derek/TheRock
1
0 Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity
Files
main
TheRock/compiler/amd-llvm/clang/test/CodeGen/PowerPC/builtins-dmf-vsx-vector-float.c
T
derek.holloway 7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
Details
CodeQL / Analyze (python) (push) Canceled after 0s
Details
pre-commit / pre-commit (push) Canceled after 0s
Details
Multi-Arch CI / setup (push) Canceled after 0s
Details
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Details
Setup (Multi-Arch) / setup (push) Canceled after 0s
Details
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Details
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
Details
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Details
Multi-Arch CI / CI Summary (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Details
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Details
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
Details
Flatten subprojects into a single base monorepo
2026-09-02 16:34:47 -07:00

515 lines
38 KiB
C
Raw Permalink Blame History

// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --version 6
// 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-prefix=AIX
// CHECK-LABEL: define dso_local void @test_dmxvbf16gerx2(
// CHECK-SAME: ptr noundef readnone captures(none) [[VDMRP:%.*]], ptr noundef readonly captures(none) [[VPP:%.*]], <16 x i8> noundef [[VC:%.*]], ptr noundef writeonly captures(none) initializes((0, 128)) [[RESP:%.*]]) local_unnamed_addr #[[ATTR0:[0-9]+]] {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: [[TMP0:%.*]] = load <256 x i1>, ptr [[VPP]], align 32, !tbaa [[__VECTOR_PAIR_TBAA6:![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 [[__DMR1024_TBAA8:![0-9]+]]
// CHECK-NEXT: ret void
//
// AIX-LABEL: define void @test_dmxvbf16gerx2(
// AIX-SAME: ptr noundef readnone captures(none) [[VDMRP:%.*]], ptr noundef readonly captures(none) [[VPP:%.*]], <16 x i8> noundef [[VC:%.*]], ptr noundef writeonly captures(none) initializes((0, 128)) [[RESP:%.*]]) local_unnamed_addr #[[ATTR0:[0-9]+]] {
// AIX-NEXT: [[ENTRY:.*:]]
// AIX-NEXT: [[TMP0:%.*]] = load <256 x i1>, ptr [[VPP]], align 32, !tbaa [[__VECTOR_PAIR_TBAA6:![0-9]+]]
// AIX-NEXT: [[TMP1:%.*]] = tail call <1024 x i1> @llvm.ppc.mma.dmxvbf16gerx2(<256 x i1> [[TMP0]], <16 x i8> [[VC]])
// AIX-NEXT: store <1024 x i1> [[TMP1]], ptr [[RESP]], align 128, !tbaa [[__DMR1024_TBAA8:![0-9]+]]
// AIX-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: define dso_local void @test_dmxvbf16gerx2nn(
// CHECK-SAME: ptr noundef readonly captures(none) [[VDMRP:%.*]], ptr noundef readonly captures(none) [[VPP:%.*]], <16 x i8> noundef [[VC:%.*]], ptr noundef writeonly captures(none) initializes((0, 128)) [[RESP:%.*]]) local_unnamed_addr #[[ATTR0]] {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: [[TMP0:%.*]] = load <1024 x i1>, ptr [[VDMRP]], align 128, !tbaa [[__DMR1024_TBAA8]]
// CHECK-NEXT: [[TMP1:%.*]] = load <256 x i1>, ptr [[VPP]], align 32, !tbaa [[__VECTOR_PAIR_TBAA6]]
// 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 [[__DMR1024_TBAA8]]
// CHECK-NEXT: ret void
//
// AIX-LABEL: define void @test_dmxvbf16gerx2nn(
// AIX-SAME: ptr noundef readonly captures(none) [[VDMRP:%.*]], ptr noundef readonly captures(none) [[VPP:%.*]], <16 x i8> noundef [[VC:%.*]], ptr noundef writeonly captures(none) initializes((0, 128)) [[RESP:%.*]]) local_unnamed_addr #[[ATTR0]] {
// AIX-NEXT: [[ENTRY:.*:]]
// AIX-NEXT: [[TMP0:%.*]] = load <1024 x i1>, ptr [[VDMRP]], align 128, !tbaa [[__DMR1024_TBAA8]]
// AIX-NEXT: [[TMP1:%.*]] = load <256 x i1>, ptr [[VPP]], align 32, !tbaa [[__VECTOR_PAIR_TBAA6]]
