
-; AVX2-FASTGATHER: Cost of 13 for VF 4: {{.*}}ir<%valB> = load
-; AVX2-FASTGATHER: Cost of 26 for VF 8: {{.*}}ir<%valB> = load
-; AVX2-FASTGATHER: Cost of 52 for VF 16: {{.*}}ir<%valB> = load
-; AVX2-FASTGATHER: Cost of 105 for VF 32: {{.*}}ir<%valB> = load
+; AVX2-FASTGATHER: Cost of 6 for VF 2: REPLICATE ir<%valB> = load ir<%inB>
+; AVX2-FASTGATHER: Cost of 13 for VF 4: REPLICATE ir<%valB> = load ir<%inB>
+; AVX2-FASTGATHER: Cost of 26 for VF 8: REPLICATE ir<%valB> = load ir<%inB>
+; AVX2-FASTGATHER: Cost of 52 for VF 16: REPLICATE ir<%valB> = load ir<%inB>
+; AVX2-FASTGATHER: Cost of 105 for VF 32: REPLICATE ir<%valB> = load ir<%inB>
;
; AVX512-LABEL: 'test'
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB = load i8, ptr %inB, align 1
-; AVX512: Cost of 6 for VF 2: {{.*}}ir<%valB> = load
-; AVX512: Cost of 13 for VF 4: {{.*}}ir<%valB> = load
-; AVX512: Cost of 27 for VF 8: {{.*}}ir<%valB> = load
-; AVX512: Cost of 54 for VF 16: {{.*}}ir<%valB> = load
-; AVX512: Cost of 109 for VF 32: {{.*}}ir<%valB> = load
-; AVX512: Cost of 219 for VF 64: {{.*}}ir<%valB> = load
+; AVX512: Cost of 6 for VF 2: REPLICATE ir<%valB> = load ir<%inB>
+; AVX512: Cost of 13 for VF 4: REPLICATE ir<%valB> = load ir<%inB>
+; AVX512: Cost of 27 for VF 8: REPLICATE ir<%valB> = load ir<%inB>
+; AVX512: Cost of 54 for VF 16: REPLICATE ir<%valB> = load ir<%inB>
+; AVX512: Cost of 109 for VF 32: REPLICATE ir<%valB> = load ir<%inB>
+; AVX512: Cost of 219 for VF 64: REPLICATE ir<%valB> = load ir<%inB>
;
entry:
br label %for.body
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/handle-iptr-with-data-layout-to-not-assert.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/handle-iptr-with-data-layout-to-not-assert.ll
index f6d2ff372d6bf..1147497d9982d 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/handle-iptr-with-data-layout-to-not-assert.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/handle-iptr-with-data-layout-to-not-assert.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*store ptr" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+ at" --version 5
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*store ptr" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+" --version 5
; REQUIRES: asserts
; RUN: opt -passes=loop-vectorize -debug-only=loop-vectorize -S < %s 2>&1 | FileCheck %s
target triple = "x86_64-unknown-linux-gnu"
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f32-stride-2.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f32-stride-2.ll
index a6f7e96bdd67f..3b3c3dcb78041 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f32-stride-2.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f32-stride-2.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+ at %v0,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f32-stride-3.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f32-stride-3.ll
index 6ae2d29de2793..2218048e47681 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f32-stride-3.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f32-stride-3.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+ at %v0,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f32-stride-4.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f32-stride-4.ll
index 26455e027af64..679ff5ecec952 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f32-stride-4.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f32-stride-4.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+ at %v0,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f32-stride-5.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f32-stride-5.ll
index cd9a59dbec852..31a1a91bdac59 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f32-stride-5.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f32-stride-5.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+ at %v0,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f32-stride-6.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f32-stride-6.ll
index ad8a602c02613..fd19eecd00445 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f32-stride-6.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f32-stride-6.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+ at %v0,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f32-stride-7.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f32-stride-7.ll
index 5ae2ff2dd178e..f0395dbb3bb89 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f32-stride-7.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f32-stride-7.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+ at %v0,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f32-stride-8.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f32-stride-8.ll
index 3f2d0acb07982..eafe9cfd912c4 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f32-stride-8.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f32-stride-8.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+ at %v0,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f64-stride-2.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f64-stride-2.ll
index 434789dc2157e..38fbf409100e8 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f64-stride-2.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f64-stride-2.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+ at %v0,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f64-stride-3.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f64-stride-3.ll
index da5095193ba22..51bc25a559fda 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f64-stride-3.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f64-stride-3.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+ at %v0,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f64-stride-4.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f64-stride-4.ll
index 2e7ae075f46f8..5f3c8a3f925e8 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f64-stride-4.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f64-stride-4.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+ at %v0,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f64-stride-5.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f64-stride-5.ll
index 07f860571331b..7d18d05a344a8 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f64-stride-5.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f64-stride-5.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+ at %v0,|REPLICATE ir<%v0> = load|WIDEN ir<%v[0-9]> = load)" --filter "^ ir<.* = load from index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+,|REPLICATE ir<%v0> = load|WIDEN ir<%v[0-9]> = load)" --filter "^ ir<.* = load from index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f64-stride-6.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f64-stride-6.ll
index 33892de8fd798..909e0a9c8ed18 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f64-stride-6.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f64-stride-6.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+ at %v0,|REPLICATE ir<%v0> = load|WIDEN ir<%v[0-9]> = load)" --filter "^ ir<.* = load from index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+,|REPLICATE ir<%v0> = load|WIDEN ir<%v[0-9]> = load)" --filter "^ ir<.* = load from index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f64-stride-7.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f64-stride-7.ll
index 0529174acd377..a9cef6bd260a1 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f64-stride-7.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f64-stride-7.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+ at %v0,|REPLICATE ir<%v0> = load|WIDEN ir<%v[0-9]> = load)" --filter "^ ir<.* = load from index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+,|REPLICATE ir<%v0> = load|WIDEN ir<%v[0-9]> = load)" --filter "^ ir<.* = load from index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f64-stride-8.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f64-stride-8.ll
index 10239f5264792..ba511ad467b1a 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f64-stride-8.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-f64-stride-8.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+ at %v0,|REPLICATE ir<%v0> = load|WIDEN ir<%v[0-9]> = load)" --filter "^ ir<.* = load from index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+,|REPLICATE ir<%v0> = load|WIDEN ir<%v[0-9]> = load)" --filter "^ ir<.* = load from index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-half.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-half.ll
index 748cb00270ba4..548825c8c5f93 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-half.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-half.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF 32: INTERLEAVE-GROUP with factor [0-9]+ at %0," --version 5
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF 32: INTERLEAVE-GROUP with factor [0-9]+, ir<%arrayidx>" --version 5
; RUN: opt -S -passes=loop-vectorize -debug-only=loop-vectorize -mattr=avx512fp16 %s 2>&1 | FileCheck %s
; REQUIRES: asserts
target datalayout = "e-m:e-p:32:32-f64:32:64-f80:32-n8:16:32-S128"
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i16-stride-2.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i16-stride-2.ll
index 4043e7f3294e4..acf9c541d9edf 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i16-stride-2.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i16-stride-2.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+ at %v0,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i16-stride-3.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i16-stride-3.ll
index 3c123b0dd8624..15baa2a627f23 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i16-stride-3.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i16-stride-3.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+ at %v0,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i16-stride-4.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i16-stride-4.ll
index 57e43282e972a..8ceb2529fed17 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i16-stride-4.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i16-stride-4.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+ at %v0,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i16-stride-5.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i16-stride-5.ll
index 084081357959a..66714ab44b62a 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i16-stride-5.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i16-stride-5.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+ at %v0,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i16-stride-6.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i16-stride-6.ll
index 2c745a7477351..65da1d5767c42 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i16-stride-6.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i16-stride-6.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+ at %v0,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i16-stride-7.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i16-stride-7.ll
index 1ae42766a6add..dcbf02f16f68d 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i16-stride-7.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i16-stride-7.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+ at %v0,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i16-stride-8.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i16-stride-8.ll
index 2181667cf5626..759f45629adf1 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i16-stride-8.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i16-stride-8.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+ at %v0,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-2-indices-0u.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-2-indices-0u.ll
index 7ac23631ad343..3d0e795d653a4 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-2-indices-0u.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-2-indices-0u.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+ at %v0,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-2.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-2.ll
index 5bbd77d88479e..302e0cb447d65 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-2.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-2.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+ at %v0,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-3-indices-01u.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-3-indices-01u.ll
index cae29abd23947..e843b716aa01b 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-3-indices-01u.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-3-indices-01u.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+ at %v0,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-3-indices-0uu.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-3-indices-0uu.ll
index cc1adf1698803..f40ad60dc6f3c 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-3-indices-0uu.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-3-indices-0uu.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+ at %v0,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-3.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-3.ll
index bb0ce149aed3f..c0de2fcacd412 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-3.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-3.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+ at %v0,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-4-indices-012u.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-4-indices-012u.ll
index e89f6ae781e69..41bd92713c386 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-4-indices-012u.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-4-indices-012u.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+ at %v0,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-4-indices-01uu.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-4-indices-01uu.ll
index bdc6334a6e84a..9a8ae47d51907 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-4-indices-01uu.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-4-indices-01uu.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+ at %v0,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-4-indices-0uuu.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-4-indices-0uuu.ll
index b8f2baeb7ccd1..d2e518a981de5 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-4-indices-0uuu.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-4-indices-0uuu.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+ at %v0,|REPLICATE ir<%v0> = load|WIDEN ir<%v[0-9]> = load)" --filter "^ ir<.* = load from index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+,|REPLICATE ir<%v0> = load|WIDEN ir<%v[0-9]> = load)" --filter "^ ir<.* = load from index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-4.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-4.ll
