On 30/03/2016 09:07, Pavel Demin wrote:
>    - NEON coprocessor supports only single-precision floating-point
> values and replacing double with float in some calculation intensive
> parts could improve the performance.
Hi Pavel & all,

if this is so then switching to using the single precision FFTW3 library 
for DFT calculations is likely to be a significant performance gain on 
ARM with this VFP.

The JT9 and JT65 decoders already use only single precision DFT and 
switching to the same for WSPR would, I expect , be straightforward.

73
Bill
G4WJS.

------------------------------------------------------------------------------
Transform Data into Opportunity.
Accelerate data analysis in your applications with
Intel Data Analytics Acceleration Library.
Click to learn more.
http://pubads.g.doubleclick.net/gampad/clk?id=278785471&iu=/4140
_______________________________________________
wsjt-devel mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/wsjt-devel

Reply via email to