[Bug middle-end/88873] missing vectorization for decomposed operations on a vector type

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

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=88873

--- Comment #8 from CVS Commits <cvs-commit at gcc dot gnu.org> ---
The master branch has been updated by Roger Sayle <sayle@gcc.gnu.org>:

https://gcc.gnu.org/g:8911879415d6c2a7baad88235554a912887a1c5c

commit r14-2526-g8911879415d6c2a7baad88235554a912887a1c5c
Author: Roger Sayle <roger@nextmovesoftware.com>
Date:   Fri Jul 14 18:10:05 2023 +0100

    i386: Improved insv of DImode/DFmode {high,low}parts into TImode.

    This is the next piece towards a fix for (the x86_64 ABI issues affecting)
    PR 88873.  This patch generalizes the recent tweak to ix86_expand_move
    for setting the highpart of a TImode reg from a DImode source using
    *insvti_highpart_1, to handle both DImode and DFmode sources, and also
    use the recently added *insvti_lowpart_1 for setting the lowpart.

    Although this is another intermediate step (not yet a fix), towards
    enabling *insvti and *concat* patterns to be candidates for TImode STV
    (by using V2DI/V2DF instructions), it already improves things a little.

    For the test case from PR 88873

    typedef struct { double x, y; } s_t;
    typedef double v2df __attribute__ ((vector_size (2 * sizeof(double))));

    s_t foo (s_t a, s_t b, s_t c)
    {
      return (s_t) { fma(a.x, b.x, c.x), fma (a.y, b.y, c.y) };
    }

    With -O2 -march=cascadelake, GCC currently generates:

    Before (29 instructions):
            vmovq   %xmm2, -56(%rsp)
            movq    -56(%rsp), %rdx
            vmovq   %xmm4, -40(%rsp)
            movq    $0, -48(%rsp)
            movq    %rdx, -56(%rsp)
            movq    -40(%rsp), %rdx
            vmovq   %xmm0, -24(%rsp)
            movq    %rdx, -40(%rsp)
            movq    -24(%rsp), %rsi
            movq    -56(%rsp), %rax
            movq    $0, -32(%rsp)
            vmovq   %xmm3, -48(%rsp)
            movq    -48(%rsp), %rcx
            vmovq   %xmm5, -32(%rsp)
            vmovq   %rax, %xmm6
            movq    -40(%rsp), %rax
            movq    $0, -16(%rsp)
            movq    %rsi, -24(%rsp)
            movq    -32(%rsp), %rsi
            vpinsrq $1, %rcx, %xmm6, %xmm6
            vmovq   %rax, %xmm7
            vmovq   %xmm1, -16(%rsp)
            vmovapd %xmm6, %xmm3
            vpinsrq $1, %rsi, %xmm7, %xmm7
            vfmadd132pd     -24(%rsp), %xmm7, %xmm3
            vmovapd %xmm3, -56(%rsp)
            vmovsd  -48(%rsp), %xmm1
            vmovsd  -56(%rsp), %xmm0
            ret

    After (20 instructions):
            vmovq   %xmm2, -56(%rsp)
            movq    -56(%rsp), %rax
            vmovq   %xmm3, -48(%rsp)
            vmovq   %xmm4, -40(%rsp)
            movq    -48(%rsp), %rcx
            vmovq   %xmm5, -32(%rsp)
            vmovq   %rax, %xmm6
            movq    -40(%rsp), %rax
            movq    -32(%rsp), %rsi
            vpinsrq $1, %rcx, %xmm6, %xmm6
            vmovq   %xmm0, -24(%rsp)
            vmovq   %rax, %xmm7
            vmovq   %xmm1, -16(%rsp)
            vmovapd %xmm6, %xmm2
            vpinsrq $1, %rsi, %xmm7, %xmm7
            vfmadd132pd     -24(%rsp), %xmm7, %xmm2
            vmovapd %xmm2, -56(%rsp)
            vmovsd  -48(%rsp), %xmm1
            vmovsd  -56(%rsp), %xmm0
            ret

    2023-07-14  Roger Sayle  <roger@nextmovesoftware.com>

    gcc/ChangeLog
            * config/i386/i386-expand.cc (ix86_expand_move): Generalize special
            case inserting of 64-bit values into a TImode register, to handle
            both DImode and DFmode using either *insvti_lowpart_1
            or *isnvti_highpart_1.