presenter: min yu,lo

10
1 Presenter: Min Yu,Lo 111/06/27 Lauri Matilainen, Erno Salminen, Timo D. Hamalainen, and Marko Hannikainen. 2011 International Conference on Embedded Computer Systems (SAMOS)

Upload: charde-finch

Post on 30-Dec-2015

31 views

Category:

Documents


0 download

DESCRIPTION

National Sun Yat-sen University Embedded System Laboratory Multicore Communications API (MCAPI) implementation on an FPGA multiprocessor. Presenter: Min Yu,Lo. Lauri Matilainen, Erno Salminen, Timo D. Hamalainen, and Marko Hannikainen. - PowerPoint PPT Presentation

TRANSCRIPT

Page 1: Presenter: Min Yu,Lo

1

Presenter: Min Yu,Lo

112/04/19

Lauri Matilainen, Erno Salminen, Timo D. Hamalainen, and Marko Hannikainen. 2011 International Conference on Embedded Computer Systems (SAMOS)

Page 2: Presenter: Min Yu,Lo

112/04/192

The design and implementation of an application programming interface (API) is a trade-off between abstraction it provides and overheads it causes. This paper presents an implementation of Multicore Communications API (MCAPI) on a heterogeneous platform consisting of FPGA-based multiprocessor system-on-chip (MPSoC) connected via PCIe to an external CPU board. The purpose is to provide a unified programming API to different processor and OS types as well as hardware IP-blocks.

Page 3: Presenter: Min Yu,Lo

112/04/193

MCAPI is shown to meet these requirements. We show the MCAPI transport implementation on three processors and two buses, measure the overhead cost, and analyze the effort required to port an application from a PC to the MPSoC. The measured library memory footprint is less than 25KB and the roundtrip communication latency is diminishing low - only few dozen clock cycles - compared to non-MCAPI implementation.

Page 4: Presenter: Min Yu,Lo

112/04/194

Multicore Communications

API Specification(MCAPI

)[3]

Reduced MPI[7][10][14][15]

Cell SDK[8][13][10]

Msg[8]

MPI

This Paper

Comparing API performance

Message - passing

This paper major method

Page 5: Presenter: Min Yu,Lo

112/04/195

Solve heterogeneous architecture◦Different processor◦Different OS type

Feasible performance◦Memory footprintd◦Performance overhead

Page 6: Presenter: Min Yu,Lo

112/04/196

This paper major method◦ Adopted MCAPI for an FPGA-based MPSOC environment.

The FUNCAPI is divided into two layers.◦ Top layers◦ Transport layers

Using virtual nodes for fixed-function units◦ ex : Discrete cosine transform(DCT)

Page 7: Presenter: Min Yu,Lo

112/04/197

MCAPI defines three communications types:◦ Messages

We don’t have to establish a connection first. ◦ Packet channels and Scalar channels

We have to establishing a connection first.

Page 8: Presenter: Min Yu,Lo

112/04/198

An example sequence of MCAPI execution in Funbase software platform.

Page 9: Presenter: Min Yu,Lo

112/04/199

Comparison to other API implementations◦ Performance◦ memory comparison

Page 10: Presenter: Min Yu,Lo

112/04/1910

Conclusions◦ we separated the platform specific parts in a transport

layer, thereby porting MCAPI conveniently to NIOS without OS and PC with Linux.

My Comments◦ This paper is not clear in comparing API architecture

individually.◦ I think the implementation of FUNCAPI is divided into two

layers is very good idea.