index f4ed289cc5c41..bd7a63609acde 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-4.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-4.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+ at %v0,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-5.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-5.ll
index 9668f9b51417c..cb315e61e57a2 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-5.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-5.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+ at %v0,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-6.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-6.ll
index 7a1cb1913417e..c916394a0c611 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-6.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-6.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+ at %v0,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-7.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-7.ll
index 0bbdd39f2ad66..0c2cc5f663ef3 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-7.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-7.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+ at %v0,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-8.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-8.ll
index 2b134fb879faa..c64076fca0d62 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-8.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i32-stride-8.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+ at %v0,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i64-stride-2.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i64-stride-2.ll
index 100ab85ddbb1e..d0a99efab706d 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i64-stride-2.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i64-stride-2.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+ at %v0,|REPLICATE ir<%v0> = load|WIDEN ir<%v[0-9]> = load)" --filter "^ ir<.* = load from index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+,|REPLICATE ir<%v0> = load|WIDEN ir<%v[0-9]> = load)" --filter "^ ir<.* = load from index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i64-stride-3.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i64-stride-3.ll
index ffaca321e9d49..17cc63d11eb40 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i64-stride-3.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i64-stride-3.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+ at %v0,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i64-stride-4.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i64-stride-4.ll
index a8d8edf1c8755..180ef142675f5 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i64-stride-4.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i64-stride-4.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+ at %v0,|REPLICATE ir<%v0> = load|WIDEN ir<%v[0-9]> = load)" --filter "^ ir<.* = load from index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+,|REPLICATE ir<%v0> = load|WIDEN ir<%v[0-9]> = load)" --filter "^ ir<.* = load from index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i64-stride-5.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i64-stride-5.ll
index 6877858a4a95c..65a27fc96f223 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i64-stride-5.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i64-stride-5.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+ at %v0,|REPLICATE ir<%v0> = load|WIDEN ir<%v[0-9]> = load)" --filter "^ ir<.* = load from index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+,|REPLICATE ir<%v0> = load|WIDEN ir<%v[0-9]> = load)" --filter "^ ir<.* = load from index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i64-stride-6.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i64-stride-6.ll
index 4146b8906fb21..d261e5242f8d8 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i64-stride-6.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i64-stride-6.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+ at %v0,|REPLICATE ir<%v0> = load|WIDEN ir<%v[0-9]> = load)" --filter "^ ir<.* = load from index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+,|REPLICATE ir<%v0> = load|WIDEN ir<%v[0-9]> = load)" --filter "^ ir<.* = load from index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i64-stride-7.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i64-stride-7.ll
index aa454516641ab..04c8db7a58357 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i64-stride-7.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i64-stride-7.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+ at %v0,|REPLICATE ir<%v0> = load|WIDEN ir<%v[0-9]> = load)" --filter "^ ir<.* = load from index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+,|REPLICATE ir<%v0> = load|WIDEN ir<%v[0-9]> = load)" --filter "^ ir<.* = load from index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i64-stride-8.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i64-stride-8.ll
index edef781eae4a2..a2b5d1c4df2f8 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i64-stride-8.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i64-stride-8.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+ at %v0,|REPLICATE ir<%v0> = load|WIDEN ir<%v[0-9]> = load)" --filter "^ ir<.* = load from index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+,|REPLICATE ir<%v0> = load|WIDEN ir<%v[0-9]> = load)" --filter "^ ir<.* = load from index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i8-stride-2.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i8-stride-2.ll
index 03f9fb7c8f1bf..f6f057ca88ca6 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i8-stride-2.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i8-stride-2.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+ at %v0,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i8-stride-3.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i8-stride-3.ll
index e1f737a2b9879..e3224b8938f7c 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i8-stride-3.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i8-stride-3.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+ at %v0,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i8-stride-4.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i8-stride-4.ll
index b92e9fe280a4d..13f02ae479c41 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i8-stride-4.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i8-stride-4.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+ at %v0,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i8-stride-5.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i8-stride-5.ll
index 1ecfd6ba6e574..3d887cb7958a9 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i8-stride-5.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i8-stride-5.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+ at %v0,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i8-stride-6.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i8-stride-6.ll
index 74af7dd09d76d..a2f22da5d7a4d 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i8-stride-6.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i8-stride-6.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+ at %v0,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i8-stride-7.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i8-stride-7.ll
index 71ffdb2e47534..d9d66e5b89598 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i8-stride-7.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i8-stride-7.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+ at %v0,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i8-stride-8.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i8-stride-8.ll
index 36ad28d25ec31..11bcbd083c59f 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i8-stride-8.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-load-i8-stride-8.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+ at %v0,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%v0 = load" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+,|REPLICATE ir<%v0> = load)" --filter "^ ir<.* = load from index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f32-stride-2.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f32-stride-2.ll
index b88c006d5b916..5e671d92251fd 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f32-stride-2.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f32-stride-2.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+ at .*, ir<%out" --filter "^ store ir<.* to index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+, ir<%out" --filter "^ store ir<.* to index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f32-stride-3.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f32-stride-3.ll
index 8c69a21d68ac1..8ee08dd0ad029 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f32-stride-3.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f32-stride-3.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+ at .*, ir<%out" --filter "^ store ir<.* to index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+, ir<%out" --filter "^ store ir<.* to index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f32-stride-4.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f32-stride-4.ll
index 1df640056a381..20eede302fb17 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f32-stride-4.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f32-stride-4.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+ at .*, ir<%out" --filter "^ store ir<.* to index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+, ir<%out" --filter "^ store ir<.* to index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f32-stride-5.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f32-stride-5.ll
index 529d0cc66c0a8..b543d3aa3a9f2 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f32-stride-5.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f32-stride-5.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+ at .*, ir<%out" --filter "^ store ir<.* to index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+, ir<%out" --filter "^ store ir<.* to index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f32-stride-6.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f32-stride-6.ll
index ad932cb745d3d..b63eacad4dcae 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f32-stride-6.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f32-stride-6.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+ at .*, ir<%out" --filter "^ store ir<.* to index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+, ir<%out" --filter "^ store ir<.* to index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f32-stride-7.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f32-stride-7.ll
index 8cf14921a6d6c..77026e28385a1 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f32-stride-7.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f32-stride-7.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+ at .*, ir<%out" --filter "^ store ir<.* to index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+, ir<%out" --filter "^ store ir<.* to index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f32-stride-8.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f32-stride-8.ll
index 1a69cf3b9b6d0..8d813d73120cb 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f32-stride-8.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f32-stride-8.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+ at .*, ir<%out" --filter "^ store ir<.* to index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+, ir<%out" --filter "^ store ir<.* to index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f64-stride-2.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f64-stride-2.ll
index 14c8628f6ba6c..dd48b126e93fc 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f64-stride-2.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f64-stride-2.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+ at .*, ir<%out" --filter "^ store ir<.* to index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+, ir<%out" --filter "^ store ir<.* to index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f64-stride-3.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f64-stride-3.ll
index 5322bfb06ff37..422fc05ba6837 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f64-stride-3.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f64-stride-3.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+ at .*, ir<%out" --filter "^ store ir<.* to index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+, ir<%out" --filter "^ store ir<.* to index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f64-stride-4.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f64-stride-4.ll
index 2a993d7a48b2c..9799b132c3697 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f64-stride-4.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f64-stride-4.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+ at .*, ir<%out" --filter "^ store ir<.* to index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+, ir<%out" --filter "^ store ir<.* to index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f64-stride-5.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f64-stride-5.ll
index 1461d2678fe24..dd5d956fac90c 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f64-stride-5.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f64-stride-5.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+ at .*, ir<%out" --filter "^ store ir<.* to index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+, ir<%out" --filter "^ store ir<.* to index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f64-stride-6.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f64-stride-6.ll
index 78715dbe67a96..74901d8a58f9c 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f64-stride-6.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f64-stride-6.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+ at .*, ir<%out" --filter "^ store ir<.* to index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+, ir<%out" --filter "^ store ir<.* to index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f64-stride-7.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f64-stride-7.ll
