From 4c4093e6e39fe6601f9c95a95a6bc242ef648cd5 Mon Sep 17 00:00:00 2001 From: Serge Pavlov Date: Thu, 5 Aug 2021 18:12:18 +0700 Subject: [PATCH] Introduce intrinsic llvm.isnan This is recommit of the patch 16ff91ebccda1128c43ff3cee104e2c603569fb2, reverted in 0c28a7c990c5218d6aec47c5052a51cba686ec5e because it had an error in call of getFastMathFlags (base type should be FPMathOperator but not Instruction). The original commit message is duplicated below: Clang has builtin function '__builtin_isnan', which implements C library function 'isnan'. This function now is implemented entirely in clang codegen, which expands the function into set of IR operations. There are three mechanisms by which the expansion can be made. * The most common mechanism is using an unordered comparison made by instruction 'fcmp uno'. This simple solution is target-independent and works well in most cases. It however is not suitable if floating point exceptions are tracked. Corresponding IEEE 754 operation and C function must never raise FP exception, even if the argument is a signaling NaN. Compare instructions usually does not have such property, they raise 'invalid' exception in such case. So this mechanism is unsuitable when exception behavior is strict. In particular it could result in unexpected trapping if argument is SNaN. * Another solution was implemented in https://reviews.llvm.org/D95948. It is used in the cases when raising FP exceptions by 'isnan' is not allowed. This solution implements 'isnan' using integer operations. It solves the problem of exceptions, but offers one solution for all targets, however some can do the check in more efficient way. * Solution implemented by https://reviews.llvm.org/D96568 introduced a hook 'clang::TargetCodeGenInfo::testFPKind', which injects target specific code into IR. Now only SystemZ implements this hook and it generates a call to target specific intrinsic function. Although these mechanisms allow to implement 'isnan' with enough efficiency, expanding 'isnan' in clang has drawbacks: * The operation 'isnan' is hidden behind generic integer operations or target-specific intrinsics. It complicates analysis and can prevent some optimizations. * IR can be created by tools other than clang, in this case treatment of 'isnan' has to be duplicated in that tool. Another issue with the current implementation of 'isnan' comes from the use of options '-ffast-math' or '-fno-honor-nans'. If such option is specified, 'fcmp uno' may be optimized to 'false'. It is valid optimization in general, but it results in 'isnan' always returning 'false'. For example, in some libc++ implementations the following code returns 'false': std::isnan(std::numeric_limits::quiet_NaN()) The options '-ffast-math' and '-fno-honor-nans' imply that FP operation operands are never NaNs. This assumption however should not be applied to the functions that check FP number properties, including 'isnan'. If such function returns expected result instead of actually making checks, it becomes useless in many cases. The option '-ffast-math' is often used for performance critical code, as it can speed up execution by the expense of manual treatment of corner cases. If 'isnan' returns assumed result, a user cannot use it in the manual treatment of NaNs and has to invent replacements, like making the check using integer operations. There is a discussion in https://reviews.llvm.org/D18513#387418, which also expresses the opinion, that limitations imposed by '-ffast-math' should be applied only to 'math' functions but not to 'tests'. To overcome these drawbacks, this change introduces a new IR intrinsic function 'llvm.isnan', which realizes the check as specified by IEEE-754 and C standards in target-agnostic way. During IR transformations it does not undergo undesirable optimizations. It reaches instruction selection, where is lowered in target-dependent way. The lowering can vary depending on options like '-ffast-math' or '-ffp-model' so the resulting code satisfies requested semantics. Differential Revision: https://reviews.llvm.org/D104854 --- clang/lib/CodeGen/CGBuiltin.cpp | 28 +- clang/test/CodeGen/X86/strictfp_builtins.c | 37 +- clang/test/CodeGen/aarch64-strictfp-builtins.c | 38 +- clang/test/CodeGen/strictfp_builtins.c | 152 ++- llvm/docs/LangRef.rst | 46 + llvm/include/llvm/CodeGen/ISDOpcodes.h | 4 + llvm/include/llvm/CodeGen/TargetLowering.h | 4 + llvm/include/llvm/IR/Intrinsics.td | 8 + llvm/lib/Analysis/ConstantFolding.cpp | 6 +- llvm/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp | 10 + .../CodeGen/SelectionDAG/LegalizeIntegerTypes.cpp | 10 + llvm/lib/CodeGen/SelectionDAG/LegalizeTypes.h | 4 + .../CodeGen/SelectionDAG/LegalizeVectorTypes.cpp | 63 ++ .../CodeGen/SelectionDAG/SelectionDAGBuilder.cpp | 24 + .../CodeGen/SelectionDAG/SelectionDAGDumper.cpp | 1 + llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp | 29 + llvm/lib/CodeGen/TargetLoweringBase.cpp | 1 + llvm/lib/Target/X86/X86ISelLowering.cpp | 41 + .../Transforms/InstCombine/InstCombineCalls.cpp | 12 + llvm/test/CodeGen/AArch64/aarch64-fpclass.ll | 490 +++++++++ llvm/test/CodeGen/PowerPC/ppc-fpclass.ll | 535 ++++++++++ llvm/test/CodeGen/X86/x86-fpclass.ll | 1098 ++++++++++++++++++++ llvm/test/Transforms/InstCombine/fpclass.ll | 73 ++ .../InstSimplify/ConstProp/fpclassify.ll | 35 + 24 files changed, 2604 insertions(+), 145 deletions(-) create mode 100644 llvm/test/CodeGen/AArch64/aarch64-fpclass.ll create mode 100644 llvm/test/CodeGen/PowerPC/ppc-fpclass.ll create mode 100644 llvm/test/CodeGen/X86/x86-fpclass.ll create mode 100644 llvm/test/Transforms/InstCombine/fpclass.ll create mode 100644 llvm/test/Transforms/InstSimplify/ConstProp/fpclassify.ll diff --git a/clang/lib/CodeGen/CGBuiltin.cpp b/clang/lib/CodeGen/CGBuiltin.cpp index 6066893..97bfb46 100644 --- a/clang/lib/CodeGen/CGBuiltin.cpp +++ b/clang/lib/CodeGen/CGBuiltin.cpp @@ -3068,37 +3068,17 @@ RValue CodeGenFunction::EmitBuiltinExpr(const GlobalDecl GD, unsigned BuiltinID, // ZExt bool to int type. return RValue::get(Builder.CreateZExt(LHS, ConvertType(E->getType()))); } + case Builtin::BI__builtin_isnan: { CodeGenFunction::CGFPOptionsRAII FPOptsRAII(*this, E); Value *V = EmitScalarExpr(E->getArg(0)); - llvm::Type *Ty = V->getType(); - const llvm::fltSemantics &Semantics = Ty->getFltSemantics(); - if (!Builder.getIsFPConstrained() || - Builder.getDefaultConstrainedExcept() == fp::ebIgnore || - !Ty->isIEEE()) { - V = Builder.CreateFCmpUNO(V, V, "cmp"); - return RValue::get(Builder.CreateZExt(V, ConvertType(E->getType()))); - } if (Value *Result = getTargetHooks().testFPKind(V, BuiltinID, Builder, CGM)) return RValue::get(Result); - // NaN has all exp bits set and a non zero significand. Therefore: - // isnan(V) == ((exp mask - (abs(V) & exp mask)) < 0) - unsigned bitsize = Ty->getScalarSizeInBits(); - llvm::IntegerType *IntTy = Builder.getIntNTy(bitsize); - Value *IntV = Builder.CreateBitCast(V, IntTy); - APInt AndMask = APInt::getSignedMaxValue(bitsize); - Value *AbsV = - Builder.CreateAnd(IntV, llvm::ConstantInt::get(IntTy, AndMask)); - APInt ExpMask = APFloat::getInf(Semantics).bitcastToAPInt(); - Value *Sub = - Builder.CreateSub(llvm::ConstantInt::get(IntTy, ExpMask), AbsV); - // V = sign bit (Sub) <=> V = (Sub < 0) - V = Builder.CreateLShr(Sub, llvm::ConstantInt::get(IntTy, bitsize - 1)); - if (bitsize > 32) - V = Builder.CreateTrunc(V, ConvertType(E->getType())); - return RValue::get(V); + Function *F = CGM.getIntrinsic(Intrinsic::isnan, V->getType()); + Value *Call = Builder.CreateCall(F, V); + return RValue::get(Builder.CreateZExt(Call, ConvertType(E->getType()))); } case Builtin::BI__builtin_matrix_transpose: { diff --git a/clang/test/CodeGen/X86/strictfp_builtins.c b/clang/test/CodeGen/X86/strictfp_builtins.c index c3c9416..4c66b24 100644 --- a/clang/test/CodeGen/X86/strictfp_builtins.c +++ b/clang/test/CodeGen/X86/strictfp_builtins.c @@ -17,7 +17,7 @@ int printf(const char *, ...); // CHECK-NEXT: store i32 [[X:%.*]], i32* [[X_ADDR]], align 4 // CHECK-NEXT: [[TMP0:%.*]] = load i8*, i8** [[STR_ADDR]], align 8 // CHECK-NEXT: [[TMP1:%.*]] = load i32, i32* [[X_ADDR]], align 4 -// CHECK-NEXT: [[CALL:%.*]] = call i32 (i8*, ...) @printf(i8* getelementptr inbounds ([8 x i8], [8 x i8]* @.str, i64 0, i64 0), i8* [[TMP0]], i32 [[TMP1]]) [[ATTR4:#.*]] +// CHECK-NEXT: [[CALL:%.*]] = call i32 (i8*, ...) @printf(i8* getelementptr inbounds ([8 x i8], [8 x i8]* @.str, i64 0, i64 0), i8* [[TMP0]], i32 [[TMP1]]) #[[ATTR3:[0-9]+]] // CHECK-NEXT: ret void // void p(char *str, int x) { @@ -29,13 +29,13 @@ void p(char *str, int x) { // CHECK-LABEL: @test_long_double_isinf( // CHECK-NEXT: entry: // CHECK-NEXT: [[LD_ADDR:%.*]] = alloca x86_fp80, align 16 -// CHECK-NEXT: store x86_fp80 [[D:%.*]], x86_fp80* [[LD_ADDR]], align 16 +// CHECK-NEXT: store x86_fp80 [[LD:%.*]], x86_fp80* [[LD_ADDR]], align 16 // CHECK-NEXT: [[TMP0:%.*]] = load x86_fp80, x86_fp80* [[LD_ADDR]], align 16 -// CHECK-NEXT: [[BITCAST:%.*]] = bitcast x86_fp80 [[TMP0]] to i80 -// CHECK-NEXT: [[SHL1:%.*]] = shl i80 [[BITCAST]], 1 -// CHECK-NEXT: [[CMP:%.*]] = icmp eq i80 [[SHL1]], -18446744073709551616 -// CHECK-NEXT: [[RES:%.*]] = zext i1 [[CMP]] to i32 -// CHECK-NEXT: call void @p(i8* getelementptr inbounds ([10 x i8], [10 x i8]* @.str.[[#STRID:1]], i64 0, i64 0), i32 [[RES]]) [[ATTR4]] +// CHECK-NEXT: [[TMP1:%.*]] = bitcast x86_fp80 [[TMP0]] to i80 +// CHECK-NEXT: [[TMP2:%.*]] = shl i80 [[TMP1]], 1 +// CHECK-NEXT: [[TMP3:%.*]] = icmp eq i80 [[TMP2]], -18446744073709551616 +// CHECK-NEXT: [[TMP4:%.*]] = zext i1 [[TMP3]] to i32 +// CHECK-NEXT: call void @p(i8* getelementptr inbounds ([10 x i8], [10 x i8]* @.str.1, i64 0, i64 0), i32 [[TMP4]]) #[[ATTR3]] // CHECK-NEXT: ret void // void test_long_double_isinf(long double ld) { @@ -47,13 +47,13 @@ void test_long_double_isinf(long double ld) { // CHECK-LABEL: @test_long_double_isfinite( // CHECK-NEXT: entry: // CHECK-NEXT: [[LD_ADDR:%.*]] = alloca x86_fp80, align 16 -// CHECK-NEXT: store x86_fp80 [[D:%.*]], x86_fp80* [[LD_ADDR]], align 16 +// CHECK-NEXT: store x86_fp80 [[LD:%.*]], x86_fp80* [[LD_ADDR]], align 16 // CHECK-NEXT: [[TMP0:%.*]] = load x86_fp80, x86_fp80* [[LD_ADDR]], align 16 -// CHECK-NEXT: [[BITCAST:%.*]] = bitcast x86_fp80 [[TMP0]] to i80 -// CHECK-NEXT: [[SHL1:%.*]] = shl i80 [[BITCAST]], 1 -// CHECK-NEXT: [[CMP:%.*]] = icmp ult i80 [[SHL1]], -18446744073709551616 -// CHECK-NEXT: [[RES:%.*]] = zext i1 [[CMP]] to i32 -// CHECK-NEXT: call void @p(i8* getelementptr inbounds ([13 x i8], [13 x i8]* @.str.[[#STRID:STRID+1]], i64 0, i64 0), i32 [[RES]]) [[ATTR4]] +// CHECK-NEXT: [[TMP1:%.*]] = bitcast x86_fp80 [[TMP0]] to i80 +// CHECK-NEXT: [[TMP2:%.*]] = shl i80 [[TMP1]], 1 +// CHECK-NEXT: [[TMP3:%.*]] = icmp ult i80 [[TMP2]], -18446744073709551616 +// CHECK-NEXT: [[TMP4:%.*]] = zext i1 [[TMP3]] to i32 +// CHECK-NEXT: call void @p(i8* getelementptr inbounds ([13 x i8], [13 x i8]* @.str.2, i64 0, i64 0), i32 [[TMP4]]) #[[ATTR3]] // CHECK-NEXT: ret void // void test_long_double_isfinite(long double ld) { @@ -65,14 +65,11 @@ void test_long_double_isfinite(long double ld) { // CHECK-LABEL: @test_long_double_isnan( // CHECK-NEXT: entry: // CHECK-NEXT: [[LD_ADDR:%.*]] = alloca x86_fp80, align 16 -// CHECK-NEXT: store x86_fp80 [[D:%.*]], x86_fp80* [[LD_ADDR]], align 16 +// CHECK-NEXT: store x86_fp80 [[LD:%.*]], x86_fp80* [[LD_ADDR]], align 16 // CHECK-NEXT: [[TMP0:%.*]] = load x86_fp80, x86_fp80* [[LD_ADDR]], align 16 -// CHECK-NEXT: [[BITCAST:%.*]] = bitcast x86_fp80 [[TMP0]] to i80 -// CHECK-NEXT: [[ABS:%.*]] = and i80 [[BITCAST]], 604462909807314587353087 -// CHECK-NEXT: [[TMP1:%.*]] = sub i80 604453686435277732577280, [[ABS]] -// CHECK-NEXT: [[ISNAN:%.*]] = lshr i80 [[TMP1]], 79 -// CHECK-NEXT: [[RES:%.*]] = trunc i80 [[ISNAN]] to i32 -// CHECK-NEXT: call void @p(i8* getelementptr inbounds ([10 x i8], [10 x i8]* @.str.[[#STRID:STRID+1]], i64 0, i64 0), i32 [[RES]]) [[ATTR4]] +// CHECK-NEXT: [[TMP1:%.*]] = call i1 @llvm.isnan.f80(x86_fp80 [[TMP0]]) #[[ATTR3]] +// CHECK-NEXT: [[TMP2:%.*]] = zext i1 [[TMP1]] to i32 +// CHECK-NEXT: call void @p(i8* getelementptr inbounds ([10 x i8], [10 x i8]* @.str.3, i64 0, i64 0), i32 [[TMP2]]) #[[ATTR3]] // CHECK-NEXT: ret void // void test_long_double_isnan(long double ld) { diff --git a/clang/test/CodeGen/aarch64-strictfp-builtins.c b/clang/test/CodeGen/aarch64-strictfp-builtins.c index 3b2a4e5..9dc6e25 100644 --- a/clang/test/CodeGen/aarch64-strictfp-builtins.c +++ b/clang/test/CodeGen/aarch64-strictfp-builtins.c @@ -1,3 +1,4 @@ +// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py // RUN: %clang_cc1 %s -emit-llvm -ffp-exception-behavior=maytrap -fexperimental-strict-floating-point -o - -triple arm64-none-linux-gnu | FileCheck %s // Test that the constrained intrinsics are picking up the exception @@ -15,7 +16,7 @@ int printf(const char *, ...); // CHECK-NEXT: store i32 [[X:%.*]], i32* [[X_ADDR]], align 4 // CHECK-NEXT: [[TMP0:%.*]] = load i8*, i8** [[STR_ADDR]], align 8 // CHECK-NEXT: [[TMP1:%.*]] = load i32, i32* [[X_ADDR]], align 4 -// CHECK-NEXT: [[CALL:%.*]] = call i32 (i8*, ...) @printf(i8* getelementptr inbounds ([8 x i8], [8 x i8]* @.str, i64 0, i64 0), i8* [[TMP0]], i32 [[TMP1]]) [[ATTR4:#.*]] +// CHECK-NEXT: [[CALL:%.*]] = call i32 (i8*, ...) @printf(i8* getelementptr inbounds ([8 x i8], [8 x i8]* @.str, i64 0, i64 0), i8* [[TMP0]], i32 [[TMP1]]) #[[ATTR3:[0-9]+]] // CHECK-NEXT: ret void // void p(char *str, int x) { @@ -27,13 +28,13 @@ void p(char *str, int x) { // CHECK-LABEL: @test_long_double_isinf( // CHECK-NEXT: entry: // CHECK-NEXT: [[LD_ADDR:%.*]] = alloca fp128, align 16 -// CHECK-NEXT: store fp128 [[D:%.*]], fp128* [[LD_ADDR]], align 16 +// CHECK-NEXT: store fp128 [[LD:%.*]], fp128* [[LD_ADDR]], align 16 // CHECK-NEXT: [[TMP0:%.*]] = load fp128, fp128* [[LD_ADDR]], align 16 -// CHECK-NEXT: [[BITCAST:%.*]] = bitcast fp128 [[TMP0]] to i128 -// CHECK-NEXT: [[SHL1:%.*]] = shl i128 [[BITCAST]], 1 -// CHECK-NEXT: [[CMP:%.*]] = icmp eq i128 [[SHL1]], -10384593717069655257060992658440192 -// CHECK-NEXT: [[RES:%.*]] = zext i1 [[CMP]] to i32 -// CHECK-NEXT: call void @p(i8* getelementptr inbounds ([10 x i8], [10 x i8]* @.str.[[#STRID:1]], i64 0, i64 0), i32 [[RES]]) [[ATTR4]] +// CHECK-NEXT: [[TMP1:%.*]] = bitcast fp128 [[TMP0]] to i128 +// CHECK-NEXT: [[TMP2:%.*]] = shl i128 [[TMP1]], 1 +// CHECK-NEXT: [[TMP3:%.*]] = icmp eq i128 [[TMP2]], -10384593717069655257060992658440192 +// CHECK-NEXT: [[TMP4:%.*]] = zext i1 [[TMP3]] to i32 +// CHECK-NEXT: call void @p(i8* getelementptr inbounds ([10 x i8], [10 x i8]* @.str.1, i64 0, i64 0), i32 [[TMP4]]) #[[ATTR3]] // CHECK-NEXT: ret void // void test_long_double_isinf(long double ld) { @@ -45,13 +46,13 @@ void test_long_double_isinf(long double ld) { // CHECK-LABEL: @test_long_double_isfinite( // CHECK-NEXT: entry: // CHECK-NEXT: [[LD_ADDR:%.*]] = alloca fp128, align 16 -// CHECK-NEXT: store fp128 [[D:%.*]], fp128* [[LD_ADDR]], align 16 +// CHECK-NEXT: store fp128 [[LD:%.*]], fp128* [[LD_ADDR]], align 16 // CHECK-NEXT: [[TMP0:%.*]] = load fp128, fp128* [[LD_ADDR]], align 16 -// CHECK-NEXT: [[BITCAST:%.*]] = bitcast fp128 [[TMP0]] to i128 -// CHECK-NEXT: [[SHL1:%.*]] = shl i128 [[BITCAST]], 1 -// CHECK-NEXT: [[CMP:%.*]] = icmp ult i128 [[SHL1]], -10384593717069655257060992658440192 -// CHECK-NEXT: [[RES:%.*]] = zext i1 [[CMP]] to i32 -// CHECK-NEXT: call void @p(i8* getelementptr inbounds ([13 x i8], [13 x i8]* @.str.[[#STRID:STRID+1]], i64 0, i64 0), i32 [[RES]]) [[ATTR4]] +// CHECK-NEXT: [[TMP1:%.*]] = bitcast fp128 [[TMP0]] to i128 +// CHECK-NEXT: [[TMP2:%.*]] = shl i128 [[TMP1]], 1 +// CHECK-NEXT: [[TMP3:%.*]] = icmp ult i128 [[TMP2]], -10384593717069655257060992658440192 +// CHECK-NEXT: [[TMP4:%.*]] = zext i1 [[TMP3]] to i32 +// CHECK-NEXT: call void @p(i8* getelementptr inbounds ([13 x i8], [13 x i8]* @.str.2, i64 0, i64 0), i32 [[TMP4]]) #[[ATTR3]] // CHECK-NEXT: ret void // void test_long_double_isfinite(long double ld) { @@ -63,14 +64,11 @@ void test_long_double_isfinite(long double ld) { // CHECK-LABEL: @test_long_double_isnan( // CHECK-NEXT: entry: // CHECK-NEXT: [[LD_ADDR:%.