On 8 October 2016 at 11:58, Marek Olšák <mar...@gmail.com> wrote:
> From: Marek Olšák <marek.ol...@amd.com>
>
> time GALLIUM_NOOP=1 ./run shaders/private/alien_isolation/ >/dev/null
>
> Before (2 takes):
>
> real    0m8.734s    0m8.773s
> user    0m34.232s   0m34.348s
> sys     0m0.084s    0m0.056s
>
> After (2 takes):
>
> real    0m8.448s    0m8.463s
> user    0m33.104s   0m33.160s
> sys     0m0.088s    0m0.076s
>
> Average change in "real" time spent: -3.4%
>
> calloc should only do 2 things compared to malloc:
> - check for overflow of "n * size"
> - call memset
>
> I'm not sure if that explains the difference.
The difference is quite interesting indeed.

One small suggestion below.

> ---
>  src/util/ralloc.c | 17 ++++++++++++++++-
>  1 file changed, 16 insertions(+), 1 deletion(-)
>
> diff --git a/src/util/ralloc.c b/src/util/ralloc.c
> index 9526011..23c89e5 100644
> --- a/src/util/ralloc.c
> +++ b/src/util/ralloc.c
> @@ -91,20 +91,23 @@ get_header(const void *ptr)
>  static void
>  add_child(ralloc_header *parent, ralloc_header *info)
>  {
>     if (parent != NULL) {
>        info->parent = parent;
>        info->next = parent->child;
>        parent->child = info;
>
>        if (info->next != NULL)
>          info->next->prev = info;
> +   } else {
> +      info->parent = NULL;
> +      info->next = NULL;
add_child is used on two occasions - rzalloc_size after memset* and
ralloc_steal after unlink_block. The latter of which already clears
the parent and siblings pointers.
Thus we can move the above two lines...

>     }
>  }
>
>  void *
>  ralloc_context(const void *ctx)
>  {
>     return ralloc_size(ctx, 0);
>  }
>
>  void *
> @@ -115,27 +118,39 @@ ralloc_size(const void *ctx, size_t size)
>      *
>      * TODO: Make ralloc_size not zero fill memory, and cleanup any code that
>      * should instead be using rzalloc.
>      */
>     return rzalloc_size(ctx, size);
>  }
>
>  void *
>  rzalloc_size(const void *ctx, size_t size)
>  {
> -   void *block = calloc(1, size + sizeof(ralloc_header));
> +   void *block = malloc(size + sizeof(ralloc_header));
>     ralloc_header *info;
>     ralloc_header *parent;
>
>     if (unlikely(block == NULL))
>        return NULL;
> +
>     info = (ralloc_header *) block;
> +   /* measurements have shown that calloc is slower, so clear things
> +    * manually
> +    */
> +   info->child = NULL;
> +   info->prev = NULL;
> +   info->destructor = NULL;
> +   /* add_child() clears other members */
> +
... here and drop the comment.

Emil
_______________________________________________
mesa-dev mailing list
mesa-dev@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/mesa-dev

Reply via email to