index b55ed5aa39f53..eeeebd43de354 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f64-stride-7.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-f64-stride-7.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+ at .*, ir<%out" --filter "^ store ir<.* to index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+, ir<%out" --filter "^ store ir<.* to index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i16-stride-2.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i16-stride-2.ll
index 13f19f309a33b..6660cbe0de210 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i16-stride-2.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i16-stride-2.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+ at .*, ir<%out" --filter "^ store ir<.* to index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+, ir<%out" --filter "^ store ir<.* to index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i16-stride-3.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i16-stride-3.ll
index 27e18adae35c7..4d88e76efacfb 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i16-stride-3.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i16-stride-3.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+ at .*, ir<%out" --filter "^ store ir<.* to index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+, ir<%out" --filter "^ store ir<.* to index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i16-stride-4.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i16-stride-4.ll
index 65836c4b9aa00..2df9e5090bbfc 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i16-stride-4.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i16-stride-4.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+ at .*, ir<%out" --filter "^ store ir<.* to index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+, ir<%out" --filter "^ store ir<.* to index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i16-stride-5.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i16-stride-5.ll
index 5772647e530a8..b2f3be8075635 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i16-stride-5.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i16-stride-5.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+ at .*, ir<%out" --filter "^ store ir<.* to index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+, ir<%out" --filter "^ store ir<.* to index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i16-stride-6.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i16-stride-6.ll
index b07588c1a9ee6..f6d703f6f854f 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i16-stride-6.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i16-stride-6.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+ at .*, ir<%out" --filter "^ store ir<.* to index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+, ir<%out" --filter "^ store ir<.* to index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i16-stride-7.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i16-stride-7.ll
index da11dd4ad9de1..710e2498bd30c 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i16-stride-7.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i16-stride-7.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+ at .*, ir<%out" --filter "^ store ir<.* to index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+, ir<%out" --filter "^ store ir<.* to index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i16-stride-8.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i16-stride-8.ll
index 023dee8edc1da..df755a8fb5cf9 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i16-stride-8.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i16-stride-8.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+ at .*, ir<%out" --filter "^ store ir<.* to index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+, ir<%out" --filter "^ store ir<.* to index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i32-stride-2.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i32-stride-2.ll
index 36b78e9309b8c..02e51ed1ebde1 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i32-stride-2.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i32-stride-2.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+ at .*, ir<%out" --filter "^ store ir<.* to index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+, ir<%out" --filter "^ store ir<.* to index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i32-stride-3.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i32-stride-3.ll
index 6ec5d91c81ace..936718168e4c7 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i32-stride-3.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i32-stride-3.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+ at .*, ir<%out" --filter "^ store ir<.* to index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+, ir<%out" --filter "^ store ir<.* to index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i32-stride-4.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i32-stride-4.ll
index 56fb08a98c7fb..0ab2aa4565e24 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i32-stride-4.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i32-stride-4.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+ at .*, ir<%out" --filter "^ store ir<.* to index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+, ir<%out" --filter "^ store ir<.* to index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i32-stride-5.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i32-stride-5.ll
index 914c82ead3aa7..d99016eaaee3c 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i32-stride-5.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i32-stride-5.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+ at .*, ir<%out" --filter "^ store ir<.* to index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+, ir<%out" --filter "^ store ir<.* to index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i32-stride-6.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i32-stride-6.ll
index bc27a61100d3b..d49f096bfe4d4 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i32-stride-6.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i32-stride-6.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+ at .*, ir<%out" --filter "^ store ir<.* to index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+, ir<%out" --filter "^ store ir<.* to index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i32-stride-7.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i32-stride-7.ll
index f20448c0f1f93..6322dbb3ff19f 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i32-stride-7.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i32-stride-7.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+ at .*, ir<%out" --filter "^ store ir<.* to index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+, ir<%out" --filter "^ store ir<.* to index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i32-stride-8.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i32-stride-8.ll
index e56dfff45bbbb..506aaab0951e4 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i32-stride-8.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i32-stride-8.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+ at .*, ir<%out" --filter "^ store ir<.* to index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+, ir<%out" --filter "^ store ir<.* to index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i64-stride-2.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i64-stride-2.ll
index 6a8332c593228..2968cf83f4b5c 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i64-stride-2.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i64-stride-2.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+ at .*, ir<%out" --filter "^ store ir<.* to index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+, ir<%out" --filter "^ store ir<.* to index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i64-stride-3.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i64-stride-3.ll
index 209af72e22ba5..8c1340772e812 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i64-stride-3.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i64-stride-3.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+ at .*, ir<%out" --filter "^ store ir<.* to index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+, ir<%out" --filter "^ store ir<.* to index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i64-stride-4.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i64-stride-4.ll
index 3dfcb6de22c77..805a50527749a 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i64-stride-4.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i64-stride-4.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+ at .*, ir<%out" --filter "^ store ir<.* to index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+, ir<%out" --filter "^ store ir<.* to index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i64-stride-5.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i64-stride-5.ll
index 523c885bc015c..b8a81a88c16a1 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i64-stride-5.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i64-stride-5.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+ at .*, ir<%out" --filter "^ store ir<.* to index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+, ir<%out" --filter "^ store ir<.* to index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i64-stride-6.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i64-stride-6.ll
index b9c688b07304b..a43e1ddb52aac 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i64-stride-6.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i64-stride-6.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+ at .*, ir<%out" --filter "^ store ir<.* to index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+, ir<%out" --filter "^ store ir<.* to index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i64-stride-7.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i64-stride-7.ll
index c4805ed4c7e01..ef46173435b29 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i64-stride-7.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i64-stride-7.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+ at .*, ir<%out" --filter "^ store ir<.* to index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+, ir<%out" --filter "^ store ir<.* to index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i64-stride-8.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i64-stride-8.ll
index d90077f6c37c9..6e808e99d351f 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i64-stride-8.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i64-stride-8.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*store i64 %v\., ptr %out" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+ at <badref>,|WIDEN store|REPLICATE store ir<%v\.>)" --filter "^ store ir<%v.?> to index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*store i64 %v\., ptr %out" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (INTERLEAVE-GROUP with factor [0-9]+, ir<%out0>|WIDEN store|REPLICATE store ir<%v\.>)" --filter "^ store ir<%v.?> to index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i8-stride-2.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i8-stride-2.ll
index b9f7c958f1178..f2c4c2367c2a6 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i8-stride-2.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i8-stride-2.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+ at .*, ir<%out" --filter "^ store ir<.* to index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+, ir<%out" --filter "^ store ir<.* to index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i8-stride-3.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i8-stride-3.ll
index af79906323121..3b161e1b6d29d 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i8-stride-3.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i8-stride-3.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+ at .*, ir<%out" --filter "^ store ir<.* to index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+, ir<%out" --filter "^ store ir<.* to index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i8-stride-4.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i8-stride-4.ll
index af0e22aa2130e..17502dc88dbce 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i8-stride-4.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i8-stride-4.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+ at .*, ir<%out" --filter "^ store ir<.* to index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+, ir<%out" --filter "^ store ir<.* to index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i8-stride-5.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i8-stride-5.ll
index 14c99e33e8356..63b6ea1820287 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i8-stride-5.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i8-stride-5.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+ at .*, ir<%out" --filter "^ store ir<.* to index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+, ir<%out" --filter "^ store ir<.* to index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i8-stride-6.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i8-stride-6.ll
index 85ce63cae0054..cc6adf535d6e0 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i8-stride-6.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i8-stride-6.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+ at .*, ir<%out" --filter "^ store ir<.* to index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+, ir<%out" --filter "^ store ir<.* to index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i8-stride-7.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i8-stride-7.ll
index 6c59a632eba6b..f64132db3b707 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i8-stride-7.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i8-stride-7.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+ at .*, ir<%out" --filter "^ store ir<.* to index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+, ir<%out" --filter "^ store ir<.* to index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i8-stride-8.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i8-stride-8.ll
index 7ea721d5abc50..7a340ef1fbc3e 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i8-stride-8.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/interleaved-store-i8-stride-8.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+ at .*, ir<%out" --filter "^ store ir<.* to index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP with factor [0-9]+, ir<%out" --filter "^ store ir<.* to index"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=AVX2
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-gather-i32-with-i8-index.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-gather-i32-with-i8-index.ll
index 1433c2ad35dcc..8f5da77027970 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-gather-i32-with-i8-index.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-gather-i32-with-i8-index.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF [0-9]+ For instruction:\s*%valB.loaded = load i32, ptr %inB, align 4"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF [0-9]+ For instruction:\s*%valB.loaded = load i32, ptr %inB, align 4" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: .* ir<%valB.loaded> = load"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=SSE
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse4.2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=SSE
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=AVX1
@@ -18,43 +18,43 @@ target triple = "x86_64-unknown-linux-gnu"
define void @test() {
; SSE-LABEL: 'test'
; SSE: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i32, ptr %inB, align 4
-; SSE: Cost of 3000000 for VF 2: {{.*}}ir<%valB.loaded> = load
-; SSE: Cost of 3000000 for VF 4: {{.*}}ir<%valB.loaded> = load
-; SSE: Cost of 3000000 for VF 8: {{.*}}ir<%valB.loaded> = load
-; SSE: Cost of 3000000 for VF 16: {{.*}}ir<%valB.loaded> = load
+; SSE: Cost of 3000000 for VF 2: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
+; SSE: Cost of 3000000 for VF 4: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
+; SSE: Cost of 3000000 for VF 8: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
+; SSE: Cost of 3000000 for VF 16: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
;
; AVX1-LABEL: 'test'
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i32, ptr %inB, align 4
-; AVX1: Cost of 3000000 for VF 2: {{.*}}ir<%valB.loaded> = load
-; AVX1: Cost of 3000000 for VF 4: {{.*}}ir<%valB.loaded> = load
-; AVX1: Cost of 3000000 for VF 8: {{.*}}ir<%valB.loaded> = load
-; AVX1: Cost of 3000000 for VF 16: {{.*}}ir<%valB.loaded> = load
-; AVX1: Cost of 3000000 for VF 32: {{.*}}ir<%valB.loaded> = load
+; AVX1: Cost of 3000000 for VF 2: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
+; AVX1: Cost of 3000000 for VF 4: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
+; AVX1: Cost of 3000000 for VF 8: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
+; AVX1: Cost of 3000000 for VF 16: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
+; AVX1: Cost of 3000000 for VF 32: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
;
; AVX2-SLOWGATHER-LABEL: 'test'
; AVX2-SLOWGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i32, ptr %inB, align 4
-; AVX2-SLOWGATHER: Cost of 3000000 for VF 2: {{.*}}ir<%valB.loaded> = load
-; AVX2-SLOWGATHER: Cost of 3000000 for VF 4: {{.*}}ir<%valB.loaded> = load
-; AVX2-SLOWGATHER: Cost of 3000000 for VF 8: {{.*}}ir<%valB.loaded> = load
-; AVX2-SLOWGATHER: Cost of 3000000 for VF 16: {{.*}}ir<%valB.loaded> = load
-; AVX2-SLOWGATHER: Cost of 3000000 for VF 32: {{.*}}ir<%valB.loaded> = load
+; AVX2-SLOWGATHER: Cost of 3000000 for VF 2: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
+; AVX2-SLOWGATHER: Cost of 3000000 for VF 4: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
+; AVX2-SLOWGATHER: Cost of 3000000 for VF 8: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
+; AVX2-SLOWGATHER: Cost of 3000000 for VF 16: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
+; AVX2-SLOWGATHER: Cost of 3000000 for VF 32: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
;
; AVX2-FASTGATHER-LABEL: 'test'
; AVX2-FASTGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i32, ptr %inB, align 4
-; AVX2-FASTGATHER: Cost of 4 for VF 2: {{.*}}ir<%valB.loaded> = load
-; AVX2-FASTGATHER: Cost of 6 for VF 4: {{.*}}ir<%valB.loaded> = load
-; AVX2-FASTGATHER: Cost of 12 for VF 8: {{.*}}ir<%valB.loaded> = load
-; AVX2-FASTGATHER: Cost of 24 for VF 16: {{.*}}ir<%valB.loaded> = load
-; AVX2-FASTGATHER: Cost of 48 for VF 32: {{.*}}ir<%valB.loaded> = load
+; AVX2-FASTGATHER: Cost of 4 for VF 2: WIDEN ir<%valB.loaded> = load ir<%inB>, ir<%canLoad>
+; AVX2-FASTGATHER: Cost of 6 for VF 4: WIDEN ir<%valB.loaded> = load ir<%inB>, ir<%canLoad>
+; AVX2-FASTGATHER: Cost of 12 for VF 8: WIDEN ir<%valB.loaded> = load ir<%inB>, ir<%canLoad>
+; AVX2-FASTGATHER: Cost of 24 for VF 16: WIDEN ir<%valB.loaded> = load ir<%inB>, ir<%canLoad>
+; AVX2-FASTGATHER: Cost of 48 for VF 32: WIDEN ir<%valB.loaded> = load ir<%inB>, ir<%canLoad>
;
; AVX512-LABEL: 'test'
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i32, ptr %inB, align 4
-; AVX512: Cost of 8 for VF 2: {{.*}}ir<%valB.loaded> = load
-; AVX512: Cost of 17 for VF 4: {{.*}}ir<%valB.loaded> = load
-; AVX512: Cost of 10 for VF 8: {{.*}}ir<%valB.loaded> = load
-; AVX512: Cost of 18 for VF 16: {{.*}}ir<%valB.loaded> = load
-; AVX512: Cost of 36 for VF 32: {{.*}}ir<%valB.loaded> = load
-; AVX512: Cost of 72 for VF 64: {{.*}}ir<%valB.loaded> = load
+; AVX512: Cost of 8 for VF 2: WIDEN ir<%valB.loaded> = load ir<%inB>, ir<%canLoad>
+; AVX512: Cost of 17 for VF 4: WIDEN ir<%valB.loaded> = load ir<%inB>, ir<%canLoad>
+; AVX512: Cost of 10 for VF 8: WIDEN ir<%valB.loaded> = load ir<%inB>, ir<%canLoad>
+; AVX512: Cost of 18 for VF 16: WIDEN ir<%valB.loaded> = load ir<%inB>, ir<%canLoad>
+; AVX512: Cost of 36 for VF 32: WIDEN ir<%valB.loaded> = load ir<%inB>, ir<%canLoad>
+; AVX512: Cost of 72 for VF 64: WIDEN ir<%valB.loaded> = load ir<%inB>, ir<%canLoad>
;
entry:
br label %for.body
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-gather-i64-with-i8-index.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-gather-i64-with-i8-index.ll
index be49e2198052e..6801a549e19c4 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-gather-i64-with-i8-index.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-gather-i64-with-i8-index.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF [0-9]+ For instruction:\s*%valB.loaded = load i64, ptr %inB, align 8"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF [0-9]+ For instruction:\s*%valB.loaded = load i64, ptr %inB, align 8" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: .* ir<%valB.loaded> = load"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=SSE
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse4.2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=SSE
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=AVX1
@@ -18,43 +18,43 @@ target triple = "x86_64-unknown-linux-gnu"
define void @test() {
; SSE-LABEL: 'test'
; SSE: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i64, ptr %inB, align 8
-; SSE: Cost of 3000000 for VF 2: {{.*}}ir<%valB.loaded> = load
-; SSE: Cost of 3000000 for VF 4: {{.*}}ir<%valB.loaded> = load
-; SSE: Cost of 3000000 for VF 8: {{.*}}ir<%valB.loaded> = load
-; SSE: Cost of 3000000 for VF 16: {{.*}}ir<%valB.loaded> = load
+; SSE: Cost of 3000000 for VF 2: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
+; SSE: Cost of 3000000 for VF 4: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
+; SSE: Cost of 3000000 for VF 8: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
+; SSE: Cost of 3000000 for VF 16: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
;
; AVX1-LABEL: 'test'
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i64, ptr %inB, align 8
-; AVX1: Cost of 3000000 for VF 2: {{.*}}ir<%valB.loaded> = load
-; AVX1: Cost of 3000000 for VF 4: {{.*}}ir<%valB.loaded> = load
-; AVX1: Cost of 3000000 for VF 8: {{.*}}ir<%valB.loaded> = load
-; AVX1: Cost of 3000000 for VF 16: {{.*}}ir<%valB.loaded> = load
-; AVX1: Cost of 3000000 for VF 32: {{.*}}ir<%valB.loaded> = load
+; AVX1: Cost of 3000000 for VF 2: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
+; AVX1: Cost of 3000000 for VF 4: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
+; AVX1: Cost of 3000000 for VF 8: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
+; AVX1: Cost of 3000000 for VF 16: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
+; AVX1: Cost of 3000000 for VF 32: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
;
; AVX2-SLOWGATHER-LABEL: 'test'
; AVX2-SLOWGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i64, ptr %inB, align 8
-; AVX2-SLOWGATHER: Cost of 3000000 for VF 2: {{.*}}ir<%valB.loaded> = load
-; AVX2-SLOWGATHER: Cost of 3000000 for VF 4: {{.*}}ir<%valB.loaded> = load
-; AVX2-SLOWGATHER: Cost of 3000000 for VF 8: {{.*}}ir<%valB.loaded> = load
-; AVX2-SLOWGATHER: Cost of 3000000 for VF 16: {{.*}}ir<%valB.loaded> = load
-; AVX2-SLOWGATHER: Cost of 3000000 for VF 32: {{.*}}ir<%valB.loaded> = load
+; AVX2-SLOWGATHER: Cost of 3000000 for VF 2: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
+; AVX2-SLOWGATHER: Cost of 3000000 for VF 4: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
+; AVX2-SLOWGATHER: Cost of 3000000 for VF 8: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
+; AVX2-SLOWGATHER: Cost of 3000000 for VF 16: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
+; AVX2-SLOWGATHER: Cost of 3000000 for VF 32: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
;
; AVX2-FASTGATHER-LABEL: 'test'
; AVX2-FASTGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i64, ptr %inB, align 8
-; AVX2-FASTGATHER: Cost of 4 for VF 2: {{.*}}ir<%valB.loaded> = load
-; AVX2-FASTGATHER: Cost of 6 for VF 4: {{.*}}ir<%valB.loaded> = load
-; AVX2-FASTGATHER: Cost of 12 for VF 8: {{.*}}ir<%valB.loaded> = load
-; AVX2-FASTGATHER: Cost of 24 for VF 16: {{.*}}ir<%valB.loaded> = load
-; AVX2-FASTGATHER: Cost of 48 for VF 32: {{.*}}ir<%valB.loaded> = load
+; AVX2-FASTGATHER: Cost of 4 for VF 2: WIDEN ir<%valB.loaded> = load ir<%inB>, ir<%canLoad>
+; AVX2-FASTGATHER: Cost of 6 for VF 4: WIDEN ir<%valB.loaded> = load ir<%inB>, ir<%canLoad>
+; AVX2-FASTGATHER: Cost of 12 for VF 8: WIDEN ir<%valB.loaded> = load ir<%inB>, ir<%canLoad>
+; AVX2-FASTGATHER: Cost of 24 for VF 16: WIDEN ir<%valB.loaded> = load ir<%inB>, ir<%canLoad>
+; AVX2-FASTGATHER: Cost of 48 for VF 32: WIDEN ir<%valB.loaded> = load ir<%inB>, ir<%canLoad>
;
; AVX512-LABEL: 'test'
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i64, ptr %inB, align 8
-; AVX512: Cost of 8 for VF 2: {{.*}}ir<%valB.loaded> = load
-; AVX512: Cost of 18 for VF 4: {{.*}}ir<%valB.loaded> = load
-; AVX512: Cost of 10 for VF 8: {{.*}}ir<%valB.loaded> = load
-; AVX512: Cost of 20 for VF 16: {{.*}}ir<%valB.loaded> = load
-; AVX512: Cost of 40 for VF 32: {{.*}}ir<%valB.loaded> = load
-; AVX512: Cost of 80 for VF 64: {{.*}}ir<%valB.loaded> = load
+; AVX512: Cost of 8 for VF 2: WIDEN ir<%valB.loaded> = load ir<%inB>, ir<%canLoad>
+; AVX512: Cost of 18 for VF 4: WIDEN ir<%valB.loaded> = load ir<%inB>, ir<%canLoad>
+; AVX512: Cost of 10 for VF 8: WIDEN ir<%valB.loaded> = load ir<%inB>, ir<%canLoad>
+; AVX512: Cost of 20 for VF 16: WIDEN ir<%valB.loaded> = load ir<%inB>, ir<%canLoad>
+; AVX512: Cost of 40 for VF 32: WIDEN ir<%valB.loaded> = load ir<%inB>, ir<%canLoad>
+; AVX512: Cost of 80 for VF 64: WIDEN ir<%valB.loaded> = load ir<%inB>, ir<%canLoad>
;
entry:
br label %for.body
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-interleaved-load-i16.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-interleaved-load-i16.ll
index af9bd7c7f4e5b..d14260279e17f 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-interleaved-load-i16.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-interleaved-load-i16.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%i[2,4] = load i16, ptr %[a-zA-Z0-7]+, align 2" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (REPLICATE ir<%i[24]> = load|INTERLEAVE-GROUP with factor [0-9]+ at %i[24])" --filter "^ ir<.* = load from index"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*%i[2,4] = load i16, ptr %[a-zA-Z0-7]+, align 2" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: (REPLICATE ir<%i[24]> = load|INTERLEAVE-GROUP with factor [0-9]+)" --filter "^ ir<.* = load from index"
; RUN: opt -passes=loop-vectorize -enable-interleaved-mem-accesses -tail-folding-policy=must-fold-tail -S -mcpu=skx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=DISABLED_MASKED_STRIDED
; RUN: opt -passes=loop-vectorize -enable-interleaved-mem-accesses -enable-masked-interleaved-mem-accesses -tail-folding-policy=must-fold-tail -S -mcpu=skx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=ENABLED_MASKED_STRIDED
; REQUIRES: asserts
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-interleaved-store-i16.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-interleaved-store-i16.ll
index 5f561b4403fba..c2e4cebc9aae6 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-interleaved-store-i16.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-interleaved-store-i16.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*store i16 %[0,2], ptr %[a-zA-Z0-7]+, align 2" --filter "Cost of [1-9][0-9]*(.[0-9]+)? for VF [0-9]+: (profitable to scalarize\s+store i16 %[02]|REPLICATE store ir<%[02]>|INTERLEAVE-GROUP with factor [0-9]+ at <badref>)"
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*store i16 %[0,2], ptr %[a-zA-Z0-7]+, align 2" --filter "Cost of [1-9][0-9]*(.[0-9]+)? for VF [0-9]+: (profitable to scalarize\s+store i16 %[02]|REPLICATE store ir<%[02]>|INTERLEAVE-GROUP with factor [0-9]+)"
; RUN: opt -passes=loop-vectorize -enable-interleaved-mem-accesses -tail-folding-policy=must-fold-tail -S -mcpu=skx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=DISABLED_MASKED_STRIDED
; RUN: opt -passes=loop-vectorize -enable-interleaved-mem-accesses -enable-masked-interleaved-mem-accesses -tail-folding-policy=must-fold-tail -S -mcpu=skx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefix=ENABLED_MASKED_STRIDED
; REQUIRES: asserts
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-load-i16.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-load-i16.ll
index f6f11624ad7e9..9cb0e482da47c 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-load-i16.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-load-i16.ll
@@ -1,10 +1,10 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF [0-9]+ For instruction:\s*%valB.loaded = load i16, ptr %inB, align 2"
-; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=SSE
-; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse4.2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=SSE
-; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=AVX1
-; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,-fast-gather --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=AVX2
-; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,+fast-gather --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=AVX2
-; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx512bw --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=AVX512
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF [0-9]+ For instruction:\s*%valB.loaded = load i16, ptr %inB, align 2" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: .* ir<%valB.loaded> = load"
+; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output -vplan-print-metadata=false < %s 2>&1 | FileCheck %s --check-prefixes=SSE
+; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse4.2 --debug-only=loop-vectorize --disable-output -vplan-print-metadata=false < %s 2>&1 | FileCheck %s --check-prefixes=SSE
+; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output -vplan-print-metadata=false < %s 2>&1 | FileCheck %s --check-prefixes=AVX1
+; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,-fast-gather --debug-only=loop-vectorize --disable-output -vplan-print-metadata=false < %s 2>&1 | FileCheck %s --check-prefixes=AVX2
+; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,+fast-gather --debug-only=loop-vectorize --disable-output -vplan-print-metadata=false < %s 2>&1 | FileCheck %s --check-prefixes=AVX2
+; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx512bw --debug-only=loop-vectorize --disable-output -vplan-print-metadata=false < %s 2>&1 | FileCheck %s --check-prefixes=AVX512
; REQUIRES: asserts
@@ -17,35 +17,35 @@ target triple = "x86_64-unknown-linux-gnu"
define void @test(ptr %B) {
; SSE-LABEL: 'test'
; SSE: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i16, ptr %inB, align 2
-; SSE: Cost of 3000000 for VF 2: {{.*}}ir<%valB.loaded> = load
-; SSE: Cost of 3000000 for VF 4: {{.*}}ir<%valB.loaded> = load
-; SSE: Cost of 3000000 for VF 8: {{.*}}ir<%valB.loaded> = load
-; SSE: Cost of 3000000 for VF 16: {{.*}}ir<%valB.loaded> = load
+; SSE: Cost of 3000000 for VF 2: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
+; SSE: Cost of 3000000 for VF 4: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
+; SSE: Cost of 3000000 for VF 8: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
+; SSE: Cost of 3000000 for VF 16: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
;
; AVX1-LABEL: 'test'
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i16, ptr %inB, align 2
-; AVX1: Cost of 3000000 for VF 2: {{.*}}ir<%valB.loaded> = load
-; AVX1: Cost of 3000000 for VF 4: {{.*}}ir<%valB.loaded> = load
-; AVX1: Cost of 3000000 for VF 8: {{.*}}ir<%valB.loaded> = load
-; AVX1: Cost of 3000000 for VF 16: {{.*}}ir<%valB.loaded> = load
-; AVX1: Cost of 3000000 for VF 32: {{.*}}ir<%valB.loaded> = load
+; AVX1: Cost of 3000000 for VF 2: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
+; AVX1: Cost of 3000000 for VF 4: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
+; AVX1: Cost of 3000000 for VF 8: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
+; AVX1: Cost of 3000000 for VF 16: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
+; AVX1: Cost of 3000000 for VF 32: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
;
; AVX2-LABEL: 'test'
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i16, ptr %inB, align 2
-; AVX2: Cost of 3000000 for VF 2: {{.*}}ir<%valB.loaded> = load
-; AVX2: Cost of 3000000 for VF 4: {{.*}}ir<%valB.loaded> = load
-; AVX2: Cost of 3000000 for VF 8: {{.*}}ir<%valB.loaded> = load
-; AVX2: Cost of 3000000 for VF 16: {{.*}}ir<%valB.loaded> = load
-; AVX2: Cost of 3000000 for VF 32: {{.*}}ir<%valB.loaded> = load
+; AVX2: Cost of 3000000 for VF 2: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
+; AVX2: Cost of 3000000 for VF 4: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
+; AVX2: Cost of 3000000 for VF 8: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
+; AVX2: Cost of 3000000 for VF 16: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
+; AVX2: Cost of 3000000 for VF 32: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
;
; AVX512-LABEL: 'test'
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i16, ptr %inB, align 2
-; AVX512: Cost of 2 for VF 2: {{.*}}ir<%valB.loaded> = load
-; AVX512: Cost of 2 for VF 4: {{.*}}ir<%valB.loaded> = load
-; AVX512: Cost of 1 for VF 8: {{.*}}ir<%valB.loaded> = load
-; AVX512: Cost of 1 for VF 16: {{.*}}ir<%valB.loaded> = load
-; AVX512: Cost of 1 for VF 32: {{.*}}ir<%valB.loaded> = load
-; AVX512: Cost of 2 for VF 64: {{.*}}ir<%valB.loaded> = load
+; AVX512: Cost of 2 for VF 2: WIDEN ir<%valB.loaded> = load vp<[[VP6:%[0-9]+]]>, ir<%canLoad>
+; AVX512: Cost of 2 for VF 4: WIDEN ir<%valB.loaded> = load vp<[[VP6]]>, ir<%canLoad>
+; AVX512: Cost of 1 for VF 8: WIDEN ir<%valB.loaded> = load vp<[[VP6]]>, ir<%canLoad>
+; AVX512: Cost of 1 for VF 16: WIDEN ir<%valB.loaded> = load vp<[[VP6]]>, ir<%canLoad>
+; AVX512: Cost of 1 for VF 32: WIDEN ir<%valB.loaded> = load vp<[[VP6]]>, ir<%canLoad>
+; AVX512: Cost of 2 for VF 64: WIDEN ir<%valB.loaded> = load vp<[[VP6]]>, ir<%canLoad>
;
entry:
br label %for.body
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-load-i32.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-load-i32.ll
index 6295588ebb07f..fc42ce6e6f73f 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-load-i32.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-load-i32.ll
@@ -1,10 +1,10 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF [0-9]+ For instruction:\s*%valB.loaded = load i32, ptr %inB, align 4"
-; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=SSE
-; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse4.2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=SSE
-; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=AVX1
-; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,-fast-gather --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=AVX2
-; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,+fast-gather --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=AVX2
-; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx512bw --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=AVX512
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF [0-9]+ For instruction:\s*%valB.loaded = load i32, ptr %inB, align 4" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: .* ir<%valB.loaded> = load"
+; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output -vplan-print-metadata=false < %s 2>&1 | FileCheck %s --check-prefixes=SSE
+; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse4.2 --debug-only=loop-vectorize --disable-output -vplan-print-metadata=false < %s 2>&1 | FileCheck %s --check-prefixes=SSE
+; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output -vplan-print-metadata=false < %s 2>&1 | FileCheck %s --check-prefixes=AVX1
+; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,-fast-gather --debug-only=loop-vectorize --disable-output -vplan-print-metadata=false < %s 2>&1 | FileCheck %s --check-prefixes=AVX2
+; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,+fast-gather --debug-only=loop-vectorize --disable-output -vplan-print-metadata=false < %s 2>&1 | FileCheck %s --check-prefixes=AVX2
+; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx512bw --debug-only=loop-vectorize --disable-output -vplan-print-metadata=false < %s 2>&1 | FileCheck %s --check-prefixes=AVX512
; REQUIRES: asserts
@@ -17,35 +17,35 @@ target triple = "x86_64-unknown-linux-gnu"
define void @test(ptr %B) {
; SSE-LABEL: 'test'
; SSE: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i32, ptr %inB, align 4
-; SSE: Cost of 3000000 for VF 2: {{.*}}ir<%valB.loaded> = load
-; SSE: Cost of 3000000 for VF 4: {{.*}}ir<%valB.loaded> = load
-; SSE: Cost of 3000000 for VF 8: {{.*}}ir<%valB.loaded> = load
-; SSE: Cost of 3000000 for VF 16: {{.*}}ir<%valB.loaded> = load
+; SSE: Cost of 3000000 for VF 2: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
+; SSE: Cost of 3000000 for VF 4: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
+; SSE: Cost of 3000000 for VF 8: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
+; SSE: Cost of 3000000 for VF 16: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
;
; AVX1-LABEL: 'test'
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i32, ptr %inB, align 4
-; AVX1: Cost of 3 for VF 2: {{.*}}ir<%valB.loaded> = load
-; AVX1: Cost of 2 for VF 4: {{.*}}ir<%valB.loaded> = load
-; AVX1: Cost of 2 for VF 8: {{.*}}ir<%valB.loaded> = load
-; AVX1: Cost of 4 for VF 16: {{.*}}ir<%valB.loaded> = load
-; AVX1: Cost of 8 for VF 32: {{.*}}ir<%valB.loaded> = load
+; AVX1: Cost of 3 for VF 2: WIDEN ir<%valB.loaded> = load vp<[[VP6:%[0-9]+]]>, ir<%canLoad>
+; AVX1: Cost of 2 for VF 4: WIDEN ir<%valB.loaded> = load vp<[[VP6]]>, ir<%canLoad>
+; AVX1: Cost of 2 for VF 8: WIDEN ir<%valB.loaded> = load vp<[[VP6]]>, ir<%canLoad>
+; AVX1: Cost of 4 for VF 16: WIDEN ir<%valB.loaded> = load vp<[[VP6]]>, ir<%canLoad>
+; AVX1: Cost of 8 for VF 32: WIDEN ir<%valB.loaded> = load vp<[[VP6]]>, ir<%canLoad>
;
; AVX2-LABEL: 'test'
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i32, ptr %inB, align 4
-; AVX2: Cost of 3 for VF 2: {{.*}}ir<%valB.loaded> = load
-; AVX2: Cost of 2 for VF 4: {{.*}}ir<%valB.loaded> = load
-; AVX2: Cost of 2 for VF 8: {{.*}}ir<%valB.loaded> = load
-; AVX2: Cost of 4 for VF 16: {{.*}}ir<%valB.loaded> = load
-; AVX2: Cost of 8 for VF 32: {{.*}}ir<%valB.loaded> = load
+; AVX2: Cost of 3 for VF 2: WIDEN ir<%valB.loaded> = load vp<[[VP6:%[0-9]+]]>, ir<%canLoad>
+; AVX2: Cost of 2 for VF 4: WIDEN ir<%valB.loaded> = load vp<[[VP6]]>, ir<%canLoad>
+; AVX2: Cost of 2 for VF 8: WIDEN ir<%valB.loaded> = load vp<[[VP6]]>, ir<%canLoad>
+; AVX2: Cost of 4 for VF 16: WIDEN ir<%valB.loaded> = load vp<[[VP6]]>, ir<%canLoad>
+; AVX2: Cost of 8 for VF 32: WIDEN ir<%valB.loaded> = load vp<[[VP6]]>, ir<%canLoad>
;
; AVX512-LABEL: 'test'
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i32, ptr %inB, align 4
-; AVX512: Cost of 2 for VF 2: {{.*}}ir<%valB.loaded> = load
-; AVX512: Cost of 1 for VF 4: {{.*}}ir<%valB.loaded> = load
-; AVX512: Cost of 1 for VF 8: {{.*}}ir<%valB.loaded> = load
-; AVX512: Cost of 1 for VF 16: {{.*}}ir<%valB.loaded> = load
-; AVX512: Cost of 2 for VF 32: {{.*}}ir<%valB.loaded> = load
-; AVX512: Cost of 4 for VF 64: {{.*}}ir<%valB.loaded> = load
+; AVX512: Cost of 2 for VF 2: WIDEN ir<%valB.loaded> = load vp<[[VP6:%[0-9]+]]>, ir<%canLoad>
+; AVX512: Cost of 1 for VF 4: WIDEN ir<%valB.loaded> = load vp<[[VP6]]>, ir<%canLoad>
+; AVX512: Cost of 1 for VF 8: WIDEN ir<%valB.loaded> = load vp<[[VP6]]>, ir<%canLoad>
+; AVX512: Cost of 1 for VF 16: WIDEN ir<%valB.loaded> = load vp<[[VP6]]>, ir<%canLoad>
+; AVX512: Cost of 2 for VF 32: WIDEN ir<%valB.loaded> = load vp<[[VP6]]>, ir<%canLoad>
+; AVX512: Cost of 4 for VF 64: WIDEN ir<%valB.loaded> = load vp<[[VP6]]>, ir<%canLoad>
;
entry:
br label %for.body
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-load-i64.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-load-i64.ll
index 85953f2b3733e..48c9b01beb888 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-load-i64.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-load-i64.ll
@@ -1,10 +1,10 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF [0-9]+ For instruction:\s*%valB.loaded = load i64, ptr %inB, align 8"
-; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=SSE
-; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse4.2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=SSE
-; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=AVX1
-; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,-fast-gather --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=AVX2
-; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,+fast-gather --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=AVX2
-; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx512bw --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=AVX512
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF [0-9]+ For instruction:\s*%valB.loaded = load i64, ptr %inB, align 8" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: .* ir<%valB.loaded> = load"
+; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output -vplan-print-metadata=false < %s 2>&1 | FileCheck %s --check-prefixes=SSE
+; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse4.2 --debug-only=loop-vectorize --disable-output -vplan-print-metadata=false < %s 2>&1 | FileCheck %s --check-prefixes=SSE
+; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output -vplan-print-metadata=false < %s 2>&1 | FileCheck %s --check-prefixes=AVX1
+; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,-fast-gather --debug-only=loop-vectorize --disable-output -vplan-print-metadata=false < %s 2>&1 | FileCheck %s --check-prefixes=AVX2
+; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,+fast-gather --debug-only=loop-vectorize --disable-output -vplan-print-metadata=false < %s 2>&1 | FileCheck %s --check-prefixes=AVX2
+; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx512bw --debug-only=loop-vectorize --disable-output -vplan-print-metadata=false < %s 2>&1 | FileCheck %s --check-prefixes=AVX512
; REQUIRES: asserts
@@ -17,35 +17,35 @@ target triple = "x86_64-unknown-linux-gnu"
define void @test(ptr %B) {
; SSE-LABEL: 'test'
; SSE: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i64, ptr %inB, align 8
-; SSE: Cost of 3000000 for VF 2: {{.*}}ir<%valB.loaded> = load
-; SSE: Cost of 3000000 for VF 4: {{.*}}ir<%valB.loaded> = load
-; SSE: Cost of 3000000 for VF 8: {{.*}}ir<%valB.loaded> = load
-; SSE: Cost of 3000000 for VF 16: {{.*}}ir<%valB.loaded> = load
+; SSE: Cost of 3000000 for VF 2: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
+; SSE: Cost of 3000000 for VF 4: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
+; SSE: Cost of 3000000 for VF 8: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
+; SSE: Cost of 3000000 for VF 16: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
;
; AVX1-LABEL: 'test'
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i64, ptr %inB, align 8
-; AVX1: Cost of 2 for VF 2: {{.*}}ir<%valB.loaded> = load
-; AVX1: Cost of 2 for VF 4: {{.*}}ir<%valB.loaded> = load
-; AVX1: Cost of 4 for VF 8: {{.*}}ir<%valB.loaded> = load
-; AVX1: Cost of 8 for VF 16: {{.*}}ir<%valB.loaded> = load
-; AVX1: Cost of 16 for VF 32: {{.*}}ir<%valB.loaded> = load
+; AVX1: Cost of 2 for VF 2: WIDEN ir<%valB.loaded> = load vp<[[VP6:%[0-9]+]]>, ir<%canLoad>
+; AVX1: Cost of 2 for VF 4: WIDEN ir<%valB.loaded> = load vp<[[VP6]]>, ir<%canLoad>