*]] = alloca fp128, align 16 -// CHECK-NEXT: store fp128 [[D:%.*]], fp128* [[LD_ADDR]], align 16 +// CHECK-NEXT: store fp128 [[LD:%.*]], fp128* [[LD_ADDR]], align 16 // CHECK-NEXT: [[TMP0:%.*]] = load fp128, fp128* [[LD_ADDR]], align 16 -// CHECK-NEXT: [[BITCAST:%.*]] = bitcast fp128 [[TMP0]] to i128 -// CHECK-NEXT: [[ABS:%.*]] = and i128 [[BITCAST]], 170141183460469231731687303715884105727 -// CHECK-NEXT: [[TMP1:%.*]] = sub i128 170135991163610696904058773219554885632, [[ABS]] -// CHECK-NEXT: [[ISNAN:%.*]] = lshr i128 [[TMP1]], 127 -// CHECK-NEXT: [[RES:%.*]] = trunc i128 [[ISNAN]] to i32 -// CHECK-NEXT: call void @p(i8* getelementptr inbounds ([10 x i8], [10 x i8]* @.str.[[#STRID:STRID+1]], i64 0, i64 0), i32 [[RES]]) +// CHECK-NEXT: [[TMP1:%.*]] = call i1 @llvm.isnan.f128(fp128 [[TMP0]]) #[[ATTR3]] +// CHECK-NEXT: [[TMP2:%.*]] = zext i1 [[TMP1]] to i32 +// CHECK-NEXT: call void @p(i8* getelementptr inbounds ([10 x i8], [10 x i8]* @.str.3, i64 0, i64 0), i32 [[TMP2]]) #[[ATTR3]] // CHECK-NEXT: ret void // void test_long_double_isnan(long double ld) { diff --git a/clang/test/CodeGen/strictfp_builtins.c b/clang/test/CodeGen/strictfp_builtins.c index fbf3c27..25eaac7 100644 --- a/clang/test/CodeGen/strictfp_builtins.c +++ b/clang/test/CodeGen/strictfp_builtins.c @@ -17,7 +17,7 @@ int printf(const char *, ...); // CHECK-NEXT: store i32 [[X:%.*]], i32* [[X_ADDR]], align 4 // CHECK-NEXT: [[TMP0:%.*]] = load i8*, i8** [[STR_ADDR]], align 8 // CHECK-NEXT: [[TMP1:%.*]] = load i32, i32* [[X_ADDR]], align 4 -// CHECK-NEXT: [[CALL:%.*]] = call i32 (i8*, ...) @printf(i8* getelementptr inbounds ([8 x i8], [8 x i8]* @.str, i64 0, i64 0), i8* [[TMP0]], i32 [[TMP1]]) [[ATTR4:#.*]] +// CHECK-NEXT: [[CALL:%.*]] = call i32 (i8*, ...) @printf(i8* getelementptr inbounds ([8 x i8], [8 x i8]* @.str, i64 0, i64 0), i8* [[TMP0]], i32 [[TMP1]]) #[[ATTR5:[0-9]+]] // CHECK-NEXT: ret void // void p(char *str, int x) { @@ -31,21 +31,21 @@ void p(char *str, int x) { // CHECK-NEXT: [[D_ADDR:%.*]] = alloca double, align 8 // CHECK-NEXT: store double [[D:%.*]], double* [[D_ADDR]], align 8 // CHECK-NEXT: [[TMP0:%.*]] = load double, double* [[D_ADDR]], align 8 -// CHECK-NEXT: [[ISZERO:%.*]] = call i1 @llvm.experimental.constrained.fcmp.f64(double [[TMP0]], double 0.000000e+00, metadata !"oeq", metadata !"fpexcept.strict") [[ATTR4]] +// CHECK-NEXT: [[ISZERO:%.*]] = call i1 @llvm.experimental.constrained.fcmp.f64(double [[TMP0]], double 0.000000e+00, metadata !"oeq", metadata !"fpexcept.strict") #[[ATTR5]] // CHECK-NEXT: br i1 [[ISZERO]], label [[FPCLASSIFY_END:%.*]], label [[FPCLASSIFY_NOT_ZERO:%.*]] // CHECK: fpclassify_end: // CHECK-NEXT: [[FPCLASSIFY_RESULT:%.*]] = phi i32 [ 4, [[ENTRY:%.*]] ], [ 0, [[FPCLASSIFY_NOT_ZERO]] ], [ 1, [[FPCLASSIFY_NOT_NAN:%.*]] ], [ [[TMP2:%.*]], [[FPCLASSIFY_NOT_INF:%.*]] ] -// CHECK-NEXT: call void @p(i8* getelementptr inbounds ([29 x i8], [29 x i8]* @.str.1, i64 0, i64 0), i32 [[FPCLASSIFY_RESULT]]) [[ATTR4]] +// CHECK-NEXT: call void @p(i8* getelementptr inbounds ([29 x i8], [29 x i8]* @.str.1, i64 0, i64 0), i32 [[FPCLASSIFY_RESULT]]) #[[ATTR5]] // CHECK-NEXT: ret void // CHECK: fpclassify_not_zero: -// CHECK-NEXT: [[CMP:%.*]] = call i1 @llvm.experimental.constrained.fcmp.f64(double [[TMP0]], double [[TMP0]], metadata !"uno", metadata !"fpexcept.strict") [[ATTR4]] +// CHECK-NEXT: [[CMP:%.*]] = call i1 @llvm.experimental.constrained.fcmp.f64(double [[TMP0]], double [[TMP0]], metadata !"uno", metadata !"fpexcept.strict") #[[ATTR5]] // CHECK-NEXT: br i1 [[CMP]], label [[FPCLASSIFY_END]], label [[FPCLASSIFY_NOT_NAN]] // CHECK: fpclassify_not_nan: -// CHECK-NEXT: [[TMP1:%.*]] = call double @llvm.fabs.f64(double [[TMP0]]) [[ATTR5:#.*]] -// CHECK-NEXT: [[ISINF:%.*]] = call i1 @llvm.experimental.constrained.fcmp.f64(double [[TMP1]], double 0x7FF0000000000000, metadata !"oeq", metadata !"fpexcept.strict") [[ATTR4]] +// CHECK-NEXT: [[TMP1:%.*]] = call double @llvm.fabs.f64(double [[TMP0]]) #[[ATTR6:[0-9]+]] +// CHECK-NEXT: [[ISINF:%.*]] = call i1 @llvm.experimental.constrained.fcmp.f64(double [[TMP1]], double 0x7FF0000000000000, metadata !"oeq", metadata !"fpexcept.strict") #[[ATTR5]] // CHECK-NEXT: br i1 [[ISINF]], label [[FPCLASSIFY_END]], label [[FPCLASSIFY_NOT_INF]] // CHECK: fpclassify_not_inf: -// CHECK-NEXT: [[ISNORMAL:%.*]] = call i1 @llvm.experimental.constrained.fcmp.f64(double [[TMP1]], double 0x10000000000000, metadata !"uge", metadata !"fpexcept.strict") [[ATTR4]] +// CHECK-NEXT: [[ISNORMAL:%.*]] = call i1 @llvm.experimental.constrained.fcmp.f64(double [[TMP1]], double 0x10000000000000, metadata !"uge", metadata !"fpexcept.strict") #[[ATTR5]] // CHECK-NEXT: [[TMP2]] = select i1 [[ISNORMAL]], i32 2, i32 3 // CHECK-NEXT: br label [[FPCLASSIFY_END]] // @@ -57,14 +57,14 @@ void test_fpclassify(double d) { // CHECK-LABEL: @test_fp16_isinf( // CHECK-NEXT: entry: -// CHECK-NEXT: [[LD_ADDR:%.*]] = alloca half, align 2 -// CHECK-NEXT: store half [[H:%.*]], half* [[LD_ADDR]], align 2 -// CHECK-NEXT: [[TMP0:%.*]] = load half, half* [[LD_ADDR]], align 2 -// CHECK-NEXT: [[BITCAST:%.*]] = bitcast half [[TMP0]] to i16 -// CHECK-NEXT: [[SHL1:%.*]] = shl i16 [[BITCAST]], 1 -// CHECK-NEXT: [[CMP:%.*]] = icmp eq i16 [[SHL1]], -2048 -// CHECK-NEXT: [[RES:%.*]] = zext i1 [[CMP]] to i32 -// CHECK-NEXT: call void @p(i8* getelementptr inbounds ([9 x i8], [9 x i8]* @.str.[[#STRID:2]], i64 0, i64 0), i32 [[RES]]) [[ATTR4]] +// CHECK-NEXT: [[H_ADDR:%.*]] = alloca half, align 2 +// CHECK-NEXT: store half [[H:%.*]], half* [[H_ADDR]], align 2 +// CHECK-NEXT: [[TMP0:%.*]] = load half, half* [[H_ADDR]], align 2 +// CHECK-NEXT: [[TMP1:%.*]] = bitcast half [[TMP0]] to i16 +// CHECK-NEXT: [[TMP2:%.*]] = shl i16 [[TMP1]], 1 +// CHECK-NEXT: [[TMP3:%.*]] = icmp eq i16 [[TMP2]], -2048 +// CHECK-NEXT: [[TMP4:%.*]] = zext i1 [[TMP3]] to i32 +// CHECK-NEXT: call void @p(i8* getelementptr inbounds ([9 x i8], [9 x i8]* @.str.2, i64 0, i64 0), i32 [[TMP4]]) #[[ATTR5]] // CHECK-NEXT: ret void // void test_fp16_isinf(__fp16 h) { @@ -75,14 +75,14 @@ void test_fp16_isinf(__fp16 h) { // CHECK-LABEL: @test_float_isinf( // CHECK-NEXT: entry: -// CHECK-NEXT: [[LD_ADDR:%.*]] = alloca float, align 4 -// CHECK-NEXT: store float [[F:%.*]], float* [[LD_ADDR]], align 4 -// CHECK-NEXT: [[TMP0:%.*]] = load float, float* [[LD_ADDR]], align 4 -// CHECK-NEXT: [[BITCAST:%.*]] = bitcast float [[TMP0]] to i32 -// CHECK-NEXT: [[SHL1:%.*]] = shl i32 [[BITCAST]], 1 -// CHECK-NEXT: [[CMP:%.*]] = icmp eq i32 [[SHL1]], -16777216 -// CHECK-NEXT: [[RES:%.*]] = zext i1 [[CMP]] to i32 -// CHECK-NEXT: call void @p(i8* getelementptr inbounds ([9 x i8], [9 x i8]* @.str.[[#STRID:STRID+1]], i64 0, i64 0), i32 [[RES]]) [[ATTR4]] +// CHECK-NEXT: [[F_ADDR:%.*]] = alloca float, align 4 +// CHECK-NEXT: store float [[F:%.*]], float* [[F_ADDR]], align 4 +// CHECK-NEXT: [[TMP0:%.*]] = load float, float* [[F_ADDR]], align 4 +// CHECK-NEXT: [[TMP1:%.*]] = bitcast float [[TMP0]] to i32 +// CHECK-NEXT: [[TMP2:%.*]] = shl i32 [[TMP1]], 1 +// CHECK-NEXT: [[TMP3:%.*]] = icmp eq i32 [[TMP2]], -16777216 +// CHECK-NEXT: [[TMP4:%.*]] = zext i1 [[TMP3]] to i32 +// CHECK-NEXT: call void @p(i8* getelementptr inbounds ([9 x i8], [9 x i8]* @.str.3, i64 0, i64 0), i32 [[TMP4]]) #[[ATTR5]] // CHECK-NEXT: ret void // void test_float_isinf(float f) { @@ -93,14 +93,14 @@ void test_float_isinf(float f) { // CHECK-LABEL: @test_double_isinf( // CHECK-NEXT: entry: -// CHECK-NEXT: [[LD_ADDR:%.*]] = alloca double, align 8 -// CHECK-NEXT: store double [[D:%.*]], double* [[LD_ADDR]], align 8 -// CHECK-NEXT: [[TMP0:%.*]] = load double, double* [[LD_ADDR]], align 8 -// CHECK-NEXT: [[BITCAST:%.*]] = bitcast double [[TMP0]] to i64 -// CHECK-NEXT: [[SHL1:%.*]] = shl i64 [[BITCAST]], 1 -// CHECK-NEXT: [[CMP:%.*]] = icmp eq i64 [[SHL1]], -9007199254740992 -// CHECK-NEXT: [[RES:%.*]] = zext i1 [[CMP]] to i32 -// CHECK-NEXT: call void @p(i8* getelementptr inbounds ([9 x i8], [9 x i8]* @.str.[[#STRID:STRID+1]], i64 0, i64 0), i32 [[RES]]) [[ATTR4]] +// CHECK-NEXT: [[D_ADDR:%.*]] = alloca double, align 8 +// CHECK-NEXT: store double [[D:%.*]], double* [[D_ADDR]], align 8 +// CHECK-NEXT: [[TMP0:%.*]] = load double, double* [[D_ADDR]], align 8 +// CHECK-NEXT: [[TMP1:%.*]] = bitcast double [[TMP0]] to i64 +// CHECK-NEXT: [[TMP2:%.*]] = shl i64 [[TMP1]], 1 +// CHECK-NEXT: [[TMP3:%.*]] = icmp eq i64 [[TMP2]], -9007199254740992 +// CHECK-NEXT: [[TMP4:%.*]] = zext i1 [[TMP3]] to i32 +// CHECK-NEXT: call void @p(i8* getelementptr inbounds ([9 x i8], [9 x i8]* @.str.4, i64 0, i64 0), i32 [[TMP4]]) #[[ATTR5]] // CHECK-NEXT: ret void // void test_double_isinf(double d) { @@ -111,14 +111,14 @@ void test_double_isinf(double d) { // CHECK-LABEL: @test_fp16_isfinite( // CHECK-NEXT: entry: -// CHECK-NEXT: [[LD_ADDR:%.*]] = alloca half, align 2 -// CHECK-NEXT: store half [[H:%.*]], half* [[LD_ADDR]], align 2 -// CHECK-NEXT: [[TMP0:%.*]] = load half, half* [[LD_ADDR]], align 2 -// CHECK-NEXT: [[BITCAST:%.*]] = bitcast half [[TMP0]] to i16 -// CHECK-NEXT: [[SHL1:%.*]] = shl i16 [[BITCAST]], 1 -// CHECK-NEXT: [[CMP:%.*]] = icmp ult i16 [[SHL1]], -2048 -// CHECK-NEXT: [[RES:%.*]] = zext i1 [[CMP]] to i32 -// CHECK-NEXT: call void @p(i8* getelementptr inbounds ([12 x i8], [12 x i8]* @.str.[[#STRID:STRID+1]], i64 0, i64 0), i32 [[RES]]) [[ATTR4]] +// CHECK-NEXT: [[H_ADDR:%.*]] = alloca half, align 2 +// CHECK-NEXT: store half [[H:%.*]], half* [[H_ADDR]], align 2 +// CHECK-NEXT: [[TMP0:%.*]] = load half, half* [[H_ADDR]], align 2 +// CHECK-NEXT: [[TMP1:%.*]] = bitcast half [[TMP0]] to i16 +// CHECK-NEXT: [[TMP2:%.*]] = shl i16 [[TMP1]], 1 +// CHECK-NEXT: [[TMP3:%.*]] = icmp ult i16 [[TMP2]], -2048 +// CHECK-NEXT: [[TMP4:%.*]] = zext i1 [[TMP3]] to i32 +// CHECK-NEXT: call void @p(i8* getelementptr inbounds ([12 x i8], [12 x i8]* @.str.5, i64 0, i64 0), i32 [[TMP4]]) #[[ATTR5]] // CHECK-NEXT: ret void // void test_fp16_isfinite(__fp16 h) { @@ -129,14 +129,14 @@ void test_fp16_isfinite(__fp16 h) { // CHECK-LABEL: @test_float_isfinite( // CHECK-NEXT: entry: -// CHECK-NEXT: [[LD_ADDR:%.*]] = alloca float, align 4 -// CHECK-NEXT: store float [[F:%.*]], float* [[LD_ADDR]], align 4 -// CHECK-NEXT: [[TMP0:%.*]] = load float, float* [[LD_ADDR]], align 4 -// CHECK-NEXT: [[BITCAST:%.*]] = bitcast float [[TMP0]] to i32 -// CHECK-NEXT: [[SHL1:%.*]] = shl i32 [[BITCAST]], 1 -// CHECK-NEXT: [[CMP:%.*]] = icmp ult i32 [[SHL1]], -16777216 -// CHECK-NEXT: [[RES:%.*]] = zext i1 [[CMP]] to i32 -// CHECK-NEXT: call void @p(i8* getelementptr inbounds ([12 x i8], [12 x i8]* @.str.[[#STRID:STRID+1]], i64 0, i64 0), i32 [[RES]]) [[ATTR4]] +// CHECK-NEXT: [[F_ADDR:%.*]] = alloca float, align 4 +// CHECK-NEXT: store float [[F:%.*]], float* [[F_ADDR]], align 4 +// CHECK-NEXT: [[TMP0:%.*]] = load float, float* [[F_ADDR]], align 4 +// CHECK-NEXT: [[TMP1:%.*]] = bitcast float [[TMP0]] to i32 +// CHECK-NEXT: [[TMP2:%.*]] = shl i32 [[TMP1]], 1 +// CHECK-NEXT: [[TMP3:%.*]] = icmp ult i32 [[TMP2]], -16777216 +// CHECK-NEXT: [[TMP4:%.*]] = zext i1 [[TMP3]] to i32 +// CHECK-NEXT: call void @p(i8* getelementptr inbounds ([12 x i8], [12 x i8]* @.str.6, i64 0, i64 0), i32 [[TMP4]]) #[[ATTR5]] // CHECK-NEXT: ret void // void test_float_isfinite(float f) { @@ -147,14 +147,14 @@ void test_float_isfinite(float f) { // CHECK-LABEL: @test_double_isfinite( // CHECK-NEXT: entry: -// CHECK-NEXT: [[LD_ADDR:%.*]] = alloca double, align 8 -// CHECK-NEXT: store double [[D:%.*]], double* [[LD_ADDR]], align 8 -// CHECK-NEXT: [[TMP0:%.*]] = load double, double* [[LD_ADDR]], align 8 -// CHECK-NEXT: [[BITCAST:%.*]] = bitcast double [[TMP0]] to i64 -// CHECK-NEXT: [[SHL1:%.*]] = shl i64 [[BITCAST]], 1 -// CHECK-NEXT: [[CMP:%.*]] = icmp ult i64 [[SHL1]], -9007199254740992 -// CHECK-NEXT: [[RES:%.*]] = zext i1 [[CMP]] to i32 -// CHECK-NEXT: call void @p(i8* getelementptr inbounds ([12 x i8], [12 x i8]* @.str.[[#STRID:STRID+1]], i64 0, i64 0), i32 [[RES]]) [[ATTR4]] +// CHECK-NEXT: [[D_ADDR:%.*]] = alloca double, align 8 +// CHECK-NEXT: store double [[D:%.*]], double* [[D_ADDR]], align 8 +// CHECK-NEXT: [[TMP0:%.*]] = load double, double* [[D_ADDR]], align 8 +// CHECK-NEXT: [[TMP1:%.*]] = bitcast double [[TMP0]] to i64 +// CHECK-NEXT: [[TMP2:%.*]] = shl i64 [[TMP1]], 1 +// CHECK-NEXT: [[TMP3:%.*]] = icmp ult i64 [[TMP2]], -9007199254740992 +// CHECK-NEXT: [[TMP4:%.*]] = zext i1 [[TMP3]] to i32 +// CHECK-NEXT: call void @p(i8* getelementptr inbounds ([12 x i8], [12 x i8]* @.str.7, i64 0, i64 0), i32 [[TMP4]]) #[[ATTR5]] // CHECK-NEXT: ret void // void test_double_isfinite(double d) { @@ -168,13 +168,13 @@ void test_double_isfinite(double d) { // CHECK-NEXT: [[D_ADDR:%.*]] = alloca double, align 8 // CHECK-NEXT: store double [[D:%.*]], double* [[D_ADDR]], align 8 // CHECK-NEXT: [[TMP0:%.*]] = load double, double* [[D_ADDR]], align 8 -// CHECK-NEXT: [[TMP1:%.*]] = call double @llvm.fabs.f64(double [[TMP0]]) [[ATTR5]] -// CHECK-NEXT: [[ISINF:%.*]] = call i1 @llvm.experimental.constrained.fcmp.f64(double [[TMP1]], double 0x7FF0000000000000, metadata !"oeq", metadata !"fpexcept.strict") [[ATTR4]] +// CHECK-NEXT: [[TMP1:%.*]] = call double @llvm.fabs.f64(double [[TMP0]]) #[[ATTR6]] +// CHECK-NEXT: [[ISINF:%.*]] = call i1 @llvm.experimental.constrained.fcmp.f64(double [[TMP1]], double 0x7FF0000000000000, metadata !"oeq", metadata !"fpexcept.strict") #[[ATTR5]] // CHECK-NEXT: [[TMP2:%.*]] = bitcast double [[TMP0]] to i64 // CHECK-NEXT: [[TMP3:%.*]] = icmp slt i64 [[TMP2]], 0 // CHECK-NEXT: [[TMP4:%.*]] = select i1 [[TMP3]], i32 -1, i32 1 // CHECK-NEXT: [[TMP5:%.*]] = select i1 [[ISINF]], i32 [[TMP4]], i32 0 -// CHECK-NEXT: call void @p(i8* getelementptr inbounds ([14 x i8], [14 x i8]* @.str.[[#STRID:STRID+1]], i64 0, i64 0), i32 [[TMP5]]) [[ATTR4]] +// CHECK-NEXT: call void @p(i8* getelementptr inbounds ([14 x i8], [14 x i8]* @.str.8, i64 0, i64 0), i32 [[TMP5]]) #[[ATTR5]] // CHECK-NEXT: ret void // void test_isinf_sign(double d) { @@ -188,12 +188,9 @@ void test_isinf_sign(double d) { // CHECK-NEXT: [[H_ADDR:%.*]] = alloca half, align 2 // CHECK-NEXT: store half [[H:%.*]], half* [[H_ADDR]], align 2 // CHECK-NEXT: [[TMP0:%.*]] = load half, half* [[H_ADDR]], align 2 -// CHECK-NEXT: [[BITCAST:%.*]] = bitcast half [[TMP0]] to i16 -// CHECK-NEXT: [[ABS:%.*]] = and i16 [[BITCAST]], [[#%u,0x7FFF]] -// CHECK-NEXT: [[TMP1:%.*]] = sub i16 [[#%u,0x7C00]], [[ABS]] -// CHECK-NEXT: [[ISNAN:%.*]] = lshr i16 [[TMP1]], 15 -// CHECK-NEXT: [[RES:%.*]] = zext i16 [[ISNAN]] to i32 -// CHECK-NEXT: call void @p(i8* getelementptr inbounds ([9 x i8], [9 x i8]* @.str.[[#STRID:STRID+1]], i64 0, i64 0), i32 [[RES]]) [[ATTR4]] +// CHECK-NEXT: [[TMP1:%.*]] = call i1 @llvm.isnan.f16(half [[TMP0]]) #[[ATTR5]] +// CHECK-NEXT: [[TMP2:%.*]] = zext i1 [[TMP1]] to i32 +// CHECK-NEXT: call void @p(i8* getelementptr inbounds ([9 x i8], [9 x i8]* @.str.9, i64 0, i64 0), i32 [[TMP2]]) #[[ATTR5]] // CHECK-NEXT: ret void // void test_fp16_isnan(__fp16 h) { @@ -207,11 +204,9 @@ void test_fp16_isnan(__fp16 h) { // CHECK-NEXT: [[F_ADDR:%.*]] = alloca float, align 4 // CHECK-NEXT: store float [[F:%.*]], float* [[F_ADDR]], align 4 // CHECK-NEXT: [[TMP0:%.*]] = load float, float* [[F_ADDR]], align 4 -// CHECK-NEXT: [[BITCAST:%.*]] = bitcast float [[TMP0]] to i32 -// CHECK-NEXT: [[ABS:%.*]] = and i32 [[BITCAST]], [[#%u,0x7FFFFFFF]] -// CHECK-NEXT: [[TMP1:%.*]] = sub i32 [[#%u,0x7F800000]], [[ABS]] -// CHECK-NEXT: [[ISNAN:%.*]] = lshr i32 [[TMP1]], 31 -// CHECK-NEXT: call void @p(i8* getelementptr inbounds ([9 x i8], [9 x i8]* @.str.[[#STRID:STRID+1]], i64 0, i64 0), i32 [[ISNAN]]) [[ATTR4]] +// CHECK-NEXT: [[TMP1:%.*]] = call i1 @llvm.isnan.f32(float [[TMP0]]) #[[ATTR5]] +// CHECK-NEXT: [[TMP2:%.*]] = zext i1 [[TMP1]] to i32 +// CHECK-NEXT: call void @p(i8* getelementptr inbounds ([9 x i8], [9 x i8]* @.str.10, i64 0, i64 0), i32 [[TMP2]]) #[[ATTR5]] // CHECK-NEXT: ret void // void test_float_isnan(float f) { @@ -225,12 +220,9 @@ void test_float_isnan(float f) { // CHECK-NEXT: [[D_ADDR:%.*]] = alloca double, align 8 // CHECK-NEXT: store double [[D:%.*]], double* [[D_ADDR]], align 8 // CHECK-NEXT: [[TMP0:%.