Interconnect Data Collator for Ordered Data Throughput
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing processing apparatuses face bottlenecks in data provision to master devices due to limited throughput and increased area requirements, particularly when data blocks need to be provided in a specific order, as the buffer size increases.
Innovation Solution
An interconnect with a data collator that allocates buffer space only when necessary, allowing for out-of-order data delivery and reordering before providing it to the master device, thereby reducing the time buffer space is allocated and improving throughput.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the buffer size is increased to provide data blocks in the required order, then the area requirements of the interconnect increase, but the potential throughput of data through the interconnect is limited by the buffer size
Solution Approach 1:
The buffer size is made dynamic rather than static. The data collator allocates buffer space on-demand based on the specific data request and availability, rather than provisioning a large fixed buffer. This allows the buffer to expand and contract dynamically, improving throughput without requiring large permanent area allocation.
Solution Approach 2:
The data collator issues a data pull request to allocate buffer space before the actual data is transferred. This preliminary action allows the buffer allocation to be timed precisely when needed, rather than holding buffer space open from the moment of request, thereby improving throughput without requiring excessive buffer area.
2Productivity
If the buffer size is increased to buffer data blocks, then the area requirements of the interconnect increase, but the throughput is limited by the buffer size
Solution Approach 1:
The data collator acts as an intermediary between the master device and the buffer storage. It manages the buffer allocation process by issuing data pull requests and receiving confirmations, simplifying the overall buffer management while improving throughput through coordinated data transfer.
Solution Approach 2:
The system implements a feedback mechanism where the data collator issues a data pull request, receives a confirmation that buffer space is allocated, and then provides the requested data. This feedback loop ensures efficient buffer utilization and improves throughput without excessive complexity.
3Reliability
If buffer space is allocated early to ensure data blocks are available in order, then the buffer occupancy increases, but the throughput is limited by the allocated buffer space
Solution Approach 1:
The system changes the timing parameter of buffer allocation. Instead of allocating buffer space immediately when a data request is received, the buffer is allocated only when the data collator issues a data pull request and receives confirmation. This parameter change maintains data order reliability while improving throughput by reducing buffer occupancy time.
Data Source
AI summary
Aspects of the present disclosure relate to an interconnect comprising an interface to couple to a master device, the interface comprising buffer storage. The interface is configured to receive a request from the master device for data comprising a plurality of data blocks, the master device requiring the data blocks in a defined order. A data collator is configured to: receive the request; issue a data pull request to cause the interface to allocate buffer space in the buffer storage for buffering the requested data; and responsive to receiving a confirmation that the buffer space is allocated, provide the requested data to the buffer storage. The interface is configured to employ the buffer storage to enable re-ordering of the plurality of data blocks of the requested data, prior to outputting the plurality of data blocks to the master device; and output the plurality of data blocks to the master device in the defined order.