On Fri, Jul 29, 2022 at 04:53:51PM +0100, Andrew Stubbs wrote:
> This patch adjusts the generation of SIMD "inbranch" clones that use integer
> masks to ensure that it vectorizes on amdgcn.
>
> The problem was only that an amdgcn mask is DImode and the shift amount was
> SImode, and the difference causes vectorization to fail.
>
> OK for mainline?
>
> Andrew
> openmp-simd-clone: Match shift types
>
> Ensure that both parameters to vector shifts use the same mode. This is most
> important for amdgcn where the masks are DImode.
>
> gcc/ChangeLog:
>
> * omp-simd-clone.cc (simd_clone_adjust): Convert shift_cnt to match
> the mask type.
>
> diff --git a/gcc/omp-simd-clone.cc b/gcc/omp-simd-clone.cc
> index 32649bc3f9a..5d3a90730e7 100644
> --- a/gcc/omp-simd-clone.cc
> +++ b/gcc/omp-simd-clone.cc
> @@ -1305,8 +1305,12 @@ simd_clone_adjust (struct cgraph_node *node)
> build_int_cst (TREE_TYPE (iter1), c));
> gsi_insert_after (&gsi, g, GSI_CONTINUE_LINKING);
> }
> + tree shift_cnt_conv = make_ssa_name (TREE_TYPE (mask));
> + g = gimple_build_assign (shift_cnt_conv,
> + fold_convert (TREE_TYPE (mask), shift_cnt));
> + gsi_insert_after (&gsi, g, GSI_CONTINUE_LINKING);
Doing the fold_convert seems to be a wasted effort to me.
Can't this be done conditional on whether some change is needed at all
and just using gimple_build_assign with NOP_EXPR, so something like:
tree shift_cvt_conv = shift_cnt;
if (!useless_type_conversion_p (TREE_TYPE (mask),
TREE_TYPE (shift_cnt)))
{
shift_cnt_conv = make_ssa_name (TREE_TYPE (mask));
g = gimple_build_assign (shift_cnt_conv, NOP_EXPR, shift_cnt);
gsi_insert_after (&gsi, g, GSI_CONTINUE_LINKING);
}
> g = gimple_build_assign (make_ssa_name (TREE_TYPE (mask)),
> - RSHIFT_EXPR, mask, shift_cnt);
> + RSHIFT_EXPR, mask, shift_cnt_conv);
> gsi_insert_after (&gsi, g, GSI_CONTINUE_LINKING);
> mask = gimple_assign_lhs (g);
> g = gimple_build_assign (make_ssa_name (TREE_TYPE (mask)),
?
Jakub
