Hi Richard,
> -----Original Message-----
> From: Gcc-patches <gcc-patches-boun...@gcc.gnu.org> On Behalf Of
> Richard Biener
> Sent: 01 October 2020 14:15
> To: gcc-patches@gcc.gnu.org
> Subject: [PATCH] tree-optimization/97236 - fix bad use of
> VMAT_CONTIGUOUS
>
> This avoids using VMAT_CONTIGUOUS with single-element interleaving
> when using V1mode vectors. Instead keep VMAT_ELEMENTWISE but
> continue to avoid load-lanes and gathers.
>
> Bootstrapped on x86_64-unknown-linux-gnu, testing in progress.
I've checked that this fix also fixes the recently-reported PR 98949 on aarch64
on the GCC 9 branch.
I've bootstrapped and tested it on the branch on aarch64-none-linux.
Is it okay to backport to the branch?
Thanks,
Kyrill
>
> Richard.
>
> 2020-10-01 Richard Biener <rguent...@suse.de>
>
> PR tree-optimization/97236
> * tree-vect-stmts.c (get_group_load_store_type): Keep
> VMAT_ELEMENTWISE for single-element vectors.
>
> * gcc.dg/vect/pr97236.c: New testcase.
> ---
> gcc/testsuite/gcc.dg/vect/pr97236.c | 43
> +++++++++++++++++++++++++++++
> gcc/tree-vect-stmts.c | 20 ++++++--------
> 2 files changed, 52 insertions(+), 11 deletions(-)
> create mode 100644 gcc/testsuite/gcc.dg/vect/pr97236.c
>
> diff --git a/gcc/testsuite/gcc.dg/vect/pr97236.c
> b/gcc/testsuite/gcc.dg/vect/pr97236.c
> new file mode 100644
> index 00000000000..03e0cc38984
> --- /dev/null
> +++ b/gcc/testsuite/gcc.dg/vect/pr97236.c
> @@ -0,0 +1,43 @@
> +typedef unsigned char __uint8_t;
> +typedef __uint8_t uint8_t;
> +typedef struct plane_t {
> + uint8_t *p_pixels;
> + int i_lines;
> + int i_pitch;
> +} plane_t;
> +
> +typedef struct {
> + plane_t p[5];
> +} picture_t;
> +
> +#define N 4
> +
> +void __attribute__((noipa))
> +picture_Clone(picture_t *picture, picture_t *res)
> +{
> + for (int i = 0; i < N; i++) {
> + res->p[i].p_pixels = picture->p[i].p_pixels;
> + res->p[i].i_lines = picture->p[i].i_lines;
> + res->p[i].i_pitch = picture->p[i].i_pitch;
> + }
> +}
> +
> +int
> +main()
> +{
> + picture_t aaa, bbb;
> + uint8_t pixels[10] = {1, 1, 1, 1, 1, 1, 1, 1};
> +
> + for (unsigned i = 0; i < N; i++)
> + aaa.p[i].p_pixels = pixels;
> +
> + picture_Clone (&aaa, &bbb);
> +
> + uint8_t c;
> + for (unsigned i = 0; i < N; i++)
> + c += bbb.p[i].p_pixels[0];
> +
> + if (c != N)
> + __builtin_abort ();
> + return 0;
> +}
> diff --git a/gcc/tree-vect-stmts.c b/gcc/tree-vect-stmts.c
> index 191957c3543..3575f25241f 100644
> --- a/gcc/tree-vect-stmts.c
> +++ b/gcc/tree-vect-stmts.c
> @@ -2235,25 +2235,23 @@ get_group_load_store_type (vec_info *vinfo,
> stmt_vec_info stmt_info,
> /* First cope with the degenerate case of a single-element
> vector. */
> if (known_eq (TYPE_VECTOR_SUBPARTS (vectype), 1U))
> - *memory_access_type = VMAT_CONTIGUOUS;
> + ;
>
> /* Otherwise try using LOAD/STORE_LANES. */
> - if (*memory_access_type == VMAT_ELEMENTWISE
> - && (vls_type == VLS_LOAD
> - ? vect_load_lanes_supported (vectype, group_size,
> masked_p)
> - : vect_store_lanes_supported (vectype, group_size,
> - masked_p)))
> + else if (vls_type == VLS_LOAD
> + ? vect_load_lanes_supported (vectype, group_size,
> masked_p)
> + : vect_store_lanes_supported (vectype, group_size,
> + masked_p))
> {
> *memory_access_type = VMAT_LOAD_STORE_LANES;
> overrun_p = would_overrun_p;
> }
>
> /* If that fails, try using permuting loads. */
> - if (*memory_access_type == VMAT_ELEMENTWISE
> - && (vls_type == VLS_LOAD
> - ? vect_grouped_load_supported (vectype,
> single_element_p,
> - group_size)
> - : vect_grouped_store_supported (vectype, group_size)))
> + else if (vls_type == VLS_LOAD
> + ? vect_grouped_load_supported (vectype,
> single_element_p,
> + group_size)
> + : vect_grouped_store_supported (vectype, group_size))
> {
> *memory_access_type = VMAT_CONTIGUOUS_PERMUTE;
> overrun_p = would_overrun_p;
> --
> 2.26.2
