[LowerMatrixIntrinsics] Add dot product tests

[virnarula]

Summary

LLVM LIT tests for our upcoming dot product lowering change

[fhahn]

Thanks for the patch. For the title, it's quite common for LLVM patches to use [PassName] prefix, so for this one [LowerMatrixIntrinsics].

llvm/test/Transforms/LowerMatrixIntrinsics/dot-product.ll

6

it might be good to also throw in a test with inputs that don't take up a full register, like <3 x float>, maybe also <1 x float>

[virnarula]

Adding tests for smaller dimensions

[fhahn]

LGTM, thanks!

[thegameg]

LGTM! If you think it's valuable, you could also add a TN test ((Nx1)^T * Nx1) in case we end up optimizing that in the future, but up to you.

llvm/test/Transforms/LowerMatrixIntrinsics/dot-product.ll

+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; REQUIRES: aarch64-registered-target
+; RUN: opt -passes='lower-matrix-intrinsics' -mtriple=arm64-apple-iphoneos -S < %s | FileCheck %s
+
+define <1 x float> @dotproduct_float_v6(<6 x float> %a, <6 x float> %b) {
+; CHECK-LABEL: @dotproduct_float_v6(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[SPLIT:%.*]] = shufflevector <6 x float> [[A:%.*]], <6 x float> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[SPLIT1:%.*]] = shufflevector <6 x float> [[A]], <6 x float> poison, <1 x i32> <i32 1>
+; CHECK-NEXT:    [[SPLIT2:%.*]] = shufflevector <6 x float> [[A]], <6 x float> poison, <1 x i32> <i32 2>
+; CHECK-NEXT:    [[SPLIT3:%.*]] = shufflevector <6 x float> [[A]], <6 x float> poison, <1 x i32> <i32 3>
+; CHECK-NEXT:    [[SPLIT4:%.*]] = shufflevector <6 x float> [[A]], <6 x float> poison, <1 x i32> <i32 4>
+; CHECK-NEXT:    [[SPLIT5:%.*]] = shufflevector <6 x float> [[A]], <6 x float> poison, <1 x i32> <i32 5>
+; CHECK-NEXT:    [[SPLIT6:%.*]] = shufflevector <6 x float> [[B:%.*]], <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:    [[TMP0:%.*]] = extractelement <6 x float> [[SPLIT6]], i64 0
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT:%.*]] = insertelement <1 x float> poison, float [[TMP0]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT:%.*]] = shufflevector <1 x float> [[SPLAT_SPLATINSERT]], <1 x float> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP1:%.*]] = fmul fast <1 x float> [[BLOCK]], [[SPLAT_SPLAT]]
+; CHECK-NEXT:    [[BLOCK7:%.*]] = shufflevector <1 x float> [[SPLIT1]], <1 x float> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <6 x float> [[SPLIT6]], i64 1
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT8:%.*]] = insertelement <1 x float> poison, float [[TMP2]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT9:%.*]] = shufflevector <1 x float> [[SPLAT_SPLATINSERT8]], <1 x float> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP3:%.*]] = call fast <1 x float> @llvm.fmuladd.v1f32(<1 x float> [[BLOCK7]], <1 x float> [[SPLAT_SPLAT9]], <1 x float> [[TMP1]])
+; CHECK-NEXT:    [[BLOCK10:%.*]] = shufflevector <1 x float> [[SPLIT2]], <1 x float> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <6 x float> [[SPLIT6]], i64 2
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT11:%.*]] = insertelement <1 x float> poison, float [[TMP4]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT12:%.*]] = shufflevector <1 x float> [[SPLAT_SPLATINSERT11]], <1 x float> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP5:%.*]] = call fast <1 x float> @llvm.fmuladd.v1f32(<1 x float> [[BLOCK10]], <1 x float> [[SPLAT_SPLAT12]], <1 x float> [[TMP3]])
+; CHECK-NEXT:    [[BLOCK13:%.*]] = shufflevector <1 x float> [[SPLIT3]], <1 x float> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <6 x float> [[SPLIT6]], i64 3
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT14:%.*]] = insertelement <1 x float> poison, float [[TMP6]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT15:%.*]] = shufflevector <1 x float> [[SPLAT_SPLATINSERT14]], <1 x float> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP7:%.*]] = call fast <1 x float> @llvm.fmuladd.v1f32(<1 x float> [[BLOCK13]], <1 x float> [[SPLAT_SPLAT15]], <1 x float> [[TMP5]])
+; CHECK-NEXT:    [[BLOCK16:%.*]] = shufflevector <1 x float> [[SPLIT4]], <1 x float> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP8:%.*]] = extractelement <6 x float> [[SPLIT6]], i64 4
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT17:%.*]] = insertelement <1 x float> poison, float [[TMP8]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT18:%.*]] = shufflevector <1 x float> [[SPLAT_SPLATINSERT17]], <1 x float> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP9:%.*]] = call fast <1 x float> @llvm.fmuladd.v1f32(<1 x float> [[BLOCK16]], <1 x float> [[SPLAT_SPLAT18]], <1 x float> [[TMP7]])
+; CHECK-NEXT:    [[BLOCK19:%.*]] = shufflevector <1 x float> [[SPLIT5]], <1 x float> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP10:%.*]] = extractelement <6 x float> [[SPLIT6]], i64 5
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT20:%.*]] = insertelement <1 x float> poison, float [[TMP10]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT21:%.*]] = shufflevector <1 x float> [[SPLAT_SPLATINSERT20]], <1 x float> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP11:%.*]] = call fast <1 x float> @llvm.fmuladd.v1f32(<1 x float> [[BLOCK19]], <1 x float> [[SPLAT_SPLAT21]], <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:
+  %c = tail call fast <1 x float> @llvm.matrix.multiply.v1f32.v6f32.v6f32(<6 x float> %a, <6 x float> %b, i32 1, i32 6, i32 1)
+  ret <1 x float> %c
+}
+
+declare <1 x float> @llvm.matrix.multiply.v1f32.v6f32.v6f32(<6 x float>, <6 x float>, i32, i32, i32)
+
+define <1 x float> @dotproduct_float_v1(<1 x float> %a, <1 x float> %b) {
+; CHECK-LABEL: @dotproduct_float_v1(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[SPLIT:%.*]] = shufflevector <1 x float> [[A:%.*]], <1 x float> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[SPLIT1:%.*]] = shufflevector <1 x float> [[B:%.*]], <1 x float> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[BLOCK:%.*]] = shufflevector <1 x float> [[SPLIT]], <1 x float> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP0:%.*]] = extractelement <1 x float> [[SPLIT1]], i64 0
