2017-07-27 18:36:09 +08:00
|
|
|
; 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
|
|
|
|
|
|
|
|
|
|
%struct.SA = type { i32 , i32 , i32 , i32 ,i32 }
|
|
|
|
|
|
|
|
|
|
define void @test_func(%struct.SA* nocapture %ctx, i32 %n) local_unnamed_addr {
|
|
|
|
|
; X64-LABEL: test_func:
|
|
|
|
|
; X64: # BB#0: # %entry
|
|
|
|
|
; X64-NEXT: movl (%rdi), %eax
|
|
|
|
|
; X64-NEXT: movl 16(%rdi), %ecx
|
|
|
|
|
; X64-NEXT: leal 1(%rax,%rcx), %eax
|
|
|
|
|
; X64-NEXT: movl %eax, 12(%rdi)
|
[X86] Improvement in CodeGen instruction selection for LEAs (re-applying post required revision changes.)
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, jmolloy
Reviewed By: lsaba
Subscribers: jmolloy, spatel, igorb, llvm-commits
Differential Revision: https://reviews.llvm.org/D35014
llvm-svn: 314886
2017-10-04 17:02:10 +08:00
|
|
|
; X64-NEXT: addq %rcx, %eax
|
2017-07-27 18:36:09 +08:00
|
|
|
; X64-NEXT: movl %eax, 16(%rdi)
|
|
|
|
|
; X64-NEXT: retq
|
|
|
|
|
;
|
|
|
|
|
; X86-LABEL: test_func:
|
|
|
|
|
; X86: # BB#0: # %entry
|
|
|
|
|
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
|
|
|
; X86-NEXT: movl (%eax), %ecx
|
|
|
|
|
; X86-NEXT: movl 16(%eax), %edx
|
[X86] Improvement in CodeGen instruction selection for LEAs (re-applying post required revision changes.)
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, jmolloy
Reviewed By: lsaba
Subscribers: jmolloy, spatel, igorb, llvm-commits
Differential Revision: https://reviews.llvm.org/D35014
llvm-svn: 314886
2017-10-04 17:02:10 +08:00
|
|
|
; X86-NEXT: leal 1(%ecx,%edx), %ecx
|
|
|
|
|
; X86-NEXT: movl %ecx, 12(%eax)
|
2017-07-27 18:36:09 +08:00
|
|
|
; X86-NEXT: addl %edx, %ecx
|
|
|
|
|
; X86-NEXT: movl %ecx, 16(%eax)
|
|
|
|
|
; X86-NEXT: retl
|
|
|
|
|
entry:
|
|
|
|
|
%h0 = getelementptr inbounds %struct.SA, %struct.SA* %ctx, i64 0, i32 0
|
|
|
|
|
%0 = load i32, i32* %h0, align 8
|
|
|
|
|
%h3 = getelementptr inbounds %struct.SA, %struct.SA* %ctx, i64 0, i32 3
|
|
|
|
|
%h4 = getelementptr inbounds %struct.SA, %struct.SA* %ctx, i64 0, i32 4
|
|
|
|
|
%1 = load i32, i32* %h4, align 8
|
|
|
|
|
%add = add i32 %0, 1
|
|
|
|
|
%add4 = add i32 %add, %1
|
|
|
|
|
store i32 %add4, i32* %h3, align 4
|
|
|
|
|
%add29 = add i32 %add4 , %1
|
|
|
|
|
store i32 %add29, i32* %h4, align 8
|
|
|
|
|
ret void
|
|
|
|
|
}
|