1 st meeting of project EES 5653 Quality

1 st meeting of project EES. 5653 Quality of Service for In-Home Digital Networks PROGRESS PROJECT EES. 5653 Terminal Qo. S M. A. Albu Philips Research 6/17/2021 Alina Albu, m. a. albu@tue. nl TU/e Computer Science, System Architecture and Networking Philips Research Laboratories Eindhoven 1

1 st meeting of project EES. 5653 Contents • Summary work • Terminal Qo. S • Collaboration with MRM project • Number of context switches estimation method • Future work Philips Research 6/17/2021 Alina Albu, m. a. albu@tue. nl TU/e Computer Science, System Architecture and Networking Philips Research Laboratories Eindhoven 2

1 st meeting of project EES. 5653 Summary work • Literature survey on Qo. S work • Qo. S overview and classification of Qo. S improvement techniques – internal report • Number of context switches estimation method: – 1 st approach: statistical approach – 2 nd approach: min-max method – 3 rd approach: average method Philips Research 6/17/2021 Alina Albu, m. a. albu@tue. nl TU/e Computer Science, System Architecture and Networking Philips Research Laboratories Eindhoven 3

1 st meeting of project EES. 5653 Terminal Qo. S • Qo. S determined by resource management of the system in discussion • Terminal resources under investigation: – CPU, – Memory, – Bus Philips Research 6/17/2021 Alina Albu, m. a. albu@tue. nl TU/e Computer Science, System Architecture and Networking Philips Research Laboratories Eindhoven 4

1 st meeting of project EES. 5653 Collaboration with MRM project • Why MRM? – Qo. S related closely to resource management. – MRM is concerned with resources management aspects in the context of a terminal. – MRM provides opportunities for inspiration, validation of my work • Aim MRM: – provide methods and means for an integrated approach to resource management in multi-resource systems. • The integrated approach has to meet at least the following requirements: – The resource management infrastructure should be able to provide resource guarantees to the building blocks of application functionality. – Individual building blocks should be able to limit or prevent resource insufficiencies, by dealing with insufficient resources in a graceful and predictable way. Philips Research 6/17/2021 Alina Albu, m. a. albu@tue. nl TU/e Computer Science, System Architecture and Networking Philips Research Laboratories Eindhoven 5

1 st meeting of project EES. 5653 Collaboration with MRM project Rationale Þ This leads to the need for developing methods for estimating the necessary of resources for the building blocks of application but also for predicting resources necessary for the composed execution of these blocks. • Why performance composition? - Just adding clock cycles of the involved components won’t do. Þ Method for the estimation of the number of context switches occurring during the execution of a streaming application. • Current experimentation setting: – HW: Trimedia (TM 1300) • incorporates a media processor for high-performance multimedia applications that deal with high-quality video and audio. – SW: TSSA Philips Research 6/17/2021 Alina Albu, m. a. albu@tue. nl TU/e Computer Science, System Architecture and Networking Philips Research Laboratories Eindhoven 6

1 st meeting of project EES. 5653 MRM project - TSSA – Tri. Media Streaming Software Architecture FP Q Component 1 Component 2 EP Q Philips Research FP Q 6/17/2021 Component 3 EP Q Alina Albu, m. a. albu@tue. nl TU/e Computer Science, System Architecture and Networking Philips Research Laboratories Eindhoven 7

1 st meeting of project EES. 5653 Reasons for context switch occurrence • Blocking. The execution of a task blocks because of the following reasons: o o Communication with the PC host (ex: FRead) Unfavorable status of the queues: - input full packets queue (IFPQ) is empty (no input) output full packets queue (OFPQ) is full (task cannot output packets for the moment) output empty packets queue (OEPQ) is empty (task cannot output packets for the moment) • Preemption. The execution of a task is preempted by another task with a higher priority. • Task execution end. The execution of a task with high priority has ended (no preemption or blocking) and the resources are allocated to another task. Philips Research 6/17/2021 Alina Albu, m. a. albu@tue. nl TU/e Computer Science, System Architecture and Networking Philips Research Laboratories Eindhoven 8

