[clang] 1b6eb56 - Stop traping on sNaN in __builtin_isinf
Thomas Preud'homme via cfe-commits
cfe-commits at lists.llvm.org
Tue Mar 2 07:54:57 PST 2021
Author: Thomas Preud'homme
Date: 2021-03-02T15:54:56Z
New Revision: 1b6eb56aa0ea2931866455a21a138fc09c08e905
URL: https://github.com/llvm/llvm-project/commit/1b6eb56aa0ea2931866455a21a138fc09c08e905
DIFF: https://github.com/llvm/llvm-project/commit/1b6eb56aa0ea2931866455a21a138fc09c08e905.diff
LOG: Stop traping on sNaN in __builtin_isinf
__builtin_isinf currently generates a floating-point compare operation
which triggers a trap when faced with a signaling NaN in StrictFP mode.
This commit uses integer operations instead to not generate any trap in
such a case.
Reviewed By: mibintc
Differential Revision: https://reviews.llvm.org/D97125
Added:
Modified:
clang/lib/CodeGen/CGBuiltin.cpp
clang/test/CodeGen/X86/strictfp_builtins.c
clang/test/CodeGen/aarch64-strictfp-builtins.c
clang/test/CodeGen/builtin_float_strictfp.c
clang/test/CodeGen/strictfp_builtins.c
Removed:
################################################################################
diff --git a/clang/lib/CodeGen/CGBuiltin.cpp b/clang/lib/CodeGen/CGBuiltin.cpp
index 5409a12698c4..1a5dfdedc037 100644
--- a/clang/lib/CodeGen/CGBuiltin.cpp
+++ b/clang/lib/CodeGen/CGBuiltin.cpp
@@ -3078,15 +3078,37 @@ RValue CodeGenFunction::EmitBuiltinExpr(const GlobalDecl GD, unsigned BuiltinID,
// isfinite(x) --> fabs(x) != infinity
// x != NaN via the ordered compare in either case.
CodeGenFunction::CGFPOptionsRAII FPOptsRAII(*this, E);
- // FIXME: for strictfp/IEEE-754 we need to not trap on SNaN here.
Value *V = EmitScalarExpr(E->getArg(0));
- Value *Fabs = EmitFAbs(*this, V);
- Constant *Infinity = ConstantFP::getInfinity(V->getType());
- CmpInst::Predicate Pred = (BuiltinID == Builtin::BI__builtin_isinf)
- ? CmpInst::FCMP_OEQ
- : CmpInst::FCMP_ONE;
- Value *FCmp = Builder.CreateFCmp(Pred, Fabs, Infinity, "cmpinf");
- return RValue::get(Builder.CreateZExt(FCmp, ConvertType(E->getType())));
+ llvm::Type *Ty = V->getType();
+ if (!Builder.getIsFPConstrained() ||
+ Builder.getDefaultConstrainedExcept() == fp::ebIgnore ||
+ !Ty->isIEEE()) {
+ Value *Fabs = EmitFAbs(*this, V);
+ Constant *Infinity = ConstantFP::getInfinity(V->getType());
+ CmpInst::Predicate Pred = (BuiltinID == Builtin::BI__builtin_isinf)
+ ? CmpInst::FCMP_OEQ
+ : CmpInst::FCMP_ONE;
+ Value *FCmp = Builder.CreateFCmp(Pred, Fabs, Infinity, "cmpinf");
+ return RValue::get(Builder.CreateZExt(FCmp, ConvertType(E->getType())));
+ }
+
+ if (Value *Result = getTargetHooks().testFPKind(V, BuiltinID, Builder, CGM))
+ return RValue::get(Result);
+
+ // Inf values have all exp bits set and a zero significand. Therefore:
+ // isinf(V) == ((V << 1) == ((exp mask) << 1))
+ unsigned bitsize = Ty->getScalarSizeInBits();
+ llvm::IntegerType *IntTy = Builder.getIntNTy(bitsize);
+ Value *IntV = Builder.CreateBitCast(V, IntTy);
+ Value *Shl1 = Builder.CreateShl(IntV, 1);
+ const llvm::fltSemantics &Semantics = Ty->getFltSemantics();
+ APInt ExpMask = APFloat::getInf(Semantics).bitcastToAPInt();
+ Value *ExpMaskShl1 = llvm::ConstantInt::get(IntTy, ExpMask.shl(1));
+ if (BuiltinID == Builtin::BI__builtin_isinf)
+ V = Builder.CreateICmpEQ(Shl1, ExpMaskShl1);
+ else
+ V = Builder.CreateICmpNE(Shl1, ExpMaskShl1);
