llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT--> @llvm/pr-subscribers-clang Author: Momchil Velikov (momchil-velikov) <details> <summary>Changes</summary> This patch add intrinsics of the form sv<type>_t svld1q_gather_u64offset_<typ>(svbool_t pg, const <type>_t *base, svuint64_t offs); void svst1q_scatter_u64offset_<typ>(sbvool_t, <type>_t *base, svuint64_t offst, sv<type>_t data); as well as their short forms. ACLE spec: ARM-software/acle#<!-- -->257 --- Patch is 703.80 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/71290.diff 20 Files Affected: - (modified) clang/include/clang/Basic/arm_sve.td (+64) - (modified) clang/lib/CodeGen/CGBuiltin.cpp (+66-19) - (added) clang/test/CodeGen/aarch64-sve2p1-intrinsics/acle_sve2p1_ld1_single.c (+255) - (added) clang/test/CodeGen/aarch64-sve2p1-intrinsics/acle_sve2p1_loads.c (+3035) - (added) clang/test/CodeGen/aarch64-sve2p1-intrinsics/acle_sve2p1_st1_single.c (+255) - (added) clang/test/CodeGen/aarch64-sve2p1-intrinsics/acle_sve2p1_store.c (+2664) - (modified) llvm/include/llvm/IR/IntrinsicsAArch64.td (+85) - (modified) llvm/lib/Target/AArch64/AArch64ISelDAGToDAG.cpp (+43-1) - (modified) llvm/lib/Target/AArch64/AArch64ISelLowering.cpp (+38-9) - (modified) llvm/lib/Target/AArch64/AArch64ISelLowering.h (+4) - (modified) llvm/lib/Target/AArch64/AArch64SVEInstrInfo.td (+50-2) - (modified) llvm/lib/Target/AArch64/SVEInstrFormats.td (+39-2) - (added) llvm/test/CodeGen/AArch64/sve2p1-intrinsics-gather-loads-128bit-index.ll (+249) - (added) llvm/test/CodeGen/AArch64/sve2p1-intrinsics-gather-loads-128bit-unscaled-offset.ll (+232) - (added) llvm/test/CodeGen/AArch64/sve2p1-intrinsics-ld1-single.ll (+144) - (added) llvm/test/CodeGen/AArch64/sve2p1-intrinsics-multivec-loads.ll (+797) - (added) llvm/test/CodeGen/AArch64/sve2p1-intrinsics-multivec-stores.ll (+910) - (added) llvm/test/CodeGen/AArch64/sve2p1-intrinsics-scatter-stores-128bit-index.ll (+248) - (added) llvm/test/CodeGen/AArch64/sve2p1-intrinsics-scatter-stores-128bit-unscaled-offset.ll (+240) - (added) llvm/test/CodeGen/AArch64/sve2p1-intrinsics-st1-single.ll (+130) ``````````diff diff --git a/clang/include/clang/Basic/arm_sve.td b/clang/include/clang/Basic/arm_sve.td index b5baafedd139602..74ca5d3aef06626 100644 --- a/clang/include/clang/Basic/arm_sve.td +++ b/clang/include/clang/Basic/arm_sve.td @@ -298,6 +298,38 @@ let TargetGuard = "sve,bf16" in { def SVBFMLALT_LANE : SInst<"svbfmlalt_lane[_{0}]", "MMddi", "b", MergeNone, "aarch64_sve_bfmlalt_lane_v2", [IsOverloadNone], [ImmCheck<3, ImmCheck0_7>]>; } +let TargetGuard = "sve2p1" in { + // Contiguous zero-extending load to quadword (single vector). + def SVLD1UWQ : MInst<"svld1uwq[_{d}]", "dPc", "iUif", [IsLoad], MemEltTyInt32, "aarch64_sve_ld1uwq">; + def SVLD1UWQ_VNUM : MInst<"svld1uwq_vnum[_{d}]", "dPcl", "iUif", [IsLoad], MemEltTyInt32, "aarch64_sve_ld1uwq">; + + def SVLD1UDQ : MInst<"svld1udq[_{d}]", "dPc", "lUld", [IsLoad], MemEltTyInt64, "aarch64_sve_ld1udq">; + def SVLD1UDQ_VNUM : MInst<"svld1udq_vnum[_{d}]", "dPcl", "lUld", [IsLoad], MemEltTyInt64, "aarch64_sve_ld1udq">; + + // Load one vector (vector base + scalar offset) + def SVLD1Q_GATHER_U64BASE_OFFSET : MInst<"svld1q_gather[_{2}base]_offset_{d}", "dPgl", "cUcsUsiUilUlfhdb", [IsGatherLoad, IsByteIndexed], MemEltTyDefault, "aarch64_sve_ld1q_gather_scalar_offset">; + def SVLD1Q_GATHER_U64BASE : MInst<"svld1q_gather[_{2}base]_{d}", "dPg", "cUcsUsiUilUlfhdb", [IsGatherLoad, IsByteIndexed], MemEltTyDefault, "aarch64_sve_ld1q_gather_scalar_offset">; + + // Load one vector (scalar base + vector offset) + def SVLD1Q_GATHER_U64OFFSET : MInst<"svld1q_gather_[{3}]offset[_{0}]", "dPcg", "cUcsUsiUilUlfhdb", [IsGatherLoad, IsByteIndexed], MemEltTyDefault, "aarch64_sve_ld1q_gather_vector_offset">; + + // Load N-element structure into N vectors (scalar base) + defm SVLD2Q : StructLoad<"svld2q[_{2}]", "2Pc", "aarch64_sve_ld2q_sret">; + defm SVLD3Q : StructLoad<"svld3q[_{2}]", "3Pc", "aarch64_sve_ld3q_sret">; + defm SVLD4Q : StructLoad<"svld4q[_{2}]", "4Pc", "aarch64_sve_ld4q_sret">; + + // Load N-element structure into N vectors (scalar base, VL displacement) + defm SVLD2Q_VNUM : StructLoad<"svld2q_vnum[_{2}]", "2Pcl", "aarch64_sve_ld2q_sret">; + defm SVLD3Q_VNUM : StructLoad<"svld3q_vnum[_{2}]", "3Pcl", "aarch64_sve_ld3q_sret">; + defm SVLD4Q_VNUM : StructLoad<"svld4q_vnum[_{2}]", "4Pcl", "aarch64_sve_ld4q_sret">; + + // Load quadwords (scalar base + vector index) + def SVLD1Q_GATHER_INDICES_U : MInst<"svld1q_gather_[{3}]index[_{0}]", "dPcg", "sUsiUilUlbhfd", [IsGatherLoad], MemEltTyDefault, "aarch64_sve_ld1q_gather_index">; + + // Load quadwords (vector base + scalar index) + def SVLD1Q_GATHER_INDEX_S : MInst<"svld1q_gather[_{2}base]_index_{0}", "dPgl", "sUsiUilUlbhfd", [IsGatherLoad], MemEltTyDefault, "aarch64_sve_ld1q_gather_scalar_offset">; +} + //////////////////////////////////////////////////////////////////////////////// // Stores @@ -420,6 +452,38 @@ let TargetGuard = "sve,bf16" in { def SVSTNT1_VNUM_BF : MInst<"svstnt1_vnum[_{d}]", "vPpld", "b", [IsStore], MemEltTyDefault, "aarch64_sve_stnt1">; } +let TargetGuard = "sve2p1" in { + // Contiguous truncating store from quadword (single vector). + def SVST1UWQ : MInst<"svst1uwq[_{d}]", "vPcd", "iUif", [IsStore], MemEltTyInt32, "aarch64_sve_st1uwq">; + def SVST1UWQ_VNUM : MInst<"svst1uwq_vnum[_{d}]", "vPcld", "iUif", [IsStore], MemEltTyInt32, "aarch64_sve_st1uwq">; + + def SVST1UDQ : MInst<"svst1udq[_{d}]", "vPcd", "lUld", [IsStore], MemEltTyInt64, "aarch64_sve_st1udq">; + def SVST1UDQ_VNUM : MInst<"svst1udq_vnum[_{d}]", "vPcld", "lUld", [IsStore], MemEltTyInt64, "aarch64_sve_st1udq">; + + // Store one vector (vector base + scalar offset) + def SVST1Q_SCATTER_U64BASE_OFFSET : MInst<"svst1q_scatter[_{2}base]_offset[_{d}]", "vPgld", "cUcsUsiUilUlfhdb", [IsScatterStore, IsByteIndexed], MemEltTyDefault, "aarch64_sve_st1q_scatter_scalar_offset">; + def SVST1Q_SCATTER_U64BASE : MInst<"svst1q_scatter[_{2}base][_{d}]", "vPgd", "cUcsUsiUilUlfhdb", [IsScatterStore, IsByteIndexed], MemEltTyDefault, "aarch64_sve_st1q_scatter_scalar_offset">; + + // Store