Skip to content

RAM delay in Simple system#2367

Merged
marnovandermaas merged 2 commits intolowRISC:masterfrom
marnovandermaas:benchmark_instructions
Feb 6, 2026
Merged

RAM delay in Simple system#2367
marnovandermaas merged 2 commits intolowRISC:masterfrom
marnovandermaas:benchmark_instructions

Conversation

@marnovandermaas
Copy link
Contributor

The aim of this pull request is to make it possible to do bench-marking on Simple System where the instruction cache actually makes a difference. The RAM must thus respond with a delay on the instruction side.

Copy link
Contributor

@luismarques luismarques left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I just noticed you're merging this into master. We probably don't want to enable that 5-cycle delay by default ;)

@marnovandermaas marnovandermaas force-pushed the benchmark_instructions branch 2 times, most recently from 62ebb33 to 739258b Compare February 5, 2026 14:14
@marnovandermaas marnovandermaas marked this pull request as ready for review February 5, 2026 14:14
@marnovandermaas
Copy link
Contributor Author

Yes, you're right. I'll make the default 0 and expose the delay as a FuseSoC parameter.

This allows an extra delay to be added to the B-port of the RAM.
Add a parameter to Simple system to delay the instruction requests and
expose this in the FuseSoC build instruction.
@marnovandermaas marnovandermaas added this pull request to the merge queue Feb 6, 2026
Merged via the queue into lowRISC:master with commit 8bc7b98 Feb 6, 2026
12 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants