Codegen integer abs more efficiently using the trick from the PPC CWG. This
improves codegen on many architectures. Tests committed as CodeGen/*/iabs.ll
X86 Old: X86 New:
_test: _test:
movl 4(%esp), %ecx movl 4(%esp), %eax
movl %ecx, %eax movl %eax, %ecx
negl %eax sarl $31, %ecx
testl %ecx, %ecx addl %ecx, %eax
cmovns %ecx, %eax xorl %ecx, %eax
ret ret
PPC Old: PPC New:
_test: _test:
cmpwi cr0, r3, -1 srawi r2, r3, 31
neg r2, r3 add r3, r3, r2
bgt cr0, LBB1_2 ; xor r3, r3, r2
LBB1_1: ; blr
mr r3, r2
LBB1_2: ;
blr
ARM Old: ARM New:
_test: _test:
rsb r3, r0, #0 add r3, r0, r0, asr #31
cmp r0, #0 eor r0, r3, r0, asr #31
movge r3, r0 bx lr
mov r0, r3
bx lr
Thumb Old: Thumb New:
_test: _test:
neg r2, r0 asr r2, r0, #31
cmp r0, #0 add r0, r0, r2
bge LBB1_2 eor r0, r2
LBB1_1: @ bx lr
cpy r0, r2
LBB1_2: @
bx lr
Sparc Old: Sparc New:
test: test:
save -96, %o6, %o6 save -96, %o6, %o6
sethi 0, %l0 sra %i0, 31, %l0
sub %l0, %i0, %l0 add %i0, %l0, %l1
subcc %i0, -1, %l1 xor %l1, %l0, %i0
bg .BB1_2 restore %g0, %g0, %g0
nop retl
.BB1_1: nop
or %g0, %l0, %i0
.BB1_2:
restore %g0, %g0, %g0
retl
nop
It also helps alpha/ia64 :)
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@35881 91177308-0d34-0410-b5e6-96231b3b80d8
1 file changed