Merge branch 'main' into users/mingmingl-llvm/samplefdo-profile-formatusers/mingmingl-llvm/samplefdo-profile-format

1 files changed, 309 insertions, 0 deletions

diff --git a/clang/test/CodeGen/PowerPC/builtins-dmf-vsx-vector-float.c b/clang/test/CodeGen/PowerPC/builtins-dmf-vsx-vector-float.c
new file mode 100644
index 000000000000..8fc9a68a5a61
--- /dev/null
+++ b/clang/test/CodeGen/PowerPC/builtins-dmf-vsx-vector-float.c
@@ -0,0 +1,309 @@
+// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --version 5
+//       Update then manual applied to commonize the checks for AIX and LoP.
+// RUN: %clang_cc1 -O3 -triple powerpc64le-unknown-unknown -target-cpu future \
+// RUN:            -emit-llvm %s -o - | FileCheck %s
+// RUN: %clang_cc1 -O3 -triple powerpc64-ibm-aix -target-cpu future \
+// RUN:             -emit-llvm %s -o - | FileCheck %s
+
+// CHECK-LABEL: void @test_dmxvbf16gerx2(
+// CHECK-NEXT:  [[ENTRY:.*:]]
+// CHECK-NEXT:    [[TMP0:%.*]] = load <256 x i1>, ptr [[VPP:%.*]], align 32, !tbaa [[TBAA2:![0-9]+]]
+// CHECK-NEXT:    [[TMP1:%.*]] = tail call <1024 x i1> @llvm.ppc.mma.dmxvbf16gerx2(<256 x i1> [[TMP0]], <16 x i8> [[VC:%.*]])
+// CHECK-NEXT:    store <1024 x i1> [[TMP1]], ptr [[RESP:%.*]], align 128, !tbaa [[TBAA6:![0-9]+]]
+// CHECK-NEXT:    ret void
+//
+void test_dmxvbf16gerx2(unsigned char *vdmrp, unsigned char *vpp, vector unsigned char vc, unsigned char *resp) {
+  __dmr1024 vdmr = *((__dmr1024 *)vdmrp);
+  __vector_pair vp = *((__vector_pair *)vpp);
+  __builtin_mma_dmxvbf16gerx2(&vdmr, vp, vc);
+  *((__dmr1024 *)resp) = vdmr;
+}
+
+// CHECK-LABEL: void @test_dmxvbf16gerx2nn(
+// CHECK-NEXT:  [[ENTRY:.*:]]
+// CHECK-NEXT:    [[TMP0:%.*]] = load <1024 x i1>, ptr [[VDMRP:%.*]], align 128, !tbaa [[TBAA6]]
+// CHECK-NEXT:    [[TMP1:%.*]] = load <256 x i1>, ptr [[VPP:%.*]], align 32, !tbaa [[TBAA2]]
+// CHECK-NEXT:    [[TMP2:%.*]] = tail call <1024 x i1> @llvm.ppc.mma.dmxvbf16gerx2nn(<1024 x i1> [[TMP0]], <256 x i1> [[TMP1]], <16 x i8> [[VC:%.*]])
+// CHECK-NEXT:    store <1024 x i1> [[TMP2]], ptr [[RESP:%.*]], align 128, !tbaa [[TBAA6]]
+// CHECK-NEXT:    ret void
+//
+void test_dmxvbf16gerx2nn(unsigned char *vdmrp, unsigned char *vpp, vector unsigned char vc, unsigned char *resp) {
+  __dmr1024 vdmr = *((__dmr1024 *)vdmrp);
+  __vector_pair vp = *((__vector_pair *)vpp);
+  __builtin_mma_dmxvbf16gerx2nn(&vdmr, vp, vc);
+  *((__dmr1024 *)resp) = vdmr;
+}
+
+// CHECK-LABEL: void @test_dmxvbf16gerx2np(
+// CHECK-NEXT:  [[ENTRY:.*:]]
+// CHECK-NEXT:    [[TMP0:%.*]] = load <1024 x i1>, ptr [[VDMRP:%.*]], align 128, !tbaa [[TBAA6]]
+// CHECK-NEXT:    [[TMP1:%.*]] = load <256 x i1>, ptr [[VPP:%.*]], align 32, !tbaa [[TBAA2]]
+// CHECK-NEXT:    [[TMP2:%.*]] = tail call <1024 x i1> @llvm.ppc.mma.dmxvbf16gerx2np(<1024 x i1> [[TMP0]], <256 x i1> [[TMP1]], <16 x i8> [[VC:%.*]])
+// CHECK-NEXT:    store <1024 x i1> [[TMP2]], ptr [[RESP:%.*]], align 128, !tbaa [[TBAA6]]
+// CHECK-NEXT:    ret void
+//
+void test_dmxvbf16gerx2np(unsigned char *vdmrp, unsigned char *vpp, vector unsigned char vc, unsigned char *resp) {
+  __dmr1024 vdmr = *((__dmr1024 *)vdmrp);
+  __vector_pair vp = *((__vector_pair *)vpp);
+  __builtin_mma_dmxvbf16gerx2np(&vdmr, vp, vc);
+  *((__dmr1024 *)resp) = vdmr;
+}
+
+// CHECK-LABEL: void @test_dmxvbf16gerx2pn(
+// CHECK-NEXT:  [[ENTRY:.*:]]
+// CHECK-NEXT:    [[TMP0:%.*]] = load <1024 x i1>, ptr [[VDMRP:%.*]], align 128, !tbaa [[TBAA6]]
+// CHECK-NEXT:    [[TMP1:%.*]] = load <256 x i1>, ptr [[VPP:%.*]], align 32, !tbaa [[TBAA2]]
+// CHECK-NEXT:    [[TMP2:%.*]] = tail call <1024 x i1> @llvm.ppc.mma.dmxvbf16gerx2pn(<1024 x i1> [[TMP0]], <256 x i1> [[TMP1]], <16 x i8> [[VC:%.*]])
+// CHECK-NEXT:    store <1024 x i1> [[TMP2]], ptr [[RESP:%.*]], align 128, !tbaa [[TBAA6]]
+// CHECK-NEXT:    ret void
+//
+void test_dmxvbf16gerx2pn(unsigned char *vdmrp, unsigned char *vpp, vector unsigned char vc, unsigned char *resp) {
+  __dmr1024 vdmr = *((__dmr1024 *)vdmrp);
+  __vector_pair vp = *((__vector_pair *)vpp);
+  __builtin_mma_dmxvbf16gerx2pn(&vdmr, vp, vc);
+  *((__dmr1024 *)resp) = vdmr;
+}
+
+// CHECK-LABEL: void @test_dmxvbf16gerx2pp(
+// CHECK-NEXT:  [[ENTRY:.*:]]
+// CHECK-NEXT:    [[TMP0:%.*]] = load <1024 x i1>, ptr [[VDMRP:%.*]], align 128, !tbaa [[TBAA6]]
+// CHECK-NEXT:    [[TMP1:%.*]] = load <256 x i1>, ptr [[VPP:%.*]], align 32, !tbaa [[TBAA2]]
+// CHECK-NEXT:    [[TMP2:%.*]] = tail call <1024 x i1> @llvm.ppc.mma.dmxvbf16gerx2pp(<1024 x i1> [[TMP0]], <256 x i1> [[TMP1]], <16 x i8> [[VC:%.*]])
+// CHECK-NEXT:    store <1024 x i1> [[TMP2]], ptr [[RESP:%.*]], align 128, !tbaa [[TBAA6]]
+// CHECK-NEXT:    ret void
+//
+void test_dmxvbf16gerx2pp(unsigned char *vdmrp, unsigned char *vpp, vector unsigned char vc, unsigned char *resp) {
+  __dmr1024 vdmr = *((__dmr1024 *)vdmrp);
+  __vector_pair vp = *((__vector_pair *)vpp);
+  __builtin_mma_dmxvbf16gerx2pp(&vdmr, vp, vc);
+  *((__dmr1024 *)resp) = vdmr;
+}
+
+// CHECK-LABEL: void @test_pmdmxvbf16gerx2(
+// CHECK-NEXT:  [[ENTRY:.*:]]
+// CHECK-NEXT:    [[TMP0:%.*]] = load <256 x i1>, ptr [[VPP:%.*]], align 32, !tbaa [[TBAA2]]
