Bridge Device for Adjustable Data Bandwidth in Computer Systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional computer systems with Intel CPUs are unable to meet the high-speed image processing requirements for advanced graphic calculations due to limitations in the PCIe and DMI bus communication.
Innovation Solution
A computer system design that includes a bridge connected to both the north and south bridges, allowing for adjustable output bandwidth and data transformation between DMI and PCIe buses, enabling efficient data transfer and supporting multiple high-speed graphic cards through additional slots.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If conventional PCIe and DMI bus communication is used for data transfer between north bridge and south bridge, then the system structure is simple, but the image processing speed is insufficient for advanced graphic calculations
Solution Approach 1:
A bridge device is introduced as an intermediary component between the north bridge and south bridge. This bridge includes a DMI interface for receiving data from the north bridge, multiple PCIe interfaces for connecting to multiple graphic cards, and a data router for intelligently distributing data to different PCIe interfaces. This intermediary structure enables parallel data transmission to multiple graphic cards, significantly improving image processing speed while maintaining a relatively simple system architecture.
2Productivity
If multiple graphic cards are supported through additional slots, then parallel image processing capability is enhanced, but the data transfer bandwidth requirement increases
Solution Approach 1:
The data transfer path is segmented into multiple independent channels. The bridge device includes a DMI interface receiving data from the north bridge, a data router that divides the incoming data stream into multiple separate data streams, and multiple PCIe interfaces that independently transmit these segmented data streams to different graphic cards. This segmentation allows parallel image processing across multiple cards while managing bandwidth requirements through distributed data transmission.
Solution Approach 2:
The data router within the bridge device dynamically distributes incoming data to different PCIe interfaces based on real-time requirements. The system can flexibly allocate bandwidth resources to different graphic cards as needed, enabling adaptive parallel processing where data transfer capacity is dynamically adjusted to match the actual processing demands of multiple graphic cards.
Data Source
AI summary
A computer system includes a central processing unit (CPU), a north bridge, a south bridge, a bridge and a slot. The north bridge is electrically connected to the CPU. The bridge is electrically connected to the north bridge and the south bridge, and the connector is connected to the bridge. The bridge generates a first data and a second data according to the data packages transmitted from the north bridge and adjusts the output bandwidth of the first data and the second data according to a channel control signal. The south bridge receives or transfers the first data via the bridge so as to communicate with the north bridge. The slot is electrically connected to the bridge and receives or transfers the second data via the bridge so as to communicate with the north bridge.