v1.0.0-rc.168 (#78)

* rugnux is substantially faster - a corpus of 145 rotation datasets processes in about two thirds of the time - with identical results.
* A crystal whose lattice looks more symmetric than it is because the beam centre is off is no longer processed on the wrong cell.
* rugnux prints at startup, and writes at the foot of every results report, a short acknowledgement of the X-ray research community whose methods it implements and of the open-source projects it builds on; `ACKNOWLEDGEMENT.md` now ships in every package beside `LICENSE` and `THIRD_PARTY_NOTICES.md`.

Reviewed-on: #78
Co-authored-by: Filip Leonarski <filip.leonarski@psi.ch>

image_analysis/image_preprocessing/ImagePreprocessorGPU.cu

@@ -338,6 +338,34 @@ float ImagePreprocessorGPU::GetLastDecompressionTime_s() const {
     return bslz4_decoder ? bslz4_decoder->GetDecodeTime_s() : 0.0f;
 }
 
+ImagePreprocessorGPU::~ImagePreprocessorGPU() {
+    // Unchecked, as everywhere else in this teardown path: a destructor is noexcept and the region
+    // may already be gone with the device.
+    if (pinned_input)
+        cudaHostUnregister(const_cast<void *>(pinned_input));
+}
+
+void ImagePreprocessorGPU::PinInputRegion(const void *ptr, size_t bytes) {
+    if (ptr == pinned_input && bytes == pinned_input_bytes)
+        return;
+    if (pinned_input)
+        cuda_err(cudaHostUnregister(const_cast<void *>(pinned_input)));
+    pinned_input = nullptr;
+    pinned_input_bytes = 0;
+    // The buffer may already be page-locked by whoever owns it - the receiver registers its image
+    // buffer once and hands out ranges inside it - and registering a range twice is an error rather
+    // than a no-op. There is nothing to do in that case: the upload is already a DMA, and the
+    // region is not ours to unregister later, so it is deliberately not remembered.
+    const auto err = cudaHostRegister(const_cast<void *>(ptr), bytes, cudaHostRegisterDefault);
+    if (err == cudaErrorHostMemoryAlreadyRegistered) {
+        cudaGetLastError();
+        return;
+    }
+    cuda_err(err);
+    pinned_input = ptr;
+    pinned_input_bytes = bytes;
+}
+
 void ImagePreprocessorGPU::PinInputBuffer(std::vector<uint8_t> &buffer, size_t size) {
     if (buffer.size() == size)
         return;