+// CHECK-NEXT:    [[TMP1:%.*]] = tail call <1024 x i1> @llvm.ppc.mma.pmdmxvbf16gerx2(<256 x i1> [[TMP0]], <16 x i8> [[VC:%.*]], i32 0, i32 0, i32 0)
+// CHECK-NEXT:    store <1024 x i1> [[TMP1]], ptr [[RESP:%.*]], align 128, !tbaa [[TBAA6]]
+// CHECK-NEXT:    ret void
+//
+void test_pmdmxvbf16gerx2(unsigned char *vdmrp, unsigned char *vpp, vector unsigned char vc, unsigned char *resp) {
+  __dmr1024 vdmr = *((__dmr1024 *)vdmrp);
+  __vector_pair vp = *((__vector_pair *)vpp);
+  __builtin_mma_pmdmxvbf16gerx2(&vdmr, vp, vc, 0, 0, 0);
+  *((__dmr1024 *)resp) = vdmr;
+}
+
+// CHECK-LABEL: void @test_pmdmxvbf16gerx2nn(
+// CHECK-NEXT:  [[ENTRY:.*:]]
+// CHECK-NEXT:    [[TMP0:%.*]] = load <1024 x i1>, ptr [[VDMRP:%.*]], align 128, !tbaa [[TBAA6]]
+// CHECK-NEXT:    [[TMP1:%.*]] = load <256 x i1>, ptr [[VPP:%.*]], align 32, !tbaa [[TBAA2]]
+// CHECK-NEXT:    [[TMP2:%.*]] = tail call <1024 x i1> @llvm.ppc.mma.pmdmxvbf16gerx2nn(<1024 x i1> [[TMP0]], <256 x i1> [[TMP1]], <16 x i8> [[VC:%.*]], i32 0, i32 0, i32 0)
+// CHECK-NEXT:    store <1024 x i1> [[TMP2]], ptr [[RESP:%.*]], align 128, !tbaa [[TBAA6]]
+// CHECK-NEXT:    ret void
+//
+void test_pmdmxvbf16gerx2nn(unsigned char *vdmrp, unsigned char *vpp, vector unsigned char vc, unsigned char *resp) {
+  __dmr1024 vdmr = *((__dmr1024 *)vdmrp);
+  __vector_pair vp = *((__vector_pair *)vpp);
+  __builtin_mma_pmdmxvbf16gerx2nn(&vdmr, vp, vc, 0, 0, 0);
+  *((__dmr1024 *)resp) = vdmr;
+}
+
+// CHECK-LABEL: void @test_pmdmxvbf16gerx2np(
+// CHECK-NEXT:  [[ENTRY:.*:]]
+// CHECK-NEXT:    [[TMP0:%.*]] = load <1024 x i1>, ptr [[VDMRP:%.*]], align 128, !tbaa [[TBAA6]]
+// CHECK-NEXT:    [[TMP1:%.*]] = load <256 x i1>, ptr [[VPP:%.*]], align 32, !tbaa [[TBAA2]]
+// CHECK-NEXT:    [[TMP2:%.*]] = tail call <1024 x i1> @llvm.ppc.mma.pmdmxvbf16gerx2np(<1024 x i1> [[TMP0]], <256 x i1> [[TMP1]], <16 x i8> [[VC:%.*]], i32 0, i32 0, i32 0)
+// CHECK-NEXT:    store <1024 x i1> [[TMP2]], ptr [[RESP:%.*]], align 128, !tbaa [[TBAA6]]
+// CHECK-NEXT:    ret void
+//
+void test_pmdmxvbf16gerx2np(unsigned char *vdmrp, unsigned char *vpp, vector unsigned char vc, unsigned char *resp) {
+  __dmr1024 vdmr = *((__dmr1024 *)vdmrp);
+  __vector_pair vp = *((__vector_pair *)vpp);
+  __builtin_mma_pmdmxvbf16gerx2np(&vdmr, vp, vc, 0, 0, 0);
+  *((__dmr1024 *)resp) = vdmr;
+}
+
+// CHECK-LABEL: void @test_pmdmxvbf16gerx2pn(
+// CHECK-NEXT:  [[ENTRY:.*:]]
+// CHECK-NEXT:    [[TMP0:%.*]] = load <1024 x i1>, ptr [[VDMRP:%.*]], align 128, !tbaa [[TBAA6]]
