[llvm] r252625 - [AArch64] add overrides for isCheapToSpeculateCttz() and isCheapToSpeculateCtlz()

[Sanjay Patel via llvm-commits]

Author: spatel
Date: Tue Nov 10 12:11:37 2015
New Revision: 252625

URL: http://llvm.org/viewvc/llvm-project?rev=252625&view=rev
Log:
[AArch64] add overrides for isCheapToSpeculateCttz() and isCheapToSpeculateCtlz()

AArch64 has instructions for efficient count-leading/trailing-zeros, so 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.

Differential Revision: http://reviews.llvm.org/D14505


Added:
    llvm/trunk/test/Transforms/SimplifyCFG/AArch64/cttz-ctlz.ll
Modified:
    llvm/trunk/lib/Target/AArch64/AArch64ISelLowering.h

Modified: llvm/trunk/lib/Target/AArch64/AArch64ISelLowering.h
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/AArch64/AArch64ISelLowering.h?rev=252625&r1=252624&r2=252625&view=diff
==============================================================================
--- llvm/trunk/lib/Target/AArch64/AArch64ISelLowering.h (original)
+++ llvm/trunk/lib/Target/AArch64/AArch64ISelLowering.h Tue Nov 10 12:11:37 2015
@@ -381,6 +381,14 @@ public:
     return AArch64::X1;
   }
 
+  bool isCheapToSpeculateCttz() const override {
+    return true;
+  }
+
+  bool isCheapToSpeculateCtlz() const override {
+    return true;
+  }
+
 private:
   bool isExtFreeImpl(const Instruction *Ext) const override;
 

Added: llvm/trunk/test/Transforms/SimplifyCFG/AArch64/cttz-ctlz.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/Transforms/SimplifyCFG/AArch64/cttz-ctlz.ll?rev=252625&view=auto
==============================================================================
--- llvm/trunk/test/Transforms/SimplifyCFG/AArch64/cttz-ctlz.ll (added)
+++ llvm/trunk/test/Transforms/SimplifyCFG/AArch64/cttz-ctlz.ll Tue Nov 10 12:11:37 2015
@@ -0,0 +1,43 @@
+; 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)
+