*]] = load double, double* [[D_ADDR]], align 8 -// CHECK-NEXT: [[BITCAST:%.*]] = bitcast double [[TMP0]] to i64 -// CHECK-NEXT: [[ABS:%.*]] = and i64 [[BITCAST]], [[#%u,0x7FFFFFFFFFFFFFFF]] -// CHECK-NEXT: [[TMP1:%.*]] = sub i64 [[#%u,0x7FF0000000000000]], [[ABS]] -// CHECK-NEXT: [[ISNAN:%.*]] = lshr i64 [[TMP1]], 63 -// CHECK-NEXT: [[RES:%.*]] = trunc i64 [[ISNAN]] to i32 -// CHECK-NEXT: call void @p(i8* getelementptr inbounds ([9 x i8], [9 x i8]* @.str.[[#STRID:STRID+1]], i64 0, i64 0), i32 [[RES]]) [[ATTR4]] +// CHECK-NEXT: [[TMP1:%.*]] = call i1 @llvm.isnan.f64(double [[TMP0]]) #[[ATTR5]] +// CHECK-NEXT: [[TMP2:%.*]] = zext i1 [[TMP1]] to i32 +// CHECK-NEXT: call void @p(i8* getelementptr inbounds ([9 x i8], [9 x i8]* @.str.11, i64 0, i64 0), i32 [[TMP2]]) #[[ATTR5]] // CHECK-NEXT: ret void // void test_double_isnan(double d) { @@ -244,14 +236,14 @@ void test_double_isnan(double d) { // CHECK-NEXT: [[D_ADDR:%.*]] = alloca double, align 8 // CHECK-NEXT: store double [[D:%.*]], double* [[D_ADDR]], align 8 // CHECK-NEXT: [[TMP0:%.*]] = load double, double* [[D_ADDR]], align 8 -// CHECK-NEXT: [[ISEQ:%.*]] = call i1 @llvm.experimental.constrained.fcmp.f64(double [[TMP0]], double [[TMP0]], metadata !"oeq", metadata !"fpexcept.strict") [[ATTR4]] -// CHECK-NEXT: [[TMP1:%.*]] = call double @llvm.fabs.f64(double [[TMP0]]) [[ATTR5]] -// CHECK-NEXT: [[ISINF:%.*]] = call i1 @llvm.experimental.constrained.fcmp.f64(double [[TMP1]], double 0x7FF0000000000000, metadata !"ult", metadata !"fpexcept.strict") [[ATTR4]] -// CHECK-NEXT: [[ISNORMAL:%.*]] = call i1 @llvm.experimental.constrained.fcmp.f64(double [[TMP1]], double 0x10000000000000, metadata !"uge", metadata !"fpexcept.strict") [[ATTR4]] +// CHECK-NEXT: [[ISEQ:%.*]] = call i1 @llvm.experimental.constrained.fcmp.f64(double [[TMP0]], double [[TMP0]], metadata !"oeq", metadata !"fpexcept.strict") #[[ATTR5]] +// CHECK-NEXT: [[TMP1:%.*]] = call double @llvm.fabs.f64(double [[TMP0]]) #[[ATTR6]] +// CHECK-NEXT: [[ISINF:%.*]] = call i1 @llvm.experimental.constrained.fcmp.f64(double [[TMP1]], double 0x7FF0000000000000, metadata !"ult", metadata !"fpexcept.strict") #[[ATTR5]] +// CHECK-NEXT: [[ISNORMAL:%.*]] = call i1 @llvm.experimental.constrained.fcmp.f64(double [[TMP1]], double 0x10000000000000, metadata !"uge", metadata !"fpexcept.strict") #[[ATTR5]] // CHECK-NEXT: [[AND:%.*]] = and i1 [[ISEQ]], [[ISINF]] // CHECK-NEXT: [[AND1:%.*]] = and i1 [[AND]], [[ISNORMAL]] // CHECK-NEXT: [[TMP2:%.*]] = zext i1 [[AND1]] to i32 -// CHECK-NEXT: call void @p(i8* getelementptr inbounds ([12 x i8], [12 x i8]* @.str.[[#STRID:STRID+1]], i64 0, i64 0), i32 [[TMP2]]) [[ATTR4]] +// CHECK-NEXT: call void @p(i8* getelementptr inbounds ([12 x i8], [12 x i8]* @.str.12, i64 0, i64 0), i32 [[TMP2]]) #[[ATTR5]] // CHECK-NEXT: ret void // void test_isnormal(double d) { diff --git a/llvm/docs/LangRef.rst b/llvm/docs/LangRef.rst index d91464a..e3b1f46 100644 --- a/llvm/docs/LangRef.rst +++ b/llvm/docs/LangRef.rst @@ -20985,6 +20985,52 @@ return any value and uses platform-independent representation of IEEE rounding modes. +Floating Point Test Intrinsics +------------------------------ + +These functions get properties of floating point values. + + +'``llvm.isnan``' Intrinsic +^^^^^^^^^^^^^^^^^^^^^^^^^^ + +Syntax: +""""""" + +:: + + declare i1 @llvm.isnan( ) + declare @llvm.isnan( ) + +Overview: +""""""""" + +The '``llvm.isnan``' intrinsic returns a boolean value or vector of boolean +values depending on whether the value is NaN. + +If the operand is a floating-point scalar, then the result type is a +boolean (:ref:`i1 `). + +If the operand is a floating-point vector, then the result type is a +vector of boolean with the same number of elements as the operand. + +Arguments: +"""""""""" + +The argument to the '``llvm.isnan``' intrinsic must be +:ref:`floating-point ` or :ref:`vector ` +of floating-point values. + + +Semantics: +"""""""""" + +The function tests if ``op`` is NaN. If ``op`` is a vector, then the +check is made element by element. Each test yields an :ref:`i1 ` +result, which is ``true``, if the value is NaN. The function never raises +floating point exceptions. + + General Intrinsics ------------------ diff --git a/llvm/include/llvm/CodeGen/ISDOpcodes.h b/llvm/include/llvm/CodeGen/ISDOpcodes.h index 6803f4d..c1368e0 100644 --- a/llvm/include/llvm/CodeGen/ISDOpcodes.h +++ b/llvm/include/llvm/CodeGen/ISDOpcodes.h @@ -482,6 +482,10 @@ enum NodeType { /// Returns platform specific canonical encoding of a floating point number. FCANONICALIZE, + /// Performs check of floating point number property, defined by IEEE-754. The + /// only operand is the floating point value to check. Returns boolean value. + ISNAN, + /// BUILD_VECTOR(ELT0, ELT1, ELT2, ELT3,...) - Return a fixed-width vector /// with the specified, possibly variable, elements. The types of the /// operands must match the vector element type, except that integer types diff --git a/llvm/include/llvm/CodeGen/TargetLowering.h b/llvm/include/llvm/CodeGen/TargetLowering.h index 69508d8..5506d33 100644 --- a/llvm/include/llvm/CodeGen/TargetLowering.h +++ b/llvm/include/llvm/CodeGen/TargetLowering.h @@ -4424,6 +4424,10 @@ public: /// \returns The expansion result SDValue expandFP_TO_INT_SAT(SDNode *N, SelectionDAG &DAG) const; + /// Expand isnan depending on function attributes. + SDValue expandISNAN(EVT ResultVT, SDValue Op, SDNodeFlags Flags, + const SDLoc &DL, SelectionDAG &DAG) const; + /// Expand CTPOP nodes. Expands vector/scalar CTPOP nodes, /// vector nodes can only succeed if all operations are legal/custom. /// \param N Node to expand diff --git a/llvm/include/llvm/IR/Intrinsics.td b/llvm/include/llvm/IR/Intrinsics.td index 28fcc13..6b4599c 100644 --- a/llvm/include/llvm/IR/Intrinsics.td +++ b/llvm/include/llvm/IR/Intrinsics.td @@ -715,6 +715,14 @@ let IntrProperties = [IntrInaccessibleMemOnly, IntrWillReturn] in { def int_set_rounding : DefaultAttrsIntrinsic<[], [llvm_i32_ty]>; } +//===--------------- Floating Point Test Intrinsics -----------------------===// +// + +def int_isnan + : DefaultAttrsIntrinsic<[LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>], + [llvm_anyfloat_ty], + [IntrNoMem, IntrWillReturn]>; + //===--------------- Constrained Floating Point Intrinsics ----------------===// // diff --git a/llvm/lib/Analysis/ConstantFolding.cpp b/llvm/lib/Analysis/ConstantFolding.cpp index b28a0d6..4a943a1 100644 --- a/llvm/lib/Analysis/ConstantFolding.cpp +++ b/llvm/lib/Analysis/ConstantFolding.cpp @@ -1579,9 +1579,10 @@ bool llvm::canConstantFoldCallTo(const CallBase *Call, const Function *F) { return !Call->isStrictFP(); // Sign operations are actually bitwise operations, they do not raise - // exceptions even for SNANs. + // exceptions even for SNANs. The same applies to classification functions. case Intrinsic::fabs: case Intrinsic::copysign: + case Intrinsic::isnan: // Non-constrained variants of rounding operations means default FP // environment, they can be folded in any case. case Intrinsic::ceil: @@ -2002,6 +2003,9 @@ static Constant *ConstantFoldScalarCall1(StringRef Name, return ConstantInt::get(Ty, Int); } + if (IntrinsicID == Intrinsic::isnan) + return ConstantInt::get(Ty, U.isNaN()); + if (!Ty->isHalfTy() && !Ty->isFloatTy() && !Ty->isDoubleTy()) return nullptr; diff --git a/llvm/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp b/llvm/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp index 2732c96..df473a0 100644 --- a/llvm/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp +++ b/llvm/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp @@ -1185,6 +1185,10 @@ void SelectionDAGLegalize::LegalizeOp(SDNode *Node) { Action = TLI.getOperationAction( Node->getOpcode(), Node->getOperand(1).getValueType()); break; + case ISD::ISNAN: + Action = TLI.getOperationAction(Node->getOpcode(), + Node->getOperand(0).getValueType()); + break; default: if (Node->getOpcode() >= ISD::BUILTIN_OP_END) { Action = TargetLowering::Legal; @@ -3108,6 +3112,12 @@ bool SelectionDAGLegalize::ExpandNode(SDNode *Node) { case ISD::FCOPYSIGN: Results.push_back(ExpandFCOPYSIGN(Node)); break; + case ISD::ISNAN: + if (SDValue Expanded = + TLI.expandISNAN(Node->getValueType(0), Node->getOperand(0), + Node->getFlags(), SDLoc(Node), DAG)) + Results.push_back(Expanded); + break; case ISD::FNEG: Results.push_back(ExpandFNEG(Node)); break; diff --git a/llvm/lib/CodeGen/SelectionDAG/LegalizeIntegerTypes.cpp b/llvm/lib/CodeGen/SelectionDAG/LegalizeIntegerTypes.cpp index b8a3dd0..40d6e01 100644 --- a/llvm/lib/CodeGen/SelectionDAG/LegalizeIntegerTypes.cpp +++ b/llvm/lib/CodeGen/SelectionDAG/LegalizeIntegerTypes.cpp @@ -139,6 +139,8 @@ void DAGTypeLegalizer::PromoteIntegerResult(SDNode *N, unsigned ResNo) { case ISD::FLT_ROUNDS_: Res = PromoteIntRes_FLT_ROUNDS(N); break; + case ISD::ISNAN: Res = PromoteIntRes_ISNAN(N); break; + case ISD::AND: case ISD::OR: case ISD::XOR: @@ -656,6 +658,14 @@ SDValue DAGTypeLegalizer::PromoteIntRes_FLT_ROUNDS(SDNode *N) { return Res; } +SDValue DAGTypeLegalizer::PromoteIntRes_ISNAN(SDNode *N) { + SDLoc DL(N); + EVT ResultVT = N->getValueType(0); + EVT NewResultVT = TLI.getTypeToTransformTo(*DAG.getContext(), ResultVT); + return DAG.getNode(N->getOpcode(), DL, NewResultVT, N->getOperand(0), + N->getFlags()); +} + SDValue DAGTypeLegalizer::PromoteIntRes_INT_EXTEND(SDNode *N) { EVT NVT = TLI.getTypeToTransformTo(*DAG.getContext(), N->getValueType(0)); SDLoc dl(N); diff --git a/llvm/lib/CodeGen/SelectionDAG/LegalizeTypes.h b/llvm/lib/CodeGen/SelectionDAG/LegalizeTypes.h index 8d17d8f..bfd3927 100644 --- a/llvm/lib/CodeGen/SelectionDAG/LegalizeTypes.h +++ b/llvm/lib/CodeGen/SelectionDAG/LegalizeTypes.h @@ -352,6 +352,7 @@ private: SDValue PromoteIntRes_MULFIX(SDNode *N); SDValue PromoteIntRes_DIVFIX(SDNode *N); SDValue PromoteIntRes_FLT_ROUNDS(SDNode *N); + SDValue PromoteIntRes_ISNAN(SDNode *N); SDValue PromoteIntRes_VECREDUCE(SDNode *N); SDValue PromoteIntRes_ABS(SDNode *N); SDValue PromoteIntRes_Rotate(SDNode *N); @@ -775,6 +776,7 @@ private: SDValue ScalarizeVecRes_UNDEF(SDNode *N); SDValue ScalarizeVecRes_VECTOR_SHUFFLE(SDNode *N); SDValue ScalarizeVecRes_FP_TO_XINT_SAT(SDNode *N); + SDValue ScalarizeVecRes_ISNAN(SDNode *N); SDValue ScalarizeVecRes_FIX(SDNode *N); @@ -835,6 +837,7 @@ private: void SplitVecRes_INSERT_SUBVECTOR(SDNode *N, SDValue &Lo, SDValue &Hi); void SplitVecRes_FPOWI(SDNode *N, SDValue &Lo, SDValue &Hi); void SplitVecRes_FCOPYSIGN(SDNode *N, SDValue &Lo, SDValue &Hi); + void SplitVecRes_ISNAN(SDNode *N, SDValue &Lo, SDValue &Hi); void SplitVecRes_INSERT_VECTOR_ELT(SDNode *N, SDValue &Lo, SDValue &Hi); void SplitVecRes_LOAD(LoadSDNode *LD, SDValue &Lo, SDValue &Hi); void SplitVecRes_MLOAD(MaskedLoadSDNode *MLD, SDValue &Lo, SDValue &Hi); @@ -944,6 +947,7 @@ private: SDValue WidenVecOp_Convert(SDNode *N); SDValue WidenVecOp_FP_TO_XINT_SAT(SDNode *N); SDValue WidenVecOp_FCOPYSIGN(SDNode *N); + SDValue WidenVecOp_ISNAN(SDNode *N); SDValue WidenVecOp_VECREDUCE(SDNode *N); SDValue WidenVecOp_VECREDUCE_SEQ(SDNode *N); diff --git a/llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp b/llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp index 91242bb..d3ebf6c 100644 --- a/llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp +++ b/llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp @@ -64,6 +64,7 @@ void DAGTypeLegalizer::ScalarizeVectorResult(SDNode *N, unsigned ResNo) { case ISD::SETCC: R = ScalarizeVecRes_SETCC(N); break; case ISD::UNDEF: R = ScalarizeVecRes_UNDEF(N); break; case ISD::VECTOR_SHUFFLE: R = ScalarizeVecRes_VECTOR_SHUFFLE(N); break; + case ISD::ISNAN: R = ScalarizeVecRes_ISNAN(N); break; case ISD::ANY_EXTEND_VECTOR_INREG: case ISD::SIGN_EXTEND_VECTOR_INREG: case ISD::ZERO_EXTEND_VECTOR_INREG: @@ -582,6 +583,28 @@ SDValue DAGTypeLegalizer::ScalarizeVecRes_SETCC(SDNode *N) { return DAG.getNode(ExtendCode, DL, NVT, Res); } +SDValue DAGTypeLegalizer::ScalarizeVecRes_ISNAN(SDNode *N) { + SDLoc DL(N); + SDValue Arg = N->getOperand(0); + EVT ArgVT = Arg.getValueType(); + EVT ResultVT = N->getValueType(0).getVectorElementType(); + + // Handle case where result is scalarized but operand is not. + if (getTypeAction(ArgVT) == TargetLowering::TypeScalarizeVector) { + Arg = GetScalarizedVector(Arg); + } else { + EVT VT = ArgVT.getVectorElementType(); + Arg = DAG.getNode(ISD::EXTRACT_VECTOR_ELT, DL, VT, Arg, + DAG.getVectorIdxConstant(0, DL)); + } + + SDValue Res = DAG.getNode(ISD::ISNAN, DL, MVT::i1, Arg, N->getFlags()); + // Vectors may have a different boolean contents to scalars. Promote the + // value appropriately. + ISD::NodeType ExtendCode = + TargetLowering::getExtendForContent(TLI.getBooleanContents(ArgVT)); + return DAG.getNode(ExtendCode, DL, ResultVT, Res); +} //===----------------------------------------------------------------------===// // Operand Vector Scalarization <1 x ty> -> ty. @@ -924,6 +947,7 @@ void DAGTypeLegalizer::SplitVectorResult(SDNode *N, unsigned ResNo) { case ISD::INSERT_SUBVECTOR: SplitVecRes_INSERT_SUBVECTOR(N, Lo, Hi); break; case ISD::FPOWI: SplitVecRes_FPOWI(N, Lo, Hi); break; case ISD::FCOPYSIGN: SplitVecRes_FCOPYSIGN(N, Lo, Hi); break; + case ISD::ISNAN: SplitVecRes_ISNAN(N, Lo, Hi); break; case ISD::INSERT_VECTOR_ELT: SplitVecRes_INSERT_VECTOR_ELT(N, Lo, Hi); break; case ISD::SPLAT_VECTOR: case ISD::SCALAR_TO_VECTOR: @@ -1360,6 +1384,17 @@ void DAGTypeLegalizer::SplitVecRes_FCOPYSIGN(SDNode *N, SDValue &Lo, Hi = DAG.getNode(ISD::FCOPYSIGN, DL, LHSHi.getValueType(), LHSHi, RHSHi); } +void DAGTypeLegalizer::SplitVecRes_ISNAN(SDNode *N, SDValue &Lo, SDValue &Hi) { + SDLoc DL(N); + SDValue ArgLo, ArgHi; + GetSplitVector(N->getOperand(0), ArgLo, ArgHi); + EVT LoVT, HiVT; + std::tie(LoVT, HiVT) = DAG.GetSplitDestVTs(N->getValueType(0)); + + Lo = DAG.getNode(ISD::ISNAN, DL, LoVT, ArgLo, N->getFlags()); + Hi = DAG.getNode(ISD::ISNAN, DL, HiVT, ArgHi, N->getFlags()); +} + void DAGTypeLegalizer::SplitVecRes_InregOp(SDNode *N, SDValue &Lo, SDValue &Hi) { SDValue LHSLo, LHSHi; @@ -4547,6 +4582,7 @@ bool DAGTypeLegalizer::WidenVectorOperand(SDNode *N, unsigned OpNo) { case ISD::STRICT_FSETCCS: Res = WidenVecOp_STRICT_FSETCC(N); break; case ISD::VSELECT: Res = WidenVecOp_VSELECT(N); break; case ISD::FCOPYSIGN: Res = WidenVecOp_FCOPYSIGN(N); break; + case ISD::ISNAN: Res = WidenVecOp_ISNAN(N); break; case ISD::ANY_EXTEND: case ISD::SIGN_EXTEND: @@ -4682,6 +4718,33 @@ SDValue DAGTypeLegalizer::WidenVecOp_FCOPYSIGN(SDNode *N) { return DAG.UnrollVectorOp(N); } +SDValue DAGTypeLegalizer::WidenVecOp_ISNAN(SDNode *N) { + SDLoc DL(N); + EVT ResultVT = N->getValueType(0); + SDValue WideArg = GetWidenedVector(N->getOperand(0)); + + // Process this node similarly to SETCC. + EVT WideResultVT = getSetCCResultType(WideArg.getValueType()); + if (ResultVT.getScalarType() == MVT::i1) + WideResultVT = EVT::getVectorVT(*DAG.getContext(), MVT::i1, + WideResultVT.getVectorNumElements()); + + SDValue WideNode = + DAG.getNode(ISD::ISNAN, DL, WideResultVT, WideArg, N->getFlags()); + + // Extract the needed results from the result vector. + EVT ResVT = + EVT::getVectorVT(*DAG.getContext(), WideResultVT.getVectorElementType(), + ResultVT.getVectorNumElements()); + SDValue CC = DAG.getNode(ISD::EXTRACT_SUBVECTOR, DL, ResVT, WideNode, + DAG.getVectorIdxConstant(0, DL)); + + EVT OpVT = N->getOperand(0).getValueType(); + ISD::NodeType ExtendCode = + TargetLowering::getExtendForContent(TLI.getBooleanContents(OpVT)); + return DAG.getNode(ExtendCode, DL, ResultVT, CC); +} + SDValue DAGTypeLegalizer::WidenVecOp_Convert(SDNode *N) { // Since the result is legal and the input is illegal. EVT VT = N->getValueType(0); diff --git a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp index be00ec1..e0e4eed 100644 --- a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp +++ b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp @@ -6408,6 +6408,30 @@ void SelectionDAGBuilder::visitIntrinsicCall(const CallInst &I, DAG.setRoot(DAG.getNode(ISD::PCMARKER, sdl, MVT::Other, getRoot(), Tmp)); return; } + case Intrinsic::isnan: { + const DataLayout DLayout = DAG.getDataLayout(); + EVT DestVT = TLI.getValueType(DLayout, I.getType()); + EVT ArgVT = TLI.getValueType(DLayout, I.getArgOperand(0)->getType()); + MachineFunction &MF = DAG.getMachineFunction(); + const Function &F = MF.getFunction(); + SDValue Op = getValue(I.getArgOperand(0)); + SDNodeFlags Flags; + Flags.setNoFPExcept( + !F.getAttributes().hasFnAttribute(llvm::Attribute::StrictFP)); + + // If ISD::ISNAN should be expanded, do it right now, because the expansion + // can use illegal types. Making expansion early allows to legalize these + // types prior to selection. + if (!TLI.isOperationLegalOrCustom(ISD::ISNAN, ArgVT)) { + SDValue Result = TLI.expandISNAN(DestVT, Op, Flags, sdl, DAG); + setValue(&I, Result); + return; + } + + SDValue V = DAG.getNode(ISD::ISNAN, sdl, DestVT, Op, Flags); + setValue(&I, V); + return; + } case Intrinsic::readcyclecounter: { SDValue Op = getRoot(); Res = DAG.getNode(ISD::READCYCLECOUNTER, sdl, diff --git a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGDumper.cpp b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGDumper.cpp index 77e9e53..4395b975 100644 --- a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGDumper.cpp +++ b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGDumper.cpp @@ -267,6 +267,7 @@ std::string SDNode::getOperationName(const SelectionDAG *G) const { case ISD::FCOPYSIGN: return "fcopysign"; case ISD::FGETSIGN: return "fgetsign"; case ISD::FCANONICALIZE: return "fcanonicalize"; + case ISD::ISNAN: return "isnan"; case ISD::FPOW: return "fpow"; case ISD::STRICT_FPOW: return "strict_fpow"; case ISD::SMIN: return "smin"; diff --git a/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp b/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp index 5e17869..52e81f2 100644 --- a/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp +++ b/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp @@ -6970,6 +6970,35 @@ SDValue TargetLowering::expandFMINNUM_FMAXNUM(SDNode *Node, return SDValue(); } +SDValue TargetLowering::expandISNAN(EVT ResultVT, SDValue Op, SDNodeFlags Flags, + const SDLoc &DL, SelectionDAG &DAG) const { + EVT OperandVT = Op.getValueType(); + assert(OperandVT.isFloatingPoint()); + + // If floating point exceptions are ignored, expand to unordered comparison. + if (Flags.hasNoFPExcept() && + isOperationLegalOrCustom(ISD::SETCC, OperandVT.getScalarType())) + return DAG.getSetCC(DL, ResultVT, Op, DAG.getConstantFP(0.0, DL, OperandVT), + ISD::SETUO); + + // In general case use integer operations to avoid traps if argument is SNaN. + + // NaN has all exp bits set and a non zero significand. Therefore: + // isnan(V) == exp mask < abs(V) + unsigned BitSize = OperandVT.getScalarSizeInBits(); + EVT IntVT = OperandVT.changeTypeToInteger(); + SDValue ArgV = DAG.getBitcast(IntVT, Op); + APInt AndMask = APInt::getSignedMaxValue(BitSize); + SDValue AndMaskV = DAG.getConstant(AndMask, DL, IntVT); + SDValue AbsV = DAG.getNode(ISD::AND, DL, IntVT, ArgV, AndMaskV); + EVT ScalarFloatVT = OperandVT.getScalarType(); + const Type *FloatTy = ScalarFloatVT.getTypeForEVT(*DAG.getContext()); + const llvm::fltSemantics &Semantics = FloatTy->getFltSemantics(); + APInt ExpMask = APFloat::getInf(Semantics).bitcastToAPInt(); + SDValue ExpMaskV = DAG.getConstant(ExpMask, DL, IntVT); + return DAG.getSetCC(DL, ResultVT, ExpMaskV, AbsV, ISD::SETLT); +} + bool TargetLowering::expandCTPOP(SDNode *Node, SDValue &Result, SelectionDAG &DAG) const { SDLoc dl(Node); diff --git a/llvm/lib/CodeGen/TargetLoweringBase.cpp b/llvm/lib/CodeGen/TargetLoweringBase.cpp index cfbbba6..d11c6b0 100644 --- a/llvm/lib/CodeGen/TargetLoweringBase.cpp +++ b/llvm/lib/CodeGen/TargetLoweringBase.cpp @@ -761,6 +761,7 @@ void TargetLoweringBase::initActions() { // These operations default to expand. setOperationAction(ISD::FGETSIGN, VT, Expand); + setOperationAction(ISD::ISNAN, VT, Expand); setOperationAction(ISD::CONCAT_VECTORS, VT, Expand); setOperationAction(ISD::FMINNUM, VT, Expand); setOperationAction(ISD::FMAXNUM, VT, Expand); diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp index e1b13c7..2efd06c 100644 --- a/llvm/lib/Target/X86/X86ISelLowering.cpp +++ b/llvm/lib/Target/X86/X86ISelLowering.cpp @@ -704,6 +704,7 @@ X86TargetLowering::X86TargetLowering(const X86TargetMachine &TM, setOperationAction(ISD::LLROUND, MVT::f80, Expand); setOperationAction(ISD::LRINT, MVT::f80, Custom); setOperationAction(ISD::LLRINT, MVT::f80, Custom); + setOperationAction(ISD::ISNAN, MVT::f80, Custom); // Handle constrained floating-point operations of scalar. setOperationAction(ISD::STRICT_FADD , MVT::f80, Legal); @@ -22154,6 +22155,45 @@ static SDValue LowerFGETSIGN(SDValue Op, SelectionDAG &DAG) { return Res; } +static SDValue lowerISNAN(SDValue Op, SelectionDAG &DAG) { + SDLoc DL(Op); + SDValue Arg = Op.getOperand(0); + MVT ArgVT = Arg.getSimpleValueType(); + MVT ResultVT = Op.getSimpleValueType(); + + // Determine classification of argument using instruction FXAM. + unsigned Opc; + switch (ArgVT.SimpleTy) { + default: + llvm_unreachable("Unexpected type!"); + case MVT::f32: + Opc = X86::XAM_Fp32; + break; + case MVT::f64: + Opc = X86::XAM_Fp64; + break; + case MVT::f80: + Opc = X86::XAM_Fp80; + break; + } + SDValue Test(DAG.getMachineNode(Opc, DL, MVT::Glue, Arg), 0); + + // Move FPSW to AX. + SDValue FNSTSW = + SDValue(DAG.getMachineNode(X86::FNSTSW16r, DL, MVT::i16, Test), 0); + + // Extract upper 8-bits of AX. + SDValue Extract = + DAG.getTargetExtractSubreg(X86::sub_8bit_hi, DL, MVT::i8, FNSTSW); + + // Mask all bits but C3, C2, C0. + Extract = DAG.getNode(ISD::AND, DL, MVT::i8, Extract, + DAG.getConstant(0x45, DL, MVT::i8)); + + return DAG.getSetCC(DL, ResultVT, Extract, DAG.getConstant(1, DL, MVT::i8), + ISD::CondCode::SETEQ); +} + /// Helper for creating a X86ISD::SETCC node. static SDValue getSETCC(X86::CondCode Cond, SDValue EFLAGS, const SDLoc &dl, SelectionDAG &DAG) { @@ -30494,6 +30534,7 @@ SDValue X86TargetLowering::LowerOperation(SDValue Op, SelectionDAG &DAG) const { case ISD::FNEG: return LowerFABSorFNEG(Op, DAG); case ISD::FCOPYSIGN: return LowerFCOPYSIGN(Op, DAG); case ISD::FGETSIGN: return LowerFGETSIGN(Op, DAG); + case ISD::ISNAN: return lowerISNAN(Op, DAG); case ISD::LRINT: case ISD::LLRINT: return LowerLRINT_LLRINT(Op, DAG); case ISD::SETCC: diff --git a/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp b/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp index b3ade55..6742ac6 100644 --- a/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp +++ b/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp @@ -1468,6 +1468,18 @@ Instruction *InstCombinerImpl::visitCallInst(CallInst &CI) { break; } + case Intrinsic::isnan: { + Value *Arg = II->getArgOperand(0); + if (const auto *FPMO = dyn_cast(Arg)) { + // If argument of this intrinsic call is an instruction that has 'nnan' + // flag, we can assume that NaN cannot be produced, otherwise it is + // undefined behavior. + if (FPMO->getFastMathFlags().noNaNs()) + return replaceInstUsesWith( + *II, ConstantInt::get(II->getType(), APInt::getNullValue(1))); + } + break; + } case Intrinsic::copysign: { Value *Mag = II->getArgOperand(0), *Sign = II->getArgOperand(1); if (SignBitMustBeZero(Sign, &TLI)) { diff --git a/llvm/test/CodeGen/AArch64/aarch64-fpclass.ll b/llvm/test/CodeGen/AArch64/aarch64-fpclass.ll new file mode 100644 index 0000000..98a4b7b --- /dev/null +++ b/llvm/test/CodeGen/AArch64/aarch64-fpclass.ll @@ -0,0 +1,490 @@ +; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py +; RUN: llc < %s -mtriple=aarch64-none-linux-gnu -mattr=+bf16 | FileCheck %s -check-prefix=CHECK + +define i1 @isnan_half(half %x) nounwind { +; CHECK-LABEL: isnan_half: +; CHECK: // %bb.0: // %entry +; CHECK-NEXT: // kill: def $h0 killed $h0 def $s0 +; CHECK-NEXT: fmov w8, s0 +; CHECK-NEXT: and w8, w8, #0x7fff +; CHECK-NEXT: mov w9, #31744 +; CHECK-NEXT: cmp w8, w9 +; CHECK-NEXT: cset w0, gt +; CHECK-NEXT: ret +entry: + %0 = tail call i1 @llvm.isnan.f16(half %x) + ret i1 %0 +} + +define i1 @isnan_float(float %x) nounwind { +; CHECK-LABEL: isnan_float: +; CHECK: // %bb.0: // %entry +; CHECK-NEXT: fcmp s0, s0 +; CHECK-NEXT: cset w0, vs +; CHECK-NEXT: ret +entry: + %0 = tail call i1 @llvm.isnan.f32(float %x) + ret i1 %0 +} + +define i1 @isnan_double(double %x) nounwind { +; CHECK-LABEL: isnan_double: +; CHECK: // %bb.0: // %entry +; CHECK-NEXT: fcmp d0, d0 +; CHECK-NEXT: cset w0, vs +; CHECK-NEXT: ret +entry: + %0 = tail call i1 @llvm.isnan.f64(double %x) + ret i1 %0 +} + +define i1 @isnan_ldouble(fp128 %x) nounwind { +; CHECK-LABEL: isnan_ldouble: +; CHECK: // %bb.0: // %entry +; CHECK-NEXT: str x30, [sp, #-16]! // 8-byte Folded Spill +; CHECK-NEXT: mov v1.16b, v0.16b +; CHECK-NEXT: bl __unordtf2 +; CHECK-NEXT: cmp w0, #0 +; CHECK-NEXT: cset w0, ne +; CHECK-NEXT: ldr x30, [sp], #16 // 8-byte Folded Reload +; CHECK-NEXT: ret +entry: + %0 = tail call i1 @llvm.isnan.f128(fp128 %x) + ret i1 %0 +} + + +define i1 @isnan_half_strictfp(half %x) strictfp nounwind { +; CHECK-LABEL: isnan_half_strictfp: +; CHECK: // %bb.0: // %entry +; CHECK-NEXT: // kill: def $h0 killed $h0 def $s0 +; CHECK-NEXT: fmov w8, s0 +; CHECK-NEXT: and w8, w8, #0x7fff +; CHECK-NEXT: mov w9, #31744 +; CHECK-NEXT: cmp w8, w9 +; CHECK-NEXT: cset w0, gt +; CHECK-NEXT: ret +entry: + %0 = tail call i1 @llvm.isnan.f16(half %x) + ret i1 %0 +} + +define i1 @isnan_bfloat_strictfp(bfloat %x) strictfp nounwind { +; CHECK-LABEL: isnan_bfloat_strictfp: +; CHECK: // %bb.0: // %entry +; CHECK-NEXT: // kill: def $h0 killed $h0 def $s0 +; CHECK-NEXT: fmov w8, s0 +; CHECK-NEXT: and w8, w8, #0x7fff +; CHECK-NEXT: mov w9, #32640 +; CHECK-NEXT: cmp w8, w9 +; CHECK-NEXT: cset w0, gt +; CHECK-NEXT: ret +entry: + %0 = tail call i1 @llvm.isnan.bf16(bfloat %x) + ret i1 %0 +} + +define i1 @isnan_float_strictfp(float %x) strictfp nounwind { +; CHECK-LABEL: isnan_float_strictfp: +; CHECK: // %bb.0: // %entry +; CHECK-NEXT: fmov w8, s0 +; CHECK-NEXT: and w8, w8, #0x7fffffff +; CHECK-NEXT: mov w9, #2139095040 +; CHECK-NEXT: cmp w8, w9 +; CHECK-NEXT: cset w0, gt +; CHECK-NEXT: ret +entry: + %0 = tail call i1 @llvm.isnan.f32(float %x) + ret i1 %0 +} + +define i1 @isnan_double_strictfp(double %x) strictfp nounwind { +; CHECK-LABEL: isnan_double_strictfp: +; CHECK: // %bb.0: // %entry +; CHECK-NEXT: fmov x8, d0 +; CHECK-NEXT: and x8, x8, #0x7fffffffffffffff +; CHECK-NEXT: mov x9, #9218868437227405312 +; CHECK-NEXT: cmp x8, x9 +; CHECK-NEXT: cset w0, gt +; CHECK-NEXT: ret +entry: + %0 = tail call i1 @llvm.isnan.f64(double %x) + ret i1 %0 +} + +define i1 @isnan_ldouble_strictfp(fp128 %x) strictfp nounwind { +; CHECK-LABEL: isnan_ldouble_strictfp: +; CHECK: // %bb.0: // %entry +; CHECK-NEXT: str q0, [sp, #-16]! +; CHECK-NEXT: ldp x8, x9, [sp], #16 +; CHECK-NEXT: mov x10, #9223090561878065152 +; CHECK-NEXT: cmp x8, #0 +; CHECK-NEXT: and x8, x9, #0x7fffffffffffffff +; CHECK-NEXT: cset w9, ne +; CHECK-NEXT: cmp x8, x10 +; CHECK-NEXT: cset w8, gt +; CHECK-NEXT: csel w0, w9, w8, eq +; CHECK-NEXT: ret +entry: + %0 = tail call i1 @llvm.isnan.f128(fp128 %x) + ret i1 %0 +} + + +define <1 x i1> @isnan_half_vec1(<1 x half> %x) nounwind { +; CHECK-LABEL: isnan_half_vec1: +; CHECK: // %bb.0: // %entry +; CHECK-NEXT: // kill: def $h0 killed $h0 def $q0 +; CHECK-NEXT: umov w8, v0.h[0] +; CHECK-NEXT: and w8, w8, #0x7fff +; CHECK-NEXT: mov w9, #31744 +; CHECK-NEXT: cmp w8, w9 +; CHECK-NEXT: cset w0, gt +; CHECK-NEXT: ret +entry: + %0 = tail call <1 x i1> @llvm.isnan.v1f16(<1 x half> %x) + ret <1 x i1> %0 +} + +define <1 x i1> @isnan_float_vec1(<1 x float> %x) nounwind { +; CHECK-LABEL: isnan_float_vec1: +; CHECK: // %bb.0: // %entry +; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0 +; CHECK-NEXT: fcmp s0, s0 +; CHECK-NEXT: cset w0, vs +; CHECK-NEXT: ret +entry: + %0 = tail call <1 x i1> @llvm.isnan.v1f32(<1 x float> %x) + ret <1 x i1> %0 +} + +define <1 x i1> @isnan_double_vec1(<1 x double> %x) nounwind { +; CHECK-LABEL: isnan_double_vec1: +; CHECK: // %bb.0: // %entry +; CHECK-NEXT: fcmp d0, d0 +; CHECK-NEXT: cset w0, vs +; CHECK-NEXT: ret +entry: + %0 = tail call <1 x i1> @llvm.isnan.v1f64(<1 x double> %x) + ret <1 x i1> %0 +} + +define <1 x i1> @isnan_ldouble_vec1(<1 x fp128> %x) nounwind { +; CHECK-LABEL: isnan_ldouble_vec1: +; CHECK: // %bb.0: // %entry +; CHECK-NEXT: str x30, [sp, #-16]! // 8-byte Folded Spill +; CHECK-NEXT: mov v1.16b, v0.16b +; CHECK-NEXT: bl __unordtf2 +; CHECK-NEXT: cmp w0, #0 +; CHECK-NEXT: cset w0, ne +; CHECK-NEXT: ldr x30, [sp], #16 // 8-byte Folded Reload +; CHECK-NEXT: ret +entry: + %0 = tail call <1 x i1> @llvm.isnan.v1f128(<1 x fp128> %x) + ret <1 x i1> %0 +} + + +define <2 x i1> @isnan_half_vec2(<2 x half> %x) nounwind { +; CHECK-LABEL: isnan_half_vec2: +; CHECK: // %bb.0: // %entry +; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0 +; CHECK-NEXT: umov w8, v0.h[0] +; CHECK-NEXT: umov w9, v0.h[1] +; CHECK-NEXT: fmov s1, w8 +; CHECK-NEXT: movi v0.2s, #127, msl #8 +; CHECK-NEXT: mov v1.s[1], w9 +; CHECK-NEXT: and v0.8b, v1.8b, v0.8b +; CHECK-NEXT: movi v1.2s, #124, lsl #8 +; CHECK-NEXT: cmgt v0.2s, v0.2s, v1.2s +; CHECK-NEXT: ret +entry: + %0 = tail call <2 x i1> @llvm.isnan.v2f16(<2 x half> %x) + ret <2 x i1> %0 +} + +define <2 x i1> @isnan_float_vec2(<2 x float> %x) nounwind { +; CHECK-LABEL: isnan_float_vec2: +; CHECK: // %bb.0: // %entry +; CHECK-NEXT: fcmge v1.2s, v0.2s, #0.0 +; CHECK-NEXT: fcmlt v0.2s, v0.2s, #0.0 +; CHECK-NEXT: orr v0.8b, v0.8b, v1.8b +; CHECK-NEXT: mvn v0.8b, v0.8b +; CHECK-NEXT: ret +entry: + %0 = tail call <2 x i1> @llvm.isnan.v2f32(<2 x float> %x) + ret <2 x i1> %0 +} + +define <2 x i1> @isnan_double_vec2(<2 x double> %x) nounwind { +; CHECK-LABEL: isnan_double_vec2: +; CHECK: // %bb.0: // %entry +; CHECK-NEXT: fcmge v1.2d, v0.2d, #0.0 +; CHECK-NEXT: fcmlt v0.2d, v0.2d, #0.0 +; CHECK-NEXT: orr v0.16b, v0.16b, v1.16b +; CHECK-NEXT: mvn v0.16b, v0.16b +; CHECK-NEXT: xtn v0.2s, v0.2d +; CHECK-NEXT: ret +entry: + %0 = tail call <2 x i1> @llvm.isnan.v2f64(<2 x double> %x) + ret <2 x i1> %0 +} + +define <2 x i1> @isnan_ldouble_vec2(<2 x fp128> %x) nounwind { +; CHECK-LABEL: isnan_ldouble_vec2: +; CHECK: // %bb.0: // %entry +; CHECK-NEXT: sub sp, sp, #48 +; CHECK-NEXT: str q0, [sp, #16] // 16-byte Folded Spill +; CHECK-NEXT: mov v0.16b, v1.16b +; CHECK-NEXT: str x30, [sp, #32] // 8-byte Folded Spill +; CHECK-NEXT: bl __unordtf2 +; CHECK-NEXT: cmp w0, #0 +; CHECK-NEXT: cset w8, ne +; CHECK-NEXT: sbfx x8, x8, #0, #1 +; CHECK-NEXT: dup v0.2d, x8 +; CHECK-NEXT: str q0, [sp] // 16-byte Folded Spill +; CHECK-NEXT: ldr q0, [sp, #16] // 16-byte Folded Reload +; CHECK-NEXT: mov v1.16b, v0.16b +; CHECK-NEXT: bl __unordtf2 +; CHECK-NEXT: cmp w0, #0 +; CHECK-NEXT: ldr q1, [sp] // 16-byte Folded Reload +; CHECK-NEXT: cset w8, ne +; CHECK-NEXT: sbfx x8, x8, #0, #1 +; CHECK-NEXT: ldr x30, [sp, #32] // 8-byte Folded Reload +; CHECK-NEXT: dup v0.2d, x8 +; CHECK-NEXT: zip1 v0.4s, v0.4s, v1.4s +; CHECK-NEXT: // kill: def $d0 killed $d0 killed $q0 +; CHECK-NEXT: add sp, sp, #48 +; CHECK-NEXT: ret +entry: + %0 = tail call <2 x i1> @llvm.isnan.v2f128(<2 x fp128> %x) + ret <2 x i1> %0 +} + + +define <2 x i1> @isnan_half_vec2_strictfp(<2 x half> %x) strictfp nounwind { +; CHECK-LABEL: isnan_half_vec2_strictfp: +; CHECK: // %bb.0: // %entry +; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0 +; CHECK-NEXT: umov w8, v0.h[0] +; CHECK-NEXT: umov w9, v0.h[1] +; CHECK-NEXT: fmov s1, w8 +; CHECK-NEXT: movi v0.2s, #127, msl #8 +; CHECK-NEXT: mov v1.s[1], w9 +; CHECK-NEXT: and v0.8b, v1.8b, v0.8b +; CHECK-NEXT: movi v1.2s, #124, lsl #8 +; CHECK-NEXT: cmgt v0.2s, v0.2s, v1.2s +; CHECK-NEXT: ret +entry: + %0 = tail call <2 x i1> @llvm.isnan.v2f16(<2 x half> %x) + ret <2 x i1> %0 +} + +define <2 x i1> @isnan_bfloat_vec2_strictfp(<2 x bfloat> %x) strictfp nounwind { +; CHECK-LABEL: isnan_bfloat_vec2_strictfp: +; CHECK: // %bb.0: // %entry +; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0 +; CHECK-NEXT: umov w8, v0.h[0] +; CHECK-NEXT: umov w9, v0.h[1] +; CHECK-NEXT: fmov s1, w8 +; CHECK-NEXT: movi v0.2s, #127, msl #8 +; CHECK-NEXT: mov w10, #32640 +; CHECK-NEXT: mov