Pipelined Multiply-Scan Circuit Using Serial Shift Modules

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current general-purpose computer systems are inefficient in executing multiply-scan operations compared to simpler operations, lacking a special-purpose circuit for pipelined multiply-scan operations.

Innovation Solution

A pipelined multiply-scan apparatus and method utilizing serially-connected left-shift modules and adder modules, with enable inputs to manage the processing of multiply-scan input signals, producing a multiply-scan result efficiently by dedicated hardware configurations such as ASICs or FPGAs.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If a general-purpose computer system executes multiply-scan operations, then the system can perform multiple types of operations, but the processing efficiency is low compared to simpler operations

Engineering Contradiction:
Improveoperation type flexibilityVSAvoidmultiply-scan processing efficiency
Core Design Contradiction:
Adaptability or versatilityVSProductivity

Solution Approach 1:

The multiply-scan operation is divided into multiple pipeline stages including left-shift modules and adder modules that process different bits independently. Each stage handles a specific portion of the computation, allowing parallel processing of multiple input values through the pipeline, thereby improving efficiency while maintaining operational versatility.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The invention transitions from sequential processing in general-purpose systems to a multi-dimensional pipeline architecture where multiple operations occur simultaneously at different stages. The pipeline structure adds a temporal dimension to processing, enabling multiple multiply-scan operations to be in progress at once, significantly improving throughput.

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

2Productivity

If a special-purpose circuit is designed for pipelined multiply-scan operations, then processing efficiency increases, but device complexity increases

Engineering Contradiction:
Improvemultiply-scan processing speedVSAvoidcircuit structure complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The complex multiply-scan operation is segmented into standardized pipeline stages with left-shift modules and adder modules. Each module performs a simple, well-defined function, making the overall complex operation manageable through modular design. This segmentation reduces circuit complexity while maintaining high processing speed through parallel pipeline execution.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The circuit employs dynamic control signals to enable different operational modes (multiply-scan, multiply, scan) in different pipeline stages. This dynamic behavior allows the same hardware structure to perform multiple functions, reducing overall device complexity while maintaining high productivity for the primary multiply-scan operation.

Inventive Principle:
Principle #15Dynamics

3Productivity

If a pipelined circuit processes inputs through multiple stages, then processing capacity increases, but latency for individual operations increases

Engineering Contradiction:
Improvethroughput of operationsVSAvoidlatency per operation
Core Design Contradiction:
ProductivityVSLoss of time

Solution Approach 1:

The pipeline circuit operates with periodic clock cycles, advancing data through stages at regular intervals. This periodic action creates a steady throughput where one result is produced per clock cycle after the pipeline is full, balancing the trade-off between throughput and latency by maintaining a continuous flow of computations.

Inventive Principle:
Principle #19Periodic action

Solution Approach 2:

The pipeline structure performs preliminary processing in early stages (such as left-shifting operations) while subsequent stages handle addition and final computation. This preliminary action in parallel pipeline stages reduces the critical path delay for individual operations while maintaining high throughput through continuous pipeline execution.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS9459832B2Pipelined multiply-scan circuit
Publication Date: 2016.10.04 BANK OF AMERICA CORP
  • US9459832B2 patent drawing
  • US9459832B2 patent drawing
  • US9459832B2 patent drawing

AI summary

A pipelined multiply-scan circuit that may be used for high-performance computing. The pipelined multiply-scan circuit may comprise dedicated hardware configured to execute one or more sub-calculations associated with a pipelined multiply-scan process utilizing one or more serially-connected left-shift modules, and one or more serially-connected adder.