Re: [PATCH] libgcc: Mostly vectorize CIE encoding extraction for FDEs

[Florian Weimer <fweimer@redhat.com>]

* Richard Biener:

> On Mon, Oct 17, 2022 at 3:01 PM Florian Weimer via Gcc-patches
> <gcc-patches@gcc.gnu.org> wrote:
>>
>> "zR" and "zPLR" are the most common augmentations.  Use a simple
>> SIMD-with-in-a-register technique to check for both augmentations,
>> and that the following variable-length integers have length 1, to
>> get more quickly at the encoding field.
>>
>> libgcc/
>>
>>         * unwind-dw2-fde.c (get_cie_encoding_slow): Rename from
>>         get_cie_encoding.  Mark as noinline.
>>         (get_cie_encoding): Add fast path for "zR" and "zPLR"
>>         augmentations.  Call get_cie_encoding_slow as a fall-back.
>>
>> ---
>>  libgcc/unwind-dw2-fde.c | 61 +++++++++++++++++++++++++++++++++++++++++++++++--
>>  1 file changed, 59 insertions(+), 2 deletions(-)
>>
>> diff --git a/libgcc/unwind-dw2-fde.c b/libgcc/unwind-dw2-fde.c
>> index 3c0cc654ec0..4e3a54c5a1a 100644
>> --- a/libgcc/unwind-dw2-fde.c
>> +++ b/libgcc/unwind-dw2-fde.c
>> @@ -333,8 +333,10 @@ base_from_object (unsigned char encoding, const struct object *ob)
>>  /* Return the FDE pointer encoding from the CIE.  */
>>  /* ??? This is a subset of extract_cie_info from unwind-dw2.c.  */
>>
>> -static int
>> -get_cie_encoding (const struct dwarf_cie *cie)
>> +/* Disable inlining because the function is only used as a slow path in
>> +   get_cie_encoding below.  */
>> +static int __attribute__ ((noinline))
>> +get_cie_encoding_slow (const struct dwarf_cie *cie)
>>  {
>>    const unsigned char *aug, *p;
>>    _Unwind_Ptr dummy;
>> @@ -389,6 +391,61 @@ get_cie_encoding (const struct dwarf_cie *cie)
>>      }
>>  }
>>
>> +static inline int
>> +get_cie_encoding (const struct dwarf_cie *cie)
>> +{
>> +  /* Fast path for some augmentations and single-byte variable-length
>> +     integers.  Do this only for targets that align struct dwarf_cie to 8
>> +     bytes, which ensures that at least 8 bytes are available starting at
>> +     cie->version.  */
>> +#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ \
>> +  || __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
>> +  if (__alignof (*cie) == 8 && sizeof (unsigned long long) == 8)
>> +    {
>> +      unsigned long long value = *(const unsigned long long *) &cie->version;
>
> TBAA?  Maybe use
>
>            unsigned long long value;
>            memcpy (&value, &cie->version, 8);
>
> instead?

It's following the existing libgcc style, see
read_encoded_value_with_base in unwind-pe.h.

We know here that the pointer is aligned, but perhaps GCC still can use
that information if using memcpy.

I can certainly change it to memcpy.

Thanks,
Florian