+// CHECK-NEXT:    [[TMP1:%.*]] = load <256 x i1>, ptr [[VPP:%.*]], align 32, !tbaa [[TBAA2]]
+// CHECK-NEXT:    [[TMP2:%.*]] = tail call <1024 x i1> @llvm.ppc.mma.pmdmxvbf16gerx2pn(<1024 x i1> [[TMP0]], <256 x i1> [[TMP1]], <16 x i8> [[VC:%.*]], i32 0, i32 0, i32 0)
+// CHECK-NEXT:    store <1024 x i1> [[TMP2]], ptr [[RESP:%.*]], align 128, !tbaa [[TBAA6]]
+// CHECK-NEXT:    ret void
+//
+void test_pmdmxvbf16gerx2pn(unsigned char *vdmrp, unsigned char *vpp, vector unsigned char vc, unsigned char *resp) {
+  __dmr1024 vdmr = *((__dmr1024 *)vdmrp);
+  __vector_pair vp = *((__vector_pair *)vpp);
+  __builtin_mma_pmdmxvbf16gerx2pn(&vdmr, vp, vc, 0, 0, 0);
+  *((__dmr1024 *)resp) = vdmr;
+}
+
+// CHECK-LABEL: void @test_pmdmxvbf16gerx2pp(
+// CHECK-NEXT:  [[ENTRY:.*:]]
+// CHECK-NEXT:    [[TMP0:%.*]] = load <1024 x i1>, ptr [[VDMRP:%.*]], align 128, !tbaa [[TBAA6]]
+// CHECK-NEXT:    [[TMP1:%.*]] = load <256 x i1>, ptr [[VPP:%.*]], align 32, !tbaa [[TBAA2]]
+// CHECK-NEXT:    [[TMP2:%.*]] = tail call <1024 x i1> @llvm.ppc.mma.pmdmxvbf16gerx2pp(<1024 x i1> [[TMP0]], <256 x i1> [[TMP1]], <16 x i8> [[VC:%.*]], i32 0, i32 0, i32 0)
+// CHECK-NEXT:    store <1024 x i1> [[TMP2]], ptr [[RESP:%.*]], align 128, !tbaa [[TBAA6]]
+// CHECK-NEXT:    ret void
+//
+void test_pmdmxvbf16gerx2pp(unsigned char *vdmrp, unsigned char *vpp, vector unsigned char vc, unsigned char *resp) {
+  __dmr1024 vdmr = *((__dmr1024 *)vdmrp);
+  __vector_pair vp = *((__vector_pair *)vpp);
+  __builtin_mma_pmdmxvbf16gerx2pp(&vdmr, vp, vc, 0, 0, 0);
+  *((__dmr1024 *)resp) = vdmr;
+}
+
+// CHECK-LABEL: void @test_dmxvf16gerx2(
+// CHECK-NEXT:  [[ENTRY:.*:]]
+// CHECK-NEXT:    [[TMP0:%.*]] = load <256 x i1>, ptr [[VPP:%.*]], align 32, !tbaa [[TBAA2:![0-9]+]]
+// CHECK-NEXT:    [[TMP1:%.*]] = tail call <1024 x i1> @llvm.ppc.mma.dmxvf16gerx2(<256 x i1> [[TMP0]], <16 x i8> [[VC:%.*]])
+// CHECK-NEXT:    store <1024 x i1> [[TMP1]], ptr [[RESP:%.*]], align 128, !tbaa [[TBAA6:![0-9]+]]
+// CHECK-NEXT:    ret void
+//
+void test_dmxvf16gerx2(unsigned char *vdmrp, unsigned char *vpp, vector unsigned char vc, unsigned char *resp) {
+  __dmr1024 vdmr = *((__dmr1024 *)vdmrp);
+  __vector_pair vp = *((__vector_pair *)vpp);
+  __builtin_mma_dmxvf16gerx2(&vdmr, vp, vc);
+  *((__dmr1024 *)resp) = vdmr;
+}
+
+// CHECK-LABEL: void @test_dmxvf16gerx2nn(
+// CHECK-NEXT:  [[ENTRY:.*:]]
+// CHECK-NEXT:    [[TMP0:%.*]] = load <1024 x i1>, ptr [[VDMRP:%.*]], align 128, !tbaa [[TBAA6]]
+// CHECK-NEXT:    [[TMP1:%.*]] = load <256 x i1>, ptr [[VPP:%.*]], align 32, !tbaa [[TBAA2]]