+; AVX1: Cost of 4 for VF 8: WIDEN ir<%valB.loaded> = load vp<[[VP6]]>, ir<%canLoad>
+; AVX1: Cost of 8 for VF 16: WIDEN ir<%valB.loaded> = load vp<[[VP6]]>, ir<%canLoad>
+; AVX1: Cost of 16 for VF 32: WIDEN ir<%valB.loaded> = load vp<[[VP6]]>, ir<%canLoad>
;
; AVX2-LABEL: 'test'
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i64, ptr %inB, align 8
-; AVX2: Cost of 2 for VF 2: {{.*}}ir<%valB.loaded> = load
-; AVX2: Cost of 2 for VF 4: {{.*}}ir<%valB.loaded> = load
-; AVX2: Cost of 4 for VF 8: {{.*}}ir<%valB.loaded> = load
-; AVX2: Cost of 8 for VF 16: {{.*}}ir<%valB.loaded> = load
-; AVX2: Cost of 16 for VF 32: {{.*}}ir<%valB.loaded> = load
+; AVX2: Cost of 2 for VF 2: WIDEN ir<%valB.loaded> = load vp<[[VP6:%[0-9]+]]>, ir<%canLoad>
+; AVX2: Cost of 2 for VF 4: WIDEN ir<%valB.loaded> = load vp<[[VP6]]>, ir<%canLoad>
+; AVX2: Cost of 4 for VF 8: WIDEN ir<%valB.loaded> = load vp<[[VP6]]>, ir<%canLoad>
+; AVX2: Cost of 8 for VF 16: WIDEN ir<%valB.loaded> = load vp<[[VP6]]>, ir<%canLoad>
+; AVX2: Cost of 16 for VF 32: WIDEN ir<%valB.loaded> = load vp<[[VP6]]>, ir<%canLoad>
;
; AVX512-LABEL: 'test'
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i64, ptr %inB, align 8
-; AVX512: Cost of 1 for VF 2: {{.*}}ir<%valB.loaded> = load
-; AVX512: Cost of 1 for VF 4: {{.*}}ir<%valB.loaded> = load
-; AVX512: Cost of 1 for VF 8: {{.*}}ir<%valB.loaded> = load
-; AVX512: Cost of 2 for VF 16: {{.*}}ir<%valB.loaded> = load
-; AVX512: Cost of 4 for VF 32: {{.*}}ir<%valB.loaded> = load
-; AVX512: Cost of 8 for VF 64: {{.*}}ir<%valB.loaded> = load
+; AVX512: Cost of 1 for VF 2: WIDEN ir<%valB.loaded> = load vp<[[VP6:%[0-9]+]]>, ir<%canLoad>
+; AVX512: Cost of 1 for VF 4: WIDEN ir<%valB.loaded> = load vp<[[VP6]]>, ir<%canLoad>
+; AVX512: Cost of 1 for VF 8: WIDEN ir<%valB.loaded> = load vp<[[VP6]]>, ir<%canLoad>
+; AVX512: Cost of 2 for VF 16: WIDEN ir<%valB.loaded> = load vp<[[VP6]]>, ir<%canLoad>
+; AVX512: Cost of 4 for VF 32: WIDEN ir<%valB.loaded> = load vp<[[VP6]]>, ir<%canLoad>
+; AVX512: Cost of 8 for VF 64: WIDEN ir<%valB.loaded> = load vp<[[VP6]]>, ir<%canLoad>
;
entry:
br label %for.body
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-load-i8.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-load-i8.ll
index 333be63f50c06..c822598977704 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-load-i8.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-load-i8.ll
@@ -1,10 +1,10 @@
-; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF [0-9]+ For instruction:\s*%valB.loaded = load i8, ptr %inB, align 1"
-; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=SSE
-; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse4.2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=SSE
-; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=AVX1
-; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,-fast-gather --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=AVX2
-; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,+fast-gather --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=AVX2
-; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx512bw --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=AVX512
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF [0-9]+ For instruction:\s*%valB.loaded = load i8, ptr %inB, align 1" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: .* ir<%valB.loaded> = load"
+; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output -vplan-print-metadata=false < %s 2>&1 | FileCheck %s --check-prefixes=SSE
+; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse4.2 --debug-only=loop-vectorize --disable-output -vplan-print-metadata=false < %s 2>&1 | FileCheck %s --check-prefixes=SSE
+; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output -vplan-print-metadata=false < %s 2>&1 | FileCheck %s --check-prefixes=AVX1
+; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,-fast-gather --debug-only=loop-vectorize --disable-output -vplan-print-metadata=false < %s 2>&1 | FileCheck %s --check-prefixes=AVX2
+; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,+fast-gather --debug-only=loop-vectorize --disable-output -vplan-print-metadata=false < %s 2>&1 | FileCheck %s --check-prefixes=AVX2
+; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx512bw --debug-only=loop-vectorize --disable-output -vplan-print-metadata=false < %s 2>&1 | FileCheck %s --check-prefixes=AVX512
; REQUIRES: asserts
@@ -17,35 +17,35 @@ target triple = "x86_64-unknown-linux-gnu"
define void @test(ptr %B) {
; SSE-LABEL: 'test'
; SSE: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i8, ptr %inB, align 1
-; SSE: Cost of 3000000 for VF 2: {{.*}}ir<%valB.loaded> = load
-; SSE: Cost of 3000000 for VF 4: {{.*}}ir<%valB.loaded> = load
-; SSE: Cost of 3000000 for VF 8: {{.*}}ir<%valB.loaded> = load
-; SSE: Cost of 3000000 for VF 16: {{.*}}ir<%valB.loaded> = load
+; SSE: Cost of 3000000 for VF 2: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
+; SSE: Cost of 3000000 for VF 4: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
+; SSE: Cost of 3000000 for VF 8: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
+; SSE: Cost of 3000000 for VF 16: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
;
; AVX1-LABEL: 'test'
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i8, ptr %inB, align 1
-; AVX1: Cost of 3000000 for VF 2: {{.*}}ir<%valB.loaded> = load
-; AVX1: Cost of 3000000 for VF 4: {{.*}}ir<%valB.loaded> = load
-; AVX1: Cost of 3000000 for VF 8: {{.*}}ir<%valB.loaded> = load
-; AVX1: Cost of 3000000 for VF 16: {{.*}}ir<%valB.loaded> = load
-; AVX1: Cost of 3000000 for VF 32: {{.*}}ir<%valB.loaded> = load
+; AVX1: Cost of 3000000 for VF 2: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
+; AVX1: Cost of 3000000 for VF 4: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
+; AVX1: Cost of 3000000 for VF 8: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
+; AVX1: Cost of 3000000 for VF 16: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
+; AVX1: Cost of 3000000 for VF 32: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
;
; AVX2-LABEL: 'test'
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i8, ptr %inB, align 1
-; AVX2: Cost of 3000000 for VF 2: {{.*}}ir<%valB.loaded> = load
-; AVX2: Cost of 3000000 for VF 4: {{.*}}ir<%valB.loaded> = load
-; AVX2: Cost of 3000000 for VF 8: {{.*}}ir<%valB.loaded> = load
-; AVX2: Cost of 3000000 for VF 16: {{.*}}ir<%valB.loaded> = load
-; AVX2: Cost of 3000000 for VF 32: {{.*}}ir<%valB.loaded> = load
+; AVX2: Cost of 3000000 for VF 2: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
+; AVX2: Cost of 3000000 for VF 4: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
+; AVX2: Cost of 3000000 for VF 8: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
+; AVX2: Cost of 3000000 for VF 16: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
+; AVX2: Cost of 3000000 for VF 32: REPLICATE ir<%valB.loaded> = load ir<%inB> (S->V)
;
; AVX512-LABEL: 'test'
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i8, ptr %inB, align 1
-; AVX512: Cost of 2 for VF 2: {{.*}}ir<%valB.loaded> = load
-; AVX512: Cost of 2 for VF 4: {{.*}}ir<%valB.loaded> = load
-; AVX512: Cost of 2 for VF 8: {{.*}}ir<%valB.loaded> = load
-; AVX512: Cost of 1 for VF 16: {{.*}}ir<%valB.loaded> = load
-; AVX512: Cost of 1 for VF 32: {{.*}}ir<%valB.loaded> = load
-; AVX512: Cost of 1 for VF 64: {{.*}}ir<%valB.loaded> = load
+; AVX512: Cost of 2 for VF 2: WIDEN ir<%valB.loaded> = load vp<[[VP6:%[0-9]+]]>, ir<%canLoad>
+; AVX512: Cost of 2 for VF 4: WIDEN ir<%valB.loaded> = load vp<[[VP6]]>, ir<%canLoad>
+; AVX512: Cost of 2 for VF 8: WIDEN ir<%valB.loaded> = load vp<[[VP6]]>, ir<%canLoad>
+; AVX512: Cost of 1 for VF 16: WIDEN ir<%valB.loaded> = load vp<[[VP6]]>, ir<%canLoad>
+; AVX512: Cost of 1 for VF 32: WIDEN ir<%valB.loaded> = load vp<[[VP6]]>, ir<%canLoad>
+; AVX512: Cost of 1 for VF 64: WIDEN ir<%valB.loaded> = load vp<[[VP6]]>, ir<%canLoad>
;
entry:
br label %for.body
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-store-i16.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-store-i16.ll
index 5b3d83a13e919..61436a61dba50 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-store-i16.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-store-i16.ll
@@ -1,10 +1,10 @@
; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*store i16 %valB, ptr %out" --filter "Cost of [1-9][0-9]*(.[0-9]+)? for VF [0-9]+: (profitable to scalarize\s+store i16 %valB|WIDEN store .*, ir<%valB>|REPLICATE store ir<%valB>)"
-; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=SSE
-; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse4.2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=SSE
-; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=AVX1
-; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,-fast-gather --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=AVX2
-; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,+fast-gather --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=AVX2
-; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx512bw --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=AVX512
+; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output -vplan-print-metadata=false < %s 2>&1 | FileCheck %s --check-prefixes=SSE
+; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse4.2 --debug-only=loop-vectorize --disable-output -vplan-print-metadata=false < %s 2>&1 | FileCheck %s --check-prefixes=SSE
+; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output -vplan-print-metadata=false < %s 2>&1 | FileCheck %s --check-prefixes=AVX1
+; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,-fast-gather --debug-only=loop-vectorize --disable-output -vplan-print-metadata=false < %s 2>&1 | FileCheck %s --check-prefixes=AVX2
+; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,+fast-gather --debug-only=loop-vectorize --disable-output -vplan-print-metadata=false < %s 2>&1 | FileCheck %s --check-prefixes=AVX2
+; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx512bw --debug-only=loop-vectorize --disable-output -vplan-print-metadata=false < %s 2>&1 | FileCheck %s --check-prefixes=AVX512
; REQUIRES: asserts
@@ -40,12 +40,12 @@ define void @test(ptr %C) {
;
; AVX512-LABEL: 'test'
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %valB, ptr %out, align 2
-; AVX512: Cost of 2 for VF 2: WIDEN store vp<[[VP7:%[0-9]+]]>, ir<%valB>, ir<%canStore> (!alias.scope {{.*}}, !noalias {{.*}})
-; AVX512: Cost of 2 for VF 4: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore> (!alias.scope {{.*}}, !noalias {{.*}})
-; AVX512: Cost of 1 for VF 8: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore> (!alias.scope {{.*}}, !noalias {{.*}})
-; AVX512: Cost of 1 for VF 16: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore> (!alias.scope {{.*}}, !noalias {{.*}})
-; AVX512: Cost of 1 for VF 32: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore> (!alias.scope {{.*}}, !noalias {{.*}})
-; AVX512: Cost of 2 for VF 64: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore> (!alias.scope {{.*}}, !noalias {{.*}})
+; AVX512: Cost of 2 for VF 2: WIDEN store vp<[[VP7:%[0-9]+]]>, ir<%valB>, ir<%canStore>
+; AVX512: Cost of 2 for VF 4: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore>
+; AVX512: Cost of 1 for VF 8: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore>
+; AVX512: Cost of 1 for VF 16: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore>
+; AVX512: Cost of 1 for VF 32: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore>
+; AVX512: Cost of 2 for VF 64: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore>
;
entry:
br label %for.body
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-store-i32.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-store-i32.ll
index c659b0a53364c..0afea8d1664d5 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-store-i32.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-store-i32.ll
@@ -1,10 +1,10 @@
; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*store i32 %valB, ptr %out" --filter "Cost of [1-9][0-9]*(.[0-9]+)? for VF [0-9]+: (profitable to scalarize\s+store i32 %valB|WIDEN store .*, ir<%valB>|REPLICATE store ir<%valB>)"
-; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=SSE2
-; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse4.2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=SSE42
-; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=AVX1
-; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,-fast-gather --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=AVX2
-; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,+fast-gather --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=AVX2
-; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx512bw --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=AVX512
+; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output -vplan-print-metadata=false < %s 2>&1 | FileCheck %s --check-prefixes=SSE2
+; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse4.2 --debug-only=loop-vectorize --disable-output -vplan-print-metadata=false < %s 2>&1 | FileCheck %s --check-prefixes=SSE42
+; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output -vplan-print-metadata=false < %s 2>&1 | FileCheck %s --check-prefixes=AVX1
+; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,-fast-gather --debug-only=loop-vectorize --disable-output -vplan-print-metadata=false < %s 2>&1 | FileCheck %s --check-prefixes=AVX2
+; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,+fast-gather --debug-only=loop-vectorize --disable-output -vplan-print-metadata=false < %s 2>&1 | FileCheck %s --check-prefixes=AVX2
+; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx512bw --debug-only=loop-vectorize --disable-output -vplan-print-metadata=false < %s 2>&1 | FileCheck %s --check-prefixes=AVX512
; REQUIRES: asserts
@@ -31,28 +31,28 @@ define void @test(ptr %C) {
;
; AVX1-LABEL: 'test'
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: store i32 %valB, ptr %out, align 4
-; AVX1: Cost of 9 for VF 2: WIDEN store vp<[[VP7:%[0-9]+]]>, ir<%valB>, ir<%canStore> (!alias.scope {{.*}}, !noalias {{.*}})
-; AVX1: Cost of 8 for VF 4: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore> (!alias.scope {{.*}}, !noalias {{.*}})
-; AVX1: Cost of 8 for VF 8: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore> (!alias.scope {{.*}}, !noalias {{.*}})
-; AVX1: Cost of 16 for VF 16: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore> (!alias.scope {{.*}}, !noalias {{.*}})
