Skip to content

[Clang][PowerPC] Add __dmr1024 type and DMF integer calculation builtins #142480

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

Merged
merged 4 commits into from
Jun 20, 2025
Merged

[Clang][PowerPC] Add __dmr1024 type and DMF integer calculation builtins #142480

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
5ef7a4c
[Clang][PowerPC] Add __dmr type and DMF integer calculation builtins
maryammo Jun 2, 2025
4b43199
Rename __dmr type to __dmr1024
maryammo Jun 9, 2025
4491c64
Rename tests to address review comments
maryammo Jun 16, 2025
4b7e16c
Address review comments
maryammo Jun 18, 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
12 changes: 12 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 @@ -1134,6 +1134,18 @@ UNALIASED_CUSTOM_BUILTIN(mma_pmxvbf16ger2np, "vW512*VVi15i15i3", true,
"mma,paired-vector-memops")
UNALIASED_CUSTOM_BUILTIN(mma_pmxvbf16ger2nn, "vW512*VVi15i15i3", true,
"mma,paired-vector-memops")
UNALIASED_CUSTOM_BUILTIN(mma_dmxvi8gerx4, "vW1024*W256V", false,
"mma,paired-vector-memops")
UNALIASED_CUSTOM_BUILTIN(mma_pmdmxvi8gerx4, "vW1024*W256Vi255i15i15", false,
"mma,paired-vector-memops")
UNALIASED_CUSTOM_BUILTIN(mma_dmxvi8gerx4pp, "vW1024*W256V", true,
"mma,paired-vector-memops")
UNALIASED_CUSTOM_BUILTIN(mma_pmdmxvi8gerx4pp, "vW1024*W256Vi255i15i15", true,
"mma,paired-vector-memops")
UNALIASED_CUSTOM_BUILTIN(mma_dmxvi8gerx4spp, "vW1024*W256V", true,
"mma,paired-vector-memops")
UNALIASED_CUSTOM_BUILTIN(mma_pmdmxvi8gerx4spp, "vW1024*W256Vi255i15i15", true,
"mma,paired-vector-memops")

// FIXME: Obviously incomplete.

Expand Down
1 change: 1 addition & 0 deletions clang/include/clang/Basic/PPCTypes.def
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,6 +30,7 @@
#endif


PPC_VECTOR_MMA_TYPE(__dmr1024, VectorDmr1024, 1024)
Copy link
Contributor

@lei137 lei137 Jun 12, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Since this is a vector type, maybe we can just keep the same naming convention?

Suggested change
PPC_VECTOR_MMA_TYPE(__dmr1024, VectorDmr1024, 1024)
PPC_VECTOR_MMA_TYPE(__vector_dmr, VectorDmr, 1024)

Copy link
Collaborator

@RolandF77 RolandF77 Jun 13, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The type names have to match GCC and are negotiated - __dmr1024 is the current choice.

PPC_VECTOR_MMA_TYPE(__vector_quad, VectorQuad, 512)
PPC_VECTOR_VSX_TYPE(__vector_pair, VectorPair, 256)

Expand Down
1 change: 1 addition & 0 deletions clang/lib/AST/ASTContext.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3455,6 +3455,7 @@ static void encodeTypeForFunctionPointerAuth(const ASTContext &Ctx,
case BuiltinType::BFloat16:
case BuiltinType::VectorQuad:
case BuiltinType::VectorPair:
case BuiltinType::VectorDmr1024:
Copy link
Contributor

@lei137 lei137 Jun 18, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

nit: Maybe we can do this since DMR is an acronym and to match the actual new type name defined?

