Postgraduate Diploma in Heterogeneous Scheduling and Thermal/Power Budget
Online 800-hour Postgraduate Diploma in Heterogeneous Scheduling and Thermal/Power Budget. 8 modules covering ISO 26262:2018, AEC-Q100 and NVIDIA Nsight Systems. Assigned tutor and open enrolment.
Take the controls.
Run a real engineering trade-off from this field. Move the sliders, watch the model react in real time and beat the challenge.
What you will be able to do
Characterise heterogeneous platforms for automated driving.
Apply real-time scheduling theory.
Schedule tasks on CPU, GPU and accelerators.
Manage the power budget of the system.
Control the thermal behaviour of embedded computing.
Optimise models for efficiency and latency.
Guarantee temporal isolation in critical systems.
Who it's for
- Embedded systems engineer who wants to specialise in Heterogeneous Scheduling and Thermal/Power Budget.
- Performance engineer who wants to specialise in Heterogeneous Scheduling and Thermal/Power Budget.
- Automotive hardware architect who wants to specialise in Heterogeneous Scheduling and Thermal/Power Budget.
- Real-time software engineer who wants to specialise in Heterogeneous Scheduling and Thermal/Power Budget.
- AI optimisation engineer who wants to specialise in Heterogeneous Scheduling and Thermal/Power Budget.
- Thermal engineer who wants to specialise in Heterogeneous Scheduling and Thermal/Power Budget.
- Engineering or science graduates seeking to enter the automotive sector.
What you'll work with
- ISO 26262:2018
- AEC-Q100
- AUTOSAR Specification of Timing Extensions
- ISO 16750-4:2023
- JEDEC JESD51
- ISO 21448:2022 (SOTIF)
- ISO/PAS 8800:2024
8 modules · 800 h
1.1SoC with CPU, GPU and NPU1.2DLA and DSP accelerators1.3Memory hierarchy and bandwidth1.4Perception and planning workloads1.5Required latency and throughput1.6Power consumption and dissipation1.7NVIDIA, Qualcomm and Mobileye platforms1.8Centralised computing1.9Chiplets and computing scalability1.10Case study: workload profile of an ADAS stack
2.1Periodic and sporadic tasks2.2Rate Monotonic and EDF2.3Response-time analysis2.4Worst-case execution time2.5Partitioned and global multicore scheduling2.6Interference on shared resources2.7Task chains and cause-effect latency2.8Analysis tools2.9Server reservation scheduling2.10Laboratory: schedulability analysis
3.1Task allocation to accelerators3.2DAG task graphs3.3GPU inferences3.4Concurrency and CUDA streams3.5Network partitioning across accelerators3.6GPU priorities3.7Dynamic scheduling based on load3.8Profiling tools3.9GPU job preemption3.10Practical: profiling with Nsight Systems
4.1DVFS on CPU and GPU4.2Low-power states4.3Power consumption models4.4Power budgets per mode4.5Energy-aware scheduling4.6Impact on electric vehicle range4.7Power measurement4.8Efficient models4.9Current peaks and power supply4.10Laboratory: performance versus power
5.1SoC thermal models5.2Thermal throttling5.3Passive and liquid cooling5.4Vehicle thermal environment5.5Temperature-aware scheduling5.6Thermal prediction5.7Functional degradation due to temperature5.8Thermal testing5.9Reliability and temperature-driven ageing5.10Practical: thermal simulation of a controller
6.1INT8 and FP16 quantisation6.2Pruning and distillation6.3TensorRT and compilers6.4Batching and pipelining6.5Hardware-software co-design6.6Design space exploration6.7Accuracy, latency and energy6.8MLPerf benchmarks6.9Mixed precision by layer6.10Laboratory: optimisation of a detector with TensorRT
7.1Safety timing requirements7.2Performance isolation7.3Deadline monitoring7.4Watchdogs and supervision7.5Interference in caches and memory7.6Mixed criticality7.7Timing evidence for ISO 262627.8System saturation7.9Program flow control7.10Workshop: timing budget of a function
8.1Chosen platform8.2Workload characterisation8.3Task model and constraints8.4Allocation strategy8.5Power and thermal budget8.6Model optimisation8.7Experimental evaluation8.8Temporal safety8.9Report and presentation8.10Final review with the tutor
How you'll learn
Training is 100 % online on the SEIUM campus, with downloadable material, recorded classes and an assigned technical tutor. There are no fixed timetables: students progress at their own pace within the intake, which makes it compatible with work.
Each module combines theory, guided reading of the original standard and applied exercises. The working software is NVIDIA Nsight Systems, NVIDIA TensorRT, INCHRON chronSUITE, Linux perf, MATLAB, in free, academic or evaluation versions. The exercises are based on real profiling procedures for a perception stack on embedded GPU, schedulability analysis of critical tasks and energy optimisation of inferences. Assessment is continuous per module plus the final integrative project.
Build it end to end
Your final project follows the real engineering workflow, step by step, reviewed by your tutor.
Characterise heterogeneous platforms for automated driving.
Apply real-time scheduling theory.
Schedule tasks on CPU, GPU and accelerators.
Manage the power budget of the system.
Control the thermal behaviour of embedded computing.
Where this takes you
Requirements
- Prior technical training or professional experience in the sector. No university degree is required.
- Internet connection and a computer capable of running the programme's software.
- Sufficient level of Spanish to follow technical standards documentation.
Ready to start?
Send your application today. Our admissions team replies within 72 hours with your study plan and funding options.
Frequently asked questions
The programme consists of 800 hours in total, spread over 6 to 8 months. That is an average of 10 to 15 hours per week, compatible with a full-time job.
The course uses NVIDIA Nsight Systems, NVIDIA TensorRT, INCHRON chronSUITE, Linux perf and MATLAB. Free, academic or evaluation versions are used, and the tutor indicates the free alternative when one exists.
A SEIUM diploma upon passing the continuous assessment and the integrative project. It is in-house training, not an official Ministry title.
Yes. Modules passed in a course or diploma in the same area can be credited towards the advanced programme. Check the recognition policy when enrolling.
Related programmes
Postgraduate Diploma in Runtime Monitoring and Safety Kernels
Online 800-hour Postgraduate Diploma in Runtime Monitoring and Safety Kernels. 8 modules covering ISO 26262:2018, UL 4600 and RTAMT. Assigned tutor and open enrolment.
Postgraduate Diploma in External Signalling (eHMI) and Passenger Acceptance
Online 800-hour Postgraduate Diploma in External Signalling (eHMI) and Passenger Acceptance. 8 modules covering ISO/TR 23049:2018, SAE J3134 and Unity. Assigned tutor and open enrolment.
Postgraduate Diploma in UDS/OBD Diagnostics, Health Monitoring and FOTA
Online 800-hour Postgraduate Diploma in UDS/OBD diagnostics, Health Monitoring and FOTA. 8 modules covering ISO 14229-1:2020, ISO 15765-2:2024 and Vector CANoe. Assigned tutor and open enrolment.
More in Autonomous, ADAS & Software-Defined Vehicle
All Autonomous, ADAS & Software-Defined Vehicle programmes → · How to apply · Fees & financing · Scholarships