I am running into throughput and throttling issues from the AXI VDMA itself (i.e., the interconnect is sitting idle waiting for transactions, but I am getting throttled on the stream side of the AXI VDMA).
What is wrong?
There is a known limitation with the core (it is actually a limitation of the AXI Datamover upon which the AXI VDMA is built) where throughput suffers greatly if your stream-side clocks are faster than your memory map-side clocks.
Please ensure that your memory map clocks (excluding the AXI Lite clock) are at least as fast as your stream clocks.
Answer Number | 问答标题 | 问题版本 | 已解决问题的版本 |
---|---|---|---|
47654 | AXI Video Direct Memory Access (VDMA) - Release Notes and Known Issues | N/A | N/A |
54448 | LogiCORE IP AXI Video Direct Memory Access - Release Notes and Known Issues for Vivado 2013.1 and newer tool versions | N/A | N/A |
AR# 54878 | |
---|---|
日期 | 06/03/2013 |
状态 | Archive |
Type | 综合文章 |
IP |