2024-06-27 Linaro Data Center Group steering committee Meeting Agenda/Minutes

 Agenda

• Previous meeting minutes: 2024-05-16 Linaro Data Center Group steering committee Meeting Agenda/Minutes
• Projects updates
• UXL
• Optimization potential future work
• Kleidi
• Events
• AOB

Documents

• INSERT

Action Items

• @ name action item here //dd-mm-yyyy  

Minutes

• Projects updates
  
  • Deploy CCA on Arm platforms (DCAP)
    • PoC: Running a confidential container workload on CoCo, using Kata containers and QEMU as the underlying base for the Realm support.
    • PoC: End to end demo with CoCo and remote attestation service running.
    • Wrote documentation on how to boot a Ubuntu based rootfs.
    • Wrote documentation for the rust-ccatoken tool.
    • Trying to recover the Kata Containers CI on Arm64 in the community.
  • System Ready Compliant Platform Collaboration (SRCPC)

    • Moved SBSA Reference Platform default processor to Arm v9.0 Neoverse N2.

    • Switched the timer frequency in SBSA reference machine type to 1 GHz, as now we have proper support with TF-A 2.11 released and integrated into QEMU CI.

    • Updated firmware used by QEMU CI to TF-A 2.11 and EDK2 stable202405, which allows to test NUMA support for CPU and memory.

    • Fixed issue in EDK2 that was preventing SBSA Reference Platform to boot after recent changes in QEMU.

    • Support for multiple PCI Express buses was written and landed in review queue on EDK2 ML.

  • Enhanced Software-Defined-Storage on Arm Servers (STOR)
    • Lustre
      • Updated rpm package for openEuler 22.03 LTS SP4.
      • Run performance tests on openEuler.
      • Functional test on multiple nodes with RDMA support.
• UXL
  • Members to bring specific requirements around UXL and whether they can provide engineers to help on this work. The discussion was mainly around library optimization.
• Optimization potential future work
  • We had discussed many times which frameworks or projects we should be optimizing. Even though everyone agrees this is an important area to explore, there hasn't been a clear consensus on which direction we should take.
  • Some direct projects, such as STOR and BDDS in the past, had worked on optimizing specific areas that were not well performant.
  • Arm provides very little information about the work they are doing in project Interstellar.
  • In the last steering committee meeting, Fujitsu talked about the work they are doing to optimize AI frameworks for Arm (oneDNN and oneDAL).
  • Everybody agreed that Linaro should be coordinating any collaboration in this area. So I decided to build a list of potential projects that might be good targets for optimization on Arm64 platforms and we can go from there. I got valuable input from Linaro employes Carlos Seo and Everton Constantino (Deactivated), who have expertise on performance optimization, to build this list.
  • Important reminder: any optimization work starts with an investigation phase. It is not possible to jump directly in the optimization work without making a good performance analysis of the target project.
  • Projects with potential performance optimization work on Arm64 platforms (I didn't check current status of these projects):
    • UXL projects
      • oneDNN: Fujitsu done optimization work. Anything else left to explore?
      • oneDAL: Fujitsu done optimization work. Anything else left to explore?

    • Computer Vision

      • OpenCV: SIMD enablement via OpenCV's HAL (Hardware Abstraction Layer)?

      • FFMPEG2: SIMD enablement?

    • BLAS

      • OpenBLAS: SIMD and SME enablement?

      • Eigen: SIMD and SME enablement?

      • BLIS: SIMD and SME enablement?

    • Boost

      • XGBoost

      • LightGBM: CUDA only today. SYCL version? UXL support?

    • Other maths

      • NumPy: is there anything left to do?

      • SciPy: is there anything left to do?

    • DNN

      • MKL-DNN

    • Algorithms that might be important (need to find relevant libraries):
      • Classification Analysis
        • Decision Tree Analysis
        • K Nearest Neighbour
        • Linear Discriminant Analysis (LDA)
        • Confusion Matrix
      • Cluster Analysis
        • K-Means
        • Agglomerate Hierarchical
        • Affinity Propagation
        • Latent Dirichlet Allocation (LDA)
        • Gaussian Mixture Model (GMM)
      • Cryptographic algorithms
        • OpenSSL
        • MBedTLS
        • Language runtimes (Golang)?

      • Data preparation

        • Sampling

        • Principal Component Analysis

      • GPU offload
        • OpenMP target
        • OpenACC?
        • SYCL?
      • Time Series Analysis
        • Fast Fourier Transform (FFT)
        • Correlation Function
      • Regression
        • Generalized Linear Model (GLM)
      • Compression / decompression
        • Zlib?
      • Association Analysis
      • Probability Distribution
      • Outlier Detection
      • Recommender Systems
      • Link Prediction
      • Statistical Functions
• Kleidi
  • Arm recently introduced Kleidi, a low-level CPU instruction library targeting Artificial Intelligence and Computer Vision workloads for the moment. This library is specifically targeting CPUs, by providing a common layer with algorithms in these areas optimized for specific CPU implementations (Armv8 NEON and Armv9 SVE2 and SME2).
  • Right now, KleidiAI has just a small number of NEON based kernels (matrix-multiply) upstreamed. Is this an area the Data Center Group should be looking at? My understanding is that current algorithms are optimized only for Arm microarchitectures.
• Events
  • Linaro Connect: 14-17 May, 2024, Madrid, Spain
    • A few talks approved that are related to the projects we have in the Data Center Group.
    • Very good conversations during the conference, as well as very good discussions in the presentations from the projects we have in the Data Center Group.
  • Confidential Computing Summit (CC Summit): 5-6 June, 2024, San Francisco, CA, USA
    • CCC is co-hosting.
    • Linaro had 2 talks accepted.
    • https://www.confidentialcomputingsummit.com/
    • Very good feedback on our talks. Technical content was not the strongest part of the conference, with more focus on uses cases for AI.
  • Black Hat: 3-8 August, 2024, Las Vegas, NV, USA
    • https://www.blackhat.com/upcoming.html#usa
  • Open Source Summit Europe (OSS EU): 16-18 September, 2024, Vienna, Austria
    
    • https://events.linuxfoundation.org/open-source-summit-europe/
  • Linux Plumber's Conference: 18-20 September, 2024, Vienna, Austria (co-located with OSS EU).
    • There will be a confidential computing microconference.
    • Linaro will be present.
    • https://lpc.events/
  • Confidential Computing Mini Summit: 19 September, 2024, Vienna, Austria (co-located with OSS EU).
    • Registration is done together with the OSS EU registrations (there is an option to register to the co-located conferences).
    • Linaro will be present.
  • Open Source Summit China (OSS-China) and KubeCon China: 26-28 September, 2024, Shanghai, China
    • We plan to attend.
    • https://www.lfasiallc.com/kubecon-cloudnativecon-open-source-summit-china/
  • Community over Code (previously ApacheCon): 7-10 October, 2024, Denver, CO, USA
    • https://communityovercode.org/
  • KubeCon North America: 12-15 November, 2024, Salt Lake City, UT, USA
    • https://events.linuxfoundation.org/kubecon-cloudnativecon-north-america-2024/
  • Open Source Summit Japan (OSS-Japan): 5-6 December, 2024, Tokyo, Japan
    • https://events.linuxfoundation.org/open-source-summit-japan/
  • Privacy-Enhancing Technology Summit Asia-Pacific (PET-APAC): date TBD, Singapore
    • CCC is an associate partner.

  • Any other events where we could collaborate or where you think Linaro should do a demo or present.

• AOB
  • Error injection in QEMU.