AVX signal processor: Passes signals above a threshold. More...

#include <AVXThresholdProcessor.hpp>

Inheritance diagram for tpglibs::AVXThresholdProcessor:

Collaboration diagram for tpglibs::AVXThresholdProcessor:

Public Member Functions
__m256i	process (const __m256i &signal) override
	Masks channels with signals below threshold.
void	configure (const nlohmann::json &config, const int16_t *plane_numbers) override
	Configures thresholds according to plane numbers.
Public Member Functions inherited from tpglibs::AbstractProcessor< __m256i >
virtual	~AbstractProcessor ()=default
virtual void	configure_internal_state_collection (const nlohmann::json &)
	No-op: state monitoring disabled at build time.
void	set_next_processor (std::shared_ptr< AbstractProcessor< __m256i > > next_processor)
	Setter for next processor.
std::shared_ptr< AbstractProcessor< __m256i > >	get_next_processor ()
	Getter for next processor.
virtual std::vector< std::string >	get_requested_internal_state_names () const
	Get the names of requested internal states (delegates to registry).
virtual ProcessorMetricArray< std::array< int16_t, 16 > >	read_internal_states_as_integer_array ()

Private Attributes
__m256i	m_threshold
	Vector of thresholds to apply.

Additional Inherited Members
Public Types inherited from tpglibs::AbstractProcessor< __m256i >
using	signal_type_t
	Signal type to process on. General __m256i.

Detailed Description

AVX signal processor: Passes signals above a threshold.

Definition at line 17 of file AVXThresholdProcessor.hpp.

Member Function Documentation

◆ configure()

void tpglibs::AVXThresholdProcessor::configure	(	const nlohmann::json &	config,
		const int16_t *	plane_numbers )

overridevirtual

Configures thresholds according to plane numbers.

Parameters

config	JSON containing thresholds for the 3 planes.
plane_numbers	Array of plane numbers. Gives the channels to apply the appropriate thresholds.

Implements tpglibs::AbstractProcessor< __m256i >.

Definition at line 16 of file AVXThresholdProcessor.cpp.

{
  int16_t thresholds[16];
  int16_t config_thresholds[3] = { config["plane0"], config["plane1"], config["plane2"] };
 
  // Messy. Assumes plane numbers are in {0, 1, 2}.
  for (int i = 0; i < 16; i++) {
    thresholds[i] = config_thresholds[plane_numbers[i]];
  }
 
  m_threshold = _mm256_lddqu_si256(reinterpret_cast<__m256i*>(thresholds));
}

◆ process()

__m256i tpglibs::AVXThresholdProcessor::process ( const __m256i & signal )

overridevirtual

Masks channels with signals below threshold.

Parameters

signal Vector of channel signals to process.

Returns: A vector of channel signals. Signals that were below threshold are set to 0.

Reimplemented from tpglibs::AVXProcessor.

Definition at line 30 of file AVXThresholdProcessor.cpp.

{
  __m256i mask = _mm256_cmpgt_epi16(signal, m_threshold);
 
  // Essentially: mask[i] ? signal[i] : 0.
  __m256i above_threshold = _mm256_blendv_epi8(_mm256_setzero_si256(), signal, mask);
  return AVXProcessor::process(above_threshold);
}

Member Data Documentation

◆ m_threshold

__m256i tpglibs::AVXThresholdProcessor::m_threshold

private

Vector of thresholds to apply.

Definition at line 20 of file AVXThresholdProcessor.hpp.

The documentation for this class was generated from the following files:

/github/workspace/dunedaq/sourcecode/tpglibs/include/tpglibs/AVXThresholdProcessor.hpp
/github/workspace/dunedaq/sourcecode/tpglibs/src/AVXThresholdProcessor.cpp

Public Member Functions