// AIX-NEXT: [[TMP2:%.*]] = tail call <1024 x i1> @llvm.ppc.mma.dmxvbf16gerx2nn(<1024 x i1> [[TMP0]], <256 x i1> [[TMP1]], <16 x i8> [[VC]])
// AIX-NEXT: store <1024 x i1> [[TMP2]], ptr [[RESP]], align 128, !tbaa [[__DMR1024_TBAA8]]
// AIX-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: define dso_local void @test_dmxvbf16gerx2np(
// CHECK-SAME: ptr noundef readonly captures(none) [[VDMRP:%.*]], ptr noundef readonly captures(none) [[VPP:%.*]], <16 x i8> noundef [[VC:%.*]], ptr noundef writeonly captures(none) initializes((0, 128)) [[RESP:%.*]]) local_unnamed_addr #[[ATTR0]] {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: [[TMP0:%.*]] = load <1024 x i1>, ptr [[VDMRP]], align 128, !tbaa [[__DMR1024_TBAA8]]
// CHECK-NEXT: [[TMP1:%.*]] = load <256 x i1>, ptr [[VPP]], align 32, !tbaa [[__VECTOR_PAIR_TBAA6]]
// 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 [[__DMR1024_TBAA8]]
// CHECK-NEXT: ret void
//
// AIX-LABEL: define void @test_dmxvbf16gerx2np(
// AIX-SAME: ptr noundef readonly captures(none) [[VDMRP:%.*]], ptr noundef readonly captures(none) [[VPP:%.*]], <16 x i8> noundef [[VC:%.*]], ptr noundef writeonly captures(none) initializes((0, 128)) [[RESP:%.*]]) local_unnamed_addr #[[ATTR0]] {
// AIX-NEXT: [[ENTRY:.*:]]
// AIX-NEXT: [[TMP0:%.*]] = load <1024 x i1>, ptr [[VDMRP]], align 128, !tbaa [[__DMR1024_TBAA8]]
// AIX-NEXT: [[TMP1:%.*]] = load <256 x i1>, ptr [[VPP]], align 32, !tbaa [[__VECTOR_PAIR_TBAA6]]
// AIX-NEXT: [[TMP2:%.*]] = tail call <1024 x i1> @llvm.ppc.mma.dmxvbf16gerx2np(<1024 x i1> [[TMP0]], <256 x i1> [[TMP1]], <16 x i8> [[VC]])
// AIX-NEXT: store <1024 x i1> [[TMP2]], ptr [[RESP]], align 128, !tbaa [[__DMR1024_TBAA8]]
// AIX-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: define dso_local void @test_dmxvbf16gerx2pn(
// CHECK-SAME: ptr noundef readonly captures(none) [[VDMRP:%.*]], ptr noundef readonly captures(none) [[VPP:%.*]], <16 x i8> noundef [[VC:%.*]], ptr noundef writeonly captures(none) initializes((0, 128)) [[RESP:%.*]]) local_unnamed_addr #[[ATTR0]] {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: [[TMP0:%.*]] = load <1024 x i1>, ptr [[VDMRP]], align 128, !tbaa [[__DMR1024_TBAA8]]
// CHECK-NEXT: [[TMP1:%.*]] = load <256 x i1>, ptr [[VPP]], align 32, !tbaa [[__VECTOR_PAIR_TBAA6]]
// 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 [[__DMR1024_TBAA8]]
// CHECK-NEXT: ret void
//
// AIX-LABEL: define void @test_dmxvbf16gerx2pn(
// AIX-SAME: ptr noundef readonly captures(none) [[VDMRP:%.*]], ptr noundef readonly captures(none) [[VPP:%.*]], <16 x i8> noundef [[VC:%.*]], ptr noundef writeonly captures(none) initializes((0, 128)) [[RESP:%.*]]) local_unnamed_addr #[[ATTR0]] {
// AIX-NEXT: [[ENTRY:.*:]]
// AIX-NEXT: [[TMP0:%.*]] = load <1024 x i1>, ptr [[VDMRP]], align 128, !tbaa [[__DMR1024_TBAA8]]
// AIX-NEXT: [[TMP1:%.*]] = load <256 x i1>, ptr [[VPP]], align 32, !tbaa [[__VECTOR_PAIR_TBAA6]]
// AIX-NEXT: [[TMP2:%.*]] = tail call <1024 x i1> @llvm.ppc.mma.dmxvbf16gerx2pn(<1024 x i1> [[TMP0]], <256 x i1> [[TMP1]], <16 x i8> [[VC]])
// AIX-NEXT: store <1024 x i1> [[TMP2]], ptr [[RESP]], align 128, !tbaa [[__DMR1024_TBAA8]]
// AIX-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: define dso_local void @test_dmxvbf16gerx2pp(
// CHECK-SAME: ptr noundef readonly captures(none) [[VDMRP:%.*]], ptr noundef readonly captures(none) [[VPP:%.*]], <16 x i8> noundef [[VC:%.*]], ptr noundef writeonly captures(none) initializes((0, 128)) [[RESP:%.*]]) local_unnamed_addr #[[ATTR0]] {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: [[TMP0:%.*]] = load <1024 x i1>, ptr [[VDMRP]], align 128, !tbaa [[__DMR1024_TBAA8]]
// CHECK-NEXT: [[TMP1:%.*]] = load <256 x i1>, ptr [[VPP]], align 32, !tbaa [[__VECTOR_PAIR_TBAA6]]
