Как можно оптимизировать этот кусочек CUDA-кода?

void OpenNNL::calculateNeuronsOutputsAndDerivatives(double * inputs, double * deviceOutputs, double * deviceDerivatives)
    {
        int inputsCount = _inputsCount;
    
        double * deviceTemp;
        double * deviceInputs;
    
        cudaCall(cudaMalloc ( (void**)&deviceInputs, inputsCount*sizeof(double) ));
    
        cudaCall(cudaMemcpy ( deviceInputs, inputs, inputsCount*sizeof(double), cudaMemcpyDeviceToDevice ));
    
        for(int i=0;i<_layersCount;i++)
        {
            cudaCall(cudaMalloc((void**)&deviceTemp, _neuronsPerLayerCount[i]*inputsCount*sizeof(double)));
    
            dim3 threadsMul = dim3(BLOCK_SIZE, 1);
            int blocksCount = floor((double) _neuronsPerLayerCount[i]*inputsCount / threadsMul.x) + 1;
            dim3 blocksMul = dim3(blocksCount, 1);
    
            weighting<<<blocksMul, threadsMul>>>(deviceTemp, deviceInputs, _neuronsInputsWeights, _inputsInPreviousLayers[i], inputsCount, _neuronsPerLayerCount[i]);
    
            cudaCall(cudaFree(deviceInputs));
    
            cudaCall(cudaMalloc((void**)&deviceInputs, _neuronsPerLayerCount[i]*sizeof(double)));
    
            dim3 threadsSum = dim3(BLOCK_SIZE, 1);
            blocksCount = floor((double) _neuronsPerLayerCount[i] / threadsSum.x) + 1;
            dim3 blocksSum = dim3(blocksCount, 1);
    
            calculateOutputsAndDerivatives<<<blocksSum, threadsSum>>>(deviceOutputs, deviceDerivatives, deviceInputs, deviceTemp, _neuronsBiases, inputsCount, _neuronsPerLayerCount[i], _neuronsInPreviousLayers[i]);
    
            inputsCount = _neuronsPerLayerCount[i];
    
            cudaCall(cudaFree(deviceTemp));
        }
    
        cudaCall(cudaFree(deviceInputs));
    }