llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT--> @llvm/pr-subscribers-clang Author: Mészáros Gergely (Maetveis) <details> <summary>Changes</summary> When `-fcomplex-arithmetic=promoted` is set complex divassign `/=` should promote to a wider type the same way division (without assignment) does. Prior to this change, Smith's algorithm would be used for divassign. Fixes: https://github.com/llvm/llvm-project/issues/131129 --- Patch is 78.24 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/131453.diff 2 Files Affected: - (modified) clang/lib/CodeGen/CGExprComplex.cpp (+12-6) - (modified) clang/test/CodeGen/cx-complex-range.c (+213-321) ``````````diff diff --git a/clang/lib/CodeGen/CGExprComplex.cpp b/clang/lib/CodeGen/CGExprComplex.cpp index a8a65a2f956f8..dc1a34ee82805 100644 --- a/clang/lib/CodeGen/CGExprComplex.cpp +++ b/clang/lib/CodeGen/CGExprComplex.cpp @@ -1212,19 +1212,24 @@ EmitCompoundAssignLValue(const CompoundAssignOperator *E, OpInfo.FPFeatures = E->getFPFeaturesInEffect(CGF.getLangOpts()); CodeGenFunction::CGFPOptionsRAII FPOptsRAII(CGF, OpInfo.FPFeatures); + const bool IsComplexDivisor = E->getOpcode() == BO_DivAssign && + E->getRHS()->getType()->isAnyComplexType(); + // Load the RHS and LHS operands. // __block variables need to have the rhs evaluated first, plus this should // improve codegen a little. QualType PromotionTypeCR; - PromotionTypeCR = getPromotionType(E->getStoredFPFeaturesOrDefault(), - E->getComputationResultType()); + PromotionTypeCR = + getPromotionType(E->getStoredFPFeaturesOrDefault(), + E->getComputationResultType(), IsComplexDivisor); if (PromotionTypeCR.isNull()) PromotionTypeCR = E->getComputationResultType(); OpInfo.Ty = PromotionTypeCR; QualType ComplexElementTy = OpInfo.Ty->castAs<ComplexType>()->getElementType(); - QualType PromotionTypeRHS = getPromotionType( - E->getStoredFPFeaturesOrDefault(), E->getRHS()->getType()); + QualType PromotionTypeRHS = + getPromotionType(E->getStoredFPFeaturesOrDefault(), + E->getRHS()->getType(), IsComplexDivisor); // The RHS should have been converted to the computation type. if (E->getRHS()->getType()->isRealFloatingType()) { @@ -1252,8 +1257,9 @@ EmitCompoundAssignLValue(const CompoundAssignOperator *E, // Load from the l-value and convert it. SourceLocation Loc = E->getExprLoc(); - QualType PromotionTypeLHS = getPromotionType( - E->getStoredFPFeaturesOrDefault(), E->getComputationLHSType()); + QualType PromotionTypeLHS = + getPromotionType(E->getStoredFPFeaturesOrDefault(), + E->getComputationLHSType(), IsComplexDivisor); if (LHSTy->isAnyComplexType()) { ComplexPairTy LHSVal = EmitLoadOfLValue(LHS, Loc); if (!PromotionTypeLHS.isNull()) diff --git a/clang/test/CodeGen/cx-complex-range.c b/clang/test/CodeGen/cx-complex-range.c index 06a349fbc2a47..a724e1ca8cb6d 100644 --- a/clang/test/CodeGen/cx-complex-range.c +++ b/clang/test/CodeGen/cx-complex-range.c @@ -721,44 +721,32 @@ _Complex float divf(_Complex float a, _Complex float b) { // PRMTD-NEXT: [[B_REAL:%.*]] = load float, ptr [[B_REALP]], align 4 // PRMTD-NEXT: [[B_IMAGP:%.*]] = getelementptr inbounds nuw { float, float }, ptr [[B]], i32 0, i32 1 // PRMTD-NEXT: [[B_IMAG:%.*]] = load float, ptr [[B_IMAGP]], align 4 +// PRMTD-NEXT: [[EXT:%.*]] = fpext float [[B_REAL]] to double +// PRMTD-NEXT: [[EXT1:%.*]] = fpext float [[B_IMAG]] to double // PRMTD-NEXT: [[TMP0:%.*]] = load ptr, ptr [[A_ADDR]], align 8 // PRMTD-NEXT: [[DOTREALP:%.*]] = getelementptr inbounds nuw { float, float }, ptr [[TMP0]], i32 0, i32 0 // PRMTD-NEXT: [[DOTREAL:%.*]] = load float, ptr [[DOTREALP]], align 4 // PRMTD-NEXT: [[DOTIMAGP:%.*]] = getelementptr inbounds nuw { float, float }, ptr [[TMP0]], i32 0, i32 1 // PRMTD-NEXT: [[DOTIMAG:%.*]] = load float, ptr [[DOTIMAGP]], align 4 -// PRMTD-NEXT: [[TMP1:%.*]] = call float @llvm.fabs.f32(float [[B_REAL]]) -// PRMTD-NEXT: [[TMP2:%.*]] = call float @llvm.fabs.f32(float [[B_IMAG]]) -// PRMTD-NEXT: [[ABS_CMP:%.*]] = fcmp ugt float [[TMP1]], [[TMP2]] -// PRMTD-NEXT: br i1 [[ABS_CMP]], label [[ABS_RHSR_GREATER_OR_EQUAL_ABS_RHSI:%.*]], label [[ABS_RHSR_LESS_THAN_ABS_RHSI:%.*]] -// PRMTD: abs_rhsr_greater_or_equal_abs_rhsi: -// PRMTD-NEXT: [[TMP3:%.*]] = fdiv float [[B_IMAG]], [[B_REAL]] -// PRMTD-NEXT: [[TMP4:%.*]] = fmul float [[TMP3]], [[B_IMAG]] -// PRMTD-NEXT: [[TMP5:%.*]] = fadd float [[B_REAL]], [[TMP4]] -// PRMTD-NEXT: [[TMP6:%.*]] = fmul float [[DOTIMAG]], [[TMP3]] -// PRMTD-NEXT: [[TMP7:%.*]] = fadd float [[DOTREAL]], [[TMP6]] -// PRMTD-NEXT: [[TMP8:%.*]] = fdiv float [[TMP7]], [[TMP5]] -// PRMTD-NEXT: [[TMP9:%.*]] = fmul float [[DOTREAL]], [[TMP3]] -// PRMTD-NEXT: [[TMP10:%.*]] = fsub float [[DOTIMAG]], [[TMP9]] -// PRMTD-NEXT: [[TMP11:%.*]] = fdiv float [[TMP10]], [[TMP5]] -// PRMTD-NEXT: br label [[COMPLEX_DIV:%.*]] -// PRMTD: abs_rhsr_less_than_abs_rhsi: -// PRMTD-NEXT: [[TMP12:%.*]] = fdiv float [[B_REAL]], [[B_IMAG]] -// PRMTD-NEXT: [[TMP13:%.*]] = fmul float [[TMP12]], [[B_REAL]] -// PRMTD-NEXT: [[TMP14:%.*]] = fadd float [[B_IMAG]], [[TMP13]] -// PRMTD-NEXT: [[TMP15:%.*]] = fmul float [[DOTREAL]], [[TMP12]] -// PRMTD-NEXT: [[TMP16:%.*]] = fadd float [[TMP15]], [[DOTIMAG]] -// PRMTD-NEXT: [[TMP17:%.*]] = fdiv float [[TMP16]], [[TMP14]] -// PRMTD-NEXT: [[TMP18:%.*]] = fmul float [[DOTIMAG]], [[TMP12]] -// PRMTD-NEXT: [[TMP19:%.*]] = fsub float [[TMP18]], [[DOTREAL]] -// PRMTD-NEXT: [[TMP20:%.*]] = fdiv float [[TMP19]], [[TMP14]] -// PRMTD-NEXT: br label [[COMPLEX_DIV]] -// PRMTD: complex_div: -// PRMTD-NEXT: [[TMP21:%.*]] = phi float [ [[TMP8]], [[ABS_RHSR_GREATER_OR_EQUAL_ABS_RHSI]] ], [ [[TMP17]], [[ABS_RHSR_LESS_THAN_ABS_RHSI]] ] -// PRMTD-NEXT: [[TMP22:%.*]] = phi float [ [[TMP11]], [[ABS_RHSR_GREATER_OR_EQUAL_ABS_RHSI]] ], [ [[TMP20]], [[ABS_RHSR_LESS_THAN_ABS_RHSI]] ] -// PRMTD-NEXT: [[DOTREALP1:%.*]] = getelementptr inbounds nuw { float, float }, ptr [[TMP0]], i32 0, i32 0 -// PRMTD-NEXT: [[DOTIMAGP2:%.*]] = getelementptr inbounds nuw { float, float }, ptr [[TMP0]], i32 0, i32 1 -// PRMTD-NEXT: store float [[TMP21]], ptr [[DOTREALP1]], align 4 -// PRMTD-NEXT: store float [[TMP22]], ptr [[DOTIMAGP2]], align 4 +// PRMTD-NEXT: [[CONV:%.*]] = fpext float [[DOTREAL]] to double +// PRMTD-NEXT: [[CONV2:%.*]] = fpext float [[DOTIMAG]] to double +// PRMTD-NEXT: [[TMP1:%.*]] = fmul double [[CONV]], [[EXT]] +// PRMTD-NEXT: [[TMP2:%.*]] = fmul double [[CONV2]], [[EXT1]] +// PRMTD-NEXT: [[TMP3:%.*]] = fadd double [[TMP1]], [[TMP2]] +// PRMTD-NEXT: [[TMP4:%.*]] = fmul double [[EXT]], [[EXT]] +// PRMTD-NEXT: [[TMP5:%.*]] = fmul double [[EXT1]], [[EXT1]] +// PRMTD-NEXT: [[TMP6:%.*]] = fadd double [[TMP4]], [[TMP5]] +// PRMTD-NEXT: [[TMP7:%.*]] = fmul double [[CONV2]], [[EXT]] +// PRMTD-NEXT: [[TMP8:%.*]] = fmul double [[CONV]], [[EXT1]] +// PRMTD-NEXT: [[TMP9:%.*]] = fsub double [[TMP7]], [[TMP8]] +// PRMTD-NEXT: [[TMP10:%.*]] = fdiv double [[TMP3]], [[TMP6]] +// PRMTD-NEXT: [[TMP11:%.*]] = fdiv double [[TMP9]], [[TMP6]] +// PRMTD-NEXT: [[CONV3:%.*]] = fptrunc double [[TMP10]] to float +// PRMTD-NEXT: [[CONV4:%.*]] = fptrunc double [[TMP11]] to float +// PRMTD-NEXT: [[DOTREALP5:%.*]] = getelementptr inbounds nuw { float, float }, ptr [[TMP0]], i32 0, i32 0 +// PRMTD-NEXT: [[DOTIMAGP6:%.*]] = getelementptr inbounds nuw { float, float }, ptr [[TMP0]], i32 0, i32 1 +// PRMTD-NEXT: store float [[CONV3]], ptr [[DOTREALP5]], align 4 +// PRMTD-NEXT: store float [[CONV4]], ptr [[DOTIMAGP6]], align 4 // PRMTD-NEXT: ret void // // X86WINPRMTD-LABEL: define dso_local void @divassignf( @@ -772,44 +760,32 @@ _Complex float divf(_Complex float a, _Complex float b) { // X86WINPRMTD-NEXT: [[B_REAL:%.*]] = load float, ptr [[B_REALP]], align 4 // X86WINPRMTD-NEXT: [[B_IMAGP:%.*]] = getelementptr inbounds nuw { float, float }, ptr [[B]], i32 0, i32 1 // X86WINPRMTD-NEXT: [[B_IMAG:%.*]] = load float, ptr [[B_IMAGP]], align 4 +// X86WINPRMTD-NEXT: [[EXT:%.*]] = fpext float [[B_REAL]] to double +// X86WINPRMTD-NEXT: [[EXT1:%.*]] = fpext float [[B_IMAG]] to double // X86WINPRMTD-NEXT: [[TMP0:%.*]] = load ptr, ptr [[A_ADDR]], align 8 // X86WINPRMTD-NEXT: [[DOTREALP:%.*]] = getelementptr inbounds nuw { float, float }, ptr [[TMP0]], i32 0, i32 0 // X86WINPRMTD-NEXT: [[DOTREAL:%.*]] = load float, ptr [[DOTREALP]], align 4 // X86WINPRMTD-NEXT: [[DOTIMAGP:%.*]] = getelementptr inbounds nuw { float, float }, ptr [[TMP0]], i32 0, i32 1 // X86WINPRMTD-NEXT: [[DOTIMAG:%.*]] = load float, ptr [[DOTIMAGP]], align 4 -// X86WINPRMTD-NEXT: [[TMP1:%.*]] = call float @llvm.fabs.f32(float [[B_REAL]]) -// X86WINPRMTD-NEXT: [[TMP2:%.*]] = call float @llvm.fabs.f32(float [[B_IMAG]]) -// X86WINPRMTD-NEXT: [[ABS_CMP:%.*]] = fcmp ugt float [[TMP1]], [[TMP2]] -// X86WINPRMTD-NEXT: br i1 [[ABS_CMP]], label [[ABS_RHSR_GREATER_OR_EQUAL_ABS_RHSI:%.*]], label [[ABS_RHSR_LESS_THAN_ABS_RHSI:%.*]] -// X86WINPRMTD: abs_rhsr_greater_or_equal_abs_rhsi: -// X86WINPRMTD-NEXT: [[TMP3:%.*]] = fdiv float [[B_IMAG]], [[B_REAL]] -// X86WINPRMTD-NEXT: [[TMP4:%.*]] = fmul float [[TMP3]], [[B_IMAG]] -// X86WINPRMTD-NEXT: [[TMP5:%.*]] = fadd float [[B_REAL]], [[TMP4]] -// X86WINPRMTD-NEXT: [[TMP6:%.*]] = fmul float [[DOTIMAG]], [[TMP3]] -// X86WINPRMTD-NEXT: [[TMP7:%.*]] = fadd float [[DOTREAL]], [[TMP6]] -// X86WINPRMTD-NEXT: [[TMP8:%.*]] = fdiv float [[TMP7]], [[TMP5]] -// X86WINPRMTD-NEXT: [[TMP9:%.*]] = fmul float [[DOTREAL]], [[TMP3]] -// X86WINPRMTD-NEXT: [[TMP10:%.*]] = fsub float [[DOTIMAG]], [[TMP9]] -// X86WINPRMTD-NEXT: [[TMP11:%.*]] = fdiv float [[TMP10]], [[TMP5]] -// X86WINPRMTD-NEXT: br label [[COMPLEX_DIV:%.*]] -// X86WINPRMTD: abs_rhsr_less_than_abs_rhsi: -// X86WINPRMTD-NEXT: [[TMP12:%.*]] = fdiv float [[B_REAL]], [[B_IMAG]] -// X86WINPRMTD-NEXT: [[TMP13:%.*]] = fmul float [[TMP12]], [[B_REAL]] -// X86WINPRMTD-NEXT: [[TMP14:%.*]] = fadd float [[B_IMAG]], [[TMP13]] -// X86WINPRMTD-NEXT: [[TMP15:%.*]] = fmul float [[DOTREAL]], [[TMP12]] -// X86WINPRMTD-NEXT: [[TMP16:%.*]] = fadd float [[TMP15]], [[DOTIMAG]] -// X86WINPRMTD-NEXT: [[TMP17:%.*]] = fdiv float [[TMP16]], [[TMP14]] -// X86WINPRMTD-NEXT: [[TMP18:%.*]] = fmul float [[DOTIMAG]], [[TMP12]] -// X86WINPRMTD-NEXT: [[TMP19:%.*]] = fsub float [[TMP18]], [[DOTREAL]] -// X86WINPRMTD-NEXT: [[TMP20:%.