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT:%.*]] = insertelement <1 x float> poison, float [[TMP0]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT:%.*]] = shufflevector <1 x float> [[SPLAT_SPLATINSERT]], <1 x float> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP1:%.*]] = fmul fast <1 x float> [[BLOCK]], [[SPLAT_SPLAT]]
+; CHECK-NEXT:    [[TMP2:%.*]] = shufflevector <1 x float> [[TMP1]], <1 x float> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP3:%.*]] = shufflevector <1 x float> undef, <1 x float> [[TMP2]], <1 x i32> <i32 1>
+; CHECK-NEXT:    ret <1 x float> [[TMP3]]
+;
+entry:
+  %c = tail call fast <1 x float> @llvm.matrix.multiply.v1f32.v1f32.v1f32(<1 x float> %a, <1 x float> %b, i32 1, i32 1, i32 1)
+  ret <1 x float> %c
+}
+
+declare <1 x float> @llvm.matrix.multiply.v1f32.v1f32.v1f32(<1 x float>, <1 x float>, i32, i32, i32)
+
+define <1 x float> @dotproduct_float_v3(<3 x float> %a, <3 x float> %b) {
+; CHECK-LABEL: @dotproduct_float_v3(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[SPLIT:%.*]] = shufflevector <3 x float> [[A:%.*]], <3 x float> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[SPLIT1:%.*]] = shufflevector <3 x float> [[A]], <3 x float> poison, <1 x i32> <i32 1>
+; CHECK-NEXT:    [[SPLIT2:%.*]] = shufflevector <3 x float> [[A]], <3 x float> poison, <1 x i32> <i32 2>
+; CHECK-NEXT:    [[SPLIT3:%.*]] = shufflevector <3 x float> [[B:%.*]], <3 x float> poison, <3 x i32> <i32 0, i32 1, i32 2>
+; CHECK-NEXT:    [[BLOCK:%.*]] = shufflevector <1 x float> [[SPLIT]], <1 x float> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP0:%.*]] = extractelement <3 x float> [[SPLIT3]], i64 0
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT:%.*]] = insertelement <1 x float> poison, float [[TMP0]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT:%.*]] = shufflevector <1 x float> [[SPLAT_SPLATINSERT]], <1 x float> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP1:%.*]] = fmul fast <1 x float> [[BLOCK]], [[SPLAT_SPLAT]]
+; CHECK-NEXT:    [[BLOCK4:%.*]] = shufflevector <1 x float> [[SPLIT1]], <1 x float> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <3 x float> [[SPLIT3]], i64 1
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT5:%.*]] = insertelement <1 x float> poison, float [[TMP2]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT6:%.*]] = shufflevector <1 x float> [[SPLAT_SPLATINSERT5]], <1 x float> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP3:%.*]] = call fast <1 x float> @llvm.fmuladd.v1f32(<1 x float> [[BLOCK4]], <1 x float> [[SPLAT_SPLAT6]], <1 x float> [[TMP1]])
+; CHECK-NEXT:    [[BLOCK7:%.*]] = shufflevector <1 x float> [[SPLIT2]], <1 x float> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <3 x float> [[SPLIT3]], i64 2
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT8:%.*]] = insertelement <1 x float> poison, float [[TMP4]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT9:%.*]] = shufflevector <1 x float> [[SPLAT_SPLATINSERT8]], <1 x float> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP5:%.*]] = call fast <1 x float> @llvm.fmuladd.v1f32(<1 x float> [[BLOCK7]], <1 x float> [[SPLAT_SPLAT9]], <1 x float> [[TMP3]])
+; CHECK-NEXT:    [[TMP6:%.*]] = shufflevector <1 x float> [[TMP5]], <1 x float> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP7:%.*]] = shufflevector <1 x float> undef, <1 x float> [[TMP6]], <1 x i32> <i32 1>
+; CHECK-NEXT:    ret <1 x float> [[TMP7]]
+;
+entry:
+  %c = tail call fast <1 x float> @llvm.matrix.multiply.v1f32.v3f32.v3f32(<3 x float> %a, <3 x float> %b, i32 1, i32 3, i32 1)
+  ret <1 x float> %c
+}
+
+declare <1 x float> @llvm.matrix.multiply.v1f32.v3f32.v3f32(<3 x float>, <3 x float>, i32, i32, i32)
+
+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 6
+; CHECK-NEXT:    [[COL_LOAD2:%.*]] = load <1 x float>, ptr [[VEC_GEP]], align 4
+; CHECK-NEXT:    [[VEC_GEP3:%.*]] = getelementptr float, ptr [[RHS_ADDRESS]], i64 12
+; CHECK-NEXT:    [[COL_LOAD4:%.*]] = load <1 x float>, ptr [[VEC_GEP3]], align 4
+; CHECK-NEXT:    [[VEC_GEP5:%.*]] = getelementptr float, ptr [[RHS_ADDRESS]], i64 18
+; CHECK-NEXT:    [[COL_LOAD6:%.*]] = load <1 x float>, ptr [[VEC_GEP5]], align 4
+; CHECK-NEXT:    [[VEC_GEP7:%.*]] = getelementptr float, ptr [[RHS_ADDRESS]], i64 24
+; CHECK-NEXT:    [[COL_LOAD8:%.*]] = load <1 x float>, ptr [[VEC_GEP7]], align 4
+; CHECK-NEXT:    [[VEC_GEP9:%.*]] = getelementptr float, ptr [[RHS_ADDRESS]], i64 30
+; 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]], i32 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]], i32 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]], i32 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]], i32 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]], i32 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]], i32 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]]
+;
+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 6, i1 false, i32 1, i32 6)
+  %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
+}
+
+declare <6 x float> @llvm.matrix.column.major.load.v6f32.i64(ptr nonnull align 4, i64, i1, i32, i32)
+
+define <1 x float> @LoadInst_dot_product_float_v7(ptr %lhs_address, ptr %rhs_address) {
+; CHECK-LABEL: @LoadInst_dot_product_float_v7(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[COL_LOAD:%.*]] = load <1 x float>, ptr [[LHS_ADDRESS:%.*]], align 32
+; 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 8
+; 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 16
+; 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:    [[VEC_GEP10:%.*]] = getelementptr float, ptr [[LHS_ADDRESS]], i64 6
+; CHECK-NEXT:    [[COL_LOAD11:%.*]] = load <1 x float>, ptr [[VEC_GEP10]], align 8
+; CHECK-NEXT:    [[COL_LOAD12:%.*]] = load <7 x float>, ptr [[RHS_ADDRESS:%.*]], align 32
+; CHECK-NEXT:    [[BLOCK:%.*]] = shufflevector <1 x float> [[COL_LOAD]], <1 x float> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP0:%.*]] = extractelement <7 x float> [[COL_LOAD12]], i64 0
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT:%.*]] = insertelement <1 x float> poison, float [[TMP0]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT:%.*]] = shufflevector <1 x float> [[SPLAT_SPLATINSERT]], <1 x float> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP1:%.*]] = fmul fast <1 x float> [[BLOCK]], [[SPLAT_SPLAT]]
+; CHECK-NEXT:    [[BLOCK13:%.*]] = shufflevector <1 x float> [[COL_LOAD1]], <1 x float> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <7 x float> [[COL_LOAD12]], i64 1
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT14:%.*]] = insertelement <1 x float> poison, float [[TMP2]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT15:%.*]] = shufflevector <1 x float> [[SPLAT_SPLATINSERT14]], <1 x float> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP3:%.*]] = call fast <1 x float> @llvm.fmuladd.v1f32(<1 x float> [[BLOCK13]], <1 x float> [[SPLAT_SPLAT15]], <1 x float> [[TMP1]])
+; CHECK-NEXT:    [[BLOCK16:%.*]] = shufflevector <1 x float> [[COL_LOAD3]], <1 x float> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <7 x float> [[COL_LOAD12]], i64 2
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT17:%.*]] = insertelement <1 x float> poison, float [[TMP4]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT18:%.*]] = shufflevector <1 x float> [[SPLAT_SPLATINSERT17]], <1 x float> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP5:%.*]] = call fast <1 x float> @llvm.fmuladd.v1f32(<1 x float> [[BLOCK16]], <1 x float> [[SPLAT_SPLAT18]], <1 x float> [[TMP3]])
+; CHECK-NEXT:    [[BLOCK19:%.*]] = shufflevector <1 x float> [[COL_LOAD5]], <1 x float> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <7 x float> [[COL_LOAD12]], i64 3
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT20:%.*]] = insertelement <1 x float> poison, float [[TMP6]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT21:%.*]] = shufflevector <1 x float> [[SPLAT_SPLATINSERT20]], <1 x float> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP7:%.*]] = call fast <1 x float> @llvm.fmuladd.v1f32(<1 x float> [[BLOCK19]], <1 x float> [[SPLAT_SPLAT21]], <1 x float> [[TMP5]])
+; CHECK-NEXT:    [[BLOCK22:%.*]] = shufflevector <1 x float> [[COL_LOAD7]], <1 x float> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP8:%.*]] = extractelement <7 x float> [[COL_LOAD12]], i64 4
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT23:%.*]] = insertelement <1 x float> poison, float [[TMP8]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT24:%.*]] = shufflevector <1 x float> [[SPLAT_SPLATINSERT23]], <1 x float> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP9:%.*]] = call fast <1 x float> @llvm.fmuladd.v1f32(<1 x float> [[BLOCK22]], <1 x float> [[SPLAT_SPLAT24]], <1 x float> [[TMP7]])
+; CHECK-NEXT:    [[BLOCK25:%.*]] = shufflevector <1 x float> [[COL_LOAD9]], <1 x float> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP10:%.*]] = extractelement <7 x float> [[COL_LOAD12]], i64 5
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT26:%.*]] = insertelement <1 x float> poison, float [[TMP10]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT27:%.*]] = shufflevector <1 x float> [[SPLAT_SPLATINSERT26]], <1 x float> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP11:%.*]] = call fast <1 x float> @llvm.fmuladd.v1f32(<1 x float> [[BLOCK25]], <1 x float> [[SPLAT_SPLAT27]], <1 x float> [[TMP9]])
+; CHECK-NEXT:    [[BLOCK28:%.*]] = shufflevector <1 x float> [[COL_LOAD11]], <1 x float> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP12:%.*]] = extractelement <7 x float> [[COL_LOAD12]], i64 6
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT29:%.*]] = insertelement <1 x float> poison, float [[TMP12]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT30:%.*]] = shufflevector <1 x float> [[SPLAT_SPLATINSERT29]], <1 x float> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP13:%.*]] = call fast <1 x float> @llvm.fmuladd.v1f32(<1 x float> [[BLOCK28]], <1 x float> [[SPLAT_SPLAT30]], <1 x float> [[TMP11]])
+; CHECK-NEXT:    [[TMP14:%.*]] = shufflevector <1 x float> [[TMP13]], <1 x float> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP15:%.*]] = shufflevector <1 x float> undef, <1 x float> [[TMP14]], <1 x i32> <i32 1>
+; CHECK-NEXT:    ret <1 x float> [[TMP15]]
+;
+entry:
+  %lhs = load <7 x float>, ptr %lhs_address
+  %rhs = load <7 x float>, ptr %rhs_address
+  %c = tail call fast <1 x float> @llvm.matrix.multiply.v1f32.v7f32.v7f32(<7 x float> %lhs, <7 x float> %rhs, i32 1, i32 7, i32 1)
+  ret <1 x float> %c
+}
+
+declare <1 x float> @llvm.matrix.multiply.v1f32.v7f32.v7f32(<7 x float>, <7 x float>, i32, i32, i32)
+
+define <1 x double> @dotproduct_double_v6(<6 x double> %a, <6 x double> %b) {
+; CHECK-LABEL: @dotproduct_double_v6(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[SPLIT:%.*]] = shufflevector <6 x double> [[A:%.*]], <6 x double> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[SPLIT1:%.*]] = shufflevector <6 x double> [[A]], <6 x double> poison, <1 x i32> <i32 1>
+; CHECK-NEXT:    [[SPLIT2:%.*]] = shufflevector <6 x double> [[A]], <6 x double> poison, <1 x i32> <i32 2>
+; CHECK-NEXT:    [[SPLIT3:%.*]] = shufflevector <6 x double> [[A]], <6 x double> poison, <1 x i32> <i32 3>
+; CHECK-NEXT:    [[SPLIT4:%.*]] = shufflevector <6 x double> [[A]], <6 x double> poison, <1 x i32> <i32 4>
+; CHECK-NEXT:    [[SPLIT5:%.*]] = shufflevector <6 x double> [[A]], <6 x double> poison, <1 x i32> <i32 5>
+; CHECK-NEXT:    [[SPLIT6:%.*]] = shufflevector <6 x double> [[B:%.*]], <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:    [[TMP0:%.*]] = extractelement <6 x double> [[SPLIT6]], i64 0
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT:%.*]] = insertelement <1 x double> poison, double [[TMP0]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT]], <1 x double> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP1:%.*]] = fmul fast <1 x double> [[BLOCK]], [[SPLAT_SPLAT]]
+; CHECK-NEXT:    [[BLOCK7:%.*]] = shufflevector <1 x double> [[SPLIT1]], <1 x double> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <6 x double> [[SPLIT6]], i64 1
