Flexible Sensor Hub Routing to Cut DRAM Bandwidth Delays
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
SoC devices in automobiles face significant processing burdens due to the increasing number and type of sensors, particularly in safety systems, leading to delays and DRAM bandwidth issues as multiple processes retrieve and reformat sensor data independently.
Innovation Solution
A hub system within the SoC distributes sensor data directly to appropriate recipients in the desired format, reducing the need for intermediate storage and reformatting in DRAM, using a demultiplexer to filter and multiplexers to route data to specific formatters, thereby enhancing data processing efficiency and reducing delays.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If sensor data is stored in DRAM and each recipient retrieves and reformats data independently, then data can be accessed by multiple processes, but processing delays increase and DRAM bandwidth is consumed
Solution Approach 1:
The hub performs preliminary actions by pre-formatting sensor data into multiple different formats and making these formatted versions available simultaneously to multiple recipients. This eliminates the need for each recipient to independently retrieve and reformat data, thereby reducing processing delays while maintaining data access flexibility.
Solution Approach 2:
The hub acts as an intermediary component between sensors and multiple recipients. It receives raw sensor data, formats it according to different recipients' requirements, and distributes the pre-formatted data. This intermediary function eliminates the need for recipients to access DRAM and perform their own reformatting operations.
2Adaptability or versatility
If multiple processes independently retrieve and reformat sensor data from DRAM, then each process can handle its own formatting requirements, but DRAM bandwidth constraints are exceeded
Solution Approach 1:
The hub performs preliminary formatting of sensor data into multiple different formats simultaneously before distribution. This allows multiple recipients to receive data in their required formats without needing to retrieve and reformat independently, thereby reducing DRAM bandwidth consumption while maintaining format customization capabilities.
Solution Approach 2:
The hub merges multiple formatting operations into a single centralized processing stage. Instead of each recipient performing separate retrieve and reformat operations that consume DRAM bandwidth, the hub combines all formatting requirements and produces multiple formatted versions in one unified process.
3Productivity
If a hub distributes data directly to recipients in desired format, then processing delays are reduced, but device complexity increases
Solution Approach 1:
The hub is designed as a universal component that can handle multiple sensor types and produce multiple output formats simultaneously. By consolidating formatting and distribution functions in a single multi-functional device, the system improves productivity without proportionally increasing overall system complexity.
Data Source
AI summary
A hub that receives sensor data streams and then distributes the data streams to the various systems that use the sensor data. A demultiplexer (demux) receives the streams, filters out undesired streams and provides desired streams to the proper multiplexer (mux) or muxes of a series of muxes. Each mux combines received streams and provides an output stream to a respective formatter or output block. The formatter or output block is configured based on the destination of the mux output stream, such as an image signal processor, a processor, memory or external transmission. The output block reformats the received stream to a format appropriate for the recipient and then provides the reformatted stream to that recipient.