[llvm] [LV] Update remaining tests to use VPlan cost output (NFC). (PR #190038)

Florian Hahn via llvm-commits llvm-commits at lists.llvm.org
Tue Apr 7 08:06:30 PDT 2026


================
@@ -14,99 +14,32 @@ 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: %v0 = load i64, ptr %in0, align 8
-; SSE2:  LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
-; SSE2:  LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
-; SSE2:  LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i64, ptr %in3, align 8
-; SSE2:  LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
-; SSE2:  LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
-; SSE2:  LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
-; SSE2:  LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i64, ptr %in3, align 8
-; SSE2:  LV: Found an estimated cost of 5 for VF 2 For instruction: %v0 = load i64, ptr %in0, align 8
-; SSE2:  LV: Found an estimated cost of 5 for VF 2 For instruction: %v1 = load i64, ptr %in1, align 8
-; SSE2:  LV: Found an estimated cost of 5 for VF 2 For instruction: %v2 = load i64, ptr %in2, align 8
-; SSE2:  LV: Found an estimated cost of 5 for VF 2 For instruction: %v3 = load i64, ptr %in3, align 8
-; SSE2:  LV: Found an estimated cost of 10 for VF 4 For instruction: %v0 = load i64, ptr %in0, align 8
-; SSE2:  LV: Found an estimated cost of 10 for VF 4 For instruction: %v1 = load i64, ptr %in1, align 8
-; SSE2:  LV: Found an estimated cost of 10 for VF 4 For instruction: %v2 = load i64, ptr %in2, align 8
-; SSE2:  LV: Found an estimated cost of 10 for VF 4 For instruction: %v3 = load i64, ptr %in3, align 8
+; SSE2:  Cost of 5 for VF 2: REPLICATE ir<%v0> = load ir<%in0>
+; SSE2:  Cost of 10 for VF 4: REPLICATE ir<%v0> = load ir<%in0>
+; SSE2:  Cost of 20 for VF 8: REPLICATE ir<%v0> = load ir<%in0>
+; SSE2:  Cost of 40 for VF 16: REPLICATE ir<%v0> = load ir<%in0>
 ;
 ; AVX1-LABEL: 'test'
 ; AVX1:  LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
-; AVX1:  LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
-; AVX1:  LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
-; AVX1:  LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i64, ptr %in3, align 8
-; AVX1:  LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
-; AVX1:  LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
-; AVX1:  LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
-; AVX1:  LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i64, ptr %in3, align 8
-; AVX1:  LV: Found an estimated cost of 4 for VF 2 For instruction: %v0 = load i64, ptr %in0, align 8
-; AVX1:  LV: Found an estimated cost of 4 for VF 2 For instruction: %v1 = load i64, ptr %in1, align 8
-; AVX1:  LV: Found an estimated cost of 4 for VF 2 For instruction: %v2 = load i64, ptr %in2, align 8
-; AVX1:  LV: Found an estimated cost of 4 for VF 2 For instruction: %v3 = load i64, ptr %in3, align 8
-; AVX1:  LV: Found an estimated cost of 9 for VF 4 For instruction: %v0 = load i64, ptr %in0, align 8
-; AVX1:  LV: Found an estimated cost of 9 for VF 4 For instruction: %v1 = load i64, ptr %in1, align 8
-; AVX1:  LV: Found an estimated cost of 9 for VF 4 For instruction: %v2 = load i64, ptr %in2, align 8
-; AVX1:  LV: Found an estimated cost of 9 for VF 4 For instruction: %v3 = load i64, ptr %in3, align 8
-; AVX1:  LV: Found an estimated cost of 18 for VF 8 For instruction: %v0 = load i64, ptr %in0, align 8
-; AVX1:  LV: Found an estimated cost of 18 for VF 8 For instruction: %v1 = load i64, ptr %in1, align 8
-; AVX1:  LV: Found an estimated cost of 18 for VF 8 For instruction: %v2 = load i64, ptr %in2, align 8
-; AVX1:  LV: Found an estimated cost of 18 for VF 8 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX1:  Cost of 4 for VF 2: REPLICATE ir<%v0> = load ir<%in0>
+; AVX1:  Cost of 9 for VF 4: REPLICATE ir<%v0> = load ir<%in0>
+; AVX1:  Cost of 18 for VF 8: REPLICATE ir<%v0> = load ir<%in0>
+; AVX1:  Cost of 36 for VF 16: REPLICATE ir<%v0> = load ir<%in0>
+; AVX1:  Cost of 72 for VF 32: REPLICATE ir<%v0> = load ir<%in0>
 ;
 ; AVX2-LABEL: 'test'
 ; AVX2:  LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
-; AVX2:  LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
-; AVX2:  LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
-; AVX2:  LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i64, ptr %in3, align 8
-; AVX2:  LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
-; AVX2:  LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
-; AVX2:  LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
-; AVX2:  LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i64, ptr %in3, align 8
-; AVX2:  LV: Found an estimated cost of 8 for VF 2 For instruction: %v0 = load i64, ptr %in0, align 8
-; AVX2:  LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i64, ptr %in1, align 8
-; AVX2:  LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i64, ptr %in2, align 8
