Dispatching function calls across accelerator devices
In one embodiment, a computer-implemented method for dispatching a function call includes receiving, at a supervisor processing element (PE) and from an origin PE, an identifier of a target device, a stack frame of the origin PE, and an address of a function called from the origin PE. The supervisor PE allocates a target PE of the target device. The supervisor PE copies the stack frame of the origin PE to a new stack frame on a call stack of the target PE. The supervisor PE instructs the target PE to execute the function. The supervisor PE receives a notification that execution of the function is complete. The supervisor PE copies the stack frame of the target PE to the stack frame of the origin PE. The supervisor PE releases the target PE of the target device. The supervisor PE instructs the origin PE to resume execution of the program.
- Research Organization:
- International Business Machines Corp., Armonk, NY (United States)
- Sponsoring Organization:
- USDOE
- DOE Contract Number:
- B599858
- Assignee:
- INTERNATIONAL BUSINESS MACHINES CORPORATION (Armonk, NY)
- Patent Number(s):
- 9,547,526
- Application Number:
- 14/744,048
- OSTI ID:
- 1339621
- Resource Relation:
- Patent File Date: 2015 Jun 19
- Country of Publication:
- United States
- Language:
- English
Signal processing device accessible as memory
|
patent | October 2002 |
Similar Records
Accessing global data from accelerator devices
Accessing global data from accelerator devices