[PATCH] D19659: [X86] Enable RRL part of the LEA optimization pass for -O2

[Andrey Turetskiy via llvm-commits]

aturetsk created this revision.
aturetsk added reviewers: nadav, qcolombet, rnk.
aturetsk added subscribers: reames, zinovy.nis, llvm-commits.

Enable "Remove Redundant LEAs" part of the LEA optimization pass for -O2.

This gives 6.4% performance improve on nnet benchmark from coremark-pro. There is no significant effect on other benchmarks.

http://reviews.llvm.org/D19659

Files:
  lib/Target/X86/X86OptimizeLEAs.cpp
  test/CodeGen/X86/lea-opt.ll

Index: test/CodeGen/X86/lea-opt.ll
===================================================================
--- test/CodeGen/X86/lea-opt.ll
+++ test/CodeGen/X86/lea-opt.ll
@@ -38,12 +38,11 @@
 ; CHECK:	movl arr1([[REG1]],[[REG1]],2), {{.*}}
 ; CHECK:	leaq arr1+4([[REG1]],[[REG1]],2), [[REG2:%[a-z]+]]
 ; CHECK:	subl arr1+4([[REG1]],[[REG1]],2), {{.*}}
-; CHECK:	leaq arr1+8([[REG1]],[[REG1]],2), [[REG3:%[a-z]+]]
 ; CHECK:	addl arr1+8([[REG1]],[[REG1]],2), {{.*}}
 ; CHECK:	movl ${{[1-4]+}}, ([[REG2]])
-; CHECK:	movl ${{[1-4]+}}, ([[REG3]])
+; CHECK:	movl ${{[1-4]+}}, 4([[REG2]])
 ; CHECK:	movl ${{[1-4]+}}, ([[REG2]])
-; CHECK:	movl ${{[1-4]+}}, ([[REG3]])
+; CHECK:	movl ${{[1-4]+}}, 4([[REG2]])
 }
 
 define void @test2(i64 %x) nounwind optsize {
@@ -78,12 +77,11 @@
 ; CHECK:	leaq arr1+4([[REG1]],[[REG1]],2), [[REG2:%[a-z]+]]
 ; CHECK:	movl -4([[REG2]]), {{.*}}
 ; CHECK:	subl ([[REG2]]), {{.*}}
-; CHECK:	leaq arr1+8([[REG1]],[[REG1]],2), [[REG3:%[a-z]+]]
-; CHECK:	addl ([[REG3]]), {{.*}}
+; CHECK:	addl 4([[REG2]]), {{.*}}
 ; CHECK:	movl ${{[1-4]+}}, ([[REG2]])
-; CHECK:	movl ${{[1-4]+}}, ([[REG3]])
+; CHECK:	movl ${{[1-4]+}}, 4([[REG2]])
 ; CHECK:	movl ${{[1-4]+}}, ([[REG2]])
-; CHECK:	movl ${{[1-4]+}}, ([[REG3]])
+; CHECK:	movl ${{[1-4]+}}, 4([[REG2]])
 }
 
 ; Check that LEA optimization pass takes into account a resultant address
@@ -109,7 +107,9 @@
 
 sw.bb.2:                                          ; preds = %entry
   store i32 333, i32* %a, align 4
-  store i32 444, i32* %b, align 4
+  ; Make sure the REG3's definition LEA won't be removed as a redundant.
+  %cvt = ptrtoint i32* %b to i32
+  store i32 %cvt, i32* %b, align 4
   br label %sw.epilog
 
 sw.epilog:                                        ; preds = %sw.bb.2, %sw.bb.1, %entry
@@ -127,7 +127,7 @@
 ; CHECK:	movl ${{[1-4]+}}, ([[REG2]])
 ; CHECK:	movl ${{[1-4]+}}, ([[REG3]])
 ; CHECK:	movl ${{[1-4]+}}, ([[REG2]])
-; CHECK:	movl ${{[1-4]+}}, ([[REG3]])
+; CHECK:	movl {{.*}}, ([[REG3]])
 }
 
 define void @test4(i64 %x) nounwind minsize {
Index: lib/Target/X86/X86OptimizeLEAs.cpp
===================================================================
--- lib/Target/X86/X86OptimizeLEAs.cpp
+++ lib/Target/X86/X86OptimizeLEAs.cpp
@@ -8,7 +8,7 @@
 //===----------------------------------------------------------------------===//
 //
 // This file defines the pass that performs some optimizations with LEA
-// instructions in order to improve code size.
+// instructions in order to improve performance and code size.
 // Currently, it does two things:
 // 1) If there are two LEA instructions calculating addresses which only differ
 //    by displacement inside a basic block, one of them is removed.
@@ -615,8 +615,7 @@
 bool OptimizeLEAPass::runOnMachineFunction(MachineFunction &MF) {
   bool Changed = false;
 
-  // Perform this optimization only if we care about code size.
-  if (DisableX86LEAOpt || !MF.getFunction()->optForSize())
+  if (DisableX86LEAOpt)
     return false;
 
   MRI = &MF.getRegInfo();
@@ -635,13 +634,13 @@
     if (LEAs.empty())
       continue;
 
-    // Remove redundant LEA instructions. The optimization may have a negative
-    // effect on performance, so do it only for -Oz.
-    if (MF.getFunction()->optForMinSize())
-      Changed |= removeRedundantLEAs(LEAs);
+    // Remove redundant LEA instructions.
+    Changed |= removeRedundantLEAs(LEAs);
 
-    // Remove redundant address calculations.
-    Changed |= removeRedundantAddrCalc(LEAs);
+    // Remove redundant address calculations. Do it only for -Os/-Oz since only
+    // a code size gain is expected from this part of the pass.
+    if (MF.getFunction()->optForSize())
+      Changed |= removeRedundantAddrCalc(LEAs);
   }
 
   return Changed;


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D19659.55411.patch
Type: text/x-patch
Size: 3727 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20160428/e0ff0dc9/attachment.bin>