[llvm] c0dbe85 - [Matrix] Fix shapes in dot product tests.
Florian Hahn via llvm-commits
llvm-commits at lists.llvm.org
Mon Apr 3 04:51:04 PDT 2023
Author: Florian Hahn
Date: 2023-04-03T12:50:05+01:00
New Revision: c0dbe857907ff7f8549dc35059c21564f4ad91ed
URL: https://github.com/llvm/llvm-project/commit/c0dbe857907ff7f8549dc35059c21564f4ad91ed
DIFF: https://github.com/llvm/llvm-project/commit/c0dbe857907ff7f8549dc35059c21564f4ad91ed.diff
LOG: [Matrix] Fix shapes in dot product tests.
The shape arguments for the @llvm.matrix.column.major.load where
incorrect. Flip them so they are in sync with the shape of the
multiplications.
Added:
Modified:
llvm/test/Transforms/LowerMatrixIntrinsics/dot-product-float.ll
llvm/test/Transforms/LowerMatrixIntrinsics/dot-product-int.ll
Removed:
################################################################################
diff --git a/llvm/test/Transforms/LowerMatrixIntrinsics/dot-product-float.ll b/llvm/test/Transforms/LowerMatrixIntrinsics/dot-product-float.ll
index 1d09bacc9e90a..cbf1e7126443e 100644
--- a/llvm/test/Transforms/LowerMatrixIntrinsics/dot-product-float.ll
+++ b/llvm/test/Transforms/LowerMatrixIntrinsics/dot-product-float.ll
@@ -110,68 +110,55 @@ declare <1 x float> @llvm.matrix.multiply.v1f32.v3f32.v3f32(<3 x float>, <3 x fl
define <1 x float> @intrinsic_column_major_load_dot_product_float_v6(ptr %lhs_address, ptr %rhs_address) {
; CHECK-LABEL: @intrinsic_column_major_load_dot_product_float_v6(
; CHECK-NEXT: entry:
-; CHECK-NEXT: [[COL_LOAD:%.*]] = load <6 x float>, ptr [[LHS_ADDRESS:%.*]], align 4
-; CHECK-NEXT: [[COL_LOAD1:%.*]] = load <1 x float>, ptr [[RHS_ADDRESS:%.*]], align 4
-; CHECK-NEXT: [[VEC_GEP:%.*]] = getelementptr float, ptr [[RHS_ADDRESS]], i64 1
-; CHECK-NEXT: [[COL_LOAD2:%.*]] = load <1 x float>, ptr [[VEC_GEP]], align 4
-; CHECK-NEXT: [[VEC_GEP3:%.*]] = getelementptr float, ptr [[RHS_ADDRESS]], i64 2
-; CHECK-NEXT: [[COL_LOAD4:%.*]] = load <1 x float>, ptr [[VEC_GEP3]], align 4
-; CHECK-NEXT: [[VEC_GEP5:%.*]] = getelementptr float, ptr [[RHS_ADDRESS]], i64 3
-; CHECK-NEXT: [[COL_LOAD6:%.*]] = load <1 x float>, ptr [[VEC_GEP5]], align 4
-; CHECK-NEXT: [[VEC_GEP7:%.*]] = getelementptr float, ptr [[RHS_ADDRESS]], i64 4
-; CHECK-NEXT: [[COL_LOAD8:%.*]] = load <1 x float>, ptr [[VEC_GEP7]], align 4
-; CHECK-NEXT: [[VEC_GEP9:%.*]] = getelementptr float, ptr [[RHS_ADDRESS]], i64 5
-; CHECK-NEXT: [[COL_LOAD10:%.*]] = load <1 x float>, ptr [[VEC_GEP9]], align 4
-; CHECK-NEXT: [[SPLIT:%.*]] = shufflevector <6 x float> [[COL_LOAD]], <6 x float> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT: [[SPLIT11:%.*]] = shufflevector <6 x float> [[COL_LOAD]], <6 x float> poison, <1 x i32> <i32 1>
-; CHECK-NEXT: [[SPLIT12:%.*]] = shufflevector <6 x float> [[COL_LOAD]], <6 x float> poison, <1 x i32> <i32 2>
-; CHECK-NEXT: [[SPLIT13:%.*]] = shufflevector <6 x float> [[COL_LOAD]], <6 x float> poison, <1 x i32> <i32 3>
-; CHECK-NEXT: [[SPLIT14:%.*]] = shufflevector <6 x float> [[COL_LOAD]], <6 x float> poison, <1 x i32> <i32 4>
-; CHECK-NEXT: [[SPLIT15:%.*]] = shufflevector <6 x float> [[COL_LOAD]], <6 x float> poison, <1 x i32> <i32 5>
-; CHECK-NEXT: [[TMP0:%.*]] = shufflevector <1 x float> [[COL_LOAD1]], <1 x float> [[COL_LOAD2]], <2 x i32> <i32 0, i32 1>
-; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <1 x float> [[COL_LOAD4]], <1 x float> [[COL_LOAD6]], <2 x i32> <i32 0, i32 1>
-; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <1 x float> [[COL_LOAD8]], <1 x float> [[COL_LOAD10]], <2 x i32> <i32 0, i32 1>
-; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <2 x float> [[TMP0]], <2 x float> [[TMP1]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; CHECK-NEXT: [[TMP4:%.*]] = shufflevector <2 x float> [[TMP2]], <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
-; CHECK-NEXT: [[TMP5:%.*]] = shufflevector <4 x float> [[TMP3]], <4 x float> [[TMP4]], <6 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5>
-; CHECK-NEXT: [[SPLIT16:%.*]] = shufflevector <6 x float> [[TMP5]], <6 x float> poison, <6 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5>
-; CHECK-NEXT: [[BLOCK:%.*]] = shufflevector <1 x float> [[SPLIT]], <1 x float> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP6:%.*]] = extractelement <6 x float> [[SPLIT16]], i64 0
-; CHECK-NEXT: [[SPLAT_SPLATINSERT:%.*]] = insertelement <1 x float> poison, float [[TMP6]], i64 0
+; CHECK-NEXT: [[COL_LOAD:%.*]] = load <1 x float>, ptr [[LHS_ADDRESS:%.*]], align 4
+; CHECK-NEXT: [[VEC_GEP:%.*]] = getelementptr float, ptr [[LHS_ADDRESS]], i64 1
+; CHECK-NEXT: [[COL_LOAD1:%.*]] = load <1 x float>, ptr [[VEC_GEP]], align 4
+; CHECK-NEXT: [[VEC_GEP2:%.*]] = getelementptr float, ptr [[LHS_ADDRESS]], i64 2
+; CHECK-NEXT: [[COL_LOAD3:%.*]] = load <1 x float>, ptr [[VEC_GEP2]], align 4
+; CHECK-NEXT: [[VEC_GEP4:%.*]] = getelementptr float, ptr [[LHS_ADDRESS]], i64 3
+; CHECK-NEXT: [[COL_LOAD5:%.*]] = load <1 x float>, ptr [[VEC_GEP4]], align 4
+; CHECK-NEXT: [[VEC_GEP6:%.*]] = getelementptr float, ptr [[LHS_ADDRESS]], i64 4
+; CHECK-NEXT: [[COL_LOAD7:%.*]] = load <1 x float>, ptr [[VEC_GEP6]], align 4
+; CHECK-NEXT: [[VEC_GEP8:%.*]] = getelementptr float, ptr [[LHS_ADDRESS]], i64 5
+; CHECK-NEXT: [[COL_LOAD9:%.*]] = load <1 x float>, ptr [[VEC_GEP8]], align 4
+; CHECK-NEXT: [[COL_LOAD10:%.*]] = load <6 x float>, ptr [[RHS_ADDRESS:%.*]], align 4
+; CHECK-NEXT: [[BLOCK:%.*]] = shufflevector <1 x float> [[COL_LOAD]], <1 x float> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP0:%.*]] = extractelement <6 x float> [[COL_LOAD10]], i64 0
+; CHECK-NEXT: [[SPLAT_SPLATINSERT:%.*]] = insertelement <1 x float> poison, float [[TMP0]], i64 0
; CHECK-NEXT: [[SPLAT_SPLAT:%.*]] = shufflevector <1 x float> [[SPLAT_SPLATINSERT]], <1 x float> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP7:%.*]] = fmul fast <1 x float> [[BLOCK]], [[SPLAT_SPLAT]]
