Connecting the world with professional
Fiber Optic Solutions

fiber optic transceiver special topic








Except products belongs to Bargain Shop section, all products are warranted by SOPTO only to purchasers for resale or for use in business or original equipment manufacturer, against defects in workmanship or materials under normal use (consumables, normal tear and wear excluded) for one year after date of purchase from SOPTO, unless otherwise stated...

Return Policies

Defective products will be accepted for exchange, at our discretion, within 14 days from receipt. Buyer might be requested to return the defective products to SOPTO for verification or authorized service location, as SOPTO designated, shipping costs prepaid. .....


PCIE Server NIC card Application

  • PCI-E NIC Cards provide redundant connectivity to ensure an uninterrupted network connection.

  • PCI-E NIC Cards are ideal for VM environments with multiple operating systems, requiring shared or dedicated NICs.

  • They are specially designed for desktop PC clients, servers, and workstations with few PCI Express slots available.


SNS Page

  • sopto facebook
  • sopto twitter
  • sopto linkedin

Cheating: Non DMA Method


In this page, we will talk about the Non DMA Method. If you don’t know why, please see the previous page.


The simplest way is having the driver software write the data to the hardware in a loop, with something like strcpy (). This is indeed very inefficient, but given the fast PCIe hardware available, it’s possible to reach satisfactory results with this plain method: For example, in a worst-case scenario, each DW (4 bytes) of payload requires 16 bytes of TLP headers (64-bit addressing) + 6 bytes for data link layer overhead, so there are 26 bytes transmitted on the data link layer for each 4 bytes of payload.


On a Gen1 link with x8 lanes, this raw link layer runs at 2.5 Gbps x (8/10) x 8 = 16 Gbps = 2 GB/s (the 8/10 factor accounts for the error correction code). The payload link rate is hence limited to 2000 MB/s x 4 / 26 = 307 MB/s. In reality, the rate is somewhat lower due to data link layer overhead, so 280-300MB/s is a more realistic figure.

Gigabit EF Dual Port Server Adapter

Gigabit EF Dual Port Server Adapter


In some cases, the processor may send more than 4 bytes on each TLP packet, in particular if a 64-bit write is supported by its instruction set. This significantly improves the throughput. Not all hosts support Gen2 links, but if it does, the potential throughput is doubled. So all in all, impressive data rates are possible using this primitive method.


The obvious downside of this non-DMA method is that the CPU is busy writing. This may be less of a concern when the processor has multiple cores, in particular with hyper threading support. For example, with a quad core processor supporting hyper threading, the data copy routine occupies one core out of the 8 virtual.


And still, the host’s hardware wasn’t designed to support high bandwidth traffic being carried out this way. Even though the bridge between the processor’s internal bus and PCIe should take the load, other peripherals may suffer from a significant performance degradation due to the flood of requests.


Complicated bus scenarios, which the processor wasn’t designed to cope with, may cause a significant performance hit on the entire system. For example, if the Ethernet hardware driver attempts to access its registers, the TLPs requesting these operations may be significantly delayed, causing a slowdown of apparently unrelated tasks.


For more information, please browse our website or contact a Sopto representative by calling 86-755-36946668, or by sending an email to