Pipelined Interconnect Clocking for High-Speed Routing

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

As integrated circuits continue to increase functionality per unit area, existing routing architectures struggle to support high-speed connections across the die, leading to performance bottlenecks due to large critical paths between sequential elements.

Innovation Solution

The implementation of pipelined interconnect circuitry with register pipelining and advanced clock selection circuitry, including a clock tree and multiplexers, to facilitate efficient clock signal distribution and routing across the integrated circuit, allowing for high-speed connections and reduced latency.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If register pipelining is implemented to increase clock frequency and throughput, then performance is improved, but device complexity and manufacturing effort increase significantly

Engineering Contradiction:
ImprovethroughputVSAvoidcomplexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The routing architecture is segmented into multiple pipelines with registers inserted between routing segments. This divides the long critical path into shorter segments, allowing each segment to be clocked independently at higher frequencies while reducing the overall path delay.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent implements dynamic clock selection circuitry that can selectively enable or disable pipeline registers based on the specific routing path and timing requirements. This dynamic control allows the system to adapt the pipeline depth to match the actual critical path length, optimizing performance while minimizing unnecessary complexity.

Inventive Principle:
Principle #15Dynamics

2Productivity

If synchronous elements are placed far apart to increase functionality per unit area, then integration density is improved, but interconnect delay increases leading to performance bottlenecks

Engineering Contradiction:
Improvefunctionality per unit areaVSAvoidinterconnect speed
Core Design Contradiction:
ProductivityVSSpeed

Solution Approach 1:

The long interconnect path between distant synchronous elements is divided into multiple shorter routing segments with pipeline registers inserted at strategic points. This segmentation reduces the delay of each individual segment while maintaining the overall functionality, allowing distant elements to communicate effectively despite the physical distance.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

Pipeline registers act as intermediary elements between distant synchronous elements, providing intermediate storage and synchronization points. These intermediaries break up the long critical path into manageable segments, enabling high-speed communication across the integrated circuit despite large physical separations between functional blocks.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Speed

If existing routing architectures are used to connect distant synchronous elements, then routing simplicity is maintained, but high-speed connection capability is insufficient

Engineering Contradiction:
Improveconnection speedVSAvoidrouting architecture complexity
Core Design Contradiction:
SpeedVSDevice complexity

Solution Approach 1:

The routing architecture incorporates dynamic clock selection circuitry that can adaptively choose the appropriate clock signal and pipeline depth based on the specific routing requirements. This dynamic adaptation allows the same physical routing infrastructure to support both high-speed long-distance connections and lower-speed local connections, optimizing performance for each case without requiring completely separate routing paths.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The enhanced routing architecture is designed to be universal, supporting both pipelined and non-pipelined operations through the same physical infrastructure. The clock selection circuitry can configure the routing resources to function in different modes depending on the timing requirements, making the architecture versatile enough to handle various connection scenarios without increasing physical complexity.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentEP2871550B1Clocking for pipelined routing
Publication Date: 2019.11.13 ALTERA CORP
  • EP2871550B1 patent drawingFigure 1
  • EP2871550B1 patent drawingFigure 2
  • EP2871550B1 patent drawingFigure 3A

AI summary

An integrated circuit may have pipelined programmable interconnects that are configured to select between a routing signal stored in a register and the identical routing signal bypassing the register. The pipelined programmable interconnect may send the selected routing signal over a wire to the next pipelined programmable interconnect circuitry. The integrated circuit may also have clock routing circuitry to select respective clock signals for the registers in the different pipelined programmable interconnects. The clock routing circuitry may include first interconnects that convey region clocks, second interconnects that conveys routing clocks, a first selector circuit to select routing clocks among the region clocks, and a second selector circuit to select routing clocks for the respective registers."