Suggested change
case BuiltinType::VectorDmr1024:
case BuiltinType::DMR1024:

OS << "?";
return;

Expand Down
13 changes: 10 additions & 3 deletions clang/test/AST/ast-dump-ppc-types.c
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,9 +1,11 @@
// RUN: %clang_cc1 -triple powerpc64le-unknown-unknown -target-cpu future \
// RUN: -ast-dump %s | FileCheck %s
// RUN: %clang_cc1 -triple powerpc64le-unknown-unknown -target-cpu pwr10 \
// RUN: -ast-dump -ast-dump-filter __vector %s | FileCheck %s
// RUN: -ast-dump %s | FileCheck %s
// RUN: %clang_cc1 -triple powerpc64le-unknown-unknown -target-cpu pwr9 \
// RUN: -ast-dump -ast-dump-filter __vector %s | FileCheck %s
// RUN: -ast-dump %s | FileCheck %s
// RUN: %clang_cc1 -triple powerpc64le-unknown-unknown -target-cpu pwr8 \
// RUN: -ast-dump -ast-dump-filter __vector %s | FileCheck %s
// RUN: -ast-dump %s | FileCheck %s
// RUN: %clang_cc1 -triple x86_64-unknown-unknown -ast-dump %s | FileCheck %s \
// RUN: --check-prefix=CHECK-X86_64
// RUN: %clang_cc1 -triple arm-unknown-unknown -ast-dump %s | FileCheck %s \
Expand All @@ -15,16 +17,21 @@
// are correctly defined. We also added checks on a couple of other targets to
// ensure the types are target-dependent.

// CHECK: TypedefDecl {{.*}} implicit __dmr1024 '__dmr1024'
// CHECK: `-BuiltinType {{.*}} '__dmr1024'
// CHECK: TypedefDecl {{.*}} implicit __vector_quad '__vector_quad'
// CHECK-NEXT: -BuiltinType {{.*}} '__vector_quad'
// CHECK: TypedefDecl {{.*}} implicit __vector_pair '__vector_pair'
// CHECK-NEXT: -BuiltinType {{.*}} '__vector_pair'

// CHECK-X86_64-NOT: __dmr1024
// CHECK-X86_64-NOT: __vector_quad
// CHECK-X86_64-NOT: __vector_pair

// CHECK-ARM-NOT: __dmr1024
// CHECK-ARM-NOT: __vector_quad
// CHECK-ARM-NOT: __vector_pair

// CHECK-RISCV64-NOT: __dmr1024
// CHECK-RISCV64-NOT: __vector_quad
// CHECK-RISCV64-NOT: __vector_pair
94 changes: 94 additions & 0 deletions clang/test/CodeGen/PowerPC/builtins-ppc-dmf.c
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,94 @@
// 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
Copy link
Contributor

@lei137 lei137 Jun 18, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

do we need testing for aix 32bit?

Copy link
Contributor Author

@maryammo maryammo Jun 18, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

PC_VECTOR_MMA_TYPE is only defined for PPC64



// 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;
}
20 changes: 20 additions & 0 deletions clang/test/CodeGen/PowerPC/ppc-dmf-paired-vec-memops-builtin-err.c
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,20 @@
// RUN: not %clang_cc1 -triple powerpc64le-unknown-linux-gnu -target-cpu future \
// RUN: %s -emit-llvm-only 2>&1 | FileCheck %s

__attribute__((target("no-paired-vector-memops")))
void test_pair(unsigned char *vdmr, unsigned char *vpp, vector unsigned char vc) {
__vector_pair vp = *((__vector_pair *)vpp);
__builtin_mma_dmxvi8gerx4((__dmr1024 *)vdmr, vp, vc);
__builtin_mma_pmdmxvi8gerx4((__dmr1024 *)vdmr, vp, vc, 0, 0, 0);
__builtin_mma_dmxvi8gerx4pp((__dmr1024 *)vdmr, vp, vc);
__builtin_mma_pmdmxvi8gerx4pp((__dmr1024 *)vdmr, vp, vc, 0, 0, 0);
__builtin_mma_dmxvi8gerx4spp((__dmr1024 *)vdmr, vp, vc);
__builtin_mma_pmdmxvi8gerx4spp((__dmr1024 *)vdmr, vp, vc, 0, 0, 0);