v1.s[1], w9 +; CHECK-NEXT: and v0.8b, v1.8b, v0.8b +; CHECK-NEXT: dup v1.2s, w10 +; CHECK-NEXT: cmgt v0.2s, v0.2s, v1.2s +; CHECK-NEXT: ret +entry: + %0 = tail call <2 x i1> @llvm.isnan.v2bf16(<2 x bfloat> %x) + ret <2 x i1> %0 +} + +define <2 x i1> @isnan_float_vec2_strictfp(<2 x float> %x) strictfp nounwind { +; CHECK-LABEL: isnan_float_vec2_strictfp: +; CHECK: // %bb.0: // %entry +; CHECK-NEXT: mov w8, #2139095040 +; CHECK-NEXT: dup v1.2s, w8 +; CHECK-NEXT: bic v0.2s, #128, lsl #24 +; CHECK-NEXT: cmgt v0.2s, v0.2s, v1.2s +; CHECK-NEXT: ret +entry: + %0 = tail call <2 x i1> @llvm.isnan.v2f32(<2 x float> %x) + ret <2 x i1> %0 +} + +define <2 x i1> @isnan_double_vec2_strictfp(<2 x double> %x) strictfp nounwind { +; CHECK-LABEL: isnan_double_vec2_strictfp: +; CHECK: // %bb.0: // %entry +; CHECK-NEXT: mov x8, #9223372036854775807 +; CHECK-NEXT: mov x9, #9218868437227405312 +; CHECK-NEXT: dup v1.2d, x8 +; CHECK-NEXT: and v0.16b, v0.16b, v1.16b +; CHECK-NEXT: dup v1.2d, x9 +; CHECK-NEXT: cmgt v0.2d, v0.2d, v1.2d +; CHECK-NEXT: xtn v0.2s, v0.2d +; CHECK-NEXT: ret +entry: + %0 = tail call <2 x i1> @llvm.isnan.v2f64(<2 x double> %x) + ret <2 x i1> %0 +} + +define <2 x i1> @isnan_ldouble_vec2_strictfp(<2 x fp128> %x) strictfp nounwind { +; CHECK-LABEL: isnan_ldouble_vec2_strictfp: +; CHECK: // %bb.0: // %entry +; CHECK-NEXT: stp q0, q1, [sp, #-32]! +; CHECK-NEXT: ldp x11, x10, [sp, #16] +; CHECK-NEXT: ldp x8, x9, [sp] +; CHECK-NEXT: mov x12, #9223090561878065152 +; CHECK-NEXT: and x10, x10, #0x7fffffffffffffff +; CHECK-NEXT: cmp x11, #0 +; CHECK-NEXT: cset w11, ne +; CHECK-NEXT: cmp x10, x12 +; CHECK-NEXT: cset w10, gt +; CHECK-NEXT: and x9, x9, #0x7fffffffffffffff +; CHECK-NEXT: csel w10, w11, w10, eq +; CHECK-NEXT: cmp x8, #0 +; CHECK-NEXT: sbfx x8, x10, #0, #1 +; CHECK-NEXT: cset w10, ne +; CHECK-NEXT: cmp x9, x12 +; CHECK-NEXT: dup v0.2d, x8 +; CHECK-NEXT: cset w8, gt +; CHECK-NEXT: csel w8, w10, w8, eq +; CHECK-NEXT: sbfx x8, x8, #0, #1 +; CHECK-NEXT: dup v1.2d, x8 +; CHECK-NEXT: zip1 v0.4s, v1.4s, v0.4s +; CHECK-NEXT: // kill: def $d0 killed $d0 killed $q0 +; CHECK-NEXT: add sp, sp, #32 +; CHECK-NEXT: ret +entry: + %0 = tail call <2 x i1> @llvm.isnan.v2f128(<2 x fp128> %x) + ret <2 x i1> %0 +} + + +define <4 x i1> @isnan_half_vec4(<4 x half> %x) nounwind { +; CHECK-LABEL: isnan_half_vec4: +; CHECK: // %bb.0: // %entry +; CHECK-NEXT: movi v1.4h, #124, lsl #8 +; CHECK-NEXT: bic v0.4h, #128, lsl #8 +; CHECK-NEXT: cmgt v0.4h, v0.4h, v1.4h +; CHECK-NEXT: ret +entry: + %0 = tail call <4 x i1> @llvm.isnan.v4f16(<4 x half> %x) + ret <4 x i1> %0 +} + +define <4 x i1> @isnan_float_vec4(<4 x float> %x) nounwind { +; CHECK-LABEL: isnan_float_vec4: +; CHECK: // %bb.0: // %entry +; CHECK-NEXT: fcmge v1.4s, v0.4s, #0.0 +; CHECK-NEXT: fcmlt v0.4s, v0.4s, #0.0 +; CHECK-NEXT: orr v0.16b, v0.16b, v1.16b +; CHECK-NEXT: mvn v0.16b, v0.16b +; CHECK-NEXT: xtn v0.4h, v0.4s +; CHECK-NEXT: ret +entry: + %0 = tail call <4 x i1> @llvm.isnan.v4f32(<4 x float> %x) + ret <4 x i1> %0 +} + +define <4 x i1> @isnan_double_vec4(<4 x double> %x) nounwind { +; CHECK-LABEL: isnan_double_vec4: +; CHECK: // %bb.0: // %entry +; CHECK-NEXT: fcmge v2.2d, v0.2d, #0.0 +; CHECK-NEXT: fcmlt v0.2d, v0.2d, #0.0 +; CHECK-NEXT: fcmge v3.2d, v1.2d, #0.0 +; CHECK-NEXT: fcmlt v1.2d, v1.2d, #0.0 +; CHECK-NEXT: orr v0.16b, v0.16b, v2.16b +; CHECK-NEXT: orr v1.16b, v1.16b, v3.16b +; CHECK-NEXT: mvn v0.16b, v0.16b +; CHECK-NEXT: xtn v0.2s, v0.2d +; CHECK-NEXT: mvn v1.16b, v1.16b +; CHECK-NEXT: xtn2 v0.4s, v1.2d +; CHECK-NEXT: xtn v0.4h, v0.4s +; CHECK-NEXT: ret +entry: + %0 = tail call <4 x i1> @llvm.isnan.v4f64(<4 x double> %x) + ret <4 x i1> %0 +} + + +define <4 x i1> @isnan_half_vec4_strictfp(<4 x half> %x) strictfp nounwind { +; CHECK-LABEL: isnan_half_vec4_strictfp: +; CHECK: // %bb.0: // %entry +; CHECK-NEXT: movi v1.4h, #124, lsl #8 +; CHECK-NEXT: bic v0.4h, #128, lsl #8 +; CHECK-NEXT: cmgt v0.4h, v0.4h, v1.4h +; CHECK-NEXT: ret +entry: + %0 = tail call <4 x i1> @llvm.isnan.v4f16(<4 x half> %x) + ret <4 x i1> %0 +} + +define <4 x i1> @isnan_bfloat_vec4_strictfp(<4 x bfloat> %x) strictfp nounwind { +; CHECK-LABEL: isnan_bfloat_vec4_strictfp: +; CHECK: // %bb.0: // %entry +; CHECK-NEXT: mov w8, #32640 +; CHECK-NEXT: dup v1.4h, w8 +; CHECK-NEXT: bic v0.4h, #128, lsl #8 +; CHECK-NEXT: cmgt v0.4h, v0.4h, v1.4h +; CHECK-NEXT: ret +entry: + %0 = tail call <4 x i1> @llvm.isnan.v4bf16(<4 x bfloat> %x) + ret <4 x i1> %0 +} + +define <4 x i1> @isnan_float_vec4_strictfp(<4 x float> %x) strictfp nounwind { +; CHECK-LABEL: isnan_float_vec4_strictfp: +; CHECK: // %bb.0: // %entry +; CHECK-NEXT: mov w8, #2139095040 +; CHECK-NEXT: dup v1.4s, w8 +; CHECK-NEXT: bic v0.4s, #128, lsl #24 +; CHECK-NEXT: cmgt v0.4s, v0.4s, v1.4s +; CHECK-NEXT: xtn v0.4h, v0.4s +; CHECK-NEXT: ret +entry: + %0 = tail call <4 x i1> @llvm.isnan.v4f32(<4 x float> %x) + ret <4 x i1> %0 +} + +define <4 x i1> @isnan_double_vec4_strictfp(<4 x double> %x) strictfp nounwind { +; CHECK-LABEL: isnan_double_vec4_strictfp: +; CHECK: // %bb.0: // %entry +; CHECK-NEXT: mov x8, #9223372036854775807 +; CHECK-NEXT: mov x9, #9218868437227405312 +; CHECK-NEXT: dup v2.2d, x8 +; CHECK-NEXT: dup v3.2d, x9 +; CHECK-NEXT: and v0.16b, v0.16b, v2.16b +; CHECK-NEXT: and v1.16b, v1.16b, v2.16b +; CHECK-NEXT: cmgt v0.2d, v0.2d, v3.2d +; CHECK-NEXT: cmgt v1.2d, v1.2d, v3.2d +; CHECK-NEXT: xtn v0.2s, v0.2d +; CHECK-NEXT: xtn2 v0.4s, v1.2d +; CHECK-NEXT: xtn v0.4h, v0.4s +; CHECK-NEXT: ret +entry: + %0 = tail call <4 x i1> @llvm.isnan.v4f64(<4 x double> %x) + ret <4 x i1> %0 +} + + +declare i1 @llvm.isnan.f16(half) +declare i1 @llvm.isnan.bf16(bfloat) +declare i1 @llvm.isnan.f32(float) +declare i1 @llvm.isnan.f64(double) +declare i1 @llvm.isnan.f128(fp128) +declare <1 x i1> @llvm.isnan.v1f16(<1 x half>) +declare <1 x i1> @llvm.isnan.v1bf16(<1 x bfloat>) +declare <1 x i1> @llvm.isnan.v1f32(<1 x float>) +declare <1 x i1> @llvm.isnan.v1f64(<1 x double>) +declare <1 x i1> @llvm.isnan.v1f128(<1 x fp128>) +declare <2 x i1> @llvm.isnan.v2f16(<2 x half>) +declare <2 x i1> @llvm.isnan.v2bf16(<2 x bfloat>) +declare <2 x i1> @llvm.isnan.v2f32(<2 x float>) +declare <2 x i1> @llvm.isnan.v2f64(<2 x double>) +declare <2 x i1> @llvm.isnan.v2f128(<2 x fp128>) +declare <4 x i1> @llvm.isnan.v4f16(<4 x half>) +declare <4 x i1> @llvm.isnan.v4bf16(<4 x bfloat>) +declare <4 x i1> @llvm.isnan.v4f32(<4 x float>) +declare <4 x i1> @llvm.isnan.v4f64(<4 x double>) +declare <4 x i1> @llvm.isnan.v4f128(<4 x fp128>) diff --git a/llvm/test/CodeGen/PowerPC/ppc-fpclass.ll b/llvm/test/CodeGen/PowerPC/ppc-fpclass.ll new file mode 100644 index 0000000..40794aa --- /dev/null +++ b/llvm/test/CodeGen/PowerPC/ppc-fpclass.ll @@ -0,0 +1,535 @@ +; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py +; RUN: llc -mtriple=powerpcle-unknown-linux-gnu -verify-machineinstrs -o - %s | FileCheck %s + + +define i1 @isnan_float(float %x) nounwind { +; CHECK-LABEL: isnan_float: +; CHECK: # %bb.0: # %entry +; CHECK-NEXT: li 3, 0 +; CHECK-NEXT: fcmpu 0, 1, 1 +; CHECK-NEXT: li 4, 1 +; CHECK-NEXT: bc 12, 3, .LBB0_1 +; CHECK-NEXT: blr +; CHECK-NEXT: .LBB0_1: # %entry +; CHECK-NEXT: addi 3, 4, 0 +; CHECK-NEXT: blr +entry: + %0 = tail call i1 @llvm.isnan.f32(float %x) + ret i1 %0 +} + +define i1 @isnan_double(double %x) nounwind { +; CHECK-LABEL: isnan_double: +; CHECK: # %bb.0: # %entry +; CHECK-NEXT: li 3, 0 +; CHECK-NEXT: fcmpu 0, 1, 1 +; CHECK-NEXT: li 4, 1 +; CHECK-NEXT: bc 12, 3, .LBB1_1 +; CHECK-NEXT: blr +; CHECK-NEXT: .LBB1_1: # %entry +; CHECK-NEXT: addi 3, 4, 0 +; CHECK-NEXT: blr +entry: + %0 = tail call i1 @llvm.isnan.f64(double %x) + ret i1 %0 +} + +define i1 @isnan_ldouble(ppc_fp128 %x) nounwind { +; CHECK-LABEL: isnan_ldouble: +; CHECK: # %bb.0: # %entry +; CHECK-NEXT: stwu 1, -32(1) +; CHECK-NEXT: stfd 1, 16(1) +; CHECK-NEXT: lis 3, 32752 +; CHECK-NEXT: lwz 4, 20(1) +; CHECK-NEXT: stfd 2, 24(1) +; CHECK-NEXT: lwz 5, 28(1) +; CHECK-NEXT: cmplw 1, 4, 3 +; CHECK-NEXT: lwz 3, 24(1) +; CHECK-NEXT: xoris 4, 4, 32752 +; CHECK-NEXT: lwz 6, 16(1) +; CHECK-NEXT: clrlwi. 5, 5, 1 +; CHECK-NEXT: cmplwi 5, 5, 0 +; CHECK-NEXT: crandc 24, 1, 22 +; CHECK-NEXT: cmpwi 3, 0 +; CHECK-NEXT: crandc 20, 22, 2 +; CHECK-NEXT: cmpwi 6, 0 +; CHECK-NEXT: cmplwi 7, 4, 0 +; CHECK-NEXT: or 3, 3, 5 +; CHECK-NEXT: crandc 21, 5, 30 +; CHECK-NEXT: crandc 22, 30, 2 +; CHECK-NEXT: cmplwi 3, 0 +; CHECK-NEXT: cror 20, 20, 24 +; CHECK-NEXT: cror 21, 22, 21 +; CHECK-NEXT: crandc 20, 20, 2 +; CHECK-NEXT: crand 21, 2, 21 +; CHECK-NEXT: crnor 20, 21, 20 +; CHECK-NEXT: li 3, 1 +; CHECK-NEXT: bc 12, 20, .LBB2_1 +; CHECK-NEXT: b .LBB2_2 +; CHECK-NEXT: .LBB2_1: # %entry +; CHECK-NEXT: li 3, 0 +; CHECK-NEXT: .LBB2_2: # %entry +; CHECK-NEXT: addi 1, 1, 32 +; CHECK-NEXT: blr +entry: + %0 = tail call i1 @llvm.isnan.ppcf128(ppc_fp128 %x) + ret i1 %0 +} + + +define i1 @isnan_float_strictfp(float %x) strictfp nounwind { +; CHECK-LABEL: isnan_float_strictfp: +; CHECK: # %bb.0: # %entry +; CHECK-NEXT: stwu 1, -16(1) +; CHECK-NEXT: stfs 1, 12(1) +; CHECK-NEXT: lis 3, 32640 +; CHECK-NEXT: lwz 4, 12(1) +; CHECK-NEXT: clrlwi 4, 4, 1 +; CHECK-NEXT: cmpw 4, 3 +; CHECK-NEXT: li 3, 0 +; CHECK-NEXT: li 4, 1 +; CHECK-NEXT: bc 12, 1, .LBB3_1 +; CHECK-NEXT: b .LBB3_2 +; CHECK-NEXT: .LBB3_1: # %entry +; CHECK-NEXT: addi 3, 4, 0 +; CHECK-NEXT: .LBB3_2: # %entry +; CHECK-NEXT: addi 1, 1, 16 +; CHECK-NEXT: blr +entry: + %0 = tail call i1 @llvm.isnan.f32(float %x) + ret i1 %0 +} + +define i1 @isnan_double_strictfp(double %x) strictfp nounwind { +; CHECK-LABEL: isnan_double_strictfp: +; CHECK: # %bb.0: # %entry +; CHECK-NEXT: stwu 1, -16(1) +; CHECK-NEXT: stfd 1, 8(1) +; CHECK-NEXT: lis 3, 32752 +; CHECK-NEXT: lwz 4, 12(1) +; CHECK-NEXT: lwz 5, 8(1) +; CHECK-NEXT: clrlwi 4, 4, 1 +; CHECK-NEXT: cmpw 4, 3 +; CHECK-NEXT: xoris 3, 4, 32752 +; CHECK-NEXT: cmplwi 1, 3, 0 +; CHECK-NEXT: crandc 20, 1, 6 +; CHECK-NEXT: cmpwi 5, 0 +; CHECK-NEXT: crandc 21, 6, 2 +; CHECK-NEXT: crnor 20, 21, 20 +; CHECK-NEXT: li 3, 1 +; CHECK-NEXT: bc 12, 20, .LBB4_1 +; CHECK-NEXT: b .LBB4_2 +; CHECK-NEXT: .LBB4_1: # %entry +; CHECK-NEXT: li 3, 0 +; CHECK-NEXT: .LBB4_2: # %entry +; CHECK-NEXT: addi 1, 1, 16 +; CHECK-NEXT: blr +entry: + %0 = tail call i1 @llvm.isnan.f64(double %x) + ret i1 %0 +} + +define i1 @isnan_ldouble_strictfp(ppc_fp128 %x) strictfp nounwind { +; CHECK-LABEL: isnan_ldouble_strictfp: +; CHECK: # %bb.0: # %entry +; CHECK-NEXT: stwu 1, -32(1) +; CHECK-NEXT: stfd 1, 16(1) +; CHECK-NEXT: lis 3, 32752 +; CHECK-NEXT: lwz 4, 20(1) +; CHECK-NEXT: stfd 2, 24(1) +; CHECK-NEXT: lwz 5, 28(1) +; CHECK-NEXT: cmplw 1, 4, 3 +; CHECK-NEXT: lwz 3, 24(1) +; CHECK-NEXT: xoris 4, 4, 32752 +; CHECK-NEXT: lwz 6, 16(1) +; CHECK-NEXT: clrlwi. 5, 5, 1 +; CHECK-NEXT: cmplwi 5, 5, 0 +; CHECK-NEXT: crandc 24, 1, 22 +; CHECK-NEXT: cmpwi 3, 0 +; CHECK-NEXT: crandc 20, 22, 2 +; CHECK-NEXT: cmpwi 6, 0 +; CHECK-NEXT: cmplwi 7, 4, 0 +; CHECK-NEXT: or 3, 3, 5 +; CHECK-NEXT: crandc 21, 5, 30 +; CHECK-NEXT: crandc 22, 30, 2 +; CHECK-NEXT: cmplwi 3, 0 +; CHECK-NEXT: cror 20, 20, 24 +; CHECK-NEXT: cror 21, 22, 21 +; CHECK-NEXT: crandc 20, 20, 2 +; CHECK-NEXT: crand 21, 2, 21 +; CHECK-NEXT: crnor 20, 21, 20 +; CHECK-NEXT: li 3, 1 +; CHECK-NEXT: bc 12, 20, .LBB5_1 +; CHECK-NEXT: b .LBB5_2 +; CHECK-NEXT: .LBB5_1: # %entry +; CHECK-NEXT: li 3, 0 +; CHECK-NEXT: .LBB5_2: # %entry +; CHECK-NEXT: addi 1, 1, 32 +; CHECK-NEXT: blr +entry: + %0 = tail call i1 @llvm.isnan.ppcf128(ppc_fp128 %x) + ret i1 %0 +} + + +define <1 x i1> @isnan_float_vec1(<1 x float> %x) nounwind { +; CHECK-LABEL: isnan_float_vec1: +; CHECK: # %bb.0: # %entry +; CHECK-NEXT: li 3, 0 +; CHECK-NEXT: fcmpu 0, 1, 1 +; CHECK-NEXT: li 4, 1 +; CHECK-NEXT: bc 12, 3, .LBB6_1 +; CHECK-NEXT: blr +; CHECK-NEXT: .LBB6_1: # %entry +; CHECK-NEXT: addi 3, 4, 0 +; CHECK-NEXT: blr +entry: + %0 = tail call <1 x i1> @llvm.isnan.v1f32(<1 x float> %x) + ret <1 x i1> %0 +} + +define <1 x i1> @isnan_double_vec1(<1 x double> %x) nounwind { +; CHECK-LABEL: isnan_double_vec1: +; CHECK: # %bb.0: # %entry +; CHECK-NEXT: li 3, 0 +; CHECK-NEXT: fcmpu 0, 1, 1 +; CHECK-NEXT: li 4, 1 +; CHECK-NEXT: bc 12, 3, .LBB7_1 +; CHECK-NEXT: blr +; CHECK-NEXT: .LBB7_1: # %entry +; CHECK-NEXT: addi 3, 4, 0 +; CHECK-NEXT: blr +entry: + %0 = tail call <1 x i1> @llvm.isnan.v1f64(<1 x double> %x) + ret <1 x i1> %0 +} + +define <1 x i1> @isnan_ldouble_vec1(<1 x ppc_fp128> %x) nounwind { +; CHECK-LABEL: isnan_ldouble_vec1: +; CHECK: # %bb.0: # %entry +; CHECK-NEXT: stwu 1, -32(1) +; CHECK-NEXT: stfd 1, 16(1) +; CHECK-NEXT: lis 3, 32752 +; CHECK-NEXT: lwz 4, 20(1) +; CHECK-NEXT: stfd 2, 24(1) +; CHECK-NEXT: lwz 5, 28(1) +; CHECK-NEXT: cmplw 1, 4, 3 +; CHECK-NEXT: lwz 3, 24(1) +; CHECK-NEXT: xoris 4, 4, 32752 +; CHECK-NEXT: lwz 6, 16(1) +; CHECK-NEXT: clrlwi. 5, 5, 1 +; CHECK-NEXT: cmplwi 5, 5, 0 +; CHECK-NEXT: crandc 24, 1, 22 +; CHECK-NEXT: cmpwi 3, 0 +; CHECK-NEXT: crandc 20, 22, 2 +; CHECK-NEXT: cmpwi 6, 0 +; CHECK-NEXT: cmplwi 7, 4, 0 +; CHECK-NEXT: or 3, 3, 5 +; CHECK-NEXT: crandc 21, 5, 30 +; CHECK-NEXT: crandc 22, 30, 2 +; CHECK-NEXT: cmplwi 3, 0 +; CHECK-NEXT: cror 20, 20, 24 +; CHECK-NEXT: cror 21, 22, 21 +; CHECK-NEXT: crandc 20, 20, 2 +; CHECK-NEXT: crand 21, 2, 21 +; CHECK-NEXT: crnor 20, 21, 20 +; CHECK-NEXT: li 3, 1 +; CHECK-NEXT: bc 12, 20, .LBB8_1 +; CHECK-NEXT: b .LBB8_2 +; CHECK-NEXT: .LBB8_1: # %entry +; CHECK-NEXT: li 3, 0 +; CHECK-NEXT: .LBB8_2: # %entry +; CHECK-NEXT: addi 1, 1, 32 +; CHECK-NEXT: blr +entry: + %0 = tail call <1 x i1> @llvm.isnan.v1ppcf128(<1 x ppc_fp128> %x) + ret <1 x i1> %0 +} + + +define <2 x i1> @isnan_float_vec2(<2 x float> %x) nounwind { +; CHECK-LABEL: isnan_float_vec2: +; CHECK: # %bb.0: # %entry +; CHECK-NEXT: li 4, 0 +; CHECK-NEXT: fcmpu 0, 2, 2 +; CHECK-NEXT: fcmpu 1, 1, 1 +; CHECK-NEXT: li 5, 1 +; CHECK-NEXT: bc 12, 7, .LBB9_2 +; CHECK-NEXT: # %bb.1: # %entry +; CHECK-NEXT: ori 3, 4, 0 +; CHECK-NEXT: b .LBB9_3 +; CHECK-NEXT: .LBB9_2: # %entry +; CHECK-NEXT: addi 3, 5, 0 +; CHECK-NEXT: .LBB9_3: # %entry +; CHECK-NEXT: bc 12, 3, .LBB9_4 +; CHECK-NEXT: blr +; CHECK-NEXT: .LBB9_4: # %entry +; CHECK-NEXT: addi 4, 5, 0 +; CHECK-NEXT: blr +entry: + %0 = tail call <2 x i1> @llvm.isnan.v2f32(<2 x float> %x) + ret <2 x i1> %0 +} + +define <2 x i1> @isnan_double_vec2(<2 x double> %x) nounwind { +; CHECK-LABEL: isnan_double_vec2: +; CHECK: # %bb.0: # %entry +; CHECK-NEXT: li 4, 0 +; CHECK-NEXT: fcmpu 0, 2, 2 +; CHECK-NEXT: fcmpu 1, 1, 1 +; CHECK-NEXT: li 5, 1 +; CHECK-NEXT: bc 12, 7, .LBB10_2 +; CHECK-NEXT: # %bb.1: # %entry +; CHECK-NEXT: ori 3, 4, 0 +; CHECK-NEXT: b .LBB10_3 +; CHECK-NEXT: .LBB10_2: # %entry +; CHECK-NEXT: addi 3, 5, 0 +; CHECK-NEXT: .LBB10_3: # %entry +; CHECK-NEXT: bc 12, 3, .LBB10_4 +; CHECK-NEXT: blr +; CHECK-NEXT: .LBB10_4: # %entry +; CHECK-NEXT: addi 4, 5, 0 +; CHECK-NEXT: blr +entry: + %0 = tail call <2 x i1> @llvm.isnan.v2f64(<2 x double> %x) + ret <2 x i1> %0 +} + +define <2 x i1> @isnan_ldouble_vec2(<2 x ppc_fp128> %x) nounwind { +; CHECK-LABEL: isnan_ldouble_vec2: +; CHECK: # %bb.0: # %entry +; CHECK-NEXT: stwu 1, -48(1) +; CHECK-NEXT: stfd 3, 32(1) +; CHECK-NEXT: lis 3, 32752 +; CHECK-NEXT: lwz 8, 32(1) +; CHECK-NEXT: stfd 4, 40(1) +; CHECK-NEXT: lwz 9, 44(1) +; CHECK-NEXT: cmpwi 1, 8, 0 +; CHECK-NEXT: lwz 10, 36(1) +; CHECK-NEXT: lwz 8, 40(1) +; CHECK-NEXT: clrlwi. 9, 9, 1 +; CHECK-NEXT: stfd 1, 16(1) +; CHECK-NEXT: cmplwi 5, 9, 0 +; CHECK-NEXT: lwz 5, 20(1) +; CHECK-NEXT: crandc 24, 1, 22 +; CHECK-NEXT: stfd 2, 24(1) +; CHECK-NEXT: cmpwi 8, 0 +; CHECK-NEXT: lwz 4, 16(1) +; CHECK-NEXT: cmplw 7, 10, 3 +; CHECK-NEXT: lwz 7, 28(1) +; CHECK-NEXT: xoris 10, 10, 32752 +; CHECK-NEXT: crandc 20, 22, 2 +; CHECK-NEXT: cmplwi 10, 0 +; CHECK-NEXT: lwz 6, 24(1) +; CHECK-NEXT: crandc 21, 29, 2 +; CHECK-NEXT: cmplw 7, 5, 3 +; CHECK-NEXT: xoris 3, 5, 32752 +; CHECK-NEXT: crandc 22, 2, 6 +; CHECK-NEXT: cmplwi 3, 0 +; CHECK-NEXT: cmpwi 1, 4, 0 +; CHECK-NEXT: crandc 23, 29, 2 +; CHECK-NEXT: crandc 25, 2, 6 +; CHECK-NEXT: clrlwi. 