one vector (scalar base + vector offset) + def SVST1Q_SCATTER_U64OFFSET : MInst<"svst1q_scatter_[{3}]offset[_{0}]", "vPpgd", "cUcsUsiUilUlfhdb", [IsScatterStore, IsByteIndexed], MemEltTyDefault, "aarch64_sve_st1q_scatter_vector_offset">; + + // Store N vectors into N-element structure (scalar base) + defm SVST2Q : StructStore<"svst2q[_{d}]", "vPc2", "aarch64_sve_st2q">; + defm SVST3Q : StructStore<"svst3q[_{d}]", "vPc3", "aarch64_sve_st3q">; + defm SVST4Q : StructStore<"svst4q[_{d}]", "vPc4", "aarch64_sve_st4q">; + + // Store N vectors into N-element structure (scalar base, VL displacement) + defm SVST2Q_VNUM : StructStore<"svst2q_vnum[_{d}]", "vPcl2", "aarch64_sve_st2q">; + defm SVST3Q_VNUM : StructStore<"svst3q_vnum[_{d}]", "vPcl3", "aarch64_sve_st3q">; + defm SVST4Q_VNUM : StructStore<"svst4q_vnum[_{d}]", "vPcl4", "aarch64_sve_st4q">; + + // Scatter store quadwords (scalar base + vector index) + def SVST1Q_SCATTER_INDICES_U : MInst<"svst1q_scatter_[{3}]index[_{0}]", "vPpgd", "sUsiUilUlbhfd", [IsScatterStore], MemEltTyDefault, "aarch64_sve_st1q_scatter_index">; + + // Scatter store quadwords (vector base + scalar index) + def SVST1Q_SCATTER_INDEX_S : MInst<"svst1q_scatter[_{2}base]_index[_{0}]", "vPgld", "sUsiUilUlbhfd", [IsScatterStore], MemEltTyDefault, "aarch64_sve_st1q_scatter_scalar_offset">; +} + //////////////////////////////////////////////////////////////////////////////// // Prefetches diff --git a/clang/lib/CodeGen/CGBuiltin.cpp b/clang/lib/CodeGen/CGBuiltin.cpp index 972aa1c708e5f65..e0f996325354fdc 100644 --- a/clang/lib/CodeGen/CGBuiltin.cpp +++ b/clang/lib/CodeGen/CGBuiltin.cpp @@ -9413,13 +9413,6 @@ Value *CodeGenFunction::EmitSVEGatherLoad(const SVETypeFlags &TypeFlags, auto *OverloadedTy = llvm::ScalableVectorType::get(SVEBuiltinMemEltTy(TypeFlags), ResultTy); - // At the ACLE level there's only one predicate type, svbool_t, which is - // mapped to <n x 16 x i1>. However, this might be incompatible with the - // actual type being loaded. For example, when loading doubles (i64) the - // predicated should be <n x 2 x i1> instead. At the IR level the type of - // the predicate and the data being loaded must match. Cast accordingly. - Ops[0] = EmitSVEPredicateCast(Ops[0], OverloadedTy); - Function *F = nullptr; if (Ops[1]->getType()->isVectorTy()) // This is the "vector base, scalar offset" case. In order to uniquely @@ -9433,6 +9426,16 @@ Value *CodeGenFunction::EmitSVEGatherLoad(const SVETypeFlags &TypeFlags, // intrinsic. F = CGM.getIntrinsic(IntID, OverloadedTy); + // At the ACLE level there's only one predicate type, svbool_t, which is + // mapped to <n x 16 x i1>. However, this might be incompatible with the + // actual type being loaded. For example, when loading doubles (i64) the + // predicate should be <n x 2 x i1> instead. At the IR level the type of + // the predicate and the data being loaded must match. Cast to the type + // expected by the intrinsic. The intrinsic itself should