Patmos: a time-predictable microprocessor

Cyber Physical Systems. Model-Based Design

2020

Self Cite

Cyber-physical systems are systems where the environment interacts with computers (the cyber part) with real-time constraints. Emerging technologies, such as artificial intelligence and machine learning, call for ever-increasing processing power. However, for real-time systems, we need to prove statically that this processing demand can be performed within strict deadlines. This paper explores a time-predictable multicore architecture for those demanding cyber-physical systems. We explore different models of communication between those multiple cores. We compare the message passing model on top of a network-on-chip with message passing on two forms of shared scratchpad memory.

Section: Discussionmentioning

confidence: 99%

Multicore Models of Communication for Cyber-Physical Systems

Cyber Physical Systems. Model-Based Design

2020

Self Cite

“…Hardware Implementation. We have implemented the proposed branch predictor targeting the Patmos processor [20,21]. For the implementation, we use the hardware construction language Chisel [1].…”

Section: Methodsmentioning

confidence: 99%

A time-predictable branch predictor

Proceedings of the 34th ACM/SIGAPP Symposium on Applied Computing

Rouxel

Puaut

2019

Self Cite

Long pipelines need good branch predictors to keep the pipeline running. Current branch predictors are optimized for the average case, which might not be a good fit for real-time systems and worstcase execution time analysis.This paper presents a time-predictable branch predictor co-designed with the associated worst-case execution time analysis. The branch predictor uses a fully-associative cache to track branch outcomes and destination addresses. The fully-associative cache avoids any false sharing of entries between branches. Therefore, we can analyze program scopes that contain a number of branches lower than or equal to the number of branches in the prediction table. Experimental results show that the worst-case execution time bounds of programs using the proposed predictor are lower than using static branch predictors at a moderate hardware cost.

“…We provide prototype implementations of tpIP first in Scala and then in C to demonstrate that it is time-predictable. With a system, such as Patmos [30], it is possible to perform WCET analysis using platin [11].…”

Section: A Overviewmentioning

confidence: 99%

“…Therefore, we restarted the tpIP implementation in C. In that case we can target the time-predictable processor Patmos [30], [32]. For Patmos, we have two WCET analysis tools available: aiT [10] tool from AbsInt and the open-source tool platin [11], which allow static computation of WCET bounds.…”

Section: Prototype Implementationmentioning

confidence: 99%

See 1 more Smart Citation

tpIP: A Time-Predictable TCP/IP Stack for Cyber-Physical Systems

2018 IEEE 21st International Symposium on Real-Time Distributed Computing (ISORC)

Pedersen

2018

Self Cite

Cyber-physical systems are networks of computers connected to the physical world. Often the interaction with the physical world is time critical. In that case computation and communication must be performed in real time. However, a standard implementation of a network stack is hardly time predictable.This paper addresses the challenge of real-time communication for time-critical cyber-physical systems with a time-predictable network stack. We present tpIP, a real-time implementation of the TCP/IP stack. We achieve time predictability by two properties:(1) the application interface is based on polling functions, instead of blocking sockets, that fits for periodic real-time tasks; (2) the implementation is carefully crafted to enable static worst-case execution time analysis of all functions.