1 files changed, 68 insertions, 0 deletions
diff --git a/llvm/test/Transforms/LowerMatrixIntrinsics/strided-store-double.ll b/llvm/test/Transforms/LowerMatrixIntrinsics/strided-store-double.ll
new file mode 100644
index 00000000000..377c7effbbf
--- /dev/null
+++ b/llvm/test/Transforms/LowerMatrixIntrinsics/strided-store-double.ll
@@ -0,0 +1,68 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt -lower-matrix-intrinsics -S < %s | FileCheck %s
+; RUN: opt -passes='lower-matrix-intrinsics' -S < %s | FileCheck %s
+
+define void @strided_store_3x2(<6 x double> %in, double* %out) {
+; CHECK-LABEL: @strided_store_3x2(
+; CHECK-NEXT:    [[SPLIT:%.*]] = shufflevector <6 x double> [[IN:%.*]], <6 x double> undef, <3 x i32> <i32 0, i32 1, i32 2>
+; CHECK-NEXT:    [[SPLIT1:%.*]] = shufflevector <6 x double> [[IN]], <6 x double> undef, <3 x i32> <i32 3, i32 4, i32 5>
+; CHECK-NEXT:    [[TMP1:%.*]] = bitcast double* [[OUT:%.*]] to <3 x double>*
+; CHECK-NEXT:    store <3 x double> [[SPLIT]], <3 x double>* [[TMP1]], align 8
+; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr double, double* [[OUT]], i32 5
+; CHECK-NEXT:    [[TMP3:%.*]] = bitcast double* [[TMP2]] to <3 x double>*
+; CHECK-NEXT:    store <3 x double> [[SPLIT1]], <3 x double>* [[TMP3]], align 8
+; CHECK-NEXT:    ret void
+;
+  call void @llvm.matrix.columnwise.store(<6 x double> %in, double* %out, i32 5, i32 3, i32 2)
+  ret void
+}
+
+define void @strided_store_3x2_nonconst_stride(<6 x double> %in, i32 %stride, double* %out) {
+; CHECK-LABEL: @strided_store_3x2_nonconst_stride(
+; CHECK-NEXT:    [[SPLIT:%.*]] = shufflevector <6 x double> [[IN:%.*]], <6 x double> undef, <3 x i32> <i32 0, i32 1, i32 2>
+; CHECK-NEXT:    [[SPLIT1:%.*]] = shufflevector <6 x double> [[IN]], <6 x double> undef, <3 x i32> <i32 3, i32 4, i32 5>
+; CHECK-NEXT:    [[TMP1:%.*]] = mul i32 0, [[STRIDE:%.*]]
+; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr double, double* [[OUT:%.*]], i32 [[TMP1]]
+; CHECK-NEXT:    [[TMP3:%.*]] = bitcast double* [[TMP2]] to <3 x double>*
+; CHECK-NEXT:    store <3 x double> [[SPLIT]], <3 x double>* [[TMP3]], align 8
+; CHECK-NEXT:    [[TMP4:%.*]] = mul i32 1, [[STRIDE]]
+; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr double, double* [[OUT]], i32 [[TMP4]]
+; CHECK-NEXT:    [[TMP6:%.*]] = bitcast double* [[TMP5]] to <3 x double>*
+; CHECK-NEXT:    store <3 x double> [[SPLIT1]], <3 x double>* [[TMP6]], align 8
+; CHECK-NEXT:    ret void
+;
+  call void @llvm.matrix.columnwise.store(<6 x double> %in, double* %out, i32 %stride, i32 3, i32 2)
+  ret void
+}
+
+
+declare void @llvm.matrix.columnwise.store(<6 x double>, double*, i32, i32, i32)
+
+define void @strided_store_2x3(<10 x double> %in, double* %out) {
+; CHECK-LABEL: @strided_store_2x3(
+; CHECK-NEXT:    [[SPLIT:%.*]] = shufflevector <10 x double> [[IN:%.*]], <10 x double> undef, <2 x i32> <i32 0, i32 1>
+; CHECK-NEXT:    [[SPLIT1:%.*]] = shufflevector <10 x double> [[IN]], <10 x double> undef, <2 x i32> <i32 2, i32 3>
+; CHECK-NEXT:    [[SPLIT2:%.*]] = shufflevector <10 x double> [[IN]], <10 x double> undef, <2 x i32> <i32 4, i32 5>
+; CHECK-NEXT:    [[SPLIT3:%.*]] = shufflevector <10 x double> [[IN]], <10 x double> undef, <2 x i32> <i32 6, i32 7>
+; CHECK-NEXT:    [[SPLIT4:%.*]] = shufflevector <10 x double> [[IN]], <10 x double> undef, <2 x i32> <i32 8, i32 9>
+; CHECK-NEXT:    [[TMP1:%.*]] = bitcast double* [[OUT:%.*]] to <2 x double>*
+; CHECK-NEXT:    store <2 x double> [[SPLIT]], <2 x double>* [[TMP1]], align 8
+; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr double, double* [[OUT]], i32 4
+; CHECK-NEXT:    [[TMP3:%.*]] = bitcast double* [[TMP2]] to <2 x double>*
+; CHECK-NEXT:    store <2 x double> [[SPLIT1]], <2 x double>* [[TMP3]], align 8
+; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr double, double* [[OUT]], i32 8
+; CHECK-NEXT:    [[TMP5:%.*]] = bitcast double* [[TMP4]] to <2 x double>*
+; CHECK-NEXT:    store <2 x double> [[SPLIT2]], <2 x double>* [[TMP5]], align 8
+; CHECK-NEXT:    [[TMP6:%.*]] = getelementptr double, double* [[OUT]], i32 12
+; CHECK-NEXT:    [[TMP7:%.*]] = bitcast double* [[TMP6]] to <2 x double>*
+; CHECK-NEXT:    store <2 x double> [[SPLIT3]], <2 x double>* [[TMP7]], align 8
+; CHECK-NEXT:    [[TMP8:%.*]] = getelementptr double, double* [[OUT]], i32 16
+; CHECK-NEXT:    [[TMP9:%.*]] = bitcast double* [[TMP8]] to <2 x double>*
+; CHECK-NEXT:    store <2 x double> [[SPLIT4]], <2 x double>* [[TMP9]], align 8
+; CHECK-NEXT:    ret void
+;
+  call void @llvm.matrix.columnwise.store.v10f64(<10 x double> %in, double* %out, i32 4, i32 2, i32 5)
+  ret void
+}
+
+declare void @llvm.matrix.columnwise.store.v10f64(<10 x double>, double*, i32, i32, i32)