Columnar Programmable Fabric With NoC Memory Controller Routing

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Programmable logic devices face challenges in efficiently routing signals and managing data throughput due to limitations in their interconnect systems, leading to performance bottlenecks and reduced configuration flexibility.

Innovation Solution

The integration of a network-on-chip (NoC) interconnect system and programmable interconnect fabric, which selectively routes data between I/O interface circuits and programmable logic, using packetized data protocols to alleviate signal routing burdens and increase data processing speeds.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Speed

If a traditional programmable interconnect fabric is used to route signals between I/O blocks and programmable logic, then the device structure remains simple and manageable, but signal routing latencies increase and data processing speeds decrease due to routing bottlenecks

Engineering Contradiction:
Improvedata processing speedVSAvoidinterconnect system complexity
Core Design Contradiction:
SpeedVSDevice complexity

Solution Approach 1:

The interconnect system is segmented into two distinct parts: a traditional programmable interconnect fabric for general-purpose routing and a novel network-on-chip (NoC) interconnect system for high-speed data transport. This segmentation allows each subsystem to be optimized for its specific function, with the NoC handling bandwidth-intensive operations and the programmable fabric handling flexible routing, thereby increasing data processing speed without overwhelming the control logic.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The NoC interconnect system acts as an intermediary between the I/O blocks and the programmable logic, providing a dedicated high-speed data path that bypasses the limitations of the traditional programmable interconnect fabric. This intermediary structure reduces signal routing latencies by handling data transport independently, allowing the programmable fabric to focus on logic operations rather than data movement bottlenecks.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Adaptability or versatility

If more I/O interface circuits are integrated into the device, then configuration flexibility and functionality increase, but the existing interconnect system becomes overwhelmed and performance bottlenecks occur

Engineering Contradiction:
Improveconfiguration flexibilityVSAvoiddata throughput
Core Design Contradiction:
Adaptability or versatilityVSProductivity

Solution Approach 1:

The patent introduces a new dimension to the interconnect architecture by adding the NoC system with its own dedicated routing resources and data paths. This dimensional expansion allows multiple I/O interface circuits to access programmable logic simultaneously through parallel NoC channels, preventing the single-bus bottleneck of traditional architectures and enabling data throughput to scale with the number of I/O interfaces.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Solution Approach 2:

The NoC interconnect system provides universal high-speed access to programmable logic from any I/O interface circuit in the device. This multi-functional capability allows the same NoC infrastructure to serve multiple I/O blocks concurrently, enabling configuration flexibility to increase without proportionally increasing routing complexity or creating performance bottlenecks.

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

3Ease of operation

If the programmable interconnect fabric is used for all data routing operations, then the system remains uniform and easy to control, but signal routing latencies increase and overall device performance decreases

Engineering Contradiction:
Improverouting control simplicityVSAvoidsignal routing latency
Core Design Contradiction:
Ease of operationVSLoss of time

Solution Approach 1:

The system dynamically selects between two routing paths based on operational requirements: the programmable interconnect fabric for flexible, control-intensive operations and the NoC interconnect system for time-critical data transport. This dynamic allocation allows the system to maintain ease of operation through unified configuration interfaces while reducing signal routing latencies by automatically utilizing the faster NoC path when available.

Inventive Principle:
Principle #15Dynamics

Data Source

PatentUS10963411B1Integrating rows of input/output blocks with memory controllers in a columnar programmable fabric archeture
Publication Date: 2021.03.30 XILINX INC
  • US10963411B1 patent drawing
  • US10963411B1 patent drawing
  • US10963411B1 patent drawing

AI summary

Programmable devices and methods of operation are disclosed. In some embodiments, a programmable device may include programmable logic selectively coupled to a plurality of input/output (I/O) interface circuits by a programmable interconnect fabric and a network-on-chip (NoC) interconnect system. The programmable logic may include configurable logic elements, programmable interconnects, and dedicated circuitry. The programmable interconnects may form part of the programmable interconnect fabric. In some embodiments, the programmable interconnect fabric selectively routes non-packetized data between the programmable logic and a first group of I/O interface circuits, and the NoC interconnect system selectively routes packetized data between the programmable logic and a second group of I/O interface circuits. The NoC interconnect system may operate according to a data packet protocol, and the second group of I/O interface circuits may include memory controllers compatible with the data packet protocol.