I created an IP core that uses axi4-stream interface with 4 hls::streams, two of them use the "typedef ap_axis<32,0,0,0> AXI_INT;" and the other two use the "typedef hls::axis<double,4,5,5> AXI_DOUBLE;". I had no problems creating the design in HLS and Vivado.
However, when I try to run the block in Vitis, I noticed I'm not able to send more than 4096 elements to both of the streams, even though I specified their depth as 9886 and 4853 respectively. Why do I have this problem? I'm using the simple mode of AXI DMA. Line 178 of vitis works sucessfuly (because I send up to 4096 elements) but the transfer right below (line 185) gets stuck forever.
Question
Gonçalo Pinho
Hello everyone,
I created an IP core that uses axi4-stream interface with 4 hls::streams, two of them use the "typedef ap_axis<32,0,0,0> AXI_INT;" and the other two use the "typedef hls::axis<double,4,5,5> AXI_DOUBLE;". I had no problems creating the design in HLS and Vivado.
However, when I try to run the block in Vitis, I noticed I'm not able to send more than 4096 elements to both of the streams, even though I specified their depth as 9886 and 4853 respectively. Why do I have this problem? I'm using the simple mode of AXI DMA. Line 178 of vitis works sucessfuly (because I send up to 4096 elements) but the transfer right below (line 185) gets stuck forever.
I send in attachment some pictures of the design.
Thanks for all the attention and time!
Link to comment
Share on other sites
2 answers to this question
Recommended Posts
Create an account or sign in to comment
You need to be a member in order to leave a comment
Create an account
Sign up for a new account in our community. It's easy!
Register a new accountSign in
Already have an account? Sign in here.
Sign In Now