Files
Jungfraujoch/receiver/JFJochReceiverTest.cpp
T
leonarski_f cc925b2668
Build Packages / build:rpm (ubuntu2404_nocuda) (push) Successful in 8m30s
Build Packages / build:rpm (rocky8_nocuda) (push) Successful in 10m13s
Build Packages / build:rpm (ubuntu2204_nocuda) (push) Successful in 9m45s
Build Packages / build:rpm (rocky9_nocuda) (push) Successful in 11m13s
Build Packages / build:rpm (rocky8_sls9) (push) Successful in 9m51s
Build Packages / build:rpm (rocky8) (push) Successful in 8m29s
Build Packages / build:rpm (rocky9_sls9) (push) Successful in 9m31s
Build Packages / build:rpm (rocky9) (push) Successful in 9m42s
Build Packages / build:rpm (ubuntu2204) (push) Successful in 8m47s
Build Packages / build:rpm (ubuntu2404) (push) Successful in 8m23s
Build Packages / Generate python client (push) Successful in 19s
Build Packages / Build documentation (push) Successful in 38s
Build Packages / Create release (push) Skipped
Build Packages / XDS test (durin plugin) (push) Successful in 6m18s
Build Packages / XDS test (neggia plugin) (push) Successful in 6m4s
Build Packages / XDS test (JFJoch plugin) (push) Successful in 6m35s
Build Packages / DIALS test (push) Successful in 10m39s
Build Packages / Unit tests (push) Successful in 1h24m58s
Remove NUMAHWPolicy and the libnuma dependency
NUMA CPU/memory pinning is no longer worthwhile: the FPGA DMA buffers are
placed device-local by the kernel (dma_alloc_coherent), the big RAM ring
buffer is random-access (first-touch handles placement), and GPU work is
already spread across all visible devices. So drop the pinning entirely
and with it libnuma.

- Delete NUMAHWPolicy; the only concern worth keeping - GPU selection -
  is done directly via pin_gpu() (round-robin over visible GPUs) in the
  indexer pool and the Lite analysis threads. CPU-only threads
  (FPGA acquire/pedestal/summation/frame-transform) no longer bind
  anything.
- Drop get_gpu_numa_node() (sysfs lookup) - only SelectGPUAndItsNUMA
  used it.
- numa_policy broker setting is deprecated and ignored (kept in the API
  for backward compatibility; warns once on startup).
- Remove NUMA_LIBRARY / numa.h / numaif.h detection from CMake.
- Docs: drop the NUMA dependency, remove the numa_policy config example,
  and document running multiple brokers on disjoint GPUs via
  CUDA_VISIBLE_DEVICES.
- Remove NUMA_GPU_REVIEW.md (the planning note; this work is now done).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-17 20:25:36 +02:00

117 lines
4.2 KiB
C++

// SPDX-FileCopyrightText: 2024 Filip Leonarski, Paul Scherrer Institute <filip.leonarski@psi.ch>
// SPDX-License-Identifier: GPL-3.0-only
#include "JFJochReceiverTest.h"
#include "JFJochReceiverService.h"
#include "../image_pusher/ZMQStream2Pusher.h"
#include "../image_pusher/TestImagePusher.h"
#define STORAGE_CELL_FOR_TEST 11
static JFCalibration GeneratePedestalCalibration(const DiffractionExperiment &x) {
JFCalibration ret(x);
std::vector<float> pedestal_g0( RAW_MODULE_SIZE), pedestal_g1(RAW_MODULE_SIZE), pedestal_g2(RAW_MODULE_SIZE);
for (int s = 0; s < x.GetStorageCellNumber(); s++) {
for (int m = 0; m < x.GetModulesNum(); m++) {
for (int i = 0; i < RAW_MODULE_SIZE; i++) {
pedestal_g0[i] = 3000 + 100 * s + 10 * m + i % 50;
if (x.IsFixedGainG1())
pedestal_g1[i] = 2500 + 100 * s + 10 * m + i % 50;
else
pedestal_g1[i] = 15000 - 100 * s + 10 * m + i % 50;
pedestal_g2[i] = 14000 - 100 * s + 10 * m + i % 50;
}
ret.Pedestal(m, 0, s).LoadPedestal(pedestal_g0);
ret.Pedestal(m, 1, s).LoadPedestal(pedestal_g1);
ret.Pedestal(m, 2, s).LoadPedestal(pedestal_g2);
}
}
return ret;
}
bool JFJochReceiverTest(JFJochReceiverOutput &output, Logger &logger,
AcquisitionDeviceGroup &aq_devices,
const DiffractionExperiment &x,
const PixelMask &pixel_mask,
uint16_t nthreads,
size_t send_buf_size_MiB,
bool quick_integrate) {
std::vector<uint16_t> raw_expected_image(RAW_MODULE_SIZE * x.GetModulesNum());
for (int i = 0; i < raw_expected_image.size(); i++)
raw_expected_image[i] = i % 65536;
return JFJochReceiverTest(output, logger, aq_devices, x, pixel_mask, raw_expected_image, nthreads,
send_buf_size_MiB, quick_integrate);
}
bool JFJochReceiverTest(JFJochReceiverOutput &output, Logger &logger,
AcquisitionDeviceGroup &aq_devices,
const DiffractionExperiment &x,
const PixelMask &pixel_mask,
const std::vector<uint16_t> &raw_expected_image,
uint16_t nthreads,
size_t send_buf_size_MiB,
bool quick_integrate) {
std::vector<uint16_t> raw_expected_image_with_mask = raw_expected_image;
if (x.IsApplyPixelMask()) {
for (int i = 0; i < raw_expected_image_with_mask.size(); i++)
if (pixel_mask.GetMaskRaw().at(i) != 0)
raw_expected_image_with_mask[i] = UINT16_MAX;
}
JFCalibration calib = GeneratePedestalCalibration(x);
int64_t image_number = x.GetImageNum() - 1;
if (x.GetStorageCellNumber() > 1)
image_number = STORAGE_CELL_FOR_TEST;
if (image_number < 0)
image_number = 0;
TestImagePusher pusher(image_number);
JFJochReceiverService service(aq_devices, logger, pusher, send_buf_size_MiB);
service.NumThreads(nthreads);
service.LoadInternalGeneratorImage(x, raw_expected_image, 0);
service.Indexing(x.GetIndexingSettings());
SpotFindingSettings settings = DiffractionExperiment::DefaultDataProcessingSettings();
settings.signal_to_noise_threshold = 2.5;
settings.photon_count_threshold = 5;
settings.min_pix_per_spot = 1;
settings.max_pix_per_spot = 200;
settings.quick_integration = quick_integrate;
service.SetSpotFindingSettings(settings);
service.Start(x, pixel_mask, &calib);
output = service.Stop();
bool no_errors = true;
if (x.GetImageNum() > 0) {
no_errors = pusher.CheckImage(x, raw_expected_image_with_mask, calib, logger);
if (output.efficiency != 1.0) {
logger.Error("Not all frames were received");
no_errors = false;
}
if (!pusher.CheckSequence()) {
logger.Error("Wrong sequence of operations for pusher");
no_errors = false;
}
if (pusher.GetCounter() != x.GetImageNum()) {
logger.Error("Wrong frame number from pusher");
no_errors = false;
}
}
return no_errors;
}