IP Library Granted Patent US 10,073,810
Granted Patent B2
US 10,073,810 · App. 15/250,902 · Granted Sep 11, 2018

Parallel processing device and parallel processing method

Inventor: Kiyoshi Miyazaki (Machida, JP)
Assignee: FUJITSU LIMITED
G06F15/7889
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 10,073,810
App. No.
15/250,902
Granted
Sep 11, 2018
Kind
B2
Abstract

A parallel processing device includes processors that execute respective processes and cause an FPGA circuit to process part of the processes. A first processor of the processors requests the FPGA to execute processing of part of a first process currently being executed, and transitions to a wait state of processing completion of the FPGA and, when the first processor initiates execution of a second process, the first processor sends movement-destination processor information to the FPGA, and also sends, to a movement-destination processor, environment setting information for the first process after completion in the FPGA. And the movement-destination processor performs setting of the environment setting information during the execution of the processing of the part of the first process by the FPGA circuit, and continues the processing of the first process in response to a processing completion notification from the FPGA circuit.

Claims (40)

1. A parallel processing device comprising:

a plurality of processors that execute respective processes and cause a field programmable gate array (FPGA) circuit to process part of the processes, wherein

a first processor of the plurality of processors requests the FPGA circuit to execute processing of part of a first process currently being executed by the first processor,

when the first processor transitions to an execution of a second process, the first processor

saves environment setting information including data stored in internal registers of the first processor,

sends movement-destination processor information including an identifier of a movement-destination processor to the FPGA circuit, and

causes the movement-destination processor to obtain the saved environment setting information for continuous processing of the first process, and

the movement-destination processor

performs setting the environment setting information in the movement-destination processor during the execution of the processing of the part of the first process by the FPGA circuit, and

continues the processing of the first process based on the environment setting information in response to a processing completion notification from the FPGA circuit.

2. The parallel processing device according to claim 1 , further comprising:

the FPGA circuit that processes the part of the processes executed by at least one of the plurality of processors.

3. The parallel processing device according to claim 2 , wherein

the FPGA circuit sends the processing completion notification to the movement-destination processor of the movement-destination processor information.

4. The parallel processing device according to claim 2 , further comprising:

a plurality of processing completion notification signal lines that transmit the processing completion notification between the FPGA circuit and the plurality of processors, wherein

the FPGA circuit transmits the processing completion notification via any of the plurality of the processing completion notification signal lines.

5. The parallel processing device according to claim 4 , wherein

the first processor sends information on a request-source processor to the FPGA circuit when the first processor requests the FPGA circuit to execute processing of part of the process currently being executed, and

the first processor transfers the processing completion notification from the FPGA circuit to the movement-destination processor when the first processor initiates the execution of the second process.

6. The parallel processing device according to claim 1 , wherein

the first processor sends information on a request-source processor to the FPGA circuit when the first processor requests the FPGA circuit to execute the processing of the part of the first process, and transitions to a wait state of the processing completion of the FPGA circuit for a first predetermined time period.

7. The parallel processing device according to claim 6 , wherein

the first processor does not initiate the execution of the second process during the first predetermined time period.

8. The parallel processing device according to claim 1 , wherein

each of the plurality of processors repeatedly executes one process of the plurality of processes for a second predetermined time period and then executes another process for the second predetermined time period.

9. The parallel processing device according to claim 1 , wherein

each of the plurality of processors activates and executes, when the processor receives an interrupt signal during execution of any process, another process having a priority higher than a priority of the process currently being executed, and stops the execution of the process currently being executed.

10. The parallel processing device according to claim 1 , wherein

the movement-destination processor transitions to a wait state of the processing completion of the FPGA circuit after completion of the setting of the environment setting information.

11. The parallel processing device according to claim 1 , wherein

the first processor sends information on the first process to the FPGA circuit when the first processor requests the FPGA to execute the processing of the part of the first process.

12. A method of a parallel process of a parallel processing device including a plurality of processors that execute respective processes and cause a field programmable gate array (FPGA) circuit to process part of the processes, the method comprising:

requesting, by a first processor of the plurality of processors, the FPGA circuit to execute processing of part of a first process currently being executed by the first processor;

when the first processor transitions to an execution of a second process after the requesting,

saving, by the first processor, environment setting information including data stored in internal registers of the first processor,

sending, by the first processor, movement-destination processor information including an identifier of a movement-destination processor to the FPGA circuit, and

causing, by the first processor, the movement-destination processor to obtain the saved environment setting information for continuous processing of the first process;

performing, by the movement-destination processor, setting the environment setting information in the movement-destination processor during the execution of the processing of the part of the first process by the FPGA circuit; and

continuing, by the movement-destination processor, the processing of the first process based on the environment setting information in response to a processing completion notification from the FPGA circuit.

Assignments (5)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 26, 2024
From: YAMATO KANZAI LIMITED
To: FCNT LLC
Reel/Frame 066908/0856 →
CHANGE OF NAME Recorded Mar 21, 2024
From: FCNT LIMITED
To: YAMATO KANZAI LIMITED
Reel/Frame 066854/0942 →
CHANGE OF NAME Recorded Mar 19, 2024
From: FUJITSU CONNECTED TECHNOLOGIES LIMITED
To: FCNT LIMITED
Reel/Frame 066832/0399 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 20, 2018
From: FUJITSU LIMITED
To: FUJITSU CONNECTED TECHNOLOGIES LIMITED
Reel/Frame 047609/0349 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 30, 2016
From: MIYAZAKI, KIYOSHI
To: FUJITSU LIMITED
Reel/Frame 039573/0166 →
Priority Claims (1)
JP 2015-199148 · Oct 7, 2015 · national
Continuity (1)
Related Publication 20170102954A1 · Apr 13, 2017