+// CHECK-NEXT:    [[TMP2:%.*]] = tail call <1024 x i1> @llvm.ppc.mma.dmxvf16gerx2nn(<1024 x i1> [[TMP0]], <256 x i1> [[TMP1]], <16 x i8> [[VC:%.*]])
+// CHECK-NEXT:    store <1024 x i1> [[TMP2]], ptr [[RESP:%.*]], align 128, !tbaa [[TBAA6]]
+// CHECK-NEXT:    ret void
+//
+void test_dmxvf16gerx2nn(unsigned char *vdmrp, unsigned char *vpp, vector unsigned char vc, unsigned char *resp) {
+  __dmr1024 vdmr = *((__dmr1024 *)vdmrp);
+  __vector_pair vp = *((__vector_pair *)vpp);
+  __builtin_mma_dmxvf16gerx2nn(&vdmr, vp, vc);
+  *((__dmr1024 *)resp) = vdmr;
+}
+
+// CHECK-LABEL: void @test_dmxvf16gerx2np(
+// CHECK-NEXT:  [[ENTRY:.*:]]
+// CHECK-NEXT:    [[TMP0:%.*]] = load <1024 x i1>, ptr [[VDMRP:%.*]], align 128, !tbaa [[TBAA6]]
+// CHECK-NEXT:    [[TMP1:%.*]] = load <256 x i1>, ptr [[VPP:%.*]], align 32, !tbaa [[TBAA2]]
+// CHECK-NEXT:    [[TMP2:%.*]] = tail call <1024 x i1> @llvm.ppc.mma.dmxvf16gerx2np(<1024 x i1> [[TMP0]], <256 x i1> [[TMP1]], <16 x i8> [[VC:%.*]])
+// CHECK-NEXT:    store <1024 x i1> [[TMP2]], ptr [[RESP:%.*]], align 128, !tbaa [[TBAA6]]
+// CHECK-NEXT:    ret void
+//
+void test_dmxvf16gerx2np(unsigned char *vdmrp, unsigned char *vpp, vector unsigned char vc, unsigned char *resp) {
+  __dmr1024 vdmr = *((__dmr1024 *)vdmrp);
+  __vector_pair vp = *((__vector_pair *)vpp);
+  __builtin_mma_dmxvf16gerx2np(&vdmr, vp, vc);
+  *((__dmr1024 *)resp) = vdmr;
+}
+
+// CHECK-LABEL: void @test_dmxvf16gerx2pn(
+// CHECK-NEXT:  [[ENTRY:.*:]]
+// CHECK-NEXT:    [[TMP0:%.*]] = load <1024 x i1>, ptr [[VDMRP:%.*]], align 128, !tbaa [[TBAA6]]
+// CHECK-NEXT:    [[TMP1:%.*]] = load <256 x i1>, ptr [[VPP:%.*]], align 32, !tbaa [[TBAA2]]
+// CHECK-NEXT:    [[TMP2:%.*]] = tail call <1024 x i1> @llvm.ppc.mma.dmxvf16gerx2pn(<1024 x i1> [[TMP0]], <256 x i1> [[TMP1]], <16 x i8> [[VC:%.*]])
+// CHECK-NEXT:    store <1024 x i1> [[TMP2]], ptr [[RESP:%.*]], align 128, !tbaa [[TBAA6]]
+// CHECK-NEXT:    ret void
+//
+void test_dmxvf16gerx2pn(unsigned char *vdmrp, unsigned char *vpp, vector unsigned char vc, unsigned char *resp) {
+  __dmr1024 vdmr = *((__dmr1024 *)vdmrp);
+  __vector_pair vp = *((__vector_pair *)vpp);
+  __builtin_mma_dmxvf16gerx2pn(&vdmr, vp, vc);
+  *((__dmr1024 *)resp) = vdmr;
+}
+
+// CHECK-LABEL: void @test_dmxvf16gerx2pp(
+// CHECK-NEXT:  [[ENTRY:.*:]]
+// CHECK-NEXT:    [[TMP0:%.*]] = load <1024 x i1>, ptr [[VDMRP:%.*]], align 128, !tbaa [[TBAA6]]
+// CHECK-NEXT:    [[TMP1:%.*]] = load <256 x i1>, ptr [[VPP:%.*]], align 32, !tbaa [[TBAA2]]