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT8:%.*]] = insertelement <1 x double> poison, double [[TMP2]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT9:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT8]], <1 x double> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP3:%.*]] = call fast <1 x double> @llvm.fmuladd.v1f64(<1 x double> [[BLOCK7]], <1 x double> [[SPLAT_SPLAT9]], <1 x double> [[TMP1]])
+; CHECK-NEXT:    [[BLOCK10:%.*]] = shufflevector <1 x double> [[SPLIT2]], <1 x double> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <6 x double> [[SPLIT6]], i64 2
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT11:%.*]] = insertelement <1 x double> poison, double [[TMP4]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT12:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT11]], <1 x double> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP5:%.*]] = call fast <1 x double> @llvm.fmuladd.v1f64(<1 x double> [[BLOCK10]], <1 x double> [[SPLAT_SPLAT12]], <1 x double> [[TMP3]])
+; CHECK-NEXT:    [[BLOCK13:%.*]] = shufflevector <1 x double> [[SPLIT3]], <1 x double> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <6 x double> [[SPLIT6]], i64 3
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT14:%.*]] = insertelement <1 x double> poison, double [[TMP6]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT15:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT14]], <1 x double> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP7:%.*]] = call fast <1 x double> @llvm.fmuladd.v1f64(<1 x double> [[BLOCK13]], <1 x double> [[SPLAT_SPLAT15]], <1 x double> [[TMP5]])
+; CHECK-NEXT:    [[BLOCK16:%.*]] = shufflevector <1 x double> [[SPLIT4]], <1 x double> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP8:%.*]] = extractelement <6 x double> [[SPLIT6]], i64 4
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT17:%.*]] = insertelement <1 x double> poison, double [[TMP8]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT18:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT17]], <1 x double> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP9:%.*]] = call fast <1 x double> @llvm.fmuladd.v1f64(<1 x double> [[BLOCK16]], <1 x double> [[SPLAT_SPLAT18]], <1 x double> [[TMP7]])
+; CHECK-NEXT:    [[BLOCK19:%.*]] = shufflevector <1 x double> [[SPLIT5]], <1 x double> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP10:%.*]] = extractelement <6 x double> [[SPLIT6]], i64 5
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT20:%.*]] = insertelement <1 x double> poison, double [[TMP10]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT21:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT20]], <1 x double> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP11:%.*]] = call fast <1 x double> @llvm.fmuladd.v1f64(<1 x double> [[BLOCK19]], <1 x double> [[SPLAT_SPLAT21]], <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:
+  %c = tail call fast <1 x double> @llvm.matrix.multiply.v1f64.v6f64.v6f64(<6 x double> %a, <6 x double> %b, i32 1, i32 6, i32 1)
+  ret <1 x double> %c
+}
+
+declare <1 x double> @llvm.matrix.multiply.v1f64.v6f64.v6f64(<6 x double>, <6 x double>, i32, i32, i32)
+
+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 6
+; CHECK-NEXT:    [[COL_LOAD2:%.*]] = load <1 x double>, ptr [[VEC_GEP]], align 4
+; CHECK-NEXT:    [[VEC_GEP3:%.*]] = getelementptr double, ptr [[RHS_ADDRESS]], i64 12
+; CHECK-NEXT:    [[COL_LOAD4:%.*]] = load <1 x double>, ptr [[VEC_GEP3]], align 4
+; CHECK-NEXT:    [[VEC_GEP5:%.*]] = getelementptr double, ptr [[RHS_ADDRESS]], i64 18
+; CHECK-NEXT:    [[COL_LOAD6:%.*]] = load <1 x double>, ptr [[VEC_GEP5]], align 4
+; CHECK-NEXT:    [[VEC_GEP7:%.*]] = getelementptr double, ptr [[RHS_ADDRESS]], i64 24
+; CHECK-NEXT:    [[COL_LOAD8:%.*]] = load <1 x double>, ptr [[VEC_GEP7]], align 4
+; CHECK-NEXT:    [[VEC_GEP9:%.*]] = getelementptr double, ptr [[RHS_ADDRESS]], i64 30
+; 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]], i32 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]], i32 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]], i32 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]], i32 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]], i32 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]], i32 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]]
+;
+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 6, i1 false, i32 1, i32 6)
+  %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
+}
+
+declare <6 x double> @llvm.matrix.column.major.load.v6f64.i64(ptr nonnull align 4, i64, i1, i32, i32)
+
+define <1 x double> @LoadInst_dot_product_double_v7(ptr %lhs_address, ptr %rhs_address) {
+; CHECK-LABEL: @LoadInst_dot_product_double_v7(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[COL_LOAD:%.*]] = load <1 x double>, ptr [[LHS_ADDRESS:%.*]], align 64
+; CHECK-NEXT:    [[VEC_GEP:%.*]] = getelementptr double, ptr [[LHS_ADDRESS]], i64 1
+; CHECK-NEXT:    [[COL_LOAD1:%.*]] = load <1 x double>, ptr [[VEC_GEP]], align 8
+; CHECK-NEXT:    [[VEC_GEP2:%.*]] = getelementptr double, ptr [[LHS_ADDRESS]], i64 2
+; CHECK-NEXT:    [[COL_LOAD3:%.*]] = load <1 x double>, ptr [[VEC_GEP2]], align 16
+; CHECK-NEXT:    [[VEC_GEP4:%.*]] = getelementptr double, ptr [[LHS_ADDRESS]], i64 3
+; CHECK-NEXT:    [[COL_LOAD5:%.*]] = load <1 x double>, ptr [[VEC_GEP4]], align 8
+; CHECK-NEXT:    [[VEC_GEP6:%.*]] = getelementptr double, ptr [[LHS_ADDRESS]], i64 4
+; CHECK-NEXT:    [[COL_LOAD7:%.*]] = load <1 x double>, ptr [[VEC_GEP6]], align 32
+; CHECK-NEXT:    [[VEC_GEP8:%.*]] = getelementptr double, ptr [[LHS_ADDRESS]], i64 5
+; CHECK-NEXT:    [[COL_LOAD9:%.*]] = load <1 x double>, ptr [[VEC_GEP8]], align 8
+; CHECK-NEXT:    [[VEC_GEP10:%.*]] = getelementptr double, ptr [[LHS_ADDRESS]], i64 6
+; CHECK-NEXT:    [[COL_LOAD11:%.*]] = load <1 x double>, ptr [[VEC_GEP10]], align 16
+; CHECK-NEXT:    [[COL_LOAD12:%.*]] = load <7 x double>, ptr [[RHS_ADDRESS:%.*]], align 64
+; CHECK-NEXT:    [[BLOCK:%.*]] = shufflevector <1 x double> [[COL_LOAD]], <1 x double> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP0:%.*]] = extractelement <7 x double> [[COL_LOAD12]], i64 0
