On Tue, May 18, 2021 at 9:16 PM H.J. Lu <hjl.to...@gmail.com> wrote:
>
> When expanding a constant constructor, don't call expand_constructor if
> it is more efficient to load the data from the memory via move by pieces.
>
> gcc/
>
> PR middle-end/90773
> * expr.c (expand_expr_real_1): Don't call expand_constructor if
> it is more efficient to load the data from the memory.
>
> gcc/testsuite/
>
> PR middle-end/90773
> * gcc.target/i386/pr90773-24.c: New test.
> * gcc.target/i386/pr90773-25.c: Likewise.
> ---
> gcc/expr.c | 10 ++++++++++
> gcc/testsuite/gcc.target/i386/pr90773-24.c | 22 ++++++++++++++++++++++
> gcc/testsuite/gcc.target/i386/pr90773-25.c | 20 ++++++++++++++++++++
> 3 files changed, 52 insertions(+)
> create mode 100644 gcc/testsuite/gcc.target/i386/pr90773-24.c
> create mode 100644 gcc/testsuite/gcc.target/i386/pr90773-25.c
>
> diff --git a/gcc/expr.c b/gcc/expr.c
> index d09ee42e262..80e01ea1cbe 100644
> --- a/gcc/expr.c
> +++ b/gcc/expr.c
> @@ -10886,6 +10886,16 @@ expand_expr_real_1 (tree exp, rtx target,
> machine_mode tmode,
> unsigned HOST_WIDE_INT ix;
> tree field, value;
>
> + /* Check if it is more efficient to load the data from
> + the memory directly. FIXME: How many stores do we
> + need here if not moved by pieces? */
> + unsigned HOST_WIDE_INT bytes
> + = tree_to_uhwi (TYPE_SIZE_UNIT (type));
that's prone to fail - it could be a VLA.
> + if ((bytes / UNITS_PER_WORD) > 2
> + && MOVE_MAX_PIECES > UNITS_PER_WORD
> + && can_move_by_pieces (bytes, TYPE_ALIGN (type)))
> + goto normal_inner_ref;
> +
It looks like you're concerned about aggregate copies but this also handles
non-aggregates (which on GIMPLE might already be optimized of course).
Also you say "if it's cheaper" but I see no cost considerations. How do
we generally handle immed const vs. load from constant pool costs?
> FOR_EACH_CONSTRUCTOR_ELT (CONSTRUCTOR_ELTS (init), ix,
> field, value)
> if (tree_int_cst_equal (field, index))
> diff --git a/gcc/testsuite/gcc.target/i386/pr90773-24.c
> b/gcc/testsuite/gcc.target/i386/pr90773-24.c
> new file mode 100644
> index 00000000000..4a4b62533dc
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/i386/pr90773-24.c
> @@ -0,0 +1,22 @@
> +/* { dg-do compile } */
> +/* { dg-options "-O2 -march=x86-64" } */
> +
> +struct S
> +{
> + long long s1 __attribute__ ((aligned (8)));
> + unsigned s2, s3, s4, s5, s6, s7, s8, s9, s10, s11, s12, s13, s14;
> +};
> +
> +const struct S array[] = {
> + { 0, 60, 640, 2112543726, 39682, 48, 16, 33, 10, 96, 2, 0, 0, 4 }
> +};
> +
> +void
> +foo (struct S *x)
> +{
> + x[0] = array[0];
> +}
> +/* { dg-final { scan-assembler-times "movups\[\\t \]%xmm\[0-9\]+,
> \\(%\[\^,\]+\\)" 1 } } */
> +/* { dg-final { scan-assembler-times "movups\[\\t \]%xmm\[0-9\]+,
> 16\\(%\[\^,\]+\\)" 1 } } */
> +/* { dg-final { scan-assembler-times "movups\[\\t \]%xmm\[0-9\]+,
> 32\\(%\[\^,\]+\\)" 1 } } */
> +/* { dg-final { scan-assembler-times "movups\[\\t \]%xmm\[0-9\]+,
> 48\\(%\[\^,\]+\\)" 1 } } */
> diff --git a/gcc/testsuite/gcc.target/i386/pr90773-25.c
> b/gcc/testsuite/gcc.target/i386/pr90773-25.c
> new file mode 100644
> index 00000000000..2520b670989
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/i386/pr90773-25.c
> @@ -0,0 +1,20 @@
> +/* { dg-do compile } */
> +/* { dg-options "-O2 -march=skylake" } */
> +
> +struct S
> +{
> + long long s1 __attribute__ ((aligned (8)));
> + unsigned s2, s3, s4, s5, s6, s7, s8, s9, s10, s11, s12, s13, s14;
> +};
> +
> +const struct S array[] = {
> + { 0, 60, 640, 2112543726, 39682, 48, 16, 33, 10, 96, 2, 0, 0, 4 }
> +};
> +
> +void
> +foo (struct S *x)
> +{
> + x[0] = array[0];
> +}
> +/* { dg-final { scan-assembler-times "vmovdqu\[\\t \]%ymm\[0-9\]+,
> \\(%\[\^,\]+\\)" 1 } } */
> +/* { dg-final { scan-assembler-times "vmovdqu\[\\t \]%ymm\[0-9\]+,
> 32\\(%\[\^,\]+\\)" 1 } } */
> --
> 2.31.1
>
