Skip to content

[PowerPC][CLANG] DMF VSX Vector float GER 2x (rank-2 update) #147383

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 3 commits into
base: main
Choose a base branch
from
Open

[PowerPC][CLANG] DMF VSX Vector float GER 2x (rank-2 update) #147383

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
c75ab01
RFC02658:CLANG: DMF VSX Vector bfloat16 GER 2x (rank-2 update)
lei137 Jul 4, 2025
211cfc9
add dmf vsx vector 16-bit floating point builtin
lei137 Jul 7, 2025
4cfc00b
fix err in rebase
lei137 Jul 9, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 8 additions & 0 deletions clang/include/clang/Basic/BuiltinsPPC.def
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1110,6 +1110,14 @@ UNALIASED_CUSTOM_MMA_BUILTIN(mma_xvbf16ger2, "vW512*VV",
"mma,paired-vector-memops")
UNALIASED_CUSTOM_MMA_BUILTIN(mma_pmxvbf16ger2, "vW512*VVi15i15i3",
"mma,paired-vector-memops")
UNALIASED_CUSTOM_MMA_BUILTIN(mma_dmxvbf16gerx2, "vW1024*W256V",
"mma,paired-vector-memops")
UNALIASED_CUSTOM_MMA_BUILTIN(mma_pmdmxvbf16gerx2, "vW1024*W256Vi255i15i3",
"mma,paired-vector-memops")
UNALIASED_CUSTOM_MMA_BUILTIN(mma_dmxvf16gerx2, "vW1024*W256V",
"mma,paired-vector-memops")
UNALIASED_CUSTOM_MMA_BUILTIN(mma_pmdmxvf16gerx2, "vW1024*W256Vi255i15i3",
"mma,paired-vector-memops")

// FIXME: Obviously incomplete.

Expand Down
309 changes: 309 additions & 0 deletions clang/test/CodeGen/PowerPC/builtins-dmf-vsx-vector-float.c
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -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}
Loading
Loading