be defined in + // a way than enforces relations between parameter types. + Ops[0] = EmitSVEPredicateCast( + Ops[0], cast<llvm::ScalableVectorType>(F->getArg(0)->getType())); + // Pass 0 when the offset is missing. This can only be applied when using // the "vector base" addressing mode for which ACLE allows no offset. The // corresponding LLVM IR always requires an offset. @@ -9497,8 +9500,11 @@ Value *CodeGenFunction::EmitSVEScatterStore(const SVETypeFlags &TypeFlags, // mapped to <n x 16 x i1>. However, this might be incompatible with the // actual type being stored. For example, when storing doubles (i64) the // predicated should be <n x 2 x i1> instead. At the IR level the type of - // the predicate and the data being stored must match. Cast accordingly. - Ops[1] = EmitSVEPredicateCast(Ops[1], OverloadedTy); + // the predicate and the data being stored must match. Cast to the type + // expected by the intrinsic. The intrinsic itself should be defined in + // a way that enforces relations between parameter types. + Ops[1] = EmitSVEPredicateCast( + Ops[1], cast<llvm::ScalableVectorType>(F->getArg(1)->getType())); // For "vector base, scalar index" scale the index so that it becomes a // scalar offset. @@ -9554,14 +9560,17 @@ Value *CodeGenFunction::EmitSVEStructLoad(const SVETypeFlags &TypeFlags, case Intrinsic::aarch64_sve_ld2_sret: case Intrinsic::aarch64_sve_ld1_pn_x2: case Intrinsic::aarch64_sve_ldnt1_pn_x2: + case Intrinsic::aarch64_sve_ld2q_sret: N = 2; break; case Intrinsic::aarch64_sve_ld3_sret: + case Intrinsic::aarch64_sve_ld3q_sret: N = 3; break; case Intrinsic::aarch64_sve_ld4_sret: case Intrinsic::aarch64_sve_ld1_pn_x4: case Intrinsic::aarch64_sve_ldnt1_pn_x4: + case Intrinsic::aarch64_sve_ld4q_sret: N = 4; break; default: @@ -9599,14 +9608,17 @@ Value *CodeGenFunction::EmitSVEStructStore(const SVETypeFlags &TypeFlags, case Intrinsic::aarch64_sve_st2: case Intrinsic::aarch64_sve_st1_pn_x2: case Intrinsic::aarch64_sve_stnt1_pn_x2: + case Intrinsic::aarch64_sve_st2q: N = 2; break; case Intrinsic::aarch64_sve_st3: + case Intrinsic::aarch64_sve_st3q: N = 3; break; case Intrinsic::aarch64_sve_st4: case Intrinsic::aarch64_sve_st1_pn_x4: case Intrinsic::aarch64_sve_stnt1_pn_x4: + case Intrinsic::aarch64_sve_st4q: N = 4; break; default: @@ -9682,7 +9694,7 @@ Value *CodeGenFunction::EmitSVEPrefetchLoad(const SVETypeFlags &TypeFlags, Value *CodeGenFunction::EmitSVEMaskedLoad(const CallExpr *E, llvm::Type *ReturnTy, SmallVectorImpl<Value *> &Ops, - unsigned BuiltinID, + unsigned IntrinsicID, bool IsZExtReturn) { QualType LangPTy = E->getArg(1)->getType(); llvm::Type *MemEltTy = CGM.getTypes().ConvertType( @@ -9691,28 +9703,46 @@ Value *CodeGenFunction::EmitSVEMaskedLoad(const CallExpr *E, // The vector type that is returned may be different from the // eventual type loaded from memory. auto VectorTy = cast<llvm::ScalableVectorType>(ReturnTy); - auto MemoryTy = llvm::ScalableVectorType::get(MemEltTy, VectorTy); + llvm::ScalableVectorType *MemoryTy = nullptr; + llvm::ScalableVectorType *PredTy = nullptr; + bool IsQuadLoad = false; + switch (IntrinsicID) { + case Intrinsic::aarch64_sve_ld1uwq: + case Intrinsic::aarch64_sve_ld1udq: + MemoryTy = llvm::ScalableVectorType::get(MemEltTy, 1); + PredTy = + llvm::ScalableVectorType::get(IntegerType::get(getLLVMContext(), 1), 1); + IsQuadLoad = true; + break; + default: + MemoryTy = llvm::ScalableVectorType::get(MemEltTy, VectorTy); + PredTy = MemoryTy; + break; + } - Value *Predicate = EmitSVEPredicateCast(Ops[0], MemoryTy); + Value *Predicate = EmitSVEPredicateCast(Ops[0], PredTy); Value *BasePtr = Ops[1]; // Does the load have an offset? if (Ops.size() > 2) BasePtr = Builder.CreateGEP(MemoryTy, BasePtr, Ops[2]); - Function *F = CGM.getIntrinsic(BuiltinID, MemoryTy); + Function *F = CGM.getIntrinsic(IntrinsicID, IsQuadLoad ? VectorTy : MemoryTy); auto *Load = cast<llvm::Instruction>(Builder.CreateCall(F, {Predicate, BasePtr})); auto TBAAInfo = CGM.getTBAAAccessInfo(LangPTy->getPointeeType()); CGM.DecorateInstructionWithTBAA(Load, TBAAInfo); + if (IsQuadLoad) + return Load; + return IsZExtReturn ? Builder.CreateZExt(Load, VectorTy) - : Builder.CreateSExt(Load, VectorTy); + : Builder.CreateSExt(Load, VectorTy); } Value *CodeGenFunction::EmitSVEMaskedStore(const CallExpr *E, SmallVectorImpl<Value *> &Ops, - unsigned BuiltinID) { + unsigned IntrinsicID) { QualType LangPTy = E->getArg(1)->getType(); llvm::Type *MemEltTy = CGM.getTypes().ConvertType( LangPTy->castAs<PointerType>()->getPointeeType()); @@ -9722,17 +9752,34 @@ Value *CodeGenFunction::EmitSVEMaskedStore(const CallExpr *E, auto VectorTy = cast<llvm::ScalableVectorType>(Ops.back()->getType()); auto MemoryTy = llvm::ScalableVectorType::get(MemEltTy, VectorTy); - Value *Predicate = EmitSVEPredicateCast(Ops[0], MemoryTy); + auto PredTy = MemoryTy; + auto AddrMemoryTy = MemoryTy; + bool IsQuadStore = false; + + switch (IntrinsicID) { + case Intrinsic::aarch64_sve_st1uwq: + case Intrinsic::aarch64_sve_st1udq: + AddrMemoryTy = llvm::ScalableVectorType::get(MemEltTy, 1); + PredTy = + llvm::ScalableVectorType::get(IntegerType::get(getLLVMContext(), 1), 1); + IsQuadStore = true; + break; + default: + break; + } + Value *Predicate = EmitSVEPredicateCast(Ops[0], PredTy); Value *BasePtr = Ops[1]; // Does the store have an offset? if (Ops.size() == 4) - BasePtr = Builder.CreateGEP(MemoryTy, BasePtr, Ops[2]); + BasePtr = Builder.CreateGEP(AddrMemoryTy, BasePtr, Ops[2]); // Last value is always the data - llvm::Value *Val = Builder.CreateTrunc(Ops.back(), MemoryTy); + Value *Val = + IsQuadStore ? Ops.back() : Builder.CreateTrunc(Ops.back(), MemoryTy); - Function *F = CGM.getIntrinsic(BuiltinID, MemoryTy); + Function *F = + CGM.getIntrinsic(IntrinsicID, IsQuadStore ? VectorTy : MemoryTy); auto *Store = cast<llvm::Instruction>(Builder.CreateCall(F, {Val, Predicate, BasePtr})); auto TBAAInfo = CGM.getTBAAAccessInfo(LangPTy->getPointeeType()); diff --git a/clang/test/CodeGen/aarch64-sve2p1-intrinsics/acle_sve2p1_ld1_single.c