+ return RValue::get(Builder.CreateZExt(V, ConvertType(E->getType())));
}
case Builtin::BI__builtin_isinf_sign: {
diff --git a/clang/test/CodeGen/X86/strictfp_builtins.c b/clang/test/CodeGen/X86/strictfp_builtins.c
index d7eda34fb45e..4be64a6fafd7 100644
--- a/clang/test/CodeGen/X86/strictfp_builtins.c
+++ b/clang/test/CodeGen/X86/strictfp_builtins.c
@@ -26,6 +26,24 @@ void p(char *str, int x) {
#define P(n,args) p(#n #args, __builtin_##n args)
+// 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: [[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.1, i64 0, i64 0), i32 [[RES]]) [[ATTR4]]
+// CHECK-NEXT: ret void
+//
+void test_long_double_isinf(long double ld) {
+ P(isinf, (ld));
+
+ return;
+}
+
// CHECK-LABEL: @test_long_double_isnan(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[LD_ADDR:%.*]] = alloca x86_fp80, align 16
@@ -36,7 +54,7 @@ void p(char *str, int x) {
// 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.1, i64 0, i64 0), i32 [[RES]]) [[ATTR4]]
+// CHECK-NEXT: call void @p(i8* getelementptr inbounds ([10 x i8], [10 x i8]* @.str.2, i64 0, i64 0), i32 [[RES]]) [[ATTR4]]
// 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 14647c31e647..a981a6d48cc5 100644
--- a/clang/test/CodeGen/aarch64-strictfp-builtins.c
+++ b/clang/test/CodeGen/aarch64-strictfp-builtins.c
@@ -15,7 +15,7 @@ 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]])
+// 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: ret void
//
void p(char *str, int x) {
@@ -24,6 +24,24 @@ void p(char *str, int x) {
#define P(n,args) p(#n #args, __builtin_##n args)
+// 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: [[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.1, i64 0, i64 0), i32 [[RES]]) [[ATTR4]]
+// CHECK-NEXT: ret void
+//
+void test_long_double_isinf(long double ld) {
+ P(isinf, (ld));
+
+ return;
+}
+
// CHECK-LABEL: @test_long_double_isnan(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[LD_ADDR:%.*]] = alloca fp128, align 16
@@ -34,7 +52,7 @@ void p(char *str, int x) {
// 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.1, i64 0, i64 0), i32 [[RES]])
+// CHECK-NEXT: call void @p(i8* getelementptr inbounds ([10 x i8], [10 x i8]* @.str.2, i64 0, i64 0), i32 [[RES]])
// CHECK-NEXT: ret void
//
void test_long_double_isnan(long double ld) {
diff --git a/clang/test/CodeGen/builtin_float_strictfp.c b/clang/test/CodeGen/builtin_float_strictfp.c
index 001d136c8bd6..8536f52e4823 100644
--- a/clang/test/CodeGen/builtin_float_strictfp.c
+++ b/clang/test/CodeGen/builtin_float_strictfp.c
@@ -16,8 +16,19 @@ void test_half(__fp16 *H, __fp16 *H2) {
// CHECK: call i1 @llvm.experimental.constrained.fcmp.f32(float %{{.*}}, float %{{.*}}, metadata !"ogt", metadata !"fpexcept.strict")
// CHECK-NEXT: zext i1
(void)__builtin_isinf(*H);
- // NOFP16: call i1 @llvm.experimental.constrained.fcmp.f32(float %{{.*}}, float 0x7FF0000000000000, metadata !"oeq", metadata !"fpexcept.strict")
- // FP16: call i1 @llvm.experimental.constrained.fcmp.f16(half %{{.*}}, half 0xH7C00, metadata !"oeq", metadata !"fpexcept.strict")
+ // NOFP16: [[LDADDR:%.*]] = load i16*, i16** %{{.*}}, align 8
+ // NOFP16-NEXT: [[IHALF:%.*]] = load i16, i16* [[LDADDR]], align 2
+ // NOFP16-NEXT: [[CONV:%.*]] = call float @llvm.convert.from.fp16.f32(i16 [[IHALF]])
+ // NOFP16-NEXT: [[IFLOAT:%.*]] = bitcast float [[CONV]] to i32