// 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 [[__DMR1024_TBAA8]]
// CHECK-NEXT: ret void
//
// AIX-LABEL: define void @test_dmxvbf16gerx2pp(
// AIX-SAME: ptr noundef readonly captures(none) [[VDMRP:%.*]], ptr noundef readonly captures(none) [[VPP:%.*]], <16 x i8> noundef [[VC:%.*]], ptr noundef writeonly captures(none) initializes((0, 128)) [[RESP:%.*]]) local_unnamed_addr #[[ATTR0]] {
// AIX-NEXT: [[ENTRY:.*:]]
// AIX-NEXT: [[TMP0:%.*]] = load <1024 x i1>, ptr [[VDMRP]], align 128, !tbaa [[__DMR1024_TBAA8]]
// AIX-NEXT: [[TMP1:%.*]] = load <256 x i1>, ptr [[VPP]], align 32, !tbaa [[__VECTOR_PAIR_TBAA6]]
// AIX-NEXT: [[TMP2:%.*]] = tail call <1024 x i1> @llvm.ppc.mma.dmxvbf16gerx2pp(<1024 x i1> [[TMP0]], <256 x i1> [[TMP1]], <16 x i8> [[VC]])
// AIX-NEXT: store <1024 x i1> [[TMP2]], ptr [[RESP]], align 128, !tbaa [[__DMR1024_TBAA8]]
// AIX-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: define dso_local void @test_pmdmxvbf16gerx2(
// CHECK-SAME: ptr noundef readnone captures(none) [[VDMRP:%.*]], ptr noundef readonly captures(none) [[VPP:%.*]], <16 x i8> noundef [[VC:%.*]], ptr noundef writeonly captures(none) initializes((0, 128)) [[RESP:%.*]]) local_unnamed_addr #[[ATTR0]] {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: [[TMP0:%.*]] = load <256 x i1>, ptr [[VPP]], align 32, !tbaa [[__VECTOR_PAIR_TBAA6]]
// 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 [[__DMR1024_TBAA8]]
// CHECK-NEXT: ret void
//
// AIX-LABEL: define void @test_pmdmxvbf16gerx2(
// AIX-SAME: ptr noundef readnone captures(none) [[VDMRP:%.*]], ptr noundef readonly captures(none) [[VPP:%.*]], <16 x i8> noundef [[VC:%.*]], ptr noundef writeonly captures(none) initializes((0, 128)) [[RESP:%.*]]) local_unnamed_addr #[[ATTR0]] {
// AIX-NEXT: [[ENTRY:.*:]]
// AIX-NEXT: [[TMP0:%.*]] = load <256 x i1>, ptr [[VPP]], align 32, !tbaa [[__VECTOR_PAIR_TBAA6]]
// AIX-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)
// AIX-NEXT: store <1024 x i1> [[TMP1]], ptr [[RESP]], align 128, !tbaa [[__DMR1024_TBAA8]]
// AIX-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: define dso_local void @test_pmdmxvbf16gerx2nn(
// CHECK-SAME: ptr noundef readonly captures(none) [[VDMRP:%.*]], ptr noundef readonly captures(none) [[VPP:%.*]], <16 x i8> noundef [[VC:%.*]], ptr noundef writeonly captures(none) initializes((0, 128)) [[RESP:%.*]]) local_unnamed_addr #[[ATTR0]] {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: [[TMP0:%.*]] = load <1024 x i1>, ptr [[VDMRP]], align 128, !tbaa [[__DMR1024_TBAA8]]
// CHECK-NEXT: [[TMP1:%.*]] = load <256 x i1>, ptr [[VPP]], align 32, !tbaa [[__VECTOR_PAIR_TBAA6]]
// 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 [[__DMR1024_TBAA8]]
// CHECK-NEXT: ret void
//
// AIX-LABEL: define void @test_pmdmxvbf16gerx2nn(
// AIX-SAME: ptr noundef readonly captures(none) [[VDMRP:%.*]], ptr noundef readonly captures(none) [[VPP:%.*]], <16 x i8> noundef [[VC:%.*]], ptr noundef writeonly captures(none) initializes((0, 128)) [[RESP:%.*]]) local_unnamed_addr #[[ATTR0]] {
// AIX-NEXT: [[ENTRY:.*:]]
// AIX-NEXT: [[TMP0:%.*]] = load <1024 x i1>, ptr [[VDMRP]], align 128, !tbaa [[__DMR1024_TBAA8]]
// AIX-NEXT: [[TMP1:%.*]] = load <256 x i1>, ptr [[VPP]], align 32, !tbaa [[__VECTOR_PAIR_TBAA6]]
// AIX-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)
// AIX-NEXT: store <1024 x i1> [[TMP2]], ptr [[RESP]], align 128, !tbaa [[__DMR1024_TBAA8]]
// AIX-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: define dso_local void @test_pmdmxvbf16gerx2np(