b/clang/test/CodeGen/aarch64-sve2p1-intrinsics/acle_sve2p1_ld1_single.c new file mode 100644 index 000000000000000..16361ecc987d3c5 --- /dev/null +++ b/clang/test/CodeGen/aarch64-sve2p1-intrinsics/acle_sve2p1_ld1_single.c @@ -0,0 +1,255 @@ +// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --version 2 +// REQUIRES: aarch64-registered-target +// RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +sve2p1 \ +// RUN: -S -Werror -emit-llvm -disable-O0-optnone -o - %s | opt -S -p mem2reg,instcombine,tailcallelim | FileCheck %s +// RUN: %clang_cc1 -DSVE_OVERLOADED_FORMS -triple aarch64-none-linux-gnu -target-feature +sve2p1 \ +// RUN: -S -Werror -emit-llvm -disable-O0-optnone -o - %s | opt -S -p mem2reg,instcombine,tailcallelim | FileCheck %s +// RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +sve2p1 \ +// RUN: -S -Werror -emit-llvm -disable-O0-optnone -o - -x c++ %s | opt -S -p mem2reg,instcombine,tailcallelim | FileCheck %s -check-prefix=CPP-CHECK +// RUN: %clang_cc1 -DSVE_OVERLOADED_FORMS -triple aarch64-none-linux-gnu -target-feature +sve2p1 \ +// RUN: -S -Werror -emit-llvm -disable-O0-optnone -o - -x c++ %s | opt -S -p mem2reg,instcombine,tailcallelim | FileCheck %s -check-prefix=CPP-CHECK +// RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +sve2p1 \ +// RUN: -S -disable-O0-optnone -Werror -Wall -o /dev/null %s + + +#include <arm_sve.h> + +#ifdef SVE_OVERLOADED_FORMS +// A simple used,unused... macro, long enough to represent any SVE builtin. +#define SVE_ACLE_FUNC(A1, A2_UNUSED, A3, A4_UNUSED) A1##A3 +#else +#define SVE_ACLE_FUNC(A1, A2, A3, A4) A1##A2##A3##A4 +#endif + +// LD1W + +// CHECK-LABEL: define dso_local <vscale x 4 x i32> @test_svld1uwq_u32 +// CHECK-SAME: (<vscale x 16 x i1> [[PRED:%.*]], ptr noundef [[BASE:%.*]]) #[[ATTR0:[0-9]+]] { +// CHECK-NEXT: entry: +// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PRED]]) +// CHECK-NEXT: [[TMP1:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.ld1uwq.nxv4i32(<vscale x 1 x i1> [[TMP0]], ptr [[BASE]]) +// CHECK-NEXT: ret <vscale x 4 x i32> [[TMP1]] +// +// CPP-CHECK-LABEL: define dso_local <vscale x 4 x i32> @_Z17test_svld1uwq_u32u10__SVBool_tPKj +// CPP-CHECK-SAME: (<vscale x 16 x i1> [[PRED:%.*]], ptr noundef [[BASE:%.*]]) #[[ATTR0:[0-9]+]] { +// CPP-CHECK-NEXT: entry: +// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PRED]]) +// CPP-CHECK-NEXT: [[TMP1:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.ld1uwq.nxv4i32(<vscale x 1 x i1> [[TMP0]], ptr [[BASE]]) +// CPP-CHECK-NEXT: ret <vscale x 4 x i32> [[TMP1]] +// +svuint32_t test_svld1uwq_u32(svbool_t pred, uint32_t const * base) { + return SVE_ACLE_FUNC(svld1uwq, _u32, , )(pred, base); +} + +// CHECK-LABEL: define dso_local <vscale x 4 x i32> @test_svld1uwq_vnum_u32 +// CHECK-SAME: (<vscale x 16 x i1> [[PRED:%.*]], ptr noundef [[BASE:%.*]]) #[[ATTR0]] { +// CHECK-NEXT: entry: +// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PRED]]) +// CHECK-NEXT: [[TMP1:%.