-; AVX2:  LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i64, ptr %in3, align 8
-; AVX2:  LV: Found an estimated cost of 12 for VF 4 For instruction: %v0 = load i64, ptr %in0, align 8
-; AVX2:  LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i64, ptr %in1, align 8
-; AVX2:  LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i64, ptr %in2, align 8
-; AVX2:  LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i64, ptr %in3, align 8
-; AVX2:  LV: Found an estimated cost of 28 for VF 8 For instruction: %v0 = load i64, ptr %in0, align 8
-; AVX2:  LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i64, ptr %in1, align 8
-; AVX2:  LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i64, ptr %in2, align 8
-; AVX2:  LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i64, ptr %in3, align 8
-; AVX2:  LV: Found an estimated cost of 72 for VF 32 For instruction: %v0 = load i64, ptr %in0, align 8
-; AVX2:  LV: Found an estimated cost of 72 for VF 32 For instruction: %v1 = load i64, ptr %in1, align 8
-; AVX2:  LV: Found an estimated cost of 72 for VF 32 For instruction: %v2 = load i64, ptr %in2, align 8
-; AVX2:  LV: Found an estimated cost of 72 for VF 32 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX2:  Cost of 8 for VF 2: INTERLEAVE-GROUP with factor 4 at %v0, ir<%in0>
+; AVX2:  Cost of 12 for VF 4: INTERLEAVE-GROUP with factor 4 at %v0, ir<%in0>
+; AVX2:  Cost of 28 for VF 8: INTERLEAVE-GROUP with factor 4 at %v0, ir<%in0>
+; AVX2:  Cost of 56 for VF 16: INTERLEAVE-GROUP with factor 4 at %v0, ir<%in0>
+; AVX2:  Cost of 72 for VF 32: REPLICATE ir<%v0> = load ir<%in0>
 ;
 ; AVX512-LABEL: 'test'
 ; AVX512:  LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
-; AVX512:  LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
-; AVX512:  LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
-; AVX512:  LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i64, ptr %in3, align 8
-; AVX512:  LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, ptr %in0, align 8
-; AVX512:  LV: Found an estimated cost of 1 for VF 1 For instruction: %v1 = load i64, ptr %in1, align 8
-; AVX512:  LV: Found an estimated cost of 1 for VF 1 For instruction: %v2 = load i64, ptr %in2, align 8
-; AVX512:  LV: Found an estimated cost of 1 for VF 1 For instruction: %v3 = load i64, ptr %in3, align 8
-; AVX512:  LV: Found an estimated cost of 5 for VF 2 For instruction: %v0 = load i64, ptr %in0, align 8
-; AVX512:  LV: Found an estimated cost of 0 for VF 2 For instruction: %v1 = load i64, ptr %in1, align 8
-; AVX512:  LV: Found an estimated cost of 0 for VF 2 For instruction: %v2 = load i64, ptr %in2, align 8
-; AVX512:  LV: Found an estimated cost of 0 for VF 2 For instruction: %v3 = load i64, ptr %in3, align 8
-; AVX512:  LV: Found an estimated cost of 8 for VF 4 For instruction: %v0 = load i64, ptr %in0, align 8
-; AVX512:  LV: Found an estimated cost of 0 for VF 4 For instruction: %v1 = load i64, ptr %in1, align 8
-; AVX512:  LV: Found an estimated cost of 0 for VF 4 For instruction: %v2 = load i64, ptr %in2, align 8
-; AVX512:  LV: Found an estimated cost of 0 for VF 4 For instruction: %v3 = load i64, ptr %in3, align 8
-; AVX512:  LV: Found an estimated cost of 22 for VF 8 For instruction: %v0 = load i64, ptr %in0, align 8
-; AVX512:  LV: Found an estimated cost of 0 for VF 8 For instruction: %v1 = load i64, ptr %in1, align 8
-; AVX512:  LV: Found an estimated cost of 0 for VF 8 For instruction: %v2 = load i64, ptr %in2, align 8
-; AVX512:  LV: Found an estimated cost of 0 for VF 8 For instruction: %v3 = load i64, ptr %in3, align 8
-; AVX512:  LV: Found an estimated cost of 20 for VF 16 For instruction: %v0 = load i64, ptr %in0, align 8
-; AVX512:  LV: Found an estimated cost of 20 for VF 16 For instruction: %v1 = load i64, ptr %in1, align 8
-; AVX512:  LV: Found an estimated cost of 20 for VF 16 For instruction: %v2 = load i64, ptr %in2, align 8
-; AVX512:  LV: Found an estimated cost of 20 for VF 16 For instruction: %v3 = load i64, ptr %in3, align 8
-; AVX512:  LV: Found an estimated cost of 40 for VF 32 For instruction: %v0 = load i64, ptr %in0, align 8
-; AVX512:  LV: Found an estimated cost of 40 for VF 32 For instruction: %v1 = load i64, ptr %in1, align 8
-; AVX512:  LV: Found an estimated cost of 40 for VF 32 For instruction: %v2 = load i64, ptr %in2, align 8
-; AVX512:  LV: Found an estimated cost of 40 for VF 32 For instruction: %v3 = load i64, ptr %in3, align 8
+; AVX512:  Cost of 5 for VF 2: INTERLEAVE-GROUP with factor 4 at %v0, ir<%in0>
+; AVX512:  Cost of 8 for VF 4: INTERLEAVE-GROUP with factor 4 at %v0, ir<%in0>
+; AVX512:  Cost of 22 for VF 8: INTERLEAVE-GROUP with factor 4 at %v0, ir<%in0>
----------------
fhahn wrote:

should be added back and filter updated, thanks

https://github.com/llvm/llvm-project/pull/190038


More information about the llvm-commits mailing list