On Sat, 2025-01-25 at 23:31 -0800, Andi Kleen wrote:
> From: Andi Kleen <[email protected]>
>
> This is the hot function in input.cc
>
> The vectorizer can vectorize it now, but in a generic cpu O2 x86
> build it isn't.
> Add a automatic target clone to handle it for x86 and build
> that function with O3.
>
> The ifdef here is ugly, perhaps gcc should have a more convenient
> "clone for vectorization if possible" attribute to handle this
> portably.
This patch is very cool (no pun intended); how much does it help?
The patch is OK by me, but given that we're in stage 4, does a release
manager approve? [CCed]
Thanks
Dave
>
> gcc/ChangeLog:
>
> * input.cc: (VECTORIZE): Add definition for x86.
> (find_end_of_line): Mark for vectorizer.
> ---
> gcc/input.cc | 7 +++++++
> 1 file changed, 7 insertions(+)
>
> diff --git a/gcc/input.cc b/gcc/input.cc
> index d5d7dbb043e..f1a15de66f1 100644
> --- a/gcc/input.cc
> +++ b/gcc/input.cc
> @@ -740,11 +740,18 @@ file_cache_slot::maybe_read_data ()
> return read_data ();
> }
>
> +#if defined(__x86_64__) && __GNUC__ >= 15
> +#define VECTORIZE
> __attribute__((target_clones("default,avx2,avx10.2,avx512f"),
> optimize("O3")))
> +#else
> +#define VECTORIZE
> +#endif
> +
> /* Helper function for file_cache_slot::get_next_line (), to find
> the end of
> the next line. Returns with the memchr convention, i.e. nullptr
> if a line
> terminator was not found. We need to determine line endings in
> the same
> manner that libcpp does: any of \n, \r\n, or \r is a line
> ending. */
>
> +VECTORIZE
> static const char *
> find_end_of_line (const char *s, size_t len)
> {
