Replace mulps+subps with fnmaddps, resulting in two less instructions inside the
inner loops.
About 1% faster FMA3 performance.
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
This reverts the changes 6467209836
and 68c3ed936a did to the SSE2 version,
which generated a hit of about 5 cycles.
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
Sandy Bridge Win64:
180 cycles on ff_synth_filter_inner_sse2
150 cycles on ff_synth_filter_inner_avx
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
Timings for Arrandale:
C SSE
win32: 2108 334
win64: 1152 322
Factorizing the inner loop with a call/jmp is a >15 cycles cost, even with
the jmp destination being aligned.
Unrolling for ARCH_X86_64 is a 20 cycles gain.
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
The vector dequantization has a test in a loop preventing effective SIMD
implementation. By moving it out of the loop, this loop can be DSPized.
Therefore, modify the current DSP implementation. In particular, the
DSP implementation no longer has to handle null loop sizes.
The decode_hf implementations have following timings:
For x86 Arrandale:
C SSE SSE2 SSE4
win32: 260 162 119 104
win64: 242 N/A 89 72
The arm NEON optimizations follow in a later patch as external asm. The
now unused check for the y modifier in arm inline asm is removed from
configure.
Timings for Arrandale:
C SSE
win32: 2108 334
win64: 1152 322
Factorizing the inner loop with a call/jmp is a >15 cycles cost, even with
the jmp destination being aligned.
Unrolling for ARCH_X86_64 is a 20 cycles gain.
Signed-off-by: Janne Grunau <janne-libav@jannau.net>
For the callable function (as opposed to the inline one):
C SSE SSE2 SSE4
Win32: 47 42 29 26
Win64: 30 33 25 23
The SSE version is neither compiled nor set for ARCH_X86_64, as the
inlinable function takes over.
Signed-off-by: Janne Grunau <janne-libav@jannau.net>
James Almer
Christophe Gisquet