21a8ea51ee
Build Packages / build:rpm (ubuntu2404_nocuda) (push) Failing after 8m56s
Build Packages / build:rpm (rocky8_nocuda) (push) Failing after 10m5s
Build Packages / build:rpm (rocky9_nocuda) (push) Failing after 11m41s
Build Packages / build:rpm (ubuntu2204_nocuda) (push) Failing after 11m39s
Build Packages / build:rpm (rocky9_sls9) (push) Failing after 11m42s
Build Packages / build:rpm (rocky8_sls9) (push) Failing after 11m45s
Build Packages / build:rpm (rocky8) (push) Failing after 11m47s
Build Packages / build:rpm (rocky9) (push) Failing after 10m21s
Build Packages / Generate python client (push) Successful in 14s
Build Packages / build:rpm (ubuntu2204) (push) Failing after 9m58s
Build Packages / Create release (push) Skipped
Build Packages / XDS test (neggia plugin) (push) Successful in 8m14s
Build Packages / Build documentation (push) Successful in 36s
Build Packages / XDS test (durin plugin) (push) Successful in 8m52s
Build Packages / build:rpm (ubuntu2404) (push) Failing after 9m4s
Build Packages / XDS test (JFJoch plugin) (push) Successful in 9m7s
Build Packages / DIALS test (push) Successful in 11m49s
Build Packages / Unit tests (push) Successful in 1h8m58s
52 lines
1.5 KiB
C++
52 lines
1.5 KiB
C++
// SPDX-FileCopyrightText: 2025 Filip Leonarski, Paul Scherrer Institute <filip.leonarski@psi.ch>
|
|
// SPDX-License-Identifier: GPL-3.0-only
|
|
|
|
#pragma once
|
|
|
|
// This include should be only included in sections of the code, where it is certain that CUDA is present
|
|
// so with JFJOCH_USE_CUDA preprocessor definition, given this file is included in the source only in this case
|
|
|
|
#include <vector>
|
|
#include <mutex>
|
|
#include <optional>
|
|
#include "CUDAMemHelpers.h"
|
|
#include "../../common/Coord.h"
|
|
#include "../../common/CrystalLattice.h"
|
|
#include "FFTIndexer.h"
|
|
#include "../common/IndexingSettings.h"
|
|
#include "FFTResult.h"
|
|
|
|
class FFTIndexerGPU : public FFTIndexer {
|
|
CudaDevicePtr<float> d_dir_x;
|
|
CudaDevicePtr<float> d_dir_y;
|
|
CudaDevicePtr<float> d_dir_z;
|
|
|
|
CudaDevicePtr<float> d_spot_x;
|
|
CudaDevicePtr<float> d_spot_y;
|
|
CudaDevicePtr<float> d_spot_z;
|
|
|
|
CudaHostPtr<float> spot_x;
|
|
CudaHostPtr<float> spot_y;
|
|
CudaHostPtr<float> spot_z;
|
|
|
|
CudaDevicePtr<float> d_input_fft;
|
|
CudaDevicePtr<cufftComplex> d_output_fft;
|
|
CudaDevicePtr<FFTResult> d_result_fft;
|
|
|
|
CudaRegisteredVector<FFTResult> result_fft_reg;
|
|
|
|
CudaFFTPlan plan;
|
|
|
|
CudaStream stream;
|
|
|
|
void ExecuteFFT(const std::vector<Coord> &coord, size_t nspots) override;
|
|
public:
|
|
explicit FFTIndexerGPU(const IndexingSettings& settings);
|
|
FFTIndexerGPU(const FFTIndexerGPU &i) = delete;
|
|
const FFTIndexerGPU &operator=(const FFTIndexerGPU &i) = delete;
|
|
~FFTIndexerGPU() override = default;
|
|
};
|
|
|
|
|
|
|