llvm-mirror/test/CodeGen/X86/fp-une-cmp.ll
Cong Hou 4458d58ad9 Allow X86::COND_NE_OR_P and X86::COND_NP_OR_E to be reversed.
Currently, AnalyzeBranch() fails non-equality comparison between floating points
on X86 (see https://llvm.org/bugs/show_bug.cgi?id=23875). This is because this
function can modify the branch by reversing the conditional jump and removing
unconditional jump if there is a proper fall-through. However, in the case of
non-equality comparison between floating points, this can turn the branch
"unanalyzable". Consider the following case:

jne.BB1
jp.BB1
jmp.BB2
.BB1:
...
.BB2:
...

AnalyzeBranch() will reverse "jp .BB1" to "jnp .BB2" and then "jmp .BB2" will be
removed:

jne.BB1
jnp.BB2
.BB1:
...
.BB2:
...

However, AnalyzeBranch() cannot analyze this branch anymore as there are two
conditional jumps with different targets. This may disable some optimizations
like block-placement: in this case the fall-through behavior is enforced even if
the fall-through block is very cold, which is suboptimal.

Actually this optimization is also done in block-placement pass, which means we
can remove this optimization from AnalyzeBranch(). However, currently
X86::COND_NE_OR_P and X86::COND_NP_OR_E are not reversible: there is no defined
negation conditions for them.

In order to reverse them, this patch defines two new CondCode X86::COND_E_AND_NP
and X86::COND_P_AND_NE. It also defines how to synthesize instructions for them.
Here only the second conditional jump is reversed. This is valid as we only need
them to do this "unconditional jump removal" optimization.


Differential Revision: http://reviews.llvm.org/D11393

llvm-svn: 264199
2016-03-23 21:45:37 +00:00

108 lines
2.5 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown | FileCheck %s
; <rdar://problem/7859988>
; Make sure we don't generate more jumps than we need to. We used to generate
; something like this:
;
; jne LBB0_1
; jnp LBB0_2
; LBB0_1:
; jmp LBB0_3
; LBB0_2:
; addsd ...
; LBB0_3:
;
; Now we generate this:
;
; jne LBB0_2
; jp LBB0_2
; addsd ...
; LBB0_2:
define double @rdar_7859988(double %x, double %y) nounwind readnone optsize ssp {
; CHECK-LABEL: rdar_7859988:
; CHECK: # BB#0: # %entry
; CHECK-NEXT: mulsd %xmm1, %xmm0
; CHECK-NEXT: xorpd %xmm1, %xmm1
; CHECK-NEXT: ucomisd %xmm1, %xmm0
; CHECK-NEXT: jne .LBB0_2
; CHECK-NEXT: jp .LBB0_2
; CHECK-NEXT: # BB#1: # %bb1
; CHECK-NEXT: addsd {{.*}}(%rip), %xmm0
; CHECK-NEXT: .LBB0_2: # %bb2
; CHECK-NEXT: retq
entry:
%mul = fmul double %x, %y
%cmp = fcmp une double %mul, 0.000000e+00
br i1 %cmp, label %bb2, label %bb1
bb1:
%add = fadd double %mul, -1.000000e+00
br label %bb2
bb2:
%phi = phi double [ %add, %bb1 ], [ %mul, %entry ]
ret double %phi
}
define double @profile_metadata(double %x, double %y) {
; CHECK-LABEL: profile_metadata:
; CHECK: # BB#0: # %entry
; CHECK-NEXT: mulsd %xmm1, %xmm0
; CHECK-NEXT: xorpd %xmm1, %xmm1
; CHECK-NEXT: ucomisd %xmm1, %xmm0
; CHECK-NEXT: jne .LBB1_1
; CHECK-NEXT: jp .LBB1_1
; CHECK-NEXT: .LBB1_2: # %bb2
; CHECK-NEXT: retq
; CHECK-NEXT: .LBB1_1: # %bb1
; CHECK-NEXT: addsd {{.*}}(%rip), %xmm0
; CHECK-NEXT: jmp .LBB1_2
entry:
%mul = fmul double %x, %y
%cmp = fcmp une double %mul, 0.000000e+00
br i1 %cmp, label %bb1, label %bb2, !prof !1
bb1:
%add = fadd double %mul, -1.000000e+00
br label %bb2
bb2:
%phi = phi double [ %add, %bb1 ], [ %mul, %entry ]
ret double %phi
}
; Test if the negation of the non-equality check between floating points are
; translated to jnp followed by jne.
define void @foo(float %f) {
; CHECK-LABEL: foo:
; CHECK: # BB#0: # %entry
; CHECK-NEXT: xorps %xmm1, %xmm1
; CHECK-NEXT: ucomiss %xmm1, %xmm0
; CHECK-NEXT: jne .LBB2_2
; CHECK-NEXT: jnp .LBB2_1
; CHECK-NEXT: .LBB2_2: # %if.then
; CHECK-NEXT: jmp a # TAILCALL
; CHECK-NEXT: .LBB2_1: # %if.end
; CHECK-NEXT: retq
entry:
%cmp = fcmp une float %f, 0.000000e+00
br i1 %cmp, label %if.then, label %if.end
if.then:
tail call void @a()
br label %if.end
if.end:
ret void
}
declare void @a()
!1 = !{!"branch_weights", i32 1, i32 1000}