Aerial SDK 23-4
Aerial SDK 23-4

Performance

The following performance achievement is possible without hyperthreading using “1+6+fractional” x86 cores. The shorthand “1+6+fractional” x86 cores is defined as follows:

  • 1 isolated physical x86 core for core-locked PTP applications (phc2sys+ptp4l) and the core-locked cuphycontroller L2A H2D prepone thread

  • 6 aditional isolated physical x86 cores for the other core-locked cuphycontroller threads

  • A fraction of a shared floating x86 core for non-core-locked cuphycontroller threads

Additionally, the tested L2 timeline is as follows:

  • FAPI SLOT.indication for Slot N is sent from L1 to L2 at the wall-clock time for Slot N-3 (i.e. 3 slot advance).

  • For the DDDSUUDDDD TDD pattern with 0-based slot numbering, L2 has up-to-500us, for slot%10 in {2,3,4,5,6}, from SLOT.indication to deliver all FAPI PDUs for Slot N.

  • For the DDDSUUDDDD TDD pattern with 0-based slot numbering, L2 has up-to-250us, for slot%10 in {0,1,7,8,9}, from SLOT.indication to deliver all FAPI PDUs for Slot N.

As of 23-4:

Supports 500us L2 processing budget and 7 beam pattern as defined below using 100MHz patterns 59c and 60c:

On discrete A100/CX6 cards:

  • BFP9: 4 4T4R peak / 8 4T4R avg cells

On A100X:

  • BFP9: 5 4T4R peak cells / 10 4T4R avg cells

  • BFP14: 4 4T4R peak cells / 8 4T4R avg cells

On AX800:

  • BFP9: 8 4T4R peak cells / 16 4T4R avg cells

  • BFP14: 8 4T4R peak cells / 16 4T4R avg cells using both FH ports of the AX800

while respecting the following configuration for 7 beam traffic patterns:

  • 8 Cells in E2E configuration (CN + RAN + UE-EM) via eCPRI connection to test equipment

    (Achieving aggregate DL throughput of 4.2Gbps which is 530MBps per cell)

  • 4 Peak Cells in E2E configuration (CN + RAN + UE-EM) via RF cabled connection to O-RU

    (Achieving aggregate DL throughput of 5.6Gbps and UL throughput of 800Mbps)

  • 3 Peak Cell in E2E configuration (CN + RAN + UE-EM) via eCPRI connection to test equipment

    (Achieving aggreagte DL throughput of 4.2Gbps)

  • 2 Peak Cells in E2E configuration (CN + RAN + UE-EM) via eCPRI connection to test equipment

    (Achieving aggregate DL throughput of 2.86Gbps and UL throughput of 420Mbps)

  • 1 Peak Cell in E2E configuration (CN + RAN + UE-EM) via RF cable connection to O-RU

    (Achieving DL throughput of 1.3Gbps and UL throughput of 100Mbps)

  • Simultaneous Front Haul capability ( 8 peak cells)

    (4 Peak cells per Front Haul port)

  • 1 Cell OTA in E2E configuration (CN + RAN + CUE) via OTA connection to UE device

    (Achieving DL throughput of 837Mbps and UL throughput of 77Mbps)

Previous Supported Features and Configurations
Next Supported Test Vector Configurations
© Copyright 2022-2023, NVIDIA.. Last updated on Apr 20, 2024.