From: Sanjay Patel Date: Mon, 5 Dec 2016 15:58:21 +0000 (+0000) Subject: [TargetLowering] add special-case for demanded bits analysis of 'not' X-Git-Url: http://review.tizen.org/git/?a=commitdiff_plain;h=1f158d6955a31b4decf03c5bf2d568f5e29cc2e8;p=platform%2Fupstream%2Fllvm.git [TargetLowering] add special-case for demanded bits analysis of 'not' We treat bitwise 'not' as a special operation and try not to reduce its all-ones mask. Presumably, this is because a 'not' may be cheaper than a generic 'xor' or it may get folded into another logic op if the target has those. However, if we can remove a logic instruction by changing the xor's constant mask value, that should always be a win. Note that the IR version of SimplifyDemandedBits() does not treat 'not' as a special-case currently (although that's marked with a FIXME). So if you run this IR through -instcombine, you should get the same end result. I'm hoping to add a different backend transform that will expose this problem though, so I need to solve this first. Differential Revision: https://reviews.llvm.org/D27356 llvm-svn: 288676 --- diff --git a/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp b/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp index 08373e0..6a7de14 100644 --- a/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp +++ b/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp @@ -554,16 +554,30 @@ bool TargetLowering::SimplifyDemandedBits(SDValue Op, // simplify the LHS, here we're using information from the LHS to simplify // the RHS. if (ConstantSDNode *RHSC = dyn_cast(Op.getOperand(1))) { + SDValue Op0 = Op.getOperand(0); APInt LHSZero, LHSOne; // Do not increment Depth here; that can cause an infinite loop. - TLO.DAG.computeKnownBits(Op.getOperand(0), LHSZero, LHSOne, Depth); + TLO.DAG.computeKnownBits(Op0, LHSZero, LHSOne, Depth); // If the LHS already has zeros where RHSC does, this and is dead. if ((LHSZero & NewMask) == (~RHSC->getAPIntValue() & NewMask)) - return TLO.CombineTo(Op, Op.getOperand(0)); + return TLO.CombineTo(Op, Op0); + // If any of the set bits in the RHS are known zero on the LHS, shrink // the constant. if (TLO.ShrinkDemandedConstant(Op, ~LHSZero & NewMask)) return true; + + // Bitwise-not (xor X, -1) is a special case: we don't usually shrink its + // constant, but if this 'and' is only clearing bits that were just set by + // the xor, then this 'and' can be eliminated by shrinking the mask of + // the xor. For example, for a 32-bit X: + // and (xor (srl X, 31), -1), 1 --> xor (srl X, 31), 1 + if (isBitwiseNot(Op0) && Op0.hasOneUse() && + LHSOne == ~RHSC->getAPIntValue()) { + SDValue Xor = TLO.DAG.getNode(ISD::XOR, dl, Op.getValueType(), + Op0.getOperand(0), Op.getOperand(1)); + return TLO.CombineTo(Op, Xor); + } } if (SimplifyDemandedBits(Op.getOperand(1), NewMask, KnownZero, @@ -679,10 +693,10 @@ bool TargetLowering::SimplifyDemandedBits(SDValue Op, // If the RHS is a constant, see if we can simplify it. // for XOR, we prefer to force bits to 1 if they will make a -1. - // if we can't force bits, try to shrink constant + // If we can't force bits, try to shrink the constant. if (ConstantSDNode *C = dyn_cast(Op.getOperand(1))) { APInt Expanded = C->getAPIntValue() | (~NewMask); - // if we can expand it to have all bits set, do it + // If we can expand it to have all bits set, do it. if (Expanded.isAllOnesValue()) { if (Expanded != C->getAPIntValue()) { EVT VT = Op.getValueType(); @@ -690,7 +704,7 @@ bool TargetLowering::SimplifyDemandedBits(SDValue Op, TLO.DAG.getConstant(Expanded, dl, VT)); return TLO.CombineTo(Op, New); } - // if it already has all the bits set, nothing to change + // If it already has all the bits set, nothing to change // but don't shrink either! } else if (TLO.ShrinkDemandedConstant(Op, NewMask)) { return true; diff --git a/llvm/test/CodeGen/X86/not-and-simplify.ll b/llvm/test/CodeGen/X86/not-and-simplify.ll index 3bee447..dfce6c6 100644 --- a/llvm/test/CodeGen/X86/not-and-simplify.ll +++ b/llvm/test/CodeGen/X86/not-and-simplify.ll @@ -5,20 +5,12 @@ ; Clear high bits via shift, set them with xor (not), then mask them off. define i32 @shrink_xor_constant1(i32 %x) { -; NO_BMI-LABEL: shrink_xor_constant1: -; NO_BMI: # BB#0: -; NO_BMI-NEXT: shrl $31, %edi -; NO_BMI-NEXT: notl %edi -; NO_BMI-NEXT: andl $1, %edi -; NO_BMI-NEXT: movl %edi, %eax -; NO_BMI-NEXT: retq -; -; BMI-LABEL: shrink_xor_constant1: -; BMI: # BB#0: -; BMI-NEXT: shrl $31, %edi -; BMI-NEXT: movl $1, %eax -; BMI-NEXT: andnl %eax, %edi, %eax -; BMI-NEXT: retq +; ALL-LABEL: shrink_xor_constant1: +; ALL: # BB#0: +; ALL-NEXT: shrl $31, %edi +; ALL-NEXT: xorl $1, %edi +; ALL-NEXT: movl %edi, %eax +; ALL-NEXT: retq ; %sh = lshr i32 %x, 31 %not = xor i32 %sh, -1 @@ -32,8 +24,7 @@ define i8 @shrink_xor_constant2(i8 %x) { ; ALL-LABEL: shrink_xor_constant2: ; ALL: # BB#0: ; ALL-NEXT: shlb $5, %dil -; ALL-NEXT: notb %dil -; ALL-NEXT: andb $-32, %dil +; ALL-NEXT: xorb $-32, %dil ; ALL-NEXT: movl %edi, %eax ; ALL-NEXT: retq ;