1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-23 11:13:28 +01:00

[x86] add SBB optimization for SETBE (ule) condition code

x86 scalar select-of-constants (Cond ? C1 : C2) combining/lowering is a mess 
with missing optimizations. We handle some patterns, but miss logical variants.

To clean that up, we should convert all select-of-constants to logic/math and 
enhance the combining for the expected patterns from that. Selecting 0 or -1 
needs extra attention to produce the optimal code as shown here.

Attempt to verify that all of these IR forms are logically equivalent:
http://rise4fun.com/Alive/plxs

Earlier steps in this series:
rL306040
rL306072
rL307404 (D34652)

As acknowledged in the earlier review, there's a possibility that some Intel
uarch would prefer to produce an xor to clear the fake register operand with
sbb %eax, %eax. This will likely need to be addressed in a separate pass.

llvm-svn: 307471
This commit is contained in:
Sanjay Patel 2017-07-08 14:04:48 +00:00
parent 0cc0979214
commit 0c17c0063e
2 changed files with 15 additions and 5 deletions

View File

@ -35027,7 +35027,19 @@ static SDValue combineAddOrSubToADCOrSBB(SDNode *N, SelectionDAG &DAG) {
Y.getOperand(1));
}
// TODO: Handle COND_BE if it was produced by X86ISD::SUB similar to below.
SDValue EFLAGS = Y->getOperand(1);
if (CC == X86::COND_BE && EFLAGS.getOpcode() == X86ISD::SUB &&
EFLAGS.hasOneUse() && EFLAGS.getValueType().isInteger() &&
!isa<ConstantSDNode>(EFLAGS.getOperand(1))) {
// Swap the operands of a SUB, and we have the same pattern as above.
// -1 + SETBE (SUB A, B) --> -1 + SETAE (SUB B, A) --> SBB %eax, %eax
SDValue NewSub =
DAG.getNode(X86ISD::SUB, SDLoc(EFLAGS), EFLAGS.getNode()->getVTList(),
EFLAGS.getOperand(1), EFLAGS.getOperand(0));
SDValue NewEFLAGS = SDValue(NewSub.getNode(), EFLAGS.getResNo());
return DAG.getNode(X86ISD::SETCC_CARRY, DL, VT,
DAG.getConstant(X86::COND_B, DL, MVT::i8), NewEFLAGS);
}
}
if (CC == X86::COND_A) {

View File

@ -161,10 +161,8 @@ define i32 @uge_select_0_or_neg1(i32 %x, i32 %y) nounwind {
define i32 @ule_select_0_or_neg1(i32 %x, i32 %y) nounwind {
; CHECK-LABEL: ule_select_0_or_neg1:
; CHECK: # BB#0:
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: cmpl %edi, %esi
; CHECK-NEXT: setbe %al
; CHECK-NEXT: decl %eax
; CHECK-NEXT: cmpl %esi, %edi
; CHECK-NEXT: sbbl %eax, %eax
; CHECK-NEXT: retq
%cmp = icmp ule i32 %y, %x
%ext = zext i1 %cmp to i32