// CHECK-SAME: ptr noundef readonly captures(none) [[VDMRP:%.*]], ptr noundef readonly captures(none) [[VPP:%.*]], <16 x i8> noundef [[VC:%.*]], ptr noundef writeonly captures(none) initializes((0, 128)) [[RESP:%.*]]) local_unnamed_addr #[[ATTR0]] {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: [[TMP0:%.*]] = load <1024 x i1>, ptr [[VDMRP]], align 128, !tbaa [[__DMR1024_TBAA8]]
// CHECK-NEXT: [[TMP1:%.*]] = load <256 x i1>, ptr [[VPP]], align 32, !tbaa [[__VECTOR_PAIR_TBAA6]]
// 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 [[__DMR1024_TBAA8]]
// CHECK-NEXT: ret void
//
// AIX-LABEL: define void @test_pmdmxvbf16gerx2np(
// AIX-SAME: ptr noundef readonly captures(none) [[VDMRP:%.*]], ptr noundef readonly captures(none) [[VPP:%.*]], <16 x i8> noundef [[VC:%.*]], ptr noundef writeonly captures(none) initializes((0, 128)) [[RESP:%.*]]) local_unnamed_addr #[[ATTR0]] {
// AIX-NEXT: [[ENTRY:.*:]]
// AIX-NEXT: [[TMP0:%.*]] = load <1024 x i1>, ptr [[VDMRP]], align 128, !tbaa [[__DMR1024_TBAA8]]
// AIX-NEXT: [[TMP1:%.*]] = load <256 x i1>, ptr [[VPP]], align 32, !tbaa [[__VECTOR_PAIR_TBAA6]]
// AIX-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)
// AIX-NEXT: store <1024 x i1> [[TMP2]], ptr [[RESP]], align 128, !tbaa [[__DMR1024_TBAA8]]
// AIX-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: define dso_local void @test_pmdmxvbf16gerx2pn(
// CHECK-SAME: ptr noundef readonly captures(none) [[VDMRP:%.*]], ptr noundef readonly captures(none) [[VPP:%.*]], <16 x i8> noundef [[VC:%.*]], ptr noundef writeonly captures(none) initializes((0, 128)) [[RESP:%.*]]) local_unnamed_addr #[[ATTR0]] {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: [[TMP0:%.*]] = load <1024 x i1>, ptr [[VDMRP]], align 128, !tbaa [[__DMR1024_TBAA8]]
// CHECK-NEXT: [[TMP1:%.*]] = load <256 x i1>, ptr [[VPP]], align 32, !tbaa [[__VECTOR_PAIR_TBAA6]]
// 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 [[__DMR1024_TBAA8]]
// CHECK-NEXT: ret void
//
// AIX-LABEL: define void @test_pmdmxvbf16gerx2pn(
// AIX-SAME: ptr noundef readonly captures(none) [[VDMRP:%.*]], ptr noundef readonly captures(none) [[VPP:%.*]], <16 x i8> noundef [[VC:%.*]], ptr noundef writeonly captures(none) initializes((0, 128)) [[RESP:%.*]]) local_unnamed_addr #[[ATTR0]] {
// AIX-NEXT: [[ENTRY:.*:]]
// AIX-NEXT: [[TMP0:%.*]] = load <1024 x i1>, ptr [[VDMRP]], align 128, !tbaa [[__DMR1024_TBAA8]]
// AIX-NEXT: [[TMP1:%.*]] = load <256 x i1>, ptr [[VPP]], align 32, !tbaa [[__VECTOR_PAIR_TBAA6]]
// AIX-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)
// AIX-NEXT: store <1024 x i1> [[TMP2]], ptr [[RESP]], align 128, !tbaa [[__DMR1024_TBAA8]]
// AIX-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: define dso_local void @test_pmdmxvbf16gerx2pp(
// CHECK-SAME: ptr noundef readonly captures(none) [[VDMRP:%.*]], ptr noundef readonly captures(none) [[VPP:%.*]], <16 x i8> noundef [[VC:%.*]], ptr noundef writeonly captures(none) initializes((0, 128)) [[RESP:%.*]]) local_unnamed_addr #[[ATTR0]] {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: [[TMP0:%.*]] = load <1024 x i1>, ptr [[VDMRP]], align 128, !tbaa [[__DMR1024_TBAA8]]
// CHECK-NEXT: [[TMP1:%.*]] = load <256 x i1>, ptr [[VPP]], align 32, !tbaa [[__VECTOR_PAIR_TBAA6]]
// 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 [[__DMR1024_TBAA8]]
// CHECK-NEXT: ret void
//
// AIX-LABEL: define void @test_pmdmxvbf16gerx2pp(
// AIX-SAME: ptr noundef readonly captures(none) [[VDMRP:%.*]], ptr noundef readonly captures(none) [[VPP:%.*]], <16 x i8> noundef [[VC:%.*]], ptr noundef writeonly captures(none) initializes((0, 128)) [[RESP:%.*]]) local_unnamed_addr #[[ATTR0]] {
// AIX-NEXT: [[ENTRY:.*:]]
// AIX-NEXT: [[TMP0:%.*]] = load <1024 x i1>, ptr [[VDMRP]], align 128, !tbaa [[__DMR1024_TBAA8]]
// AIX-NEXT: [[TMP1:%.*]] = load <256 x i1>, ptr [[VPP]], align 32, !tbaa [[__VECTOR_PAIR_TBAA6]]
