Versions Compared

Old Version 28

changes.mady.by.user Larry Ruckman

Saved on

compared with

New Version 29

changes.mady.by.user Larry Ruckman

Saved on

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

...

Word#Word's BYTETypeNameDescriptionNote
0[5:0]HeaderDestMacDestination MAC
  • Network mode only
0[11:6]HeaderSrcMacSource MAC
  • Network mode only
0[13:12]HeaderEtherTypeTBD Value
  • Network mode only
014HeaderVersion0x1
  • Hard coded
015HeaderTIDTransaction ID
  • Increments once per packet
  • Used for out-of-order frame reorganizing in network mode
0[17:16]HeaderPauseVirtual Channel Pause
  • 1 bit per Virtual Channel
018HeaderVCVirtual Channel Index
  • BIT[3:0]: Virtual Channel Index
  • BIT[7:4]: Reserved
019HeadertUserFirstfirst 8-bits of tUser 
020HeaderOpCodeEnOP-code Enable 
0[29:20]HeaderReservedReserved
  • Zeros
0[31:30]HeaderHdrXsum16-bit Header Checksum
  • Header Only
0[47:32]HeaderOpCodeData128-bit OP-code Data
  • Supports 64-bit timestamp + more information
0[63:48]HeaderUserData128-bit User Data
  • Sampled every packet sent
1[63:0]PayloadAXIS DataUser Payload Data 
............... 
(MAX_SIZE/64)[63:0]PayloadAXIS DataUser Payload Data 
(MAX_SIZE/64)+10FootertKeepLastTKEEP on last payload word
  • Converted from byte map to an integer
(MAX_SIZE/64)+11FooterEOF/EOFEEOF and EOFE marker
  • BIT0 = EOF, BIT1 = EOFE
(MAX_SIZE/64)+1[3:2]FooterPauseVirtual Channel Pause
  • paused bits are sampled and latched during the payload transport
(MAX_SIZE/64)+1[5:4]FooterPayloadSizeNumber of bytes in payload
  • Units of bytes

 

Performance

Going "point-to-point" we are measuring 97.3 Gb/s throughput rate for 1MB frames using 8196B PGP-ETH burst size.  97.3 Gb/s is < 98.9% theoretical limit, which we think is related to some unaccounted inefficiency in the CMAC4 hard IP core that we used in this testing.  The DMA bandwidth limit in this test was 101 Gb/s, which means the DMA was not back pressuring on the PGP-ETH link.

Image Added