forked from OSchip/llvm-project
Make a transformation added in 63266 a bit less aggressive.
It was transforming (x&y)==y to (x&y)!=0 in the case where y is variable and known to have at most one bit set (e.g. z&1). This is not correct; the expressions are not equivalent when y==0. I believe this patch salvages what can be salvaged, including all the cases in bt.ll. Dan, please review. Fixes gcc.c-torture/execute/20040709-[12].c llvm-svn: 64314
This commit is contained in:
parent
761b90b825
commit
cc5fc44d02
|
@ -1346,20 +1346,21 @@ unsigned TargetLowering::ComputeNumSignBitsForTargetNode(SDValue Op,
|
|||
return 1;
|
||||
}
|
||||
|
||||
static bool ValueHasAtMostOneBitSet(SDValue Val, const SelectionDAG &DAG) {
|
||||
static bool ValueHasExactlyOneBitSet(SDValue Val, const SelectionDAG &DAG) {
|
||||
// Logical shift right or left won't ever introduce new set bits.
|
||||
// We check for this case because we don't care which bits are
|
||||
// set, but ComputeMaskedBits won't know anything unless it can
|
||||
// determine which specific bits may be set.
|
||||
if (Val.getOpcode() == ISD::SHL || Val.getOpcode() == ISD::SRL)
|
||||
return ValueHasAtMostOneBitSet(Val.getOperand(0), DAG);
|
||||
return ValueHasExactlyOneBitSet(Val.getOperand(0), DAG);
|
||||
|
||||
MVT OpVT = Val.getValueType();
|
||||
unsigned BitWidth = OpVT.getSizeInBits();
|
||||
APInt Mask = APInt::getAllOnesValue(BitWidth);
|
||||
APInt KnownZero, KnownOne;
|
||||
DAG.ComputeMaskedBits(Val, Mask, KnownZero, KnownOne);
|
||||
return KnownZero.countPopulation() == BitWidth - 1;
|
||||
return (KnownZero.countPopulation() == BitWidth - 1) &&
|
||||
(KnownOne.countPopulation() == 1);
|
||||
}
|
||||
|
||||
/// SimplifySetCC - Try to simplify a setcc built with the specified operands
|
||||
|
@ -1832,9 +1833,12 @@ TargetLowering::SimplifySetCC(MVT VT, SDValue N0, SDValue N1,
|
|||
}
|
||||
|
||||
// Simplify x&y == y to x&y != 0 if y has exactly one bit set.
|
||||
// Note that where y is variable and is known to have at most
|
||||
// one bit set (for example, if it is z&1) we cannot do this;
|
||||
// the expressions are not equivalent when y==0.
|
||||
if (N0.getOpcode() == ISD::AND)
|
||||
if (N0.getOperand(0) == N1 || N0.getOperand(1) == N1) {
|
||||
if (ValueHasAtMostOneBitSet(N1, DAG)) {
|
||||
if (ValueHasExactlyOneBitSet(N1, DAG)) {
|
||||
Cond = ISD::getSetCCInverse(Cond, /*isInteger=*/true);
|
||||
SDValue Zero = DAG.getConstant(0, N1.getValueType());
|
||||
return DAG.getSetCC(dl, VT, N0, Zero, Cond);
|
||||
|
@ -1842,7 +1846,7 @@ TargetLowering::SimplifySetCC(MVT VT, SDValue N0, SDValue N1,
|
|||
}
|
||||
if (N1.getOpcode() == ISD::AND)
|
||||
if (N1.getOperand(0) == N0 || N1.getOperand(1) == N0) {
|
||||
if (ValueHasAtMostOneBitSet(N0, DAG)) {
|
||||
if (ValueHasExactlyOneBitSet(N0, DAG)) {
|
||||
Cond = ISD::getSetCCInverse(Cond, /*isInteger=*/true);
|
||||
SDValue Zero = DAG.getConstant(0, N0.getValueType());
|
||||
return DAG.getSetCC(dl, VT, N1, Zero, Cond);
|
||||
|
|
|
@ -0,0 +1,70 @@
|
|||
; RUN: llvm-as < %s | llc -march=x86 | not grep btl
|
||||
|
||||
; This tests some cases where BT must not be generated. See also bt.ll.
|
||||
; Fixes 20040709-[12].c in gcc testsuite.
|
||||
|
||||
define void @test2(i32 %x, i32 %n) nounwind {
|
||||
entry:
|
||||
%tmp1 = and i32 %x, 1
|
||||
%tmp2 = urem i32 %tmp1, 15
|
||||
%tmp3 = and i32 %tmp2, 1 ; <i32> [#uses=1]
|
||||
%tmp4 = icmp eq i32 %tmp3, %tmp2 ; <i1> [#uses=1]
|
||||
br i1 %tmp4, label %bb, label %UnifiedReturnBlock
|
||||
|
||||
bb: ; preds = %entry
|
||||
call void @foo()
|
||||
ret void
|
||||
|
||||
UnifiedReturnBlock: ; preds = %entry
|
||||
ret void
|
||||
}
|
||||
|
||||
define void @test3(i32 %x, i32 %n) nounwind {
|
||||
entry:
|
||||
%tmp1 = and i32 %x, 1
|
||||
%tmp2 = urem i32 %tmp1, 15
|
||||
%tmp3 = and i32 %tmp2, 1 ; <i32> [#uses=1]
|
||||
%tmp4 = icmp eq i32 %tmp2, %tmp3 ; <i1> [#uses=1]
|
||||
br i1 %tmp4, label %bb, label %UnifiedReturnBlock
|
||||
|
||||
bb: ; preds = %entry
|
||||
call void @foo()
|
||||
ret void
|
||||
|
||||
UnifiedReturnBlock: ; preds = %entry
|
||||
ret void
|
||||
}
|
||||
|
||||
define void @test4(i32 %x, i32 %n) nounwind {
|
||||
entry:
|
||||
%tmp1 = and i32 %x, 1
|
||||
%tmp2 = urem i32 %tmp1, 15
|
||||
%tmp3 = and i32 %tmp2, 1 ; <i32> [#uses=1]
|
||||
%tmp4 = icmp ne i32 %tmp2, %tmp3 ; <i1> [#uses=1]
|
||||
br i1 %tmp4, label %bb, label %UnifiedReturnBlock
|
||||
|
||||
bb: ; preds = %entry
|
||||
call void @foo()
|
||||
ret void
|
||||
|
||||
UnifiedReturnBlock: ; preds = %entry
|
||||
ret void
|
||||
}
|
||||
|
||||
define void @test5(i32 %x, i32 %n) nounwind {
|
||||
entry:
|
||||
%tmp1 = and i32 %x, 1
|
||||
%tmp2 = urem i32 %tmp1, 15
|
||||
%tmp3 = and i32 %tmp2, 1 ; <i32> [#uses=1]
|
||||
%tmp4 = icmp ne i32 %tmp2, %tmp3 ; <i1> [#uses=1]
|
||||
br i1 %tmp4, label %bb, label %UnifiedReturnBlock
|
||||
|
||||
bb: ; preds = %entry
|
||||
call void @foo()
|
||||
ret void
|
||||
|
||||
UnifiedReturnBlock: ; preds = %entry
|
||||
ret void
|
||||
}
|
||||
|
||||
declare void @foo()
|
Loading…
Reference in New Issue