Jan Svabenik 2efae6fd9c feat: add CUDA decimate preparation path		3 dagar sedan
..
build	feat: add CUDA decimate preparation path	3 dagar sedan
README.md	build: add CUDA demod kernel build helper	3 dagar sedan
doc.go	docs: add initial CUDA demod kernel source	3 dagar sedan
gpudemod.go	feat: add CUDA decimate preparation path	3 dagar sedan
gpudemod_cufft_test.go	build: wire CUDA demod package through nvcc and MSVC	3 dagar sedan
gpudemod_stub.go	feat: extend CUDA demod telemetry and FM kernel prep	3 dagar sedan
gpudemod_test.go	feat: prepare CUDA demod launch boundary	3 dagar sedan
kernels.cu	feat: add CUDA decimate preparation path	3 dagar sedan
validation.go	feat: wire CUDA freq-shift launcher	3 dagar sedan
validation_test.go	feat: validate CUDA freq-shift output	3 dagar sedan

README.md

gpudemod

Phase 1 CUDA demod scaffolding.

Current state

Standard Go builds use gpudemod_stub.go (!cufft).
cufft builds allocate GPU buffers and cross the CGO/CUDA launch boundary.
If CUDA launch wrappers are not backed by compiled kernels yet, the code falls back to CPU DSP.
The shifted IQ path is already wired so a successful GPU freq-shift result can be copied back and reused immediately.

First real kernel

kernels.cu contains the first candidate implementation:

gpud_freq_shift_kernel

This is not compiled automatically yet in the current environment because the machine currently lacks a CUDA compiler toolchain in PATH (nvcc not found).

Next machine-side step

On a CUDA-capable dev machine with toolchain installed:

Compile kernels.cu into an object file
- helper script: tools/build-gpudemod-kernel.ps1
Link it into the cufft build
Replace gpud_launch_freq_shift(...) stub body with the real kernel launch
Validate copied-back shifted IQ against dsp.FreqShift
Only then move the next stage (FM discriminator) onto the GPU

Why this is still useful

The runtime/buffer/recorder/fallback structure is already in place, so once kernel compilation is available, real acceleration can be inserted without another architecture rewrite.