1 st meeting of project EES. 5653 NCS Estimation Method Properties of streaming applications executions • Property 1: Running streaming applications, after an initialization phase, adopt a pattern of execution that repeats after a specific interval of time (hyperperiod). The repetitive execution is caused by the differences in the components’ rates of production/consumption of full/empty packets. • Execution consists of 3 phases: initialization, stable-state, finalization hyperperiod Initialization Stable-state Finalization • => by knowing the NCS occuring during initialization, finalization and during a hyperperiod of the steady-state, we obtain the total NCS • Property 2: When one of the components in the streaming chain is periodic, when other components depend on it in execution, their tasks will execute periodic. Philips Research 6/17/2021 Alina Albu, m. a. albu@tue. nl TU/e Computer Science, System Architecture and Networking Philips Research Laboratories Eindhoven 9

1 st meeting of project EES. 5653 NCS Estimation Method Case study description FP Q FRead VDec EP Q Philips Research FP Q 6/17/2021 VRend. VO EP Q Alina Albu, m. a. albu@tue. nl TU/e Computer Science, System Architecture and Networking Philips Research Laboratories Eindhoven 10

1 st meeting of project EES. 5653 NCS Estimation Method Steps 1 – 4 : initialization, finalization phases Step 1. Initialization phase: End phase: 169. 261 ms Duration: 169. 261 ms Step 2. Initialization phase: NCS_initialization. Phase(FRead) = 26 NCS_initialization. Phase (VDec) = 22 NCS_initialization. Phase (VRend. VO) = 6 Step 3. Finalization phase: Beginning phase: 4539. 029 ms Duration: 1569. 428 ms Step 4. Finalization phase: NCS_finalization. Phase(FRead) = 8 NCS_finalization. Phase(VDec) = 356 NCS_finalization. Phase(VRend. VO) = 94 Philips Research 6/17/2021 Alina Albu, m. a. albu@tue. nl TU/e Computer Science, System Architecture and Networking Philips Research Laboratories Eindhoven 11

1 st meeting of project EES. 5653 NCS Estimation Method Steps 5 – 6 : stable-state phase, production/consumption rates Step 5. Stable state: Beginning phase: 169. 261 ms End phase: 4539. 029 ms Duration: 4369. 768 ms Step 6. Identify for each component the full packets production rate (FPPR), the full packets consumption rate (FPCR), and the empty packets production rate (EPPR). FRead Vdec Vrend. VO Priority 90 70 80 FPPR FPCR EPPR T 2. 2 4. 6 AT CT CEPT (ms) 2. 524 17. 9 16. 3 4. 5 16. 3 0. 056 2 32. 6 - measurements of components rates and computation times in isolation. Philips Research 6/17/2021 Alina Albu, m. a. albu@tue. nl TU/e Computer Science, System Architecture and Networking Philips Research Laboratories Eindhoven 12

1 st meeting of project EES. 5653 NCS Estimation Method Steps 5 – 6 : stable-state phase, production/consumption rates Step 5. Stable state: Beginning phase: 169. 261 ms End phase: 4539. 029 ms Duration: 4369. 768 ms Step 6. Identify for each component the full packets production rate (FPPR), the full packets consumption rate (FPCR), and the empty packets production rate (EPPR). FRead Vdec Vrend. VO Philips Research Priority 90 70 80 FPPR FPCR EPPR T 2. 2 4. 6 16. 3 AT CT CEPT (ms) 2. 524 17. 9 4. 5 2*FPPR(VO) 6/17/2021 16. 3 0. 056 2 32. 6 Alina Albu, m. a. albu@tue. nl TU/e Computer Science, System Architecture and Networking Philips Research Laboratories Eindhoven 13

1 st meeting of project EES. 5653 NCS Estimation Method Steps 5 – 6 : stable-state phase, production/consumption rates Step 5. Stable state: Beginning phase: 169. 261 ms End phase: 4539. 029 ms Duration: 4369. 768 ms Step 6. Identify for each component the full packets production rate (FPPR), the full packets consumption rate (FPCR), and the empty packets production rate (EPPR). FRead Vdec Vrend. VO Philips Research Priority 90 70 80 FPPR FPCR EPPR T 2. 2 4. 6 16. 3 AT CT CEPT (ms) 2. 524 17. 9 4. 5 2*FPPR(VO) 6/17/2021 16. 3 0. 056 2 32. 6 Alina Albu, m. a. albu@tue. nl TU/e Computer Science, System Architecture and Networking Philips Research Laboratories Eindhoven 14

1 st meeting of project EES. 5653 NCS Estimation Method Steps 5 – 6 : stable-state phase, production/consumption rates Step 5. Stable state: Beginning phase: 169. 261 ms End phase: 4539. 029 ms Duration: 4369. 768 ms Step 6. Identify for each component the full packets production rate (FPPR), the full packets consumption rate (FPCR), and the empty packets production rate (EPPR). FRead Vdec Vrend. VO Philips Research Priority 90 70 80 FPPR FPCR EPPR T 2. 2 4. 6 16. 3 AT CT CEPT (ms) 2. 524 17. 9 4*FPPR(VDec) 2*FPPR(VO) 6/17/2021 4. 5 16. 3 0. 056 Alina Albu, m. a. albu@tue. nl TU/e Computer Science, System Architecture and Networking Philips Research Laboratories Eindhoven 2 32. 6 15

1 st meeting of project EES. 5653 NCS Estimation Method Steps 5 – 6 : stable-state phase, production/consumption rates Step 5. Stable state: Beginning phase: 169. 261 ms End phase: 4539. 029 ms Duration: 4369. 768 ms Step 6. Identify for each component the full packets production rate (FPPR), the full packets consumption rate (FPCR), and the empty packets production rate (EPPR). Priority FPPR FPCR EPPR - FRead 90 2. 2 - Vdec Vrend. VO 70 80 4. 6 17. 9 Philips Research 16. 3 4*FPPR(VDec) 2*FPPR(VO) 6/17/2021 T 16. 3 AT CT CEPT (ms) 2. 524 - 4. 5 2 0. 056 Alina Albu, m. a. albu@tue. nl TU/e Computer Science, System Architecture and Networking Philips Research Laboratories Eindhoven 32. 6 16

1 st meeting of project EES. 5653 NCS Estimation Method Step 7 : dependencies between components Step 7 a - Determine the dependencies in the execution of the components by taking into consideration FPPR, FPCR and EPPR for each component. b - Determining the dependencies in the execution of the components, leads to determining the period (T(Ti)) of each task Ti on which the components Ci are mapped. VDec: a - FPPR (VDec) > FPCR (VRend. VO) (> = rate higher) => OFPQ (VDec) at stable state is full => OEPQ (VDec) is empty => VDec depends on VRend. VO to produce 1 EP so that VDec can produce 1 FP => FPPR (VDec) : = EPPR (VRend. VO) = 2 * FPPR(Vrend. VO) = 2 * T(Vrend. VO) = 32. 6 ms. => b - Since T(Vdec) = FPPR(VDec) => T(Vdec) = 32. 6 ms Philips Research 6/17/2021 Alina Albu, m. a. albu@tue. nl TU/e Computer Science, System Architecture and Networking Philips Research Laboratories Eindhoven 17

1 st meeting of project EES. 5653 NCS Estimation Method Step 7 : dependencies between components Step 7 a - Determine the dependencies in the execution of the components by taking into consideration FPPR, FPCR and EPPR for each component. b - Determining the dependencies in the execution of the components, leads to determining the period (T(Ti)) of each task Ti on which the components Ci are mapped. FRead: a – FPPR (FRead) > FPCR (VDec) (> = rate higher) => OFPQ (FRead) at stable state is full => OEPQ (FRead) is empty => FRead depends on VDec to produce 1 EP so that FRead can produce 1 FP => FPPR (FRead) : = EPPR (VDec) = 4 * FPPR(VDec) = 4 * T(VDec) = 4*2*T(Vrend. VO) : =130. 4 ms => b - Since T(FRead) = FPPR(FRead) => T(FRead) = 130. 4 ms Philips Research 6/17/2021 Alina Albu, m. a. albu@tue. nl TU/e Computer Science, System Architecture and Networking Philips Research Laboratories Eindhoven 18

1 st meeting of project EES. 5653 NCS Estimation Method Step 7 : dependencies between components Step 7 Priority FPPR FPCR EPPR - FRead 90 2. 2 - Vdec Vrend. VO 70 80 4. 6 17. 9 Philips Research 16. 3 4*FPPR(VDec) 2*FPPR(VO) 6/17/2021 T 16. 3 AT CT CEPT (ms) 2. 524 - 4. 5 2 0. 056 Alina Albu, m. a. albu@tue. nl TU/e Computer Science, System Architecture and Networking Philips Research Laboratories Eindhoven 32. 6 19

1 st meeting of project EES. 5653 NCS Estimation Method Step 7 : dependencies between components Step 7 Priority FRead Vdec Vrend. VO Philips Research 90 70 80 FPPR FPCR EPPR 2. 2 - - 4. 6 17. 9 130. 4 16. 3 32. 6 6/17/2021 T 16. 3 AT CT CEPT 2. 524 - 4. 5 2 0. 056 (ms) 32. 6 Alina Albu, m. a. albu@tue. nl TU/e Computer Science, System Architecture and Networking Philips Research Laboratories Eindhoven 20

1 st meeting of project EES. 5653 NCS Estimation Method Step 7 : dependencies between components Step 7 FRead Vdec Vrend. VO Philips Research Priority FPPR FPCR EPPR 90 70 80 130. 4 - - 2. 524 - 32. 6 17. 9 130. 4 4. 5 2 16. 3 32. 6 0. 056 32. 6 6/17/2021 T 16. 3 AT CT CEPT (ms) Alina Albu, m. a. albu@tue. nl TU/e Computer Science, System Architecture and Networking Philips Research Laboratories Eindhoven 21

1 st meeting of project EES. 5653 NCS Estimation Method Step 7 : dependencies between components Step 7 FRead Vdec Vrend. VO Philips Research Priority FPPR FPCR EPPR 90 70 80 130. 4 - - 130. 4 32. 6 17. 9 130. 4 16. 3 32. 6 6/17/2021 T AT CT CEPT 2. 524 - 32. 6 4. 5 2 16. 3 0. 056 (ms) 32. 6 Alina Albu, m. a. albu@tue. nl TU/e Computer Science, System Architecture and Networking Philips Research Laboratories Eindhoven 22

1 st meeting of project EES. 5653 NCS Estimation Method Step 8 : hyperperiod length, number of hyperperiods Step 8. Identify hyperperiod length. CIS (component index set) = the set of natural numbers that serve as indexes for components in a streaming chain. The indexes of components will be equal with the indexes of the tasks on which the components are mapped at execution. HL = max T(Ti) = 8 * T(VRend. VO) = 130. 4 ms i CIS Duration stable phase = 4369. 768 ms => average number of hyperperiods during stable phase: HN = Duration_stable. State. Phase/HL = 4369. 768/130. 4 = 34 Philips Research 6/17/2021 Alina Albu, m. a. albu@tue. nl TU/e Computer Science, System Architecture and Networking Philips Research Laboratories Eindhoven 23

1 st meeting of project EES. 5653 NCS Estimation Method Step 9 : NCS due to blocking Step 9. Determine the NCS due to blocking. FRead: • FRead blocks 4 times for each packet that it delivers due to communication with the PC host and has its period equal with the hyperperiod (because it only gets to deliveres 1 full packet during the hyperperiod after which it blocks until the next hyperperiod) => NCS_blocking(FRead) = HL / T(Ti) + NCS_inherent. Blocking(FRead) =1 + 4 = 5; Philips Research 6/17/2021 Alina Albu, m. a. albu@tue. nl TU/e Computer Science, System Architecture and Networking Philips Research Laboratories Eindhoven 24

1 st meeting of project EES. 5653 NCS Estimation Method Step 9 : NCS due to blocking Step 9. VDec: • • • VDec delivers 1 full packet every time it is activated after which it is blocked. VDec is activated periodically and that its period fits 4 time during the hyperperiod => VDec is activated 4 times during the hyperperiod => VDec is blocked 4 times during the hyperperiod. NCS_blocking(VDec) = HL / T(Ti) + NCS_inherent. Blocking(VDec) = HL / T(VDEc) + 0 = 8*T(VRend. VO) / 2*T(VRend. VO) = 4; VRend. VO: • VRend. VO is the component that does not depend on any other component in its execution, and has no inherent blockings => it does not block. NCS_blocking(VRend. VO) = 0; Philips Research 6/17/2021 Alina Albu, m. a. albu@tue. nl TU/e Computer Science, System Architecture and Networking Philips Research Laboratories Eindhoven 25

1 st meeting of project EES. 5653 NCS Estimation Method Step 10 : NCS due to normal execution end. Step 10. Determine the NCS due to normal execution. • Applies only to components that are not preempted and do not depend on any other component in its execution, thus do not get blocked. => Applies only to VRend. VO: NCS_normal. Execution. End(VRend. VO) = HL / T(VRend. VO) = 8*T(VRend. VO) / T(VRend. VO) =8 Philips Research 6/17/2021 Alina Albu, m. a. albu@tue. nl TU/e Computer Science, System Architecture and Networking Philips Research Laboratories Eindhoven 26

1 st meeting of project EES. 5653 NCS Estimation Method Step 11 : Task activation time (AT) Step 11. For each component by considering the dependencies dictated by the rates of production/consumption packets, calculate the first AT in the hyperperiod. In general: For each component Ci mapped on task Ti: 1. If j CIS | Ci dependent on Cj: If P(Ti) < P(Tj): AT(Ti) = AT(Tj) + (N-1)* FPPR(Tj) + CT(Tj) if Ti depends on Tj to release N FP. (N-1)* EPPR(Tj) + CT(Tj) if Ti depends on Tj to release N EP. N=4 CT-CEPT Ti CT-CEPT CT (CT-CFPT) Tj CEPT(CFPT) Philips Research EPPR(FPPR) 6/17/2021 Alina Albu, m. a. albu@tue. nl TU/e Computer Science, System Architecture and Networking Philips Research Laboratories Eindhoven 27

1 st meeting of project EES. 5653 NCS Estimation Method Step 11 : Task activation time (AT) If P(Ti) > P(Tj): AT(Ti) = AT(Tj) + CFPT(Tj) + (N-1)* FPPR(Tj) if Ti depends on Tj to release N FP. CEPT(Tj) + (N-1)* EPPR(Tj) if Ti depends on Tj to release N EP. N=4 Ti CT Tj CEPT(CFPT) Philips Research EPPR(FPPR) 6/17/2021 Alina Albu, m. a. albu@tue. nl TU/e Computer Science, System Architecture and Networking Philips Research Laboratories Eindhoven 28

1 st meeting of project EES. 5653 NCS Estimation Method Step 11 : Task activation time (AT) For the current case study: FRead dependent on Vdec to release 1 EP => P(FRead) > P(VDec) => AT(FRead) = AT(VDec) + (1 -1)*EPPR(Vdec) + CEPT (VDec) = AT(VDec) + CEPT(VDec) = AT(VDec) + 2 ms. Vdec: Vdec dependent on VRend. VO to release 1 EP => P(VRend. VO) > P(VDec) => AT(VDec) = AT(VRend. VO) + (1 -1)*EPPR(VRend. VO) + CT (VRend. VO) = AT(VRend. VO) + 0. 056 ms. = 0. 056 ms First AT(VRend. VO) = 0 relative to the beginning of the hyperperiod. => AT(FRead) = 0. 056 ms +2 ms = 2. 056 ms Philips Research 6/17/2021 Alina Albu, m. a. albu@tue. nl TU/e Computer Science, System Architecture and Networking Philips Research Laboratories Eindhoven 29

1 st meeting of project EES. 5653 NCS Estimation Method Step 11 : Task activation time (AT) Step 11 FRead Vdec Vrend. VO Philips Research Priority FPPR FPCR EPPR 90 70 80 130. 4 - - 130. 4 32. 6 17. 9 130. 4 16. 3 32. 6 6/17/2021 T AT CT CEPT 2. 524 - 32. 6 4. 5 2 16. 3 0. 056 (ms) 32. 6 Alina Albu, m. a. albu@tue. nl TU/e Computer Science, System Architecture and Networking Philips Research Laboratories Eindhoven 30

1 st meeting of project EES. 5653 NCS Estimation Method Step 11 : Task activation time (AT) Step 11 FRead Vdec Vrend. VO Philips Research Priority FPPR FPCR EPPR 90 70 80 130. 4 - - 32. 6 17. 9 16. 3 32. 6 6/17/2021 T AT CT CEPT 130. 4 2. 056 2. 524 - 130. 4 32. 6 0. 056 4. 5 2 32. 6 16. 3 0 0. 056 (ms) 32. 6 Alina Albu, m. a. albu@tue. nl TU/e Computer Science, System Architecture and Networking Philips Research Laboratories Eindhoven 31

1 st meeting of project EES. 5653 NCS Estimation Method Task response time, NCS due to preemptions P(Ti) > P(Tj) AT(Ti) (AT(Tj), AT(Tj) + CT(Tj)) => Ti preempts Tj. Ti Tj AT(Tj) CT(Tj) Philips Research 6/17/2021 R 0(Tj) = CT(Tj) Alina Albu, m. a. albu@tue. nl TU/e Computer Science, System Architecture and Networking Philips Research Laboratories Eindhoven 32

1 st meeting of project EES. 5653 NCS Estimation Method Task response time, NCS due to preemptions P(Ti) > P(Tj) AT(Ti) (AT(Tj), AT(Tj) + CT(Tj)) => Ti preempts Tj. CT(Ti) Ti Tj AT(Tj) AT(Ti) R 1(Tj) = Ro(Tj)+CT(Ti) Philips Research 6/17/2021 Alina Albu, m. a. albu@tue. nl TU/e Computer Science, System Architecture and Networking Philips Research Laboratories Eindhoven 33

1 st meeting of project EES. 5653 NCS Estimation Method Task response time, NCS due to preemptions P(Ti) > P(Tj) AT(Ti) (AT(Tj), AT(Tj) + CT(Tj)) => Ti preempts Tj. T(Ti) CT(Ti) Ti Tj AT(Tj) AT(Ti) R 1(Tj) = Ro(Tj)+2*CT(Ti) Philips Research 6/17/2021 Alina Albu, m. a. albu@tue. nl TU/e Computer Science, System Architecture and Networking Philips Research Laboratories Eindhoven 34

1 st meeting of project EES. 5653 NCS Estimation Method Task response time, NCS due to preemptions P(Ti) > P(Tj) AT(Ti) (AT(Tj), AT(Tj) + CT(Tj)) => Ti preempts Tj. NCS_preemption(Tj) = Ro (Tj)/T(Ti) R 1(Tj) = NCS_preemption(Tj)*CT(Ti) Ti Tj AT(Tj) Philips Research AT(Ti) 6/17/2021 AT(Ti) R 1(Tj) = Ro(Tj)+3*CT(Ti) Alina Albu, m. a. albu@tue. nl TU/e Computer Science, System Architecture and Networking Philips Research Laboratories Eindhoven 35

