Interconnect Data Request Compression Using Persistent Frame Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In communication channel interconnects like chip-to-chip and die-to-die connections, bandwidth is limited due to the transmission of duplicate information across multiple frames, leading to wasted bandwidth and increased latency.
Innovation Solution
Implementing a persistent data component that extracts and reinserts persistent data within frames, using identifiers to reduce redundant data transmission and increase bandwidth efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If data is transmitted across a datalink in multiple frames, then data transfer is facilitated, but bandwidth is wasted due to duplicate information in each frame
Solution Approach 1:
The patent extracts persistent data (originator ID, destination ID, tag) from each frame and stores it in a persistent data structure at the transmitting device. Only the data payload is transmitted in subsequent frames after the initial full frame, reducing redundant data transmission and improving bandwidth utilization.
Solution Approach 2:
The patent creates a copy of the persistent data structure at the receiving device that mirrors the transmitter's persistent data structure. This allows the receiver to reconstruct complete frames from compressed transmissions by combining received payloads with local persistent data, eliminating the need to retransmit duplicate identification information.
2Reliability
If complete frames are transmitted each time, then data integrity is maintained, but frame size is large and latency increases
Solution Approach 1:
The patent segments the frame transmission into two parts: an initial complete frame that establishes the persistent data context, and subsequent frames that transmit only the data payload. This segmentation maintains data integrity through the persistent data structure while reducing latency in subsequent transmissions by eliminating redundant header information.
3Loss of energy
If persistent data is extracted and stored, then bandwidth is improved, but device complexity increases
Solution Approach 1:
The persistent data structure serves multiple functions: it stores identification information for bandwidth compression, provides context for reconstructing compressed frames at the receiver, and maintains data integrity across multiple transmissions. This multi-functionality justifies the added complexity by delivering significant bandwidth efficiency gains.
Data Source
AI summary
A includes a memory and one or more processing devices operatively coupled to the memory. The one or more processing devices to determine that a data request comprises first persistent data, remove the first persistent data from the data request to obtain first dynamic data, generate first modification data representing the first persistent data, combine the first dynamic data and first modification data to obtain a first modified data request, and cause the first modified data request to be transmitted to a second device over a communication link.


