// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
// 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: @test_dmxvi8gerx4(
// 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.dmxvi8gerx4(<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_dmxvi8gerx4(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_dmxvi8gerx4(&vdmr, vp, vc);
  *((__dmr1024 *)resp) = vdmr;
}

// CHECK-LABEL: @test_pmdmxvi8gerx4(
// 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.pmdmxvi8gerx4(<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_pmdmxvi8gerx4(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_pmdmxvi8gerx4(&vdmr, vp, vc, 0, 0, 0);
  *((__dmr1024 *)resp) = vdmr;
}

// CHECK-LABEL: @test_dmxvi8gerx4pp(
// 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.dmxvi8gerx4pp(<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_dmxvi8gerx4pp(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_dmxvi8gerx4pp(&vdmr, vp, vc);
  *((__dmr1024 *)resp) = vdmr;
}

// CHECK-LABEL: @test_pmdmxvi8gerx4pp(
// 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.pmdmxvi8gerx4pp(<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_pmdmxvi8gerx4pp(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_pmdmxvi8gerx4pp(&vdmr, vp, vc, 0, 0, 0);
  *((__dmr1024 *)resp) = vdmr;
}

// CHECK-LABEL: @test_dmxvi8gerx4spp(
// 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.dmxvi8gerx4spp(<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_dmxvi8gerx4spp(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_dmxvi8gerx4spp(&vdmr, vp, vc);
  *((__dmr1024 *)resp) = vdmr;
}

// CHECK-LABEL: @test_pmdmxvi8gerx4spp(
// 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.pmdmxvi8gerx4spp(<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_pmdmxvi8gerx4spp(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_pmdmxvi8gerx4spp(&vdmr, vp, vc, 0, 0, 0);
  *((__dmr1024 *)resp) = vdmr;
}

// CHECK-LABEL: @test_dmf_basic
// CHECK-NEXT: entry:
// CHECK-NEXT: [[TMP0:%.*]] = tail call <1024 x i1> @llvm.ppc.mma.dmsetdmrz()
// CHECK-NEXT: [[TMP1:%.*]] = tail call <1024 x i1> @llvm.ppc.mma.dmmr(<1024 x i1> [[TMP0]])
// CHECK-NEXT: store <1024 x i1> [[TMP1]], ptr %res1, align 128
// CHECK-NEXT: [[TMP2:%.*]] = load <1024 x i1>, ptr %res2, align 128
// CHECK-NEXT: [[TMP3:%.*]] = load <1024 x i1>, ptr %p, align 128
// CHECK-NEXT: [[TMP4:%.*]] = tail call <1024 x i1> @llvm.ppc.mma.dmxor(<1024 x i1> [[TMP2]], <1024 x i1> [[TMP3]])
// CHECK-NEXT: store <1024 x i1> [[TMP4]], ptr %res2, align 128
void test_dmf_basic(char *p, char *res1, char *res2) {
  __dmr1024 x[2];
  __builtin_mma_dmsetdmrz(&x[0]);
  __builtin_mma_dmmr((__dmr1024*)res1, &x[0]);
  __builtin_mma_dmxor((__dmr1024*)res2, (__dmr1024*)p);
}