def makesendbufs(wmap, destmap, nmax=10000):
'''
Given a WaveformMap wmap and a destmap, as produced by keyroute, that
maps ranks in an MPI communicator to sets of keys in wmap that should
be sent to that rank, prepare and return a map from destination ranks
to a list of BytesIO buffers that each hold a serialized representation
of subset (of at most nmax Waveforms) of wmap to be sent to that rank.
'''
# Assign the buffers to target ranks
buffers = defaultdict(list)
for rank, rkeys in destmap.items():
remaining = list(rkeys.intersection(wmap))
while remaining:
# Build a submap to serialize
rmap = WaveformMap((k, wmap[k]) for k in remaining[:nmax])
# Serialize to a BytesIO stream
bstr = io.BytesIO()
rmap.store(bstr)
# Append the buffer to the map
buffers[rank].append(bstr)
# Discard the serialized portion
remaining = remaining[nmax:]
return buffers
def fhfft(infile, outfile, groupmap, **kwargs):
'''
For a real WaveformSet file infile, perform Hadamard decoding and then
a DFT of the temporal samples. The Hadamard decoding follows the
grouping configuration stored in groupmap, a map
(element index) -> (local Hadamard index, group number)
that defines Hadamard groups and must agree with the local group
configuration represented in the input. The resulting transformed
records will be stored in the output outfile. The nature of outfile
depends on the optional argument trmap (see below).
If trmap is not provided, all records will be written as a binary blob;
the outfile should be a single string providing the location of the
output. The output will have shape Ns x Nt x Nr, where Ns is the number
of output samples per waveform (as governed by the spectral or temporal
windows applied), Nt is the number of input transmit channels, and Nr
is the number of input receive channels.
If trmap is provided, outfile should be a one-to-one map from the keys
of trmap to output files. A WaveformMap object will be created for each
key in trmap and stored at the location indicated by the corresponding
value in outfile.
Output file(s) will be created or truncated.
Any TGC parameters in the input, accessible as wset.context['tgc'],
will be used to adjust the amplitudes of the waveforms prior to
applying Hadamard and Fourier transforms.
The kwargs contain optional values or default overrides:
* freqs (default: None): When not None, a sequence (start, end)
to be passed as slice(start, end) to bandpass filter the input after
Hadamard decoding.
* rolloff (default: None): When not None, an integer that defines the
half-width of a Hann window that rolls off the bandpass filter
specified in freqs. Ignored if freqs is not provided.
* nsamp (default: None): The length of the time window over which
waveforms are considered (and DFTs are performed), starting from
global time 0 (i.e., without consideration for input F2C). If None,
the value of nsamp in the input is used.
** NOTE: Because the time window always starts at global time 0,
a waveform with a data window (start, length) will be cropped when
(f2c + start + length) > nsamp, even if nsamp is the value encoded in
the file.
* tgcsamps (default: 16 [for integer datatypes] or 0 [else]): The
number of temporal samples to which a single TGC parameter applies.
Signals will be scaled by an appropriate section of the multiplier
mpy = (invtgc[:,np.newaxis] *
np.ones((ntgc, tgcsamps), dtype=np.float32)).ravel('C'),
where the values invtgc = 10.**(-wset.context['tgc'] / 20.) and
ntgc = len(wset.context['tgc']). The multiplier mpy is defined over a
window that starts at file sample 0 (global time wset.f2c).
Set tgcsamps to 0 (or None) to disable compensation. If the
WaveformSet includes TGC parameters and tgcsamps is a positive
integer, then len(mpy) must be at least long enough to encompass all
data windows encoded in the file.
* tgcmap (default: None): If provided, should be a two-column, rank-2
Numpy array (or compatible sequence) that relates nominal gains in
column 0 to actual gains in column 1. The rows of the array will be
used as control points in a piecewise linear interpolation (using
numpy.interp) that will map TGC parameters specified in the
WaveformSet file to actual gains. In other words, the TGC values
described above will be replaced with
tgc = np.interp(tgc, tgcmap[:,0], tgcmap[:,1])
whenever tgcmap is provided.