// AIX-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)
// AIX-NEXT: store <1024 x i1> [[TMP2]], ptr [[RESP]], align 128, !tbaa [[__DMR1024_TBAA8]]
// AIX-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: define dso_local void @test_dmxvf16gerx2(
// CHECK-SAME: ptr noundef readnone captures(none) [[VDMRP:%.*]], ptr noundef readonly captures(none) [[VPP:%.*]], <16 x i8> noundef [[VC:%.*]], ptr noundef writeonly captures(none) initializes((0, 128)) [[RESP:%.*]]) local_unnamed_addr #[[ATTR0]] {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: [[TMP0:%.*]] = load <256 x i1>, ptr [[VPP]], align 32, !tbaa [[__VECTOR_PAIR_TBAA6]]
// 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 [[__DMR1024_TBAA8]]
// CHECK-NEXT: ret void
//
// AIX-LABEL: define void @test_dmxvf16gerx2(
// AIX-SAME: ptr noundef readnone captures(none) [[VDMRP:%.*]], ptr noundef readonly captures(none) [[VPP:%.*]], <16 x i8> noundef [[VC:%.*]], ptr noundef writeonly captures(none) initializes((0, 128)) [[RESP:%.*]]) local_unnamed_addr #[[ATTR0]] {
// AIX-NEXT: [[ENTRY:.*:]]
// AIX-NEXT: [[TMP0:%.*]] = load <256 x i1>, ptr [[VPP]], align 32, !tbaa [[__VECTOR_PAIR_TBAA6]]
// AIX-NEXT: [[TMP1:%.*]] = tail call <1024 x i1> @llvm.ppc.mma.dmxvf16gerx2(<256 x i1> [[TMP0]], <16 x i8> [[VC]])
// AIX-NEXT: store <1024 x i1> [[TMP1]], ptr [[RESP]], align 128, !tbaa [[__DMR1024_TBAA8]]
// AIX-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: define dso_local void @test_dmxvf16gerx2nn(
// CHECK-SAME: ptr noundef readonly captures(none) [[VDMRP:%.*]], ptr noundef readonly captures(none) [[VPP:%.*]], <16 x i8> noundef [[VC:%.*]], ptr noundef writeonly captures(none) initializes((0, 128)) [[RESP:%.*]]) local_unnamed_addr #[[ATTR0]] {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: [[TMP0:%.*]] = load <1024 x i1>, ptr [[VDMRP]], align 128, !tbaa [[__DMR1024_TBAA8]]
// CHECK-NEXT: [[TMP1:%.*]] = load <256 x i1>, ptr [[VPP]], align 32, !tbaa [[__VECTOR_PAIR_TBAA6]]
// 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 [[__DMR1024_TBAA8]]
// CHECK-NEXT: ret void
//
// AIX-LABEL: define void @test_dmxvf16gerx2nn(
// AIX-SAME: ptr noundef readonly captures(none) [[VDMRP:%.*]], ptr noundef readonly captures(none) [[VPP:%.*]], <16 x i8> noundef [[VC:%.*]], ptr noundef writeonly captures(none) initializes((0, 128)) [[RESP:%.*]]) local_unnamed_addr #[[ATTR0]] {
// AIX-NEXT: [[ENTRY:.*:]]
// AIX-NEXT: [[TMP0:%.*]] = load <1024 x i1>, ptr [[VDMRP]], align 128, !tbaa [[__DMR1024_TBAA8]]
// AIX-NEXT: [[TMP1:%.*]] = load <256 x i1>, ptr [[VPP]], align 32, !tbaa [[__VECTOR_PAIR_TBAA6]]
// AIX-NEXT: [[TMP2:%.*]] = tail call <1024 x i1> @llvm.ppc.mma.dmxvf16gerx2nn(<1024 x i1> [[TMP0]], <256 x i1> [[TMP1]], <16 x i8> [[VC]])
// AIX-NEXT: store <1024 x i1> [[TMP2]], ptr [[RESP]], align 128, !tbaa [[__DMR1024_TBAA8]]
// AIX-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: define dso_local void @test_dmxvf16gerx2np(
// CHECK-SAME: ptr noundef readonly captures(none) [[VDMRP:%.*]], ptr noundef readonly captures(none) [[VPP:%.*]], <16 x i8> noundef [[VC:%.*]], ptr noundef writeonly captures(none) initializes((0, 128)) [[RESP:%.*]]) local_unnamed_addr #[[ATTR0]] {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: [[TMP0:%.*]] = load <1024 x i1>, ptr [[VDMRP]], align 128, !tbaa [[__DMR1024_TBAA8]]
// CHECK-NEXT: [[TMP1:%.*]] = load <256 x i1>, ptr [[VPP]], align 32, !tbaa [[__VECTOR_PAIR_TBAA6]]
// 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 [[__DMR1024_TBAA8]]
// CHECK-NEXT: ret void
//
// AIX-LABEL: define void @test_dmxvf16gerx2np(