// CHECK: error: '__builtin_mma_dmxvi8gerx4' needs target feature mma,paired-vector-memops
// CHECK: error: '__builtin_mma_pmdmxvi8gerx4' needs target feature mma,paired-vector-memops
// CHECK: error: '__builtin_mma_dmxvi8gerx4pp' needs target feature mma,paired-vector-memops
// CHECK: error: '__builtin_mma_pmdmxvi8gerx4pp' needs target feature mma,paired-vector-memops
// CHECK: error: '__builtin_mma_dmxvi8gerx4spp' needs target feature mma,paired-vector-memops
// CHECK: error: '__builtin_mma_pmdmxvi8gerx4spp' needs target feature mma,paired-vector-memops
}
184 changes: 184 additions & 0 deletions clang/test/CodeGen/PowerPC/ppc-dmf-types.c
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,184 @@
// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
// RUN: %clang_cc1 -triple powerpc64le-linux-unknown -target-cpu future \
// RUN: -emit-llvm -o - %s | FileCheck %s
// RUN: %clang_cc1 -triple powerpc64le-linux-unknown -target-cpu pwr10 \
// RUN: -emit-llvm -o - %s | FileCheck %s
// RUN: %clang_cc1 -triple powerpc64le-linux-unknown -target-cpu pwr9 \
// RUN: -emit-llvm -o - %s | FileCheck %s
// RUN: %clang_cc1 -triple powerpc64le-linux-unknown -target-cpu pwr8 \
// RUN: -emit-llvm -o - %s | FileCheck %s
Copy link
Contributor

@lei137 lei137 Jun 18, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Since DMR is future specific, do we need run lines on cpu targets that it won't be valid for?


typedef __vector_quad vq_t;

// CHECK-LABEL: @test_dmr_copy(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[PTR1_ADDR:%.*]] = alloca ptr, align 8
// CHECK-NEXT: [[PTR2_ADDR:%.*]] = alloca ptr, align 8
// CHECK-NEXT: store ptr [[PTR1:%.*]], ptr [[PTR1_ADDR]], align 8
// CHECK-NEXT: store ptr [[PTR2:%.*]], ptr [[PTR2_ADDR]], align 8
// CHECK-NEXT: [[TMP0:%.*]] = load ptr, ptr [[PTR1_ADDR]], align 8
// CHECK-NEXT: [[ADD_PTR:%.*]] = getelementptr inbounds <1024 x i1>, ptr [[TMP0]], i64 2
// CHECK-NEXT: [[TMP1:%.*]] = load <1024 x i1>, ptr [[ADD_PTR]], align 128
// CHECK-NEXT: [[TMP2:%.*]] = load ptr, ptr [[PTR2_ADDR]], align 8
// CHECK-NEXT: [[ADD_PTR1:%.*]] = getelementptr inbounds <1024 x i1>, ptr [[TMP2]], i64 1
// CHECK-NEXT: store <1024 x i1> [[TMP1]], ptr [[ADD_PTR1]], align 128
// CHECK-NEXT: ret void
//
void test_dmr_copy(__dmr1024 *ptr1, __dmr1024 *ptr2) {
*(ptr2 + 1) = *(ptr1 + 2);
}

// CHECK-LABEL: @test_dmr_typedef(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[INP_ADDR:%.*]] = alloca ptr, align 8
// CHECK-NEXT: [[OUTP_ADDR:%.*]] = alloca ptr, align 8
// CHECK-NEXT: [[VDMRIN:%.*]] = alloca ptr, align 8
// CHECK-NEXT: [[VDMROUT:%.*]] = alloca ptr, align 8
// CHECK-NEXT: store ptr [[INP:%.*]], ptr [[INP_ADDR]], align 8
// CHECK-NEXT: store ptr [[OUTP:%.*]], ptr [[OUTP_ADDR]], align 8
// CHECK-NEXT: [[TMP0:%.*]] = load ptr, ptr [[INP_ADDR]], align 8
// CHECK-NEXT: store ptr [[TMP0]], ptr [[VDMRIN]], align 8
// CHECK-NEXT: [[TMP1:%.*]] = load ptr, ptr [[OUTP_ADDR]], align 8
// CHECK-NEXT: store ptr [[TMP1]], ptr [[VDMROUT]], align 8
// CHECK-NEXT: [[TMP2:%.*]] = load ptr, ptr [[VDMRIN]], align 8
// CHECK-NEXT: [[TMP3:%.*]] = load <1024 x i1>, ptr [[TMP2]], align 128
// CHECK-NEXT: [[TMP4:%.*]] = load ptr, ptr [[VDMROUT]], align 8
// CHECK-NEXT: store <1024 x i1> [[TMP3]], ptr [[TMP4]], align 128
// CHECK-NEXT: ret void
//
void test_dmr_typedef(int *inp, int *outp) {
__dmr1024 *vdmrin = (__dmr1024 *)inp;
__dmr1024 *vdmrout = (__dmr1024 *)outp;
*vdmrout = *vdmrin;
}