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT:%.*]] = insertelement <1 x double> poison, double [[TMP0]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT]], <1 x double> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP1:%.*]] = fmul fast <1 x double> [[BLOCK]], [[SPLAT_SPLAT]]
+; CHECK-NEXT:    [[BLOCK13:%.*]] = shufflevector <1 x double> [[COL_LOAD1]], <1 x double> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <7 x double> [[COL_LOAD12]], i64 1
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT14:%.*]] = insertelement <1 x double> poison, double [[TMP2]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT15:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT14]], <1 x double> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP3:%.*]] = call fast <1 x double> @llvm.fmuladd.v1f64(<1 x double> [[BLOCK13]], <1 x double> [[SPLAT_SPLAT15]], <1 x double> [[TMP1]])
+; CHECK-NEXT:    [[BLOCK16:%.*]] = shufflevector <1 x double> [[COL_LOAD3]], <1 x double> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <7 x double> [[COL_LOAD12]], i64 2
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT17:%.*]] = insertelement <1 x double> poison, double [[TMP4]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT18:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT17]], <1 x double> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP5:%.*]] = call fast <1 x double> @llvm.fmuladd.v1f64(<1 x double> [[BLOCK16]], <1 x double> [[SPLAT_SPLAT18]], <1 x double> [[TMP3]])
+; CHECK-NEXT:    [[BLOCK19:%.*]] = shufflevector <1 x double> [[COL_LOAD5]], <1 x double> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <7 x double> [[COL_LOAD12]], i64 3
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT20:%.*]] = insertelement <1 x double> poison, double [[TMP6]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT21:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT20]], <1 x double> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP7:%.*]] = call fast <1 x double> @llvm.fmuladd.v1f64(<1 x double> [[BLOCK19]], <1 x double> [[SPLAT_SPLAT21]], <1 x double> [[TMP5]])
+; CHECK-NEXT:    [[BLOCK22:%.*]] = shufflevector <1 x double> [[COL_LOAD7]], <1 x double> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP8:%.*]] = extractelement <7 x double> [[COL_LOAD12]], i64 4
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT23:%.*]] = insertelement <1 x double> poison, double [[TMP8]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT24:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT23]], <1 x double> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP9:%.*]] = call fast <1 x double> @llvm.fmuladd.v1f64(<1 x double> [[BLOCK22]], <1 x double> [[SPLAT_SPLAT24]], <1 x double> [[TMP7]])
+; CHECK-NEXT:    [[BLOCK25:%.*]] = shufflevector <1 x double> [[COL_LOAD9]], <1 x double> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP10:%.*]] = extractelement <7 x double> [[COL_LOAD12]], i64 5
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT26:%.*]] = insertelement <1 x double> poison, double [[TMP10]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT27:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT26]], <1 x double> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP11:%.*]] = call fast <1 x double> @llvm.fmuladd.v1f64(<1 x double> [[BLOCK25]], <1 x double> [[SPLAT_SPLAT27]], <1 x double> [[TMP9]])
+; CHECK-NEXT:    [[BLOCK28:%.*]] = shufflevector <1 x double> [[COL_LOAD11]], <1 x double> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP12:%.*]] = extractelement <7 x double> [[COL_LOAD12]], i64 6
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT29:%.*]] = insertelement <1 x double> poison, double [[TMP12]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT30:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT29]], <1 x double> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP13:%.*]] = call fast <1 x double> @llvm.fmuladd.v1f64(<1 x double> [[BLOCK28]], <1 x double> [[SPLAT_SPLAT30]], <1 x double> [[TMP11]])
+; CHECK-NEXT:    [[TMP14:%.*]] = shufflevector <1 x double> [[TMP13]], <1 x double> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP15:%.*]] = shufflevector <1 x double> undef, <1 x double> [[TMP14]], <1 x i32> <i32 1>
+; CHECK-NEXT:    ret <1 x double> [[TMP15]]
+;
+entry:
+  %lhs = load <7 x double>, ptr %lhs_address
+  %rhs = load <7 x double>, ptr %rhs_address
+  %c = tail call fast <1 x double> @llvm.matrix.multiply.v1f64.v7f64.v7f64(<7 x double> %lhs, <7 x double> %rhs, i32 1, i32 7, i32 1)
+  ret <1 x double> %c
+}
+
+declare <1 x double> @llvm.matrix.multiply.v1f64.v7f64.v7f64(<7 x double>, <7 x double>, i32, i32, i32)
+
+define <1 x i64> @dotproduct_i64_v8(<8 x i64> %a, <8 x i64> %b) {
+; CHECK-LABEL: @dotproduct_i64_v8(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[SPLIT:%.*]] = shufflevector <8 x i64> [[A:%.*]], <8 x i64> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[SPLIT1:%.*]] = shufflevector <8 x i64> [[A]], <8 x i64> poison, <1 x i32> <i32 1>
+; CHECK-NEXT:    [[SPLIT2:%.*]] = shufflevector <8 x i64> [[A]], <8 x i64> poison, <1 x i32> <i32 2>
+; CHECK-NEXT:    [[SPLIT3:%.*]] = shufflevector <8 x i64> [[A]], <8 x i64> poison, <1 x i32> <i32 3>
+; CHECK-NEXT:    [[SPLIT4:%.*]] = shufflevector <8 x i64> [[A]], <8 x i64> poison, <1 x i32> <i32 4>
+; CHECK-NEXT:    [[SPLIT5:%.*]] = shufflevector <8 x i64> [[A]], <8 x i64> poison, <1 x i32> <i32 5>
+; CHECK-NEXT:    [[SPLIT6:%.*]] = shufflevector <8 x i64> [[A]], <8 x i64> poison, <1 x i32> <i32 6>
+; CHECK-NEXT:    [[SPLIT7:%.*]] = shufflevector <8 x i64> [[A]], <8 x i64> poison, <1 x i32> <i32 7>
+; CHECK-NEXT:    [[SPLIT8:%.*]] = shufflevector <8 x i64> [[B:%.*]], <8 x i64> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT:    [[BLOCK:%.*]] = shufflevector <1 x i64> [[SPLIT]], <1 x i64> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP0:%.*]] = extractelement <8 x i64> [[SPLIT8]], i64 0
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT:%.*]] = insertelement <1 x i64> poison, i64 [[TMP0]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT:%.*]] = shufflevector <1 x i64> [[SPLAT_SPLATINSERT]], <1 x i64> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP1:%.*]] = mul <1 x i64> [[BLOCK]], [[SPLAT_SPLAT]]
+; CHECK-NEXT:    [[BLOCK9:%.*]] = shufflevector <1 x i64> [[SPLIT1]], <1 x i64> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <8 x i64> [[SPLIT8]], i64 1
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT10:%.*]] = insertelement <1 x i64> poison, i64 [[TMP2]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT11:%.*]] = shufflevector <1 x i64> [[SPLAT_SPLATINSERT10]], <1 x i64> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP3:%.*]] = mul <1 x i64> [[BLOCK9]], [[SPLAT_SPLAT11]]
+; CHECK-NEXT:    [[TMP4:%.*]] = add <1 x i64> [[TMP1]], [[TMP3]]
+; CHECK-NEXT:    [[BLOCK12:%.*]] = shufflevector <1 x i64> [[SPLIT2]], <1 x i64> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <8 x i64> [[SPLIT8]], i64 2
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT13:%.*]] = insertelement <1 x i64> poison, i64 [[TMP5]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT14:%.*]] = shufflevector <1 x i64> [[SPLAT_SPLATINSERT13]], <1 x i64> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP6:%.*]] = mul <1 x i64> [[BLOCK12]], [[SPLAT_SPLAT14]]
+; CHECK-NEXT:    [[TMP7:%.*]] = add <1 x i64> [[TMP4]], [[TMP6]]
+; CHECK-NEXT:    [[BLOCK15:%.*]] = shufflevector <1 x i64> [[SPLIT3]], <1 x i64> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP8:%.*]] = extractelement <8 x i64> [[SPLIT8]], i64 3
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT16:%.*]] = insertelement <1 x i64> poison, i64 [[TMP8]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT17:%.*]] = shufflevector <1 x i64> [[SPLAT_SPLATINSERT16]], <1 x i64> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP9:%.*]] = mul <1 x i64> [[BLOCK15]], [[SPLAT_SPLAT17]]
+; CHECK-NEXT:    [[TMP10:%.*]] = add <1 x i64> [[TMP7]], [[TMP9]]
+; CHECK-NEXT:    [[BLOCK18:%.*]] = shufflevector <1 x i64> [[SPLIT4]], <1 x i64> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP11:%.*]] = extractelement <8 x i64> [[SPLIT8]], i64 4
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT19:%.*]] = insertelement <1 x i64> poison, i64 [[TMP11]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT20:%.*]] = shufflevector <1 x i64> [[SPLAT_SPLATINSERT19]], <1 x i64> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP12:%.*]] = mul <1 x i64> [[BLOCK18]], [[SPLAT_SPLAT20]]
+; CHECK-NEXT:    [[TMP13:%.*]] = add <1 x i64> [[TMP10]], [[TMP12]]
+; CHECK-NEXT:    [[BLOCK21:%.*]] = shufflevector <1 x i64> [[SPLIT5]], <1 x i64> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP14:%.*]] = extractelement <8 x i64> [[SPLIT8]], i64 5
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT22:%.*]] = insertelement <1 x i64> poison, i64 [[TMP14]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT23:%.*]] = shufflevector <1 x i64> [[SPLAT_SPLATINSERT22]], <1 x i64> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP15:%.*]] = mul <1 x i64> [[BLOCK21]], [[SPLAT_SPLAT23]]
+; CHECK-NEXT:    [[TMP16:%.*]] = add <1 x i64> [[TMP13]], [[TMP15]]
+; CHECK-NEXT:    [[BLOCK24:%.*]] = shufflevector <1 x i64> [[SPLIT6]], <1 x i64> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP17:%.*]] = extractelement <8 x i64> [[SPLIT8]], i64 6
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT25:%.*]] = insertelement <1 x i64> poison, i64 [[TMP17]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT26:%.*]] = shufflevector <1 x i64> [[SPLAT_SPLATINSERT25]], <1 x i64> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP18:%.*]] = mul <1 x i64> [[BLOCK24]], [[SPLAT_SPLAT26]]
+; CHECK-NEXT:    [[TMP19:%.*]] = add <1 x i64> [[TMP16]], [[TMP18]]
+; CHECK-NEXT:    [[BLOCK27:%.*]] = shufflevector <1 x i64> [[SPLIT7]], <1 x i64> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP20:%.*]] = extractelement <8 x i64> [[SPLIT8]], i64 7
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT28:%.*]] = insertelement <1 x i64> poison, i64 [[TMP20]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT29:%.*]] = shufflevector <1 x i64> [[SPLAT_SPLATINSERT28]], <1 x i64> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP21:%.*]] = mul <1 x i64> [[BLOCK27]], [[SPLAT_SPLAT29]]
+; CHECK-NEXT:    [[TMP22:%.*]] = add <1 x i64> [[TMP19]], [[TMP21]]
+; CHECK-NEXT:    [[TMP23:%.*]] = shufflevector <1 x i64> [[TMP22]], <1 x i64> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP24:%.*]] = shufflevector <1 x i64> undef, <1 x i64> [[TMP23]], <1 x i32> <i32 1>
+; CHECK-NEXT:    ret <1 x i64> [[TMP24]]
+;
+entry:
+  %c = tail call <1 x i64> @llvm.matrix.multiply.v1i64.v8i64.v8i64(<8 x i64> %a, <8 x i64> %b, i32 1, i32 8, i32 1)
+  ret <1 x i64> %c
+}
+
+declare <1 x i64> @llvm.matrix.multiply.v1i64.v8i64.v8i64(<8 x i64>, <8 x i64>, i32, i32, i32)
+
+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:    [[COL_LOAD:%.*]] = load <8 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 8
+; CHECK-NEXT:    [[COL_LOAD2:%.*]] = load <1 x i32>, ptr [[VEC_GEP]], align 4
+; CHECK-NEXT:    [[VEC_GEP3:%.*]] = getelementptr i32, ptr [[RHS_ADDRESS]], i64 16
+; CHECK-NEXT:    [[COL_LOAD4:%.*]] = load <1 x i32>, ptr [[VEC_GEP3]], align 4
+; CHECK-NEXT:    [[VEC_GEP5:%.*]] = getelementptr i32, ptr [[RHS_ADDRESS]], i64 24
+; CHECK-NEXT:    [[COL_LOAD6:%.*]] = load <1 x i32>, ptr [[VEC_GEP5]], align 4
+; CHECK-NEXT:    [[VEC_GEP7:%.*]] = getelementptr i32, ptr [[RHS_ADDRESS]], i64 32
+; CHECK-NEXT:    [[COL_LOAD8:%.*]] = load <1 x i32>, ptr [[VEC_GEP7]], align 4
+; CHECK-NEXT:    [[VEC_GEP9:%.*]] = getelementptr i32, ptr [[RHS_ADDRESS]], i64 40
+; CHECK-NEXT:    [[COL_LOAD10:%.*]] = load <1 x i32>, ptr [[VEC_GEP9]], align 4
+; CHECK-NEXT:    [[VEC_GEP11:%.*]] = getelementptr i32, ptr [[RHS_ADDRESS]], i64 48
+; CHECK-NEXT:    [[COL_LOAD12:%.*]] = load <1 x i32>, ptr [[VEC_GEP11]], align 4
+; CHECK-NEXT:    [[VEC_GEP13:%.*]] = getelementptr i32, ptr [[RHS_ADDRESS]], i64 56
+; CHECK-NEXT:    [[COL_LOAD14:%.*]] = load <1 x i32>, ptr [[VEC_GEP13]], align 4
