cs.ARcs.DCEmpirical
CODA: Algorithm-Hardware Co-design for Edge Video Diffusion via NMP-Enabled Compute-Cache Operator Disaggregation
Jul 16, 2026
The paper proposes CODA, an algorithm-hardware co-designed architecture for deploying Video Diffusion Models on edge devices, achieving up to 1.80x speedup and 1.74x energy efficiency.
Proposed an algorithm-hardware co-designed architecture, CODA, to improve the performance and energy efficiency of Video Diffusion Models on edge devices.
Before reading this…
Applications
To understand this paper, make sure you know these concepts first:
Deploying Video Diffusion Models (VDMs) on edge devices is appealing for localized and privacy-preserving generation, but their iterative Transformer-based denoising remains too slow for practical local inference. Cross-Timestep Caching (CTC) has emerged as a promising direction for reducing redundant computation, reusing activations across adjacent denoising steps rather than modifying model weights, while largely preserving generation fidelity. However, on memory-constrained edge GPUs, CTC requires a massive cache footprint that quickly exceeds on-device VRAM and forces the cache into host memory. More fundamentally, cache operators remain tightly interleaved and chain-dependent with native compute operators, so naive near-memory offloading still incurs repeated PCIe exchanges for residual and fusion computations, turning cache reuse into a communication- and serialization-bound execution flow. We therefore propose CODA, an algorithm-hardware co-designed architecture centered on Compute-Cache Operator Disaggregation. CODA separates dense compute paths and memory-bound cache paths across the xPU and a lightweight DIMM-side near-memory engine, reorganizes fragmented cache activity into hardware-friendly coalesced segments, and exploits Classifier-Free Guidance (CFG) branch independence to overlap xPU compute with cache-side execution. Experiments show that CODA achieves up to 1.80x end-to-end speedup and 1.74x higher energy efficiency, while preserving competitive generation quality compared with a state-of-the-art caching algorithm.