gcc defines an intrinsic called __builtin_clrsb which counts the number of extra sign bits on a number. This is equivalent to counting the number of leading zeros on a positive number or the number of leading ones on a negative number and subtracting one from the result. Since we can't count leading ones we need to invert negative numbers to count zeros.
This patch will cause the builtin to be expanded inline while gcc uses a call to a function like clrsbdi2 that is implemented in libgcc. But this is similar to what we already do for popcnt. And I don't think compiler-rt supports clrsbdi2.
Differential Revision: https://reviews.llvm.org/D50168
llvm-svn: 339282
BUILTIN(__builtin_popcount , "iUi" , "nc")
BUILTIN(__builtin_popcountl , "iULi" , "nc")
BUILTIN(__builtin_popcountll, "iULLi", "nc")
+BUILTIN(__builtin_clrsb , "ii" , "nc")
+BUILTIN(__builtin_clrsbl , "iLi" , "nc")
+BUILTIN(__builtin_clrsbll, "iLLi", "nc")
// FIXME: These type signatures are not correct for targets with int != 32-bits
// or with ULL != 64-bits.
return RValue::get(ComplexVal.second);
}
+ case Builtin::BI__builtin_clrsb:
+ case Builtin::BI__builtin_clrsbl:
+ case Builtin::BI__builtin_clrsbll: {
+ // clrsb(x) -> clz(x < 0 ? ~x : x) - 1 or
+ Value *ArgValue = EmitScalarExpr(E->getArg(0));
+
+ llvm::Type *ArgType = ArgValue->getType();
+ Value *F = CGM.getIntrinsic(Intrinsic::ctlz, ArgType);
+
+ llvm::Type *ResultType = ConvertType(E->getType());
+ Value *Zero = llvm::Constant::getNullValue(ArgType);
+ Value *IsNeg = Builder.CreateICmpSLT(ArgValue, Zero, "isneg");
+ Value *Inverse = Builder.CreateNot(ArgValue, "not");
+ Value *Tmp = Builder.CreateSelect(IsNeg, Inverse, ArgValue);
+ Value *Ctlz = Builder.CreateCall(F, {Tmp, Builder.getFalse()});
+ Value *Result = Builder.CreateSub(Ctlz, llvm::ConstantInt::get(ArgType, 1));
+ Result = Builder.CreateIntCast(Result, ResultType, /*isSigned*/true,
+ "cast");
+ return RValue::get(Result);
+ }
case Builtin::BI__builtin_ctzs:
case Builtin::BI__builtin_ctz:
case Builtin::BI__builtin_ctzl:
--- /dev/null
+// RUN: %clang_cc1 %s -emit-llvm -o - | FileCheck %s
+
+int test__builtin_clrsb(int x) {
+// CHECK-LABEL: test__builtin_clrsb
+// CHECK: [[C:%.*]] = icmp slt i32 [[X:%.*]], 0
+// CHECK-NEXT: [[INV:%.*]] = xor i32 [[X]], -1
+// CHECK-NEXT: [[SEL:%.*]] = select i1 [[C]], i32 [[INV]], i32 [[X]]
+// CHECK-NEXT: [[CTLZ:%.*]] = call i32 @llvm.ctlz.i32(i32 [[SEL]], i1 false)
+// CHECK-NEXT: [[SUB:%.*]] = sub i32 [[CTLZ]], 1
+ return __builtin_clrsb(x);
+}
+
+int test__builtin_clrsbll(long long x) {
+// CHECK-LABEL: test__builtin_clrsbll
+// CHECK: [[C:%.*]] = icmp slt i64 [[X:%.*]], 0
+// CHECK-NEXT: [[INV:%.*]] = xor i64 [[X]], -1
+// CHECK-NEXT: [[SEL:%.*]] = select i1 [[C]], i64 [[INV]], i64 [[X]]
+// CHECK-NEXT: [[CTLZ:%.*]] = call i64 @llvm.ctlz.i64(i64 [[SEL]], i1 false)
+// CHECK-NEXT: [[SUB:%.*]] = sub i64 [[CTLZ]], 1
+// CHECK-NEXT: trunc i64 [[SUB]] to i32
+ return __builtin_clrsbll(x);
+}