NVMe Video Codec Device Scaling Density
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current hardware-assisted video codec solutions, such as those built into CPUs or integrated into GPUs, face scalability issues due to separate video codec modules that require additional processing units, leading to inefficient use of computational power and limited density, while FPGA and ASIC-based solutions face challenges with proprietary drivers and limited expansion slots.
Innovation Solution
Implementing NVMe-based video codec devices that connect to a host computer via a PCIe bus, utilizing the NVMe interface to house video codec modules within a Solid State Drive (SSD) form factor, allowing for high-density video codec functionality without the need for special drivers and enabling easy scaling through existing storage infrastructure.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If video codec modules are built into CPUs or integrated into GPUs, then video encoding and decoding functionality is provided, but device complexity increases and scalability is limited due to separate video codec modules requiring additional processing units
Solution Approach 1:
The patent merges video codec modules with storage devices (SSD/HDD) to create a unified device that provides both storage and video encoding/decoding functionalities. This eliminates the need for separate video codec hardware modules integrated into CPUs or GPUs, thereby reducing device complexity while maintaining video codec capabilities.
Solution Approach 2:
The storage device is designed to perform multiple functions: it serves as both a storage device and a video codec device. The video codec modules can encode and decode video streams while the storage component stores video data, creating a universal device that replaces multiple separate components.
2Productivity
If FPGA or ASIC-based video codec solutions are used, then hardware-assisted video codec functionality is achieved, but adaptability decreases due to proprietary drivers and limited expansion slots
Solution Approach 1:
The video codec device uses standard storage device interfaces and protocols, making it compatible with existing storage infrastructure and operating systems without requiring proprietary drivers. This universal interface approach enhances adaptability while maintaining hardware-assisted video codec processing capabilities.
Solution Approach 2:
The device serves itself by integrating both storage and video codec functionalities into a single unit that can operate independently without requiring additional specialized hardware or proprietary software drivers, thereby improving adaptability to different systems.
3Adaptability or versatility
If separate video codec modules are integrated into CPUs or GPUs, then video codec functionality is provided, but density is limited due to the need for additional processing units
Solution Approach 1:
By combining video codec modules with storage devices, the patent achieves high-density video codec functionality within an existing form factor. This merging allows multiple video codec instances to be packed into a single storage device unit, significantly increasing density compared to separate CPU or GPU integration.
Data Source
AI summary
A NVMe™ or NVMe-over-fabrics enabled device with video codec functionality may be seen to overcome scalability problem of known hardware assisted video codec solutions. The device of aspects of the present application may or may not have storage media. A host computer communicates with the device through NVMe™ commands. The device may be in one of many SSD form factors, such as U.2 or AIC. The device may be provided as a component in NVMe-enabled computers or NVMe-over-fabrics-enabled systems.