// AIX-SAME: ptr noundef readonly captures(none) [[VDMRP:%.*]], ptr noundef readonly captures(none) [[VPP:%.*]], <16 x i8> noundef [[VC:%.*]], ptr noundef writeonly captures(none) initializes((0, 128)) [[RESP:%.*]]) local_unnamed_addr #[[ATTR0]] {
// AIX-NEXT: [[ENTRY:.*:]]
// AIX-NEXT: [[TMP0:%.*]] = load <1024 x i1>, ptr [[VDMRP]], align 128, !tbaa [[__DMR1024_TBAA8]]
// AIX-NEXT: [[TMP1:%.*]] = load <256 x i1>, ptr [[VPP]], align 32, !tbaa [[__VECTOR_PAIR_TBAA6]]
// AIX-NEXT: [[TMP2:%.*]] = tail call <1024 x i1> @llvm.ppc.mma.dmxvf16gerx2np(<1024 x i1> [[TMP0]], <256 x i1> [[TMP1]], <16 x i8> [[VC]])
// AIX-NEXT: store <1024 x i1> [[TMP2]], ptr [[RESP]], align 128, !tbaa [[__DMR1024_TBAA8]]
// AIX-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: define dso_local void @test_dmxvf16gerx2pn(
// CHECK-SAME: ptr noundef readonly captures(none) [[VDMRP:%.*]], ptr noundef readonly captures(none) [[VPP:%.*]], <16 x i8> noundef [[VC:%.*]], ptr noundef writeonly captures(none) initializes((0, 128)) [[RESP:%.*]]) local_unnamed_addr #[[ATTR0]] {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: [[TMP0:%.*]] = load <1024 x i1>, ptr [[VDMRP]], align 128, !tbaa [[__DMR1024_TBAA8]]
// CHECK-NEXT: [[TMP1:%.*]] = load <256 x i1>, ptr [[VPP]], align 32, !tbaa [[__VECTOR_PAIR_TBAA6]]
// 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 [[__DMR1024_TBAA8]]
// CHECK-NEXT: ret void
//
// AIX-LABEL: define void @test_dmxvf16gerx2pn(
// AIX-SAME: ptr noundef readonly captures(none) [[VDMRP:%.*]], ptr noundef readonly captures(none) [[VPP:%.*]], <16 x i8> noundef [[VC:%.*]], ptr noundef writeonly captures(none) initializes((0, 128)) [[RESP:%.*]]) local_unnamed_addr #[[ATTR0]] {
// AIX-NEXT: [[ENTRY:.*:]]
// AIX-NEXT: [[TMP0:%.*]] = load <1024 x i1>, ptr [[VDMRP]], align 128, !tbaa [[__DMR1024_TBAA8]]
// AIX-NEXT: [[TMP1:%.*]] = load <256 x i1>, ptr [[VPP]], align 32, !tbaa [[__VECTOR_PAIR_TBAA6]]
// AIX-NEXT: [[TMP2:%.*]] = tail call <1024 x i1> @llvm.ppc.mma.dmxvf16gerx2pn(<1024 x i1> [[TMP0]], <256 x i1> [[TMP1]], <16 x i8> [[VC]])
// AIX-NEXT: store <1024 x i1> [[TMP2]], ptr [[RESP]], align 128, !tbaa [[__DMR1024_TBAA8]]
// AIX-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: define dso_local void @test_dmxvf16gerx2pp(
// CHECK-SAME: ptr noundef readonly captures(none) [[VDMRP:%.*]], ptr noundef readonly captures(none) [[VPP:%.*]], <16 x i8> noundef [[VC:%.*]], ptr noundef writeonly captures(none) initializes((0, 128)) [[RESP:%.*]]) local_unnamed_addr #[[ATTR0]] {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: [[TMP0:%.*]] = load <1024 x i1>, ptr [[VDMRP]], align 128, !tbaa [[__DMR1024_TBAA8]]
// CHECK-NEXT: [[TMP1:%.*]] = load <256 x i1>, ptr [[VPP]], align 32, !tbaa [[__VECTOR_PAIR_TBAA6]]
// 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 [[__DMR1024_TBAA8]]
// CHECK-NEXT: ret void
//
// AIX-LABEL: define void @test_dmxvf16gerx2pp(
// AIX-SAME: ptr noundef readonly captures(none) [[VDMRP:%.*]], ptr noundef readonly captures(none) [[VPP:%.*]], <16 x i8> noundef [[VC:%.*]], ptr noundef writeonly captures(none) initializes((0, 128)) [[RESP:%.*]]) local_unnamed_addr #[[ATTR0]] {
// AIX-NEXT: [[ENTRY:.*:]]
// AIX-NEXT: [[TMP0:%.*]] = load <1024 x i1>, ptr [[VDMRP]], align 128, !tbaa [[__DMR1024_TBAA8]]
// AIX-NEXT: [[TMP1:%.*]] = load <256 x i1>, ptr [[VPP]], align 32, !tbaa [[__VECTOR_PAIR_TBAA6]]
// AIX-NEXT: [[TMP2:%.*]] = tail call <1024 x i1> @llvm.ppc.mma.dmxvf16gerx2pp(<1024 x i1> [[TMP0]], <256 x i1> [[TMP1]], <16 x i8> [[VC]])
// AIX-NEXT: store <1024 x i1> [[TMP2]], ptr [[RESP]], align 128, !tbaa [[__DMR1024_TBAA8]]
// AIX-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: define dso_local void @test_pmdmxvf16gerx2(
