[X86] PR32755 : Improvement in CodeGen instruction selection for LEAs.

Summary:
   1/  Operand folding during complex pattern matching for LEAs has been
       extended, such that it promotes Scale to accommodate similar operand
       appearing in the DAG.
       e.g.
          T1 = A + B
          T2 = T1 + 10
          T3 = T2 + A
       For above DAG rooted at T3, X86AddressMode will no look like
          Base = B , Index = A , Scale = 2 , Disp = 10

   2/  During OptimizeLEAPass down the pipeline factorization is now performed over LEAs
       so that if there is an opportunity then complex LEAs (having 3 operands)
       could be factored out.
       e.g.
          leal 1(%rax,%rcx,1), %rdx
          leal 1(%rax,%rcx,2), %rcx
       will be factored as following
          leal 1(%rax,%rcx,1), %rdx
          leal (%rdx,%rcx)   , %edx

   3/ Aggressive operand folding for AM based selection for LEAs is sensitive to loops,
      thus avoiding creation of any complex LEAs within a loop.

Reviewers: lsaba, RKSimon, craig.topper, qcolombet

Reviewed By: lsaba

Subscribers: spatel, igorb, llvm-commits

Differential Revision: https://reviews.llvm.org/D35014

llvm-svn: 313343

1 files changed, 18 insertions, 24 deletions

diff --git a/llvm/test/CodeGen/X86/lea-opt-cse2.ll b/llvm/test/CodeGen/X86/lea-opt-cse2.ll
index 573b93dde43..73aeea06e6a 100644
--- a/llvm/test/CodeGen/X86/lea-opt-cse2.ll
+++ b/llvm/test/CodeGen/X86/lea-opt-cse2.ll
@@ -1,6 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc < %s -mtriple=x86_64-unknown | FileCheck %s -check-prefix=X64
-; RUN: llc < %s -mtriple=i686-unknown   | FileCheck %s -check-prefix=X86
+; RUN: llc < %s -mtriple=x86_64-unknown  -mattr=+slow-3ops-lea | FileCheck %s -check-prefix=X64
+; RUN: llc < %s -mtriple=i686-unknown  -mattr=+slow-3ops-lea  | FileCheck %s -check-prefix=X86
 
 %struct.SA = type { i32 , i32 , i32 , i32 , i32};
 
@@ -10,47 +10,41 @@ define void @foo(%struct.SA* nocapture %ctx, i32 %n) local_unnamed_addr #0 {
 ; X64-NEXT:    .p2align 4, 0x90
 ; X64-NEXT:  .LBB0_1: # %loop
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
-; X64-NEXT:    movl (%rdi), %eax
-; X64-NEXT:    movl 16(%rdi), %ecx
-; X64-NEXT:    leal 1(%rax,%rcx), %edx
-; X64-NEXT:    movl %edx, 12(%rdi)
+; X64-NEXT:    movl 16(%rdi), %eax
+; X64-NEXT:    movl (%rdi), %ecx
+; X64-NEXT:    addl %eax, %ecx
+; X64-NEXT:    incl %ecx
+; X64-NEXT:    movl %ecx, 12(%rdi)
 ; X64-NEXT:    decl %esi
 ; X64-NEXT:    jne .LBB0_1
 ; X64-NEXT:  # BB#2: # %exit
-; X64-NEXT:    addl %ecx, %eax
-; X64-NEXT:    leal 1(%rcx,%rax), %eax
-; X64-NEXT:    movl %eax, 16(%rdi)
+; X64-NEXT:    addl %eax, %ecx
+; X64-NEXT:    movl %ecx, 16(%rdi)
 ; X64-NEXT:    retq
 ;
 ; X86-LABEL: foo:
 ; X86:       # BB#0: # %entry
-; X86-NEXT:    pushl %edi
+; X86-NEXT:    pushl %esi
 ; X86-NEXT:  .Lcfi0:
 ; X86-NEXT:    .cfi_def_cfa_offset 8
-; X86-NEXT:    pushl %esi
 ; X86-NEXT:  .Lcfi1:
-; X86-NEXT:    .cfi_def_cfa_offset 12
-; X86-NEXT:  .Lcfi2:
-; X86-NEXT:    .cfi_offset %esi, -12
-; X86-NEXT:  .Lcfi3:
-; X86-NEXT:    .cfi_offset %edi, -8
+; X86-NEXT:    .cfi_offset %esi, -8
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; X86-NEXT:    .p2align 4, 0x90
 ; X86-NEXT:  .LBB0_1: # %loop
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
-; X86-NEXT:    movl (%eax), %edx
-; X86-NEXT:    movl 16(%eax), %esi
-; X86-NEXT:    leal 1(%edx,%esi), %edi
-; X86-NEXT:    movl %edi, 12(%eax)
+; X86-NEXT:    movl 16(%eax), %edx
+; X86-NEXT:    movl (%eax), %esi
+; X86-NEXT:    addl %edx, %esi
+; X86-NEXT:    incl %esi
+; X86-NEXT:    movl %esi, 12(%eax)
 ; X86-NEXT:    decl %ecx
 ; X86-NEXT:    jne .LBB0_1
 ; X86-NEXT:  # BB#2: # %exit
-; X86-NEXT:    addl %esi, %edx
-; X86-NEXT:    leal 1(%esi,%edx), %ecx
-; X86-NEXT:    movl %ecx, 16(%eax)
+; X86-NEXT:    addl %edx, %esi
+; X86-NEXT:    movl %esi, 16(%eax)
 ; X86-NEXT:    popl %esi
-; X86-NEXT:    popl %edi
 ; X86-NEXT:    retl
  entry:
    br label %loop