john.brawn created this revision.
john.brawn added reviewers: kpn, cameron.mcinally, dmgreen, t.p.northover.
Herald added a subscriber: kristof.beyls.
john.brawn requested review of this revision.
Herald added a project: clang.
Repository:
rG LLVM Github Monorepo
https://reviews.llvm.org/D118257
Files:
clang/lib/CodeGen/CGBuiltin.cpp
clang/test/CodeGen/aarch64-neon-intrinsics-constrained.c
Index: clang/test/CodeGen/aarch64-neon-intrinsics-constrained.c
===================================================================
--- clang/test/CodeGen/aarch64-neon-intrinsics-constrained.c
+++ clang/test/CodeGen/aarch64-neon-intrinsics-constrained.c
@@ -585,7 +585,7 @@
// COMMON-LABEL: test_vcges_f32
// UNCONSTRAINED: [[TMP0:%.*]] = fcmp oge float %a, %b
-// CONSTRAINED: [[TMP0:%.*]] = call i1 @llvm.experimental.constrained.fcmp.f32(float %a, float %b, metadata !"oge", metadata !"fpexcept.strict")
+// CONSTRAINED: [[TMP0:%.*]] = call i1 @llvm.experimental.constrained.fcmps.f32(float %a, float %b, metadata !"oge", metadata !"fpexcept.strict")
// CHECK-ASM: fcmp s{{[0-9]+}}, s{{[0-9]+}}
// CHECK-ASM-NEXT:cset {{w[0-9]+}}, ge
// COMMONIR: [[VCMPD_I:%.*]] = sext i1 [[TMP0]] to i32
@@ -596,7 +596,7 @@
// COMMON-LABEL: test_vcged_f64
// UNCONSTRAINED: [[TMP0:%.*]] = fcmp oge double %a, %b
-// CONSTRAINED: [[TMP0:%.*]] = call i1 @llvm.experimental.constrained.fcmp.f64(double %a, double %b, metadata !"oge", metadata !"fpexcept.strict")
+// CONSTRAINED: [[TMP0:%.*]] = call i1 @llvm.experimental.constrained.fcmps.f64(double %a, double %b, metadata !"oge", metadata !"fpexcept.strict")
// CHECK-ASM: fcmp d{{[0-9]+}}, d{{[0-9]+}}
// CHECK-ASM-NEXT:cset {{w[0-9]+}}, ge
// COMMONIR: [[VCMPD_I:%.*]] = sext i1 [[TMP0]] to i64
@@ -607,7 +607,7 @@
// COMMON-LABEL: test_vcgezs_f32
// UNCONSTRAINED: [[TMP0:%.*]] = fcmp oge float %a, 0.000000e+00
-// CONSTRAINED: [[TMP0:%.*]] = call i1 @llvm.experimental.constrained.fcmp.f32(float %a, float 0.000000e+00, metadata !"oge", metadata !"fpexcept.strict")
+// CONSTRAINED: [[TMP0:%.*]] = call i1 @llvm.experimental.constrained.fcmps.f32(float %a, float 0.000000e+00, metadata !"oge", metadata !"fpexcept.strict")
// CHECK-ASM: fcmp s{{[0-9]+}}, #0.0
// CHECK-ASM-NEXT:cset {{w[0-9]+}}, ge
// COMMONIR: [[VCGEZ_I:%.*]] = sext i1 [[TMP0]] to i32
@@ -618,7 +618,7 @@
// COMMON-LABEL: test_vcgezd_f64
// UNCONSTRAINED: [[TMP0:%.*]] = fcmp oge double %a, 0.000000e+00
-// CONSTRAINED: [[TMP0:%.*]] = call i1 @llvm.experimental.constrained.fcmp.f64(double %a, double 0.000000e+00, metadata !"oge", metadata !"fpexcept.strict")
+// CONSTRAINED: [[TMP0:%.*]] = call i1 @llvm.experimental.constrained.fcmps.f64(double %a, double 0.000000e+00, metadata !"oge", metadata !"fpexcept.strict")
// CHECK-ASM: fcmp d{{[0-9]+}}, #0.0
// CHECK-ASM-NEXT:cset {{w[0-9]+}}, ge
// COMMONIR: [[VCGEZ_I:%.*]] = sext i1 [[TMP0]] to i64
@@ -629,7 +629,7 @@