-; CHECK-NEXT: [[BLOCK17:%.*]] = shufflevector <1 x float> [[SPLIT11]], <1 x float> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP8:%.*]] = extractelement <6 x float> [[SPLIT16]], i64 1
-; CHECK-NEXT: [[SPLAT_SPLATINSERT18:%.*]] = insertelement <1 x float> poison, float [[TMP8]], i64 0
+; CHECK-NEXT: [[TMP1:%.*]] = fmul fast <1 x float> [[BLOCK]], [[SPLAT_SPLAT]]
+; CHECK-NEXT: [[BLOCK11:%.*]] = shufflevector <1 x float> [[COL_LOAD1]], <1 x float> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP2:%.*]] = extractelement <6 x float> [[COL_LOAD10]], i64 1
+; CHECK-NEXT: [[SPLAT_SPLATINSERT12:%.*]] = insertelement <1 x float> poison, float [[TMP2]], i64 0
+; CHECK-NEXT: [[SPLAT_SPLAT13:%.*]] = shufflevector <1 x float> [[SPLAT_SPLATINSERT12]], <1 x float> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP3:%.*]] = call fast <1 x float> @llvm.fmuladd.v1f32(<1 x float> [[BLOCK11]], <1 x float> [[SPLAT_SPLAT13]], <1 x float> [[TMP1]])
+; CHECK-NEXT: [[BLOCK14:%.*]] = shufflevector <1 x float> [[COL_LOAD3]], <1 x float> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP4:%.*]] = extractelement <6 x float> [[COL_LOAD10]], i64 2
+; CHECK-NEXT: [[SPLAT_SPLATINSERT15:%.*]] = insertelement <1 x float> poison, float [[TMP4]], i64 0
+; CHECK-NEXT: [[SPLAT_SPLAT16:%.*]] = shufflevector <1 x float> [[SPLAT_SPLATINSERT15]], <1 x float> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP5:%.*]] = call fast <1 x float> @llvm.fmuladd.v1f32(<1 x float> [[BLOCK14]], <1 x float> [[SPLAT_SPLAT16]], <1 x float> [[TMP3]])
+; CHECK-NEXT: [[BLOCK17:%.*]] = shufflevector <1 x float> [[COL_LOAD5]], <1 x float> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP6:%.*]] = extractelement <6 x float> [[COL_LOAD10]], i64 3
+; CHECK-NEXT: [[SPLAT_SPLATINSERT18:%.*]] = insertelement <1 x float> poison, float [[TMP6]], i64 0
; CHECK-NEXT: [[SPLAT_SPLAT19:%.*]] = shufflevector <1 x float> [[SPLAT_SPLATINSERT18]], <1 x float> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP9:%.*]] = call fast <1 x float> @llvm.fmuladd.v1f32(<1 x float> [[BLOCK17]], <1 x float> [[SPLAT_SPLAT19]], <1 x float> [[TMP7]])
-; CHECK-NEXT: [[BLOCK20:%.*]] = shufflevector <1 x float> [[SPLIT12]], <1 x float> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP10:%.*]] = extractelement <6 x float> [[SPLIT16]], i64 2
-; CHECK-NEXT: [[SPLAT_SPLATINSERT21:%.*]] = insertelement <1 x float> poison, float [[TMP10]], i64 0
+; CHECK-NEXT: [[TMP7:%.*]] = call fast <1 x float> @llvm.fmuladd.v1f32(<1 x float> [[BLOCK17]], <1 x float> [[SPLAT_SPLAT19]], <1 x float> [[TMP5]])
+; CHECK-NEXT: [[BLOCK20:%.*]] = shufflevector <1 x float> [[COL_LOAD7]], <1 x float> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP8:%.*]] = extractelement <6 x float> [[COL_LOAD10]], i64 4
+; CHECK-NEXT: [[SPLAT_SPLATINSERT21:%.*]] = insertelement <1 x float> poison, float [[TMP8]], i64 0
; CHECK-NEXT: [[SPLAT_SPLAT22:%.*]] = shufflevector <1 x float> [[SPLAT_SPLATINSERT21]], <1 x float> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP11:%.*]] = call fast <1 x float> @llvm.fmuladd.v1f32(<1 x float> [[BLOCK20]], <1 x float> [[SPLAT_SPLAT22]], <1 x float> [[TMP9]])
-; CHECK-NEXT: [[BLOCK23:%.*]] = shufflevector <1 x float> [[SPLIT13]], <1 x float> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP12:%.*]] = extractelement <6 x float> [[SPLIT16]], i64 3
-; CHECK-NEXT: [[SPLAT_SPLATINSERT24:%.*]] = insertelement <1 x float> poison, float [[TMP12]], i64 0
+; CHECK-NEXT: [[TMP9:%.*]] = call fast <1 x float> @llvm.fmuladd.v1f32(<1 x float> [[BLOCK20]], <1 x float> [[SPLAT_SPLAT22]], <1 x float> [[TMP7]])
+; CHECK-NEXT: [[BLOCK23:%.*]] = shufflevector <1 x float> [[COL_LOAD9]], <1 x float> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP10:%.*]] = extractelement <6 x float> [[COL_LOAD10]], i64 5
+; CHECK-NEXT: [[SPLAT_SPLATINSERT24:%.*]] = insertelement <1 x float> poison, float [[TMP10]], i64 0
; CHECK-NEXT: [[SPLAT_SPLAT25:%.*]] = shufflevector <1 x float> [[SPLAT_SPLATINSERT24]], <1 x float> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP13:%.*]] = call fast <1 x float> @llvm.fmuladd.v1f32(<1 x float> [[BLOCK23]], <1 x float> [[SPLAT_SPLAT25]], <1 x float> [[TMP11]])
-; CHECK-NEXT: [[BLOCK26:%.*]] = shufflevector <1 x float> [[SPLIT14]], <1 x float> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP14:%.*]] = extractelement <6 x float> [[SPLIT16]], i64 4
-; CHECK-NEXT: [[SPLAT_SPLATINSERT27:%.*]] = insertelement <1 x float> poison, float [[TMP14]], i64 0
-; CHECK-NEXT: [[SPLAT_SPLAT28:%.*]] = shufflevector <1 x float> [[SPLAT_SPLATINSERT27]], <1 x float> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP15:%.*]] = call fast <1 x float> @llvm.fmuladd.v1f32(<1 x float> [[BLOCK26]], <1 x float> [[SPLAT_SPLAT28]], <1 x float> [[TMP13]])
-; CHECK-NEXT: [[BLOCK29:%.*]] = shufflevector <1 x float> [[SPLIT15]], <1 x float> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP16:%.*]] = extractelement <6 x float> [[SPLIT16]], i64 5
-; CHECK-NEXT: [[SPLAT_SPLATINSERT30:%.*]] = insertelement <1 x float> poison, float [[TMP16]], i64 0
-; CHECK-NEXT: [[SPLAT_SPLAT31:%.*]] = shufflevector <1 x float> [[SPLAT_SPLATINSERT30]], <1 x float> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP17:%.*]] = call fast <1 x float> @llvm.fmuladd.v1f32(<1 x float> [[BLOCK29]], <1 x float> [[SPLAT_SPLAT31]], <1 x float> [[TMP15]])
-; CHECK-NEXT: [[TMP18:%.*]] = shufflevector <1 x float> [[TMP17]], <1 x float> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP19:%.*]] = shufflevector <1 x float> undef, <1 x float> [[TMP18]], <1 x i32> <i32 1>
-; CHECK-NEXT: ret <1 x float> [[TMP19]]
+; CHECK-NEXT: [[TMP11:%.*]] = call fast <1 x float> @llvm.fmuladd.v1f32(<1 x float> [[BLOCK23]], <1 x float> [[SPLAT_SPLAT25]], <1 x float> [[TMP9]])
+; CHECK-NEXT: [[TMP12:%.*]] = shufflevector <1 x float> [[TMP11]], <1 x float> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP13:%.*]] = shufflevector <1 x float> undef, <1 x float> [[TMP12]], <1 x i32> <i32 1>