3, 7, 1 +; CHECK-NEXT: cmplwi 1, 3, 0 +; CHECK-NEXT: crandc 26, 1, 6 +; CHECK-NEXT: cmpwi 6, 0 +; CHECK-NEXT: or 4, 8, 9 +; CHECK-NEXT: crandc 27, 6, 2 +; CHECK-NEXT: cmplwi 4, 0 +; CHECK-NEXT: or 3, 6, 3 +; CHECK-NEXT: cror 20, 20, 24 +; CHECK-NEXT: cror 21, 22, 21 +; CHECK-NEXT: cmplwi 1, 3, 0 +; CHECK-NEXT: cror 22, 25, 23 +; CHECK-NEXT: crandc 20, 20, 2 +; CHECK-NEXT: crand 21, 2, 21 +; CHECK-NEXT: cror 23, 27, 26 +; CHECK-NEXT: crand 22, 6, 22 +; CHECK-NEXT: crnor 20, 21, 20 +; CHECK-NEXT: crandc 21, 23, 6 +; CHECK-NEXT: crnor 21, 22, 21 +; CHECK-NEXT: li 4, 1 +; CHECK-NEXT: bc 12, 21, .LBB11_2 +; CHECK-NEXT: # %bb.1: # %entry +; CHECK-NEXT: ori 3, 4, 0 +; CHECK-NEXT: b .LBB11_3 +; CHECK-NEXT: .LBB11_2: # %entry +; CHECK-NEXT: li 3, 0 +; CHECK-NEXT: .LBB11_3: # %entry +; CHECK-NEXT: bc 12, 20, .LBB11_4 +; CHECK-NEXT: b .LBB11_5 +; CHECK-NEXT: .LBB11_4: # %entry +; CHECK-NEXT: li 4, 0 +; CHECK-NEXT: .LBB11_5: # %entry +; CHECK-NEXT: addi 1, 1, 48 +; CHECK-NEXT: blr +entry: + %0 = tail call <2 x i1> @llvm.isnan.v2ppcf128(<2 x ppc_fp128> %x) + ret <2 x i1> %0 +} + + +define <2 x i1> @isnan_float_vec2_strictfp(<2 x float> %x) strictfp nounwind { +; CHECK-LABEL: isnan_float_vec2_strictfp: +; CHECK: # %bb.0: # %entry +; CHECK-NEXT: stwu 1, -16(1) +; CHECK-NEXT: stfs 1, 8(1) +; CHECK-NEXT: lis 3, 32640 +; CHECK-NEXT: stfs 2, 12(1) +; CHECK-NEXT: lwz 4, 12(1) +; CHECK-NEXT: lwz 5, 8(1) +; CHECK-NEXT: clrlwi 4, 4, 1 +; CHECK-NEXT: cmpw 4, 3 +; CHECK-NEXT: clrlwi 5, 5, 1 +; CHECK-NEXT: li 4, 0 +; CHECK-NEXT: cmpw 1, 5, 3 +; CHECK-NEXT: li 5, 1 +; CHECK-NEXT: bc 12, 5, .LBB12_2 +; CHECK-NEXT: # %bb.1: # %entry +; CHECK-NEXT: ori 3, 4, 0 +; CHECK-NEXT: b .LBB12_3 +; CHECK-NEXT: .LBB12_2: # %entry +; CHECK-NEXT: addi 3, 5, 0 +; CHECK-NEXT: .LBB12_3: # %entry +; CHECK-NEXT: bc 12, 1, .LBB12_4 +; CHECK-NEXT: b .LBB12_5 +; CHECK-NEXT: .LBB12_4: # %entry +; CHECK-NEXT: addi 4, 5, 0 +; CHECK-NEXT: .LBB12_5: # %entry +; CHECK-NEXT: addi 1, 1, 16 +; CHECK-NEXT: blr +entry: + %0 = tail call <2 x i1> @llvm.isnan.v2f32(<2 x float> %x) + ret <2 x i1> %0 +} + +define <2 x i1> @isnan_double_vec2_strictfp(<2 x double> %x) strictfp nounwind { +; CHECK-LABEL: isnan_double_vec2_strictfp: +; CHECK: # %bb.0: # %entry +; CHECK-NEXT: stwu 1, -32(1) +; CHECK-NEXT: stfd 2, 24(1) +; CHECK-NEXT: lis 3, 32752 +; CHECK-NEXT: lwz 5, 28(1) +; CHECK-NEXT: stfd 1, 16(1) +; CHECK-NEXT: lwz 6, 20(1) +; CHECK-NEXT: clrlwi 5, 5, 1 +; CHECK-NEXT: lwz 7, 24(1) +; CHECK-NEXT: cmpw 5, 3 +; CHECK-NEXT: xoris 5, 5, 32752 +; CHECK-NEXT: lwz 4, 16(1) +; CHECK-NEXT: cmplwi 1, 5, 0 +; CHECK-NEXT: crandc 20, 1, 6 +; CHECK-NEXT: cmpwi 7, 0 +; CHECK-NEXT: clrlwi 5, 6, 1 +; CHECK-NEXT: crandc 21, 6, 2 +; CHECK-NEXT: cmpw 5, 3 +; CHECK-NEXT: xoris 3, 5, 32752 +; CHECK-NEXT: cmplwi 1, 3, 0 +; CHECK-NEXT: crandc 22, 1, 6 +; CHECK-NEXT: cmpwi 4, 0 +; CHECK-NEXT: crandc 23, 6, 2 +; CHECK-NEXT: crnor 20, 21, 20 +; CHECK-NEXT: crnor 21, 23, 22 +; CHECK-NEXT: li 4, 1 +; CHECK-NEXT: bc 12, 21, .LBB13_2 +; CHECK-NEXT: # %bb.1: # %entry +; CHECK-NEXT: ori 3, 4, 0 +; CHECK-NEXT: b .LBB13_3 +; CHECK-NEXT: .LBB13_2: # %entry +; CHECK-NEXT: li 3, 0 +; CHECK-NEXT: .LBB13_3: # %entry +; CHECK-NEXT: bc 12, 20, .LBB13_4 +; CHECK-NEXT: b .LBB13_5 +; CHECK-NEXT: .LBB13_4: # %entry +; CHECK-NEXT: li 4, 0 +; CHECK-NEXT: .LBB13_5: # %entry +; CHECK-NEXT: addi 1, 1, 32 +; CHECK-NEXT: blr +entry: + %0 = tail call <2 x i1> @llvm.isnan.v2f64(<2 x double> %x) + ret <2 x i1> %0 +} + +define <2 x i1> @isnan_ldouble_vec2_strictfp(<2 x ppc_fp128> %x) strictfp nounwind { +; CHECK-LABEL: isnan_ldouble_vec2_strictfp: +; CHECK: # %bb.0: # %entry +; CHECK-NEXT: stwu 1, -48(1) +; CHECK-NEXT: stfd 3, 32(1) +; CHECK-NEXT: lis 3, 32752 +; CHECK-NEXT: lwz 8, 32(1) +; CHECK-NEXT: stfd 4, 40(1) +; CHECK-NEXT: lwz 9, 44(1) +; CHECK-NEXT: cmpwi 1, 8, 0 +; CHECK-NEXT: lwz 10, 36(1) +; CHECK-NEXT: lwz 8, 40(1) +; CHECK-NEXT: clrlwi. 9, 9, 1 +; CHECK-NEXT: stfd 1, 16(1) +; CHECK-NEXT: cmplwi 5, 9, 0 +; CHECK-NEXT: lwz 5, 20(1) +; CHECK-NEXT: crandc 24, 1, 22 +; CHECK-NEXT: stfd 2, 24(1) +; CHECK-NEXT: cmpwi 8, 0 +; CHECK-NEXT: lwz 4, 16(1) +; CHECK-NEXT: cmplw 7, 10, 3 +; CHECK-NEXT: lwz 7, 28(1) +; CHECK-NEXT: xoris 10, 10, 32752 +; CHECK-NEXT: crandc 20, 22, 2 +; CHECK-NEXT: cmplwi 10, 0 +; CHECK-NEXT: lwz 6, 24(1) +; CHECK-NEXT: crandc 21, 29, 2 +; CHECK-NEXT: cmplw 7, 5, 3 +; CHECK-NEXT: xoris 3, 5, 32752 +; CHECK-NEXT: crandc 22, 2, 6 +; CHECK-NEXT: cmplwi 3, 0 +; CHECK-NEXT: cmpwi 1, 4, 0 +; CHECK-NEXT: crandc 23, 29, 2 +; CHECK-NEXT: crandc 25, 2, 6 +; CHECK-NEXT: clrlwi. 3, 7, 1 +; CHECK-NEXT: cmplwi 1, 3, 0 +; CHECK-NEXT: crandc 26, 1, 6 +; CHECK-NEXT: cmpwi 6, 0 +; CHECK-NEXT: or 4, 8, 9 +; CHECK-NEXT: crandc 27, 6, 2 +; CHECK-NEXT: cmplwi 4, 0 +; CHECK-NEXT: or 3, 6, 3 +; CHECK-NEXT: cror 20, 20, 24 +; CHECK-NEXT: cror 21, 22, 21 +; CHECK-NEXT: cmplwi 1, 3, 0 +; CHECK-NEXT: cror 22, 25, 23 +; CHECK-NEXT: crandc 20, 20, 2 +; CHECK-NEXT: crand 21, 2, 21 +; CHECK-NEXT: cror 23, 27, 26 +; CHECK-NEXT: crand 22, 6, 22 +; CHECK-NEXT: crnor 20, 21, 20 +; CHECK-NEXT: crandc 21, 23, 6 +; CHECK-NEXT: crnor 21, 22, 21 +; CHECK-NEXT: li 4, 1 +; CHECK-NEXT: bc 12, 21, .LBB14_2 +; CHECK-NEXT: # %bb.1: # %entry +; CHECK-NEXT: ori 3, 4, 0 +; CHECK-NEXT: b .LBB14_3 +; CHECK-NEXT: .LBB14_2: # %entry +; CHECK-NEXT: li 3, 0 +; CHECK-NEXT: .LBB14_3: # %entry +; CHECK-NEXT: bc 12, 20, .LBB14_4 +; CHECK-NEXT: b .LBB14_5 +; CHECK-NEXT: .LBB14_4: # %entry +; CHECK-NEXT: li 4, 0 +; CHECK-NEXT: .LBB14_5: # %entry +; CHECK-NEXT: addi 1, 1, 48 +; CHECK-NEXT: blr +entry: + %0 = tail call <2 x i1> @llvm.isnan.v2ppcf128(<2 x ppc_fp128> %x) + ret <2 x i1> %0 +} + + +declare i1 @llvm.isnan.f32(float) +declare i1 @llvm.isnan.f64(double) +declare i1 @llvm.isnan.ppcf128(ppc_fp128) +declare <1 x i1> @llvm.isnan.v1f32(<1 x float>) +declare <1 x i1> @llvm.isnan.v1f64(<1 x double>) +declare <1 x i1> @llvm.isnan.v1ppcf128(<1 x ppc_fp128>) +declare <2 x i1> @llvm.isnan.v2f32(<2 x float>) +declare <2 x i1> @llvm.isnan.v2f64(<2 x double>) +declare <2 x i1> @llvm.isnan.v2ppcf128(<2 x ppc_fp128>) diff --git a/llvm/test/CodeGen/X86/x86-fpclass.ll b/llvm/test/CodeGen/X86/x86-fpclass.ll new file mode 100644 index 0000000..601ce1f --- /dev/null +++ b/llvm/test/CodeGen/X86/x86-fpclass.ll @@ -0,0 +1,1098 @@ +; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py +; RUN: llc < %s -mtriple=i686 | FileCheck %s -check-prefix=CHECK-32 +; RUN: llc < %s -mtriple=x86_64 | FileCheck %s -check-prefix=CHECK-64 + +define i1 @isnan_half(half %x) nounwind { +; CHECK-32-LABEL: isnan_half: +; CHECK-32: # %bb.0: # %entry +; CHECK-32-NEXT: movzwl {{[0-9]+}}(%esp), %eax +; CHECK-32-NEXT: andl $32767, %eax # imm = 0x7FFF +; CHECK-32-NEXT: cmpl $31745, %eax # imm = 0x7C01 +; CHECK-32-NEXT: setge %al +; CHECK-32-NEXT: retl +; +; CHECK-64-LABEL: isnan_half: +; CHECK-64: # %bb.0: # %entry +; CHECK-64-NEXT: andl $32767, %edi # imm = 0x7FFF +; CHECK-64-NEXT: cmpl $31745, %edi # imm = 0x7C01 +; CHECK-64-NEXT: setge %al +; CHECK-64-NEXT: retq +entry: + %0 = tail call i1 @llvm.isnan.f16(half %x) + ret i1 %0 +} + +define i1 @isnan_bfloat(i16 %x) nounwind { +; CHECK-32-LABEL: isnan_bfloat: +; CHECK-32: # %bb.0: # %entry +; CHECK-32-NEXT: movzwl {{[0-9]+}}(%esp), %eax +; CHECK-32-NEXT: andl $32767, %eax # imm = 0x7FFF +; CHECK-32-NEXT: cmpl $32641, %eax # imm = 0x7F81 +; CHECK-32-NEXT: setge %al +; CHECK-32-NEXT: retl +; +; CHECK-64-LABEL: isnan_bfloat: +; CHECK-64: # %bb.0: # %entry +; CHECK-64-NEXT: andl $32767, %edi # imm = 0x7FFF +; CHECK-64-NEXT: cmpl $32641, %edi # imm = 0x7F81 +; CHECK-64-NEXT: setge %al +; CHECK-64-NEXT: retq +entry: + %0 = bitcast i16 %x to bfloat + %1 = tail call i1 @llvm.isnan.bf16(bfloat %0) + ret i1 %1 +} + +define i1 @isnan_float(float %x) nounwind { +; CHECK-32-LABEL: isnan_float: +; CHECK-32: # %bb.0: # %entry +; CHECK-32-NEXT: flds {{[0-9]+}}(%esp) +; CHECK-32-NEXT: fucomp %st(0) +; CHECK-32-NEXT: fnstsw %ax +; CHECK-32-NEXT: # kill: def $ah killed $ah killed $ax +; CHECK-32-NEXT: sahf +; CHECK-32-NEXT: setp %al +; CHECK-32-NEXT: retl +; +; CHECK-64-LABEL: isnan_float: +; CHECK-64: # %bb.0: # %entry +; CHECK-64-NEXT: ucomiss %xmm0, %xmm0 +; CHECK-64-NEXT: setp %al +; CHECK-64-NEXT: retq +; NOSSE-32-LABEL: isnan_float: +entry: + %0 = tail call i1 @llvm.isnan.f32(float %x) + ret i1 %0 +} + +define i1 @isnan_double(double %x) nounwind { +; CHECK-32-LABEL: isnan_double: +; CHECK-32: # %bb.0: # %entry +; CHECK-32-NEXT: fldl {{[0-9]+}}(%esp) +; CHECK-32-NEXT: fucomp %st(0) +; CHECK-32-NEXT: fnstsw %ax +; CHECK-32-NEXT: # kill: def $ah killed $ah killed $ax +; CHECK-32-NEXT: sahf +; CHECK-32-NEXT: setp %al +; CHECK-32-NEXT: retl +; +; CHECK-64-LABEL: isnan_double: +; CHECK-64: # %bb.0: # %entry +; CHECK-64-NEXT: ucomisd %xmm0, %xmm0 +; CHECK-64-NEXT: setp %al +; CHECK-64-NEXT: retq +entry: + %0 = tail call i1 @llvm.isnan.f64(double %x) + ret i1 %0 +} + +define i1 @isnan_ldouble(x86_fp80 %x) nounwind { +; CHECK-32-LABEL: isnan_ldouble: +; CHECK-32: # %bb.0: # %entry +; CHECK-32-NEXT: fldt {{[0-9]+}}(%esp) +; CHECK-32-NEXT: fxam +; CHECK-32-NEXT: fstp %st(0) +; CHECK-32-NEXT: fnstsw %ax +; CHECK-32-NEXT: andb $69, %ah +; CHECK-32-NEXT: cmpb $1, %ah +; CHECK-32-NEXT: sete %al +; CHECK-32-NEXT: retl +; +; CHECK-64-LABEL: isnan_ldouble: +; CHECK-64: # %bb.0: # %entry +; CHECK-64-NEXT: fldt {{[0-9]+}}(%rsp) +; CHECK-64-NEXT: fxam +; CHECK-64-NEXT: fstp %st(0) +; CHECK-64-NEXT: fnstsw %ax +; CHECK-64-NEXT: andb $69, %ah +; CHECK-64-NEXT: cmpb $1, %ah +; CHECK-64-NEXT: sete %al +; CHECK-64-NEXT: retq +entry: + %0 = tail call i1 @llvm.isnan.f80(x86_fp80 %x) + ret i1 %0 +} + +define i1 @isnan_half_strictfp(half %x) strictfp nounwind { +; CHECK-32-LABEL: isnan_half_strictfp: +; CHECK-32: # %bb.0: # %entry +; CHECK-32-NEXT: movzwl {{[0-9]+}}(%esp), %eax +; CHECK-32-NEXT: andl $32767, %eax # imm = 0x7FFF +; CHECK-32-NEXT: cmpl $31745, %eax # imm = 0x7C01 +; CHECK-32-NEXT: setge %al +; CHECK-32-NEXT: retl +; +; CHECK-64-LABEL: isnan_half_strictfp: +; CHECK-64: # %bb.0: # %entry +; CHECK-64-NEXT: andl $32767, %edi # imm = 0x7FFF +; CHECK-64-NEXT: cmpl $31745, %edi # imm = 0x7C01 +; CHECK-64-NEXT: setge %al +; CHECK-64-NEXT: retq +entry: + %0 = tail call i1 @llvm.isnan.f16(half %x) + ret i1 %0 +} + +define i1 @isnan_bfloat_strict(i16 %x) strictfp nounwind { +; CHECK-32-LABEL: isnan_bfloat_strict: +; CHECK-32: # %bb.0: # %entry +; CHECK-32-NEXT: movzwl {{[0-9]+}}(%esp), %eax +; CHECK-32-NEXT: andl $32767, %eax # imm = 0x7FFF +; CHECK-32-NEXT: cmpl $32641, %eax # imm = 0x7F81 +; CHECK-32-NEXT: setge %al +; CHECK-32-NEXT: retl +; +; CHECK-64-LABEL: isnan_bfloat_strict: +; CHECK-64: # %bb.0: # %entry +; CHECK-64-NEXT: andl $32767, %edi # imm = 0x7FFF +; CHECK-64-NEXT: cmpl $32641, %edi # imm = 0x7F81 +; CHECK-64-NEXT: setge %al +; CHECK-64-NEXT: retq +entry: + %0 = bitcast i16 %x to bfloat + %1 = tail call i1 @llvm.isnan.bf16(bfloat %0) + ret i1 %1 +} + +define i1 @isnan_float_strictfp(float %x) strictfp nounwind { +; CHECK-32-LABEL: isnan_float_strictfp: +; CHECK-32: # %bb.0: # %entry +; CHECK-32-NEXT: movl $2147483647, %eax # imm = 0x7FFFFFFF +; CHECK-32-NEXT: andl {{[0-9]+}}(%esp), %eax +; CHECK-32-NEXT: cmpl $2139095041, %eax # imm = 0x7F800001 +; CHECK-32-NEXT: setge %al +; CHECK-32-NEXT: retl +; +; CHECK-64-LABEL: isnan_float_strictfp: +; CHECK-64: # %bb.0: # %entry +; CHECK-64-NEXT: movd %xmm0, %eax +; CHECK-64-NEXT: andl $2147483647, %eax # imm = 0x7FFFFFFF +; CHECK-64-NEXT: cmpl $2139095041, %eax # imm = 0x7F800001 +; CHECK-64-NEXT: setge %al +; CHECK-64-NEXT: retq +; NOSSE-32-LABEL: isnan_float_strictfp: +entry: + %0 = tail call i1 @llvm.isnan.f32(float %x) + ret i1 %0 +} + +define i1 @isnan_double_strictfp(double %x) strictfp nounwind { +; CHECK-32-LABEL: isnan_double_strictfp: +; CHECK-32: # %bb.0: # %entry +; CHECK-32-NEXT: movl $2147483647, %eax # imm = 0x7FFFFFFF +; CHECK-32-NEXT: andl {{[0-9]+}}(%esp), %eax +; CHECK-32-NEXT: xorl %ecx, %ecx +; CHECK-32-NEXT: cmpl {{[0-9]+}}(%esp), %ecx +; CHECK-32-NEXT: movl $2146435072, %ecx # imm = 0x7FF00000 +; CHECK-32-NEXT: sbbl %eax, %ecx +; CHECK-32-NEXT: setl %al +; CHECK-32-NEXT: retl +; +; CHECK-64-LABEL: isnan_double_strictfp: +; CHECK-64: # %bb.0: # %entry +; CHECK-64-NEXT: movq %xmm0, %rax +; CHECK-64-NEXT: movabsq $9223372036854775807, %rcx # imm = 0x7FFFFFFFFFFFFFFF +; CHECK-64-NEXT: andq %rax, %rcx +; CHECK-64-NEXT: movabsq $9218868437227405312, %rax # imm = 0x7FF0000000000000 +; CHECK-64-NEXT: cmpq %rax, %rcx +; CHECK-64-NEXT: setg %al +; CHECK-64-NEXT: retq +entry: + %0 = tail call i1 @llvm.isnan.f64(double %x) + ret i1 %0 +} + +define i1 @isnan_ldouble_strictfp(x86_fp80 %x) strictfp nounwind { +; CHECK-32-LABEL: isnan_ldouble_strictfp: +; CHECK-32: # %bb.0: # %entry +; CHECK-32-NEXT: fldt {{[0-9]+}}(%esp) +; CHECK-32-NEXT: fxam +; CHECK-32-NEXT: fstp %st(0) +; CHECK-32-NEXT: wait +; CHECK-32-NEXT: fnstsw %ax +; CHECK-32-NEXT: andb $69, %ah +; CHECK-32-NEXT: cmpb $1, %ah +; CHECK-32-NEXT: sete %al +; CHECK-32-NEXT: retl +; +; CHECK-64-LABEL: isnan_ldouble_strictfp: +; CHECK-64: # %bb.0: # %entry +; CHECK-64-NEXT: fldt {{[0-9]+}}(%rsp) +; CHECK-64-NEXT: fxam +; CHECK-64-NEXT: fstp %st(0) +; CHECK-64-NEXT: wait +; CHECK-64-NEXT: fnstsw %ax +; CHECK-64-NEXT: andb $69, %ah +; CHECK-64-NEXT: cmpb $1, %ah +; CHECK-64-NEXT: sete %al +; CHECK-64-NEXT: retq +entry: + %0 = tail call i1 @llvm.isnan.f80(x86_fp80 %x) + ret i1 %0 +} + +define <1 x i1> @isnan_half_vec1(<1 x half> %x) nounwind { +; CHECK-32-LABEL: isnan_half_vec1: +; CHECK-32: # %bb.0: # %entry +; CHECK-32-NEXT: movzwl {{[0-9]+}}(%esp), %eax +; CHECK-32-NEXT: andl $32767, %eax # imm = 0x7FFF +; CHECK-32-NEXT: cmpl $31745, %eax # imm = 0x7C01 +; CHECK-32-NEXT: setge %al +; CHECK-32-NEXT: retl +; +; CHECK-64-LABEL: isnan_half_vec1: +; CHECK-64: # %bb.0: # %entry +; CHECK-64-NEXT: andl $32767, %edi # imm = 0x7FFF +; CHECK-64-NEXT: cmpl $31745, %edi # imm = 0x7C01 +; CHECK-64-NEXT: setge %al +; CHECK-64-NEXT: retq +entry: + %0 = tail call <1 x i1> @llvm.isnan.v1f16(<1 x half> %x) + ret <1 x i1> %0 +} + +define <1 x i1> @isnan_bfloat_vec1(<1 x i16> %x) nounwind { +; CHECK-32-LABEL: isnan_bfloat_vec1: +; CHECK-32: # %bb.0: # %entry +; CHECK-32-NEXT: movzwl {{[0-9]+}}(%esp), %eax +; CHECK-32-NEXT: andl $32767, %eax # imm = 0x7FFF +; CHECK-32-NEXT: cmpl $32641, %eax # imm = 0x7F81 +; CHECK-32-NEXT: setge %al +; CHECK-32-NEXT: retl +; +; CHECK-64-LABEL: isnan_bfloat_vec1: +; CHECK-64: # %bb.0: # %entry +; CHECK-64-NEXT: andl $32767, %edi # imm = 0x7FFF +; CHECK-64-NEXT: cmpl $32641, %edi # imm = 0x7F81 +; CHECK-64-NEXT: setge %al +; CHECK-64-NEXT: retq +entry: + %0 = bitcast <1 x i16> %x to <1 x bfloat> + %1 = tail call <1 x i1> @llvm.isnan.v1bf16(<1 x bfloat> %0) + ret <1 x i1> %1 +} + +define <1 x i1> @isnan_float_vec1(<1 x float> %x) nounwind { +; CHECK-32-LABEL: isnan_float_vec1: +; CHECK-32: # %bb.0: # %entry +; CHECK-32-NEXT: flds {{[0-9]+}}(%esp) +; CHECK-32-NEXT: fucomp %st(0) +; CHECK-32-NEXT: fnstsw %ax +; CHECK-32-NEXT: # kill: def $ah killed $ah killed $ax +; CHECK-32-NEXT: sahf +; CHECK-32-NEXT: setp %al +; CHECK-32-NEXT: retl +; +; CHECK-64-LABEL: isnan_float_vec1: +; CHECK-64: # %bb.0: # %entry +; CHECK-64-NEXT: ucomiss %xmm0, %xmm0 +; CHECK-64-NEXT: setp %al +; CHECK-64-NEXT: retq +entry: + %0 = tail call <1 x i1> @llvm.isnan.v1f32(<1 x float> %x) + ret <1 x i1> %0 +} + +define <1 x i1> @isnan_double_vec1(<1 x double> %x) nounwind { +; CHECK-32-LABEL: isnan_double_vec1: +; CHECK-32: # %bb.0: # %entry +; CHECK-32-NEXT: fldl {{[0-9]+}}(%esp) +; CHECK-32-NEXT: fucomp %st(0) +; CHECK-32-NEXT: fnstsw %ax +; CHECK-32-NEXT: # kill: def $ah killed $ah killed $ax +; CHECK-32-NEXT: sahf +; CHECK-32-NEXT: setp %al +; CHECK-32-NEXT: retl +; +; CHECK-64-LABEL: isnan_double_vec1: +; CHECK-64: # %bb.0: # %entry +; CHECK-64-NEXT: ucomisd %xmm0, %xmm0 +; CHECK-64-NEXT: setp %al +; CHECK-64-NEXT: retq +entry: + %0 = tail call <1 x i1> @llvm.isnan.v1f64(<1 x double> %x) + ret <1 x i1> %0 +} + +define <2 x i1> @isnan_half_vec2(<2 x half> %x) nounwind { +; CHECK-32-LABEL: isnan_half_vec2: +; CHECK-32: # %bb.0: # %entry +; CHECK-32-NEXT: movzwl {{[0-9]+}}(%esp), %ecx +; CHECK-32-NEXT: movzwl {{[0-9]+}}(%esp), %eax +; CHECK-32-NEXT: andl $32767, %eax # imm = 0x7FFF +; CHECK-32-NEXT: cmpl $31745, %eax # imm = 0x7C01 +; CHECK-32-NEXT: setge %al +; CHECK-32-NEXT: andl $32767, %ecx # imm = 0x7FFF +; CHECK-32-NEXT: cmpl $31745, %ecx # imm = 0x7C01 +; CHECK-32-NEXT: setge %dl +; CHECK-32-NEXT: retl +; +; CHECK-64-LABEL: isnan_half_vec2: +; CHECK-64: # %bb.0: # %entry +; CHECK-64-NEXT: movw %si, -{{[0-9]+}}(%rsp) +; CHECK-64-NEXT: movw %di, -{{[0-9]+}}(%rsp) +; CHECK-64-NEXT: movdqa -{{[0-9]+}}(%rsp), %xmm0 +; CHECK-64-NEXT: pand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0 +; CHECK-64-NEXT: pcmpgtw {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0 +; CHECK-64-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,0,0,0] +; CHECK-64-NEXT: pshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,5,5,5,5] +; CHECK-64-NEXT: retq +entry: + %0 = tail call <2 x i1> @llvm.isnan.v2f16(<2 x half> %x) + ret <2 x i1> %0 +} + +define <2 x i1> @isnan_bfloat_vec2(<2 x i16> %x) nounwind { +; CHECK-32-LABEL: isnan_bfloat_vec2: +; CHECK-32: # %bb.0: # %entry +; CHECK-32-NEXT: movzwl {{[0-9]+}}(%esp), %ecx +; CHECK-32-NEXT: movzwl {{[0-9]+}}(%esp), %eax +; CHECK-32-NEXT: andl $32767, %eax # imm = 0x7FFF +; CHECK-32-NEXT: cmpl $32641, %eax # imm = 0x7F81 +; CHECK-32-NEXT: setge %al +; CHECK-32-NEXT: andl $32767, %ecx # imm = 0x7FFF +; CHECK-32-NEXT: cmpl $32641, %ecx # imm = 0x7F81 +; CHECK-32-NEXT: setge %dl +; CHECK-32-NEXT: retl +; +; CHECK-64-LABEL: isnan_bfloat_vec2: +; CHECK-64: # %bb.0: # %entry +; CHECK-64-NEXT: pand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0 +; CHECK-64-NEXT: pcmpgtw {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0 +; CHECK-64-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,0,0,0] +; CHECK-64-NEXT: pshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,5,5,5,5] +; CHECK-64-NEXT: retq +entry: + %0 = bitcast <2 x i16> %x to <2 x bfloat> + %1 = tail call <2 x i1> @llvm.isnan.v2bf16(<2 x bfloat> %0) + ret <2 x i1> %1 +} + +define <2 x i1> @isnan_float_vec2(<2 x float> %x) nounwind { +; CHECK-32-LABEL: isnan_float_vec2: +; CHECK-32: # %bb.0: # %entry +; CHECK-32-NEXT: flds {{[0-9]+}}(%esp) +; CHECK-32-NEXT: flds {{[0-9]+}}(%esp) +; CHECK-32-NEXT: fucomp %st(0) +; CHECK-32-NEXT: fnstsw %ax +; CHECK-32-NEXT: # kill: def $ah killed $ah killed $ax +; CHECK-32-NEXT: sahf +; CHECK-32-NEXT: setp %cl +; CHECK-32-NEXT: fucomp %st(0) +; CHECK-32-NEXT: fnstsw %ax +; CHECK-32-NEXT: # kill: def $ah killed $ah killed $ax +; CHECK-32-NEXT: sahf +; CHECK-32-NEXT: setp %dl +; CHECK-32-NEXT: movl %ecx, %eax +; CHECK-32-NEXT: retl +; +; CHECK-64-LABEL: isnan_float_vec2: +; CHECK-64: # %bb.0: # %entry +; CHECK-64-NEXT: xorps %xmm1, %xmm1 +; CHECK-64-NEXT: cmpunordps %xmm0, %xmm1 +; CHECK-64-NEXT: shufps {{.*#+}} xmm1 = xmm1[0,1,1,3] +; CHECK-64-NEXT: movaps %xmm1, %xmm0 +; CHECK-64-NEXT: retq +entry: + %0 = tail call <2 x i1> @llvm.isnan.v2f32(<2 x float> %x) + ret <2 x i1> %0 +} + +define <2 x i1> @isnan_double_vec2(<2 x double> %x) nounwind { +; CHECK-32-LABEL: isnan_double_vec2: +; CHECK-32: # %bb.0: # %entry +; CHECK-32-NEXT: fldl {{[0-9]+}}(%esp) +; CHECK-32-NEXT: fldl {{[0-9]+}}(%esp) +; CHECK-32-NEXT: fucomp %st(0) +; CHECK-32-NEXT: fnstsw %ax +; CHECK-32-NEXT: # kill: def $ah killed $ah killed $ax +; CHECK-32-NEXT: sahf +; CHECK-32-NEXT: setp %cl +; CHECK-32-NEXT: fucomp %st(0) +; CHECK-32-NEXT: fnstsw %ax +; CHECK-32-NEXT: # kill: def $ah killed $ah killed $ax +; CHECK-32-NEXT: sahf +; CHECK-32-NEXT: setp %dl +; CHECK-32-NEXT: movl %ecx, %eax +; CHECK-32-NEXT: retl +; +; CHECK-64-LABEL: isnan_double_vec2: +; CHECK-64: # %bb.0: # %entry +; CHECK-64-NEXT: xorpd %xmm1, %xmm1 +; CHECK-64-NEXT: cmpunordpd %xmm1, %xmm0 +; CHECK-64-NEXT: retq +entry: + %0 = tail call <2 x i1> @llvm.isnan.v2f64(<2 x double> %x) + ret <2 x i1> %0 +} + +define <4 x i1> @isnan_half_vec4(<4 x half> %x) nounwind { +; CHECK-32-LABEL: isnan_half_vec4: +; CHECK-32: # %bb.0: # %entry +; CHECK-32-NEXT: pushl %ebx +; CHECK-32-NEXT: pushl %edi +; CHECK-32-NEXT: pushl %esi +; CHECK-32-NEXT: movl {{[0-9]+}}(%esp), %eax +; CHECK-32-NEXT: movzwl {{[0-9]+}}(%esp), %ecx +; CHECK-32-NEXT: movzwl {{[0-9]+}}(%esp), %edx +; CHECK-32-NEXT: movzwl {{[0-9]+}}(%esp), %esi +; CHECK-32-NEXT: movzwl {{[0-9]+}}(%esp), %edi +; CHECK-32-NEXT: andl $32767, %edi # imm = 0x7FFF +; CHECK-32-NEXT: cmpl $31745, %edi # imm = 0x7C01 +; CHECK-32-NEXT: setge %bl +; CHECK-32-NEXT: andl $32767, %esi # imm = 0x7FFF +; CHECK-32-NEXT: cmpl $31745, %esi # imm = 0x7C01 +; CHECK-32-NEXT: setge %bh +; CHECK-32-NEXT: addb %bh, %bh +; CHECK-32-NEXT: orb %bl, %bh +; CHECK-32-NEXT: andl $32767, %edx # imm = 0x7FFF +; CHECK-32-NEXT: cmpl $31745, %edx # imm = 0x7C01 +; CHECK-32-NEXT: setge %dl +; CHECK-32-NEXT: andl $32767, %ecx # imm = 0x7FFF +; CHECK-32-NEXT: cmpl $31745, %ecx # imm = 0x7C01 +; CHECK-32-NEXT: setge %cl +; CHECK-32-NEXT: addb %cl, %cl +; CHECK-32-NEXT: orb %dl, %cl +; CHECK-32-NEXT: shlb $2, %cl +; CHECK-32-NEXT: orb %bh, %cl +; CHECK-32-NEXT: movb %cl, (%eax) +; CHECK-32-NEXT: popl %esi +; CHECK-32-NEXT: popl %edi +; CHECK-32-NEXT: popl %ebx +; CHECK-32-NEXT: retl $4 +; +; CHECK-64-LABEL: isnan_half_vec4: +; CHECK-64: # %bb.0: # %entry +; CHECK-64-NEXT: movw %cx, -{{[0-9]+}}(%rsp) +; CHECK-64-NEXT: movw %dx, -{{[0-9]+}}(%rsp) +; CHECK-64-NEXT: movw %si, -{{[0-9]+}}(%rsp) +; CHECK-64-NEXT: movw %di, -{{[0-9]+}}(%rsp) +; CHECK-64-NEXT: movdqa -{{[0-9]+}}(%rsp), %xmm0 +; CHECK-64-NEXT: pand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0 +; CHECK-64-NEXT: pcmpgtw {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0 +; CHECK-64-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3] +; CHECK-64-NEXT: retq +entry: + %0 = tail call <4 x i1> @llvm.isnan.v4f16(<4 x half> %x) + ret <4 x i1> %0 +} + +define <4 x i1> @isnan_bfloat_vec4(<4 x i16> %x) nounwind { +; CHECK-32-LABEL: isnan_bfloat_vec4: +; CHECK-32: # %bb.0: # %entry +; CHECK-32-NEXT: pushl %ebx +; CHECK-32-NEXT: pushl %edi +; CHECK-32-NEXT: pushl %esi +; CHECK-32-NEXT: movl {{[0-9]+}}(%esp), %eax +; CHECK-32-NEXT: movzwl {{[0-9]+}}(%esp), %ecx +; CHECK-32-NEXT: movzwl {{[0-9]+}}(%esp), %edx +; CHECK-32-NEXT: movzwl {{[0-9]+}}(%esp), %esi +; CHECK-32-NEXT: movzwl {{[0-9]+}}(%esp), %edi +; CHECK-32-NEXT: andl $32767, %edi # imm = 0x7FFF +; CHECK-32-NEXT: cmpl $32641, %edi # imm = 0x7F81 +; CHECK-32-NEXT: setge %bl +; CHECK-32-NEXT: andl $32767, %esi # imm = 0x7FFF +; CHECK-32-NEXT: cmpl $32641, %esi # imm = 0x7F81 +; CHECK-32-NEXT: setge %bh +; CHECK-32-NEXT: addb %bh, %bh +; CHECK-32-NEXT: orb %bl, %bh +; CHECK-32-NEXT: andl $32767, %edx # imm = 0x7FFF +; CHECK-32-NEXT: cmpl $32641, %edx # imm = 0x7F81 +; CHECK-32-NEXT: setge %dl +; CHECK-32-NEXT: andl $32767, %ecx # imm = 0x7FFF +; CHECK-32-NEXT: cmpl $32641, %ecx # imm = 0x7F81 +; CHECK-32-NEXT: setge %cl +; CHECK-32-NEXT: addb %cl, %cl +; CHECK-32-NEXT: orb %dl, %cl +; CHECK-32-NEXT: shlb $2, %cl +; CHECK-32-NEXT: orb %bh, %cl +; CHECK-32-NEXT: movb %cl, (%eax) +; CHECK-32-NEXT: popl %esi +; CHECK-32-NEXT: popl %edi +; CHECK-32-NEXT: popl %ebx +; CHECK-32-NEXT: retl $4 +; +; CHECK-64-LABEL: isnan_bfloat_vec4: +; CHECK-64: # %bb.0: # %entry +; CHECK-64-NEXT: pand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0 +; CHECK-64-NEXT: pcmpgtw {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0 +; CHECK-64-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3] +; CHECK-64-NEXT: retq +entry: + %0 = bitcast <4 x i16> %x to <4 x bfloat> + %1 = tail call <4 x i1> @llvm.isnan.v4bf16(<4 x bfloat> %0) + ret <4 x i1> %1 +} + +define <4 x i1> @isnan_float_vec4(<4 x float> %x) nounwind { +; CHECK-32-LABEL: isnan_float_vec4: +; CHECK-32: # %bb.0: # %entry +; CHECK-32-NEXT: movl {{[0-9]+}}(%esp), %ecx +; CHECK-32-NEXT: flds {{[0-9]+}}(%esp) +; CHECK-32-NEXT: flds {{[0-9]+}}(%esp) +; CHECK-32-NEXT: flds {{[0-9]+}}(%esp) +; CHECK-32-NEXT: flds {{[0-9]+}}(%esp) +; CHECK-32-NEXT: fucomp %st(0) +; CHECK-32-NEXT: fnstsw %ax +; CHECK-32-NEXT: # kill: def $ah killed $ah killed $ax +; CHECK-32-NEXT: sahf +; CHECK-32-NEXT: setp %dl +; CHECK-32-NEXT: fucomp %st(0) +; CHECK-32-NEXT: fnstsw %ax +; CHECK-32-NEXT: # kill: def $ah killed $ah killed $ax +; CHECK-32-NEXT: sahf +; CHECK-32-NEXT: setp %dh +; CHECK-32-NEXT: addb %dh, %dh +; CHECK-32-NEXT: orb %dl, %dh +; CHECK-32-NEXT: fucomp %st(0) +; CHECK-32-NEXT: fnstsw %ax +; CHECK-32-NEXT: # kill: def $ah killed $ah killed $ax +; CHECK-32-NEXT: sahf +; CHECK-32-NEXT: setp %dl +; CHECK-32-NEXT: fucomp %st(0) +; CHECK-32-NEXT: fnstsw %ax +; CHECK-32-NEXT: # kill: def $ah killed $ah killed $ax +; CHECK-32-NEXT: sahf +; CHECK-32-NEXT: setp %al +; CHECK-32-NEXT: addb %al, %al +; CHECK-32-NEXT: orb %dl, %al +; CHECK-32-NEXT: shlb $2, %al +; CHECK-32-NEXT: orb %dh, %al +; CHECK-32-NEXT: movb %al, (%ecx) +; CHECK-32-NEXT: movl %ecx, %eax +; CHECK-32-NEXT: retl $4 +; +; CHECK-64-LABEL: isnan_float_vec4: +; CHECK-64: # %bb.0: # %entry +; CHECK-64-NEXT: xorps %xmm1, %xmm1 +; CHECK-64-NEXT: cmpunordps %xmm1, %xmm0 +; CHECK-64-NEXT: retq +entry: + %0 = tail call <4 x i1> @llvm.isnan.v4f32(<4 x float> %x) + ret <4 x i1> %0 +} + +define <4 x i1> @isnan_double_vec4(<4 x double> %x) nounwind { +; CHECK-32-LABEL: isnan_double_vec4: +; CHECK-32: # %bb.0: # %entry +; CHECK-32-NEXT: movl {{[0-9]+}}(%esp), %ecx +; CHECK-32-NEXT: fldl {{[0-9]+}}(%esp) +; CHECK-32-NEXT: fldl {{[0-9]+}}(%esp) +; CHECK-32-NEXT: fldl {{[0-9]+}}(%esp) +; CHECK-32-NEXT: fldl {{[0-9]+}}(%esp) +; CHECK-32-NEXT: fucomp %st(0) +; CHECK-32-NEXT: fnstsw %ax +; CHECK-32-NEXT: # kill: def $ah killed $ah killed $ax +; CHECK-32-NEXT: sahf +; CHECK-32-NEXT: setp %dl +; CHECK-32-NEXT: fucomp %st(0) +; CHECK-32-NEXT: fnstsw %ax +; CHECK-32-NEXT: # kill: def $ah killed $ah killed $ax +; CHECK-32-NEXT: sahf +; CHECK-32-NEXT: setp %dh +; CHECK-32-NEXT: addb %dh, %dh +; CHECK-32-NEXT: orb %dl, %dh +; CHECK-32-NEXT: fucomp %st(0) +; CHECK-32-NEXT: fnstsw %ax +; CHECK-32-NEXT: # kill: def $ah killed $ah killed $ax +; CHECK-32-NEXT: sahf +; CHECK-32-NEXT: setp %dl +; CHECK-32-NEXT: fucomp %st(0) +; CHECK-32-NEXT: fnstsw %ax +; CHECK-32-NEXT: # kill: def $ah killed $ah killed $ax +; CHECK-32-NEXT: sahf +; CHECK-32-NEXT: setp %al +; CHECK-32-NEXT: addb %al, %al +; CHECK-32-NEXT: orb %dl, %al +; CHECK-32-NEXT: shlb $2, %al +; CHECK-32-NEXT: orb %dh, %al +; CHECK-32-NEXT: movb %al, (%ecx) +; CHECK-32-NEXT: movl %ecx, %eax +; CHECK-32-NEXT: retl $4 +; +; CHECK-64-LABEL: isnan_double_vec4: +; CHECK-64: # %bb.0: # %entry +; CHECK-64-NEXT: xorpd %xmm2, %xmm2 +; CHECK-64-NEXT: cmpunordpd %xmm2, %xmm1 +; CHECK-64-NEXT: cmpunordpd %xmm2, %xmm0 +; CHECK-64-NEXT: packssdw %xmm1, %xmm0 +; CHECK-64-NEXT: retq +entry: + %0 = tail call <4 x i1> @llvm.isnan.v4f64(<4 x double> %x) + ret <4 x i1> %0 +} + + +define <1 x i1> @isnan_half_vec1_strictfp(<1 x half> %x) strictfp nounwind { +; CHECK-32-LABEL: isnan_half_vec1_strictfp: +; CHECK-32: # %bb.0: # %entry +; CHECK-32-NEXT: movzwl {{[0-9]+}}(%esp), %eax +; CHECK-32-NEXT: andl $32767, %eax # imm = 0x7FFF +; CHECK-32-NEXT: cmpl $31745, %eax # imm = 0x7C01 +; CHECK-32-NEXT: setge %al +; CHECK-32-NEXT: retl +; +; CHECK-64-LABEL: isnan_half_vec1_strictfp: +; CHECK-64: # %bb.0: # %entry +; CHECK-64-NEXT: andl $32767, %edi # imm = 0x7FFF +; CHECK-64-NEXT: cmpl $31745, %edi # imm = 0x7C01 +; CHECK-64-NEXT: setge %al +; CHECK-64-NEXT: retq +entry: + %0 = tail call <1 x i1> @llvm.isnan.v1f16(<1 x half> %x) + ret <1 x i1> %0 +} + +define <1 x i1> @isnan_bfloat_vec1_strictfp(<1 x i16> %x) strictfp nounwind { +; CHECK-32-LABEL: isnan_bfloat_vec1_strictfp: +; CHECK-32: # %bb.0: # %entry +; CHECK-32-NEXT: movzwl {{[0-9]+}}(%esp), %eax +; CHECK-32-NEXT: andl $32767, %eax # imm = 0x7FFF +; CHECK-32-NEXT: cmpl $32641, %eax # imm = 0x7F81 +; CHECK-32-NEXT: setge %al +; CHECK-32-NEXT: retl +; +; CHECK-64-LABEL: isnan_bfloat_vec1_strictfp: +; CHECK-64: # %bb.0: # %entry +; CHECK-64-NEXT: andl $32767, %edi # imm = 0x7FFF +; CHECK-64-NEXT: cmpl $32641, %edi # imm = 0x7F81 +; CHECK-64-NEXT: setge %al +; CHECK-64-NEXT: retq +entry: + %0 = bitcast <1 x i16> %x to <1 x bfloat> + %1 = tail call <1 x i1> @llvm.isnan.v1bf16(<1 x bfloat> %0) + ret <1 x i1> %1 +} + +define <1 x i1> @isnan_float_vec1_strictfp(<1 x float> %x) strictfp nounwind { +; CHECK-32-LABEL: isnan_float_vec1_strictfp: +; CHECK-32: # %bb.0: # %entry +; CHECK-32-NEXT: movl $2147483647, %eax # imm = 0x7FFFFFFF +; CHECK-32-NEXT: andl {{[0-9]+}}(%esp), %eax +; CHECK-32-NEXT: cmpl $2139095041, %eax # imm = 0x7F800001 +; CHECK-32-NEXT: setge %al +; CHECK-32-NEXT: retl +; +; CHECK-64-LABEL: isnan_float_vec1_strictfp: +; CHECK-64: # %bb.0: # %entry +; CHECK-64-NEXT: movd %xmm0, %eax +; CHECK-64-NEXT: andl $2147483647, %eax # imm = 0x7FFFFFFF +; CHECK-64-NEXT: cmpl $2139095041, %eax # imm = 0x7F800001 +; CHECK-64-NEXT: setge %al +; CHECK-64-NEXT: retq +entry: + %0 = tail call <1 x i1> @llvm.isnan.v1f32(<1 x float> %x) + ret <1 x i1> %0 +} + +define <1 x i1> @isnan_double_vec1_strictfp(<1 x double> %x) strictfp nounwind { +; CHECK-32-LABEL: isnan_double_vec1_strictfp: +; CHECK-32: # %bb.0: # %entry +; CHECK-32-NEXT: pushl %ebp +; CHECK-32-NEXT: movl %esp, %ebp +; CHECK-32-NEXT: andl $-8, %esp +; CHECK-32-NEXT: subl $8, %esp +; CHECK-32-NEXT: fldl 8(%ebp) +; CHECK-32-NEXT: fstpl (%esp) +; CHECK-32-NEXT: wait +; CHECK-32-NEXT: movl $2147483647, %eax # imm = 0x7FFFFFFF +; CHECK-32-NEXT: andl {{[0-9]+}}(%esp), %eax +; CHECK-32-NEXT: xorl %ecx, %ecx +; CHECK-32-NEXT: cmpl (%esp), %ecx +; CHECK-32-NEXT: movl $2146435072, %ecx # imm = 0x7FF00000 +; CHECK-32-NEXT: sbbl %eax, %ecx +; CHECK-32-NEXT: setl %al +; CHECK-32-NEXT: movl %ebp, %esp +; CHECK-32-NEXT: popl %ebp +; CHECK-32-NEXT: retl +; +; CHECK-64-LABEL: isnan_double_vec1_strictfp: +; CHECK-64: # %bb.0: # %entry +; CHECK-64-NEXT: movq %xmm0, %rax +; CHECK-64-NEXT: movabsq $9223372036854775807, %rcx # imm = 0x7FFFFFFFFFFFFFFF +; CHECK-64-NEXT: andq %rax, %rcx +; CHECK-64-NEXT: movabsq $9218868437227405312, %rax # imm = 0x7FF0000000000000 +; CHECK-64-NEXT: cmpq %rax, %rcx +; CHECK-64-NEXT: setg %al +; CHECK-64-NEXT: retq +entry: + %0 = tail call <1 x i1> @llvm.isnan.v1f64(<1 x double> %x) + ret <1 x i1> %0 +} + +define <2 x i1> @isnan_half_vec2_strictfp(<2 x half> %x) strictfp nounwind { +; CHECK-32-LABEL: isnan_half_vec2_strictfp: +; CHECK-32: # %bb.0: # %entry +; CHECK-32-NEXT: movzwl {{[0-9]+}}(%esp), %ecx +; CHECK-32-NEXT: movzwl {{[0-9]+}}(%esp), %eax +; CHECK-32-NEXT: andl $32767, %eax # imm = 0x7FFF +; CHECK-32-NEXT: cmpl $31745, %eax # imm = 0x7C01 +; CHECK-32-NEXT: setge %al +; CHECK-32-NEXT: andl $32767, %ecx # imm = 0x7FFF +; CHECK-32-NEXT: cmpl $31745, %ecx # imm = 0x7C01 +; CHECK-32-NEXT: setge %dl +; CHECK-32-NEXT: retl +; +; CHECK-64-LABEL: isnan_half_vec2_strictfp: +; CHECK-64: # %bb.0: # %entry +; CHECK-64-NEXT: movw %si, -{{[0-9]+}}(%rsp) +; CHECK-64-NEXT: movw %di, -{{[0-9]+}}(%rsp) +; CHECK-64-NEXT: movdqa -{{[0-9]+}}(%rsp), %xmm0 +; CHECK-64-NEXT: pand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0 +; CHECK-64-NEXT: pcmpgtw {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0 +; CHECK-64-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,0,0,0] +; CHECK-64-NEXT: pshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,5,5,5,5] +; CHECK-64-NEXT: retq +entry: + %0 = tail call <2 x i1> @llvm.isnan.v2f16(<2 x half> %x) + ret <2 x i1> %0 +} + +define <2 x i1> @isnan_bfloat_vec2_strictfp(<2 x i16> %x) strictfp nounwind { +; CHECK-32-LABEL: isnan_bfloat_vec2_strictfp: +; CHECK-32: # %bb.0: # %entry +; CHECK-32-NEXT: movzwl {{[0-9]+}}(%esp), %ecx +; CHECK-32-NEXT: movzwl {{[0-9]+}}(%esp), %eax +; CHECK-32-NEXT: andl $32767, %eax # imm = 0x7FFF +; CHECK-32-NEXT: cmpl $32641, %eax # imm = 0x7F81 +; CHECK-32-NEXT: setge %al +; CHECK-32-NEXT: andl $32767, %ecx # imm = 0x7FFF +; CHECK-32-NEXT: cmpl $32641, %ecx # imm = 0x7F81 +; CHECK-32-NEXT: setge %dl +; CHECK-32-NEXT: retl +; +; CHECK-64-LABEL: isnan_bfloat_vec2_strictfp: +; CHECK-64: # %bb.0: # %entry +; CHECK-64-NEXT: pand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0 +; CHECK-64-NEXT: pcmpgtw {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0 +; CHECK-64-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,0,0,0] +; CHECK-64-NEXT: pshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,5,5,5,5] +; CHECK-64-NEXT: retq +entry: + %0 = bitcast <2 x i16> %x to <2 x bfloat> + %1 = tail call <2 x i1> @llvm.isnan.v2bf16(<2 x bfloat> %0) + ret <2 x i1> %1 +} + +define <2 x i1> @isnan_float_vec2_strictfp(<2 x float> %x) strictfp nounwind { +; CHECK-32-LABEL: isnan_float_vec2_strictfp: +; CHECK-32: # %bb.0: # %entry +; CHECK-32-NEXT: movl $2147483647, %ecx # imm = 0x7FFFFFFF +; CHECK-32-NEXT: movl {{[0-9]+}}(%esp), %eax +; CHECK-32-NEXT: andl %ecx, %eax +; CHECK-32-NEXT: cmpl $2139095041, %eax # imm = 0x7F800001 +; CHECK-32-NEXT: setge %al +; CHECK-32-NEXT: andl {{[0-9]+}}(%esp), %ecx +; CHECK-32-NEXT: cmpl $2139095041, %ecx # imm = 0x7F800001 +; CHECK-32-NEXT: setge %dl +; CHECK-32-NEXT: retl +; +; CHECK-64-LABEL: isnan_float_vec2_strictfp: +; CHECK-64: # %bb.0: # %entry +; CHECK-64-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,1,1,3] +; CHECK-64-NEXT: andps {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0 +; CHECK-64-NEXT: pcmpgtd {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0 +; CHECK-64-NEXT: retq +entry: + %0 = tail call <2 x i1> @llvm.isnan.v2f32(<2 x float> %x) + ret <2 x i1> %0 +} + +define <2 x i1> @isnan_double_vec2_strictfp(<2 x double> %x) strictfp nounwind { +; CHECK-32-LABEL: isnan_double_vec2_strictfp: +; CHECK-32: # %bb.0: # %entry +; CHECK-32-NEXT: pushl %ebp +; CHECK-32-NEXT: movl %esp, %ebp +; CHECK-32-NEXT: pushl %edi +; CHECK-32-NEXT: pushl %esi +; CHECK-32-NEXT: andl $-8, %esp +; CHECK-32-NEXT: subl $16, %esp +; CHECK-32-NEXT: fldl 8(%ebp) +; CHECK-32-NEXT: fstpl (%esp) +; CHECK-32-NEXT: fldl 16(%ebp) +; CHECK-32-NEXT: fstpl {{[0-9]+}}(%esp) +; CHECK-32-NEXT: wait +; CHECK-32-NEXT: movl $2147483647, %ecx # imm = 0x7FFFFFFF +; CHECK-32-NEXT: movl {{[0-9]+}}(%esp), %eax +; CHECK-32-NEXT: andl %ecx, %eax +; CHECK-32-NEXT: xorl %edx, %edx +; CHECK-32-NEXT: cmpl (%esp), %edx +; CHECK-32-NEXT: movl $2146435072, %esi # imm = 0x7FF00000 +; CHECK-32-NEXT: movl $2146435072, %edi # imm = 0x7FF00000 +; CHECK-32-NEXT: sbbl %eax, %edi +; CHECK-32-NEXT: setl %al +; CHECK-32-NEXT: andl {{[0-9]+}}(%esp), %ecx +; CHECK-32-NEXT: cmpl {{[0-9]+}}(%esp), %edx +; CHECK-32-NEXT: sbbl %ecx, %esi +; CHECK-32-NEXT: setl %dl +; CHECK-32-NEXT: leal -8(%ebp), %esp +; CHECK-32-NEXT: popl %esi +; CHECK-32-NEXT: popl %edi +; CHECK-32-NEXT: popl %ebp +; CHECK-32-NEXT: retl +; +; CHECK-64-LABEL: isnan_double_vec2_strictfp: +; CHECK-64: # %bb.0: # %entry +; CHECK-64-NEXT: pand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0 +; CHECK-64-NEXT: pxor {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0 +; CHECK-64-NEXT: movdqa {{.*#+}} xmm1 = [9218868439374888960,9218868439374888960] +; CHECK-64-NEXT: movdqa %xmm0, %xmm2 +; CHECK-64-NEXT: pcmpgtd %xmm1, %xmm2 +; CHECK-64-NEXT: pshufd {{.*#+}} xmm3 = xmm2[0,0,2,2] +; CHECK-64-NEXT: pcmpeqd %xmm1, %xmm0 +; CHECK-64-NEXT: pshufd {{.*#+}} xmm1 = xmm0[1,1,3,3] +; CHECK-64-NEXT: pand %xmm3, %xmm1 +; CHECK-64-NEXT: pshufd {{.*#+}} xmm0 = xmm2[1,1,3,3] +; CHECK-64-NEXT: por %xmm1, %xmm0 +; CHECK-64-NEXT: retq +entry: + %0 = tail call <2 x i1> @llvm.isnan.v2f64(<2 x double> %x) + ret <2 x i1> %0 +} + +define <4 x i1> @isnan_half_vec4_strictfp(<4 x half> %x) strictfp nounwind { +; CHECK-32-LABEL: isnan_half_vec4_strictfp: +; CHECK-32: # %bb.0: # %entry +; CHECK-32-NEXT: pushl %ebx +; CHECK-32-NEXT: pushl %edi +; CHECK-32-NEXT: pushl %esi +; CHECK-32-NEXT: movl {{[0-9]+}}(%esp), %eax +; CHECK-32-NEXT: movzwl {{[0-9]+}}(%esp), %ecx +; CHECK-32-NEXT: movzwl {{[0-9]+}}(%esp), %edx +; CHECK-32-NEXT: movzwl {{[0-9]+}}(%esp), %esi +; CHECK-32-NEXT: movzwl {{[0-9]+}}(%esp), %edi +; CHECK-32-NEXT: andl $32767, %edi # imm = 0x7FFF +; CHECK-32-NEXT: cmpl $31745, %edi # imm = 0x7C01 +; CHECK-32-NEXT: setge %bl +; CHECK-32-NEXT: andl $32767, %esi # imm = 0x7FFF +; CHECK-32-NEXT: cmpl $31745, %esi # imm = 0x7C01 +; CHECK-32-NEXT: setge %bh +; CHECK-32-NEXT: addb %bh, %bh +; CHECK-32-NEXT: orb %bl, %bh +; CHECK-32-NEXT: andl $32767, %edx # imm = 0x7FFF +; CHECK-32-NEXT: cmpl $31745, %edx # imm = 0x7C01 +; CHECK-32-NEXT: setge %dl +; CHECK-32-NEXT: andl $32767, %ecx # imm = 0x7FFF +; CHECK-32-NEXT: cmpl $31745, %ecx # imm = 0x7C01 +; CHECK-32-NEXT: setge %cl +; CHECK-32-NEXT: addb %cl, %cl +; CHECK-32-NEXT: orb %dl, %cl +; CHECK-32-NEXT: shlb $2, %cl +; CHECK-32-NEXT: orb %bh, %cl +; CHECK-32-NEXT: movb %cl, (%eax) +; CHECK-32-NEXT: popl %esi +; CHECK-32-NEXT: popl %edi +; CHECK-32-NEXT: popl %ebx +; CHECK-32-NEXT: retl $4 +; +; CHECK-64-LABEL: isnan_half_vec4_strictfp: +; CHECK-64: # %bb.0: # %entry +; CHECK-64-NEXT: movw %cx, -{{[0-9]+}}(%rsp) +; CHECK-64-NEXT: movw %dx, -{{[0-9]+}}(%rsp) +; CHECK-64-NEXT: movw %si, -{{[0-9]+}}(%rsp) +; CHECK-64-NEXT: movw %di, -{{[0-9]+}}(%rsp) +; CHECK-64-NEXT: movdqa -{{[0-9]+}}(%rsp), %xmm0 +; CHECK-64-NEXT: pand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0 +; CHECK-64-NEXT: pcmpgtw {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0 +; CHECK-64-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3] +; CHECK-64-NEXT: retq +entry: + %0 = tail call <4 x i1> @llvm.isnan.v4f16(<4 x half> %x) + ret <4 x i1> %0 +} + +define <4 x i1> @isnan_bfloat_vec4_strictfp(<4 x i16> %x) strictfp nounwind { +; CHECK-32-LABEL: isnan_bfloat_vec4_strictfp: +; CHECK-32: # %bb.0: # %entry +; CHECK-32-NEXT: pushl %ebx +; CHECK-32-NEXT: pushl %edi +; CHECK-32-NEXT: pushl %esi +; CHECK-32-NEXT: movl {{[0-9]+}}(%esp), %eax +; CHECK-32-NEXT: movzwl {{[0-9]+}}(%esp), %ecx +; CHECK-32-NEXT: movzwl {{[0-9]+}}(%esp), %edx +; CHECK-32-NEXT: movzwl {{[0-9]+}}(%esp), %esi +; CHECK-32-NEXT: movzwl {{[0-9]+}}(%esp), %edi +; CHECK-32-NEXT: andl $32767, %edi # imm = 0x7FFF +; CHECK-32-NEXT: cmpl $32641, %edi # imm = 0x7F81 +; CHECK-32-NEXT: setge %bl +; CHECK-32-NEXT: andl $32767, %esi # imm = 0x7FFF +; CHECK-32-NEXT: cmpl $32641, %esi # imm = 0x7F81 +; CHECK-32-NEXT: setge %bh +; CHECK-32-NEXT: addb %bh, %bh +; CHECK-32-NEXT: orb %bl, %bh +; CHECK-32-NEXT: andl $32767, %edx # imm = 0x7FFF +; CHECK-32-NEXT: cmpl $32641, %edx # imm = 0x7F81 +; CHECK-32-NEXT: setge %dl +; CHECK-32-NEXT: andl $32767, %ecx # imm = 0x7FFF +; CHECK-32-NEXT: cmpl $32641, %ecx # imm = 0x7F81 +; CHECK-32-NEXT: setge %cl +; CHECK-32-NEXT: addb %cl, %cl +; CHECK-32-NEXT: orb %dl, %cl +; CHECK-32-NEXT: shlb $2, %cl +; CHECK-32-NEXT: orb %bh, %cl +; CHECK-32-NEXT: movb %cl, (%eax) +; CHECK-32-NEXT: popl %esi +; CHECK-32-NEXT: popl %edi +; CHECK-32-NEXT: popl %ebx +; CHECK-32-NEXT: retl $4 +; +; CHECK-64-LABEL: isnan_bfloat_vec4_strictfp: +; CHECK-64: # %bb.0: # %entry +; CHECK-64-NEXT: pand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0 +; CHECK-64-NEXT: pcmpgtw {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0 +; CHECK-64-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3] +; CHECK-64-NEXT: retq +entry: + %0 = bitcast <4 x i16> %x to <4 x bfloat> + %1 = tail call <4 x i1> @llvm.isnan.v4bf16(<4 x bfloat> %0) + ret <4 x i1> %1 +} + +define <4 x i1> @isnan_float_vec4_strictfp(<4 x float> %x) strictfp nounwind { +; CHECK-32-LABEL: isnan_float_vec4_strictfp: +; CHECK-32: # %bb.0: # %entry +; CHECK-32-NEXT: pushl %esi +; CHECK-32-NEXT: movl {{[0-9]+}}(%esp), %eax +; CHECK-32-NEXT: movl $2147483647, %ecx # imm = 0x7FFFFFFF +; CHECK-32-NEXT: movl {{[0-9]+}}(%esp), %edx +; CHECK-32-NEXT: andl %ecx, %edx +; CHECK-32-NEXT: cmpl $2139095041, %edx # imm = 0x7F800001 +; CHECK-32-NEXT: setge %dl +; CHECK-32-NEXT: movl {{[0-9]+}}(%esp), %esi +; CHECK-32-NEXT: andl %ecx, %esi +; CHECK-32-NEXT: cmpl $2139095041, %esi # imm = 0x7F800001 +; CHECK-32-NEXT: setge %dh +; CHECK-32-NEXT: addb %dh, %dh +; CHECK-32-NEXT: orb %dl, %dh +; CHECK-32-NEXT: movl {{[0-9]+}}(%esp), %esi +; CHECK-32-NEXT: andl %ecx, %esi +; CHECK-32-NEXT: cmpl $2139095041, %esi # imm = 0x7F800001 +; CHECK-32-NEXT: setge %dl +; CHECK-32-NEXT: andl {{[0-9]+}}(%esp), %ecx +; CHECK-32-NEXT: cmpl $2139095041, %ecx # imm = 0x7F800001 +; CHECK-32-NEXT: setge %cl +; CHECK-32-NEXT: addb %cl, %cl +; CHECK-32-NEXT: orb %dl, %cl +; CHECK-32-NEXT: shlb $2, %cl +; CHECK-32-NEXT: orb %dh, %cl +; CHECK-32-NEXT: movb %cl, (%eax) +; CHECK-32-NEXT: popl %esi +; CHECK-32-NEXT: retl $4 +; +; CHECK-64-LABEL: isnan_float_vec4_strictfp: +; CHECK-64: # %bb.0: # %entry +; CHECK-64-NEXT: pand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0 +; CHECK-64-NEXT: pcmpgtd {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0 +; CHECK-64-NEXT: retq +entry: + %0 = tail call <4 x i1> @llvm.isnan.v4f32(<4 x float> %x) + ret <4 x i1> %0 +} + +define <4 x i1> @isnan_double_vec4_strictfp(<4 x double> %x) strictfp nounwind { +; CHECK-32-LABEL: isnan_double_vec4_strictfp: +; CHECK-32: # %bb.0: # %entry +; CHECK-32-NEXT: pushl %ebp +; CHECK-32-NEXT: movl %esp, %ebp +; CHECK-32-NEXT: pushl %edi +; CHECK-32-NEXT: pushl %esi +; CHECK-32-NEXT: andl $-8, %esp +; CHECK-32-NEXT: subl $32, %esp +; CHECK-32-NEXT: fldl 12(%ebp) +; CHECK-32-NEXT: fstpl (%esp) +; CHECK-32-NEXT: fldl 20(%ebp) +; CHECK-32-NEXT: fstpl {{[0-9]+}}(%esp) +; CHECK-32-NEXT: fldl 28(%ebp) +; CHECK-32-NEXT: fstpl {{[0-9]+}}(%esp) +; CHECK-32-NEXT: fldl 36(%ebp) +; CHECK-32-NEXT: fstpl {{[0-9]+}}(%esp) +; CHECK-32-NEXT: wait +; CHECK-32-NEXT: movl $2147483647, %eax # imm = 0x7FFFFFFF +; CHECK-32-NEXT: movl {{[0-9]+}}(%esp), %ecx +; CHECK-32-NEXT: andl %eax, %ecx +; CHECK-32-NEXT: xorl %edx, %edx +; CHECK-32-NEXT: cmpl (%esp), %edx +; CHECK-32-NEXT: movl $2146435072, %esi # imm = 0x7FF00000 +; CHECK-32-NEXT: sbbl %ecx, %esi +; CHECK-32-NEXT: setl %cl +; CHECK-32-NEXT: movl {{[0-9]+}}(%esp), %esi +; CHECK-32-NEXT: andl %eax, %esi +; CHECK-32-NEXT: cmpl {{[0-9]+}}(%esp), %edx +; CHECK-32-NEXT: movl $2146435072, %edi # imm = 0x7FF00000 +; CHECK-32-NEXT: sbbl %esi, %edi +; CHECK-32-NEXT: setl %ch +; CHECK-32-NEXT: addb %ch, %ch +; CHECK-32-NEXT: orb %cl, %ch +; CHECK-32-NEXT: movl {{[0-9]+}}(%esp), %esi +; CHECK-32-NEXT: andl %eax, %esi +; CHECK-32-NEXT: cmpl {{[0-9]+}}(%esp), %edx +; CHECK-32-NEXT: movl $2146435072, %edi # imm = 0x7FF00000 +; CHECK-32-NEXT: sbbl %esi, %edi +; CHECK-32-NEXT: setl %cl +; CHECK-32-NEXT: andl {{[0-9]+}}(%esp), %eax +; CHECK-32-NEXT: cmpl {{[0-9]+}}(%esp), %edx +; CHECK-32-NEXT: movl $2146435072, %edx # imm = 0x7FF00000 +; CHECK-32-NEXT: sbbl %eax, %edx +; CHECK-32-NEXT: setl %dl +; CHECK-32-NEXT: addb %dl, %dl +; CHECK-32-NEXT: orb %cl, %dl +; CHECK-32-NEXT: shlb $2, %dl +; CHECK-32-NEXT: orb %ch, %dl +; CHECK-32-NEXT: movl 8(%ebp), %eax +; CHECK-32-NEXT: movb %dl, (%eax) +; CHECK-32-NEXT: leal -8(%ebp), %esp +; CHECK-32-NEXT: popl %esi +; CHECK-32-NEXT: popl %edi +; CHECK-32-NEXT: popl %ebp +; CHECK-32-NEXT: retl $4 +; +; CHECK-64-LABEL: isnan_double_vec4_strictfp: +; CHECK-64: # %bb.0: # %entry +; CHECK-64-NEXT: movdqa {{.*#+}} xmm2 = [9223372036854775807,9223372036854775807] +; CHECK-64-NEXT: pand %xmm2, %xmm0 +; CHECK-64-NEXT: pand %xmm2, %xmm1 +; CHECK-64-NEXT: movdqa {{.*#+}} xmm2 = [2147483648,2147483648] +; CHECK-64-NEXT: pxor %xmm2, %xmm1 +; CHECK-64-NEXT: movdqa {{.*#+}} xmm3 = [9218868439374888960,9218868439374888960] +; CHECK-64-NEXT: movdqa %xmm1, %xmm4 +; CHECK-64-NEXT: pcmpgtd %xmm3, %xmm4 +; CHECK-64-NEXT: pshufd {{.*#+}} xmm5 = xmm4[0,0,2,2] +; CHECK-64-NEXT: pcmpeqd %xmm3, %xmm1 +; CHECK-64-NEXT: pshufd {{.*#+}} xmm1 = xmm1[1,1,3,3] +; CHECK-64-NEXT: pand %xmm5, %xmm1 +; CHECK-64-NEXT: pshufd {{.*#+}} xmm4 = xmm4[1,1,3,3] +; CHECK-64-NEXT: por %xmm1, %xmm4 +; CHECK-64-NEXT: pxor %xmm2, %xmm0 +; CHECK-64-NEXT: movdqa %xmm0, %xmm1 +; CHECK-64-NEXT: pcmpgtd %xmm3, %xmm1 +; CHECK-64-NEXT: pshufd {{.*#+}} xmm2 = xmm1[0,0,2,2] +; CHECK-64-NEXT: pcmpeqd %xmm3, %xmm0 +; CHECK-64-NEXT: pshufd {{.*#+}} xmm3 = xmm0[1,1,3,3] +; CHECK-64-NEXT: pand %xmm2, %xmm3 +; CHECK-64-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,1,3,3] +; CHECK-64-NEXT: por %xmm3, %xmm0 +; CHECK-64-NEXT: packssdw %xmm4, %xmm0 +; CHECK-64-NEXT: retq +entry: + %0 = tail call <4 x i1> @llvm.isnan.v4f64(<4 x double> %x) + ret <4 x i1> %0 +} + + +declare i1 @llvm.isnan.f16(half) +declare i1 @llvm.isnan.bf16(bfloat) +declare i1 @llvm.isnan.f32(float) +declare i1 @llvm.isnan.f64(double) +declare i1 @llvm.isnan.f80(x86_fp80) +declare <1 x i1> @llvm.isnan.v1f16(<1 x half>) +declare <1 x i1> @llvm.isnan.v1bf16(<1 x bfloat>) +declare <1 x i1> @llvm.isnan.v1f32(<1 x float>) +declare <1 x i1> @llvm.isnan.v1f64(<1 x double>) +declare <2 x i1> @llvm.isnan.v2f16(<2 x half>) +declare <2 x i1> @llvm.isnan.v2bf16(<2 x bfloat>) +declare <2 x i1> @llvm.isnan.v2f32(<2 x float>) +declare <2 x i1> @llvm.isnan.v2f64(<2 x double>) +declare <4 x i1> @llvm.isnan.v4f16(<4 x half>) +declare <4 x i1> @llvm.isnan.v4bf16(<4 x bfloat>) +declare <4 x i1> @llvm.isnan.v4f32(<4 x float>) +declare <4 x i1> @llvm.isnan.v4f64(<4 x double>) diff --git a/llvm/test/Transforms/InstCombine/fpclass.ll b/llvm/test/Transforms/InstCombine/fpclass.ll new file mode 100644 index 0000000..60c783f --- /dev/null +++ b/llvm/test/Transforms/InstCombine/fpclass.ll @@ -0,0 +1,73 @@ +; NOTE: Assertions have been autogenerated by utils/update_test_checks.py +; RUN: opt -S -instcombine < %s | FileCheck %s + +define i1 @isnan_f32_noflags(float %x, float %y) { +; CHECK-LABEL: @isnan_f32_noflags( +; CHECK-NEXT: [[R:%.*]] = fmul float [[X:%.*]], [[Y:%.*]] +; CHECK-NEXT: [[T:%.*]] = call i1 @llvm.isnan.f32(float [[R]]) +; CHECK-NEXT: ret i1 [[T]] +; + %r = fmul float %x, %y + %t = call i1 @llvm.isnan.f32(float %r) + ret i1 %t +} + + +define i1 @isnan_f32_load(float* %p) { + %r = load float, float* %p + %t = call i1 @llvm.isnan.f32(float %r) + ret i1 %t +} + +define i1 @isnan_f32_ninf(float %x, float %y) { +; CHECK-LABEL: @isnan_f32_ninf( +; CHECK-NEXT: [[R:%.*]] = fsub ninf float [[X:%.*]], [[Y:%.*]] +; CHECK-NEXT: [[T:%.*]] = call i1 @llvm.isnan.f32(float [[R]]) +; CHECK-NEXT: ret i1 [[T]] +; + %r = fsub ninf float %x, %y + %t = call i1 @llvm.isnan.f32(float %r) + ret i1 %t +} + +define i1 @isnan_f32_nsz(float %x, float %y) { +; CHECK-LABEL: @isnan_f32_nsz( +; CHECK-NEXT: [[R:%.*]] = fdiv nsz float [[X:%.*]], [[Y:%.*]] +; CHECK-NEXT: [[T:%.*]] = call i1 @llvm.isnan.f32(float [[R]]) +; CHECK-NEXT: ret i1 [[T]] +; + %r = fdiv nsz float %x, %y + %t = call i1 @llvm.isnan.f32(float %r) + ret i1 %t +} + +define i1 @isnan_f32(float %x, float %y) { +; CHECK-LABEL: @isnan_f32( +; CHECK-NEXT: ret i1 false +; + %r = fadd nnan float %x, %y + %t = call i1 @llvm.isnan.f32(float %r) + ret i1 %t +} + +define <1 x i1> @isnan_v1f32(<1 x float> %x, <1 x float> %y) { +; CHECK-LABEL: @isnan_v1f32( +; CHECK-NEXT: ret <1 x i1> zeroinitializer +; + %r = fadd nnan <1 x float> %x, %y + %t = call <1 x i1> @llvm.isnan.v1f32(<1 x float> %r) + ret <1 x i1> %t +} + +define <2 x i1> @isnan_v2f32(<2 x float> %x, <2 x float> %y) { +; CHECK-LABEL: @isnan_v2f32( +; CHECK-NEXT: ret <2 x i1> zeroinitializer +; + %r = fadd nnan <2 x float> %x, %y + %t = call <2 x i1> @llvm.isnan.v2f32(<2 x float> %r) + ret <2 x i1> %t +} + +declare i1 @llvm.isnan.f32(float %r) +declare <1 x i1> @llvm.isnan.v1f32(<1 x float> %r) +declare <2 x i1> @llvm.isnan.v2f32(<2 x float> %r) diff --git a/llvm/test/Transforms/InstSimplify/ConstProp/fpclassify.ll b/llvm/test/Transforms/InstSimplify/ConstProp/fpclassify.ll new file mode 100644 index 0000000..27488e9 --- /dev/null +++ b/llvm/test/Transforms/InstSimplify/ConstProp/fpclassify.ll @@ -0,0 +1,35 @@ +; NOTE: Assertions have been autogenerated by utils/update_test_checks.py +; RUN: opt < %s -instsimplify -S | FileCheck %s + +define i1 @isnan_01() { +; CHECK-LABEL: @isnan_01( +; CHECK-NEXT: entry: +; CHECK-NEXT: ret i1 true +; +entry: + %0 = tail call i1 @llvm.isnan.f32(float 0x7FF8000000000000) + ret i1 %0 +} + +define i1 @isnan_02() { +; CHECK-LABEL: @isnan_02( +; CHECK-NEXT: entry: +; CHECK-NEXT: ret i1 false +; +entry: + %0 = tail call i1 @llvm.isnan.f32(float 0x7FF0000000000000) + ret i1 %0 +} + +define <4 x i1> @isnan_03() { +; CHECK-LABEL: @isnan_03( +; CHECK-NEXT: entry: +; CHECK-NEXT: ret <4 x i1> +; +entry: + %0 = tail call <4 x i1> @llvm.isnan.v4f32(<4 x float>) + ret <4 x i1> %0 +} + +declare i1 @llvm.isnan.f32(float) +declare <4 x i1> @llvm.isnan.v4f32(<4 x float>) -- 2.7.4