* tdout (default: False): Set to True to output time-domain waveforms
rather than spectral samples. Preserves input acquisition windows.
* signs (default: None): When not None, should be a sequence of length
wset.txgrps.size that specifies a 1 for any local Hadamard index
(corresponding to lines in the file) that should be negated, and 0
anywhere else. Ignored when an FHT is not performed.
* trmap (default: None): If provided, must be a map from a label
(referencing an output location in the map outfile) to a map from
receive indices to lists of transmit indices that, together, identify
transmit-receive pairs to extract from the input.
* start (default: 0) and stride (default: 1): For an input WaveformSet
wset, process receive channels in wset.rxidx[start::stride].
* lock (default: None): If not None, it should be a context manager
that is invoked to serialize writes to output.
* event (default: None): Only used then trmap is not provided. If not
None, event.set() and event.wait() are called to ensure the output
header is written to the binary-blob output before records are
appended. The value event.is_set() should be False prior to
execution.
'''
# Override acquisition window, if desired
nsamp = kwargs.pop('nsamp', None)
# Grab synchronization mechanisms
try:
lock = kwargs.pop('lock')
except KeyError:
lock = multiprocessing.Lock()
try:
event = kwargs.pop('event')
except KeyError:
event = multiprocessing.Event()
# Grab FFT and FHT switches and options
tdout = kwargs.pop('tdout', False)
freqs = kwargs.pop('freqs', None)
rolloff = kwargs.pop('rolloff', None)
dofft = (freqs is not None) or not tdout
if freqs is not None:
flo, fhi = freqs
if rolloff and not 0 < rolloff < (fhi - flo) // 2:
raise ValueError(
'Rolloff must be None or less than half bandwidth')
# Grab striding information
start = kwargs.pop('start', 0)
stride = kwargs.pop('stride', 1)
# Grab sign map information
signs = kwargs.pop('signs', None)
# Grab the number of samples per TGC value and an optional gain map
tgcsamps = kwargs.pop('tgcsamps', None)
tgcmap = kwargs.pop('tgcmap', None)
trmap = kwargs.pop('trmap', None)
if len(kwargs):
raise TypeError(f"Unrecognized keyword '{next(iter(kwargs))}'")
# Open the input and create a corresponding output
wset = WaveformSet.load(infile)
# Pull default sample count from input file
if nsamp is None: nsamp = wset.nsamp
elif wset.nsamp < nsamp: wset.nsamp = nsamp
# Handle TGC compensation if necessary
try:
tgc = np.asarray(wset.context['tgc'], dtype=np.float32)
except (KeyError, AttributeError):
tgc = np.array([], dtype=np.float32)
if tgcmap is not None:
# Make sure that the TGC map is sorted and interpolate
tgx, tgy = zip(*sorted((k, v) for k, v in tgcmap))
# TGC curves are always float32, regardless of tgcmap types
tgc = np.interp(tgc, tgx, tgy).astype(np.float32)
# Pick a suitable default value for tgcsamps
if tgcsamps is None:
tgcsamps = 16 if np.issubdtype(wset.dtype, np.integer) else 0
# Linearize, invert, and expand the TGC curves
tgc = ((10.**(-tgc[:, np.newaxis] / 20.) * np.ones(
(len(tgc), tgcsamps), dtype=np.float32))).ravel('C')
# Figure out the data type of compensated waveforms
if len(tgc): itype = np.dtype(wset.dtype.type(0) * tgc.dtype.type(0))
else: itype = wset.dtype
# Make sure that the data type is always floating-point
if not np.issubdtype(itype, np.floating): itype = np.dtype('float64')
# Create a WaveformSet object to hold the ungrouped data
ftype = _r2c_datatype(itype)
otype = ftype if not tdout else itype