+; CHECK-NEXT:    [[SPLIT:%.*]] = shufflevector <8 x i32> [[COL_LOAD]], <8 x i32> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[SPLIT15:%.*]] = shufflevector <8 x i32> [[COL_LOAD]], <8 x i32> poison, <1 x i32> <i32 1>
+; CHECK-NEXT:    [[SPLIT16:%.*]] = shufflevector <8 x i32> [[COL_LOAD]], <8 x i32> poison, <1 x i32> <i32 2>
+; CHECK-NEXT:    [[SPLIT17:%.*]] = shufflevector <8 x i32> [[COL_LOAD]], <8 x i32> poison, <1 x i32> <i32 3>
+; CHECK-NEXT:    [[SPLIT18:%.*]] = shufflevector <8 x i32> [[COL_LOAD]], <8 x i32> poison, <1 x i32> <i32 4>
+; CHECK-NEXT:    [[SPLIT19:%.*]] = shufflevector <8 x i32> [[COL_LOAD]], <8 x i32> poison, <1 x i32> <i32 5>
+; CHECK-NEXT:    [[SPLIT20:%.*]] = shufflevector <8 x i32> [[COL_LOAD]], <8 x i32> poison, <1 x i32> <i32 6>
+; CHECK-NEXT:    [[SPLIT21:%.*]] = shufflevector <8 x i32> [[COL_LOAD]], <8 x i32> poison, <1 x i32> <i32 7>
+; 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 <1 x i32> [[COL_LOAD8]], <1 x i32> [[COL_LOAD10]], <2 x i32> <i32 0, i32 1>
+; CHECK-NEXT:    [[TMP3:%.*]] = shufflevector <1 x i32> [[COL_LOAD12]], <1 x i32> [[COL_LOAD14]], <2 x i32> <i32 0, i32 1>
+; CHECK-NEXT:    [[TMP4:%.*]] = shufflevector <2 x i32> [[TMP0]], <2 x i32> [[TMP1]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+; CHECK-NEXT:    [[TMP5:%.*]] = shufflevector <2 x i32> [[TMP2]], <2 x i32> [[TMP3]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+; CHECK-NEXT:    [[TMP6:%.*]] = shufflevector <4 x i32> [[TMP4]], <4 x i32> [[TMP5]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT:    [[SPLIT22:%.*]] = shufflevector <8 x i32> [[TMP6]], <8 x i32> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT:    [[BLOCK:%.*]] = shufflevector <1 x i32> [[SPLIT]], <1 x i32> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP7:%.*]] = extractelement <8 x i32> [[SPLIT22]], i64 0
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT:%.*]] = insertelement <1 x i32> poison, i32 [[TMP7]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT]], <1 x i32> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP8:%.*]] = mul <1 x i32> [[BLOCK]], [[SPLAT_SPLAT]]
+; CHECK-NEXT:    [[BLOCK23:%.*]] = shufflevector <1 x i32> [[SPLIT15]], <1 x i32> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP9:%.*]] = extractelement <8 x i32> [[SPLIT22]], i64 1
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT24:%.*]] = insertelement <1 x i32> poison, i32 [[TMP9]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT25:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT24]], <1 x i32> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP10:%.*]] = mul <1 x i32> [[BLOCK23]], [[SPLAT_SPLAT25]]
+; CHECK-NEXT:    [[TMP11:%.*]] = add <1 x i32> [[TMP8]], [[TMP10]]
+; CHECK-NEXT:    [[BLOCK26:%.*]] = shufflevector <1 x i32> [[SPLIT16]], <1 x i32> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP12:%.*]] = extractelement <8 x i32> [[SPLIT22]], i64 2
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT27:%.*]] = insertelement <1 x i32> poison, i32 [[TMP12]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT28:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT27]], <1 x i32> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP13:%.*]] = mul <1 x i32> [[BLOCK26]], [[SPLAT_SPLAT28]]
+; CHECK-NEXT:    [[TMP14:%.*]] = add <1 x i32> [[TMP11]], [[TMP13]]
+; CHECK-NEXT:    [[BLOCK29:%.*]] = shufflevector <1 x i32> [[SPLIT17]], <1 x i32> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP15:%.*]] = extractelement <8 x i32> [[SPLIT22]], i64 3
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT30:%.*]] = insertelement <1 x i32> poison, i32 [[TMP15]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT31:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT30]], <1 x i32> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP16:%.*]] = mul <1 x i32> [[BLOCK29]], [[SPLAT_SPLAT31]]
+; CHECK-NEXT:    [[TMP17:%.*]] = add <1 x i32> [[TMP14]], [[TMP16]]
+; CHECK-NEXT:    [[BLOCK32:%.*]] = shufflevector <1 x i32> [[SPLIT18]], <1 x i32> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP18:%.*]] = extractelement <8 x i32> [[SPLIT22]], i64 4
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT33:%.*]] = insertelement <1 x i32> poison, i32 [[TMP18]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT34:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT33]], <1 x i32> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP19:%.*]] = mul <1 x i32> [[BLOCK32]], [[SPLAT_SPLAT34]]
+; CHECK-NEXT:    [[TMP20:%.*]] = add <1 x i32> [[TMP17]], [[TMP19]]
+; CHECK-NEXT:    [[BLOCK35:%.*]] = shufflevector <1 x i32> [[SPLIT19]], <1 x i32> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP21:%.*]] = extractelement <8 x i32> [[SPLIT22]], i64 5
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT36:%.*]] = insertelement <1 x i32> poison, i32 [[TMP21]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT37:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT36]], <1 x i32> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP22:%.*]] = mul <1 x i32> [[BLOCK35]], [[SPLAT_SPLAT37]]
+; CHECK-NEXT:    [[TMP23:%.*]] = add <1 x i32> [[TMP20]], [[TMP22]]
+; CHECK-NEXT:    [[BLOCK38:%.*]] = shufflevector <1 x i32> [[SPLIT20]], <1 x i32> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP24:%.*]] = extractelement <8 x i32> [[SPLIT22]], i64 6
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT39:%.*]] = insertelement <1 x i32> poison, i32 [[TMP24]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT40:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT39]], <1 x i32> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP25:%.*]] = mul <1 x i32> [[BLOCK38]], [[SPLAT_SPLAT40]]
+; CHECK-NEXT:    [[TMP26:%.*]] = add <1 x i32> [[TMP23]], [[TMP25]]
+; CHECK-NEXT:    [[BLOCK41:%.*]] = shufflevector <1 x i32> [[SPLIT21]], <1 x i32> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP27:%.*]] = extractelement <8 x i32> [[SPLIT22]], i64 7