+; CHECK-NEXT: ret <1 x float> [[TMP13]]
;
entry:
- %lhs = tail call fast <6 x float> @llvm.matrix.column.major.load.v6f32.i64(ptr nonnull align 4 %lhs_address, i64 6, i1 false, i32 6, i32 1)
- %rhs = tail call fast <6 x float> @llvm.matrix.column.major.load.v6f32.i64(ptr nonnull align 4 %rhs_address, i64 1, i1 false, i32 1, i32 6)
+ %lhs = tail call fast <6 x float> @llvm.matrix.column.major.load.v6f32.i64(ptr nonnull align 4 %lhs_address, i64 1, i1 false, i32 1, i32 6)
+ %rhs = tail call fast <6 x float> @llvm.matrix.column.major.load.v6f32.i64(ptr nonnull align 4 %rhs_address, i64 6, i1 false, i32 6, i32 1)
%result = tail call fast <1 x float> @llvm.matrix.multiply.v1f32.v6f32.v6f32(<6 x float> %lhs, <6 x float> %rhs, i32 1, i32 6, i32 1)
ret <1 x float> %result
}
@@ -297,68 +284,55 @@ declare <1 x double> @llvm.matrix.multiply.v1f64.v6f64.v6f64(<6 x double>, <6 x
define <1 x double> @intrinsic_column_major_load_dot_product_double_v6(ptr %lhs_address, ptr %rhs_address) {
; CHECK-LABEL: @intrinsic_column_major_load_dot_product_double_v6(
; CHECK-NEXT: entry:
-; CHECK-NEXT: [[COL_LOAD:%.*]] = load <6 x double>, ptr [[LHS_ADDRESS:%.*]], align 4
-; CHECK-NEXT: [[COL_LOAD1:%.*]] = load <1 x double>, ptr [[RHS_ADDRESS:%.*]], align 4
-; CHECK-NEXT: [[VEC_GEP:%.*]] = getelementptr double, ptr [[RHS_ADDRESS]], i64 1
-; CHECK-NEXT: [[COL_LOAD2:%.*]] = load <1 x double>, ptr [[VEC_GEP]], align 4
-; CHECK-NEXT: [[VEC_GEP3:%.*]] = getelementptr double, ptr [[RHS_ADDRESS]], i64 2
-; CHECK-NEXT: [[COL_LOAD4:%.*]] = load <1 x double>, ptr [[VEC_GEP3]], align 4
-; CHECK-NEXT: [[VEC_GEP5:%.*]] = getelementptr double, ptr [[RHS_ADDRESS]], i64 3
-; CHECK-NEXT: [[COL_LOAD6:%.*]] = load <1 x double>, ptr [[VEC_GEP5]], align 4
-; CHECK-NEXT: [[VEC_GEP7:%.*]] = getelementptr double, ptr [[RHS_ADDRESS]], i64 4
-; CHECK-NEXT: [[COL_LOAD8:%.*]] = load <1 x double>, ptr [[VEC_GEP7]], align 4
-; CHECK-NEXT: [[VEC_GEP9:%.*]] = getelementptr double, ptr [[RHS_ADDRESS]], i64 5
-; CHECK-NEXT: [[COL_LOAD10:%.*]] = load <1 x double>, ptr [[VEC_GEP9]], align 4
-; CHECK-NEXT: [[SPLIT:%.*]] = shufflevector <6 x double> [[COL_LOAD]], <6 x double> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT: [[SPLIT11:%.*]] = shufflevector <6 x double> [[COL_LOAD]], <6 x double> poison, <1 x i32> <i32 1>
-; CHECK-NEXT: [[SPLIT12:%.*]] = shufflevector <6 x double> [[COL_LOAD]], <6 x double> poison, <1 x i32> <i32 2>
-; CHECK-NEXT: [[SPLIT13:%.*]] = shufflevector <6 x double> [[COL_LOAD]], <6 x double> poison, <1 x i32> <i32 3>
-; CHECK-NEXT: [[SPLIT14:%.*]] = shufflevector <6 x double> [[COL_LOAD]], <6 x double> poison, <1 x i32> <i32 4>
-; CHECK-NEXT: [[SPLIT15:%.*]] = shufflevector <6 x double> [[COL_LOAD]], <6 x double> poison, <1 x i32> <i32 5>
-; CHECK-NEXT: [[TMP0:%.*]] = shufflevector <1 x double> [[COL_LOAD1]], <1 x double> [[COL_LOAD2]], <2 x i32> <i32 0, i32 1>
-; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <1 x double> [[COL_LOAD4]], <1 x double> [[COL_LOAD6]], <2 x i32> <i32 0, i32 1>
-; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <1 x double> [[COL_LOAD8]], <1 x double> [[COL_LOAD10]], <2 x i32> <i32 0, i32 1>
-; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <2 x double> [[TMP0]], <2 x double> [[TMP1]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; CHECK-NEXT: [[TMP4:%.*]] = shufflevector <2 x double> [[TMP2]], <2 x double> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
-; CHECK-NEXT: [[TMP5:%.*]] = shufflevector <4 x double> [[TMP3]], <4 x double> [[TMP4]], <6 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5>
-; CHECK-NEXT: [[SPLIT16:%.*]] = shufflevector <6 x double> [[TMP5]], <6 x double> poison, <6 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5>
-; CHECK-NEXT: [[BLOCK:%.*]] = shufflevector <1 x double> [[SPLIT]], <1 x double> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP6:%.*]] = extractelement <6 x double> [[SPLIT16]], i64 0
-; CHECK-NEXT: [[SPLAT_SPLATINSERT:%.*]] = insertelement <1 x double> poison, double [[TMP6]], i64 0
+; CHECK-NEXT: [[COL_LOAD:%.*]] = load <1 x double>, ptr [[LHS_ADDRESS:%.*]], align 4
+; CHECK-NEXT: [[VEC_GEP:%.*]] = getelementptr double, ptr [[LHS_ADDRESS]], i64 1
+; CHECK-NEXT: [[COL_LOAD1:%.*]] = load <1 x double>, ptr [[VEC_GEP]], align 4
+; CHECK-NEXT: [[VEC_GEP2:%.*]] = getelementptr double, ptr [[LHS_ADDRESS]], i64 2
+; CHECK-NEXT: [[COL_LOAD3:%.*]] = load <1 x double>, ptr [[VEC_GEP2]], align 4
+; CHECK-NEXT: [[VEC_GEP4:%.*]] = getelementptr double, ptr [[LHS_ADDRESS]], i64 3
+; CHECK-NEXT: [[COL_LOAD5:%.*]] = load <1 x double>, ptr [[VEC_GEP4]], align 4
+; CHECK-NEXT: [[VEC_GEP6:%.*]] = getelementptr double, ptr [[LHS_ADDRESS]], i64 4
+; CHECK-NEXT: [[COL_LOAD7:%.*]] = load <1 x double>, ptr [[VEC_GEP6]], align 4
+; CHECK-NEXT: [[VEC_GEP8:%.*]] = getelementptr double, ptr [[LHS_ADDRESS]], i64 5
+; CHECK-NEXT: [[COL_LOAD9:%.*]] = load <1 x double>, ptr [[VEC_GEP8]], align 4
+; CHECK-NEXT: [[COL_LOAD10:%.*]] = load <6 x double>, ptr [[RHS_ADDRESS:%.*]], align 4
+; CHECK-NEXT: [[BLOCK:%.*]] = shufflevector <1 x double> [[COL_LOAD]], <1 x double> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP0:%.*]] = extractelement <6 x double> [[COL_LOAD10]], i64 0
+; CHECK-NEXT: [[SPLAT_SPLATINSERT:%.*]] = insertelement <1 x double> poison, double [[TMP0]], i64 0
; CHECK-NEXT: [[SPLAT_SPLAT:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT]], <1 x double> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP7:%.*]] = fmul fast <1 x double> [[BLOCK]], [[SPLAT_SPLAT]]
-; CHECK-NEXT: [[BLOCK17:%.*]] = shufflevector <1 x double> [[SPLIT11]], <1 x double> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP8:%.*]] = extractelement <6 x double> [[SPLIT16]], i64 1
-; CHECK-NEXT: [[SPLAT_SPLATINSERT18:%.*]] = insertelement <1 x double> poison, double [[TMP8]], i64 0
+; CHECK-NEXT: [[TMP1:%.*]] = fmul fast <1 x double> [[BLOCK]], [[SPLAT_SPLAT]]
