[PowerPC] Enable speculation of cttz/ctlz

PPC has an instruction for ctlz with defined zero behavior, and our lowering of
cttz (provided by DAGCombine) is also efficient and branchless, so speculating
these makes sense.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@225150 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/PowerPC/PPCISelLowering.h b/lib/Target/PowerPC/PPCISelLowering.h
index d9142c7e7d03f6f934eea44e4612419c889ae9bd..dd2431e9579ea8bff66183c1147c16dba65f49d4 100644 (file)
--- a/lib/Target/PowerPC/PPCISelLowering.h
+++ b/lib/Target/PowerPC/PPCISelLowering.h
@@ -387,6 +387,14 @@ namespace llvm {
 
     MVT getScalarShiftAmountTy(EVT LHSTy) const override { return MVT::i32; }
 
+    bool isCheapToSpeculateCttz() const override {
+      return true;
+    }
+
+    bool isCheapToSpeculateCtlz() const override {
+      return true;
+    }
+
     /// getSetCCResultType - Return the ISD::SETCC ValueType
     EVT getSetCCResultType(LLVMContext &Context, EVT VT) const override;
 

diff --git a/test/CodeGen/PowerPC/cttz-ctlz-spec.ll b/test/CodeGen/PowerPC/cttz-ctlz-spec.ll
new file mode 100644 (file)
index 0000000..13b017a
--- /dev/null
+++ b/test/CodeGen/PowerPC/cttz-ctlz-spec.ll
@@ -0,0 +1,41 @@
+; RUN: opt -S -codegenprepare < %s | FileCheck %s
+target datalayout = "E-m:e-i64:64-n32:64"
+target triple = "powerpc64-unknown-linux-gnu"
+
+define i64 @test1(i64 %A) {
+; CHECK-LABEL: @test1(
+; CHECK: [[CTLZ:%[A-Za-z0-9]+]] = call i64 @llvm.ctlz.i64(i64 %A, i1 false)
+; CHECK-NEXT: ret i64 [[CTLZ]]
+entry:
+  %tobool = icmp eq i64 %A, 0
+  br i1 %tobool, label %cond.end, label %cond.true
+
+cond.true:                                        ; preds = %entry
+  %0 = tail call i64 @llvm.ctlz.i64(i64 %A, i1 true)
+  br label %cond.end
+
+cond.end:                                         ; preds = %entry, %cond.true
+  %cond = phi i64 [ %0, %cond.true ], [ 64, %entry ]
+  ret i64 %cond
+}
+
+define i64 @test1b(i64 %A) {
+; CHECK-LABEL: @test1b(
+; CHECK: [[CTTZ:%[A-Za-z0-9]+]] = call i64 @llvm.cttz.i64(i64 %A, i1 false)
+; CHECK-NEXT: ret i64 [[CTTZ]]
+entry:
+  %tobool = icmp eq i64 %A, 0
+  br i1 %tobool, label %cond.end, label %cond.true
+
+cond.true:                                        ; preds = %entry
+  %0 = tail call i64 @llvm.cttz.i64(i64 %A, i1 true)
+  br label %cond.end
+
+cond.end:                                         ; preds = %entry, %cond.true
+  %cond = phi i64 [ %0, %cond.true ], [ 64, %entry ]
+  ret i64 %cond
+}
+
+declare i64 @llvm.ctlz.i64(i64, i1)
+declare i64 @llvm.cttz.i64(i64, i1)
+