arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2606.21791cs.GRcs.DC
收藏

3D高斯泼溅渲染中的单粒子翻转:比特级关键性、空间范围及并行支持防护

Single-Event Upsets in 3D Gaussian Splatting Rendering: Bit-Level Criticality, Spatial Extent, and a Parallel Support Guard

Bahçeşehir University(巴切希尔大学)

Faruk Alpay, Baris Basaran

AI总结:

本文通过GPU并行故障注入引擎,系统评估了3D高斯泼溅模型中单比特翻转的影响,发现高阶比特翻转可导致单个图元覆盖高达75.7%的帧,并提出一种基于训练坐标框的逐图元参数钳位防护机制,将最坏情况下的损坏面积限制在11.68%以内。

摘要:

三维高斯泼溅是一种标准的实时场景表示,越来越多地部署在暴露于瞬态故障的硬件上,例如星载处理器和机器人边缘设备,在这些设备中会发生静默数据损坏。训练好的模型是GPU内存中的一大组浮点参数,其中单粒子翻转对应于单个比特翻转。本文测量了这些影响并构建了一种防御机制。一个GPU驻留的并行故障注入引擎在四个场景、六个字段、所有比特位置和三种数值格式(fp32、fp16、bf16)上应用了超过380万次受控的单比特翻转,耗时5.3 GPU小时。影响高度集中:大多数翻转由于高冗余性而不会在感知上改变图像,但一小部分高阶比特(主要是对数尺度的符号位)会使单个图元放大到覆盖高达75.7%的帧。基于IEEE-754布局和流水线激活的闭式扰动界预测了这种逐比特顺序。这种集中性促使了一种支持防护:对每个图元的每个参数进行钳位,限制到训练期间观察到的坐标框,每帧耗时76微秒。在超过76.8万次受防护的翻转中,最坏情况下的损坏面积被限制在帧的11.68%以内。我们证明该防护不会改变干净模型,并防止了覆盖整个帧的损坏。在累积20000次同时翻转的剂量下,未防护的渲染器退化到10.6 dB,而防护的渲染器保持在21.8 dB。损坏面积还决定了分布式渲染器中受污染的瓦片/合成节点的数量,而逐节点防护可以控制这一点。

英文摘要:

Three-dimensional Gaussian splatting is a standard real-time scene representation increasingly deployed on hardware exposed to transient faults, such as spaceborne processors and robotic edge devices where silent data corruption occurs. A trained model is a large array of floating-point parameters in GPU memory, where a single-event upset corresponds to a single flipped bit. This paper measures these effects and constructs a defense. A GPU-resident parallel fault-injection engine applies over 3.8 million controlled single-bit upsets across four scenes, six fields, all bit positions, and three numeric formats (fp32, fp16, bf16), using 5.3 GPU-hours. The effect is highly concentrated: most upsets leave the image perceptually unchanged due to high redundancy, but a small set of high-order bits principally the logarithmic scale's sign bit enlarge a single primitive to cover up to 75.7% of the frame. A closed-form perturbation bound derived from the IEEE-754 layout and pipeline activations predicts this per-bit ordering. This concentration motivates a support guard: a per-primitive clamp of each parameter to the coordinate box observed during training, costing 76 us per frame. Over 768,000 guarded upsets, the worst corruption footprint is restricted to 11.68% of the frame. We prove the guard leaves clean models unchanged and prevents frame-covering corruption. Under an accumulated dose of 20,000 simultaneous upsets, the unguarded renderer degrades to 10.6 dB, whereas the guarded renderer remains at 21.8 dB. The corruption footprint also dictates the number of tile/compositing nodes contaminated in distributed renderers, where the per-node guard contains it.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