From: Kevin Qin Date: Mon, 30 Dec 2013 02:05:13 +0000 (+0000) Subject: Fix a bug in DAGcombiner about zero-extend after setcc. X-Git-Url: http://plrg.eecs.uci.edu/git/?a=commitdiff_plain;h=3f8f3c9feb2e10e1f936dee23973b56bc361722d;p=oota-llvm.git Fix a bug in DAGcombiner about zero-extend after setcc. For AArch64 backend, if DAGCombiner see "sext(setcc)", it will combine them together to a single setcc with extended value type. Then if it see "zext(setcc)", it assumes setcc is Vxi1, and try to create "(and (vsetcc), (1, 1, ...)". While setcc isn't Vxi1, DAGcombiner will create wrong node and get wrong code emitted. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@198190 91177308-0d34-0410-b5e6-96231b3b80d8 --- diff --git a/lib/CodeGen/SelectionDAG/DAGCombiner.cpp b/lib/CodeGen/SelectionDAG/DAGCombiner.cpp index 68d0521e763..3b87922b789 100644 --- a/lib/CodeGen/SelectionDAG/DAGCombiner.cpp +++ b/lib/CodeGen/SelectionDAG/DAGCombiner.cpp @@ -4970,7 +4970,8 @@ SDValue DAGCombiner::visitZERO_EXTEND(SDNode *N) { } if (N0.getOpcode() == ISD::SETCC) { - if (!LegalOperations && VT.isVector()) { + if (!LegalOperations && VT.isVector() && + N0.getValueType().getVectorElementType() == MVT::i1) { // zext(setcc) -> (and (vsetcc), (1, 1, ...) for vectors. // Only do this before legalize for now. EVT N0VT = N0.getOperand(0).getValueType(); diff --git a/test/CodeGen/AArch64/neon-shift-left-long.ll b/test/CodeGen/AArch64/neon-shift-left-long.ll index d45c47685b0..d10d551805a 100644 --- a/test/CodeGen/AArch64/neon-shift-left-long.ll +++ b/test/CodeGen/AArch64/neon-shift-left-long.ll @@ -191,3 +191,13 @@ define <2 x i64> @test_ushll2_shl0_v4i32(<4 x i32> %a) { %tmp = zext <2 x i32> %1 to <2 x i64> ret <2 x i64> %tmp } + +define <8 x i16> @test_ushll_cmp(<8 x i8> %a, <8 x i8> %b) #0 { +; CHECK: test_ushll_cmp: +; CHECK: cmeq {{v[0-9]+}}.8b, {{v[0-9]+}}.8b, {{v[0-9]+}}.8b +; CHECK-NEXT: ushll {{v[0-9]+}}.8h, {{v[0-9]+}}.8b, #0 + %cmp.i = icmp eq <8 x i8> %a, %b + %vcgtz.i.i = sext <8 x i1> %cmp.i to <8 x i8> + %vmovl.i.i.i = zext <8 x i8> %vcgtz.i.i to <8 x i16> + ret <8 x i16> %vmovl.i.i.i +}