Intel Arria 10 compatibility #234
Open
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Split the critical path from global lock signal to ifetch's cycle and lock counters. Registers the input to the counters, so that the global lock signal does not need to propagate entirely through the 64-bit adder.
Variants of xilinx_dp_blockram which infer BRAM on Arria 10.
Also tests the functionality of intel bram-models. (Doesn't test that they infer correctly)
pjaaskel
approved these changes
Jun 19, 2023
|
Also this needs to be rebased, tested and pulled in. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Some recent changes I needed to get processors generated for Intel Arria 10. These include:
Adding BRAM models that infer on Arria 10. (The old ones wouldn't infer BRAM, and the ones I add now don't infer on Xilinx :( They are just regular RTL, but the tools are very picky about the exact syntax)
Add latency to the clock cycle counter. This helped quite a lot with the clock frequency since it cuts the critical path from global_lock to the 64-bit counter.
Add wlast to AlmaIF's AXI master interface. Intel tools needed this, or it wouldn't work. The signal is hardcoded to 1, since there is no burst support from the master IF.