caio/clang-p2996
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[Matrix] Update column.major.load call in PPC test.

Browse Source 
a1ef81de35 adjusted the definition of the intrinsic, but did not
update a PowerPC test. Fix the test by updating the call & declaration
of @llvm.matrix.column.major.load.
This commit is contained in:
Florian Hahn
2021-08-12 11:25:10 +01:00
parent 68616584c3
commit 1f87c7c478
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
llvm/test/Analysis/CostModel/PowerPC/matrix.ll
View File

@@ -8,15 +8,15 @@ target triple = "powerpc64-unknown-linux-gnu"
define void @matrix() {
; CHECK-LABEL: 'matrix'
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %matrix1 = call <1 x i32> @llvm.matrix.column.major.load.v1i32(i32* nonnull align 4 undef, i64 1, i1 false, i32 1, i32 1)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %matrix1 = call <1 x i32> @llvm.matrix.column.major.load.v1i32.i64(i32* nonnull align 4 undef, i64 1, i1 false, i32 1, i32 1)
; CHECK-NEXT: Cost Model: Found an estimated cost of 452 for instruction: %0 = call <10 x i32> @llvm.matrix.multiply.v10i32.v10i32.v1i32(<10 x i32> undef, <1 x i32> %matrix1, i32 10, i32 1, i32 1)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
entry:
%matrix1 = call <1 x i32> @llvm.matrix.column.major.load.v1i32(i32* nonnull align 4 undef, i64 1, i1 false, i32 1, i32 1)
%matrix1 = call <1 x i32> @llvm.matrix.column.major.load.v1i32.i64(i32* nonnull align 4 undef, i64 1, i1 false, i32 1, i32 1)
%0 = call <10 x i32> @llvm.matrix.multiply.v10i32.v10i32.v1i32(<10 x i32> undef, <1 x i32> %matrix1, i32 10, i32 1, i32 1)
ret void
}
declare <1 x i32> @llvm.matrix.column.major.load.v1i32(i32* nocapture, i64, i1 immarg, i32 immarg, i32 immarg) #2
declare <1 x i32> @llvm.matrix.column.major.load.v1i32.i64(i32* nocapture, i64, i1 immarg, i32 immarg, i32 immarg) #2
declare <10 x i32> @llvm.matrix.multiply.v10i32.v10i32.v1i32(<10 x i32>, <1 x i32>, i32 immarg, i32 immarg, i32 immarg) #3