Tools and Benchmarks for Real-Time Systems

2019 industrial challenge • Re: Amalthea Model of the Industrial Challenge 2019

2019-10-04T13:05:42+01:00

I am happy to announce the Amalthea model describing the application presented in the Industrial Challenge 2019. Please read the description for details about the application and the modelling concepts. We also provide a small Amalthea example model (CPU_Mapping_Changes) illustrating the transformations involved when moving a task from the GPU to a CPU.
The task "Planner" is activated every 12 ms but its execution time is higher than 12 ms for the A57 and the Denver.
Therefore please change the period of the task (stimuli in the Amalthea model) to 15ms.

I uploaded a model that incorporates this fix (top of the page).

Statistics: Posted by arne.hamann — Fri Oct 04, 2019

2019 industrial challenge • Re: Amalthea Model of the Industrial Challenge 2019

2019-08-29T09:24:34+01:00

I am happy to announce the Amalthea model describing the application presented in the Industrial Challenge 2019. Please read the description for details about the application and the modelling concepts. We also provide a small Amalthea example model (CPU_Mapping_Changes) illustrating the transformations involved when moving a task from the GPU to a CPU.

The task "Planner" is activated every 12 ms but its execution time is higher than 12 ms for the A57 and the Denver.
Therefore please change the period of the task (stimuli in the Amalthea model) to 15ms.

Statistics: Posted by Falk — Thu Aug 29, 2019

2019 industrial challenge • Re: Challenge 2019 Solution #2: Combined Data Transfer Response Time and Mapping Exploration in MPSoCs

2019-07-29T10:25:39+01:00

Dear all,

please excuse the late upload of the slides presented at the WATERS'19 workshop. They are attached.
Note that slide 5 and 7 originally contained animations, so please excuse the slighly wrong layout.

Best regards,

Alexander Diewald

waters2019.pdf

Statistics: Posted by Alexander_Diewald — Mon Jul 29, 2019

2019 industrial challenge • Re: Challenge 2019 Solution #3: An analytical approach for calculating end-to-end response times in autonomous driving a

2019-07-15T09:38:50+01:00

Dear all,

please find attached the slides of our presentation.

Best regards,

Lukas

20190709_WATERS2019.pdf

Statistics: Posted by lukas.krawczyk — Mon Jul 15, 2019

2019 industrial challenge • Re: Challenge 2019 Solution #2: Combined Data Transfer Response Time and Mapping Exploration in MPSoCs

2019-06-26T19:56:26+01:00

Dear all,

please find our approach to address the challenge in the attached pdf file.
Also, a big thanks to the organizers for all the efforts and provisioning the challenge.

Best regards,

Alexander Diewald, Simon Barner and Selma Saidi

FinalVersion.pdf

Statistics: Posted by Alexander_Diewald — Wed Jun 26, 2019

2019 industrial challenge • Re: Challenge 2019 Solution #3: An analytical approach for calculating end-to-end response times in autonomous driving a

2019-06-26T13:51:08+01:00

Dear all,

Please find attached our contribution to the WATERS2019 challenge.

Best Regards,
Lukas Krawczyk, Mahmoud Bazzal, Ram Prasath Govindarajan and Carsten Wolff

paper_final.pdf

Statistics: Posted by lukas.krawczyk — Wed Jun 26, 2019

2019 industrial challenge • Re: Challenge 2019 Solution #1: CPU-GPU Response Time and Mapping Analysis for High-Performance Automotive Systems

2019-06-26T10:11:38+01:00

Hi everyone,

please find attached our paper addressing the WATERS2019 challenge.
We hope you do not mind the additional (seventh) page.

Looking forward to meeting you in Stuttgart and best regards,
Robert

waters19_CPU-GPU_final.pdf

Statistics: Posted by robert — Wed Jun 26, 2019

2019 industrial challenge • Re: Challenge 2019 Solution #4: Addressing Analysis and Partitioning issues for the WATERS 2019 Challenge

2019-06-25T15:58:32+01:00

Dear all,

Please find attached our contribution to the WATERS 2019 Challenge.

