Hard Processor System Technical Reference Manual: Agilex™ 5 SoCs

ID 814346
Date 4/01/2024
Public
Document Table of Contents

5.1.6.9.1. Delay Request-Response Mechanism

The system or network is classified into the time transmitter and time receiver nodes for distributing the timing and clock information. Figure below shows the process that PTP uses for synchronizing a time receiver node to a time transmitter node by exchanging PTP messages.

Figure 75. Networked Time Synchronization

The PTP uses the following process:

  1. The time transmitter broadcasts the PTP Sync messages to all its nodes. The Sync message contains the reference time information of the time transmitter. This message leaves the system of the time transmitter at t1. This time must be captured for Ethernet ports at GMII.
  2. The time receiver receives the Sync message and also captures the exact time, t2, using its timing reference.
  3. The time transmitter sends a Follow_up message to the time receiver, which contains t1 information for later use.
  4. The time receiver sends a Delay_Req message to the time transmitter and notes the exact time, t3, at which this packet leaves the GMII interface.
  5. The time transmitter receives the message, capturing the exact time t4, at which the message enters its system.
  6. The time transmitter sends the t4 information to the time receiver in the Delay_Resp message.
  7. The time receiver uses the four values of t1, t2, t3, and t4 to synchronize its local timing reference to the timing reference of the time transmitter.

Most of the PTP implementation is done in the software that is above the UDP layer. However, the hardware support is required to capture the exact time when specific PTP packets enter or leave the Ethernet port at the GMII interface. This timing information must be captured and returned to the software for proper implementation of PTP with high accuracy