+; CHECK-NEXT: [[BLOCK11:%.*]] = shufflevector <1 x double> [[COL_LOAD1]], <1 x double> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP2:%.*]] = extractelement <6 x double> [[COL_LOAD10]], i64 1
+; CHECK-NEXT: [[SPLAT_SPLATINSERT12:%.*]] = insertelement <1 x double> poison, double [[TMP2]], i64 0
+; CHECK-NEXT: [[SPLAT_SPLAT13:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT12]], <1 x double> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP3:%.*]] = call fast <1 x double> @llvm.fmuladd.v1f64(<1 x double> [[BLOCK11]], <1 x double> [[SPLAT_SPLAT13]], <1 x double> [[TMP1]])
+; CHECK-NEXT: [[BLOCK14:%.*]] = shufflevector <1 x double> [[COL_LOAD3]], <1 x double> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP4:%.*]] = extractelement <6 x double> [[COL_LOAD10]], i64 2
+; CHECK-NEXT: [[SPLAT_SPLATINSERT15:%.*]] = insertelement <1 x double> poison, double [[TMP4]], i64 0
+; CHECK-NEXT: [[SPLAT_SPLAT16:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT15]], <1 x double> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP5:%.*]] = call fast <1 x double> @llvm.fmuladd.v1f64(<1 x double> [[BLOCK14]], <1 x double> [[SPLAT_SPLAT16]], <1 x double> [[TMP3]])
+; CHECK-NEXT: [[BLOCK17:%.*]] = shufflevector <1 x double> [[COL_LOAD5]], <1 x double> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP6:%.*]] = extractelement <6 x double> [[COL_LOAD10]], i64 3
+; CHECK-NEXT: [[SPLAT_SPLATINSERT18:%.*]] = insertelement <1 x double> poison, double [[TMP6]], i64 0
; CHECK-NEXT: [[SPLAT_SPLAT19:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT18]], <1 x double> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP9:%.*]] = call fast <1 x double> @llvm.fmuladd.v1f64(<1 x double> [[BLOCK17]], <1 x double> [[SPLAT_SPLAT19]], <1 x double> [[TMP7]])
-; CHECK-NEXT: [[BLOCK20:%.*]] = shufflevector <1 x double> [[SPLIT12]], <1 x double> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP10:%.*]] = extractelement <6 x double> [[SPLIT16]], i64 2
-; CHECK-NEXT: [[SPLAT_SPLATINSERT21:%.*]] = insertelement <1 x double> poison, double [[TMP10]], i64 0
+; CHECK-NEXT: [[TMP7:%.*]] = call fast <1 x double> @llvm.fmuladd.v1f64(<1 x double> [[BLOCK17]], <1 x double> [[SPLAT_SPLAT19]], <1 x double> [[TMP5]])
+; CHECK-NEXT: [[BLOCK20:%.*]] = shufflevector <1 x double> [[COL_LOAD7]], <1 x double> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP8:%.*]] = extractelement <6 x double> [[COL_LOAD10]], i64 4
+; CHECK-NEXT: [[SPLAT_SPLATINSERT21:%.*]] = insertelement <1 x double> poison, double [[TMP8]], i64 0
; CHECK-NEXT: [[SPLAT_SPLAT22:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT21]], <1 x double> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP11:%.*]] = call fast <1 x double> @llvm.fmuladd.v1f64(<1 x double> [[BLOCK20]], <1 x double> [[SPLAT_SPLAT22]], <1 x double> [[TMP9]])
-; CHECK-NEXT: [[BLOCK23:%.*]] = shufflevector <1 x double> [[SPLIT13]], <1 x double> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP12:%.*]] = extractelement <6 x double> [[SPLIT16]], i64 3
-; CHECK-NEXT: [[SPLAT_SPLATINSERT24:%.*]] = insertelement <1 x double> poison, double [[TMP12]], i64 0
+; CHECK-NEXT: [[TMP9:%.*]] = call fast <1 x double> @llvm.fmuladd.v1f64(<1 x double> [[BLOCK20]], <1 x double> [[SPLAT_SPLAT22]], <1 x double> [[TMP7]])
+; CHECK-NEXT: [[BLOCK23:%.*]] = shufflevector <1 x double> [[COL_LOAD9]], <1 x double> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP10:%.*]] = extractelement <6 x double> [[COL_LOAD10]], i64 5
+; CHECK-NEXT: [[SPLAT_SPLATINSERT24:%.*]] = insertelement <1 x double> poison, double [[TMP10]], i64 0
; CHECK-NEXT: [[SPLAT_SPLAT25:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT24]], <1 x double> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP13:%.*]] = call fast <1 x double> @llvm.fmuladd.v1f64(<1 x double> [[BLOCK23]], <1 x double> [[SPLAT_SPLAT25]], <1 x double> [[TMP11]])
-; CHECK-NEXT: [[BLOCK26:%.*]] = shufflevector <1 x double> [[SPLIT14]], <1 x double> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP14:%.*]] = extractelement <6 x double> [[SPLIT16]], i64 4
-; CHECK-NEXT: [[SPLAT_SPLATINSERT27:%.*]] = insertelement <1 x double> poison, double [[TMP14]], i64 0
-; CHECK-NEXT: [[SPLAT_SPLAT28:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT27]], <1 x double> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP15:%.*]] = call fast <1 x double> @llvm.fmuladd.v1f64(<1 x double> [[BLOCK26]], <1 x double> [[SPLAT_SPLAT28]], <1 x double> [[TMP13]])
-; CHECK-NEXT: [[BLOCK29:%.*]] = shufflevector <1 x double> [[SPLIT15]], <1 x double> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP16:%.*]] = extractelement <6 x double> [[SPLIT16]], i64 5
-; CHECK-NEXT: [[SPLAT_SPLATINSERT30:%.*]] = insertelement <1 x double> poison, double [[TMP16]], i64 0
-; CHECK-NEXT: [[SPLAT_SPLAT31:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT30]], <1 x double> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP17:%.*]] = call fast <1 x double> @llvm.fmuladd.v1f64(<1 x double> [[BLOCK29]], <1 x double> [[SPLAT_SPLAT31]], <1 x double> [[TMP15]])
-; CHECK-NEXT: [[TMP18:%.*]] = shufflevector <1 x double> [[TMP17]], <1 x double> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP19:%.*]] = shufflevector <1 x double> undef, <1 x double> [[TMP18]], <1 x i32> <i32 1>
-; CHECK-NEXT: ret <1 x double> [[TMP19]]
+; CHECK-NEXT: [[TMP11:%.*]] = call fast <1 x double> @llvm.fmuladd.v1f64(<1 x double> [[BLOCK23]], <1 x double> [[SPLAT_SPLAT25]], <1 x double> [[TMP9]])
+; CHECK-NEXT: [[TMP12:%.*]] = shufflevector <1 x double> [[TMP11]], <1 x double> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP13:%.*]] = shufflevector <1 x double> undef, <1 x double> [[TMP12]], <1 x i32> <i32 1>
+; CHECK-NEXT: ret <1 x double> [[TMP13]]
;
entry:
- %lhs = tail call fast <6 x double> @llvm.matrix.column.major.load.v6f64.i64(ptr nonnull align 4 %lhs_address, i64 6, i1 false, i32 6, i32 1)
