Rendering and inverse-rendering algorithms that drive conventional computer graphics have recently been superseded by neural representations (NR). NRs have recently been used to learn the geometric and the material properties of the scenes and use the information to synthesize photorealistic imagery, thereby promising a replacement for traditional rendering algorithms with scalable quality and predictable performance. In this work we ask the question: Does neural graphics (NG) need hardware support? We studied representative NG applications showing that, if we want to render 4k res. at 60FPS there is a gap of 1.5X-55X in the desired performance on current GPUs. For AR/VR applications, there is an even larger gap of 2-4 OOM between the desired performance and the required system power. We identify that the input encoding and the MLP kernels are the performance bottlenecks, consuming 72%,60% and 59% of application time for multi res. hashgrid, multi res. densegrid and low res. densegrid encodings, respectively. We propose a NG processing cluster, a scalable and flexible hardware architecture that directly accelerates the input encoding and MLP kernels through dedicated engines and supports a wide range of NG applications. We also accelerate the rest of the kernels by fusing them together in Vulkan, which leads to 9.94X kernel-level performance improvement compared to un-fused implementation of the pre-processing and the post-processing kernels. Our results show that, NGPC gives up to 58X end-to-end application-level performance improvement, for multi res. hashgrid encoding on average across the four NG applications, the performance benefits are 12X,20X,33X and 39X for the scaling factor of 8,16,32 and 64, respectively. Our results show that with multi res. hashgrid encoding, NGPC enables the rendering of 4k res. at 30FPS for NeRF and 8k res. at 120FPS for all our other NG applications.

翻译：驱动传统计算机图形学的渲染与逆渲染算法近期已被神经表示（NR）所取代。NR 已用于学习场景的几何与材质属性，并利用这些信息合成逼真图像，从而有望以可扩展的质量和可预测的性能替代传统渲染算法。本文探讨的核心问题是：神经图形学（NG）是否需要硬件支持？我们通过研究代表性 NG 应用发现，若要在当前 GPU 上以60FPS渲染4K分辨率，性能差距达1.5倍至55倍；对于AR/VR应用，预期性能与所需系统功耗之间的差距甚至高达2-4个数量级。我们识别出输入编码与MLP内核是性能瓶颈——分别占用多分辨率哈希网格、多分辨率密集网格和低分辨率密集网格编码应用运行时间的72%、60%和59%。为此，我们提出一种可扩展、灵活的硬件架构——神经图形处理簇（NGPC），通过专用引擎直接加速输入编码与MLP内核，并支持多种NG应用。同时，我们通过Vulkan融合其余内核，使预处理与后处理内核的性能相比未融合实现提升9.94倍。实验结果表明：NGPC可将多分辨率哈希编码的平均端到端应用性能提升58倍；在四种NG应用中，当缩放因子为8、16、32和64时，性能分别提升12倍、20倍、33倍和39倍。此外，采用多分辨率哈希编码的NGPC支持NeRF以30FPS渲染4K分辨率，并支持其他NG应用以120FPS渲染8K分辨率。