# Make sure the WaveformSet has a local configuration
try:
gcount, gsize = wset.txgrps
except TypeError:
raise ValueError('A valid Tx-group configuration is required')
if gsize < 1 or (gsize & (gsize - 1)):
raise ValueError('Hadamard length must be a positive power of 2')
# Validate local portion of the group map and assign
wset.groupmap = groupmap
if signs is not None:
# Ensure signs has values 0 or 1 in the right type
signs = np.asarray([1 - 2 * s for s in signs], dtype=itype)
if signs.ndim != 1 or len(signs) != gsize:
msg = f'Sign list must have shape ({wset.txgrps[1]},)'
raise ValueError(msg)
# Identify all FHTs represented by stored transmission indices
fhts = {}
for i in wset.txidx:
g, l = i // gsize, i % gsize
try:
fhts[g].append(l)
except KeyError:
fhts[g] = [l]
# Verify that all FHTs are complete
for g, ll in fhts.items():
if len(ll) != gsize:
raise ValueError(f'FHT group {gi} is incomplete')
if any(i != j for i, j in enumerate(sorted(ll))):
raise ValueError(f'FHT group {gi} has improper local indices')
# Map each FHT group to a list of row indices for the FHT
# and each element corresponding to an FHT output to row indices
gidx = lambda l, g: g * gsize + l
fhts = {g: [wset.tx2row(gidx(l, g)) for l in range(gsize)] for g in fhts}
invgroups = {(l, g): i for i, (l, g) in wset.groupmap.items()}
el2row = {
invgroups[l, g]: wset.tx2row(gidx(l, g))
for g in fhts for l in range(gsize)
}
# Create intermediate (FHT) and output (FHFFT) arrays
# FFT axis is contiguous for FFT performance
b = pyfftw.empty_aligned((wset.ntx, nsamp), dtype=itype, order='C')
if dofft:
# Create FFT output and a plan
cdim = (wset.ntx, nsamp // 2 + 1)
c = pyfftw.empty_aligned(cdim, dtype=ftype, order='C')
fwdfft = pyfftw.FFTW(b, c, axes=(1, ), direction='FFTW_FORWARD')
# Create an inverse FFT plan for time-domain output
if tdout:
invfft = pyfftw.FFTW(c, b, axes=(1, ), direction='FFTW_BACKWARD')
# Find the spectral window of interest
fswin = specwin(cdim[1], freqs)
# Try to build bandpass tails
if rolloff: tails = np.hanning(2 * int(rolloff))
else: tails = np.array([])
if trmap:
# Identify the subset of receive channels needed
allrx = reduce(set.union, (trm.keys() for trm in trmap.values()),
set())
rxneeded = sorted(allrx.intersection(wset.rxidx))[start::stride]
else:
rxneeded = wset.rxidx[start::stride]
# In blob mode, the first write must create a header
with lock:
if not event.is_set():
# Create a sliced binary matrix output
windim = (nsamp if tdout else fswin.length, wset.ntx, wset.nrx)
mio.Slicer(outfile, dtype=otype, trunc=True, dim=windim)
event.set()
# Ensure the output header has been written
event.wait()
# Map receive channels to rows (slabs) in the output
rx2slab = dict((i, j) for (j, i) in enumerate(sorted(wset.rxidx)))
# Map transmit channels to decoded FHT rows
outrows = [r for (e, r) in sorted(el2row.items())]
outbin = mio.Slicer(outfile)
for rxc in rxneeded:
# Find the input window relative to 0 f2c
iwin = wset.getheader(rxc).win.shift(wset.f2c)
owin = (0, nsamp)
try:
# Find overlap of global input and output windows
ostart, istart, dlength = cutil.overlap(owin, iwin)
except TypeError:
# Default to 0-length windows at start of acquisition
iwin = Window(0, 0, nonneg=True)
owin = Window(0, 0, nonneg=True)
else:
# Convert input and output windows from global f2c to file f2c
iwin = Window(istart, dlength, nonneg=True)
owin = Window(ostart, dlength, nonneg=True)
# Read the data over the input window
data = wset.getrecord(rxc, window=iwin)[1]
# Clear the data array
b[:, :] = 0.