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT42:%.*]] = insertelement <1 x i32> poison, i32 [[TMP27]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT43:%.*]] = shufflevector <1 x i32> [[SPLAT_SPLATINSERT42]], <1 x i32> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP28:%.*]] = mul <1 x i32> [[BLOCK41]], [[SPLAT_SPLAT43]]
+; CHECK-NEXT:    [[TMP29:%.*]] = add <1 x i32> [[TMP26]], [[TMP28]]
+; CHECK-NEXT:    [[TMP30:%.*]] = shufflevector <1 x i32> [[TMP29]], <1 x i32> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP31:%.*]] = shufflevector <1 x i32> undef, <1 x i32> [[TMP30]], <1 x i32> <i32 1>
+; CHECK-NEXT:    ret <1 x i32> [[TMP31]]
+;
+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 8, i1 false, i32 1, i32 8)
+  %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
+}
+
+declare <8 x i32> @llvm.matrix.column.major.load.v8i32.i64(ptr nonnull align 4, i64, i1, i32, i32)
+declare <1 x i32> @llvm.matrix.multiply.v1i32.v8i32.v8i32(<8 x i32>, <8 x i32>, i32, i32, i32)
+
+define <1 x i16> @LoadInst_dot_product_i16_v6(ptr %lhs_address, ptr %rhs_address) {
+; CHECK-LABEL: @LoadInst_dot_product_i16_v6(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[COL_LOAD:%.*]] = load <1 x i16>, ptr [[LHS_ADDRESS:%.*]], align 16
+; CHECK-NEXT:    [[VEC_GEP:%.*]] = getelementptr i16, ptr [[LHS_ADDRESS]], i64 1
+; CHECK-NEXT:    [[COL_LOAD1:%.*]] = load <1 x i16>, ptr [[VEC_GEP]], align 2
+; CHECK-NEXT:    [[VEC_GEP2:%.*]] = getelementptr i16, ptr [[LHS_ADDRESS]], i64 2
+; CHECK-NEXT:    [[COL_LOAD3:%.*]] = load <1 x i16>, ptr [[VEC_GEP2]], align 4
+; CHECK-NEXT:    [[VEC_GEP4:%.*]] = getelementptr i16, ptr [[LHS_ADDRESS]], i64 3
+; CHECK-NEXT:    [[COL_LOAD5:%.*]] = load <1 x i16>, ptr [[VEC_GEP4]], align 2
+; CHECK-NEXT:    [[VEC_GEP6:%.*]] = getelementptr i16, ptr [[LHS_ADDRESS]], i64 4
+; CHECK-NEXT:    [[COL_LOAD7:%.*]] = load <1 x i16>, ptr [[VEC_GEP6]], align 8
+; CHECK-NEXT:    [[VEC_GEP8:%.*]] = getelementptr i16, ptr [[LHS_ADDRESS]], i64 5
+; CHECK-NEXT:    [[COL_LOAD9:%.*]] = load <1 x i16>, ptr [[VEC_GEP8]], align 2
+; CHECK-NEXT:    [[COL_LOAD10:%.*]] = load <6 x i16>, ptr [[RHS_ADDRESS:%.*]], align 16
+; CHECK-NEXT:    [[BLOCK:%.*]] = shufflevector <1 x i16> [[COL_LOAD]], <1 x i16> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP0:%.*]] = extractelement <6 x i16> [[COL_LOAD10]], i64 0
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT:%.*]] = insertelement <1 x i16> poison, i16 [[TMP0]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT:%.*]] = shufflevector <1 x i16> [[SPLAT_SPLATINSERT]], <1 x i16> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP1:%.*]] = mul <1 x i16> [[BLOCK]], [[SPLAT_SPLAT]]
+; CHECK-NEXT:    [[BLOCK11:%.*]] = shufflevector <1 x i16> [[COL_LOAD1]], <1 x i16> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <6 x i16> [[COL_LOAD10]], i64 1
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT12:%.*]] = insertelement <1 x i16> poison, i16 [[TMP2]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT13:%.*]] = shufflevector <1 x i16> [[SPLAT_SPLATINSERT12]], <1 x i16> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP3:%.*]] = mul <1 x i16> [[BLOCK11]], [[SPLAT_SPLAT13]]
+; CHECK-NEXT:    [[TMP4:%.*]] = add <1 x i16> [[TMP1]], [[TMP3]]
+; CHECK-NEXT:    [[BLOCK14:%.*]] = shufflevector <1 x i16> [[COL_LOAD3]], <1 x i16> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <6 x i16> [[COL_LOAD10]], i64 2
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT15:%.*]] = insertelement <1 x i16> poison, i16 [[TMP5]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT16:%.*]] = shufflevector <1 x i16> [[SPLAT_SPLATINSERT15]], <1 x i16> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP6:%.*]] = mul <1 x i16> [[BLOCK14]], [[SPLAT_SPLAT16]]
+; CHECK-NEXT:    [[TMP7:%.*]] = add <1 x i16> [[TMP4]], [[TMP6]]
+; CHECK-NEXT:    [[BLOCK17:%.*]] = shufflevector <1 x i16> [[COL_LOAD5]], <1 x i16> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP8:%.*]] = extractelement <6 x i16> [[COL_LOAD10]], i64 3
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT18:%.*]] = insertelement <1 x i16> poison, i16 [[TMP8]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT19:%.*]] = shufflevector <1 x i16> [[SPLAT_SPLATINSERT18]], <1 x i16> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP9:%.*]] = mul <1 x i16> [[BLOCK17]], [[SPLAT_SPLAT19]]
+; CHECK-NEXT:    [[TMP10:%.*]] = add <1 x i16> [[TMP7]], [[TMP9]]
+; CHECK-NEXT:    [[BLOCK20:%.*]] = shufflevector <1 x i16> [[COL_LOAD7]], <1 x i16> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP11:%.*]] = extractelement <6 x i16> [[COL_LOAD10]], i64 4
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT21:%.*]] = insertelement <1 x i16> poison, i16 [[TMP11]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT22:%.*]] = shufflevector <1 x i16> [[SPLAT_SPLATINSERT21]], <1 x i16> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP12:%.*]] = mul <1 x i16> [[BLOCK20]], [[SPLAT_SPLAT22]]
+; CHECK-NEXT:    [[TMP13:%.*]] = add <1 x i16> [[TMP10]], [[TMP12]]
+; CHECK-NEXT:    [[BLOCK23:%.*]] = shufflevector <1 x i16> [[COL_LOAD9]], <1 x i16> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP14:%.*]] = extractelement <6 x i16> [[COL_LOAD10]], i64 5
+; CHECK-NEXT:    [[SPLAT_SPLATINSERT24:%.*]] = insertelement <1 x i16> poison, i16 [[TMP14]], i32 0
+; CHECK-NEXT:    [[SPLAT_SPLAT25:%.*]] = shufflevector <1 x i16> [[SPLAT_SPLATINSERT24]], <1 x i16> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP15:%.*]] = mul <1 x i16> [[BLOCK23]], [[SPLAT_SPLAT25]]
+; CHECK-NEXT:    [[TMP16:%.*]] = add <1 x i16> [[TMP13]], [[TMP15]]
+; CHECK-NEXT:    [[TMP17:%.*]] = shufflevector <1 x i16> [[TMP16]], <1 x i16> poison, <1 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP18:%.*]] = shufflevector <1 x i16> undef, <1 x i16> [[TMP17]], <1 x i32> <i32 1>
+; CHECK-NEXT:    ret <1 x i16> [[TMP18]]
+;
+entry:
+  %lhs = load <6 x i16>, ptr %lhs_address
+  %rhs = load <6 x i16>, ptr %rhs_address
+  %result = tail call <1 x i16> @llvm.matrix.multiply.v1i16.v6i16.v6i16(<6 x i16> %lhs, <6 x i16> %rhs, i32 1, i32 6, i32 1)
+  ret <1 x i16> %result
+}
+
+declare <1 x i16> @llvm.matrix.multiply.v1i16.v6i16.v6i16(<6 x i16>, <6 x i16>, i32, i32, i32)