// COMMON-LABEL: test_vcgts_f32
// UNCONSTRAINED: [[TMP0:%.*]] = fcmp ogt float %a, %b
-// CONSTRAINED: [[TMP0:%.*]] = call i1 @llvm.experimental.constrained.fcmp.f32(float %a, float %b, metadata !"ogt", metadata !"fpexcept.strict")
+// CONSTRAINED: [[TMP0:%.*]] = call i1 @llvm.experimental.constrained.fcmps.f32(float %a, float %b, metadata !"ogt", metadata !"fpexcept.strict")
// CHECK-ASM: fcmp s{{[0-9]+}}, s{{[0-9]+}}
// CHECK-ASM-NEXT:cset {{w[0-9]+}}, gt
// COMMONIR: [[VCMPD_I:%.*]] = sext i1 [[TMP0]] to i32
@@ -640,7 +640,7 @@
// COMMON-LABEL: test_vcgtd_f64
// UNCONSTRAINED: [[TMP0:%.*]] = fcmp ogt double %a, %b
-// CONSTRAINED: [[TMP0:%.*]] = call i1 @llvm.experimental.constrained.fcmp.f64(double %a, double %b, metadata !"ogt", metadata !"fpexcept.strict")
+// CONSTRAINED: [[TMP0:%.*]] = call i1 @llvm.experimental.constrained.fcmps.f64(double %a, double %b, metadata !"ogt", metadata !"fpexcept.strict")
// CHECK-ASM: fcmp d{{[0-9]+}}, d{{[0-9]+}}
// CHECK-ASM-NEXT:cset {{w[0-9]+}}, gt
// COMMONIR: [[VCMPD_I:%.*]] = sext i1 [[TMP0]] to i64
@@ -651,7 +651,7 @@
// COMMON-LABEL: test_vcgtzs_f32
// UNCONSTRAINED: [[TMP0:%.*]] = fcmp ogt float %a, 0.000000e+00
-// CONSTRAINED: [[TMP0:%.*]] = call i1 @llvm.experimental.constrained.fcmp.f32(float %a, float 0.000000e+00, metadata !"ogt", metadata !"fpexcept.strict")
+// CONSTRAINED: [[TMP0:%.*]] = call i1 @llvm.experimental.constrained.fcmps.f32(float %a, float 0.000000e+00, metadata !"ogt", metadata !"fpexcept.strict")
// CHECK-ASM: fcmp s{{[0-9]+}}, #0.0
// CHECK-ASM-NEXT:cset {{w[0-9]+}}, gt
// COMMONIR: [[VCGTZ_I:%.*]] = sext i1 [[TMP0]] to i32
@@ -662,7 +662,7 @@
// COMMON-LABEL: test_vcgtzd_f64
// UNCONSTRAINED: [[TMP0:%.*]] = fcmp ogt double %a, 0.000000e+00
-// CONSTRAINED: [[TMP0:%.*]] = call i1 @llvm.experimental.constrained.fcmp.f64(double %a, double 0.000000e+00, metadata !"ogt", metadata !"fpexcept.strict")
+// CONSTRAINED: [[TMP0:%.*]] = call i1 @llvm.experimental.constrained.fcmps.f64(double %a, double 0.000000e+00, metadata !"ogt", metadata !"fpexcept.strict")
// CHECK-ASM: fcmp d{{[0-9]+}}, #0.0
// CHECK-ASM-NEXT:cset {{w[0-9]+}}, gt
// COMMONIR: [[VCGTZ_I:%.*]] = sext i1 [[TMP0]] to i64
@@ -673,7 +673,7 @@
// COMMON-LABEL: test_vcles_f32
// UNCONSTRAINED: [[TMP0:%.*]] = fcmp ole float %a, %b
-// CONSTRAINED: [[TMP0:%.*]] = call i1 @llvm.experimental.constrained.fcmp.f32(float %a, float %b, metadata !"ole", metadata !"fpexcept.strict")
+// CONSTRAINED: [[TMP0:%.*]] = call i1 @llvm.experimental.constrained.fcmps.f32(float %a, float %b, metadata !"ole", metadata !"fpexcept.strict")
// CHECK-ASM: fcmp s{{[0-9]+}}, s{{[0-9]+}}
// CHECK-ASM-NEXT:cset {{w[0-9]+}}, ls
// COMMONIR: [[VCMPD_I:%.*]] = sext i1 [[TMP0]] to i32
@@ -684,7 +684,7 @@
// COMMON-LABEL: test_vcled_f64
// UNCONSTRAINED: [[TMP0:%.*]] = fcmp ole double %a, %b