*]] = getelementptr <vscale x 1 x i32>, ptr [[BASE]], i64 -8 +// CHECK-NEXT: [[TMP2:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.ld1uwq.nxv4i32(<vscale x 1 x i1> [[TMP0]], ptr [[TMP1]]) +// CHECK-NEXT: ret <vscale x 4 x i32> [[TMP2]] +// +// CPP-CHECK-LABEL: define dso_local <vscale x 4 x i32> @_Z22test_svld1uwq_vnum_u32u10__SVBool_tPKj +// CPP-CHECK-SAME: (<vscale x 16 x i1> [[PRED:%.*]], ptr noundef [[BASE:%.*]]) #[[ATTR0]] { +// CPP-CHECK-NEXT: entry: +// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PRED]]) +// CPP-CHECK-NEXT: [[TMP1:%.*]] = getelementptr <vscale x 1 x i32>, ptr [[BASE]], i64 -8 +// CPP-CHECK-NEXT: [[TMP2:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.ld1uwq.nxv4i32(<vscale x 1 x i1> [[TMP0]], ptr [[TMP1]]) +// CPP-CHECK-NEXT: ret <vscale x 4 x i32> [[TMP2]] +// +svuint32_t test_svld1uwq_vnum_u32(svbool_t pred, uint32_t const * base) { + return SVE_ACLE_FUNC(svld1uwq_vnum, _u32, , )(pred, base, -8); +} + +// CHECK-LABEL: define dso_local <vscale x 4 x i32> @test_svld1uwq_s32 +// CHECK-SAME: (<vscale x 16 x i1> [[PRED:%.*]], ptr noundef [[BASE:%.*]]) #[[ATTR0]] { +// CHECK-NEXT: entry: +// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PRED]]) +// CHECK-NEXT: [[TMP1:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.ld1uwq.nxv4i32(<vscale x 1 x i1> [[TMP0]], ptr [[BASE]]) +// CHECK-NEXT: ret <vscale x 4 x i32> [[TMP1]] +// +// CPP-CHECK-LABEL: define dso_local <vscale x 4 x i32> @_Z17test_svld1uwq_s32u10__SVBool_tPKi +// CPP-CHECK-SAME: (<vscale x 16 x i1> [[PRED:%.*]], ptr noundef [[BASE:%.*]]) #[[ATTR0]] { +// CPP-CHECK-NEXT: entry: +// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PRED]]) +// CPP-CHECK-NEXT: [[TMP1:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.ld1uwq.nxv4i32(<vscale x 1 x i1> [[TMP0]], ptr [[BASE]]) +// CPP-CHECK-NEXT: ret <vscale x 4 x i32> [[TMP1]] +// +svint32_t test_svld1uwq_s32(svbool_t pred, int32_t const * base) { + return SVE_ACLE_FUNC(svld1uwq, _s32, , )(pred, base); +} + +// CHECK-LABEL: define dso_local <vscale x 4 x i32> @test_svld1uwq_vnum_s32 +// CHECK-SAME: (<vscale x 16 x i1> [[PRED:%.*]], ptr noundef [[BASE:%.*]]) #[[ATTR0]] { +// CHECK-NEXT: entry: +// CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PRED]]) +// CHECK-NEXT: [[TMP1:%.*]] = getelementptr <vscale x 1 x i32>, ptr [[BASE]], i64 7 +// CHECK-NEXT: [[TMP2:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.ld1uwq.nxv4i32(<vscale x 1 x i1> [[TMP0]], ptr [[TMP1]]) +// CHECK-NEXT: ret <vscale x 4 x i32> [[TMP2]] +// +// CPP-CHECK-LABEL: define dso_local <vscale x 4 x i32> @_Z22test_svld1uwq_vnum_s32u10__SVBool_tPKi +// CPP-CHECK-SAME: (<vscale x 16 x i1> [[PRED:%.*]], ptr noundef [[BASE:%.*]]) #[[ATTR0]] { +// CPP-CHECK-NEXT: entry: +// CPP-CHECK-NEXT: [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PRED]]) +// CPP-CHECK-NEXT: [[TMP1:%.*]] = getelementptr <vscale x 1 x i32>, ptr [[BASE]], i64 7 +// CPP-CHECK-NEXT:... [truncated] `````````` </details> https://github.com/llvm/llvm-project/pull/71290 _______________________________________________ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits