IP Library Granted Patent US 7,797,647
Granted Patent B2
US 7,797,647 · App. 10/551,837 · Granted Sep 14, 2010

Circuit having hardware threading

Assignee: Tufts University
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 7,797,647
App. No.
10/551,837
Granted
Sep 14, 2010
Kind
B2
Abstract

Hardware threading optimizes use of hardware resources in a dynamic workload environment. Unutilized hardware resources are dynamically borrowed to increase throughput performance and/or power savings by enabling parallel processing of application pipeline stages.

Claims (18)

1. A computer-implemented method of scheduling processing in a hardware threaded circuit, comprising:

in a processor, receiving inputs corresponding to unthreaded processing of an application;

receiving and storing in a memory information including processing element resources, a number of processing elements, and a window size corresponding to a number of downstream processing states to be examined;

generating a hardware threaded schedule for processing the application with at least first and second one of the processing elements being interconnected to enable dynamic resource sharing;

synthesizing the hardware threaded schedule to an Application Specific Circuit (ASC); and

synthesizing the hardware schedule to maximize throughput,

wherein the first and second processing elements each include a first type of resource and a second type of resource and a multiplexer such that the interconnection includes at least one input signal being provided to the first type of resource in the first and second processing elements.

2. The method according to claim 1 , further including synthesizing the hardware threaded schedule to reduce power consumption.

3. The method according to claim 1 , further including receiving resource constraint information for the processing elements.

4. The method of claim 1 , wherein the at least first and second one of the processing elements are multiplexed.

5. A hardware threaded circuit system, comprising:

an input to receive inputs corresponding to unthreaded processing of an application;

a memory to store information including processing element resources, a number of processing elements, and a window size corresponding to a number of downstream processing states to be examined;

a task manager coupled to the memory for synthesizing a hardware threaded schedule to an Application Specific Circuit (ASC) and maximizing throughput; and

a plurality of the processing elements coupled to the task manager, wherein first and second ones of the plurality of processing elements are interconnected for hardware threaded processing to enable dynamic borrowing of processing resources associated with the second one of the plurality of processing elements by the first one of the plurality of processing elements,

wherein the first and processing elements each include a first type of resource and second type of resource and a multiplexer such that the interconnection includes at least one input signal being provided to the first type of resource in the first and second processing elements.

6. The system according to claim 5 , wherein the circuit reduces power consumption compared to a non-threaded processing for substantially similar system wait times.

7. The system according to claim 5 , wherein the interconnection includes a connection from an output of the second processing element first type of resource to the first processing element.

Assignments (2)
CONFIRMATORY LICENSE Recorded Jun 18, 2015
From: TUFTS UNIVERSITY
To: NATIONAL SCIENCE FOUNDATION
Reel/Frame 035925/0401 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 3, 2005
From: HASSOUN, SOHA M. N.; SWAHN, BRIAN G.
To: TUFTS UNIVERSITY
Reel/Frame 017860/0319 →
Continuity (2)
Provisional Application 6046008000 · Apr 3, 2003
Related Publication 20060225002A1 · Oct 5, 2006