Updates HackRF native byte buffers with automatic DC removal.
Creates new half-band channel source to replace the cic-based channel source in the heterodyne channelizer. Resolves issue in RTL native buffer processing. Creates a CACHED thread pool and reduces the number of threads for the SCHEDULED thread pool to 2. Changes each of the channel source implementations to use a dedicated thread (Dispatcher class) instead of the scheduled thread pool, to reduce the amount of buffered/retained samples objects in memory. Lots of other small changes and tweaks.
Removes last of Reusable buffer code. Updates DFTProcessor to use a single thread scheduled executor. Updates Polyphase channelizer to use threads instead of an executor. Removes a number of unused classes.
Commenting out window calibration. Scalar is faster in both implementations.
Adds vector and scalar implementations for windows. Repackages window and window type classes.
WIP adds vector implementations for Airspy non-interleaved buffer iterator and calibration plugins for both interleaved and non-interleaved buffer iterators.
WIP adds vector implementations for Airspy interleaved buffer iterator.
Work on developing scalar and vector implementations of airspy sample conversion and airspy native buffer processing.
Introduces new INativeBuffer framework where tuner raw samples are retained in their native (compressed) format until when they're needed and they are converted on-demand into smaller complex sample buffers to aid garbage collection.
Removes all usage of ReusableComplexBuffers and ReusableChannelREsultsBuffers. Updates polyphase channelizer to be more efficient in output channel processing.
Updates ViterbiDecoder to change Map usage to array for memory efficiency.
Updates channel processors to used scalar implementation for gain and mixer, until the polyphase channel results can be fixed to be a multiple of the SIMD lane width.
Resolves final changes for the conversion from interleaved sample arrays to complexsamples buffers for distributing baseband samples to channels and processing chains.
Updates tuner channel sources and all decoders to receive new complex samples buffers, removing the previous reusable complex buffers as the default baseband samples buffer object.
Still to resolve is the ComplexMixer implementations. Needs validation and a calibration implementation with an update to the complex mixer factory.
Updates the DMR decoder to use optimal (scalar vs vector) implementations of filter and AGC controls.
Updates the AM demodulator for separated I&Q float sample processing.
Code review and testing changes.
updates build script for runtime configuration.
Integrates calibration manager with main sdrtrunk application. Updates NBFMDecoder to use new optimized FIR and Decimation filter options.
Updates real half-band decimation filters to select the optimal (scalar vs vector) implementation.
Adds calibration manager plugins.
Adds calibration manager and plugins to determine the optimal (scalar vs vector) implementation type to use for various classes of dsp components.
Adds vector squelching FM demodulator and cleans up the IIR filter and power squelch to use all floats.
Adds vector implementation of FM demodulator. This introduces a new interface that accepts i/q samples as two separate float arrays, versus an interleaved array, which enables more efficient processing. This new complex sample interface will be used across the codebase eventually.
Adds ComplexOscillator and a SIMD version VectorComplexOscillator. Deprecates the LowPhaseNoiseOscillator because the ComplexOscillator is about 35% faster. The vectorized version is about 43% faster when SIMD lane width is 8x.
Adds new vector complex filters and new real oscillators. Note: the RealOscillator using straight Java math sin() function is 3x slower than the existing legacy implementation. Will replace this with a complex oscillator that only uses the real part.
Updates ComplexFIRFilter to be 50% more efficient.
Adds 23 tap filter implementations. Will not add 63-tap implementations because they are slower than the default vector implementation.
Adds 15-tap customized vector half band filters.
Adds initial custom complex vector half-band decimation filters for 11-tap and 15-tap decimation filters..
Adds vector complex half band filter implementations. Note: performance of the generic 64-bit 2-lane filter is horrible and is not included.
Optimizes complex half-band filter to be 27% more efficient.
Implements vectorized real half-band filter implementations.
Implements a new FIR filter class that processes sample buffers instead of single sample at a time.
Refactored all of the calibratons to be time-duration based. Testing on windows i7 gen 3 CPU showed that it took 1000x longer for one of the calibrations to run, versus my AMD 5800x.
Changed gradle jvm args so that the windows plaf export is always applied.
