* Switch all conversion routines to use starch.
main user-visible changes:
* ensure you check out submodules ('git clone --recurse-submodules")
* --version shows the CPU features and DSP implementations in use
* --wisdom allows overriding of the built-in architecture wisdom
* --dcfilter no longer supported
* "starch-benchmark" binary will benchmark all options on the
current machine and can produce a wisdom file to feed to
the --wisdom option
If you have a usecase for --dcfilter, please get in touch and
let me know - it's an edge case and for now there's no starch/DSP
support for it, but support can be written if needed.
In almost all cases the new conversion routines are slightly or
substantially faster than the old conversion routines. The only case
that is slower is SC16/SC16Q11 on a Pi 0, which is around 10% slower
due to changing from heavily approximated lookup tables to higher
quality results (but SC16 is probably already out of reach of a Pi 0)
* No need to build with SC16Q11_TABLE_BITS any more
* Add oneoff/uc8_capture_stats
(reads a UC8 capture; measures min/max/mean I and Q)
* Switch UC8 conversion to 127.4 center, 128 range.
Looking at actual UC8 captures from a RTL2832, the mean I and Q
are actually at 127.4, so use that as the zero point.
This means that the resulting I/Q maximum values could be as large as
127.6. Switch to 128 for simplicity.
* Switch to the new UC8 zero offset in benchmarks, fix some bugs
* Fix some bugs in SC16/SC16Q11 validation, tighten the max error requirements
* Ditch UC8 approximation path, add a NEON VRQSQRTE path.
* Tweak the SC16 exact path, add a new impl that uses a mix of
u32 & floats.
* SC16Q11 impl tweaks:
* add a u32->float exact path
* ditch the approximation path
* add a NEON VRSQRTE path
* add a 12-bit table path (using the full signed I/Q value, not absolute value)
* Ditch SC16 approximation path, add NEON vrsqrte path
* Add oneoff/dsp_error_measurement
This runs sample input through the DSP functions that are
allowed to be inexact and dumps the results as a TSV suitable for
feeding to gnuplot to look at the actual errors.
* Update make clean, make wisdom targets
* Update wisdom based on benchmarking
* Preserve the raw wisdom benchmark data
* Update to latest starch
* Update .gitignore for new wisdom files
* Update starch generated code
* Build starch-benchmark as part of the 'all' target
* Use wisdom from /etc/dump1090-fa/wisdom.local if present
* Package starch-benchmark and a helper script to generate local wisdom data
* Remove submodules in preparation for importing them directly
* Import cpu_features v0.6.0 from https://github.com/google/cpu_features/releases/tag/v0.6.0
* Import starch at commit a725c8491dc33a321565d451b385131e589d8490
from https://github.com/flightaware/starch
reduce dependency requirements a little.
(Ideally we'd have some sort of module system here, and split
the dependencies out nicely into separate packages, but that's a
problem for other day; for now I can live with custom packages
having the same name as the full build, since we'll never
distribute them ourselves)
When accessing Dump 1090 JSON from another web server, I found that the "Access-Control-Allow-Origin" parameter was set twice ("*, *") which Chrome objected to. By changing "add-response-header" to "set-response-header" we ensure that the correct header is sent, but never duplicated.
In recent versions of Firefox and (especially) Chrome, ".dev" domains are
force-redirected to a secure connection (HTTPS) instead of HTTP. Not
supporting an HTTPS connection makes for a bad user experience, so we want
to make enabling SSL support easy. Since we don't issue certificates, this
section is commented out by default, and it will require modification.
This is done primarily for PiAware, though it is applicable to just the
Dump1090 project.
--fix --fix was a poor choice for this, as some existing configs
happened to specify --fix twice but only expected 1-bit correction.
So move 2-bit correction to a separate option.
"--fix" or "--fix --fix" now gives 1-bit correction.
"--fix-2bit" or "--fix --fix-2bit" or "--fix-2bit --fix" gives 2-bit correction.
Version bump to 3.8.2~dev
Standard lighttpd will refuse to start if modules are loaded more than
once. Turn the module addition into a comment, explain why it's disabled
by default and in which cases you should enable it.
On some instances of lighttpd, like the one that comes with PiHole, the
alias module is not loaded by default. This makes the configuration of
PiAware's lighttpd not work (see e.g.
https://discourse.pi-hole.net/t/pi-hole-and-piaware-lighttpd/9611).
This way we ensure that the alias module is loaded even on non-default
lighttpd configurations.
eric1tran
Oliver Jowett
Eric Tran
Ian Renton
John Berninger
Claudio Moretti
Carlos Pizarro
Oliver Jowett
Matthias Wirth