1 st meeting of project EES. 5653 NCS Estimation Method Step 12: Task response time, NCS due to preemptions Step 12 Calculate NCS_preemption for all components: In general: Rn(Ti) = Rn-1 (Ti) + Rn-1 (Ti)/T(Tj) * CT(Tj), j {k CIS | P(Tk) > P(Ti) AT(Tk) (AT(Ti), AT(Ti) + CT(Ti))} where Ro – initial response time, Ro(Ti) = CT(Ti) From here, the total number of context switches due to preemptions will be: NCS_preemption(Ti) = Rn-1 (Ti)/Tj j {k CIS | P(Tk) > P(Ti) AT(Tk) (AT(Ti), AT(Ti) + CT(Ti))} Philips Research 6/17/2021 Alina Albu, m. a. albu@tue. nl TU/e Computer Science, System Architecture and Networking Philips Research Laboratories Eindhoven 36

1 st meeting of project EES. 5653 NCS Estimation Method Step 12: Task response time, NCS due to preemptions Step 12 For the current case study: FRead has he highest priority assigned => never preempted. => NCS(FRead)_preemption = 0 VDec: P(VRend. VO) > P(VDec) " AT(VRend. VO), AT(VRend. VO) (AT(VDec), AT(VDec) + CT(VDec)) => Vrend. VO does not preempt VDec. P(FRead) > P(VDec) AT(FRead), AT(FRead) (AT(VDec), AT(VDec) + CT(VDec)) => FRead preempts VDec NCS_preemption (VDec) = 5 VRend. VO: P(FRead) > P(VRend. VO) " AT(FRead), AT(FRead) (AT(VRend. VO), AT(VRend. VO) + CT(VRend. VO)) => FRead does not preempt VRend. VO. => NCS_preemption(VRend. VO)=0 Philips Research 6/17/2021 Alina Albu, m. a. albu@tue. nl TU/e Computer Science, System Architecture and Networking Philips Research Laboratories Eindhoven 37

1 st meeting of project EES. 5653 NCS Estimation Method Step 13: Total NCS/hyperperiod Step 13 Determine NCS_total for each of the components involved: For each hyperperiod: NCS_total(Ci) = NCS_blocking(Ci) + NCS_preemption(Ci) + NCS_normal. Execution. End(Ci) => Total NCS/hyperperiod: NCS_hyperperiod (FRead) = NCS_blocking(FRead) + NCS_preemption(FRead) = 5 + 0=5 NCS_hyperperiod (VDec) = NCS_blocking (VDec) + NCS_preemption (VDec) = 5 + 4 = 9 NCS_hyperperiod (VRend. VO) = NCS_blocking VRend. VO) + NCS_preemption (VRend. VO) + NCS_normal. Execution. End(VRend. VO) = 0 + 8 = 8 Philips Research 6/17/2021 Alina Albu, m. a. albu@tue. nl TU/e Computer Science, System Architecture and Networking Philips Research Laboratories Eindhoven 42

1 st meeting of project EES. 5653 NCS Estimation Method Step 14: Total NCS Step 14 Determine the total NCS during the entire execution of the streaming application. We know that the average number of hyperperiods during stable phase HN = 34 (from step 8) => Total estimated NCS: NCS_total(FRead) = 5*34 + 26 + 8 = 204 NCS_total (VDec) = 9*34 + 22 + 356 = 684 NCS_total (VRend. VO) = 8*34 + 6 + 94 = 372 vs measured 207 vs measured 679 vs measured 362 Note: Differences come from the fact that we work with averages in the components models which determines an average length for the hyperperiod an average number of hyperperiods. Philips Research 6/17/2021 Alina Albu, m. a. albu@tue. nl TU/e Computer Science, System Architecture and Networking Philips Research Laboratories Eindhoven 43

1 st meeting of project EES. 5653 Future work • Test method on more complex, realistic case studies • Write paper describing the aforementioned findings • Extend estimation method for applications containing multiple dependent/independent chains. • Continue studies to finding ways to estimate the necessary of memory and bus for streaming applications. • Continue studies on estimating necessary of resources streaming applications running on multiple processors platforms. Philips Research 6/17/2021 Alina Albu, m. a. albu@tue. nl TU/e Computer Science, System Architecture and Networking Philips Research Laboratories Eindhoven 44