llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT--> @llvm/pr-subscribers-clang-codegen Author: Joseph Huber (jhuber6) <details> <summary>Changes</summary> Summary: Right now these enformce alignment, which isn't convenient for the user on platforms that support unaligned accesses. The options are to either permit passing the alignment manually, or just assume it's unaligned unless the user specifies it. I've added https://github.com/llvm/llvm-project/pull/156057 which should make the requiested alignment show up on the intrinsic if the user passed `__builtin_assume_aligned`, however that's only with optimizations. This shouldn't cause issues unless the backend categorically decides to reject an unaligned access. --- Full diff: https://github.com/llvm/llvm-project/pull/156063.diff 3 Files Affected: - (modified) clang/docs/LanguageExtensions.rst (+2-1) - (modified) clang/lib/CodeGen/CGBuiltin.cpp (+5-11) - (modified) clang/test/CodeGen/builtin-masked.c (+3-3) ``````````diff diff --git a/clang/docs/LanguageExtensions.rst b/clang/docs/LanguageExtensions.rst index cbe59124d5b99..3c280c7ea3a1d 100644 --- a/clang/docs/LanguageExtensions.rst +++ b/clang/docs/LanguageExtensions.rst @@ -948,7 +948,8 @@ Each builtin accesses memory according to a provided boolean mask. These are provided as ``__builtin_masked_load`` and ``__builtin_masked_store``. The first argument is always boolean mask vector. The ``__builtin_masked_load`` builtin takes an optional third vector argument that will be used for the result of the -masked-off lanes. These builtins assume the memory is always aligned. +masked-off lanes. These builtins assume the memory is unaligned, use +``__builtin_assume_aligned`` if alignment is desired. The ``__builtin_masked_expand_load`` and ``__builtin_masked_compress_store`` builtins have the same interface but store the result in consecutive indices. diff --git a/clang/lib/CodeGen/CGBuiltin.cpp b/clang/lib/CodeGen/CGBuiltin.cpp index 172a521e63c17..b00b9dddd75fb 100644 --- a/clang/lib/CodeGen/CGBuiltin.cpp +++ b/clang/lib/CodeGen/CGBuiltin.cpp @@ -4277,10 +4277,6 @@ RValue CodeGenFunction::EmitBuiltinExpr(const GlobalDecl GD, unsigned BuiltinID, llvm::Value *Ptr = EmitScalarExpr(E->getArg(1)); llvm::Type *RetTy = CGM.getTypes().ConvertType(E->getType()); - CharUnits Align = CGM.getNaturalTypeAlignment(E->getType(), nullptr); - llvm::Value *AlignVal = - llvm::ConstantInt::get(Int32Ty, Align.getQuantity()); - llvm::Value *PassThru = llvm::PoisonValue::get(RetTy); if (E->getNumArgs() > 2) PassThru = EmitScalarExpr(E->getArg(2)); @@ -4289,8 +4285,9 @@ RValue CodeGenFunction::EmitBuiltinExpr(const GlobalDecl GD, unsigned BuiltinID, if (BuiltinID == Builtin::BI__builtin_masked_load) { Function *F = CGM.getIntrinsic(Intrinsic::masked_load, {RetTy, UnqualPtrTy}); - Result = - Builder.CreateCall(F, {Ptr, AlignVal, Mask, PassThru}, "masked_load"); + Result = Builder.CreateCall( + F, {Ptr, llvm::ConstantInt::get(Int32Ty, 1), Mask, PassThru}, + "masked_load"); } else { Function *F = CGM.getIntrinsic(Intrinsic::masked_expandload, {RetTy}); Result = @@ -4308,14 +4305,11 @@ RValue CodeGenFunction::EmitBuiltinExpr(const GlobalDecl GD, unsigned BuiltinID, llvm::Type *ValLLTy = CGM.getTypes().ConvertType(ValTy); llvm::Type *PtrTy = Ptr->getType(); - CharUnits Align = CGM.getNaturalTypeAlignment(ValTy, nullptr); - llvm::Value *AlignVal = - llvm::ConstantInt::get(Int32Ty, Align.getQuantity()); - if (BuiltinID == Builtin::BI__builtin_masked_store) { llvm::Function *F = CGM.getIntrinsic(llvm::Intrinsic::masked_store, {ValLLTy, PtrTy}); - Builder.CreateCall(F, {Val, Ptr, AlignVal, Mask}); + Builder.CreateCall(F, + {Val, Ptr, llvm::ConstantInt::get(Int32Ty, 1), Mask}); } else { llvm::Function *F = CGM.getIntrinsic(llvm::Intrinsic::masked_compressstore, {ValLLTy}); diff --git a/clang/test/CodeGen/builtin-masked.c b/clang/test/CodeGen/builtin-masked.c index 579cf5c413c9b..1e0f63d280840 100644 --- a/clang/test/CodeGen/builtin-masked.c +++ b/clang/test/CodeGen/builtin-masked.c @@ -19,7 +19,7 @@ typedef _Bool v8b __attribute__((ext_vector_type(8))); // CHECK-NEXT: [[LOAD_BITS2:%.*]] = load i8, ptr [[M_ADDR]], align 1 // CHECK-NEXT: [[TMP1:%.*]] = bitcast i8 [[LOAD_BITS2]] to <8 x i1> // CHECK-NEXT: [[TMP2:%.*]] = load ptr, ptr [[P_ADDR]], align 8 -// CHECK-NEXT: [[MASKED_LOAD:%.*]] = call <8 x i32> @llvm.masked.load.v8i32.p0(ptr [[TMP2]], i32 32, <8 x i1> [[TMP1]], <8 x i32> poison) +// CHECK-NEXT: [[MASKED_LOAD:%.*]] = call <8 x i32> @llvm.masked.load.v8i32.p0(ptr [[TMP2]], i32 1, <8 x i1> [[TMP1]], <8 x i32> poison) // CHECK-NEXT: ret <8 x i32> [[MASKED_LOAD]] // v8i test_load(v8b m, v8i *p) { @@ -45,7 +45,7 @@ v8i test_load(v8b m, v8i *p) { // CHECK-NEXT: [[TMP2:%.*]] = bitcast i8 [[LOAD_BITS2]] to <8 x i1> // CHECK-NEXT: [[TMP3:%.*]] = load ptr, ptr [[P_ADDR]], align 8 // CHECK-NEXT: [[TMP4:%.*]] = load <8 x i32>, ptr [[T_ADDR]], align 32 -// CHECK-NEXT: [[MASKED_LOAD:%.*]] = call <8 x i32> @llvm.masked.load.v8i32.p0(ptr [[TMP3]], i32 32, <8 x i1> [[TMP2]], <8 x i32> [[TMP4]]) +// CHECK-NEXT: [[MASKED_LOAD:%.*]] = call <8 x i32> @llvm.masked.load.v8i32.p0(ptr [[TMP3]], i32 1, <8 x i1> [[TMP2]], <8 x i32> [[TMP4]]) // CHECK-NEXT: ret <8 x i32> [[MASKED_LOAD]] // v8i test_load_passthru(v8b m, v8i *p, v8i t) { @@ -97,7 +97,7 @@ v8i test_load_expand(v8b m, v8i *p, v8i t) { // CHECK-NEXT: [[TMP2:%.*]] = bitcast i8 [[LOAD_BITS2]] to <8 x i1> // CHECK-NEXT: [[TMP3:%.*]] = load <8 x i32>, ptr [[V_ADDR]], align 32 // CHECK-NEXT: [[TMP4:%.*]] = load ptr, ptr [[P_ADDR]], align 8 -// CHECK-NEXT: call void @llvm.masked.store.v8i32.p0(<8 x i32> [[TMP3]], ptr [[TMP4]], i32 32, <8 x i1> [[TMP2]]) +// CHECK-NEXT: call void @llvm.masked.store.v8i32.p0(<8 x i32> [[TMP3]], ptr [[TMP4]], i32 1, <8 x i1> [[TMP2]]) // CHECK-NEXT: ret void // void test_store(v8b m, v8i v, v8i *p) { `````````` </details> https://github.com/llvm/llvm-project/pull/156063 _______________________________________________ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