Updates gradle build script to ensure incubator module is included and to cleanup javafx library management for building runtime images.
Testing tweaks and changes.
Adds logging limiter to dispatcher for buffer overflows
Adds User Preferences editor for performing Vector/SIMD calibrations and new startup dialog prompting the user to perform calibrations.
Updates calibration manager and all calibration implementations to add warm-up and test phases and to reduce the overall time it takes to calibrate a system.
Co-authored-by: Dennis Sheirer <dsheirer@github.com>
-Separates USB timeout event processing to a dedicated thread
-Updates USB transfer buffer processor to better detect errors and auto-restart on error (max 3 times)
-Updates Tuner to add an error state and SourceManager to not select tuners with an error state
-Updates ChannelProcessingManager to auto-shutdown channels sourced from tuners set with error state
-Improves logging of USB related errors.
only update the center frequency when needed and to place the set of
decoding channels adjacent to the right side of the tuner's center
frequency when the complete set of channels fit into the usable half
bandwidth of the tuner.
channel manager so that channel source requests can have a start
timestamp specified and the channel can be preloaded with samples from
the delay buffer. If no timestamp is specified, current time is assumed.
This feature requires corresponding updates to any decoder that wishes
to implement the timestamped sample preloading functionality.
and auto-correction for R820T tuners.
-Updated TunerModel and TunerViewPanel to add 2 new columns to
display the current tuner's PPM setting and (when available) the
measured frequency error averaged over 5 second intervals provided by
certain decoders (e.g. P25 C4FM and LSM). Frequency error value from
P25 decoders is provided from the Costas Loop PLL once 2 or more P25
message sync events have been observed in a short period.
-Updated R820T tuner to auto-correct PPM when measured frequency error
exceeds the +/- 0.4PPM threshold for a period of 30 seconds or more.
Feature can be enabled/disabled by user in the tuner editor panel.
Resolved several issues with P25 C4FM/LSM decoders that was impacting
performance related to channel misalignment from tuner PPM offsets.
produces a significant reduction in memory usage, especially for tuners
like the airspy and hackrf that produce 10/20 MSPS sample rates. This
is observed to be around 66% reduction in peak memory usage and provides
a more stable memory utilization across time reducing stress on the
garbage collector.
Use of these reusable memory buffers will be pushed further down into
the processing chain modules to ensure we keep new object creation
to the lowest levels possible.
TestTuner and TestTunerController implementations. This implementation
only has support for channels that are completely centered within a
channelizer output. Two output slice stitching to form a composite
channel will be implemented next.
Initial profiling indicates that the FFT function within the polyphase
channelizer is now the dominant processing workload - 28% cpu loading
when channelizing a 10 MHz sample rate input into 800 channels running
at 25.0 kHz each. This is ideal for offloading to an OpenCL kernel and
running on a GPU.
messages and events can be accurately timestamped, and more importantly,
allocated traffic channels can request to be pre-loaded with buffered
samples to ensure that traffic channels don't miss any samples that
are currently missed due processing latency inherent in current buffer
sizing. This should reduce the clipping of starting messages or voice
on the traffic channels.
Restructures processing path for tuner frequency and sample rate change
events. The tuner now embeds these events in the sequence of buffers
that are generated immediately after the event occurs since those are
the buffers that will be impacted by the change. Previously, the change
event would be broadcast throughout the system and would impact any
buffered/cached buffers. This also reduces the number of source event
change listeners that have to be managed. Note: this change is not yet
implemented in all tuners ... only in the TestTuner implementation.
Updates the polyphase channelizer to now buffer channel results and then
dispatch the buffer to the channel output processors to improve efficiency
of using float arrays versus single value complex float processing.
center frequency each time we allocate a new DDC/channel. Adds
support for broadcasting channel count change source events so that the
tuner can accurately convey sourced channel counts via tuner events.
Completes changeover of polyphase channel manager to support arbitrary
bandwidth channels. The new approach provides greater compatibility
across any tuner sample rates. Likewise, all decoders will have to be
updated to adapt to any channel sample rate, although channel bandwidths
will be at least 12.5 kHz and likely no more than 25.0 kHz, with a 2x
oversampling that produces channel sample rates in range 25.0 - 50.0
kHz.
