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

[LowerMatrixIntrinsics] Fix type suffix for matrix.multiply.* (#100940)

Browse Source 
Based on the [proposal
PDF](https://llvm.org/devmtg/2020-09/slides/Hahn-Matrix_Support_in_LLVM_and_Clang.pdf)
and the test code under
[llvm/test/Transforms/LowerMatrixIntrinsics](https://github.com/llvm/llvm-project/tree/main/llvm/test/Transforms/LowerMatrixIntrinsics),
the suffix for the `@llvm.matrix.multiply.*` intrinsic should be {output
matrix type}.{input matrix 1 type}.{input matrix 2 type} (e.g.,
`@llvm.matrix.multiply.v4i32.v4i32.v4i32`).

This PR corrects the places where these suffixes do not follow the
aforementioned format.
This commit is contained in:
sbite0138
2024-08-01 19:47:35 +09:00
committed by GitHub
parent 67730ae19c
commit 05d3f5ed91
4 changed files with 12 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
llvm/test/Transforms/LowerMatrixIntrinsics/multiply-double-row-major.ll
View File

@@ -246,8 +246,8 @@ define <9 x double> @multiply_2x3(<6 x double> %a, <6 x double> %b) {
; CHECK-NEXT: ret <9 x double> [[TMP65]]
;
entry:
%c = call <9 x double> @llvm.matrix.multiply.v6f64.v6f64.v6f64(<6 x double> %a, <6 x double> %b, i32 3, i32 2, i32 3)
%c = call <9 x double> @llvm.matrix.multiply.v9f64.v6f64.v6f64(<6 x double> %a, <6 x double> %b, i32 3, i32 2, i32 3)
ret <9 x double> %c
}
declare <9 x double> @llvm.matrix.multiply.v6f64.v6f64.v6f64(<6 x double>, <6 x double>, i32, i32, i32)
declare <9 x double> @llvm.matrix.multiply.v9f64.v6f64.v6f64(<6 x double>, <6 x double>, i32, i32, i32)

4
llvm/test/Transforms/LowerMatrixIntrinsics/multiply-double.ll
View File

@@ -246,8 +246,8 @@ define <9 x double> @multiply_2x3(<6 x double> %a, <6 x double> %b) {
; CHECK-NEXT: ret <9 x double> [[TMP65]]
;
entry:
%c = call <9 x double> @llvm.matrix.multiply.v6f64.v6f64.v6f64(<6 x double> %a, <6 x double> %b, i32 3, i32 2, i32 3)
%c = call <9 x double> @llvm.matrix.multiply.v9f64.v6f64.v6f64(<6 x double> %a, <6 x double> %b, i32 3, i32 2, i32 3)
ret <9 x double> %c
}
declare <9 x double> @llvm.matrix.multiply.v6f64.v6f64.v6f64(<6 x double>, <6 x double>, i32, i32, i32)
declare <9 x double> @llvm.matrix.multiply.v9f64.v6f64.v6f64(<6 x double>, <6 x double>, i32, i32, i32)

12
llvm/test/Transforms/LowerMatrixIntrinsics/multiply-i32-row-major.ll
View File

@@ -67,11 +67,11 @@ define <4 x i32> @multiply_2x2(<4 x i32> %a, <4 x i32> %b) {
; RM-NEXT: ret <4 x i32> [[TMP28]]
;
entry:
%c = call <4 x i32> @llvm.matrix.multiply.v4f64.v4f64.v4f64(<4 x i32> %a, <4 x i32> %b, i32 2, i32 2, i32 2)
%c = call <4 x i32> @llvm.matrix.multiply.v4i32.v4i32.v4i32(<4 x i32> %a, <4 x i32> %b, i32 2, i32 2, i32 2)
ret <4 x i32> %c
}
declare <4 x i32> @llvm.matrix.multiply.v4f64.v4f64.v4f64(<4 x i32>, <4 x i32>, i32, i32, i32)
declare <4 x i32> @llvm.matrix.multiply.v4i32.v4i32.v4i32(<4 x i32>, <4 x i32>, i32, i32, i32)
define <4 x i32> @multiply_1x2(<2 x i32> %a, <2 x i32> %b) {
; RM-LABEL: @multiply_1x2(
@@ -111,11 +111,11 @@ define <4 x i32> @multiply_1x2(<2 x i32> %a, <2 x i32> %b) {
; RM-NEXT: ret <4 x i32> [[TMP16]]
;
entry:
%c = call <4 x i32> @llvm.matrix.multiply.v4f64.v2f64.v2f64(<2 x i32> %a, <2 x i32> %b, i32 2, i32 1, i32 2)
%c = call <4 x i32> @llvm.matrix.multiply.v4i32.v2i32.v2i32(<2 x i32> %a, <2 x i32> %b, i32 2, i32 1, i32 2)
ret <4 x i32> %c
}
declare <4 x i32> @llvm.matrix.multiply.v4f64.v2f64.v2f64(<2 x i32>, <2 x i32>, i32, i32, i32)
declare <4 x i32> @llvm.matrix.multiply.v4i32.v2i32.v2i32(<2 x i32>, <2 x i32>, i32, i32, i32)
define <9 x i32> @multiply_2x3(<6 x i32> %a, <6 x i32> %b) {
; RM-LABEL: @multiply_2x3(
@@ -248,8 +248,8 @@ define <9 x i32> @multiply_2x3(<6 x i32> %a, <6 x i32> %b) {
; RM-NEXT: ret <9 x i32> [[TMP65]]
;
entry:
%c = call <9 x i32> @llvm.matrix.multiply.v6f64.v6f64.v6f64(<6 x i32> %a, <6 x i32> %b, i32 3, i32 2, i32 3)
%c = call <9 x i32> @llvm.matrix.multiply.v9i32.v6i32.v6i32(<6 x i32> %a, <6 x i32> %b, i32 3, i32 2, i32 3)
ret <9 x i32> %c
}
declare <9 x i32> @llvm.matrix.multiply.v6f64.v6f64.v6f64(<6 x i32>, <6 x i32>, i32, i32, i32)
declare <9 x i32> @llvm.matrix.multiply.v9i32.v6i32.v6i32(<6 x i32>, <6 x i32>, i32, i32, i32)

4
llvm/test/Transforms/LowerMatrixIntrinsics/multiply-i32.ll
View File

@@ -246,8 +246,8 @@ define <9 x i32> @multiply_2x3(<6 x i32> %a, <6 x i32> %b) {
; CHECK-NEXT: ret <9 x i32> [[TMP65]]
;
entry:
%c = call <9 x i32> @llvm.matrix.multiply.v6i32.v6i32.v6i32(<6 x i32> %a, <6 x i32> %b, i32 3, i32 2, i32 3)
%c = call <9 x i32> @llvm.matrix.multiply.v9i32.v6i32.v6i32(<6 x i32> %a, <6 x i32> %b, i32 3, i32 2, i32 3)
ret <9 x i32> %c
}
declare <9 x i32> @llvm.matrix.multiply.v6i32.v6i32.v6i32(<6 x i32>, <6 x i32>, i32, i32, i32)
declare <9 x i32> @llvm.matrix.multiply.v9i32.v6i32.v6i32(<6 x i32>, <6 x i32>, i32, i32, i32)