2009-09-09 01:54:48 +02:00
|
|
|
; RUN: llc < %s -march=x86 -mattr=+sse2 > %t
|
2008-10-21 05:55:19 +02:00
|
|
|
; RUN: not grep cmp %t
|
|
|
|
; RUN: not grep xor %t
|
|
|
|
; RUN: grep jne %t | count 1
|
|
|
|
; RUN: grep jp %t | count 1
|
|
|
|
; RUN: grep setnp %t | count 1
|
|
|
|
; RUN: grep sete %t | count 1
|
|
|
|
; RUN: grep and %t | count 1
|
|
|
|
; RUN: grep cvt %t | count 4
|
Optimized FCMP_OEQ and FCMP_UNE for x86.
Where previously LLVM might emit code like this:
ucomisd %xmm1, %xmm0
setne %al
setp %cl
orb %al, %cl
jne .LBB4_2
it now emits this:
ucomisd %xmm1, %xmm0
jne .LBB4_2
jp .LBB4_2
It has fewer instructions and uses fewer registers, but it does
have more branches. And in the case that this code is followed by
a non-fallthrough edge, it may be followed by a jmp instruction,
resulting in three branch instructions in sequence. Some effort
is made to avoid this situation.
To achieve this, X86ISelLowering.cpp now recognizes FCMP_OEQ and
FCMP_UNE in lowered form, and replace them with code that emits
two branches, except in the case where it would require converting
a fall-through edge to an explicit branch.
Also, X86InstrInfo.cpp's branch analysis and transform code now
knows now to handle blocks with multiple conditional branches. It
uses loops instead of having fixed checks for up to two
instructions. It can now analyze and transform code generated
from FCMP_OEQ and FCMP_UNE.
llvm-svn: 57873
2008-10-21 05:29:32 +02:00
|
|
|
|
|
|
|
define i32 @isint_return(double %d) nounwind {
|
|
|
|
%i = fptosi double %d to i32
|
|
|
|
%e = sitofp i32 %i to double
|
|
|
|
%c = fcmp oeq double %d, %e
|
|
|
|
%z = zext i1 %c to i32
|
|
|
|
ret i32 %z
|
|
|
|
}
|
|
|
|
|
|
|
|
declare void @foo()
|
|
|
|
|
|
|
|
define void @isint_branch(double %d) nounwind {
|
|
|
|
%i = fptosi double %d to i32
|
|
|
|
%e = sitofp i32 %i to double
|
|
|
|
%c = fcmp oeq double %d, %e
|
|
|
|
br i1 %c, label %true, label %false
|
|
|
|
true:
|
|
|
|
call void @foo()
|
|
|
|
ret void
|
|
|
|
false:
|
|
|
|
ret void
|
|
|
|
}
|