Versions Compared

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.
Comment: Today's plans

...

  • (tick) Crypto / Security
    • Trusted Execution Environments
    • NXP accelerator blocks?
    • Firmware framework for Cortex-A, OPTEE, how to access secure computing from the general application, ...
  • (red star) Ethernet AvB / Time Sensitive Networking
    • NXP accelerator blocks?
    • Can the HW be partitioned, and use pass-through to more than one VM.
    • HW+SW stack, how is it divided up between HV, VMs, ...
    • Assume one or two "typical" intended use-cases or system designs and discuss from there.
  • (smile) Automotive networks, in particular CAN
  • Accelerators   
    • (green star) Tensor-Processing Units
      • Will be used for some safety critical features?  Is it feasible to virtualize?
    • DSPs (is that discussion done in AVPS or is there more?)
  • (smile) Camera
  • (smile) (blue star) (lightbulb) Next-gen PCI and future interconnects.  Used for example for inter-chip communication and peripherals 
    • Automotive working group exists within PCI v6 work
    • Future interconnects: CCIX (pronounced "C-six"), CXL, Gen Z and other alternatives, NVidia alternative, ... 
  • Graphics (again...)

...

  •  (lightbulb)(red star) IPC and Inter-Chip Communication
    • Communication between different guests or hardware parts.  Does it affect the Virtual Platform or is it just run transparently on virtual socket?
    • One specific use case is inter-cpu communication. Particularly in the case of converged SoCs, e.g. comms between app on RT and general purpose CPU.
    • Are there standard choices?  Are there many vendor-specific proposals, like  IC-COM?    (Is that an AUTOSAR standard?)
      RPMSG → https://www.kernel.org/doc/html/latest/staging/rpmsg.html
      NXP has some framework?
    • MCAL is intended to be abstraction layer for the actual communication choice?
      • ... but it still need to be implemented, (so actual choices matter at some level)
    • There are non-AUTOSAR implementations as well.
    • Impact and design of security.
    • Hypervisors using inter-chip communication somehow?
      • Example (Xen): HV controlling  MFIS (Renesas specific) for communication between. Cortex-R / Cortex-A cores
    • VIRTIO usage as a protocol between system partitions (not only VM-to-HV but other types of partitioning)
      • Uses HW capability for the low-level mailbox / similar
      • Subset of VIRTIO (can't assume access to whole memory as often done by VIRTIO to HV implementation)
      • Can VIRTIO be transformed into a safety-optimized communication.  E.g. some parts of memory only written by one party, read by the other.  Also sealing needed (if it's a shared-memory buffer).
  • Go through operating system kernel special needs for each popular OS choice.
    • e.g. Is VIRTIO reasonably supported for RTOSes or other requirements?
    • e.g. What is the impact of new RTOS initiatives, as well as migration of legacy code from dedicated hardware to a virtualized environment (because the hardware goes out of production or similar).  Thread-X, AUTOSAR (OSEK), Zaphyr, FreeRTOS, Arm MBed, (and no-RTOS bare-metal VMs).
  • (green star) (smile)  Clock synchronization, real-time clock abstraction (probably a good topic for the AVPS)
    • Discussed today for the purpose of synchronized logs... but are not there more reasons?  E.g. systems that can do load-balancing, redundancy (offloading, transferring tasks), don't they need a common time?
  • (smile) Timer paravirtualization
    • CPU scheduling reporting HV<->VM, e.g. kernels do not get accurate information about system load.  Steal time reporting.  The time while a VM was not scheduled, even though it should run (= Steal time).
    • A spec from Arm ("Arm para-virtualized time" DEN0057A ) covers how to report steal time.
  • (blue star) General topic: Needs for (easier, better) virtualization support in future SoCs.
    • Still examples of how IP-block diversity and limitations causes issues (32 bit device in an otherwise 64-bit architecture)
    • Is virtualization truly a top priority for SoC vendors?
  • Agreed definition of virtualization.  Non-MMU systems seem to use the term even if the implementation is rather hardware separation.

...

OPTEE maintainer Renesas.  OPTEE related topics - Volodomyr Babchuk

TSN - Torsten (Renesas) is interested.
   - Previous material (Torsten made presentation in AMM Munich (2019?))

IPC - Thomas Bruss (Renesas)

    ... requested some guidance on topics first.

PCI - Thomas Bruss

Microcontrollers

  - (RH850) Juergen Himmelberg?
   ... some details are proprietary (partners/NDA only)
   ... idea: discussion group among companies that have NDA setups with silicon vendor (not ideal)

 - Adam and Oleksandr interested
 - ARM representative - discussing with Bernhard

...