Run-time Mapping of Applications to a Heterogeneous SoC

In this paper, we define the problem of spatial mapping. We present reasons why performing spatial mappings at run-time is both necessary and desirable. We propose what is-to our knowledge-the first attempt at a formal description of spatial mappings for the embedded real-time streaming application domain. Thereby, we introduce criteria for a qualitative comparison of these spatial mappings. As an illustration of how our formalization relates to practice, we relate our own spatial mapping algorithm to the formal model.

show abstract

“…Preliminary experiments [23] were promising with respect to the feasibility of run-time spatial mapping in general. Our implementation (see Sect.…”

Section: Necessity and Advantagesmentioning

confidence: 99%

Run-time Spatial Mapping of Streaming Applications to Heterogeneous Multi-Processor Systems

Hölzenspies

Braak

Kuper

et al. 2009

Int J Parallel Prog

View full text Add to dashboard Cite

show abstract

“…The first loop (lines 4-9) analyzes all clusters that have available resources to map the application, selecting the one with the smallest accumulated energy. If there are no clusters with available resources to map the application, a cluster with the smallest accumulated energy is selected, regardless the number of available resources (lines [11][12][13][14][15][16]. Note that the application is mapped in the MPSoC iff the system has available resources for the application.…”

Section: Cluster Selectionmentioning

confidence: 99%

“…The available SP in the list with the smallest TE is selected (lines 8-13). If no SP can be selected, the bounding box is increased by one hop (lines [14][15][16]. This process continues up to find an SP or to visit all SPs of the cluster.…”

Section: Non-initial Task Mappingmentioning

confidence: 99%

Hierarchical energy monitoring for task mapping in many-core systems

Castilhos

Mandelli

Ost

et al. 2016

Journal of Systems Architecture

View full text Add to dashboard Cite

Highlights• Executed at runtime. The proposed approach can better manage time-varying workloads and system changes.• Hierarchical mapping approach. The proposed approach is implemented in a many-core managed in a hierarchical way. Such hierarchical system management improves system scalability by dividing the system into regions, each one with a manager responsible for actions inside it. Further, it reduces mapping decision computational effort, not compromising the system performance.• Induces to a better system reliability. The proposed approach aims to improve energy balancing, which are directly related to a better system reliability.• Hierarchical energy monitoring. The proposed approach does not employ physical sensors in the mapping decision, which increases area and energy costs. The energy data is obtained at runtime using a hierarchical monitoring approach.• Clock-cycle model for validation. The proposed mapping approach is validated in a large many-core system (up to 256 processing elements), modeled in SystemC. ACCEPTED MANUSCRIPT A C C E P T E D M A N U S C R I P T

show abstract

“…To reduce the energy consumption, each process is mapped on the PE that can execute it most efficiently. This so called spatial mapping of processes is performed at run-time by the spatial mapping tool [5]. Run-time mapping offers a number of advantages over design-time mapping.…”

Section: Run-time Mappingmentioning

confidence: 99%

“…In our case, the Montium tiles have single port memories, so we can derive the throughput of the sample application by combining three inequalities (5).…”

Section: B Predicting the Throughput Of A Single Processmentioning

confidence: 99%

Mapping streaming applications on a reconfigurable MPSoC platform at run-time

Hölzenspies

Smit

Kuper

2007

2007 International Symposium on System-on-Chip

View full text Add to dashboard Cite

-In this paper we present a method for mapping streaming applications, with real-time requirements, onto a reconfigurable MPSoC. In this method, the performance of the hardware architecture (the reconfigurable Processing Element, the Network Interface and the Network-on-Chip) is integrated in the performance models of the applications. In this way the performance of the mapped application can be determined at runtime. A predictable NoC (guaranteed bandwidth and bounded latency), a predictable Network Interface and a predictable Processing Element are key requirements for our approach.

show abstract

Run-time Mapping of Applications to a Heterogeneous SoC

Cited by 37 publications

References 3 publications

Run-time Spatial Mapping of Streaming Applications to Heterogeneous Multi-Processor Systems

Run-time Spatial Mapping of Streaming Applications to Heterogeneous Multi-Processor Systems

Hierarchical energy monitoring for task mapping in many-core systems

Mapping streaming applications on a reconfigurable MPSoC platform at run-time

Contact Info

Product

Resources

About