[AArch64] add overrides for isCheapToSpeculateCttz() and isCheapToSpeculateCtlz()

[spatel]

Summary

AArch64 is using the default TLI cost settings (expensive) for count-leading/trailing-zeros. I think this should be considered a cheap operation (and therefore fair game for speculation) for any AArch64 implementation.

The net result of allowing this speculation for the regression tests in this patch is that we get this code:

ctlz:
  clz  w0, w0
  ret

cttz:
  rbit  w8, w0
  clz  w0, w8
  ret

Instead of:

ctlz:
  cbz  w0, .LBB0_2
  clz  w0, w0
  ret
.LBB0_2:
  orr  w0, wzr, #0x20
  ret

cttz:
  cbz  w0, .LBB1_2
  rbit  w8, w0
  clz  w0, w8
  ret
.LBB1_2:
  orr  w0, wzr, #0x20
  ret

See D14469 for the larger motivation.

[rengolin]

LGTM, thanks!

llvm/trunk/lib/Target/AArch64/AArch64ISelLowering.h

public:
   /// If a physical register, this returns the register that receives the
   /// exception typeid on entry to a landing pad.
   unsigned
   getExceptionSelectorRegister(const Constant *PersonalityFn) const override {
     // FIXME: This is a guess. Has this been defined yet?
     return AArch64::X1;
   }
 
+  bool isCheapToSpeculateCttz() const override {
+    return true;
+  }
+
+  bool isCheapToSpeculateCtlz() const override {
+    return true;
+  }
+
 private:
   bool isExtFreeImpl(const Instruction *Ext) const override;
 
   /// Keep a pointer to the AArch64Subtarget around so that we can
   /// make the right decision when generating code for different targets.
   const AArch64Subtarget *Subtarget;
 
   void addTypeForNEON(EVT VT, EVT PromotedBitwiseVT);

llvm/trunk/test/Transforms/SimplifyCFG/AArch64/cttz-ctlz.ll

+; RUN: opt -S -simplifycfg -mtriple=aarch64 < %s | FileCheck %s
+
+define i32 @ctlz(i32 %A) {
+; CHECK-LABEL: @ctlz(
+; CHECK: [[ICMP:%[A-Za-z0-9]+]] = icmp eq i32 %A, 0
+; CHECK-NEXT: [[CTZ:%[A-Za-z0-9]+]] = tail call i32 @llvm.ctlz.i32(i32 %A, i1 true)
+; CHECK-NEXT: [[SEL:%[A-Za-z0-9.]+]] = select i1 [[ICMP]], i32 32, i32 [[CTZ]]
+; CHECK-NEXT: ret i32 [[SEL]]
+entry:
+  %tobool = icmp eq i32 %A, 0
+  br i1 %tobool, label %cond.end, label %cond.true
+
+cond.true:
+  %0 = tail call i32 @llvm.ctlz.i32(i32 %A, i1 true)
+  br label %cond.end
+
+cond.end:
+  %cond = phi i32 [ %0, %cond.true ], [ 32, %entry ]
+  ret i32 %cond
+}
+
+define i32 @cttz(i32 %A) {
+; CHECK-LABEL: @cttz(
+; CHECK: [[ICMP:%[A-Za-z0-9]+]] = icmp eq i32 %A, 0
+; CHECK-NEXT: [[CTZ:%[A-Za-z0-9]+]] = tail call i32 @llvm.cttz.i32(i32 %A, i1 true)
+; CHECK-NEXT: [[SEL:%[A-Za-z0-9.]+]] = select i1 [[ICMP]], i32 32, i32 [[CTZ]]
+; CHECK-NEXT: ret i32 [[SEL]]
+entry:
+  %tobool = icmp eq i32 %A, 0
+  br i1 %tobool, label %cond.end, label %cond.true
+
+cond.true:
+  %0 = tail call i32 @llvm.cttz.i32(i32 %A, i1 true)
+  br label %cond.end
+
+cond.end:
+  %cond = phi i32 [ %0, %cond.true ], [ 32, %entry ]
+  ret i32 %cond
+}
+
+declare i32 @llvm.ctlz.i32(i32, i1)
+declare i32 @llvm.cttz.i32(i32, i1)
+