- %rhs = tail call fast <6 x double> @llvm.matrix.column.major.load.v6f64.i64(ptr nonnull align 4 %rhs_address, i64 1, i1 false, i32 1, i32 6)
+ %lhs = tail call fast <6 x double> @llvm.matrix.column.major.load.v6f64.i64(ptr nonnull align 4 %lhs_address, i64 1, i1 false, i32 1, i32 6)
+ %rhs = tail call fast <6 x double> @llvm.matrix.column.major.load.v6f64.i64(ptr nonnull align 4 %rhs_address, i64 6, i1 false, i32 6, i32 1)
%result = tail call fast <1 x double> @llvm.matrix.multiply.v1f64.v6f64.v6f64(<6 x double> %lhs, <6 x double> %rhs, i32 1, i32 6, i32 1)
ret <1 x double> %result
}
diff --git a/llvm/test/Transforms/LowerMatrixIntrinsics/dot-product-int.ll b/llvm/test/Transforms/LowerMatrixIntrinsics/dot-product-int.ll
index 47484cec72aea..83d6eb38815f2 100644
--- a/llvm/test/Transforms/LowerMatrixIntrinsics/dot-product-int.ll
+++ b/llvm/test/Transforms/LowerMatrixIntrinsics/dot-product-int.ll
@@ -338,16 +338,76 @@ declare <1 x i64> @llvm.matrix.multiply.v1i64.v8i64.v8i64(<8 x i64>, <8 x i64>,
define <1 x i32> @intrinsic_column_major_load_dot_product_i32_v8(ptr %lhs_address, ptr %rhs_address) {
; CHECK-LABEL: @intrinsic_column_major_load_dot_product_i32_v8(
; CHECK-NEXT: entry:
-; CHECK-NEXT: [[TMP0:%.*]] = load <8 x i32>, ptr [[LHS_ADDRESS:%.*]], align 32
-; CHECK-NEXT: [[TMP1:%.*]] = load <8 x i32>, ptr [[RHS_ADDRESS:%.*]], align 32
-; CHECK-NEXT: [[TMP2:%.*]] = mul <8 x i32> [[TMP0]], [[TMP1]]
-; CHECK-NEXT: [[TMP3:%.*]] = call i32 @llvm.vector.reduce.add.v8i32(<8 x i32> [[TMP2]])
-; CHECK-NEXT: [[TMP4:%.*]] = insertelement <1 x i32> poison, i32 [[TMP3]], i64 0
-; CHECK-NEXT: ret <1 x i32> [[TMP4]]
+; CHECK-NEXT: [[COL_LOAD:%.*]] = load <1 x i32>, ptr [[LHS_ADDRESS:%.*]], align 4
+; CHECK-NEXT: [[VEC_GEP:%.*]] = getelementptr i32, ptr [[LHS_ADDRESS]], i64 1
+; CHECK-NEXT: [[COL_LOAD1:%.*]] = load <1 x i32>, ptr [[VEC_GEP]], align 4
+; CHECK-NEXT: [[VEC_GEP2:%.*]] = getelementptr i32, ptr [[LHS_ADDRESS]], i64 2
+; CHECK-NEXT: [[COL_LOAD3:%.*]] = load <1 x i32>, ptr [[VEC_GEP2]], align 4
+; CHECK-NEXT: [[VEC_GEP4:%.*]] = getelementptr i32, ptr [[LHS_ADDRESS]], i64 3
+; CHECK-NEXT: [[COL_LOAD5:%.*]] = load <1 x i32>, ptr [[VEC_GEP4]], align 4
+; CHECK-NEXT: [[VEC_GEP6:%.*]] = getelementptr i32, ptr [[LHS_ADDRESS]], i64 4
+; CHECK-NEXT: [[COL_LOAD7:%.*]] = load <1 x i32>, ptr [[VEC_GEP6]], align 4
+; CHECK-NEXT: [[VEC_GEP8:%.*]] = getelementptr i32, ptr [[LHS_ADDRESS]], i64 5
+; CHECK-NEXT: [[COL_LOAD9:%.*]] = load <1 x i32>, ptr [[VEC_GEP8]], align 4
+; CHECK-NEXT: [[VEC_GEP10:%.*]] = getelementptr i32, ptr [[LHS_ADDRESS]], i64 6
+; CHECK-NEXT: [[COL_LOAD11:%.*]] = load <1 x i32>, ptr [[VEC_GEP10]], align 4
+; CHECK-NEXT: [[VEC_GEP12:%.*]] = getelementptr i32, ptr [[LHS_ADDRESS]], i64 7
+; CHECK-NEXT: [[COL_LOAD13:%.*]] = load <1 x i32>, ptr [[VEC_GEP12]], align 4
+; CHECK-NEXT: [[COL_LOAD14:%.*]] = load <8 x i32>, ptr [[RHS_ADDRESS:%.*]], align 4
+; CHECK-NEXT: [[BLOCK:%.*]] = shufflevector <1 x i32> [[COL_LOAD]], <1 x i32> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP0:%.*]] = extractelement <8 x i32> [[COL_LOAD14]], i64 0
+; CHECK-NEXT: [[SPLAT_SPLATINSERT:%.*]] = insertelement <1 x i32> poison, i32 [[TMP0]], i64 0
+; CHECK-NEXT: [[SPLAT_SPLAT:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT]], <1 x i32> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP1:%.*]] = mul <1 x i32> [[BLOCK]], [[SPLAT_SPLAT]]
+; CHECK-NEXT: [[BLOCK15:%.*]] = shufflevector <1 x i32> [[COL_LOAD1]], <1 x i32> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP2:%.*]] = extractelement <8 x i32> [[COL_LOAD14]], i64 1
+; CHECK-NEXT: [[SPLAT_SPLATINSERT16:%.*]] = insertelement <1 x i32> poison, i32 [[TMP2]], i64 0
+; CHECK-NEXT: [[SPLAT_SPLAT17:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT16]], <1 x i32> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP3:%.*]] = mul <1 x i32> [[BLOCK15]], [[SPLAT_SPLAT17]]
+; CHECK-NEXT: [[TMP4:%.*]] = add <1 x i32> [[TMP1]], [[TMP3]]
+; CHECK-NEXT: [[BLOCK18:%.*]] = shufflevector <1 x i32> [[COL_LOAD3]], <1 x i32> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP5:%.*]] = extractelement <8 x i32> [[COL_LOAD14]], i64 2
+; CHECK-NEXT: [[SPLAT_SPLATINSERT19:%.*]] = insertelement <1 x i32> poison, i32 [[TMP5]], i64 0
+; CHECK-NEXT: [[SPLAT_SPLAT20:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT19]], <1 x i32> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP6:%.*]] = mul <1 x i32> [[BLOCK18]], [[SPLAT_SPLAT20]]
+; CHECK-NEXT: [[TMP7:%.*]] = add <1 x i32> [[TMP4]], [[TMP6]]
+; CHECK-NEXT: [[BLOCK21:%.*]] = shufflevector <1 x i32> [[COL_LOAD5]], <1 x i32> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP8:%.*]] = extractelement <8 x i32> [[COL_LOAD14]], i64 3
+; CHECK-NEXT: [[SPLAT_SPLATINSERT22:%.*]] = insertelement <1 x i32> poison, i32 [[TMP8]], i64 0
+; CHECK-NEXT: [[SPLAT_SPLAT23:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT22]], <1 x i32> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP9:%.*]] = mul <1 x i32> [[BLOCK21]], [[SPLAT_SPLAT23]]
+; CHECK-NEXT: [[TMP10:%.*]] = add <1 x i32> [[TMP7]], [[TMP9]]
+; CHECK-NEXT: [[BLOCK24:%.*]] = shufflevector <1 x i32> [[COL_LOAD7]], <1 x i32> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP11:%.*]] = extractelement <8 x i32> [[COL_LOAD14]], i64 4
+; CHECK-NEXT: [[SPLAT_SPLATINSERT25:%.*]] = insertelement <1 x i32> poison, i32 [[TMP11]], i64 0
+; CHECK-NEXT: [[SPLAT_SPLAT26:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT25]], <1 x i32> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP12:%.*]] = mul <1 x i32> [[BLOCK24]], [[SPLAT_SPLAT26]]
+; CHECK-NEXT: [[TMP13:%.*]] = add <1 x i32> [[TMP10]], [[TMP12]]
+; CHECK-NEXT: [[BLOCK27:%.*]] = shufflevector <1 x i32> [[COL_LOAD9]], <1 x i32> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP14:%.*]] = extractelement <8 x i32> [[COL_LOAD14]], i64 5
+; CHECK-NEXT: [[SPLAT_SPLATINSERT28:%.*]] = insertelement <1 x i32> poison, i32 [[TMP14]], i64 0
