Do not emit intermediate register for zero FP immediate

This updates check for double precision zero floating point constant to allow
use of instruction with immediate value rather than temporary register.
Currently "a == 0.0", where "a" is of "double" type generates:

vmov.i32        d16, #0x0
vcmpe.f64       d0, d16

With this change it becomes:

vcmpe.f64        d0, #0

Patch by Sergey Dmitrouk.

llvm-svn: 220486

2 files changed, 24 insertions, 0 deletions

diff --git a/llvm/lib/Target/ARM/ARMISelLowering.cpp b/llvm/lib/Target/ARM/ARMISelLowering.cpp
index 7df13834055..680b497fb15 100644
--- a/llvm/lib/Target/ARM/ARMISelLowering.cpp
+++ b/llvm/lib/Target/ARM/ARMISelLowering.cpp
@@ -3245,6 +3245,18 @@ static bool isFloatingPointZero(SDValue Op) {
         if (const ConstantFP *CFP = dyn_cast<ConstantFP>(CP->getConstVal()))
           return CFP->getValueAPF().isPosZero();
     }
+  } else if (Op->getOpcode() == ISD::BITCAST &&
+             Op->getValueType(0) == MVT::f64) {
+    // Handle (ISD::BITCAST (ARMISD::VMOVIMM (ISD::TargetConstant 0)) MVT::f64)
+    // created by LowerConstantFP().
+    SDValue BitcastOp = Op->getOperand(0);
+    if (BitcastOp->getOpcode() == ARMISD::VMOVIMM) {
+      SDValue MoveOp = BitcastOp->getOperand(0);
+      if (MoveOp->getOpcode() == ISD::TargetConstant &&
+          cast<ConstantSDNode>(MoveOp)->getZExtValue() == 0) {
+        return true;
+      }
+    }
   }
   return false;
 }
diff --git a/llvm/test/CodeGen/ARM/fpcmp-f64-neon-opt.ll b/llvm/test/CodeGen/ARM/fpcmp-f64-neon-opt.ll
new file mode 100644
index 00000000000..7444a6851d9
--- /dev/null
+++ b/llvm/test/CodeGen/ARM/fpcmp-f64-neon-opt.ll
@@ -0,0 +1,12 @@
+; RUN: llc -mtriple=linux-arm-gnueabihf -mattr=+neon %s -o - | FileCheck %s
+
+; Check that no intermediate integer register is used.
+define i32 @no-intermediate-register-for-zero-imm(double %x) #0 {
+entry:
+; CHECK-LABEL: no-intermediate-register-for-zero-imm
+; CHECK-NOT: vmov
+; CHECK: vcmp
+  %cmp = fcmp une double %x, 0.000000e+00
+  %conv = zext i1 %cmp to i32
+  ret i32 %conv
+}