+// CHECK-NEXT:    [[TMP2:%.*]] = tail call <1024 x i1> @llvm.ppc.mma.dmxvf16gerx2pp(<1024 x i1> [[TMP0]], <256 x i1> [[TMP1]], <16 x i8> [[VC:%.*]])
+// CHECK-NEXT:    store <1024 x i1> [[TMP2]], ptr [[RESP:%.*]], align 128, !tbaa [[TBAA6]]
+// CHECK-NEXT:    ret void
+//
+void test_dmxvf16gerx2pp(unsigned char *vdmrp, unsigned char *vpp, vector unsigned char vc, unsigned char *resp) {
+  __dmr1024 vdmr = *((__dmr1024 *)vdmrp);
+  __vector_pair vp = *((__vector_pair *)vpp);
+  __builtin_mma_dmxvf16gerx2pp(&vdmr, vp, vc);
+  *((__dmr1024 *)resp) = vdmr;
+}
+
+// CHECK-LABEL: void @test_pmdmxvf16gerx2(
+// CHECK-NEXT:  [[ENTRY:.*:]]
+// CHECK-NEXT:    [[TMP0:%.*]] = load <256 x i1>, ptr [[VPP:%.*]], align 32, !tbaa [[TBAA2]]
+// CHECK-NEXT:    [[TMP1:%.*]] = tail call <1024 x i1> @llvm.ppc.mma.pmdmxvf16gerx2(<256 x i1> [[TMP0]], <16 x i8> [[VC:%.*]], i32 0, i32 0, i32 0)
+// CHECK-NEXT:    store <1024 x i1> [[TMP1]], ptr [[RESP:%.*]], align 128, !tbaa [[TBAA6]]
+// CHECK-NEXT:    ret void
+//
+void test_pmdmxvf16gerx2(unsigned char *vdmrp, unsigned char *vpp, vector unsigned char vc, unsigned char *resp) {
+  __dmr1024 vdmr = *((__dmr1024 *)vdmrp);
+  __vector_pair vp = *((__vector_pair *)vpp);
+  __builtin_mma_pmdmxvf16gerx2(&vdmr, vp, vc, 0, 0, 0);
+  *((__dmr1024 *)resp) = vdmr;
+}
+
+// CHECK-LABEL: void @test_pmdmxvf16gerx2nn(
+// CHECK-NEXT:  [[ENTRY:.*:]]
+// CHECK-NEXT:    [[TMP0:%.*]] = load <1024 x i1>, ptr [[VDMRP:%.*]], align 128, !tbaa [[TBAA6]]
+// CHECK-NEXT:    [[TMP1:%.*]] = load <256 x i1>, ptr [[VPP:%.*]], align 32, !tbaa [[TBAA2]]
+// CHECK-NEXT:    [[TMP2:%.*]] = tail call <1024 x i1> @llvm.ppc.mma.pmdmxvf16gerx2nn(<1024 x i1> [[TMP0]], <256 x i1> [[TMP1]], <16 x i8> [[VC:%.*]], i32 0, i32 0, i32 0)
+// CHECK-NEXT:    store <1024 x i1> [[TMP2]], ptr [[RESP:%.*]], align 128, !tbaa [[TBAA6]]
+// CHECK-NEXT:    ret void
+//
+void test_pmdmxvf16gerx2nn(unsigned char *vdmrp, unsigned char *vpp, vector unsigned char vc, unsigned char *resp) {
+  __dmr1024 vdmr = *((__dmr1024 *)vdmrp);
+  __vector_pair vp = *((__vector_pair *)vpp);
+  __builtin_mma_pmdmxvf16gerx2nn(&vdmr, vp, vc, 0, 0, 0);
+  *((__dmr1024 *)resp) = vdmr;
+}
+
+// CHECK-LABEL: void @test_pmdmxvf16gerx2np(
+// CHECK-NEXT:  [[ENTRY:.*:]]
+// CHECK-NEXT:    [[TMP0:%.*]] = load <1024 x i1>, ptr [[VDMRP:%.*]], align 128, !tbaa [[TBAA6]]
+// CHECK-NEXT:    [[TMP1:%.*]] = load <256 x i1>, ptr [[VPP:%.*]], align 32, !tbaa [[TBAA2]]
+// CHECK-NEXT:    [[TMP2:%.*]] = tail call <1024 x i1> @llvm.ppc.mma.pmdmxvf16gerx2np(<1024 x i1> [[TMP0]], <256 x i1> [[TMP1]], <16 x i8> [[VC:%.*]], i32 0, i32 0, i32 0)
