diff options
author | Sanjay Patel <spatel@rotateright.com> | 2017-07-07 14:56:20 +0000 |
---|---|---|
committer | Sanjay Patel <spatel@rotateright.com> | 2017-07-07 14:56:20 +0000 |
commit | dd36f7573330ef12c1b150a83ae128c5c4d26a77 (patch) | |
tree | 6381cdf1e4028faca1e42ac031fff28be9a0b967 | |
parent | 1bbdf4e11a6cc876a8a3dc3f0170f06afe95529b (diff) | |
download | bcm5719-llvm-dd36f7573330ef12c1b150a83ae128c5c4d26a77.tar.gz bcm5719-llvm-dd36f7573330ef12c1b150a83ae128c5c4d26a77.zip |
[x86] add SBB optimization for SETAE (uge) 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. DAGCombiner already
has the foundation to allow the transforms, so we just need to fill in the holes
for x86 math op lowering. 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
Differential Revision: https://reviews.llvm.org/D34652
llvm-svn: 307404
-rw-r--r-- | llvm/lib/Target/X86/X86ISelLowering.cpp | 17 | ||||
-rw-r--r-- | llvm/test/CodeGen/X86/sbb.ll | 8 |
2 files changed, 18 insertions, 7 deletions
diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp index e4edceeedd9..c5ce88bd1a6 100644 --- a/llvm/lib/Target/X86/X86ISelLowering.cpp +++ b/llvm/lib/Target/X86/X86ISelLowering.cpp @@ -35015,6 +35015,21 @@ static SDValue combineAddOrSubToADCOrSBB(SDNode *N, SelectionDAG &DAG) { return DAG.getNode(IsSub ? ISD::SUB : ISD::ADD, DL, VT, X, SBB); } + auto *ConstantX = dyn_cast<ConstantSDNode>(X); + if (!IsSub && ConstantX && ConstantX->isAllOnesValue()) { + if (CC == X86::COND_AE) { + // This is a complicated way to get -1 or 0 from the carry flag: + // -1 + SETAE --> -1 + (!CF) --> CF ? -1 : 0 --> SBB %eax, %eax + // We don't have to match the subtract equivalent because sub X, 1 is + // canonicalized to add X, -1. + return DAG.getNode(X86ISD::SETCC_CARRY, DL, VT, + DAG.getConstant(X86::COND_B, DL, MVT::i8), + Y.getOperand(1)); + } + + // TODO: Handle COND_BE if it was produced by X86ISD::SUB similar to below. + } + if (CC == X86::COND_A) { SDValue EFLAGS = Y->getOperand(1); // Try to convert COND_A into COND_B in an attempt to facilitate @@ -35051,7 +35066,7 @@ static SDValue combineAddOrSubToADCOrSBB(SDNode *N, SelectionDAG &DAG) { // If X is -1 or 0, then we have an opportunity to avoid constants required in // the general case below. - if (auto *ConstantX = dyn_cast<ConstantSDNode>(X)) { + if (ConstantX) { // 'neg' sets the carry flag when Z != 0, so create 0 or -1 using 'sbb' with // fake operands: // 0 - (Z != 0) --> sbb %eax, %eax, (neg Z) diff --git a/llvm/test/CodeGen/X86/sbb.ll b/llvm/test/CodeGen/X86/sbb.ll index 414780b2d4e..e77bbd8be08 100644 --- a/llvm/test/CodeGen/X86/sbb.ll +++ b/llvm/test/CodeGen/X86/sbb.ll @@ -146,10 +146,8 @@ define i32 @ugt_select_neg1_or_0(i32 %x, i32 %y) nounwind { define i32 @uge_select_0_or_neg1(i32 %x, i32 %y) nounwind { ; CHECK-LABEL: uge_select_0_or_neg1: ; CHECK: # BB#0: -; CHECK-NEXT: xorl %eax, %eax ; CHECK-NEXT: cmpl %esi, %edi -; CHECK-NEXT: setae %al -; CHECK-NEXT: decl %eax +; CHECK-NEXT: sbbl %eax, %eax ; CHECK-NEXT: retq %cmp = icmp uge i32 %x, %y %ext = zext i1 %cmp to i32 @@ -180,10 +178,8 @@ define i32 @ule_select_0_or_neg1(i32 %x, i32 %y) nounwind { define i32 @uge_select_0_or_neg1_sub(i32 %x, i32 %y) nounwind { ; CHECK-LABEL: uge_select_0_or_neg1_sub: ; CHECK: # BB#0: -; CHECK-NEXT: xorl %eax, %eax ; CHECK-NEXT: cmpl %esi, %edi -; CHECK-NEXT: setae %al -; CHECK-NEXT: decl %eax +; CHECK-NEXT: sbbl %eax, %eax ; CHECK-NEXT: retq %cmp = icmp uge i32 %x, %y %ext = zext i1 %cmp to i32 |