+ // NOFP16-NEXT: [[SHL:%.*]] = shl i32 [[IFLOAT]], 1
+ // NOFP16-NEXT: [[RES1:%.*]] = icmp eq i32 [[SHL]], -16777216
+ // NOFP16-NEXT: zext i1 [[RES1]] to i32
+ // FP16: [[LDADDR:%.*]] = load half*, half** %{{.*}}, align 8
+ // FP16-NEXT: [[HALF:%.*]] = load half, half* [[LDADDR]], align 2
+ // FP16-NEXT: [[IHALF:%.*]] = bitcast half [[HALF]] to i16
+ // FP16-NEXT: [[SHL:%.*]] = shl i16 [[IHALF]], 1
+ // FP16-NEXT: [[RES1:%.*]] = icmp eq i16 [[SHL]], -2048
+ // FP16-NEXT: zext i1 [[RES1]] to i32
}
// CHECK-LABEL: @test_mixed
diff --git a/clang/test/CodeGen/strictfp_builtins.c b/clang/test/CodeGen/strictfp_builtins.c
index 131c9406fab6..618bb70d5ed3 100644
--- a/clang/test/CodeGen/strictfp_builtins.c
+++ b/clang/test/CodeGen/strictfp_builtins.c
@@ -1,5 +1,5 @@
// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
-// RUN: %clang_cc1 %s -emit-llvm -ffp-exception-behavior=maytrap -o - -triple x86_64-unknown-unknown | FileCheck %s
+// RUN: %clang_cc1 %s -emit-llvm -ffp-exception-behavior=maytrap -fallow-half-arguments-and-returns -o - -triple x86_64-unknown-unknown | FileCheck %s
// Test that the constrained intrinsics are picking up the exception
// metadata from the AST instead of the global default from the command line.
@@ -55,18 +55,55 @@ void test_fpclassify(double d) {
return;
}
-// CHECK-LABEL: @test_isinf(
+// CHECK-LABEL: @test_fp16_isinf(
// CHECK-NEXT: entry:
-// 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: [[CMPINF:%.*]] = call i1 @llvm.experimental.constrained.fcmp.f64(double [[TMP1]], double 0x7FF0000000000000, metadata !"oeq", metadata !"fpexcept.strict") [[ATTR4]]
-// CHECK-NEXT: [[TMP2:%.*]] = zext i1 [[CMPINF]] to i32
-// CHECK-NEXT: call void @p(i8* getelementptr inbounds ([9 x i8], [9 x i8]* @.str.2, i64 0, i64 0), i32 [[TMP2]]) [[ATTR4]]
+// 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: ret void
+//
+void test_fp16_isinf(__fp16 h) {
+ P(isinf, (h));
+
+ return;
+}
+
+// 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: ret void
+//
+void test_float_isinf(float f) {
+ P(isinf, (f));
+
+ return;
+}
+
+// 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: ret void
//
-void test_isinf(double d) {
+void test_double_isinf(double d) {
P(isinf, (d));
return;
@@ -83,7 +120,7 @@ void test_isinf(double d) {
// 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.3, i64 0, i64 0), i32 [[TMP5]]) [[ATTR4]]
+// 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: ret void
//
void test_isinf_sign(double d) {
@@ -101,7 +138,7 @@ void test_isinf_sign(double d) {
// 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.4, i64 0, i64 0), i32 [[ISNAN]]) [[ATTR4]]
+// 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: ret void
//
void test_float_isnan(float f) {
@@ -120,7 +157,7 @@ void test_float_isnan(float f) {
// 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.5, i64 0, i64 0), i32 [[RES]]) [[ATTR4]]
+// 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: ret void
//
void test_double_isnan(double d) {
@@ -141,7 +178,7 @@ void test_double_isnan(double d) {
// 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.6, i64 0, i64 0), i32 [[TMP2]]) [[ATTR4]]
+// 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: ret void
//
void test_isnormal(double d) {
More information about the cfe-commits
mailing list