+; CHECK-NEXT: [[SPLAT_SPLAT29:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT28]], <1 x i32> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP15:%.*]] = mul <1 x i32> [[BLOCK27]], [[SPLAT_SPLAT29]]
+; CHECK-NEXT: [[TMP16:%.*]] = add <1 x i32> [[TMP13]], [[TMP15]]
+; CHECK-NEXT: [[BLOCK30:%.*]] = shufflevector <1 x i32> [[COL_LOAD11]], <1 x i32> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP17:%.*]] = extractelement <8 x i32> [[COL_LOAD14]], i64 6
+; CHECK-NEXT: [[SPLAT_SPLATINSERT31:%.*]] = insertelement <1 x i32> poison, i32 [[TMP17]], i64 0
+; CHECK-NEXT: [[SPLAT_SPLAT32:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT31]], <1 x i32> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP18:%.*]] = mul <1 x i32> [[BLOCK30]], [[SPLAT_SPLAT32]]
+; CHECK-NEXT: [[TMP19:%.*]] = add <1 x i32> [[TMP16]], [[TMP18]]
+; CHECK-NEXT: [[BLOCK33:%.*]] = shufflevector <1 x i32> [[COL_LOAD13]], <1 x i32> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP20:%.*]] = extractelement <8 x i32> [[COL_LOAD14]], i64 7
+; CHECK-NEXT: [[SPLAT_SPLATINSERT34:%.*]] = insertelement <1 x i32> poison, i32 [[TMP20]], i64 0
+; CHECK-NEXT: [[SPLAT_SPLAT35:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT34]], <1 x i32> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP21:%.*]] = mul <1 x i32> [[BLOCK33]], [[SPLAT_SPLAT35]]
+; CHECK-NEXT: [[TMP22:%.*]] = add <1 x i32> [[TMP19]], [[TMP21]]
+; CHECK-NEXT: [[TMP23:%.*]] = shufflevector <1 x i32> [[TMP22]], <1 x i32> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP24:%.*]] = shufflevector <1 x i32> undef, <1 x i32> [[TMP23]], <1 x i32> <i32 1>
+; CHECK-NEXT: ret <1 x i32> [[TMP24]]
;
entry:
- %lhs = tail call <8 x i32> @llvm.matrix.column.major.load.v8i32.i64(ptr nonnull align 4 %lhs_address, i64 8, i1 false, i32 8, i32 1)
- %rhs = tail call <8 x i32> @llvm.matrix.column.major.load.v8i32.i64(ptr nonnull align 4 %rhs_address, i64 1, i1 false, i32 1, i32 8)
+ %lhs = tail call <8 x i32> @llvm.matrix.column.major.load.v8i32.i64(ptr nonnull align 4 %lhs_address, i64 1, i1 false, i32 1, i32 8)
+ %rhs = tail call <8 x i32> @llvm.matrix.column.major.load.v8i32.i64(ptr nonnull align 4 %rhs_address, i64 8, i1 false, i32 8, i32 1)
%result = tail call <1 x i32> @llvm.matrix.multiply.v1i32.v8i32.v8i32(<8 x i32> %lhs, <8 x i32> %rhs, i32 1, i32 8, i32 1)
ret <1 x i32> %result
}
@@ -359,52 +419,44 @@ declare <8 x i32> @llvm.matrix.column.major.load.v8i32.i64(ptr nonnull align 4,
define <1 x i32> @intrinsic_column_major_load_dot_product_i32_stride_too_large_1(ptr %lhs_address, ptr %rhs_address) {
; CHECK-LABEL: @intrinsic_column_major_load_dot_product_i32_stride_too_large_1(
; CHECK-NEXT: entry:
-; CHECK-NEXT: [[COL_LOAD:%.*]] = load <4 x i32>, ptr [[LHS_ADDRESS:%.*]], align 4
-; CHECK-NEXT: [[COL_LOAD1:%.*]] = load <1 x i32>, ptr [[RHS_ADDRESS:%.*]], align 4
-; CHECK-NEXT: [[VEC_GEP:%.*]] = getelementptr i32, ptr [[RHS_ADDRESS]], i64 4
-; CHECK-NEXT: [[COL_LOAD2:%.*]] = load <1 x i32>, ptr [[VEC_GEP]], align 4
-; CHECK-NEXT: [[VEC_GEP3:%.*]] = getelementptr i32, ptr [[RHS_ADDRESS]], i64 8
-; CHECK-NEXT: [[COL_LOAD4:%.*]] = load <1 x i32>, ptr [[VEC_GEP3]], align 4
-; CHECK-NEXT: [[VEC_GEP5:%.*]] = getelementptr i32, ptr [[RHS_ADDRESS]], i64 12
-; CHECK-NEXT: [[COL_LOAD6:%.*]] = load <1 x i32>, ptr [[VEC_GEP5]], align 4
-; CHECK-NEXT: [[SPLIT:%.*]] = shufflevector <4 x i32> [[COL_LOAD]], <4 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT: [[SPLIT7:%.*]] = shufflevector <4 x i32> [[COL_LOAD]], <4 x i32> poison, <1 x i32> <i32 1>
-; CHECK-NEXT: [[SPLIT8:%.*]] = shufflevector <4 x i32> [[COL_LOAD]], <4 x i32> poison, <1 x i32> <i32 2>
-; CHECK-NEXT: [[SPLIT9:%.*]] = shufflevector <4 x i32> [[COL_LOAD]], <4 x i32> poison, <1 x i32> <i32 3>
-; CHECK-NEXT: [[TMP0:%.*]] = shufflevector <1 x i32> [[COL_LOAD1]], <1 x i32> [[COL_LOAD2]], <2 x i32> <i32 0, i32 1>
-; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <1 x i32> [[COL_LOAD4]], <1 x i32> [[COL_LOAD6]], <2 x i32> <i32 0, i32 1>
-; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <2 x i32> [[TMP0]], <2 x i32> [[TMP1]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; CHECK-NEXT: [[SPLIT10:%.*]] = shufflevector <4 x i32> [[TMP2]], <4 x i32> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; CHECK-NEXT: [[BLOCK:%.*]] = shufflevector <1 x i32> [[SPLIT]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP3:%.*]] = extractelement <4 x i32> [[SPLIT10]], i64 0
-; CHECK-NEXT: [[SPLAT_SPLATINSERT:%.*]] = insertelement <1 x i32> poison, i32 [[TMP3]], i64 0
+; CHECK-NEXT: [[COL_LOAD:%.*]] = load <1 x i32>, ptr [[LHS_ADDRESS:%.*]], align 4
+; CHECK-NEXT: [[VEC_GEP:%.*]] = getelementptr i32, ptr [[LHS_ADDRESS]], i64 4
+; CHECK-NEXT: [[COL_LOAD1:%.*]] = load <1 x i32>, ptr [[VEC_GEP]], align 4
+; CHECK-NEXT: [[VEC_GEP2:%.*]] = getelementptr i32, ptr [[LHS_ADDRESS]], i64 8
+; CHECK-NEXT: [[COL_LOAD3:%.*]] = load <1 x i32>, ptr [[VEC_GEP2]], align 4
+; CHECK-NEXT: [[VEC_GEP4:%.*]] = getelementptr i32, ptr [[LHS_ADDRESS]], i64 12
+; CHECK-NEXT: [[COL_LOAD5:%.*]] = load <1 x i32>, ptr [[VEC_GEP4]], align 4
+; CHECK-NEXT: [[COL_LOAD6:%.*]] = load <4 x i32>, ptr [[RHS_ADDRESS:%.*]], align 4
+; CHECK-NEXT: [[BLOCK:%.*]] = shufflevector <1 x i32> [[COL_LOAD]], <1 x i32> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP0:%.*]] = extractelement <4 x i32> [[COL_LOAD6]], i64 0
+; CHECK-NEXT: [[SPLAT_SPLATINSERT:%.*]] = insertelement <1 x i32> poison, i32 [[TMP0]], i64 0
; CHECK-NEXT: [[SPLAT_SPLAT:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP4:%.*]] = mul <1 x i32> [[BLOCK]], [[SPLAT_SPLAT]]
-; CHECK-NEXT: [[BLOCK11:%.*]] = shufflevector <1 x i32> [[SPLIT7]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP5:%.*]] = extractelement <4 x i32> [[SPLIT10]], i64 1
-; CHECK-NEXT: [[SPLAT_SPLATINSERT12:%.*]] = insertelement <1 x i32> poison, i32 [[TMP5]], i64 0
