Feat: Add --fast-mode supersampled point-source accumulation

Add an optional CPU preview path that deposits each point-source image as a
supersampled delta and resolves the whole frame with one global Moffat
convolution plus an N x N box average, instead of splatting a per-event PSF.

- optics: FastPsfAccumulator builds the pixel-area-integral kernel of the
  target Moffat at the supersampled scale (width N*alpha, same beta).  The
  1/N^2 box average then reproduces the final pixel-area integral, so the
  requested FWHM and beta are preserved without renormalisation.  Deposits are
  per-cell atomic adds; resolve accumulates into the caller's HDR buffer.
- frame: fast branch in frame_splat_catalog with one shared supersampled
  buffer and a single resolve per frame; the accumulator is reused across
  movie frames and built from the map dimensions on lens-map import.
- main: --fast-mode, --fast-supersample N (1..8, default 2) and
  --fast-deposit nearest|bilinear (default nearest).  CPU-only and rejected in
  the HIP/dummy backends; --psf-min-y still applies per event while
  --max-cache-psf-flux does not.
- The deposition scheme was chosen by scripts/fast_mode_deposit_error.py:
  nearest keeps the PSF shape exactly with <= 0.5/N px position quantization;
  bilinear keeps the exact centroid but broadens FWHM and beta.  Recorded in
  benchmarks/fast_mode_deposit_2026-09-18.md.
- tests/test_frame.c covers fast nearest vs the direct evaluator at the snapped
  centre, flux conservation, bilinear centroid, min-Y discard, frame plumbing,
  and HDR accumulation onto a non-zero background.
- benchmarks/fast_mode_cpu_2026-09-18.md records a ~10x speedup on the 2MASS
  galactic-centre field with small tone-mapped differences.
This commit is contained in:
wyj committed 2026-09-24 01:36:25 -04:00
1 parent 7ddc58515a
commit 3deebfb2fa
13 files changed
+1249 -36

No files matched your search

+4 -2
View File
@@ -132,8 +132,10 @@ PNGs. The command above omits the optional HDR and lens-map exports.
This example infers a position facing the hole from its look direction and radius. Adaptive refinement should
be configured for the desired image accuracy; it is disabled by default.
Camera controls, movie sequences, lens-map reuse, PSF settings, and HDR output
are described in [usage.md](usage.md). Both binaries provide a complete option
list with `--help`.
are described in [usage.md](usage.md). For fast previews, `--fast-mode` replaces
per-event PSF splats with a supersampled delta deposit plus one global PSF
convolution and downsample. Both binaries provide a complete option list with
`--help`.
### Example: Looking outward just above the Schwarzschild horizon