// CHECK-LABEL: @test_dmr_arg(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[VDMR_ADDR:%.*]] = alloca ptr, align 8
// CHECK-NEXT: [[PTR_ADDR:%.*]] = alloca ptr, align 8
// CHECK-NEXT: [[VDMRP:%.*]] = alloca ptr, align 8
// CHECK-NEXT: store ptr [[VDMR:%.*]], ptr [[VDMR_ADDR]], align 8
// CHECK-NEXT: store ptr [[PTR:%.*]], ptr [[PTR_ADDR]], align 8
// CHECK-NEXT: [[TMP0:%.*]] = load ptr, ptr [[PTR_ADDR]], align 8
// CHECK-NEXT: store ptr [[TMP0]], ptr [[VDMRP]], align 8
// CHECK-NEXT: [[TMP1:%.*]] = load ptr, ptr [[VDMR_ADDR]], align 8
// CHECK-NEXT: [[TMP2:%.*]] = load <1024 x i1>, ptr [[TMP1]], align 128
// CHECK-NEXT: [[TMP3:%.*]] = load ptr, ptr [[VDMRP]], align 8
// CHECK-NEXT: store <1024 x i1> [[TMP2]], ptr [[TMP3]], align 128
// CHECK-NEXT: ret void
//
void test_dmr_arg(__dmr1024 *vdmr, int *ptr) {
__dmr1024 *vdmrp = (__dmr1024 *)ptr;
*vdmrp = *vdmr;
}

// CHECK-LABEL: @test_dmr_const_arg(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[VDMR_ADDR:%.*]] = alloca ptr, align 8
// CHECK-NEXT: [[PTR_ADDR:%.*]] = alloca ptr, align 8
// CHECK-NEXT: [[VDMRP:%.*]] = alloca ptr, align 8
// CHECK-NEXT: store ptr [[VDMR:%.*]], ptr [[VDMR_ADDR]], align 8
// CHECK-NEXT: store ptr [[PTR:%.*]], ptr [[PTR_ADDR]], align 8
// CHECK-NEXT: [[TMP0:%.*]] = load ptr, ptr [[PTR_ADDR]], align 8
// CHECK-NEXT: store ptr [[TMP0]], ptr [[VDMRP]], align 8
// CHECK-NEXT: [[TMP1:%.*]] = load ptr, ptr [[VDMR_ADDR]], align 8
// CHECK-NEXT: [[TMP2:%.*]] = load <1024 x i1>, ptr [[TMP1]], align 128
// CHECK-NEXT: [[TMP3:%.*]] = load ptr, ptr [[VDMRP]], align 8
// CHECK-NEXT: store <1024 x i1> [[TMP2]], ptr [[TMP3]], align 128
// CHECK-NEXT: ret void
//
void test_dmr_const_arg(const __dmr1024 *const vdmr, int *ptr) {
__dmr1024 *vdmrp = (__dmr1024 *)ptr;
*vdmrp = *vdmr;
}

