使用 XDSP API 進行含包絡的單一串流摺積

class ConvolveOneBufferManager
{
private:
    float const* _outputBuffer = nullptr;
    uint32_t _maxBufferFrameCount = 0;
    uint32_t _bufferStride = 0;
    uint32_t _maxBufferCount = 0;
    uint32_t _acquiredBufferCount = 0;
    uint32_t _channelCount = 1;

public:
    void Reset(float const* outputBuffer, uint32_t maxBufferCount, uint32_t maxBufferFrameCount, uint32_t channelCount) {
        _outputBuffer = outputBuffer;
        _maxBufferCount = maxBufferCount;
        _maxBufferFrameCount = maxBufferFrameCount;
        _channelCount = channelCount;
    }

    uint32_t GetMaxBufferFrameCount() const {
        return _maxBufferFrameCount;
    }

    bool IsFull() const {
        return _acquiredBufferCount >= _maxBufferCount;
    }

    void Acquire() {
        if (_acquiredBufferCount < _maxBufferCount) {
            _acquiredBufferCount++;
        }
    }

    void Release() {
        if (_acquiredBufferCount > 0) {
            _acquiredBufferCount--;
        }
    }

    float* GetOutputBuffer(uint32_t index) {
        return const_cast<float*>(_outputBuffer) + (((index % _maxBufferCount) * _maxBufferFrameCount * _channelCount));
    }

};

#define ROUND_UP_TO_16BYTE_ALIGNED(x) (((x) + (15)) & ~(0xF))
uint32_t blockSize = 1024; // can be 512 or 1024
uint32_t irLengthInComplexes = impulseResponseLengthInFloats/2;
uint32_t numFilterBlocks = irLengthInComplexes/blockSize;

// In case of a stereo impulse response filter, the envelope buffer length will be 2 * envelopeLengthInBytes assuming impulseResponseLengthInFloats is the impule response length of a single channel.
uint32_t envelopeLengthInBytes = ROUND_UP_TO_16BYTE_ALIGNED(numFilterBlocks * sizeof(float));
uint32_t envelopeGainCount = envelopeLengthInBytes/sizeof(float);

static const ULONGLONG XMemAllocAttributes = MAKE_XALLOC_ATTRIBUTES(allocatorId,
                      0,
                      XALLOC_MEMTYPE_PHYSICAL_CACHEABLE,
                      XALLOC_PAGESIZE_64KB,
                      XALLOC_ALIGNMENT_64K,
                      FALSE);

float* baseBuffer = (float *)XMemAlloc(baseBufferLength, XMemAllocAttributes);

hr = XDspConnect(baseBuffer, baseBufferLength, 32 /*aggregateImpulseResponseInSeconds*/, &clientHandle);

XDspActivationParameters params;
XDspStatus* status;
XDspStreamHandle* streamHandle;
params.type = XDspProcessType::Convolution;
params.blockFrameCount = maxBufferFrameCount;
params.channelCount = channelCount; // mono or stereo
params.impulseResponseLengthInFloats = filterFrameCount;
params.impulseResponse = filterBuffer;

if (channelCount == 2 && deinterleaved)
{
    params.options |= XDspActivationOptions::Deinterleaved;
}
if (stereoImpulseResponse)
{
    params.options |= XDspActivationOptions::StereoImpulseResponse;
}
hr = XDspActivate(clientHandle, &params, &status, &streamHandle); 

XDspCommand command;

command.beginScale = 1.0f;
command.endScale = 1.0f;
command.inputBlockBuffer = inputDataBuffer;
command.outputBlockBuffer =  bufferManager.GetOutputBuffer(_totalCommandsSubmitted + 1);
command.blockBufferMultiplier = nullptr;

uint32_t sequence = 0;
hr = XDspSubmitCommand(streamHandle, &command, &sequence);

if (SUCCEEDED(hr))
{
    totalCommandsSubmitted++;
}

// Please see the code snippet at the beginning of this example for information on the envelope buffer size and envelope gain counts.
void CreateEnvelopeParams(
    float* envelopeBuffer, 
    uint32_t envelopeGainCount, 
    uint32_t numFilterBlocks,
    bool stereoImpulseResponse)
{
    const uint32_t envelopeRatio = 0.5f; // Use only half of the impulse response filter
    uint32_t numGains = (uint32_t)(envelopeRatio * numFilterBlocks);
    float gainDecrement = 1.0f/numGains;

    envelopeBuffer[0] = 1.0f;
        
    for (uint32_t i = 1; i < envelopeGainCount; i++)
    {
        if (i < numGains)
        {
            envelopeBuffer[i] = envelopeBuffer[i-1] - gainDecrement;
        }
        else
        {
            envelopeBuffer[i] = 0.0f;
        }
    }

    if (stereoImpulseResponse)
    {
        // Populate gain values for the right channel envelope
        memcpy((void*)&envelopeBuffer[envelopeGainCount], (void*)&envelopeBuffer[0], envelopeGainCount * sizeof(float));
    }
}

XDspCommand command;

command.beginScale = 1.0f;
command.endScale = 1.0f;
command.inputBlockBuffer = inputDataBuffer;
command.outputBlockBuffer =  bufferManager.GetOutputBuffer(_totalCommandsSubmitted + 1);
command.blockBufferMultiplier = nullptr;

uint32_t sequence = 0;
hr = XDspSubmitCommandWithEnvelope(streamHandle, &command, envelopeBuffer, &sequence);

if (SUCCEEDED(hr))
{
    totalCommandsSubmitted++;
}

while (status->lastProcessedCommandSequence > totalResponsesReceived)
{
    totalResponsesReceived++;
 
    // Hardware status is only updated when there is a hardware fault and the
    // error is going to persist for the duration of the stream. But, all the
    // commands that have already been submitted will still be processed by
    // the hardware and we have to wait for these commands to be processed 
    // before calling XDspDeactivate.
    hr = status->result; 
     
    float* outBuffer = bufferManager.GetOutputBuffer(totalResponsesReceived);
    // The output will be in the outBuffer
    // Do something with the outBuffer
    bufferManager.Release();
}

while (totalResponsesReceived < totalCommandsSubmitted)
{
    // run the above code in the while loop to obtain all the responses
}
hr = XDspDeactivate(streamHandle);

hr = XDspDisconnect(clientHandle);
XMemFree(baseBuffer, XMemAllocAttributes);