// CHECK-SAME: ptr noundef readnone captures(none) [[VDMRP:%.*]], ptr noundef readonly captures(none) [[VPP:%.*]], <16 x i8> noundef [[VC:%.*]], ptr noundef writeonly captures(none) initializes((0, 128)) [[RESP:%.*]]) local_unnamed_addr #[[ATTR0]] {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: [[TMP0:%.*]] = load <256 x i1>, ptr [[VPP]], align 32, !tbaa [[__VECTOR_PAIR_TBAA6]]
// 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 [[__DMR1024_TBAA8]]
// CHECK-NEXT: ret void
//
// AIX-LABEL: define void @test_pmdmxvf16gerx2(
// AIX-SAME: ptr noundef readnone captures(none) [[VDMRP:%.*]], ptr noundef readonly captures(none) [[VPP:%.*]], <16 x i8> noundef [[VC:%.*]], ptr noundef writeonly captures(none) initializes((0, 128)) [[RESP:%.*]]) local_unnamed_addr #[[ATTR0]] {
// AIX-NEXT: [[ENTRY:.*:]]
// AIX-NEXT: [[TMP0:%.*]] = load <256 x i1>, ptr [[VPP]], align 32, !tbaa [[__VECTOR_PAIR_TBAA6]]
// AIX-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)
// AIX-NEXT: store <1024 x i1> [[TMP1]], ptr [[RESP]], align 128, !tbaa [[__DMR1024_TBAA8]]
// AIX-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: define dso_local void @test_pmdmxvf16gerx2nn(
// CHECK-SAME: ptr noundef readonly captures(none) [[VDMRP:%.*]], ptr noundef readonly captures(none) [[VPP:%.*]], <16 x i8> noundef [[VC:%.*]], ptr noundef writeonly captures(none) initializes((0, 128)) [[RESP:%.*]]) local_unnamed_addr #[[ATTR0]] {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: [[TMP0:%.*]] = load <1024 x i1>, ptr [[VDMRP]], align 128, !tbaa [[__DMR1024_TBAA8]]
// CHECK-NEXT: [[TMP1:%.*]] = load <256 x i1>, ptr [[VPP]], align 32, !tbaa [[__VECTOR_PAIR_TBAA6]]
// 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 [[__DMR1024_TBAA8]]
// CHECK-NEXT: ret void
//
// AIX-LABEL: define void @test_pmdmxvf16gerx2nn(
// AIX-SAME: ptr noundef readonly captures(none) [[VDMRP:%.*]], ptr noundef readonly captures(none) [[VPP:%.*]], <16 x i8> noundef [[VC:%.*]], ptr noundef writeonly captures(none) initializes((0, 128)) [[RESP:%.*]]) local_unnamed_addr #[[ATTR0]] {
// AIX-NEXT: [[ENTRY:.*:]]
// AIX-NEXT: [[TMP0:%.*]] = load <1024 x i1>, ptr [[VDMRP]], align 128, !tbaa [[__DMR1024_TBAA8]]
// AIX-NEXT: [[TMP1:%.*]] = load <256 x i1>, ptr [[VPP]], align 32, !tbaa [[__VECTOR_PAIR_TBAA6]]
// AIX-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)
// AIX-NEXT: store <1024 x i1> [[TMP2]], ptr [[RESP]], align 128, !tbaa [[__DMR1024_TBAA8]]
// AIX-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: define dso_local void @test_pmdmxvf16gerx2np(
// CHECK-SAME: ptr noundef readonly captures(none) [[VDMRP:%.*]], ptr noundef readonly captures(none) [[VPP:%.*]], <16 x i8> noundef [[VC:%.*]], ptr noundef writeonly captures(none) initializes((0, 128)) [[RESP:%.*]]) local_unnamed_addr #[[ATTR0]] {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: [[TMP0:%.*]] = load <1024 x i1>, ptr [[VDMRP]], align 128, !tbaa [[__DMR1024_TBAA8]]
// CHECK-NEXT: [[TMP1:%.*]] = load <256 x i1>, ptr [[VPP]], align 32, !tbaa [[__VECTOR_PAIR_TBAA6]]
// 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 [[__DMR1024_TBAA8]]
// CHECK-NEXT: ret void
//
// AIX-LABEL: define void @test_pmdmxvf16gerx2np(
// AIX-SAME: ptr noundef readonly captures(none) [[VDMRP:%.*]], ptr noundef readonly captures(none) [[VPP:%.*]], <16 x i8> noundef [[VC:%.*]], ptr noundef writeonly captures(none) initializes((0, 128)) [[RESP:%.*]]) local_unnamed_addr #[[ATTR0]] {
// AIX-NEXT: [[ENTRY:.*:]]
// AIX-NEXT: [[TMP0:%.*]] = load <1024 x i1>, ptr [[VDMRP]], align 128, !tbaa [[__DMR1024_TBAA8]]
// AIX-NEXT: [[TMP1:%.*]] = load <256 x i1>, ptr [[VPP]], align 32, !tbaa [[__VECTOR_PAIR_TBAA6]]
// AIX-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)
