Abstract
Future heterogeneous domain-specific systems on a chip (DSSoCs) will be extraordinarily complex in terms of processors, memory hierarchies, and interconnection networks. To manage this complexity, architects, system software designers, and application developers need programming technologies that are flexible, accurate, efficient, and productive. These technologies must be as independent of any one specific architecture as is practical because the sheer dimensionality and scale of the complexity will not allow porting and optimizing applications for each given DSSoC. To address these issues, the authors are developing Cosmic Castle, a performance portable programming toolchain for streaming applications on heterogeneous architectures. The primary focus of Cosmic Castle is on enabling efficient and performant code generation through the smart compiler and intelligent runtime system. This paper presents the preliminary evaluation of the authors' ongoing work toward Cosmic Castle. Specifically, this paper details the code-porting efforts and evaluates various benchmarks on the Qualcomm Snapdragon SoC using tools developed through Cosmic Castle.
Original language | English |
---|---|
Title of host publication | 2021 IEEE High Performance Extreme Computing Conference, HPEC 2021 |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
ISBN (Electronic) | 9781665423694 |
DOIs | |
State | Published - 2021 |
Event | 2021 IEEE High Performance Extreme Computing Conference, HPEC 2021 - Virtual, Online, United States Duration: Sep 20 2021 → Sep 24 2021 |
Publication series
Name | 2021 IEEE High Performance Extreme Computing Conference, HPEC 2021 |
---|
Conference
Conference | 2021 IEEE High Performance Extreme Computing Conference, HPEC 2021 |
---|---|
Country/Territory | United States |
City | Virtual, Online |
Period | 09/20/21 → 09/24/21 |
Funding
This research was supported by the following sources: (1) the Defense Advanced Research Projects Agency Microsystems Technology Office Domain-Specific System-on-Chip Program and (2) DOE Office of Science, Office of Advanced Scientific Computing Research, Scientific Discovery through Advanced Computing program. This research used resources of the Experimental Computing Laboratory (ExCL) at Oak Ridge National Laboratory, which is supported by the US Department of Energy (DOE) Office of Science under contract no. DE-AC05-00OR22725.