forked from OSchip/llvm-project
Fix FCOPYSIGN expansion
In expansion of FCOPYSIGN, the shift node is missing when the two operands of FCOPYSIGN are of the same size. We should always generate shift node (if the required shift bit is not zero) to put the sign bit into the right position, regardless of the size of underlying types. Differential Revision: https://reviews.llvm.org/D49973 llvm-svn: 338665
This commit is contained in:
parent
06baa7e0f2
commit
b9a7b7a84d
|
@ -1489,24 +1489,20 @@ SDValue SelectionDAGLegalize::ExpandFCOPYSIGN(SDNode *Node) const {
|
|||
|
||||
// Get the signbit at the right position for MagAsInt.
|
||||
int ShiftAmount = SignAsInt.SignBit - MagAsInt.SignBit;
|
||||
if (SignBit.getValueSizeInBits() > ClearedSign.getValueSizeInBits()) {
|
||||
if (ShiftAmount > 0) {
|
||||
SDValue ShiftCnst = DAG.getConstant(ShiftAmount, DL, IntVT);
|
||||
SignBit = DAG.getNode(ISD::SRL, DL, IntVT, SignBit, ShiftCnst);
|
||||
} else if (ShiftAmount < 0) {
|
||||
SDValue ShiftCnst = DAG.getConstant(-ShiftAmount, DL, IntVT);
|
||||
SignBit = DAG.getNode(ISD::SHL, DL, IntVT, SignBit, ShiftCnst);
|
||||
}
|
||||
SignBit = DAG.getNode(ISD::TRUNCATE, DL, MagVT, SignBit);
|
||||
} else if (SignBit.getValueSizeInBits() < ClearedSign.getValueSizeInBits()) {
|
||||
EVT ShiftVT = IntVT;
|
||||
if (SignBit.getValueSizeInBits() < ClearedSign.getValueSizeInBits()) {
|
||||
SignBit = DAG.getNode(ISD::ZERO_EXTEND, DL, MagVT, SignBit);
|
||||
if (ShiftAmount > 0) {
|
||||
SDValue ShiftCnst = DAG.getConstant(ShiftAmount, DL, MagVT);
|
||||
SignBit = DAG.getNode(ISD::SRL, DL, MagVT, SignBit, ShiftCnst);
|
||||
} else if (ShiftAmount < 0) {
|
||||
SDValue ShiftCnst = DAG.getConstant(-ShiftAmount, DL, MagVT);
|
||||
SignBit = DAG.getNode(ISD::SHL, DL, MagVT, SignBit, ShiftCnst);
|
||||
}
|
||||
ShiftVT = MagVT;
|
||||
}
|
||||
if (ShiftAmount > 0) {
|
||||
SDValue ShiftCnst = DAG.getConstant(ShiftAmount, DL, ShiftVT);
|
||||
SignBit = DAG.getNode(ISD::SRL, DL, ShiftVT, SignBit, ShiftCnst);
|
||||
} else if (ShiftAmount < 0) {
|
||||
SDValue ShiftCnst = DAG.getConstant(-ShiftAmount, DL, ShiftVT);
|
||||
SignBit = DAG.getNode(ISD::SHL, DL, ShiftVT, SignBit, ShiftCnst);
|
||||
}
|
||||
if (SignBit.getValueSizeInBits() > ClearedSign.getValueSizeInBits()) {
|
||||
SignBit = DAG.getNode(ISD::TRUNCATE, DL, MagVT, SignBit);
|
||||
}
|
||||
|
||||
// Store the part with the modified sign and convert back to float.
|
||||
|
|
|
@ -5,10 +5,12 @@ target triple = "aarch64--"
|
|||
|
||||
declare fp128 @llvm.copysign.f128(fp128, fp128)
|
||||
|
||||
@val = global double zeroinitializer, align 8
|
||||
@val_float = global float zeroinitializer, align 4
|
||||
@val_double = global double zeroinitializer, align 8
|
||||
@val_fp128 = global fp128 zeroinitializer, align 16
|
||||
|
||||
; CHECK-LABEL: copysign0
|
||||
; CHECK: ldr [[REG:x[0-9]+]], [x8, :lo12:val]
|
||||
; CHECK: ldr [[REG:x[0-9]+]], [x8, :lo12:val_double]
|
||||
; CHECK: and [[ANDREG:x[0-9]+]], [[REG]], #0x8000000000000000
|
||||
; CHECK: lsr x[[LSRREGNUM:[0-9]+]], [[ANDREG]], #56
|
||||
; CHECK: bfxil w[[LSRREGNUM]], w{{[0-9]+}}, #0, #7
|
||||
|
@ -16,8 +18,25 @@ declare fp128 @llvm.copysign.f128(fp128, fp128)
|
|||
; CHECK: ldr q{{[0-9]+}},
|
||||
define fp128 @copysign0() {
|
||||
entry:
|
||||
%v = load double, double* @val, align 8
|
||||
%v = load double, double* @val_double, align 8
|
||||
%conv = fpext double %v to fp128
|
||||
%call = tail call fp128 @llvm.copysign.f128(fp128 0xL00000000000000007FFF000000000000, fp128 %conv) #2
|
||||
ret fp128 %call
|
||||
}
|
||||
|
||||
; CHECK-LABEL: copysign1
|
||||
; CHECK-DAG: ldr [[REG:q[0-9]+]], [x8, :lo12:val_fp128]
|
||||
; CHECK-DAG: ldr [[REG:w[0-9]+]], [x8, :lo12:val_float]
|
||||
; CHECK: and [[ANDREG:w[0-9]+]], [[REG]], #0x80000000
|
||||
; CHECK: lsr w[[LSRREGNUM:[0-9]+]], [[ANDREG]], #24
|
||||
; CHECK: bfxil w[[LSRREGNUM]], w{{[0-9]+}}, #0, #7
|
||||
; CHECK: strb w[[LSRREGNUM]],
|
||||
; CHECK: ldr q{{[0-9]+}},
|
||||
define fp128@copysign1() {
|
||||
entry:
|
||||
%v0 = load fp128, fp128* @val_fp128, align 16
|
||||
%v1 = load float, float* @val_float, align 4
|
||||
%conv = fpext float %v1 to fp128
|
||||
%call = tail call fp128 @llvm.copysign.f128(fp128 %v0, fp128 %conv)
|
||||
ret fp128 %call
|
||||
}
|
||||
|
|
Loading…
Reference in New Issue