+// CHECK-NEXT:    store <1024 x i1> [[TMP2]], ptr [[RESP:%.*]], align 128, !tbaa [[TBAA6]]
+// CHECK-NEXT:    ret void
+//
+void test_pmdmxvf16gerx2np(unsigned char *vdmrp, unsigned char *vpp, vector unsigned char vc, unsigned char *resp) {
+  __dmr1024 vdmr = *((__dmr1024 *)vdmrp);
+  __vector_pair vp = *((__vector_pair *)vpp);
+  __builtin_mma_pmdmxvf16gerx2np(&vdmr, vp, vc, 0, 0, 0);
+  *((__dmr1024 *)resp) = vdmr;
+}
+
+// CHECK-LABEL: void @test_pmdmxvf16gerx2pn(
+// CHECK-NEXT:  [[ENTRY:.*:]]
+// CHECK-NEXT:    [[TMP0:%.*]] = load <1024 x i1>, ptr [[VDMRP:%.*]], align 128, !tbaa [[TBAA6]]
+// CHECK-NEXT:    [[TMP1:%.*]] = load <256 x i1>, ptr [[VPP:%.*]], align 32, !tbaa [[TBAA2]]
+// CHECK-NEXT:    [[TMP2:%.*]] = tail call <1024 x i1> @llvm.ppc.mma.pmdmxvf16gerx2pn(<1024 x i1> [[TMP0]], <256 x i1> [[TMP1]], <16 x i8> [[VC:%.*]], i32 0, i32 0, i32 0)
+// CHECK-NEXT:    store <1024 x i1> [[TMP2]], ptr [[RESP:%.*]], align 128, !tbaa [[TBAA6]]
+// CHECK-NEXT:    ret void
+//
+void test_pmdmxvf16gerx2pn(unsigned char *vdmrp, unsigned char *vpp, vector unsigned char vc, unsigned char *resp) {
+  __dmr1024 vdmr = *((__dmr1024 *)vdmrp);
+  __vector_pair vp = *((__vector_pair *)vpp);
+  __builtin_mma_pmdmxvf16gerx2pn(&vdmr, vp, vc, 0, 0, 0);
+  *((__dmr1024 *)resp) = vdmr;
+}
+
+// CHECK-LABEL: void @test_pmdmxvf16gerx2pp(
+// CHECK-NEXT:  [[ENTRY:.*:]]
+// CHECK-NEXT:    [[TMP0:%.*]] = load <1024 x i1>, ptr [[VDMRP:%.*]], align 128, !tbaa [[TBAA6]]
+// CHECK-NEXT:    [[TMP1:%.*]] = load <256 x i1>, ptr [[VPP:%.*]], align 32, !tbaa [[TBAA2]]
+// CHECK-NEXT:    [[TMP2:%.*]] = tail call <1024 x i1> @llvm.ppc.mma.pmdmxvf16gerx2pp(<1024 x i1> [[TMP0]], <256 x i1> [[TMP1]], <16 x i8> [[VC:%.*]], i32 0, i32 0, i32 0)
+// CHECK-NEXT:    store <1024 x i1> [[TMP2]], ptr [[RESP:%.*]], align 128, !tbaa [[TBAA6]]
+// CHECK-NEXT:    ret void
+//
+void test_pmdmxvf16gerx2pp(unsigned char *vdmrp, unsigned char *vpp, vector unsigned char vc, unsigned char *resp) {
+  __dmr1024 vdmr = *((__dmr1024 *)vdmrp);
+  __vector_pair vp = *((__vector_pair *)vpp);
+  __builtin_mma_pmdmxvf16gerx2pp(&vdmr, vp, vc, 0, 0, 0);
+  *((__dmr1024 *)resp) = vdmr;
+}
+
+// CHECK: [[TBAA2]] = !{[[META3:![0-9]+]], [[META3]], i64 0}
+// CHECK: [[META3]] = !{!"__vector_pair", [[META4:![0-9]+]], i64 0}
+// CHECK: [[META4]] = !{!"omnipotent char", [[META5:![0-9]+]], i64 0}
+// CHECK: [[META5]] = !{!"Simple C/C++ TBAA"}
+// CHECK: [[TBAA6]] = !{[[META7:![0-9]+]], [[META7]], i64 0}
+// CHECK: [[META7]] = !{!"__dmr1024", [[META4]], i64 0}