Summary
Overview
This filing turns DRAM into a deterministic streaming substrate by staging model data into bounded on-chip buffers ahead of compute.
Abstract
Technical Abstract
A compiler and runtime tile model parameters, program DMA descriptors with dependency fences, and overlap transfer with execution through double- or multi-buffering. The architecture removes off-chip memory from the steady-state compute critical path and produces predictable latency and power behavior.
Search Context
SEO Keywords
deterministic inference patent, DMA transfer patent, bounded buffer patent, neural network memory patent, accelerator streaming patent
Related Patents
More Patents in memory residency, KV systems, and deterministic inference
These filings sit nearby in the portfolio and strengthen internal linking across related patent topics.