The vec_splat() intrinsic requires a constant argument for the
element number, and the code relies on the compiler unrolling
the loop to provide this.  Manually unrolling the loop avoids
this reliance and works with all compilers.

Signed-off-by: Mans Rullgard <mans@mansr.com>

Signed-off-by: Mans Rullgard <mans@mansr.com>

Signed-off-by: Martin Storsjö <martin@martin.st>

Signed-off-by: Martin Storsjö <martin@martin.st>

Signed-off-by: Martin Storsjö <martin@martin.st>

Signed-off-by: Mans Rullgard <mans@mansr.com>

This moves all VP3-specific function pointers from dsputil to a
new vp3dsp context.  There is no reason to ever use the VP3 IDCT
where an MPEG2 IDCT is expected or vice versa.

Signed-off-by: Mans Rullgard <mans@mansr.com>

Move vector_fmul() from DSPContext to AVFloatDSPContext.

This will allow for easier implementation of Altivec functions in libraries
other than libavcodec.

Signed-off-by: Mans Rullgard <mans@mansr.com>

The shift parameter was removed from this interface in 7e1ce6a.
This updates the Altivec implementation to match.

Signed-off-by: Mans Rullgard <mans@mansr.com>

To load unaligned vector data in the usual way, explicit vec_ld()
should be used rather than dereferencing a pointer to a vector type.
When the VSX extension is enabled, gcc may compile vector pointer
dereferences using the VSX lxvw4x instruction instead of the lvx
instruction typically used with Altivec/VMX.  As the behaviour of
these instructions with unaligned addresses differs, it is important
that only lvx is used here.

Signed-off-by: Mans Rullgard <mans@mansr.com>

This feature is complex, of questionable utility, and slows down
normal decoding.

Signed-off-by: Mans Rullgard <mans@mansr.com>

This also allows dropping some PPC-specific ugliness from dsputil.[ch].

On 64bit platforms with 32bit int, this means we won't have to sign-
extend the integer anymore.

Signed-off-by: Martin Storsjö <martin@martin.st>

Signed-off-by: Martin Storsjö <martin@martin.st>

Signed-off-by: Martin Storsjö <martin@martin.st>

Signed-off-by: Mans Rullgard <mans@mansr.com>

Neon parts by Mans Rullgard <mans@mansr.com>.

Signed-off-by: Diego Biurrun <diego@biurrun.de>
Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>

On 32-bit ppc, the GOT pointer must be loaded manually.
This adds a "get_got" assembler macro to compute the
GOT address.  The "movrel" macro is updated to take an
additional parameter containing the GOT address since
no register is reserved for this purpose on ppc32.
These changes have no effect on ppc64 builds.

Signed-off-by: Mans Rullgard <mans@mansr.com>

This is already set by dsputil_init_ppc() and is best done in only
one place.

Signed-off-by: Mans Rullgard <mans@mansr.com>

Signed-off-by: Mans Rullgard <mans@mansr.com>

Signed-off-by: Mans Rullgard <mans@mansr.com>

Signed-off-by: Mans Rullgard <mans@mansr.com>

Signed-off-by: Mans Rullgard <mans@mansr.com>

The Altivec IMDCT works with size 32 and higher only.

Signed-off-by: Mans Rullgard <mans@mansr.com>

Note: this is 4:4:4 from the 2007 spec revision, not the previous (now deprecated) 4:4:4 mode in H.264.

Signed-off-by: Mans Rullgard <mans@mansr.com>

This separation allows these functions to be used in a cleaner
fashion from other codecs (e.g. qdm2) and simplifies creating
optimised versions of them.

Signed-off-by: Mans Rullgard <mans@mansr.com>

This patch lets e.g. dsputil_init chose dsp functions with respect to
the bit depth to decode. The naming scheme of bit depth dependent
functions is <base name>_<bit depth>[_<prefix>] (i.e. the old
clear_blocks_c is now named clear_blocks_8_c).

Note: Some of the functions for high bit depth is not dependent on the
bit depth, but only on the pixel size. This leaves some room for
optimizing binary size.

Preparatory patch for high bit depth h264 decoding support.

Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>

This reverts commit f8bed30d8b. The reason
for this is that the overlap filter, which runs after IDCT, should run
on unclamped values, and thus IDCT and put_pixels() cannot be merged if
we want to attempt to be bitexact.

According to ISO 9899:1999 S 6.5.7/4:

The result of E1 << E2 is E1 left-shifted E2 bit positions; vacated bits
are filled with zeros. If E1 has an unsigned type, the value of the
result is E1× 2^E2, reduced modulo one more than the maximum value
representable in the result type. If E1 has a signed type and
nonnegative value, and E1× 2^E2 is representable in the result type, then
that is the resulting value; otherwise, the behavior is undefined.

Signed-off-by: Mans Rullgard <mans@mansr.com>

It only has Altivec functions and is not compiled if Altivec is disabled.