Best Regards,
Daniel Casini, Paolo Pazzaglia, Alessandro Biondi, Giorgio Buttazzo and Marco Di Natale

WATERS2019_Final.pdf

Statistics: Posted by d.casini — Tue Jun 25, 2019

2019 industrial challenge • Challenge 2019 Solution #4: Addressing Analysis and Partitioning issues for the WATERS 2019 Challenge

2019-06-17T12:06:04+01:00

Title: Addressing Analysis and Partitioning issues for the WATERS 2019 Challenge
Authors: Daniel Casini, Paolo Pazzaglia, Alessandro Biondi, Giorgio Buttazzo and Marco Di Natale

Statistics: Posted by pagetti — Mon Jun 17, 2019

2019 industrial challenge • Challenge 2019 Solution #3: An analytical approach for calculating end-to-end response times in autonomous driving appli

2019-06-17T12:02:36+01:00

Title: An analytical approach for calculating end-to-end response times in autonomous driving applications
Authors: Lukas Krawczyk, Mahmoud Bazzal, Ram Prasath Govindarajan and Carsten Wolff

Statistics: Posted by pagetti — Mon Jun 17, 2019

2019 industrial challenge • Challenge 2019 Solution #2: Combined Data Transfer Response Time and Mapping Exploration in MPSoCs

2019-06-17T11:57:54+01:00

Title: Combined Data Transfer Response Time and Mapping Exploration in MPSoCs
Authors: Alexander Diewald, Simon Barner and Selma Saidi

Statistics: Posted by pagetti — Mon Jun 17, 2019

2019 industrial challenge • Challenge 2019 Solution #1: CPU-GPU Response Time and Mapping Analysis for High-Performance Automotive Systems

2019-06-17T11:54:56+01:00

Title CPU-GPU Response Time and Mapping Analysis for High-Performance Automotive Systems
Authors Robert Hoettger, Junhyung Ki, The Bao Bui, Burkhard Igel and Olaf Spinczyk

Statistics: Posted by pagetti — Mon Jun 17, 2019

2019 industrial challenge • Re: Memory contention model (example)

2019-05-14T16:17:26+01:00

Hello,
thank you very much for your answer!

I am currently analyzing the Jetson TX2 platform and have another question:
Does anyone eventually know if the GPU of Jetson TX2 has accessible hardware performance counters and if yes, how to access them?

Many thanks in advance.

Best regards

Hi,

We have never profiled an application at that level but as far as I know you can access it by using this API https://docs.nvidia.com/cuda/cupti/inde ... r_overview

Nacho

Statistics: Posted by Nacho_S — Tue May 14, 2019

2019 industrial challenge • Re: Memory contention model (example)

2019-05-07T14:25:25+01:00

Hello,
thank you very much for your answer!

I am currently analyzing the Jetson TX2 platform and have another question:
Does anyone eventually know if the GPU of Jetson TX2 has accessible hardware performance counters and if yes, how to access them?

Many thanks in advance.

Best regards

Statistics: Posted by lkrupp — Tue May 07, 2019

2019 industrial challenge • Re: Memory contention model (example)

2019-04-29T16:49:45+01:00

Hi,
the document describing the memory latency measurements states that LMBench (LAT_MEM_RD as specified in detail above) in conjuction with a custom-made program is used. I am interested in how exactly the latency is measured. Therefore, my questions are:

1) Are the measurements on the Tegra platforms conducted using standard Linux for Tegra or was the Linux kernel adapted?
2) In case of standard L4T: Are timing primitives of the OS (like gettime() or clocks()) used and how do you account for the overhead of the OS?

Thank you in advance!

Best regards,

Lukas Krupp

Hi,
>> 1) Are the measurements on the Tegra platforms conducted using standard Linux for Tegra or was the Linux kernel adapted?
The experiments have been done by using the standard Linux for Tegra.

>> 2) In case of standard L4T: Are timing primitives of the OS (like gettime() or clocks()) used and how do you account for the overhead of the OS?
We used OS timing primitives, unfortunately we do not take into account the OS overhead, however, we tried to minimize this overhead as much as possible by launching the tasks in isolation (with synthetic parameters as input), maximum OS priority, etc...
Nacho.

Statistics: Posted by Nacho_S — Mon Apr 29, 2019