Second half of my fixed-sized-alloca patch. This folds the LEA to compute
the alloca address into common operations like loads/stores.
In a simple testcase like this (which is just designed to excersize the
alloca A, nothing more):
int %test(int %X, bool %C) {
%A = alloca int
store int %X, int* %A
store int* %A, int** %G
br bool %C, label %T, label %F
T:
call int %test(int 1, bool false)
%V = load int* %A
ret int %V
F:
call int %test(int 123, bool true)
%V2 = load int* %A
ret int %V2
}
We now generate:
test:
sub %ESP, 12
mov %EAX, DWORD PTR [%ESP + 16]
mov %CL, BYTE PTR [%ESP + 20]
*** mov DWORD PTR [%ESP + 8], %EAX
mov %EAX, OFFSET G
lea %EDX, DWORD PTR [%ESP + 8]
mov DWORD PTR [%EAX], %EDX
test %CL, %CL
je .LBB2 # PC rel: F
.LBB1: # T
mov DWORD PTR [%ESP], 1
mov DWORD PTR [%ESP + 4], 0
call test
*** mov %EAX, DWORD PTR [%ESP + 8]
add %ESP, 12
ret
.LBB2: # F
mov DWORD PTR [%ESP], 123
mov DWORD PTR [%ESP + 4], 1
call test
*** mov %EAX, DWORD PTR [%ESP + 8]
add %ESP, 12
ret
Instead of:
test:
sub %ESP, 20
mov %EAX, DWORD PTR [%ESP + 24]
mov %CL, BYTE PTR [%ESP + 28]
*** lea %EDX, DWORD PTR [%ESP + 16]
*** mov DWORD PTR [%EDX], %EAX
mov %EAX, OFFSET G
mov DWORD PTR [%EAX], %EDX
test %CL, %CL
*** mov DWORD PTR [%ESP + 12], %EDX
je .LBB2 # PC rel: F
.LBB1: # T
mov DWORD PTR [%ESP], 1
mov %EAX, 0
mov DWORD PTR [%ESP + 4], %EAX
call test
*** mov %EAX, DWORD PTR [%ESP + 12]
*** mov %EAX, DWORD PTR [%EAX]
add %ESP, 20
ret
.LBB2: # F
mov DWORD PTR [%ESP], 123
mov %EAX, 1
mov DWORD PTR [%ESP + 4], %EAX
call test
*** mov %EAX, DWORD PTR [%ESP + 12]
*** mov %EAX, DWORD PTR [%EAX]
add %ESP, 20
ret
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@13557 91177308-0d34-0410-b5e6-96231b3b80d8
2 files changed