-; AVX1: Cost of 32 for VF 32: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore> (!alias.scope {{.*}}, !noalias {{.*}})
+; AVX1: Cost of 9 for VF 2: WIDEN store vp<[[VP7:%[0-9]+]]>, ir<%valB>, ir<%canStore>
+; AVX1: Cost of 8 for VF 4: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore>
+; AVX1: Cost of 8 for VF 8: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore>
+; AVX1: Cost of 16 for VF 16: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore>
+; AVX1: Cost of 32 for VF 32: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore>
;
; AVX2-LABEL: 'test'
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i32 %valB, ptr %out, align 4
-; AVX2: Cost of 9 for VF 2: WIDEN store vp<[[VP7:%[0-9]+]]>, ir<%valB>, ir<%canStore> (!alias.scope {{.*}}, !noalias {{.*}})
-; AVX2: Cost of 8 for VF 4: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore> (!alias.scope {{.*}}, !noalias {{.*}})
-; AVX2: Cost of 8 for VF 8: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore> (!alias.scope {{.*}}, !noalias {{.*}})
-; AVX2: Cost of 16 for VF 16: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore> (!alias.scope {{.*}}, !noalias {{.*}})
-; AVX2: Cost of 32 for VF 32: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore> (!alias.scope {{.*}}, !noalias {{.*}})
+; AVX2: Cost of 9 for VF 2: WIDEN store vp<[[VP7:%[0-9]+]]>, ir<%valB>, ir<%canStore>
+; AVX2: Cost of 8 for VF 4: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore>
+; AVX2: Cost of 8 for VF 8: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore>
+; AVX2: Cost of 16 for VF 16: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore>
+; AVX2: Cost of 32 for VF 32: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore>
;
; AVX512-LABEL: 'test'
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store i32 %valB, ptr %out, align 4
-; AVX512: Cost of 2 for VF 2: WIDEN store vp<[[VP7:%[0-9]+]]>, ir<%valB>, ir<%canStore> (!alias.scope {{.*}}, !noalias {{.*}})
-; AVX512: Cost of 1 for VF 4: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore> (!alias.scope {{.*}}, !noalias {{.*}})
-; AVX512: Cost of 1 for VF 8: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore> (!alias.scope {{.*}}, !noalias {{.*}})
-; AVX512: Cost of 1 for VF 16: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore> (!alias.scope {{.*}}, !noalias {{.*}})
-; AVX512: Cost of 2 for VF 32: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore> (!alias.scope {{.*}}, !noalias {{.*}})
-; AVX512: Cost of 4 for VF 64: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore> (!alias.scope {{.*}}, !noalias {{.*}})
+; AVX512: Cost of 2 for VF 2: WIDEN store vp<[[VP7:%[0-9]+]]>, ir<%valB>, ir<%canStore>
+; AVX512: Cost of 1 for VF 4: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore>
+; AVX512: Cost of 1 for VF 8: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore>
+; AVX512: Cost of 1 for VF 16: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore>
+; AVX512: Cost of 2 for VF 32: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore>
+; AVX512: Cost of 4 for VF 64: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore>
;
entry:
br label %for.body
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-store-i64.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-store-i64.ll
index 1c05a4c25d973..ce2d69fca6a3b 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-store-i64.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-store-i64.ll
@@ -1,10 +1,10 @@
; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*store i64 %valB, ptr %out" --filter "Cost of [1-9][0-9]*(.[0-9]+)? for VF [0-9]+: (profitable to scalarize\s+store i64 %valB|WIDEN store .*, ir<%valB>|REPLICATE store ir<%valB>)"
-; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=SSE2
-; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse4.2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=SSE42
-; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=AVX1
-; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,-fast-gather --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=AVX2
-; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,+fast-gather --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=AVX2
-; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx512bw --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=AVX512
+; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output -vplan-print-metadata=false < %s 2>&1 | FileCheck %s --check-prefixes=SSE2
+; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse4.2 --debug-only=loop-vectorize --disable-output -vplan-print-metadata=false < %s 2>&1 | FileCheck %s --check-prefixes=SSE42
+; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output -vplan-print-metadata=false < %s 2>&1 | FileCheck %s --check-prefixes=AVX1
+; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,-fast-gather --debug-only=loop-vectorize --disable-output -vplan-print-metadata=false < %s 2>&1 | FileCheck %s --check-prefixes=AVX2
+; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,+fast-gather --debug-only=loop-vectorize --disable-output -vplan-print-metadata=false < %s 2>&1 | FileCheck %s --check-prefixes=AVX2
+; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx512bw --debug-only=loop-vectorize --disable-output -vplan-print-metadata=false < %s 2>&1 | FileCheck %s --check-prefixes=AVX512
; REQUIRES: asserts
@@ -31,28 +31,28 @@ define void @test(ptr %C) {
;
; AVX1-LABEL: 'test'
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %valB, ptr %out, align 8
-; AVX1: Cost of 8 for VF 2: WIDEN store vp<[[VP7:%[0-9]+]]>, ir<%valB>, ir<%canStore> (!alias.scope {{.*}}, !noalias {{.*}})
-; AVX1: Cost of 8 for VF 4: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore> (!alias.scope {{.*}}, !noalias {{.*}})
-; AVX1: Cost of 16 for VF 8: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore> (!alias.scope {{.*}}, !noalias {{.*}})
-; AVX1: Cost of 32 for VF 16: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore> (!alias.scope {{.*}}, !noalias {{.*}})
-; AVX1: Cost of 64 for VF 32: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore> (!alias.scope {{.*}}, !noalias {{.*}})
+; AVX1: Cost of 8 for VF 2: WIDEN store vp<[[VP7:%[0-9]+]]>, ir<%valB>, ir<%canStore>
+; AVX1: Cost of 8 for VF 4: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore>
+; AVX1: Cost of 16 for VF 8: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore>
+; AVX1: Cost of 32 for VF 16: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore>
+; AVX1: Cost of 64 for VF 32: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore>
;
; AVX2-LABEL: 'test'
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %valB, ptr %out, align 8
-; AVX2: Cost of 8 for VF 2: WIDEN store vp<[[VP7:%[0-9]+]]>, ir<%valB>, ir<%canStore> (!alias.scope {{.*}}, !noalias {{.*}})
-; AVX2: Cost of 8 for VF 4: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore> (!alias.scope {{.*}}, !noalias {{.*}})
-; AVX2: Cost of 16 for VF 8: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore> (!alias.scope {{.*}}, !noalias {{.*}})
-; AVX2: Cost of 32 for VF 16: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore> (!alias.scope {{.*}}, !noalias {{.*}})
-; AVX2: Cost of 64 for VF 32: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore> (!alias.scope {{.*}}, !noalias {{.*}})
+; AVX2: Cost of 8 for VF 2: WIDEN store vp<[[VP7:%[0-9]+]]>, ir<%valB>, ir<%canStore>
+; AVX2: Cost of 8 for VF 4: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore>
+; AVX2: Cost of 16 for VF 8: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore>
+; AVX2: Cost of 32 for VF 16: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore>
+; AVX2: Cost of 64 for VF 32: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore>
;
; AVX512-LABEL: 'test'
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %valB, ptr %out, align 8
-; AVX512: Cost of 1 for VF 2: WIDEN store vp<[[VP7:%[0-9]+]]>, ir<%valB>, ir<%canStore> (!alias.scope {{.*}}, !noalias {{.*}})
-; AVX512: Cost of 1 for VF 4: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore> (!alias.scope {{.*}}, !noalias {{.*}})
-; AVX512: Cost of 1 for VF 8: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore> (!alias.scope {{.*}}, !noalias {{.*}})
-; AVX512: Cost of 2 for VF 16: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore> (!alias.scope {{.*}}, !noalias {{.*}})
-; AVX512: Cost of 4 for VF 32: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore> (!alias.scope {{.*}}, !noalias {{.*}})
-; AVX512: Cost of 8 for VF 64: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore> (!alias.scope {{.*}}, !noalias {{.*}})
+; AVX512: Cost of 1 for VF 2: WIDEN store vp<[[VP7:%[0-9]+]]>, ir<%valB>, ir<%canStore>
+; AVX512: Cost of 1 for VF 4: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore>
+; AVX512: Cost of 1 for VF 8: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore>
+; AVX512: Cost of 2 for VF 16: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore>
+; AVX512: Cost of 4 for VF 32: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore>
+; AVX512: Cost of 8 for VF 64: WIDEN store vp<[[VP7]]>, ir<%valB>, ir<%canStore>
;
entry:
br label %for.body
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-store-i8.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-store-i8.ll
index 16a7768bbc302..9028e1c5525a0 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-store-i8.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/masked-store-i8.ll
@@ -1,10 +1,10 @@
; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+(.[0-9]+)? for VF 1 For instruction:\s*store i8 %valB, ptr %out" --filter "Cost of [1-9][0-9]*(.[0-9]+)? for VF [0-9]+: (profitable to scalarize\s+store i8 %valB|WIDEN store .*, ir<%valB>|REPLICATE store ir<%valB>)"
-; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=SSE2
-; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse4.2 --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=SSE42
-; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=AVX1
-; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,-fast-gather --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=AVX2
-; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,+fast-gather --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=AVX2
-; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx512bw --debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=AVX512
+; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize --disable-output -vplan-print-metadata=false < %s 2>&1 | FileCheck %s --check-prefixes=SSE2
+; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse4.2 --debug-only=loop-vectorize --disable-output -vplan-print-metadata=false < %s 2>&1 | FileCheck %s --check-prefixes=SSE42
+; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize --disable-output -vplan-print-metadata=false < %s 2>&1 | FileCheck %s --check-prefixes=AVX1
+; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,-fast-gather --debug-only=loop-vectorize --disable-output -vplan-print-metadata=false < %s 2>&1 | FileCheck %s --check-prefixes=AVX2
+; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,+fast-gather --debug-only=loop-vectorize --disable-output -vplan-print-metadata=false < %s 2>&1 | FileCheck %s --check-prefixes=AVX2
+; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx512bw --debug-only=loop-vectorize --disable-output -vplan-print-metadata=false < %s 2>&1 | FileCheck %s --check-prefixes=AVX512
; REQUIRES: asserts
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/strided-load-i16.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/strided-load-i16.ll
index 2e479adbe03d6..b77b8ac294163 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/strided-load-i16.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/strided-load-i16.ll
@@ -1,3 +1,4 @@
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Found an estimated cost of [0-9]+(.[0-9]+)? for VF [0-9]+ For instruction:\s*%1" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP" --version 6
; REQUIRES: asserts
; RUN: opt -passes=loop-vectorize -S -mattr=avx512bw --debug-only=loop-vectorize --disable-output < %s 2>&1| FileCheck %s
@@ -8,13 +9,14 @@ target triple = "x86_64-unknown-linux-gnu"
@B = global [10240 x i16] zeroinitializer, align 16
define void @load_i16_stride2() {
-;CHECK-LABEL: load_i16_stride2
-;CHECK: Found an estimated cost of 1 for VF 1 For instruction: %1 = load
-;CHECK: Cost of 1 for VF 2: INTERLEAVE-GROUP with factor 2,
-;CHECK: Cost of 1 for VF 4: INTERLEAVE-GROUP with factor 2,
-;CHECK: Cost of 2 for VF 8: INTERLEAVE-GROUP with factor 2,
-;CHECK: Cost of 2 for VF 16: INTERLEAVE-GROUP with factor 2,
-;CHECK: Cost of 3 for VF 32: INTERLEAVE-GROUP with factor 2,
+; CHECK-LABEL: 'load_i16_stride2'
+; CHECK: LV: Found an estimated cost of 1 for VF 1 For instruction: %1 = load i16, ptr %arrayidx, align 4
+; CHECK: Cost of 1 for VF 2: INTERLEAVE-GROUP with factor 2, ir<%arrayidx>
+; CHECK: Cost of 1 for VF 4: INTERLEAVE-GROUP with factor 2, ir<%arrayidx>
+; CHECK: Cost of 2 for VF 8: INTERLEAVE-GROUP with factor 2, ir<%arrayidx>
+; CHECK: Cost of 2 for VF 16: INTERLEAVE-GROUP with factor 2, ir<%arrayidx>
+; CHECK: Cost of 3 for VF 32: INTERLEAVE-GROUP with factor 2, ir<%arrayidx>
+;
entry:
br label %for.body
@@ -34,13 +36,14 @@ for.end:
}
define void @load_i16_stride3() {
-;CHECK-LABEL: load_i16_stride3
-;CHECK: Found an estimated cost of 1 for VF 1 For instruction: %1 = load
-;CHECK: Cost of 1 for VF 2: INTERLEAVE-GROUP with factor 3,
-;CHECK: Cost of 2 for VF 4: INTERLEAVE-GROUP with factor 3,
-;CHECK: Cost of 2 for VF 8: INTERLEAVE-GROUP with factor 3,
-;CHECK: Cost of 3 for VF 16: INTERLEAVE-GROUP with factor 3,
-;CHECK: Cost of 5 for VF 32: INTERLEAVE-GROUP with factor 3,
+; CHECK-LABEL: 'load_i16_stride3'
+; CHECK: LV: Found an estimated cost of 1 for VF 1 For instruction: %1 = load i16, ptr %arrayidx, align 4
+; CHECK: Cost of 1 for VF 2: INTERLEAVE-GROUP with factor 3, ir<%arrayidx>
+; CHECK: Cost of 2 for VF 4: INTERLEAVE-GROUP with factor 3, ir<%arrayidx>
+; CHECK: Cost of 2 for VF 8: INTERLEAVE-GROUP with factor 3, ir<%arrayidx>
+; CHECK: Cost of 3 for VF 16: INTERLEAVE-GROUP with factor 3, ir<%arrayidx>
+; CHECK: Cost of 5 for VF 32: INTERLEAVE-GROUP with factor 3, ir<%arrayidx>
+;
entry:
br label %for.body
@@ -60,13 +63,14 @@ for.end:
}
define void @load_i16_stride4() {
-;CHECK-LABEL: load_i16_stride4
-;CHECK: Found an estimated cost of 1 for VF 1 For instruction: %1 = load
-;CHECK: Cost of 1 for VF 2: INTERLEAVE-GROUP with factor 4,
-;CHECK: Cost of 2 for VF 4: INTERLEAVE-GROUP with factor 4,
-;CHECK: Cost of 2 for VF 8: INTERLEAVE-GROUP with factor 4,
