[Bug tree-optimization/68501] New: [6 Regression] sqrt builtin is not used anymore

["afomin.mailbox at gmail dot com" <gcc-bugzilla at gcc dot gnu dot org>]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=68501

            Bug ID: 68501
           Summary: [6 Regression] sqrt builtin is not used anymore
           Product: gcc
           Version: 6.0
            Status: UNCONFIRMED
          Severity: normal
          Priority: P3
         Component: tree-optimization
          Assignee: unassigned at gcc dot gnu.org
          Reporter: afomin.mailbox at gmail dot com
                CC: izamyatin at gmail dot com, rsandifo at redhat dot com,
                    ysrumyan at gmail dot com
  Target Milestone: ---
            Target: x86_64-*-*

Created attachment 36812
  --> https://gcc.gnu.org/bugzilla/attachment.cgi?id=36812&action=edit
A reproducer

For the attached reproducer compiled with g++ -mavx -Ofast we do not use IA
sqrt builtin since r230492 thus emitting more insns.

r230491
.L8:
    vmovaps (%r14,%rax), %ymm0
    addl    $1, %r12d
    vmovups 0(%r13,%rax), %xmm1
    vinsertf128 $0x1, 16(%r13,%rax), %ymm1, %ymm1
    vmulps  %ymm1, %ymm1, %ymm1
    vmulps  %ymm0, %ymm0, %ymm0
    vaddps  %ymm1, %ymm0, %ymm1
    vrsqrtps    %ymm1, %ymm2
    vmulps  %ymm1, %ymm2, %ymm0
    vmulps  %ymm2, %ymm0, %ymm0
    vaddps  %ymm4, %ymm0, %ymm0
    vmulps  %ymm3, %ymm2, %ymm2
    vmulps  %ymm2, %ymm0, %ymm0
    vmovups %xmm0, (%r10,%rax)
    vextractf128    $0x1, %ymm0, 16(%r10,%rax)
    addq    $32, %rax
    cmpl    %r12d, %r9d
    ja  .L8 

r230492
.L8:
.L8:
    vmovaps (%r14,%rax), %ymm0
    addl    $1, %r12d
    vmovups 0(%r13,%rax), %xmm1
    vinsertf128 $0x1, 16(%r13,%rax), %ymm1, %ymm1
    vmulps  %ymm1, %ymm1, %ymm1
    vmulps  %ymm0, %ymm0, %ymm0
    vaddps  %ymm1, %ymm0, %ymm1
    vcmpneqps   %ymm1, %ymm2, %ymm5
    vrsqrtps    %ymm1, %ymm0
    vandps  %ymm5, %ymm0, %ymm0
    vmulps  %ymm1, %ymm0, %ymm1
    vmulps  %ymm0, %ymm1, %ymm0
    vaddps  %ymm4, %ymm0, %ymm0
    vmulps  %ymm3, %ymm1, %ymm1
    vmulps  %ymm1, %ymm0, %ymm0
    vrcpps  %ymm0, %ymm1
    vmulps  %ymm0, %ymm1, %ymm0
    vmulps  %ymm0, %ymm1, %ymm0
    vaddps  %ymm1, %ymm1, %ymm1
    vsubps  %ymm0, %ymm1, %ymm0
    vmovups %xmm0, (%r10,%rax)
    vextractf128    $0x1, %ymm0, 16(%r10,%rax)
    addq    $32, %rax
    cmpl    %r12d, %r9d
    ja  .L8