*]] = fdiv float [[TMP19]], [[TMP14]] -// X86WINPRMTD-NEXT: br label [[COMPLEX_DIV]] -// X86WINPRMTD: complex_div: -// X86WINPRMTD-NEXT: [[TMP21:%.*]] = phi float [ [[TMP8]], [[ABS_RHSR_GREATER_OR_EQUAL_ABS_RHSI]] ], [ [[TMP17]], [[ABS_RHSR_LESS_THAN_ABS_RHSI]] ] -// X86WINPRMTD-NEXT: [[TMP22:%.*]] = phi float [ [[TMP11]], [[ABS_RHSR_GREATER_OR_EQUAL_ABS_RHSI]] ], [ [[TMP20]], [[ABS_RHSR_LESS_THAN_ABS_RHSI]] ] -// X86WINPRMTD-NEXT: [[DOTREALP1:%.*]] = getelementptr inbounds nuw { float, float }, ptr [[TMP0]], i32 0, i32 0 -// X86WINPRMTD-NEXT: [[DOTIMAGP2:%.*]] = getelementptr inbounds nuw { float, float }, ptr [[TMP0]], i32 0, i32 1 -// X86WINPRMTD-NEXT: store float [[TMP21]], ptr [[DOTREALP1]], align 4 -// X86WINPRMTD-NEXT: store float [[TMP22]], ptr [[DOTIMAGP2]], align 4 +// X86WINPRMTD-NEXT: [[CONV:%.*]] = fpext float [[DOTREAL]] to double +// X86WINPRMTD-NEXT: [[CONV2:%.*]] = fpext float [[DOTIMAG]] to double +// X86WINPRMTD-NEXT: [[TMP1:%.*]] = fmul double [[CONV]], [[EXT]] +// X86WINPRMTD-NEXT: [[TMP2:%.*]] = fmul double [[CONV2]], [[EXT1]] +// X86WINPRMTD-NEXT: [[TMP3:%.*]] = fadd double [[TMP1]], [[TMP2]] +// X86WINPRMTD-NEXT: [[TMP4:%.*]] = fmul double [[EXT]], [[EXT]] +// X86WINPRMTD-NEXT: [[TMP5:%.*]] = fmul double [[EXT1]], [[EXT1]] +// X86WINPRMTD-NEXT: [[TMP6:%.*]] = fadd double [[TMP4]], [[TMP5]] +// X86WINPRMTD-NEXT: [[TMP7:%.*]] = fmul double [[CONV2]], [[EXT]] +// X86WINPRMTD-NEXT: [[TMP8:%.*]] = fmul double [[CONV]], [[EXT1]] +// X86WINPRMTD-NEXT: [[TMP9:%.*]] = fsub double [[TMP7]], [[TMP8]] +// X86WINPRMTD-NEXT: [[TMP10:%.*]] = fdiv double [[TMP3]], [[TMP6]] +// X86WINPRMTD-NEXT: [[TMP11:%.*]] = fdiv double [[TMP9]], [[TMP6]] +// X86WINPRMTD-NEXT: [[CONV3:%.*]] = fptrunc double [[TMP10]] to float +// X86WINPRMTD-NEXT: [[CONV4:%.*]] = fptrunc double [[TMP11]] to float +// X86WINPRMTD-NEXT: [[DOTREALP5:%.*]] = getelementptr inbounds nuw { float, float }, ptr [[TMP0]], i32 0, i32 0 +// X86WINPRMTD-NEXT: [[DOTIMAGP6:%.*]] = getelementptr inbounds nuw { float, float }, ptr [[TMP0]], i32 0, i32 1 +// X86WINPRMTD-NEXT: store float [[CONV3]], ptr [[DOTREALP5]], align 4 +// X86WINPRMTD-NEXT: store float [[CONV4]], ptr [[DOTIMAGP6]], align 4 // X86WINPRMTD-NEXT: ret void // // AVRFP32-LABEL: define dso_local void @divassignf( @@ -880,44 +856,32 @@ _Complex float divf(_Complex float a, _Complex float b) { // AVRFP64-NEXT: [[B_REAL:%.*]] = load float, ptr [[B_REALP]], align 1 // AVRFP64-NEXT: [[B_IMAGP:%.*]] = getelementptr inbounds nuw { float, float }, ptr [[B]], i32 0, i32 1 // AVRFP64-NEXT: [[B_IMAG:%.