ws, we = owin.start, owin.end
if iwin.length and gsize > 1:
# Perform grouped Hadamard transforms with optional sign flips
for grp, rows in fhts.items():
# Ensure FHT axis is contiguous for performance
dblk = np.asfortranarray(data[rows, :])
b[rows, ws:we] = fwht(dblk, axes=0) / gsize
if signs is not None: b[rows, ws:we] *= signs[:, np.newaxis]
else: b[:, ws:we] = data
# Time-gain compensation, if necessary
if len(tgc) and iwin.length:
twin = (0, len(tgc))
try:
tstart, istart, dlength = cutil.overlap(twin, iwin)
if dlength != iwin.length: raise ValueError
except (TypeError, ValueError):
raise ValueError(
f'TGC curve does not encompass data for channel {rxc}')
b[:, ws:we] *= tgc[np.newaxis, tstart:tstart + dlength]
if dofft:
fwdfft()
# Suppress content out of the band
c[:, :fswin.start] = 0.
c[:, fswin.end:] = 0.
# Bandpass filter the spectral samples
if len(tails) > 0:
ltails = len(tails) // 2
c[:, fswin.start:fswin.start +
ltails] *= tails[np.newaxis, :ltails]
c[:, fswin.end - ltails:fswin.end] *= tails[np.newaxis,
-ltails:]
# Revert to time-domain representation if necessary
if tdout: invfft()
if not trmap:
# Write the binary blob for this receive channel
orow = rx2slab[rxc]
with lock:
if tdout: outbin[orow] = b[outrows, :].T
else: outbin[orow] = c[outrows, fswin.start:fswin.end].T
# Nothing more to do in blob mode
continue
# Slice desired range from output data
if tdout:
dblock = b[:, ws:we]
dstart = ws
else:
dblock = c[:, fswin.start:fswin.end]
dstart = fswin.start
for label, trm in trmap.items():
# Pull tx list for this tier and rx channel, if possible
try:
tl = trm[rxc]
except KeyError:
tl = []
if not len(tl): continue
# Collect all transmissions for this rx channel
wmap = WaveformMap()
for t in tl:
# Make sure transmission is represented in output
try:
row = el2row[t]
except KeyError:
continue
wave = Waveform(nsamp, dblock[row], dstart)
wmap[t, rxc] = wave
# Flush the waveform map to disk
with lock:
wmap.store(outfile[label], append=True)
# Process the messages, adding waveforms to the local map
printroot(grank, 'Collecting incoming waveforms...')
wmap.update(procmessages(sendreqs, recvreqs, recvbufs))
printroot(grank, f'Final size of local map at rank {grank} is {len(wmap)}')
gnsize = MPI.COMM_WORLD.reduce(len(wmap))
printroot(grank, f'{gnsize} waveforms scattered globally')
# Build an output map
omap = WaveformMap()
while wmap:
(t, r), left = wmap.popitem()
try:
right = wmap.pop((r, t))
except KeyError:
continue
omap[min(t, r), max(t, r)] = pairavg(left, right, args.osamp,
args.clip)
gosize = MPI.COMM_WORLD.reduce(len(omap))
printroot(grank, f'{gosize} reciprocal pairs averaged globally')
# Write the output, serializing within local communicators
for i in range(lsize):
if i == lrank: omap.store(args.output, append=i)
lcomm.Barrier()
printroot(grank, 'End of control')
MPI.COMM_WORLD.Barrier()
parser.add_argument('inputs', type=str, nargs='+',
help='Input WaveformMap files from which to extract')
args = parser.parse_args(sys.argv[1:])
# Try to read all input WaveformMap files
infiles = matchfiles(args.inputs)
# Read a defined receive-to-transmit-list map
if args.trmap: args.trmap = loadkeymat(args.trmap, scalar=False)
# At first, clobber the output
append = False
for infile in infiles:
wmap = WaveformMap.load(infile)
# Build the appropriate subset of the WaveformMap
if not args.backscatter: wvs = trextract(wmap, args.trmap, args.random)
else: wvs = ((k, v) for k, v in wmap.items() if k[0] == k[1])
omap = WaveformMap(wvs)
if args.output:
# Save to common output and switch to append mode
omap.store(args.output, compression=args.compression, append=append)
append = True
else:
output = os.path.splitext(infile)[0] + 'extract.wmz'
omap.store(output, compression=args.compression, append=False)