Fine-grained conditional dispatching
Abstract
Techniques for executing workgroups are provided. The techniques include executing, for a first workgroup of a first kernel dispatch, a workgroup dependency instruction that includes an indication to prioritize execution of a second workgroup of a second kernel dispatch, and in response to the workgroup dependency instruction, dispatching the second workgroup of the second kernel dispatch prior to dispatching a third workgroup of the second kernel dispatch, wherein no workgroup dependency instruction including an indication to prioritize execution of the third workgroup has been executed.
- Inventors:
- Issue Date:
- Research Org.:
- Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States); Advanced Micro Devices, Inc., Santa Clara, CA (United States)
- Sponsoring Org.:
- USDOE
- OSTI Identifier:
- 2293834
- Patent Number(s):
- 11809902
- Application Number:
- 17/031,424
- Assignee:
- Advanced Micro Devices, Inc. (Santa Clara, CA)
- DOE Contract Number:
- AC52-07NA27344; B620717
- Resource Type:
- Patent
- Resource Relation:
- Patent File Date: 09/24/2020
- Country of Publication:
- United States
- Language:
- English
Citation Formats
Dutu, Alexandru, Chow, Marcus Nathaniel, Sinclair, Matthew D., Beckmann, Bradford M., and Wood, David A. Fine-grained conditional dispatching. United States: N. p., 2023.
Web.
Dutu, Alexandru, Chow, Marcus Nathaniel, Sinclair, Matthew D., Beckmann, Bradford M., & Wood, David A. Fine-grained conditional dispatching. United States.
Dutu, Alexandru, Chow, Marcus Nathaniel, Sinclair, Matthew D., Beckmann, Bradford M., and Wood, David A. Tue .
"Fine-grained conditional dispatching". United States. https://www.osti.gov/servlets/purl/2293834.
@article{osti_2293834,
title = {Fine-grained conditional dispatching},
author = {Dutu, Alexandru and Chow, Marcus Nathaniel and Sinclair, Matthew D. and Beckmann, Bradford M. and Wood, David A.},
abstractNote = {Techniques for executing workgroups are provided. The techniques include executing, for a first workgroup of a first kernel dispatch, a workgroup dependency instruction that includes an indication to prioritize execution of a second workgroup of a second kernel dispatch, and in response to the workgroup dependency instruction, dispatching the second workgroup of the second kernel dispatch prior to dispatching a third workgroup of the second kernel dispatch, wherein no workgroup dependency instruction including an indication to prioritize execution of the third workgroup has been executed.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2023},
month = {11}
}
Works referenced in this record:
Adaptive Task Aggregation for High-Performance Sparse Solvers on GPUs
conference, September 2019
- Helal, Ahmed E.; Aji, Ashwin M.; Chu, Michael L.
- 2019 28th International Conference on Parallel Architectures and Compilation Techniques (PACT)
Gravel: fine-grain GPU-initiated network messages
conference, November 2017
- Orr, Marc S.; Che, Shuai; Beckmann, Bradford M.
- SC '17: The International Conference for High Performance Computing, Networking, Storage and Analysis, Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis
Implementation of Strassen's algorithm for matrix multiplication
conference, November 1996
- Huss-Lederman, Steven; Jacobson, Elaine M.; Tsao, Anna
- Proceedings of the 1996 ACM/IEEE conference on Supercomputing
OptiX: a general purpose ray tracing engine
journal, July 2010
- Parker, Steven G.; Robison, Austin; Stich, Martin
- ACM Transactions on Graphics, Vol. 29, Issue 4
The iray light transport simulation and rendering system
conference, July 2017
- Keller, Alexander; Wächter, Carsten; Raab, Matthias
- ACM SIGGRAPH 2017 Talks
Fine-grain task aggregation and coordination on GPUs
conference, June 2014
- Orr, Marc S.; Beckmann, Bradford M.; Reinhardt, Steven K.
- 2014 ACM/IEEE 41st International Symposium on Computer Architecture (ISCA)