Could you add a testcase? Otherwise LGTM.
Option: -O2 -mtune=thead-c906 -march=rv64gc -mabi=lp64
void foo(char *dst){
__builtin_memset(dst, 0, 15);
}
On Thu, Jul 22, 2021 at 8:53 PM Christoph Muellner via Gcc-patches
<[email protected]> wrote:
>
> This patch enables the overlap-by-pieces feature of the by-pieces
> infrastructure for inlining builtins in case the target has set
> riscv_slow_unaligned_access_p to false.
>
> To demonstrate the effect for targets with fast unaligned access,
> the following code sequences are generated for a 15-byte memset-zero.
>
> Without overlap_op_by_pieces we get:
> 8e: 00053023 sd zero,0(a0)
> 92: 00052423 sw zero,8(a0)
> 96: 00051623 sh zero,12(a0)
> 9a: 00050723 sb zero,14(a0)
>
> With overlap_op_by_pieces we get:
> 7e: 00053023 sd zero,0(a0)
> 82: 000533a3 sd zero,7(a0)
>
> gcc/ChangeLog:
>
> * config/riscv/riscv.c (riscv_overlap_op_by_pieces): New function.
> (TARGET_OVERLAP_OP_BY_PIECES_P): Connect to
> riscv_overlap_op_by_pieces.
>
> Signed-off-by: Christoph Muellner <[email protected]>
> ---
> gcc/config/riscv/riscv.c | 11 +++++++++++
> 1 file changed, 11 insertions(+)
>
> diff --git a/gcc/config/riscv/riscv.c b/gcc/config/riscv/riscv.c
> index 576960bb37c..98c76ba657a 100644
> --- a/gcc/config/riscv/riscv.c
> +++ b/gcc/config/riscv/riscv.c
> @@ -5201,6 +5201,14 @@ riscv_slow_unaligned_access (machine_mode, unsigned
> int)
> return riscv_slow_unaligned_access_p;
> }
>
> +/* Implement TARGET_OVERLAP_OP_BY_PIECES_P. */
> +
> +static bool
> +riscv_overlap_op_by_pieces (void)
> +{
> + return !riscv_slow_unaligned_access_p;
> +}
> +
> /* Implement TARGET_CAN_CHANGE_MODE_CLASS. */
>
> static bool
> @@ -5525,6 +5533,9 @@ riscv_asan_shadow_offset (void)
> #undef TARGET_SLOW_UNALIGNED_ACCESS
> #define TARGET_SLOW_UNALIGNED_ACCESS riscv_slow_unaligned_access
>
> +#undef TARGET_OVERLAP_OP_BY_PIECES_P
> +#define TARGET_OVERLAP_OP_BY_PIECES_P riscv_overlap_op_by_pieces
> +
> #undef TARGET_SECONDARY_MEMORY_NEEDED
> #define TARGET_SECONDARY_MEMORY_NEEDED riscv_secondary_memory_needed
>
> --
> 2.31.1
>
