Displaying 4 results from an estimated 4 matches for "add32_fix".
Did you mean:
add32_fixed
2017 Feb 15
2
[PATCH] Refactor silk_LPC_analysis_filter() & Optimize celt_fir_permit_overflow() for ARM NEON
...rated.
Maybe this is the reason why silk_LPC_analysis_filter() switched the FIR
from celt_fir() to celt_fir_permit_overflow() half a year ago.
Because of silk_LPC_analysis_filter(), celt_fir_permit_overflow() must
behave the same for both floating-point and fixed-point, and this is why we
defined ADD32_FIXED(), ..., PSHR32_FIXED() etc.
It's still a messy.
For the NEON optimization part, the previous celt_fir() optimization calls
xcorr_kernel(). We tested and found that calling the xcorr_kernel()
optimization didn't help too much here. The optimization in the patch is
about 1% faster than si...
2017 Feb 18
0
[PATCH] Refactor silk_LPC_analysis_filter() & Optimize celt_fir_permit_overflow() for ARM NEON
...ate the rest of the time. That way we can test for
overflows in the CELT code, without preventing optimization of the SILK
code.
> Because of silk_LPC_analysis_filter(), celt_fir_permit_overflow() must
> behave the same for both floating-point and fixed-point, and this is why
> we defined ADD32_FIXED(), ..., PSHR32_FIXED() etc.
I don't think you will need these anymore, but if you ever need
fixed-point macros that remain integer for float compilation, then you
should use the silk_*() fixed-point macros (and the code should be in
silk/).
> For the NEON optimization part, the previous...
2017 Mar 01
2
[PATCH] Refactor silk_LPC_analysis_filter() & Optimize celt_fir_permit_overflow() for ARM NEON
...t way we can test for
> overflows in the CELT code, without preventing optimization of the SILK
> code.
>
> > Because of silk_LPC_analysis_filter(), celt_fir_permit_overflow() must
> > behave the same for both floating-point and fixed-point, and this is why
> > we defined ADD32_FIXED(), ..., PSHR32_FIXED() etc.
>
> I don't think you will need these anymore, but if you ever need
> fixed-point macros that remain integer for float compilation, then you
> should use the silk_*() fixed-point macros (and the code should be in
> silk/).
>
> > For the NEON...
2017 Feb 15
4
[PATCH] Refactor silk_LPC_analysis_filter() & Optimize celt_fir_permit_overflow() for ARM NEON
Hi,
Attached are two patches. Patch 1 refactors silk_LPC_analysis_filter(). And
Patch 2 optimizes the new function celt_fir_permit_overflow() for ARM NEON.
Please recommend a better function name.
We did the same internal code review and testing already.
Thanks,
Linfeng
-------------- next part --------------
An HTML attachment was scrubbed...
URL: