<?xml version="1.0" encoding="UTF-8"?>
<feed xmlns="http://www.w3.org/2005/Atom" xml:lang="en-gb">
	<link rel="self" type="application/atom+xml" href="http://localhost/app.php/feed/topics" />

	<title>Tools and Benchmarks for Real-Time Systems</title>
	<subtitle>ECRTS Community Forum</subtitle>
	<link href="http://localhost/index.php" />
	<updated>2019-06-17T12:06:04+01:00</updated>

	<author><name><![CDATA[Tools and Benchmarks for Real-Time Systems]]></name></author>
	<id>http://localhost/app.php/feed/topics</id>

		<entry>
		<author><name><![CDATA[pagetti]]></name></author>
		<updated>2019-06-17T12:06:04+01:00</updated>

		<published>2019-06-17T12:06:04+01:00</published>
		<id>http://localhost/viewtopic.php?t=137&amp;p=262#p262</id>
		<link href="http://localhost/viewtopic.php?t=137&amp;p=262#p262"/>
		<title type="html"><![CDATA[2019 industrial challenge • Challenge 2019 Solution #4: Addressing Analysis and Partitioning issues for the WATERS 2019 Challenge]]></title>

					<category term="2019 industrial challenge" scheme="http://localhost/viewforum.php?f=43" label="2019 industrial challenge"/>
		
		<content type="html" xml:base="http://localhost/viewtopic.php?t=137&amp;p=262#p262"><![CDATA[
Title: Addressing Analysis and Partitioning issues for the WATERS 2019 Challenge<br>Authors: Daniel Casini, Paolo Pazzaglia, Alessandro Biondi, Giorgio Buttazzo and Marco Di Natale<p>Statistics: Posted by <a href="http://localhost/memberlist.php?mode=viewprofile&amp;u=75">pagetti</a> — Mon Jun 17, 2019 — Replies 1 — Views 4597</p><hr />
]]></content>
	</entry>
		<entry>
		<author><name><![CDATA[pagetti]]></name></author>
		<updated>2019-06-17T12:02:36+01:00</updated>

		<published>2019-06-17T12:02:36+01:00</published>
		<id>http://localhost/viewtopic.php?t=136&amp;p=261#p261</id>
		<link href="http://localhost/viewtopic.php?t=136&amp;p=261#p261"/>
		<title type="html"><![CDATA[2019 industrial challenge • Challenge 2019 Solution #3: An analytical approach for calculating end-to-end response times in autonomous driving appli]]></title>

					<category term="2019 industrial challenge" scheme="http://localhost/viewforum.php?f=43" label="2019 industrial challenge"/>
		
		<content type="html" xml:base="http://localhost/viewtopic.php?t=136&amp;p=261#p261"><![CDATA[
Title: An analytical approach for calculating end-to-end response times in autonomous driving applications<br>Authors: Lukas Krawczyk, Mahmoud Bazzal, Ram Prasath Govindarajan and Carsten Wolff<p>Statistics: Posted by <a href="http://localhost/memberlist.php?mode=viewprofile&amp;u=75">pagetti</a> — Mon Jun 17, 2019 — Replies 2 — Views 5901</p><hr />
]]></content>
	</entry>
		<entry>
		<author><name><![CDATA[pagetti]]></name></author>
		<updated>2019-06-17T11:57:54+01:00</updated>

		<published>2019-06-17T11:57:54+01:00</published>
		<id>http://localhost/viewtopic.php?t=135&amp;p=260#p260</id>
		<link href="http://localhost/viewtopic.php?t=135&amp;p=260#p260"/>
		<title type="html"><![CDATA[2019 industrial challenge • Challenge 2019 Solution #2: Combined Data Transfer Response Time and Mapping Exploration in MPSoCs]]></title>

					<category term="2019 industrial challenge" scheme="http://localhost/viewforum.php?f=43" label="2019 industrial challenge"/>
		
		<content type="html" xml:base="http://localhost/viewtopic.php?t=135&amp;p=260#p260"><![CDATA[
Title: Combined Data Transfer Response Time and Mapping Exploration in MPSoCs<br>Authors: Alexander Diewald, Simon Barner and Selma Saidi<p>Statistics: Posted by <a href="http://localhost/memberlist.php?mode=viewprofile&amp;u=75">pagetti</a> — Mon Jun 17, 2019 — Replies 2 — Views 5621</p><hr />
]]></content>
	</entry>
		<entry>
		<author><name><![CDATA[pagetti]]></name></author>
		<updated>2019-06-17T11:54:56+01:00</updated>

		<published>2019-06-17T11:54:56+01:00</published>
		<id>http://localhost/viewtopic.php?t=134&amp;p=259#p259</id>
		<link href="http://localhost/viewtopic.php?t=134&amp;p=259#p259"/>
		<title type="html"><![CDATA[2019 industrial challenge • Challenge 2019 Solution #1: CPU-GPU Response Time and Mapping Analysis for High-Performance Automotive Systems]]></title>

					<category term="2019 industrial challenge" scheme="http://localhost/viewforum.php?f=43" label="2019 industrial challenge"/>
		
		<content type="html" xml:base="http://localhost/viewtopic.php?t=134&amp;p=259#p259"><![CDATA[
Title CPU-GPU Response Time and Mapping Analysis for High-Performance Automotive Systems<br>Authors Robert Hoettger, Junhyung Ki, The Bao Bui, Burkhard Igel and Olaf Spinczyk<p>Statistics: Posted by <a href="http://localhost/memberlist.php?mode=viewprofile&amp;u=75">pagetti</a> — Mon Jun 17, 2019 — Replies 1 — Views 4873</p><hr />
]]></content>
	</entry>
		<entry>
		<author><name><![CDATA[pagetti]]></name></author>
		<updated>2019-05-29T13:55:22+01:00</updated>

		<published>2019-05-29T13:55:22+01:00</published>
		<id>http://localhost/viewtopic.php?t=133&amp;p=258#p258</id>
		<link href="http://localhost/viewtopic.php?t=133&amp;p=258#p258"/>
		<title type="html"><![CDATA[Regular contributions • Evaluation Framework for Self-Suspending Task Systems]]></title>

					<category term="Regular contributions" scheme="http://localhost/viewforum.php?f=44" label="Regular contributions"/>
		
		<content type="html" xml:base="http://localhost/viewtopic.php?t=133&amp;p=258#p258"><![CDATA[
Title: Evaluation Framework for Self-Suspending Task Systems<br><br>Authors: Georg von der Brüggen, Milad Nayebi, Junjie Shi, Kuan-Hsun Chen and Jian-Jia Chen<br><br>Abstract:<dl class="file"><dt><span class="imageset icon_topic_attach"></span> <a class="postlink" href="http://localhost/download/file.php?id=106&amp;sid=60502f956c0b62a5ccd2ae557192615e">WATERS_2019_paper_8.pdf</a></dt></dl><p>Statistics: Posted by <a href="http://localhost/memberlist.php?mode=viewprofile&amp;u=75">pagetti</a> — Wed May 29, 2019 — Replies 0 — Views 8577</p><hr />
]]></content>
	</entry>
		<entry>
		<author><name><![CDATA[pagetti]]></name></author>
		<updated>2019-05-29T13:49:58+01:00</updated>

		<published>2019-05-29T13:49:58+01:00</published>
		<id>http://localhost/viewtopic.php?t=132&amp;p=257#p257</id>
		<link href="http://localhost/viewtopic.php?t=132&amp;p=257#p257"/>
		<title type="html"><![CDATA[Regular contributions • A time, energy and security coordination approach]]></title>

					<category term="Regular contributions" scheme="http://localhost/viewforum.php?f=44" label="Regular contributions"/>
		
		<content type="html" xml:base="http://localhost/viewtopic.php?t=132&amp;p=257#p257"><![CDATA[
Title: A time, energy and security coordination approach<br><br>Authors: Benjamin Rouxel, Julius Roeder, Sebastian Altmeyer and Clemens Grelck<br><br>Abstract:<dl class="file"><dt><span class="imageset icon_topic_attach"></span> <a class="postlink" href="http://localhost/download/file.php?id=105&amp;sid=60502f956c0b62a5ccd2ae557192615e">WATERS_2019_paper_1.pdf</a></dt></dl><p>Statistics: Posted by <a href="http://localhost/memberlist.php?mode=viewprofile&amp;u=75">pagetti</a> — Wed May 29, 2019 — Replies 0 — Views 7556</p><hr />
]]></content>
	</entry>
		<entry>
		<author><name><![CDATA[pagetti]]></name></author>
		<updated>2019-05-29T13:43:48+01:00</updated>

		<published>2019-05-29T13:43:48+01:00</published>
		<id>http://localhost/viewtopic.php?t=131&amp;p=256#p256</id>
		<link href="http://localhost/viewtopic.php?t=131&amp;p=256#p256"/>
		<title type="html"><![CDATA[Regular contributions • Machine Learning Based Cross-Platform Runtime Prediction]]></title>

					<category term="Regular contributions" scheme="http://localhost/viewforum.php?f=44" label="Regular contributions"/>
		
		<content type="html" xml:base="http://localhost/viewtopic.php?t=131&amp;p=256#p256"><![CDATA[
Title: Machine Learning Based Cross-Platform Runtime Prediction<br><br>Authors: Ahsan Saeed, Falk Wurst, Michael Pressler, Arne Hamann and Dakshina Dasari<br><br>Abstract:<dl class="file"><dt><span class="imageset icon_topic_attach"></span> <a class="postlink" href="http://localhost/download/file.php?id=104&amp;sid=60502f956c0b62a5ccd2ae557192615e">WATERS_2019_paper_2.pdf</a></dt></dl><p>Statistics: Posted by <a href="http://localhost/memberlist.php?mode=viewprofile&amp;u=75">pagetti</a> — Wed May 29, 2019 — Replies 0 — Views 7702</p><hr />
]]></content>
	</entry>
		<entry>
		<author><name><![CDATA[pagetti]]></name></author>
		<updated>2019-05-29T13:41:56+01:00</updated>

		<published>2019-05-29T13:41:56+01:00</published>
		<id>http://localhost/viewtopic.php?t=130&amp;p=255#p255</id>
		<link href="http://localhost/viewtopic.php?t=130&amp;p=255#p255"/>
		<title type="html"><![CDATA[Regular contributions • Interference analysis of shared last-level cache on embedded GP-GPUs with multiple CUDA streams]]></title>

					<category term="Regular contributions" scheme="http://localhost/viewforum.php?f=44" label="Regular contributions"/>
		
		<content type="html" xml:base="http://localhost/viewtopic.php?t=130&amp;p=255#p255"><![CDATA[
Title: Interference analysis of shared last-level cache on embedded GP-GPUs with multiple CUDA streams<br><br>Authors: Gianluca Brilli and Paolo Burgio<br><br>Abstract:<dl class="file"><dt><span class="imageset icon_topic_attach"></span> <a class="postlink" href="http://localhost/download/file.php?id=103&amp;sid=60502f956c0b62a5ccd2ae557192615e">WATERS_2019_paper_3.pdf</a></dt></dl><p>Statistics: Posted by <a href="http://localhost/memberlist.php?mode=viewprofile&amp;u=75">pagetti</a> — Wed May 29, 2019 — Replies 0 — Views 7559</p><hr />
]]></content>
	</entry>
		<entry>
		<author><name><![CDATA[pagetti]]></name></author>
		<updated>2019-05-29T13:20:07+01:00</updated>

		<published>2019-05-29T13:20:07+01:00</published>
		<id>http://localhost/viewtopic.php?t=129&amp;p=254#p254</id>
		<link href="http://localhost/viewtopic.php?t=129&amp;p=254#p254"/>
		<title type="html"><![CDATA[Regular contributions • On an industrial approach for multi-core timing analysis]]></title>

					<category term="Regular contributions" scheme="http://localhost/viewforum.php?f=44" label="Regular contributions"/>
		
		<content type="html" xml:base="http://localhost/viewtopic.php?t=129&amp;p=254#p254"><![CDATA[
Title: On an industrial approach for multi-core timing analysis<br><br>Authors: Francisco J. Cazorla, Enrico Mezzetti, Jaume Abella (BSC); Christos Evripidou, Guillem Bernat (Rapita)<br><br>Abstract:<br>COTS multicores are becoming ubiquitous in critical domains such as automotive and avionics to support efficient and timely execution of advanced software functionalities. Fuelled by the need for higher degree of autonomous decision-making and operation, advanced software functionalities deploy increasingly complex and performance-hungry critical artificial intelligence algorithms to control the whole vehicle. At hardware level, embedded critical industries have been forced to consider multicore accelerator-based processors capable of providing huge levels of performance. The other side of the coin is that high-performance COTS multicores challenge the status quo in timing analysis, for which reason both the research community and the certification/standardization bodies are devoting notable effort to master the complexity of high-performance multicores in terms of software timing. As an example, in the avionics domain, in response to the increased use of multicore processors, the Certification Authorities Software Team (CAST) published the Position Paper CAST-32A named ‘Multi-core Processors’ (often referred to as just ‘CAST-32A’). This document identifies topics that could impact safety, performance and integrity of airborne software systems executing on multicore processors and provides objectives intended to guide the production of safe multicore avionics systems, thus extending DO-178C safety regulation. Similarly, in the automotive domain, functional safety is regulated by the ISO26262 standard, should the processor be multicore or not.<br><br>In this task we will show the joint effort by the Barcelona Supercomuting Center and Rapita Systems Ltd. to set the basis of a viable solution for Multicore Timing Analysis (MTA) to adhere to applicable standards and support documents (e.g. ISO26262, DO-178C and CAST-32A). We will show that the MTA process is a structured framework based on requirements traceability, which allows gathering concrete evidence for the quantification of interference channels and their impact on software timing. The proposed inter-disciplinary framework exploits the combined skills and tools of real-time experts (RPT) and hardware experts (BSC). Originally matured as part of a series of FP7 and H2020 EU projects, the MTA methodology has received a HiPEAC Technology Transfer Award in 2017. Currently, several pilot studies evaluating the technology are in execution with OEM/TIER companies in the automotive and avionics domains. <br><br>More in detail, we will cover the principles driving the proposed MTA approach including: adherence to standards to support traceability of verification requirements; MTA main technological building blocks as BSC’s micro-benchmark technology and Rapita’s Verification Suite; and its specific application steps along the standard ‘V’ software development process. We will also show examples of use of the MTA technology to capture real-time requirements in real high-performance multicore boards.<p>Statistics: Posted by <a href="http://localhost/memberlist.php?mode=viewprofile&amp;u=75">pagetti</a> — Wed May 29, 2019 — Replies 0 — Views 7585</p><hr />
]]></content>
	</entry>
		<entry>
		<author><name><![CDATA[pagetti]]></name></author>
		<updated>2019-05-29T13:16:35+01:00</updated>

		<published>2019-05-29T13:16:35+01:00</published>
		<id>http://localhost/viewtopic.php?t=128&amp;p=253#p253</id>
		<link href="http://localhost/viewtopic.php?t=128&amp;p=253#p253"/>
		<title type="html"><![CDATA[Regular contributions • The challenge of profiling multi-core safety-critical embedded systems]]></title>

					<category term="Regular contributions" scheme="http://localhost/viewforum.php?f=44" label="Regular contributions"/>
		
		<content type="html" xml:base="http://localhost/viewtopic.php?t=128&amp;p=253#p253"><![CDATA[
Title: The challenge of profiling multi-core safety-critical embedded systems<br><br>Authors: Sylvain Girbal and Jimmy Le Rhun<br><br>Abstract: <br>For many decades, the High Performance Computing (HPC) industry has relied for on profiling techniques for debugging and performance optimization purposes, may it be for single-core or multi-core systems.<br><br>On the other hand, the safety-critical industry, with the shift from single-core to multi-core COTS processors for time critical products such as avionics, railway or space computer subsystems is facing new challenges with a trade-off in terms of performance versus predictability.<br><br>In multi-core processors, concurrent accesses to shared hardware resources are generating inter-task or inter-application timing interference, breaking the timing isolation principles required by the qualification / certification standards associated with for such critical software. Several solutions have been proposed in the literature to control or regulate timing interference, but most of these solutions require to perform some level of profiling, or<br>monitoring.<br><br>However, regular profiling techniques relying on interrupts, multi-threading, or OS modules are usually not an option with Real Time Operating Systems (RTOS).<br><br>Additionally, to accurately quantify the maximum inter-application slowdown due to timing interference, we requires some specific co-runners stressing benchmarks dedicated at producing a preset workload on each shared hardware resources, and generate the adhoc traffic.<br><br>In this talk, we present the profiling techniques we are using to evaluate time predictability in the presence of timing interference and ensure real-time behavior of safety-critical applications:<br>1) METrICS, a measurement environment for multi-core time-critical systems running on top of the industry-standard PikeOS RTOS.<br>2) A set of Stressing Benchmarks, dedicated at generating workloads on specific hardware resources.<br>3) xTRACT Visualizer, a GUI allowing us to visualize and to analyze the collected information and measure timing-interference level.<dl class="file"><dt><span class="imageset icon_topic_attach"></span> <a class="postlink" href="http://localhost/download/file.php?id=113&amp;sid=60502f956c0b62a5ccd2ae557192615e">trt-slides-noanim.pdf</a></dt></dl><br /><dl class="file"><dt><span class="imageset icon_topic_attach"></span> <a class="postlink" href="http://localhost/download/file.php?id=107&amp;sid=60502f956c0b62a5ccd2ae557192615e">waters-metrics.pdf</a></dt></dl><p>Statistics: Posted by <a href="http://localhost/memberlist.php?mode=viewprofile&amp;u=75">pagetti</a> — Wed May 29, 2019 — Replies 0 — Views 7667</p><hr />
]]></content>
	</entry>
	</feed>
