thopre created this revision.
thopre added reviewers: kpn, efriedma, mibintc, sepavloff, rjmccall.
Herald added a subscriber: pengfei.
thopre requested review of this revision.
Herald added a project: clang.
__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.
Repository:
rG LLVM Github Monorepo
https://reviews.llvm.org/D97125
Files:
clang/lib/CodeGen/CGBuiltin.cpp
clang/test/CodeGen/X86/strictfp_builtins.c
clang/test/CodeGen/aarch64-strictfp-builtins.c
clang/test/CodeGen/strictfp_builtins.c
Index: clang/test/CodeGen/strictfp_builtins.c
===================================================================
--- clang/test/CodeGen/strictfp_builtins.c
+++ clang/test/CodeGen/strictfp_builtins.c
@@ -55,18 +55,37 @@
return;
}
-// CHECK-LABEL: @test_isinf(
+// CHECK-LABEL: @test_float_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 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.2, 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.3, 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 +102,7 @@
// 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.4, i64 0, i64 0), i32 [[TMP5]]) [[ATTR4]]
// CHECK-NEXT: ret void
//
void test_isinf_sign(double d) {
@@ -101,7 +120,7 @@
// 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.5, i64 0, i64 0), i32 [[ISNAN]]) [[ATTR4]]
// CHECK-NEXT: ret void
//
void test_float_isnan(float f) {
@@ -120,7 +139,7 @@
// 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.6, i64 0, i64 0), i32 [[RES]]) [[ATTR4]]
// CHECK-NEXT: ret void
//
void test_double_isnan(double d) {
@@ -141,7 +160,7 @@
// 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.7, i64 0, i64 0), i32 [[TMP2]]) [[ATTR4]]
// CHECK-NEXT: ret void
//
void test_isnormal(double d) {
Index: clang/test/CodeGen/aarch64-strictfp-builtins.c
===================================================================
--- clang/test/CodeGen/aarch64-strictfp-builtins.c
+++ clang/test/CodeGen/aarch64-strictfp-builtins.c
@@ -15,7 +15,7 @@
// 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 @@
#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 @@
// 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) {
Index: clang/test/CodeGen/X86/strictfp_builtins.c
===================================================================
--- clang/test/CodeGen/X86/strictfp_builtins.c
+++ clang/test/CodeGen/X86/strictfp_builtins.c
@@ -26,6 +26,24 @@
#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 @@
// 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) {
Index: clang/lib/CodeGen/CGBuiltin.cpp
===================================================================
--- clang/lib/CodeGen/CGBuiltin.cpp
+++ clang/lib/CodeGen/CGBuiltin.cpp
@@ -3077,15 +3077,37 @@
// 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: {
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
