Rendering and inverse-rendering algorithms that drive conventional computer graphics have recently been superseded by neural representations (NR).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的渲染与逆渲染算法近年来已被神经表示（NR）所取代。NR 近期被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。本文提出疑问：神经图形学（NG）是否需要硬件支持？我们研究了代表性 NG 应用，结果表明，若要在当前 GPU 上以 60FPS 渲染 4K 分辨率，存在 1.5 倍至 55 倍的性能差距。对于 AR/VR 应用，期望性能与系统功耗需求之间甚至存在 2 至 4 个数量级的更大差距。我们识别出输入编码与 MLP 核为性能瓶颈，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时间的 72%、60% 和 59%。我们提出 NG 处理集群（NGPC），这是一种可扩展且灵活的硬件架构，通过专用引擎直接加速输入编码与 MLP 核，并支持多种 NG 应用。我们还通过 Vulkan 融合其余核，相比未融合的前处理与后处理核实现 9.94 倍的核级性能提升。实验结果显示，NGPC 在四个 NG 应用中平均带来高达 58 倍的端到端应用级性能提升；对于多分辨率哈希网格编码，缩放因子分别为 8、16、32 和 64 时，性能增益分别为 12 倍、20 倍、33 倍和 39 倍。结果表明，采用多分辨率哈希网格编码时，NGPC 可实现 NeRF 在 30FPS 下渲染 4K 分辨率，以及所有其他 NG 应用在 120FPS 下渲染 8K 分辨率。