Implement 1-pass inverse transform and reconstruction for inter blocks.

Extract processing of intra 16x16 blocks from intra macroblock
processing.
Also implement a function performing inverse transform and block
reconstruction for DC-only blocks in 1 pass instead of 2.

When decoding coefficients, detect whether the block is DC-only, and take
advantage of this knowledge to perform DC-only inverse transform.

This is achieved by:
- first, changing the 108x4 element modulo_three_table into a 108 element
  table (kind of base4), and accessing each value using mask and shifts.
- then, checking low bits for 0 (as they represent the presence of higher
  frequency coefficients)

Also provide x86 SIMD code for the DC-only inverse transform.

Signed-off-by: Kostya Shishkov <kostya.shishkov@gmail.com>

This is required to handle clobbering of XMM registers on Win64
correctly. Fixes FFT and all tests depending on FFT on Win64.

Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>
Signed-off-by: Janne Grunau <janne-libav@jannau.net>

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

Originally, prior to 8742a4ff8, the caller code was compiled
within this condition:

ARCH_X86 && HAVE_7REGS && HAVE_EBX_AVAILABLE && !defined(BROKEN_RELOCATIONS)

Since HAVE_7REGS is defined as
(ARCH_X86_64 || (HAVE_EBX_AVAILABLE && HAVE_EBP_AVAILABLE))
the subcondition HAVE_7REGS && HAVE_EBX_AVAILABLE is equal
to HAVE_7REGS (for 32 bit at least). The correct simplification
of the original condition thus is HAVE_7REGS, not
HAVE_EBX_AVAILABLE.

This fixes compilation in some cases where HAVE_EBP_AVAILABLE = 0
and HAVE_EBX_AVAILABLE = 1.

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

On 32-bit OS X with gcc 4.0/4.2 and shared libraries enabled, the ebx register
is not available, but required to assemble the functions.

This reverts commit 8742a4f to a simplified version of the original constraints.

The change in 599b4c6ef didn't turn out to work properly on
i386 on OS X, where it broke building with PIC enabled.

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

This replaces the explicit offset(reg) memory references with
"m" operands for the same locations.  As a result, one fewer
register operand is needed for these inline asm statements.

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

avoids passing around the extra argument among all the macros it uses

This allows emulated_edge_mc_sse() and gmc_sse() to be used under
AV_CPU_FLAG_SSE.

Filenames are brittle across renames and add no useful information.

The calling convention only allows 4 non-stack parameter, with each
float or int register being skipped if not used.

fixes Bug 64

Add whitespace.

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

Right now it's not actually initialized on 32-bit, leading to crashes
on win32.

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>

This avoids some unused variable warnings with YASM disabled.

Signed-off-by: Janne Grunau <janne-libav@jannau.net>

~3.0-3.5x as fast as original C version, 1.6x as fast overall.

As a signed integer, 1<<31 overflows, so force it to unsigned.

Signed-off-by: Alex Converse <alex.converse@gmail.com>

This allows sharing them between multiple .asm files.

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

This allows using it in swscale also.

This allows using it in libswscale/ also.

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

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

This fixes build with clang.

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

Inspection of compiled code shows gcc handles these fine on its own.
Benchmarking also shows no measurable speed difference.

Removing the remaining cases in get_cabac_bypass_sign_x86() does
cause more substantial changes to the compiled code with uncertain
impact.

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

The upcoming gcc 4.7 has more advanced constant propagation
resulting some inline asm operands becoming constants and thus
emitted as literals, sometimes in contexts where this results
in invalid instructions.

This patch changes the constraints of the relevant operands
to "rm" thus forcing a valid type.  While obviously suboptimal,
this is what older gcc versions already did, and there is no
change to the code generated with these.

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

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