Remove some assembly that the compiler can easily handle optimally on its own.
GCC produces almost identical assembly.
Signed-off-by: NJames Cowgill <james410@cowgill.org.uk>
Signed-off-by: NMichael Niedermayer <michaelni@gmx.at>

Signed-off-by: NReimar Döffinger <Reimar.Doeffinger@gmx.de>

Iterative implementation of 32 bit fixed point split-radix FFT.
Max FFT that can be calculated currently is 2^12.
Signed-off-by: NNedeljko Babic <nbabic@mips.com>
Signed-off-by: NMichael Niedermayer <michaelni@gmx.at>

Floating point FFT (nips optimized) breaks when hard coded tables are
not enabled because MIPS optimization of floating point FFT uses only
ff_init_ff_cos_tabs(16) which is not enabled by default in that case.

This patch is fixing it.
Signed-off-by: NNedeljko Babic <nbabic@mips.com>
Signed-off-by: NMichael Niedermayer <michaelni@gmx.at>

List of clobbered registers fixed and added where it is lacking.
Signed-off-by: NNedeljko Babic <nbabic@mips.com>
Signed-off-by: NMichael Niedermayer <michaelni@gmx.at>

Add dependencies on HAVE_INLINE_ASM for files and parts of code
 where it is necessary.
Signed-off-by: NNedeljko Babic <nbabic@mips.com>
Reviewed-by: NVitor Sessak <vitor1001@gmail.com>
Signed-off-by: NMichael Niedermayer <michaelni@gmx.at>

FFT in MIPS implementation is working iteratively instead
 of "recursively" calling functions for smaller FFT sizes.
Some of DSP and format convert utils functions are also optimized.
Signed-off-by: NNedeljko Babic <nbabic@mips.com>
Reviewed-by: NVitor Sessak <vitor1001@gmail.com>
Signed-off-by: NMichael Niedermayer <michaelni@gmx.at>