[Bug rtl-optimization/60086] suboptimal asm generated for a loop (store/load false aliasing)

["amonakov at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org>]

http://gcc.gnu.org/bugzilla/show_bug.cgi?id=60086

Alexander Monakov <amonakov at gcc dot gnu.org> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
                 CC|                            |amonakov at gcc dot gnu.org

--- Comment #7 from Alexander Monakov <amonakov at gcc dot gnu.org> ---
(In reply to Jakub Jelinek from comment #1)
> alignment, but still the scheduler doesn't reorder the loads vs. the store,
> unless -O3 -mavx -fschedule-insns.  The reason why the second scheduler
> doesn't reorder those is that RA allocates the same register

I think you usually want -fschedule-insns (pre-regalloc scheduling) or
-frename-registers rather than -fselective-scheduling2 when the goal is to
workaround RA conservativeness.  Unfortunately, stack accesses in the loop
prevent sched2 from using the additional freedom supplied by regrename for AVX
code in this case (when tuning is enabled).  The stack accesses seem to be a
trunk regression judging by good code supplied in the opening comment. 

(-O3 -mavx -fschedule-insns or -frename-registers, same modulo ymm* names,
%rpb-based accesses in the loop are pretty bad, but otherwise it's scheduled as
desired)
.L9:    
        movq    -136(%rbp), %rdx
        vmovapd (%r9,%rax), %ymm1
        addq    $1, %rdi
        vmovapd (%r10,%rax), %ymm0
        vaddpd  (%rdx,%rax), %ymm1, %ymm1
        movq    -144(%rbp), %rdx
        vaddpd  (%rdx,%rax), %ymm0, %ymm0
        vmovapd %ymm1, (%r9,%rax)
        vmovapd %ymm0, (%r10,%rax)
        addq    $32, %rax
        cmpq    %rdi, -152(%rbp)
        ja      .L9

(-O3 -fschedule-insns or -frename-registers, same modulo xmm* names, scheduled
as desired)
.L7:
        movapd  (%r9,%rax), %xmm0
        addq    $1, %rdi
        movapd  (%r10,%rax), %xmm2
        addpd   (%r11,%rax), %xmm0
        addpd   (%rcx,%rax), %xmm2
        movaps  %xmm0, (%r9,%rax)
        movaps  %xmm2, (%r10,%rax)
        addq    $16, %rax
        cmpq    %rdi, %r8
        ja      .L7

(-mavx -O3 -mtune=corei7-avx -frename-registers, stack-based references prevent
good scheduling)
.L9:
        movq    -136(%rbp), %rdx
        addq    $1, %rdi
        vmovapd (%r9,%rax), %ymm0
        vmovapd (%r10,%rax), %ymm3
        vaddpd  (%rdx,%rax), %ymm0, %ymm2
        movq    -144(%rbp), %rdx
        vmovapd %ymm2, (%r9,%rax)
        vaddpd  (%rdx,%rax), %ymm3, %ymm4
        vmovapd %ymm4, (%r10,%rax)
        addq    $32, %rax
        cmpq    %rdi, -152(%rbp)
        ja      .L9

(-mavx -O3 -mtune=corei7-avx -fschedule-insns -fno-ivopts, no spilling in the
loop, scheduled as desired)
.L9:    
        addq    $32, %rcx
        addq    $32, %r10
        vmovapd (%rdx), %ymm1
        addq    $32, %rsi
        vmovapd (%rdi), %ymm0
        addq    $32, %r11
        addq    $1, %rax
        addq    $32, %rdx
        vaddpd  -32(%rcx), %ymm1, %ymm1
        addq    $32, %rdi
        vaddpd  -32(%r10), %ymm0, %ymm0
        vmovapd %ymm1, -32(%rsi)
        vmovapd %ymm0, -32(%r11)
        cmpq    %rax, -184(%rbp)
        ja      .L9