{"id":1914,"date":"2017-01-11T04:05:43","date_gmt":"2017-01-11T04:05:43","guid":{"rendered":"http:\/\/support.plunify.com\/en\/?p=1914"},"modified":"2018-08-21T16:05:55","modified_gmt":"2018-08-21T16:05:55","slug":"who-says-you-cant-use-random-seeds-in-vivado","status":"publish","type":"post","link":"https:\/\/support.plunify.com\/en\/2017\/01\/11\/who-says-you-cant-use-random-seeds-in-vivado\/","title":{"rendered":"Who says you can’t use random seeds in Vivado?"},"content":{"rendered":"

It is common knowledge that Vivado uses an analytical place and route engine for better and more predictable design\u00a0closure. As a result, Vivado got rid of the \"cost table\" (also commonly known as random seeds) user options.<\/p>\n

What may be less well-known is that designers still have ways to introduce randomness into Vivado placement. Like the random seeds, this achieves different performance results. We have first-hand accounts from multiple customers relating how they got 10s of nanoseconds of WNS\u00a0fluctuations, by simply making minute tweaks that do not affect the functionality at all. Unfortunately, these fluctuations can go either way, reminiscent of the effects of cost tables or placement seeds.<\/p>\n

We have incorporated this behaviour into a feature on InTime.<\/p>\n

How to run \"random seeds\" with InTime 1.6<\/h2>\n

Without talking too much Chaos Theory and butterflies flapping their wings from across the ocean, this approach is not a hack but a method to subtly introduce various stimuli. The intention is for Vivado to attempt different calculations and end up with different (and potentially better!) results for the otherwise unmodified design.<\/p>\n

InTime's implementation requires that your design be routed beforehand, and it has to contain false timing paths<\/del>. *From InTime 2.0 onwards, this requirement is no longer necessary. Here is how to use the new Placement Exploration<\/em> recipe for Vivado:<\/p>\n

    \n
  1. Open your routed project or DCP in InTime<\/a><\/li>\n
  2. From the recipes dropdown, click and select the Placement Exploration<\/em>\u00a0recipe.
    \n\"button_placement_exploration\"<\/li>\n
  3. Specify the number of different results you want in the \"Runs per Round\" flow property (10 in this example).
    \n\"property_runs_per_round\"<\/li>\n
  4. Click \"Start Recipe\" to start running.<\/li>\n<\/ol>\n

    The following images show the chip view of the implemented design, before and after the Placement Exploration<\/em>:<\/p>\n\n\n\n\n
    Before<\/td>\nAfter<\/td>\n<\/tr>\n
    \"cpu_before<\/td>\n\"cpu_after<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

    Noticeable placement differences
    \nprior to (left) and after (right) running Placement Exploration<\/em>.<\/p>\n

    \n

    We query one of the affected cells via:
    \nget_property LOC [get_cells mgtEngine\/no_chipscope.gt3_rxuserrdy_r_reg].<\/code><\/span><\/p>\n

    Before running the recipe,\u00a0the cell above was at SLICE_X52Y100.<\/code>\u00a0After the placement was stimulated, this cell shifted to SLICE_X38Y126<\/code>. More importantly, the TNS improved by 78ns -- without changing the design at all.\u00a0As randomness is involved, not all results generated via the new Placement Exploration<\/em> recipe will be good. This is a painless approach with no impact on functionality. Read more about it in\u00a0Application Note of Placement Exploration recipe<\/a>.<\/p>\n

    Evaluation<\/h2>\n

    If you are interested in\u00a0trying this feature, sign up here <\/a>to get a free evaluation.<\/p>\n

    Related Post:\u00a0How Much Do You Really Know About Placement Seed Sweep?<\/a><\/p>\n

    Join Plunify Newsletter<\/h3>\n

    <\/h2>\n
    \n\t\t\t\t

    Enter your email address and have the latest insights on FPGA, cloud and Machine Learning delivered straight to your inbox.<\/p>\n<\/div>

    \n

    \n \n \n \n \n\t\t\t\t\t\t