*]] = load float, ptr [[B_IMAGP]], align 1 +// AVRFP64-NEXT: [[EXT:%.*]] = fpext float [[B_REAL]] to double +// AVRFP64-NEXT: [[EXT1:%.*]] = fpext float [[B_IMAG]] to double // AVRFP64-NEXT: [[TMP2:%.*]] = load ptr, ptr [[A_ADDR]], align 1 // AVRFP64-NEXT: [[DOTREALP:%.*]] = getelementptr inbounds nuw { float, float }, ptr [[TMP2]], i32 0, i32 0 // AVRFP64-NEXT: [[DOTREAL:%.*]] = load float, ptr [[DOTREALP]], align 1 // AVRFP64-NEXT: [[DOTIMAGP:%.*]] = getelementptr inbounds nuw { float, float }, ptr [[TMP2]], i32 0, i32 1 // AVRFP64-NEXT: [[DOTIMAG:%.*]] = load float, ptr [[DOTIMAGP]], align 1 -// AVRFP64-NEXT: [[TMP3:%.*]] = call addrspace(1) float @llvm.fabs.f32(float [[B_REAL]]) -// AVRFP64-NEXT: [[TMP4:%.*]] = call addrspace(1) float @llvm.fabs.f32(float [[B_IMAG]]) -// AVRFP64-NEXT: [[ABS_CMP:%.*]] = fcmp ugt float [[TMP3]], [[TMP4]] -// AVRFP64-NEXT: br i1 [[ABS_CMP]], label [[ABS_RHSR_GREATER_OR_EQUAL_ABS_RHSI:%.*]], label [[ABS_RHSR_LESS_THAN_ABS_RHSI:%.*]] -// AVRFP64: abs_rhsr_greater_or_equal_abs_rhsi: -// AVRFP64-NEXT: [[TMP5:%.*]] = fdiv float [[B_IMAG]], [[B_REAL]] -// AVRFP64-NEXT: [[TMP6:%.*]] = fmul float [[TMP5]], [[B_IMAG]] -// AVRFP64-NEXT: [[TMP7:%.*]] = fadd float [[B_REAL]], [[TMP6]] -// AVRFP64-NEXT: [[TMP8:%.*]] = fmul float [[DOTIMAG]], [[TMP5]] -// AVRFP64-NEXT: [[TMP9:%.*]] = fadd float [[DOTREAL]], [[TMP8]] -// AVRFP64-NEXT: [[TMP10:%.*]] = fdiv float [[TMP9]], [[TMP7]] -// AVRFP64-NEXT: [[TMP11:%.*]] = fmul float [[DOTREAL]], [[TMP5]] -// AVRFP64-NEXT: [[TMP12:%.*]] = fsub float [[DOTIMAG]], [[TMP11]] -// AVRFP64-NEXT: [[TMP13:%.*]] = fdiv float [[TMP12]], [[TMP7]] -// AVRFP64-NEXT: br label [[COMPLEX_DIV:%.*]] -// AVRFP64: abs_rhsr_less_than_abs_rhsi: -// AVRFP64-NEXT: [[TMP14:%.*]] = fdiv float [[B_REAL]], [[B_IMAG]] -// AVRFP64-NEXT: [[TMP15:%.*]] = fmul float [[TMP14]], [[B_REAL]] -// AVRFP64-NEXT: [[TMP16:%.*]] = fadd float [[B_IMAG]], [[TMP15]] -// AVRFP64-NEXT: [[TMP17:%.*]] = fmul float [[DOTREAL]], [[TMP14]] -// AVRFP64-NEXT: [[TMP18:%.*]] = fadd float [[TMP17]], [[DOTIMAG]] -// AVRFP64-NEXT: [[TMP19:%.*]] = fdiv float [[TMP18]], [[TMP16]] -// AVRFP64-NEXT: [[TMP20:%.*]] = fmul float [[DOTIMAG]], [[TMP14]] -// AVRFP64-NEXT: [[TMP21:%.*]] = fsub float [[TMP20]], [[DOTREAL]] -// AVRFP64-NEXT: [[TMP22:%.*]] = fdiv float [[TMP21]], [[TMP16]] -// AVRFP64-NEXT: br label [[COMPLEX_DIV]] -// AVRFP64: complex_div: -// AVRFP64-NEXT: [[TMP23:%.*]] = phi float [ [[TMP10]], [[ABS_RHSR_GREATER_OR_EQUAL_ABS_RHSI]] ], [ [[TMP19]], [[ABS_RHSR_LESS_THAN_ABS_RHSI]] ] -// AVRFP64-NEXT: [[TMP24:%.*]] = phi float [ [[TMP13]], [[ABS_RHSR_GREATER_OR_EQUAL_ABS_RHSI]] ], [ [[TMP22]], [[ABS_RHSR_LESS_THAN_ABS_RHSI]] ] -// AVRFP64-NEXT: [[DOTREALP1:%.*]] = getelementptr inbounds nuw { float, float }, ptr [[TMP2]], i32 0, i32 0 -// AVRFP64-NEXT: [[DOTIMAGP2:%.*]] = getelementptr inbounds nuw { float, float }, ptr [[TMP2]], i32 0, i32 1 -// AVRFP64-NEXT: store float [[TMP23]], ptr [[DOTREALP1]], align 1 -// AVRFP64-NEXT: store float [[TMP24]], ptr [[DOTIMAGP2]], align 1 +// AVRFP64-NEXT: [[CONV:%.*]] = fpext float [[DOTREAL]] to double +// AVRFP64-NEXT: [[CONV2:%.*]] = fpext float [[DOTIMAG]] to double +// AVRFP64-NEXT: [[TMP3:%.*]] = fmul double [[CONV]], [[EXT]] +// AVRFP64-NEXT: [[TMP4:%.*]] = fmul double [[CONV2]], [[EXT1]] +// AVRFP64-NEXT: [[TMP5:%.*]] = fadd double [[TMP3]], [[TMP4]] +// AVRFP64-NEXT: [[TMP6:%.*]] = fmul double [[EXT]], [[EXT]] +// AVRFP64-NEXT: [[TMP7:%.*]] = fmul double [[EXT1]], [[EXT1]] +// AVRFP64-NEXT: [[TMP8:%.*]] = fadd double [[TMP6]], [[TMP7]] +// AVRFP64-NEXT: [[TMP9:%.*]] = fmul double [[CONV2]], [[EXT]] +// AVRFP64-NEXT: [[TMP10:%.*]] = fmul double [[CONV]], [[EXT1]] +// AVRFP64-NEXT: [[TMP11:%.*]] = fsub double [[TMP9]], [[TMP10]] +// AVRFP64-NEXT: [[TMP12:%.*]] = fdiv double [[TMP5]], [[TMP8]] +// AVRFP64-NEXT: [[TMP13:%.*]] = fdiv double [[TMP11]], [[TMP8]] +// AVRFP64-NEXT: [[CONV3:%.*]] = fptrunc double [[TMP12]] to float +// AVRFP64-NEXT: [[CONV4:%.*]] = fptrunc double [[TMP13]] to float +// AVRFP64-NEXT: [[DOTREALP5:%.*]] = getelementptr inbounds nuw { float, float }, ptr [[TMP2]], i32 0, i32 0 +// AVRFP64-NEXT: [[DOTIMAGP6:%.*]] = getelementptr inbounds nuw { float, float }, ptr [[TMP2]], i32 0, i32 1 +// AVRFP64-NEXT: store float [[CONV3]], ptr [[DOTREALP5]], align 1 +// AVRFP64-NEXT: store float [[CONV4]], ptr [[DOTIMAGP6]], align 1 // AVRFP64-NEXT: ret void // // BASIC_FAST-LABEL: define dso_local void @divassignf( @@ -1044,44 +1008,32 @@ _Complex float divf(_Complex float a, _Complex float b) { // PRMTD_FAST-NEXT: [[B_REAL:%.*]] = load float, ptr [[B_REALP]], align 4 // PRMTD_FAST-NEXT: [[B_IMAGP:%.*]] = getelementptr inbounds nuw { float, float }, ptr [[B]], i32 0, i32 1 // PRMTD_FAST-NEXT: [[B_IMAG:%.*]] = load float, ptr [[B_IMAGP]], align 4 +// PRMTD_FAST-NEXT: [[EXT:%.*]] = fpext reassoc nnan ninf nsz arcp afn float [[B_REAL]] to double +// PRMTD_FAST-NEXT: [[EXT1:%.*]] = fpext reassoc nnan ninf nsz arcp afn float [[B_IMAG]] to double // PRMTD_FAST-NEXT: [[TMP0:%.*]] = load ptr, ptr [[A_ADDR]], align 8 // PRMTD_FAST-NEXT: [[DOTREALP:%.