IPB

Welcome Guest ( Log In | Register )

Profile
Personal Photo
Rating
 
Options
Options
Personal Statement
joeclark doesn't have a personal statement currently.
Personal Info
joeclark
sofer
Age Unknown
Gender Not Set
Location Unknown
Birthday Unknown
Interests
No Information
Statistics
Joined: 21-June 17
Profile Views: 0*
Last Seen: 25th July 2017 - 11:20 AM
Local Time: Mar 29 2024, 01:54 PM
72 posts (0.03 per day)
Contact Information
AIM No Information
Yahoo No Information
ICQ No Information
MSN No Information
* Profile views updated each hour

joeclark

Membri

***


Topics
Posts
Comments
Friends
My Content
10 Jul 2017
Hi all, apologies if this is the wrong forum for this, it would be much appreciated if someone could point toward the right one.

Disclaimer: I'm new to VHDL.

I'm looking to implement a multiplier-less multiplier for an FIR filter. I'm trying to be as general as possible, so I don't want to hard-code my component placements. Is there a good method of procedurally generating a component (i.e. a multiplier)? I've encoded the digits of the constant multiplicand in CSD and stored it as string which I'm passing into the component via a 'generic' statement. Now I'm attempting to use a generate loop (looping over the string) to place adders, subtractors, and shifters. The issue is that the Startup Marketing Video output of one adder/subtractor is piped directly into the input of the next one and since there is an unknown amount of adders, I can't declare the signals before hand. What's the best way to go about this?
10 Jul 2017
Hello,
I am trying to create a design where I have three IP block one block doing matrix-vector multiplication at a different clock, the second block inititlaizes the algortihm parameters to zero and the third ip implements the rest of the algorithm I am using Microblaze to send vectors and matrix input to the blocks.
The design looks like this:
- The microblaze sends vector input to the initialization block which then initializes few vectors to be then used by matrix-vector mul ip and main ip. The output from the init block is in the form of a stream and is send to the matrix multiplication block for matrix-vector multiplication. The Matrix is send to the matrix mul block by microblaze as its a huge matrix and cant be stored locally on fpga. The init block should be used only for the first time and later it should not be used for any computation and the rest computation should be carried by main ip block. After computing matrix mul, the output is sent as stream to the main algorithm ip, where several operations are computed in a loop and whenever the matrix vector cal occurs the vector is sent as input stream to the matrix-vector mul block and matrix is retrieved from microblaze and output from matrix vector is again sent as stream to the main ip block.
My question is since at first I am using init block to send input vector as hls:stream to matrix-vector mul ip only once and then everytime I require matrix-vector multiplication to happen, I am sending vectors from main IT Security Explainer Video ip as hls:stream to the matrix-vector mul ip. How can I make sure that matrix-vector mul block takes input streams from init block only for the first time and for rest of the time the input vectors are taken from main ip.
Last Visitors


24 Jul 2017 - 15:48

Comments
Other users have left no comments for joeclark.

Friends
There are no friends to display.
RSS Lo-Fi Version Time is now: 29th March 2024 - 02:54 PM
IPS Driver Error

IPS Driver Error

There appears to be an error with the database.
You can try to refresh the page by clicking here