-; CHECK-NEXT: [[SPLAT_SPLAT13:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT12]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP6:%.*]] = mul <1 x i32> [[BLOCK11]], [[SPLAT_SPLAT13]]
+; CHECK-NEXT: [[TMP1:%.*]] = mul <1 x i32> [[BLOCK]], [[SPLAT_SPLAT]]
+; CHECK-NEXT: [[BLOCK7:%.*]] = shufflevector <1 x i32> [[COL_LOAD1]], <1 x i32> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP2:%.*]] = extractelement <4 x i32> [[COL_LOAD6]], i64 1
+; CHECK-NEXT: [[SPLAT_SPLATINSERT8:%.*]] = insertelement <1 x i32> poison, i32 [[TMP2]], i64 0
+; CHECK-NEXT: [[SPLAT_SPLAT9:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT8]], <1 x i32> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP3:%.*]] = mul <1 x i32> [[BLOCK7]], [[SPLAT_SPLAT9]]
+; CHECK-NEXT: [[TMP4:%.*]] = add <1 x i32> [[TMP1]], [[TMP3]]
+; CHECK-NEXT: [[BLOCK10:%.*]] = shufflevector <1 x i32> [[COL_LOAD3]], <1 x i32> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP5:%.*]] = extractelement <4 x i32> [[COL_LOAD6]], i64 2
+; CHECK-NEXT: [[SPLAT_SPLATINSERT11:%.*]] = insertelement <1 x i32> poison, i32 [[TMP5]], i64 0
+; CHECK-NEXT: [[SPLAT_SPLAT12:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT11]], <1 x i32> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP6:%.*]] = mul <1 x i32> [[BLOCK10]], [[SPLAT_SPLAT12]]
; CHECK-NEXT: [[TMP7:%.*]] = add <1 x i32> [[TMP4]], [[TMP6]]
-; CHECK-NEXT: [[BLOCK14:%.*]] = shufflevector <1 x i32> [[SPLIT8]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP8:%.*]] = extractelement <4 x i32> [[SPLIT10]], i64 2
-; CHECK-NEXT: [[SPLAT_SPLATINSERT15:%.*]] = insertelement <1 x i32> poison, i32 [[TMP8]], i64 0
-; CHECK-NEXT: [[SPLAT_SPLAT16:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT15]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP9:%.*]] = mul <1 x i32> [[BLOCK14]], [[SPLAT_SPLAT16]]
+; CHECK-NEXT: [[BLOCK13:%.*]] = shufflevector <1 x i32> [[COL_LOAD5]], <1 x i32> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP8:%.*]] = extractelement <4 x i32> [[COL_LOAD6]], i64 3
+; CHECK-NEXT: [[SPLAT_SPLATINSERT14:%.*]] = insertelement <1 x i32> poison, i32 [[TMP8]], i64 0
+; CHECK-NEXT: [[SPLAT_SPLAT15:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT14]], <1 x i32> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP9:%.*]] = mul <1 x i32> [[BLOCK13]], [[SPLAT_SPLAT15]]
; CHECK-NEXT: [[TMP10:%.*]] = add <1 x i32> [[TMP7]], [[TMP9]]
-; CHECK-NEXT: [[BLOCK17:%.*]] = shufflevector <1 x i32> [[SPLIT9]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP11:%.*]] = extractelement <4 x i32> [[SPLIT10]], i64 3
-; CHECK-NEXT: [[SPLAT_SPLATINSERT18:%.*]] = insertelement <1 x i32> poison, i32 [[TMP11]], i64 0
-; CHECK-NEXT: [[SPLAT_SPLAT19:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT18]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP12:%.*]] = mul <1 x i32> [[BLOCK17]], [[SPLAT_SPLAT19]]
-; CHECK-NEXT: [[TMP13:%.*]] = add <1 x i32> [[TMP10]], [[TMP12]]
-; CHECK-NEXT: [[TMP14:%.*]] = shufflevector <1 x i32> [[TMP13]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP15:%.*]] = shufflevector <1 x i32> undef, <1 x i32> [[TMP14]], <1 x i32> <i32 1>
-; CHECK-NEXT: ret <1 x i32> [[TMP15]]
+; CHECK-NEXT: [[TMP11:%.*]] = shufflevector <1 x i32> [[TMP10]], <1 x i32> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP12:%.*]] = shufflevector <1 x i32> undef, <1 x i32> [[TMP11]], <1 x i32> <i32 1>
+; CHECK-NEXT: ret <1 x i32> [[TMP12]]
;
entry:
- %lhs = tail call <4 x i32> @llvm.matrix.column.major.load.v4i32.i64(ptr nonnull align 4 %lhs_address, i64 4, i1 false, i32 4, i32 1)
- %rhs = tail call <4 x i32> @llvm.matrix.column.major.load.v4i32.i64(ptr nonnull align 4 %rhs_address, i64 4, i1 false, i32 1, i32 4)
+ %lhs = tail call <4 x i32> @llvm.matrix.column.major.load.v4i32.i64(ptr nonnull align 4 %lhs_address, i64 4, i1 false, i32 1, i32 4)
+ %rhs = tail call <4 x i32> @llvm.matrix.column.major.load.v4i32.i64(ptr nonnull align 4 %rhs_address, i64 4, i1 false, i32 4, i32 1)
%result = tail call <1 x i32> @llvm.matrix.multiply.v1i32.v4i32.v4i32(<4 x i32> %lhs, <4 x i32> %rhs, i32 1, i32 4, i32 1)
ret <1 x i32> %result
}
@@ -415,52 +467,44 @@ declare <1 x i32> @llvm.matrix.multiply.v1i32.v4i32.v4i32(<4 x i32>, <4 x i32>,
define <1 x i32> @intrinsic_column_major_load_dot_product_i32_stride_too_large_2(ptr %lhs_address, ptr %rhs_address) {
; CHECK-LABEL: @intrinsic_column_major_load_dot_product_i32_stride_too_large_2(
; CHECK-NEXT: entry:
-; CHECK-NEXT: [[COL_LOAD:%.*]] = load <4 x i32>, ptr [[LHS_ADDRESS:%.*]], align 4
-; CHECK-NEXT: [[COL_LOAD1:%.*]] = load <1 x i32>, ptr [[RHS_ADDRESS:%.*]], align 4
-; CHECK-NEXT: [[VEC_GEP:%.*]] = getelementptr i32, ptr [[RHS_ADDRESS]], i64 1
-; CHECK-NEXT: [[COL_LOAD2:%.*]] = load <1 x i32>, ptr [[VEC_GEP]], align 4
-; CHECK-NEXT: [[VEC_GEP3:%.*]] = getelementptr i32, ptr [[RHS_ADDRESS]], i64 2
-; CHECK-NEXT: [[COL_LOAD4:%.*]] = load <1 x i32>, ptr [[VEC_GEP3]], align 4
-; CHECK-NEXT: [[VEC_GEP5:%.*]] = getelementptr i32, ptr [[RHS_ADDRESS]], i64 3
-; CHECK-NEXT: [[COL_LOAD6:%.*]] = load <1 x i32>, ptr [[VEC_GEP5]], align 4
-; CHECK-NEXT: [[SPLIT:%.*]] = shufflevector <4 x i32> [[COL_LOAD]], <4 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT: [[SPLIT7:%.*]] = shufflevector <4 x i32> [[COL_LOAD]], <4 x i32> poison, <1 x i32> <i32 1>
-; CHECK-NEXT: [[SPLIT8:%.*]] = shufflevector <4 x i32> [[COL_LOAD]], <4 x i32> poison, <1 x i32> <i32 2>
-; CHECK-NEXT: [[SPLIT9:%.*]] = shufflevector <4 x i32> [[COL_LOAD]], <4 x i32> poison, <1 x i32> <i32 3>
-; CHECK-NEXT: [[TMP0:%.*]] = shufflevector <1 x i32> [[COL_LOAD1]], <1 x i32> [[COL_LOAD2]], <2 x i32> <i32 0, i32 1>
-; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <1 x i32> [[COL_LOAD4]], <1 x i32> [[COL_LOAD6]], <2 x i32> <i32 0, i32 1>
-; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <2 x i32> [[TMP0]], <2 x i32> [[TMP1]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; CHECK-NEXT: [[SPLIT10:%.*]] = shufflevector <4 x i32> [[TMP2]], <4 x i32> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; CHECK-NEXT: [[BLOCK:%.*]] = shufflevector <1 x i32> [[SPLIT]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP3:%.*]] = extractelement <4 x i32> [[SPLIT10]], i64 0
-; CHECK-NEXT: [[SPLAT_SPLATINSERT:%.*]] = insertelement <1 x i32> poison, i32 [[TMP3]], i64 0
+; CHECK-NEXT: [[COL_LOAD:%.*]] = load <1 x i32>, ptr [[LHS_ADDRESS:%.*]], align 4
+; CHECK-NEXT: [[VEC_GEP:%.*]] = getelementptr i32, ptr [[LHS_ADDRESS]], i64 5
+; CHECK-NEXT: [[COL_LOAD1:%.*]] = load <1 x i32>, ptr [[VEC_GEP]], align 4
+; CHECK-NEXT: [[VEC_GEP2:%.*]] = getelementptr i32, ptr [[LHS_ADDRESS]], i64 10
+; CHECK-NEXT: [[COL_LOAD3:%.*]] = load <1 x i32>, ptr [[VEC_GEP2]], align 4
+; CHECK-NEXT: [[VEC_GEP4:%.*]] = getelementptr i32, ptr [[LHS_ADDRESS]], i64 15
+; CHECK-NEXT: [[COL_LOAD5:%.*]] = load <1 x i32>, ptr [[VEC_GEP4]], align 4
+; CHECK-NEXT: [[COL_LOAD6:%.*]] = load <4 x i32>, ptr [[RHS_ADDRESS:%.*]], align 4
+; CHECK-NEXT: [[BLOCK:%.*]] = shufflevector <1 x i32> [[COL_LOAD]], <1 x i32> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP0:%.*]] = extractelement <4 x i32> [[COL_LOAD6]], i64 0
+; CHECK-NEXT: [[SPLAT_SPLATINSERT:%.*]] = insertelement <1 x i32> poison, i32 [[TMP0]], i64 0
; CHECK-NEXT: [[SPLAT_SPLAT:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP4:%.*]] = mul <1 x i32> [[BLOCK]], [[SPLAT_SPLAT]]
-; CHECK-NEXT: [[BLOCK11:%.*]] = shufflevector <1 x i32> [[SPLIT7]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP5:%.*]] = extractelement <4 x i32> [[SPLIT10]], i64 1
-; CHECK-NEXT: [[SPLAT_SPLATINSERT12:%.*]] = insertelement <1 x i32> poison, i32 [[TMP5]], i64 0
-; CHECK-NEXT: [[SPLAT_SPLAT13:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT12]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP6:%.*]] = mul <1 x i32> [[BLOCK11]], [[SPLAT_SPLAT13]]
+; CHECK-NEXT: [[TMP1:%.*]] = mul <1 x i32> [[BLOCK]], [[SPLAT_SPLAT]]
+; CHECK-NEXT: [[BLOCK7:%.*]] = shufflevector <1 x i32> [[COL_LOAD1]], <1 x i32> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP2:%.*]] = extractelement <4 x i32> [[COL_LOAD6]], i64 1
+; CHECK-NEXT: [[SPLAT_SPLATINSERT8:%.*]] = insertelement <1 x i32> poison, i32 [[TMP2]], i64 0
+; CHECK-NEXT: [[SPLAT_SPLAT9:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT8]], <1 x i32> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP3:%.*]] = mul <1 x i32> [[BLOCK7]], [[SPLAT_SPLAT9]]
+; CHECK-NEXT: [[TMP4:%.*]] = add <1 x i32> [[TMP1]], [[TMP3]]
+; CHECK-NEXT: [[BLOCK10:%.*]] = shufflevector <1 x i32> [[COL_LOAD3]], <1 x i32> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP5:%.*]] = extractelement <4 x i32> [[COL_LOAD6]], i64 2
+; CHECK-NEXT: [[SPLAT_SPLATINSERT11:%.*]] = insertelement <1 x i32> poison, i32 [[TMP5]], i64 0
+; CHECK-NEXT: [[SPLAT_SPLAT12:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT11]], <1 x i32> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP6:%.*]] = mul <1 x i32> [[BLOCK10]], [[SPLAT_SPLAT12]]
; CHECK-NEXT: [[TMP7:%.*]] = add <1 x i32> [[TMP4]], [[TMP6]]
-; CHECK-NEXT: [[BLOCK14:%.*]] = shufflevector <1 x i32> [[SPLIT8]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP8:%.*]] = extractelement <4 x i32> [[SPLIT10]], i64 2
-; CHECK-NEXT: [[SPLAT_SPLATINSERT15:%.*]] = insertelement <1 x i32> poison, i32 [[TMP8]], i64 0
-; CHECK-NEXT: [[SPLAT_SPLAT16:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT15]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP9:%.*]] = mul <1 x i32> [[BLOCK14]], [[SPLAT_SPLAT16]]
+; CHECK-NEXT: [[BLOCK13:%.*]] = shufflevector <1 x i32> [[COL_LOAD5]], <1 x i32> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP8:%.*]] = extractelement <4 x i32> [[COL_LOAD6]], i64 3
+; CHECK-NEXT: [[SPLAT_SPLATINSERT14:%.*]] = insertelement <1 x i32> poison, i32 [[TMP8]], i64 0
+; CHECK-NEXT: [[SPLAT_SPLAT15:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT14]], <1 x i32> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP9:%.*]] = mul <1 x i32> [[BLOCK13]], [[SPLAT_SPLAT15]]
; CHECK-NEXT: [[TMP10:%.*]] = add <1 x i32> [[TMP7]], [[TMP9]]
-; CHECK-NEXT: [[BLOCK17:%.*]] = shufflevector <1 x i32> [[SPLIT9]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP11:%.*]] = extractelement <4 x i32> [[SPLIT10]], i64 3
-; CHECK-NEXT: [[SPLAT_SPLATINSERT18:%.*]] = insertelement <1 x i32> poison, i32 [[TMP11]], i64 0
-; CHECK-NEXT: [[SPLAT_SPLAT19:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT18]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP12:%.*]] = mul <1 x i32> [[BLOCK17]], [[SPLAT_SPLAT19]]
-; CHECK-NEXT: [[TMP13:%.*]] = add <1 x i32> [[TMP10]], [[TMP12]]
-; CHECK-NEXT: [[TMP14:%.*]] = shufflevector <1 x i32> [[TMP13]], <1 x i32> poison, <1 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP15:%.*]] = shufflevector <1 x i32> undef, <1 x i32> [[TMP14]], <1 x i32> <i32 1>
-; CHECK-NEXT: ret <1 x i32> [[TMP15]]
+; CHECK-NEXT: [[TMP11:%.*]] = shufflevector <1 x i32> [[TMP10]], <1 x i32> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP12:%.*]] = shufflevector <1 x i32> undef, <1 x i32> [[TMP11]], <1 x i32> <i32 1>
+; CHECK-NEXT: ret <1 x i32> [[TMP12]]
;
entry:
- %lhs = tail call <4 x i32> @llvm.matrix.column.major.load.v4i32.i64(ptr nonnull align 4 %lhs_address, i64 5, i1 false, i32 4, i32 1)
- %rhs = tail call <4 x i32> @llvm.matrix.column.major.load.v4i32.i64(ptr nonnull align 4 %rhs_address, i64 1, i1 false, i32 1, i32 4)
+ %lhs = tail call <4 x i32> @llvm.matrix.column.major.load.v4i32.i64(ptr nonnull align 4 %lhs_address, i64 5, i1 false, i32 1, i32 4)
+ %rhs = tail call <4 x i32> @llvm.matrix.column.major.load.v4i32.i64(ptr nonnull align 4 %rhs_address, i64 4, i1 false, i32 4, i32 1)
%result = tail call <1 x i32> @llvm.matrix.multiply.v1i32.v4i32.v4i32(<4 x i32> %lhs, <4 x i32> %rhs, i32 1, i32 4, i32 1)
ret <1 x i32> %result
}
More information about the llvm-commits
mailing list