// AIX-NEXT: store <1024 x i1> [[TMP2]], ptr [[RESP]], align 128, !tbaa [[__DMR1024_TBAA8]]
// AIX-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: define dso_local void @test_pmdmxvf16gerx2pn(
// CHECK-SAME: ptr noundef readonly captures(none) [[VDMRP:%.*]], ptr noundef readonly captures(none) [[VPP:%.*]], <16 x i8> noundef [[VC:%.*]], ptr noundef writeonly captures(none) initializes((0, 128)) [[RESP:%.*]]) local_unnamed_addr #[[ATTR0]] {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: [[TMP0:%.*]] = load <1024 x i1>, ptr [[VDMRP]], align 128, !tbaa [[__DMR1024_TBAA8]]
// CHECK-NEXT: [[TMP1:%.*]] = load <256 x i1>, ptr [[VPP]], align 32, !tbaa [[__VECTOR_PAIR_TBAA6]]
// 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 [[__DMR1024_TBAA8]]
// CHECK-NEXT: ret void
//
// AIX-LABEL: define void @test_pmdmxvf16gerx2pn(
// AIX-SAME: ptr noundef readonly captures(none) [[VDMRP:%.*]], ptr noundef readonly captures(none) [[VPP:%.*]], <16 x i8> noundef [[VC:%.*]], ptr noundef writeonly captures(none) initializes((0, 128)) [[RESP:%.*]]) local_unnamed_addr #[[ATTR0]] {
// AIX-NEXT: [[ENTRY:.*:]]
// AIX-NEXT: [[TMP0:%.*]] = load <1024 x i1>, ptr [[VDMRP]], align 128, !tbaa [[__DMR1024_TBAA8]]
// AIX-NEXT: [[TMP1:%.*]] = load <256 x i1>, ptr [[VPP]], align 32, !tbaa [[__VECTOR_PAIR_TBAA6]]
// AIX-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)
// AIX-NEXT: store <1024 x i1> [[TMP2]], ptr [[RESP]], align 128, !tbaa [[__DMR1024_TBAA8]]
// AIX-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: define dso_local void @test_pmdmxvf16gerx2pp(
// CHECK-SAME: ptr noundef readonly captures(none) [[VDMRP:%.*]], ptr noundef readonly captures(none) [[VPP:%.*]], <16 x i8> noundef [[VC:%.*]], ptr noundef writeonly captures(none) initializes((0, 128)) [[RESP:%.*]]) local_unnamed_addr #[[ATTR0]] {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: [[TMP0:%.*]] = load <1024 x i1>, ptr [[VDMRP]], align 128, !tbaa [[__DMR1024_TBAA8]]
// CHECK-NEXT: [[TMP1:%.*]] = load <256 x i1>, ptr [[VPP]], align 32, !tbaa [[__VECTOR_PAIR_TBAA6]]
// 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 [[__DMR1024_TBAA8]]
// CHECK-NEXT: ret void
//
// AIX-LABEL: define void @test_pmdmxvf16gerx2pp(
// AIX-SAME: ptr noundef readonly captures(none) [[VDMRP:%.*]], ptr noundef readonly captures(none) [[VPP:%.*]], <16 x i8> noundef [[VC:%.*]], ptr noundef writeonly captures(none) initializes((0, 128)) [[RESP:%.*]]) local_unnamed_addr #[[ATTR0]] {
// AIX-NEXT: [[ENTRY:.*:]]
// AIX-NEXT: [[TMP0:%.*]] = load <1024 x i1>, ptr [[VDMRP]], align 128, !tbaa [[__DMR1024_TBAA8]]
// AIX-NEXT: [[TMP1:%.*]] = load <256 x i1>, ptr [[VPP]], align 32, !tbaa [[__VECTOR_PAIR_TBAA6]]
// AIX-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)
// AIX-NEXT: store <1024 x i1> [[TMP2]], ptr [[RESP]], align 128, !tbaa [[__DMR1024_TBAA8]]
// AIX-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: [[META4:![0-9]+]] = !{!"omnipotent char", [[META5:![0-9]+]], i64 0}
// CHECK: [[META5]] = !{!"Simple C/C++ TBAA"}
// CHECK: [[__VECTOR_PAIR_TBAA6]] = !{[[META7:![0-9]+]], [[META7]], i64 0}
// CHECK: [[META7]] = !{!"__vector_pair", [[META4]], i64 0}
// CHECK: [[__DMR1024_TBAA8]] = !{[[META9:![0-9]+]], [[META9]], i64 0}
// CHECK: [[META9]] = !{!"__dmr1024", [[META4]], i64 0}
//.
// AIX: [[META4:![0-9]+]] = !{!"omnipotent char", [[META5:![0-9]+]], i64 0}
// AIX: [[META5]] = !{!"Simple C/C++ TBAA"}
// AIX: [[__VECTOR_PAIR_TBAA6]] = !{[[META7:![0-9]+]], [[META7]], i64 0}
// AIX: [[META7]] = !{!"__vector_pair", [[META4]], i64 0}
// AIX: [[__DMR1024_TBAA8]] = !{[[META9:![0-9]+]], [[META9]], i64 0}
// AIX: [[META9]] = !{!"__dmr1024", [[META4]], i64 0}
//.
Reference in new issue View Git Blame Copy Permalink