*]] = getelementptr inbounds nuw { float, float }, ptr [[TMP0]], i32 0, i32 0 // PRMTD_FAST-NEXT: [[DOTREAL:%.*]] = load float, ptr [[DOTREALP]], align 4 // PRMTD_FAST-NEXT: [[DOTIMAGP:%.*]] = getelementptr inbounds nuw { float, float }, ptr [[TMP0]], i32 0, i32 1 // PRMTD_FAST-NEXT: [[DOTIMAG:%.*]] = load float, ptr [[DOTIMAGP]], align 4 -// PRMTD_FAST-NEXT: [[TMP1:%.*]] = call reassoc nnan ninf nsz arcp afn float @llvm.fabs.f32(float [[B_REAL]]) -// PRMTD_FAST-NEXT: [[TMP2:%.*]] = call reassoc nnan ninf nsz arcp afn float @llvm.fabs.f32(float [[B_IMAG]]) -// PRMTD_FAST-NEXT: [[ABS_CMP:%.*]] = fcmp reassoc nnan ninf nsz arcp afn ugt float [[TMP1]], [[TMP2]] -// PRMTD_FAST-NEXT: br i1 [[ABS_CMP]], label [[ABS_RHSR_GREATER_OR_EQUAL_ABS_RHSI:%.*]], label [[ABS_RHSR_LESS_THAN_ABS_RHSI:%.*]] -// PRMTD_FAST: abs_rhsr_greater_or_equal_abs_rhsi: -// PRMTD_FAST-NEXT: [[TMP3:%.*]] = fdiv reassoc nnan ninf nsz arcp afn float [[B_IMAG]], [[B_REAL]] -// PRMTD_FAST-NEXT: [[TMP4:%.*]] = fmul reassoc nnan ninf nsz arcp afn float [[TMP3]], [[B_IMAG]] -// PRMTD_FAST-NEXT: [[TMP5:%.*]] = fadd reassoc nnan ninf nsz arcp afn float [[B_REAL]], [[TMP4]] -// PRMTD_FAST-NEXT: [[TMP6:%.*]] = fmul reassoc nnan ninf nsz arcp afn float [[DOTIMAG]], [[TMP3]] -// PRMTD_FAST-NEXT: [[TMP7:%.*]] = fadd reassoc nnan ninf nsz arcp afn float [[DOTREAL]], [[TMP6]] -// PRMTD_FAST-NEXT: [[TMP8:%.*]] = fdiv reassoc nnan ninf nsz arcp afn float [[TMP7]], [[TMP5]] -// PRMTD_FAST-NEXT: [[TMP9:%.*]] = fmul reassoc nnan ninf nsz arcp afn float [[DOTREAL]], [[TMP3]] -// PRMTD_FAST-NEXT: [[TMP10:%.*]] = fsub reassoc nnan ninf nsz arcp afn float [[DOTIMAG]], [[TMP9]] -// PRMTD_FAST-NEXT: [[TMP11:%.*]] = fdiv reassoc nnan ninf nsz arcp afn float [[TMP10]], [[TMP5]] -// PRMTD_FAST-NEXT: br label [[COMPLEX_DIV:%.*]] -// PRMTD_FAST: abs_rhsr_less_than_abs_rhsi: -// PRMTD_FAST-NEXT: [[TMP12:%.*]] = fdiv reassoc nnan ninf nsz arcp afn float [[B_REAL]], [[B_IMAG]] -// PRMTD_FAST-NEXT: [[TMP13:%.*]] = fmul reassoc nnan ninf nsz arcp afn float [[TMP12]], [[B_REAL]] -// PRMTD_FAST-NEXT: [[TMP14:%.*]] = fadd reassoc nnan ninf nsz arcp afn float [[B_IMAG]], [[TMP13]] -// PRMTD_FAST-NEXT: [[TMP15:%.*]] = fmul reassoc nnan ninf nsz arcp afn float [[DOTREAL]], [[TMP12]] -// PRMTD_FAST-NEXT: [[TMP16:%.*]] = fadd reassoc nnan ninf nsz arcp afn float [[TMP15]], [[DOTIMAG]] -// PRMTD_FAST-NEXT: [[TM... [truncated] `````````` </details> https://github.com/llvm/llvm-project/pull/131453 _______________________________________________ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