-// CONSTRAINED: [[TMP0:%.*]] = call i1 @llvm.experimental.constrained.fcmp.f64(double %a, double %b, metadata !"ole", metadata !"fpexcept.strict")
+// CONSTRAINED: [[TMP0:%.*]] = call i1 @llvm.experimental.constrained.fcmps.f64(double %a, double %b, metadata !"ole", metadata !"fpexcept.strict")
// CHECK-ASM: fcmp d{{[0-9]+}}, d{{[0-9]+}}
// CHECK-ASM-NEXT:cset {{w[0-9]+}}, ls
// COMMONIR: [[VCMPD_I:%.*]] = sext i1 [[TMP0]] to i64
@@ -695,7 +695,7 @@
// COMMON-LABEL: test_vclezs_f32
// UNCONSTRAINED: [[TMP0:%.*]] = fcmp ole float %a, 0.000000e+00
-// CONSTRAINED: [[TMP0:%.*]] = call i1 @llvm.experimental.constrained.fcmp.f32(float %a, float 0.000000e+00, metadata !"ole", metadata !"fpexcept.strict")
+// CONSTRAINED: [[TMP0:%.*]] = call i1 @llvm.experimental.constrained.fcmps.f32(float %a, float 0.000000e+00, metadata !"ole", metadata !"fpexcept.strict")
// CHECK-ASM: fcmp s{{[0-9]+}}, #0.0
// CHECK-ASM-NEXT:cset {{w[0-9]+}}, ls
// COMMONIR: [[VCLEZ_I:%.*]] = sext i1 [[TMP0]] to i32
@@ -706,7 +706,7 @@
// COMMON-LABEL: test_vclezd_f64
// UNCONSTRAINED: [[TMP0:%.*]] = fcmp ole double %a, 0.000000e+00
-// CONSTRAINED: [[TMP0:%.*]] = call i1 @llvm.experimental.constrained.fcmp.f64(double %a, double 0.000000e+00, metadata !"ole", metadata !"fpexcept.strict")
+// CONSTRAINED: [[TMP0:%.*]] = call i1 @llvm.experimental.constrained.fcmps.f64(double %a, double 0.000000e+00, metadata !"ole", metadata !"fpexcept.strict")
// CHECK-ASM: fcmp d{{[0-9]+}}, #0.0
// CHECK-ASM-NEXT:cset {{w[0-9]+}}, ls
// COMMONIR: [[VCLEZ_I:%.*]] = sext i1 [[TMP0]] to i64
@@ -717,7 +717,7 @@
// COMMON-LABEL: test_vclts_f32
// UNCONSTRAINED: [[TMP0:%.*]] = fcmp olt float %a, %b
-// CONSTRAINED: [[TMP0:%.*]] = call i1 @llvm.experimental.constrained.fcmp.f32(float %a, float %b, metadata !"olt", metadata !"fpexcept.strict")
+// CONSTRAINED: [[TMP0:%.*]] = call i1 @llvm.experimental.constrained.fcmps.f32(float %a, float %b, metadata !"olt", metadata !"fpexcept.strict")
// CHECK-ASM: fcmp s{{[0-9]+}}, s{{[0-9]+}}
// CHECK-ASM-NEXT:cset {{w[0-9]+}}, mi
// COMMONIR: [[VCMPD_I:%.*]] = sext i1 [[TMP0]] to i32
@@ -728,7 +728,7 @@
// COMMON-LABEL: test_vcltd_f64
// UNCONSTRAINED: [[TMP0:%.*]] = fcmp olt double %a, %b
-// CONSTRAINED: [[TMP0:%.*]] = call i1 @llvm.experimental.constrained.fcmp.f64(double %a, double %b, metadata !"olt", metadata !"fpexcept.strict")
+// CONSTRAINED: [[TMP0:%.*]] = call i1 @llvm.experimental.constrained.fcmps.f64(double %a, double %b, metadata !"olt", metadata !"fpexcept.strict")
// CHECK-ASM: fcmp d{{[0-9]+}}, d{{[0-9]+}}
// CHECK-ASM-NEXT:cset {{w[0-9]+}}, mi
// COMMONIR: [[VCMPD_I:%.*]] = sext i1 [[TMP0]] to i64
@@ -739,7 +739,7 @@
// COMMON-LABEL: test_vcltzs_f32
// UNCONSTRAINED: [[TMP0:%.*]] = fcmp olt float %a, 0.000000e+00
-// CONSTRAINED: [[TMP0:%.*]] = call i1 @llvm.experimental.constrained.fcmp.f32(float %a, float 0.000000e+00, metadata !"olt", metadata !"fpexcept.strict")