-;CHECK: Cost of 3 for VF 16: INTERLEAVE-GROUP with factor 4,
-;CHECK: Cost of 8 for VF 32: INTERLEAVE-GROUP with factor 4,
+; CHECK-LABEL: 'load_i16_stride4'
+; CHECK: LV: Found an estimated cost of 1 for VF 1 For instruction: %1 = load i16, ptr %arrayidx, align 4
+; CHECK: Cost of 1 for VF 2: INTERLEAVE-GROUP with factor 4, ir<%arrayidx>
+; CHECK: Cost of 2 for VF 4: INTERLEAVE-GROUP with factor 4, ir<%arrayidx>
+; CHECK: Cost of 2 for VF 8: INTERLEAVE-GROUP with factor 4, ir<%arrayidx>
+; CHECK: Cost of 3 for VF 16: INTERLEAVE-GROUP with factor 4, ir<%arrayidx>
+; CHECK: Cost of 8 for VF 32: INTERLEAVE-GROUP with factor 4, ir<%arrayidx>
+;
entry:
br label %for.body
@@ -86,13 +90,14 @@ for.end:
}
define void @load_i16_stride5() {
-;CHECK-LABEL: load_i16_stride5
-;CHECK: Found an estimated cost of 1 for VF 1 For instruction: %1 = load
-;CHECK: Cost of 2 for VF 2: INTERLEAVE-GROUP with factor 5,
-;CHECK: Cost of 2 for VF 4: INTERLEAVE-GROUP with factor 5,
-;CHECK: Cost of 3 for VF 8: INTERLEAVE-GROUP with factor 5,
-;CHECK: Cost of 5 for VF 16: INTERLEAVE-GROUP with factor 5,
-;CHECK: Cost of 10 for VF 32: INTERLEAVE-GROUP with factor 5,
+; CHECK-LABEL: 'load_i16_stride5'
+; CHECK: LV: Found an estimated cost of 1 for VF 1 For instruction: %1 = load i16, ptr %arrayidx, align 4
+; CHECK: Cost of 2 for VF 2: INTERLEAVE-GROUP with factor 5, ir<%arrayidx>
+; CHECK: Cost of 2 for VF 4: INTERLEAVE-GROUP with factor 5, ir<%arrayidx>
+; CHECK: Cost of 3 for VF 8: INTERLEAVE-GROUP with factor 5, ir<%arrayidx>
+; CHECK: Cost of 5 for VF 16: INTERLEAVE-GROUP with factor 5, ir<%arrayidx>
+; CHECK: Cost of 10 for VF 32: INTERLEAVE-GROUP with factor 5, ir<%arrayidx>
+;
entry:
br label %for.body
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/strided-load-i32.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/strided-load-i32.ll
index 36a11e6baf8ac..da9722b65ff06 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/strided-load-i32.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/strided-load-i32.ll
@@ -1,3 +1,4 @@
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Found an estimated cost of [0-9]+(.[0-9]+)? for VF [0-9]+ For instruction:\s*%1" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP" --version 6
; REQUIRES: asserts
; RUN: opt -passes=loop-vectorize -S -mattr=avx512f --debug-only=loop-vectorize --disable-output < %s 2>&1| FileCheck %s
@@ -8,12 +9,13 @@ target triple = "x86_64-unknown-linux-gnu"
@B = global [10240 x i32] zeroinitializer, align 16
define void @load_int_stride2() {
-;CHECK-LABEL: load_int_stride2
-;CHECK: Found an estimated cost of 1 for VF 1 For instruction: %1 = load
-;CHECK: Cost of 1 for VF 2: INTERLEAVE-GROUP with factor 2,
-;CHECK: Cost of 1 for VF 4: INTERLEAVE-GROUP with factor 2,
-;CHECK: Cost of 1 for VF 8: INTERLEAVE-GROUP with factor 2,
-;CHECK: Cost of 3 for VF 16: INTERLEAVE-GROUP with factor 2,
+; CHECK-LABEL: 'load_int_stride2'
+; CHECK: LV: Found an estimated cost of 1 for VF 1 For instruction: %1 = load i32, ptr %arrayidx, align 4
+; CHECK: Cost of 1 for VF 2: INTERLEAVE-GROUP with factor 2, ir<%arrayidx>
+; CHECK: Cost of 1 for VF 4: INTERLEAVE-GROUP with factor 2, ir<%arrayidx>
+; CHECK: Cost of 1 for VF 8: INTERLEAVE-GROUP with factor 2, ir<%arrayidx>
+; CHECK: Cost of 3 for VF 16: INTERLEAVE-GROUP with factor 2, ir<%arrayidx>
+;
entry:
br label %for.body
@@ -33,12 +35,13 @@ for.end:
}
define void @load_int_stride3() {
-;CHECK-LABEL: load_int_stride3
-;CHECK: Found an estimated cost of 1 for VF 1 For instruction: %1 = load
-;CHECK: Cost of 1 for VF 2: INTERLEAVE-GROUP with factor 3,
-;CHECK: Cost of 1 for VF 4: INTERLEAVE-GROUP with factor 3,
-;CHECK: Cost of 3 for VF 8: INTERLEAVE-GROUP with factor 3,
-;CHECK: Cost of 5 for VF 16: INTERLEAVE-GROUP with factor 3,
+; CHECK-LABEL: 'load_int_stride3'
+; CHECK: LV: Found an estimated cost of 1 for VF 1 For instruction: %1 = load i32, ptr %arrayidx, align 4
+; CHECK: Cost of 1 for VF 2: INTERLEAVE-GROUP with factor 3, ir<%arrayidx>
+; CHECK: Cost of 1 for VF 4: INTERLEAVE-GROUP with factor 3, ir<%arrayidx>
+; CHECK: Cost of 3 for VF 8: INTERLEAVE-GROUP with factor 3, ir<%arrayidx>
+; CHECK: Cost of 5 for VF 16: INTERLEAVE-GROUP with factor 3, ir<%arrayidx>
+;
entry:
br label %for.body
@@ -58,12 +61,13 @@ for.end:
}
define void @load_int_stride4() {
-;CHECK-LABEL: load_int_stride4
-;CHECK: Found an estimated cost of 1 for VF 1 For instruction: %1 = load
-;CHECK: Cost of 1 for VF 2: INTERLEAVE-GROUP with factor 4,
-;CHECK: Cost of 1 for VF 4: INTERLEAVE-GROUP with factor 4,
-;CHECK: Cost of 3 for VF 8: INTERLEAVE-GROUP with factor 4,
-;CHECK: Cost of 8 for VF 16: INTERLEAVE-GROUP with factor 4,
+; CHECK-LABEL: 'load_int_stride4'
+; CHECK: LV: Found an estimated cost of 1 for VF 1 For instruction: %1 = load i32, ptr %arrayidx, align 4
+; CHECK: Cost of 1 for VF 2: INTERLEAVE-GROUP with factor 4, ir<%arrayidx>
+; CHECK: Cost of 1 for VF 4: INTERLEAVE-GROUP with factor 4, ir<%arrayidx>
+; CHECK: Cost of 3 for VF 8: INTERLEAVE-GROUP with factor 4, ir<%arrayidx>
+; CHECK: Cost of 8 for VF 16: INTERLEAVE-GROUP with factor 4, ir<%arrayidx>
+;
entry:
br label %for.body
@@ -83,12 +87,13 @@ for.end:
}
define void @load_int_stride5() {
-;CHECK-LABEL: load_int_stride5
-;CHECK: Found an estimated cost of 1 for VF 1 For instruction: %1 = load
-;CHECK: Cost of 1 for VF 2: INTERLEAVE-GROUP with factor 5,
-;CHECK: Cost of 3 for VF 4: INTERLEAVE-GROUP with factor 5,
-;CHECK: Cost of 5 for VF 8: INTERLEAVE-GROUP with factor 5,
-;CHECK: Cost of 10 for VF 16: INTERLEAVE-GROUP with factor 5,
+; CHECK-LABEL: 'load_int_stride5'
+; CHECK: LV: Found an estimated cost of 1 for VF 1 For instruction: %1 = load i32, ptr %arrayidx, align 4
+; CHECK: Cost of 1 for VF 2: INTERLEAVE-GROUP with factor 5, ir<%arrayidx>
+; CHECK: Cost of 3 for VF 4: INTERLEAVE-GROUP with factor 5, ir<%arrayidx>
+; CHECK: Cost of 5 for VF 8: INTERLEAVE-GROUP with factor 5, ir<%arrayidx>
+; CHECK: Cost of 10 for VF 16: INTERLEAVE-GROUP with factor 5, ir<%arrayidx>
+;
entry:
br label %for.body
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/strided-load-i64.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/strided-load-i64.ll
index c9a3de926250f..49a5fc47944a8 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/strided-load-i64.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/strided-load-i64.ll
@@ -1,3 +1,4 @@
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Found an estimated cost of [0-9]+(.[0-9]+)? for VF [0-9]+ For instruction:\s*%1" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP" --version 6
; REQUIRES: asserts
; RUN: opt -passes=loop-vectorize -S -mattr=avx512f --debug-only=loop-vectorize --disable-output < %s 2>&1| FileCheck %s
@@ -8,11 +9,12 @@ target triple = "x86_64-unknown-linux-gnu"
@B = global [10240 x i64] zeroinitializer, align 16
define void @load_i64_stride2() {
-;CHECK-LABEL: load_i64_stride2
-;CHECK: Found an estimated cost of 1 for VF 1 For instruction: %1 = load
-;CHECK: Cost of 1 for VF 2: INTERLEAVE-GROUP with factor 2,
-;CHECK: Cost of 1 for VF 4: INTERLEAVE-GROUP with factor 2,
-;CHECK: Cost of 3 for VF 8: INTERLEAVE-GROUP with factor 2,
+; CHECK-LABEL: 'load_i64_stride2'
+; CHECK: LV: Found an estimated cost of 1 for VF 1 For instruction: %1 = load i64, ptr %arrayidx, align 16
+; CHECK: Cost of 1 for VF 2: INTERLEAVE-GROUP with factor 2, ir<%arrayidx>
+; CHECK: Cost of 1 for VF 4: INTERLEAVE-GROUP with factor 2, ir<%arrayidx>
+; CHECK: Cost of 3 for VF 8: INTERLEAVE-GROUP with factor 2, ir<%arrayidx>
+;
entry:
br label %for.body
@@ -32,11 +34,12 @@ for.end:
}
define void @load_i64_stride3() {
-;CHECK-LABEL: load_i64_stride3
-;CHECK: Found an estimated cost of 1 for VF 1 For instruction: %1 = load
-;CHECK: Cost of 1 for VF 2: INTERLEAVE-GROUP with factor 3,
-;CHECK: Cost of 3 for VF 4: INTERLEAVE-GROUP with factor 3,
-;CHECK: Cost of 5 for VF 8: INTERLEAVE-GROUP with factor 3,
+; CHECK-LABEL: 'load_i64_stride3'
+; CHECK: LV: Found an estimated cost of 1 for VF 1 For instruction: %1 = load i64, ptr %arrayidx, align 16
+; CHECK: Cost of 1 for VF 2: INTERLEAVE-GROUP with factor 3, ir<%arrayidx>
+; CHECK: Cost of 3 for VF 4: INTERLEAVE-GROUP with factor 3, ir<%arrayidx>
+; CHECK: Cost of 5 for VF 8: INTERLEAVE-GROUP with factor 3, ir<%arrayidx>
+;
entry:
br label %for.body
@@ -56,11 +59,12 @@ for.end:
}
define void @load_i64_stride4() {
-;CHECK-LABEL: load_i64_stride4
-;CHECK: Found an estimated cost of 1 for VF 1 For instruction: %1 = load
-;CHECK: Cost of 1 for VF 2: INTERLEAVE-GROUP with factor 4,
-;CHECK: Cost of 3 for VF 4: INTERLEAVE-GROUP with factor 4,
-;CHECK: Cost of 8 for VF 8: INTERLEAVE-GROUP with factor 4,
+; CHECK-LABEL: 'load_i64_stride4'
+; CHECK: LV: Found an estimated cost of 1 for VF 1 For instruction: %1 = load i64, ptr %arrayidx, align 16
+; CHECK: Cost of 1 for VF 2: INTERLEAVE-GROUP with factor 4, ir<%arrayidx>
+; CHECK: Cost of 3 for VF 4: INTERLEAVE-GROUP with factor 4, ir<%arrayidx>
+; CHECK: Cost of 8 for VF 8: INTERLEAVE-GROUP with factor 4, ir<%arrayidx>
+;
entry:
br label %for.body
diff --git a/llvm/test/Transforms/LoopVectorize/X86/CostModel/strided-load-i8.ll b/llvm/test/Transforms/LoopVectorize/X86/CostModel/strided-load-i8.ll
index df0a191ce638f..9ac785187cc1a 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/CostModel/strided-load-i8.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/CostModel/strided-load-i8.ll
@@ -1,3 +1,4 @@
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Found an estimated cost of [0-9]+(.[0-9]+)? for VF [0-9]+ For instruction:\s*%1" --filter "Cost of [0-9]+(.[0-9]+)? for VF [0-9]+: INTERLEAVE-GROUP" --version 6
; REQUIRES: asserts
; RUN: opt -passes=loop-vectorize -S -mattr=avx512bw --debug-only=loop-vectorize --disable-output < %s 2>&1| FileCheck %s
@@ -8,14 +9,15 @@ target triple = "x86_64-unknown-linux-gnu"
@B = global [10240 x i8] zeroinitializer, align 16
define void @load_i8_stride2() {
-;CHECK-LABEL: load_i8_stride2
-;CHECK: Found an estimated cost of 1 for VF 1 For instruction: %1 = load
-;CHECK: Cost of 1 for VF 2: INTERLEAVE-GROUP with factor 2,
-;CHECK: Cost of 1 for VF 4: INTERLEAVE-GROUP with factor 2,
-;CHECK: Cost of 1 for VF 8: INTERLEAVE-GROUP with factor 2,
-;CHECK: Cost of 4 for VF 16: INTERLEAVE-GROUP with factor 2,
-;CHECK: Cost of 8 for VF 32: INTERLEAVE-GROUP with factor 2,
-;CHECK: Cost of 20 for VF 64: INTERLEAVE-GROUP with factor 2,
+; CHECK-LABEL: 'load_i8_stride2'
+; CHECK: LV: Found an estimated cost of 1 for VF 1 For instruction: %1 = load i8, ptr %arrayidx, align 2
+; CHECK: Cost of 1 for VF 2: INTERLEAVE-GROUP with factor 2, ir<%arrayidx>
+; CHECK: Cost of 1 for VF 4: INTERLEAVE-GROUP with factor 2, ir<%arrayidx>
+; CHECK: Cost of 1 for VF 8: INTERLEAVE-GROUP with factor 2, ir<%arrayidx>
+; CHECK: Cost of 4 for VF 16: INTERLEAVE-GROUP with factor 2, ir<%arrayidx>
+; CHECK: Cost of 8 for VF 32: INTERLEAVE-GROUP with factor 2, ir<%arrayidx>
+; CHECK: Cost of 20 for VF 64: INTERLEAVE-GROUP with factor 2, ir<%arrayidx>
+;
entry:
br label %for.body
@@ -35,14 +37,15 @@ for.end:
}
define void @load_i8_stride3() {
-;CHECK-LABEL: load_i8_stride3
-;CHECK: Found an estimated cost of 1 for VF 1 For instruction: %1 = load
-;CHECK: Cost of 1 for VF 2: INTERLEAVE-GROUP with factor 3,
-;CHECK: Cost of 1 for VF 4: INTERLEAVE-GROUP with factor 3,
-;CHECK: Cost of 4 for VF 8: INTERLEAVE-GROUP with factor 3,
-;CHECK: Cost of 13 for VF 16: INTERLEAVE-GROUP with factor 3,
-;CHECK: Cost of 16 for VF 32: INTERLEAVE-GROUP with factor 3,
-;CHECK: Cost of 25 for VF 64: INTERLEAVE-GROUP with factor 3,
+; CHECK-LABEL: 'load_i8_stride3'
+; CHECK: LV: Found an estimated cost of 1 for VF 1 For instruction: %1 = load i8, ptr %arrayidx, align 2
+; CHECK: Cost of 1 for VF 2: INTERLEAVE-GROUP with factor 3, ir<%arrayidx>
+; CHECK: Cost of 1 for VF 4: INTERLEAVE-GROUP with factor 3, ir<%arrayidx>
+; CHECK: Cost of 4 for VF 8: INTERLEAVE-GROUP with factor 3, ir<%arrayidx>
+; CHECK: Cost of 13 for VF 16: INTERLEAVE-GROUP with factor 3, ir<%arrayidx>
+; CHECK: Cost of 16 for VF 32: INTERLEAVE-GROUP with factor 3, ir<%arrayidx>
+; CHECK: Cost of 25 for VF 64: INTERLEAVE-GROUP with factor 3, ir<%arrayidx>
+;
entry:
br label %for.body
@@ -62,14 +65,15 @@ for.end:
}
define void @load_i8_stride4() {
-;CHECK-LABEL: load_i8_stride4
-;CHECK: Found an estimated cost of 1 for VF 1 For instruction: %1 = load
-;CHECK: Cost of 1 for VF 2: INTERLEAVE-GROUP with factor 4,
-;CHECK: Cost of 1 for VF 4: INTERLEAVE-GROUP with factor 4,
-;CHECK: Cost of 4 for VF 8: INTERLEAVE-GROUP with factor 4,
-;CHECK: Cost of 8 for VF 16: INTERLEAVE-GROUP with factor 4,
-;CHECK: Cost of 20 for VF 32: INTERLEAVE-GROUP with factor 4,
-;CHECK: Cost of 59 for VF 64: INTERLEAVE-GROUP with factor 4,
+; CHECK-LABEL: 'load_i8_stride4'
+; CHECK: LV: Found an estimated cost of 1 for VF 1 For instruction: %1 = load i8, ptr %arrayidx, align 2
+; CHECK: Cost of 1 for VF 2: INTERLEAVE-GROUP with factor 4, ir<%arrayidx>
+; CHECK: Cost of 1 for VF 4: INTERLEAVE-GROUP with factor 4, ir<%arrayidx>
+; CHECK: Cost of 4 for VF 8: INTERLEAVE-GROUP with factor 4, ir<%arrayidx>
+; CHECK: Cost of 8 for VF 16: INTERLEAVE-GROUP with factor 4, ir<%arrayidx>
+; CHECK: Cost of 20 for VF 32: INTERLEAVE-GROUP with factor 4, ir<%arrayidx>
+; CHECK: Cost of 59 for VF 64: INTERLEAVE-GROUP with factor 4, ir<%arrayidx>
+;
entry:
br label %for.body
@@ -89,14 +93,15 @@ for.end:
}
define void @load_i8_stride5() {
-;CHECK-LABEL: load_i8_stride5
-;CHECK: Found an estimated cost of 1 for VF 1 For instruction: %1 = load
-;CHECK: Cost of 1 for VF 2: INTERLEAVE-GROUP with factor 5,
-;CHECK: Cost of 4 for VF 4: INTERLEAVE-GROUP with factor 5,
-;CHECK: Cost of 8 for VF 8: INTERLEAVE-GROUP with factor 5,
-;CHECK: Cost of 20 for VF 16: INTERLEAVE-GROUP with factor 5,
-;CHECK: Cost of 39 for VF 32: INTERLEAVE-GROUP with factor 5,
-;CHECK: Cost of 78 for VF 64: INTERLEAVE-GROUP with factor 5,
+; CHECK-LABEL: 'load_i8_stride5'
+; CHECK: LV: Found an estimated cost of 1 for VF 1 For instruction: %1 = load i8, ptr %arrayidx, align 2
+; CHECK: Cost of 1 for VF 2: INTERLEAVE-GROUP with factor 5, ir<%arrayidx>
+; CHECK: Cost of 4 for VF 4: INTERLEAVE-GROUP with factor 5, ir<%arrayidx>
+; CHECK: Cost of 8 for VF 8: INTERLEAVE-GROUP with factor 5, ir<%arrayidx>
+; CHECK: Cost of 20 for VF 16: INTERLEAVE-GROUP with factor 5, ir<%arrayidx>
+; CHECK: Cost of 39 for VF 32: INTERLEAVE-GROUP with factor 5, ir<%arrayidx>
+; CHECK: Cost of 78 for VF 64: INTERLEAVE-GROUP with factor 5, ir<%arrayidx>
+;
entry:
br label %for.body
More information about the llvm-commits
mailing list