Method get_mws

src/cpu/kernels/CpuMulKernel.cpp:1729–1780

}

size_t CpuMulKernel::get_mws(const CPUInfo &platform, size_t thread_count) const
{
    ARM_COMPUTE_UNUSED(thread_count);

#if defined(ENABLE_FP32_KERNELS)
    if (this->_func_float == &mul_F32_F32_F32)
    {
        size_t mws = ICPPKernel::default_mws;
        if (platform.get_cpu_model() == CPUModel::N1)
        {
            mws = default_mws_N1_fp32_neon;
        }
        else if (platform.get_cpu_model() == CPUModel::V1)
        {
            mws = default_mws_V1_fp32_neon;
        }
        else
        {
            if (_split_dimension == Window::DimX)
            {
                // Don't split the work load too small if the tensor has been reinterpreted as 1D.
                // This number is loosely chosen as threading overhead in each platform varies wildly.
                return default_mws_other_platforms_1d_tensor;
            }
            return default_mws;
        }

        // tensor is 1D or was re-interpreted as 1D
        if (this->window().shape().num_dimensions() == 1)
        {
            return mws;
        }
        else
        {
            // scale mws down by the number of elements along all the dimensions (x, z, w, etc) except the one
            // that we parallelize along (the y dimension). This allows for parallelization when the Y_SIZE is small
            // but the other sizes are large, which boosts performance.
            mws = static_cast<size_t>(mws / (this->window().num_iterations_total() / this->window().num_iterations(1)));
            return std::max(static_cast<size_t>(1), mws);
        }
    }
#else  /* ENABLE_FP32_KERNELS */
    ARM_COMPUTE_UNUSED(platform);
#endif /* ENABLE_FP32_KERNELS */
    if (_split_dimension == Window::DimX)
    {
        // Don't split the work load too small if the tensor has been reinterpreted as 1D.
        // This number is loosely chosen as threading overhead in each platform varies wildly.
        return default_mws_other_platforms_1d_tensor;
    }
    return default_mws;
}

Status CpuMulKernel::validate(const ITensorInfo *src1,
                              const ITensorInfo *src2,