// CHECK-LABEL: @test_dmr_array_arg(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[VDMRA_ADDR:%.*]] = alloca ptr, align 8
// CHECK-NEXT: [[PTR_ADDR:%.*]] = alloca ptr, align 8
// CHECK-NEXT: [[VDMRP:%.*]] = alloca ptr, align 8
// CHECK-NEXT: store ptr [[VDMRA:%.*]], ptr [[VDMRA_ADDR]], align 8
// CHECK-NEXT: store ptr [[PTR:%.*]], ptr [[PTR_ADDR]], align 8
// CHECK-NEXT: [[TMP0:%.*]] = load ptr, ptr [[PTR_ADDR]], align 8
// CHECK-NEXT: store ptr [[TMP0]], ptr [[VDMRP]], align 8
// CHECK-NEXT: [[TMP1:%.*]] = load ptr, ptr [[VDMRA_ADDR]], align 8
// CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds <1024 x i1>, ptr [[TMP1]], i64 0
// CHECK-NEXT: [[TMP2:%.*]] = load <1024 x i1>, ptr [[ARRAYIDX]], align 128
// CHECK-NEXT: [[TMP3:%.*]] = load ptr, ptr [[VDMRP]], align 8
// CHECK-NEXT: store <1024 x i1> [[TMP2]], ptr [[TMP3]], align 128
// CHECK-NEXT: ret void
//
void test_dmr_array_arg(__dmr1024 vdmra[], int *ptr) {
__dmr1024 *vdmrp = (__dmr1024 *)ptr;
*vdmrp = vdmra[0];
}

// CHECK-LABEL: @test_dmr_ret(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[PTR_ADDR:%.*]] = alloca ptr, align 8
// CHECK-NEXT: [[VDMRP:%.*]] = alloca ptr, align 8
// CHECK-NEXT: store ptr [[PTR:%.*]], ptr [[PTR_ADDR]], align 8
// CHECK-NEXT: [[TMP0:%.*]] = load ptr, ptr [[PTR_ADDR]], align 8
// CHECK-NEXT: store ptr [[TMP0]], ptr [[VDMRP]], align 8
// CHECK-NEXT: [[TMP1:%.*]] = load ptr, ptr [[VDMRP]], align 8
// CHECK-NEXT: [[ADD_PTR:%.*]] = getelementptr inbounds <1024 x i1>, ptr [[TMP1]], i64 2
// CHECK-NEXT: ret ptr [[ADD_PTR]]
//
__dmr1024 *test_dmr_ret(int *ptr) {
__dmr1024 *vdmrp = (__dmr1024 *)ptr;
return vdmrp + 2;
}

// CHECK-LABEL: @test_dmr_ret_const(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[PTR_ADDR:%.*]] = alloca ptr, align 8
// CHECK-NEXT: [[VDMRP:%.*]] = alloca ptr, align 8
// CHECK-NEXT: store ptr [[PTR:%.*]], ptr [[PTR_ADDR]], align 8
// CHECK-NEXT: [[TMP0:%.*]] = load ptr, ptr [[PTR_ADDR]], align 8
// CHECK-NEXT: store ptr [[TMP0]], ptr [[VDMRP]], align 8
// CHECK-NEXT: [[TMP1:%.*]] = load ptr, ptr [[VDMRP]], align 8
// CHECK-NEXT: [[ADD_PTR:%.*]] = getelementptr inbounds <1024 x i1>, ptr [[TMP1]], i64 2
// CHECK-NEXT: ret ptr [[ADD_PTR]]
//
const __dmr1024 *test_dmr_ret_const(int *ptr) {
__dmr1024 *vdmrp = (__dmr1024 *)ptr;
return vdmrp + 2;
}

