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

[via llvm-commits]

https://github.com/sbite0138 created https://github.com/llvm/llvm-project/pull/100940

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.

>From bd93e831963fd18a3359832a5449ab3da37d66cd Mon Sep 17 00:00:00 2001
From: sbite0138 <24842740+sbite0138 at users.noreply.github.com>
Date: Sun, 28 Jul 2024 16:02:30 +0000
Subject: [PATCH] [LowerMatrixIntrinsics] Fix type suffix for matrix.multiply.*

---
 .../multiply-double-row-major.ll                     |  4 ++--
 .../LowerMatrixIntrinsics/multiply-double.ll         |  4 ++--
 .../LowerMatrixIntrinsics/multiply-i32-row-major.ll  | 12 ++++++------
 .../Transforms/LowerMatrixIntrinsics/multiply-i32.ll |  4 ++--
 4 files changed, 12 insertions(+), 12 deletions(-)

diff --git a/llvm/test/Transforms/LowerMatrixIntrinsics/multiply-double-row-major.ll b/llvm/test/Transforms/LowerMatrixIntrinsics/multiply-double-row-major.ll
index c196de17c4fe3..1638c1b1dd867 100644
--- a/llvm/test/Transforms/LowerMatrixIntrinsics/multiply-double-row-major.ll
+++ b/llvm/test/Transforms/LowerMatrixIntrinsics/multiply-double-row-major.ll
@@ -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)
diff --git a/llvm/test/Transforms/LowerMatrixIntrinsics/multiply-double.ll b/llvm/test/Transforms/LowerMatrixIntrinsics/multiply-double.ll
index c27dd0ceaea60..fa07c51630305 100644
--- a/llvm/test/Transforms/LowerMatrixIntrinsics/multiply-double.ll
+++ b/llvm/test/Transforms/LowerMatrixIntrinsics/multiply-double.ll
@@ -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)
diff --git a/llvm/test/Transforms/LowerMatrixIntrinsics/multiply-i32-row-major.ll b/llvm/test/Transforms/LowerMatrixIntrinsics/multiply-i32-row-major.ll
index d7e3f92354f5f..8ad9e2e77860a 100644
--- a/llvm/test/Transforms/LowerMatrixIntrinsics/multiply-i32-row-major.ll
+++ b/llvm/test/Transforms/LowerMatrixIntrinsics/multiply-i32-row-major.ll
@@ -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)
diff --git a/llvm/test/Transforms/LowerMatrixIntrinsics/multiply-i32.ll b/llvm/test/Transforms/LowerMatrixIntrinsics/multiply-i32.ll
index 1fbc7a2c0b87a..243cf84b64647 100644
--- a/llvm/test/Transforms/LowerMatrixIntrinsics/multiply-i32.ll
+++ b/llvm/test/Transforms/LowerMatrixIntrinsics/multiply-i32.ll
@@ -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)