+// CONSTRAINED: [[TMP0:%.*]] = call i1 @llvm.experimental.constrained.fcmps.f32(float %a, float 0.000000e+00, metadata !"olt", metadata !"fpexcept.strict")
// CHECK-ASM: fcmp s{{[0-9]+}}, #0.0
// CHECK-ASM-NEXT:cset {{w[0-9]+}}, mi
// COMMONIR: [[VCLTZ_I:%.*]] = sext i1 [[TMP0]] to i32
@@ -750,7 +750,7 @@
// COMMON-LABEL: test_vcltzd_f64
// UNCONSTRAINED: [[TMP0:%.*]] = fcmp olt double %a, 0.000000e+00
-// CONSTRAINED: [[TMP0:%.*]] = call i1 @llvm.experimental.constrained.fcmp.f64(double %a, double 0.000000e+00, metadata !"olt", metadata !"fpexcept.strict")
+// CONSTRAINED: [[TMP0:%.*]] = call i1 @llvm.experimental.constrained.fcmps.f64(double %a, double 0.000000e+00, metadata !"olt", metadata !"fpexcept.strict")
// CHECK-ASM: fcmp d{{[0-9]+}}, #0.0
// CHECK-ASM-NEXT:cset {{w[0-9]+}}, mi
// COMMONIR: [[VCLTZ_I:%.*]] = sext i1 [[TMP0]] to i64
Index: clang/lib/CodeGen/CGBuiltin.cpp
===================================================================
--- clang/lib/CodeGen/CGBuiltin.cpp
+++ clang/lib/CodeGen/CGBuiltin.cpp
@@ -7282,7 +7282,10 @@
Op = Builder.CreateBitCast(Op, OTy);
if (OTy->getScalarType()->isFloatingPointTy()) {
- Op = Builder.CreateFCmp(Fp, Op, Constant::getNullValue(OTy));
+ if (Fp == CmpInst::FCMP_OEQ)
+ Op = Builder.CreateFCmp(Fp, Op, Constant::getNullValue(OTy));
+ else
+ Op = Builder.CreateFCmpS(Fp, Op, Constant::getNullValue(OTy));
} else {
Op = Builder.CreateICmp(Ip, Op, Constant::getNullValue(OTy));
}
@@ -10275,7 +10278,10 @@
Ops.push_back(EmitScalarExpr(E->getArg(1)));
Ops[0] = Builder.CreateBitCast(Ops[0], DoubleTy);
Ops[1] = Builder.CreateBitCast(Ops[1], DoubleTy);
- Ops[0] = Builder.CreateFCmp(P, Ops[0], Ops[1]);
+ if (P == llvm::FCmpInst::FCMP_OEQ)
+ Ops[0] = Builder.CreateFCmp(P, Ops[0], Ops[1]);
+ else
+ Ops[0] = Builder.CreateFCmpS(P, Ops[0], Ops[1]);
return Builder.CreateSExt(Ops[0], Int64Ty, "vcmpd");
}
case NEON::BI__builtin_neon_vceqs_f32:
@@ -10295,7 +10301,10 @@
Ops.push_back(EmitScalarExpr(E->getArg(1)));
Ops[0] = Builder.CreateBitCast(Ops[0], FloatTy);
Ops[1] = Builder.CreateBitCast(Ops[1], FloatTy);
- Ops[0] = Builder.CreateFCmp(P, Ops[0], Ops[1]);
+ if (P == llvm::FCmpInst::FCMP_OEQ)
+ Ops[0] = Builder.CreateFCmp(P, Ops[0], Ops[1]);
+ else
+ Ops[0] = Builder.CreateFCmpS(P, Ops[0], Ops[1]);
return Builder.CreateSExt(Ops[0], Int32Ty, "vcmpd");
}
case NEON::BI__builtin_neon_vceqh_f16:
@@ -10315,7 +10324,10 @@
Ops.push_back(EmitScalarExpr(E->getArg(1)));
Ops[0] = Builder.CreateBitCast(Ops[0], HalfTy);
Ops[1] = Builder.CreateBitCast(Ops[1], HalfTy);
- Ops[0] = Builder.CreateFCmp(P, Ops[0], Ops[1]);
+ if (P == llvm::FCmpInst::FCMP_OEQ)
+ Ops[0] = Builder.CreateFCmp(P, Ops[0], Ops[1]);
+ else
+ Ops[0] = Builder.CreateFCmpS(P, Ops[0], Ops[1]);
return Builder.CreateSExt(Ops[0], Int16Ty, "vcmpd");
}
case NEON::BI__builtin_neon_vceqd_s64:
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