// CHECK-LABEL: @test_dmr_sizeof_alignof(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[PTR_ADDR:%.*]] = alloca ptr, align 8
// CHECK-NEXT: [[VDMRP:%.*]] = alloca ptr, align 8
// CHECK-NEXT: [[VDMR:%.*]] = alloca <1024 x i1>, align 128
// CHECK-NEXT: [[SIZET:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[ALIGNT:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[SIZEV:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[ALIGNV:%.*]] = alloca i32, align 4
// CHECK-NEXT: store ptr [[PTR:%.*]], ptr [[PTR_ADDR]], align 8
// CHECK-NEXT: [[TMP0:%.*]] = load ptr, ptr [[PTR_ADDR]], align 8
// CHECK-NEXT: store ptr [[TMP0]], ptr [[VDMRP]], align 8
// CHECK-NEXT: [[TMP1:%.*]] = load ptr, ptr [[VDMRP]], align 8
// CHECK-NEXT: [[TMP2:%.*]] = load <1024 x i1>, ptr [[TMP1]], align 128
// CHECK-NEXT: store <1024 x i1> [[TMP2]], ptr [[VDMR]], align 128
// CHECK-NEXT: store i32 128, ptr [[SIZET]], align 4
// CHECK-NEXT: store i32 128, ptr [[ALIGNT]], align 4
// CHECK-NEXT: store i32 128, ptr [[SIZEV]], align 4
// CHECK-NEXT: store i32 128, ptr [[ALIGNV]], align 4
// CHECK-NEXT: [[TMP3:%.*]] = load i32, ptr [[SIZET]], align 4
// CHECK-NEXT: [[TMP4:%.*]] = load i32, ptr [[ALIGNT]], align 4
// CHECK-NEXT: [[ADD:%.*]] = add i32 [[TMP3]], [[TMP4]]
// CHECK-NEXT: [[TMP5:%.*]] = load i32, ptr [[SIZEV]], align 4
// CHECK-NEXT: [[ADD1:%.*]] = add i32 [[ADD]], [[TMP5]]
// CHECK-NEXT: [[TMP6:%.*]] = load i32, ptr [[ALIGNV]], align 4
// CHECK-NEXT: [[ADD2:%.*]] = add i32 [[ADD1]], [[TMP6]]
// CHECK-NEXT: ret i32 [[ADD2]]
//
int test_dmr_sizeof_alignof(int *ptr) {
__dmr1024 *vdmrp = (__dmr1024 *)ptr;
__dmr1024 vdmr = *vdmrp;
unsigned sizet = sizeof(__dmr1024);
unsigned alignt = __alignof__(__dmr1024);
unsigned sizev = sizeof(vdmr);
unsigned alignv = __alignof__(vdmr);
return sizet + alignt + sizev + alignv;
}
21 changes: 21 additions & 0 deletions clang/test/CodeGen/PowerPC/ppc-future-mma-builtin-err.c
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,21 @@
// RUN: not %clang_cc1 -triple powerpc64le-unknown-linux-gnu -target-cpu future \
// RUN: %s -emit-llvm-only 2>&1 | FileCheck %s

__attribute__((target("no-mma")))
void test_mma(unsigned char *vdmrp, unsigned char *vpp, vector unsigned char vc) {
__dmr1024 vdmr = *((__dmr1024 *)vdmrp);
__vector_pair vp = *((__vector_pair *)vpp);
__builtin_mma_dmxvi8gerx4(&vdmr, vp, vc);
__builtin_mma_pmdmxvi8gerx4(&vdmr, vp, vc, 0, 0, 0);
__builtin_mma_dmxvi8gerx4pp(&vdmr, vp, vc);
__builtin_mma_pmdmxvi8gerx4pp(&vdmr, vp, vc, 0, 0, 0);
__builtin_mma_dmxvi8gerx4spp(&vdmr, vp, vc);
__builtin_mma_pmdmxvi8gerx4spp(&vdmr, vp, vc, 0, 0, 0);

// CHECK: error: '__builtin_mma_dmxvi8gerx4' needs target feature mma,paired-vector-memops
// CHECK: error: '__builtin_mma_pmdmxvi8gerx4' needs target feature mma,paired-vector-memops
// CHECK: error: '__builtin_mma_dmxvi8gerx4pp' needs target feature mma,paired-vector-memops
// CHECK: error: '__builtin_mma_pmdmxvi8gerx4pp' needs target feature mma,paired-vector-memops
// CHECK: error: '__builtin_mma_dmxvi8gerx4spp' needs target feature mma,paired-vector-memops
// CHECK: error: '__builtin_mma_pmdmxvi8gerx4spp' needs target feature mma,paired-vector-memops
}
Loading
Loading