On Fri, May 13, 2022 at 1:43 PM liuhongt <hongtao....@intel.com> wrote:
>
> When d->perm[i] == d->perm[i-1] + 1 and d->perm[i] == nelt, it's not
> continuous. It should fail if there's more than 2 continuous areas.
>
> Bootstrapped and regtested on x86_64-pc-linux-gnu{-m32,}.
> Ok for trunk?
>
>
> gcc/ChangeLog:
>
> PR target/105587
> * config/i386/i386-expand.cc
> (expand_vec_perm_pslldq_psrldq_por): Fail when (d->perm[i] ==
> d->perm[i-1] + 1) && d->perm[i] == nelt && start != -1.
>
> gcc/testsuite/ChangeLog:
>
> * gcc.target/i386/pr105587.c: New test.
LGTM, probably even obvious patch.
Thanks,
Uros.
> ---
> gcc/config/i386/i386-expand.cc | 9 ++-------
> gcc/testsuite/gcc.target/i386/pr105587.c | 11 +++++++++++
> 2 files changed, 13 insertions(+), 7 deletions(-)
> create mode 100644 gcc/testsuite/gcc.target/i386/pr105587.c
>
> diff --git a/gcc/config/i386/i386-expand.cc b/gcc/config/i386/i386-expand.cc
> index 0fd3028c205..806e1f5aaa3 100644
> --- a/gcc/config/i386/i386-expand.cc
> +++ b/gcc/config/i386/i386-expand.cc
> @@ -20963,7 +20963,8 @@ expand_vec_perm_pslldq_psrldq_por (struct
> expand_vec_perm_d *d, bool pandn)
> start1 = d->perm[0];
> for (i = 1; i < nelt; i++)
> {
> - if (d->perm[i] != d->perm[i-1] + 1)
> + if (d->perm[i] != d->perm[i-1] + 1
> + || d->perm[i] == nelt)
> {
> if (start2 == -1)
> {
> @@ -20973,12 +20974,6 @@ expand_vec_perm_pslldq_psrldq_por (struct
> expand_vec_perm_d *d, bool pandn)
> else
> return false;
> }
> - else if (d->perm[i] >= nelt
> - && start2 == -1)
> - {
> - start2 = d->perm[i];
> - end1 = d->perm[i-1];
> - }
> }
>
> clear_op0 = end1 != nelt - 1;
> diff --git a/gcc/testsuite/gcc.target/i386/pr105587.c
> b/gcc/testsuite/gcc.target/i386/pr105587.c
> new file mode 100644
> index 00000000000..a5b6ab2a016
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/i386/pr105587.c
> @@ -0,0 +1,11 @@
> +#/* { dg-do compile } */
> +/* { dg-options "-O3 -msse2 -mno-ssse3" } */
> +
> +extern short arr_108[][4][2][24][12], arr_110[][4][2][24][12];
> +void test() {
> + for (unsigned a = 0; a < 2; a += 2)
> + for (unsigned b = 4; b < 22; b++)
> + for (int c = 1; c < 11; c++)
> + arr_110[0][0][a][b][c] = (unsigned char)arr_108[0][0][a][b][c];
> +}
> +
> --
> 2.18.1
>
