-
Notifications
You must be signed in to change notification settings - Fork 75
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
FD2.1 finish cleanup of runtime address map (use dynamic address map) #4984
Labels
Comments
pgkeller
added a commit
that referenced
this issue
Jan 26, 2024
pgkeller
added a commit
that referenced
this issue
Jan 28, 2024
pgkeller
added a commit
that referenced
this issue
Jan 28, 2024
pgkeller
added a commit
that referenced
this issue
Jan 29, 2024
pgkeller
added a commit
that referenced
this issue
Jan 29, 2024
pgkeller
added a commit
that referenced
this issue
Jan 29, 2024
pgkeller
added a commit
that referenced
this issue
Jan 29, 2024
vtangTT
pushed a commit
that referenced
this issue
Jan 31, 2024
vtangTT
pushed a commit
that referenced
this issue
Jan 31, 2024
pgkeller
changed the title
finish cleanup of runtime address map
finish cleanup of runtime address map (use dynamic address map)
Feb 13, 2024
pgkeller
changed the title
finish cleanup of runtime address map (use dynamic address map)
FD2.1 finish cleanup of runtime address map (use dynamic address map)
Apr 13, 2024
pgkeller
added a commit
that referenced
this issue
Jul 29, 2024
pgkeller
added a commit
that referenced
this issue
Jul 29, 2024
pgkeller
added a commit
that referenced
this issue
Jul 29, 2024
pgkeller
added a commit
that referenced
this issue
Jul 29, 2024
Turns out ZEROS is still used, so couldn't reclaim that This reduces the dead space at low memory and fixes a hack in watcher for determining hex value of the jump insn at address 0
pgkeller
added a commit
that referenced
this issue
Jul 30, 2024
In prep for having firmware/kernel specific linker scripts
pgkeller
added a commit
that referenced
this issue
Jul 30, 2024
pgkeller
added a commit
that referenced
this issue
Jul 30, 2024
Turns out ZEROS is still used, so couldn't reclaim that This reduces the dead space at low memory and fixes a hack in watcher for determining hex value of the jump insn at address 0
pgkeller
added a commit
that referenced
this issue
Jul 30, 2024
In prep for having firmware/kernel specific linker scripts
mo-tenstorrent
added a commit
that referenced
this issue
Sep 12, 2024
mo-tenstorrent
added a commit
that referenced
this issue
Sep 12, 2024
mo-tenstorrent
added a commit
that referenced
this issue
Sep 12, 2024
mo-tenstorrent
added a commit
that referenced
this issue
Sep 12, 2024
mo-tenstorrent
added a commit
that referenced
this issue
Sep 12, 2024
mo-tenstorrent
added a commit
that referenced
this issue
Sep 12, 2024
mo-tenstorrent
added a commit
that referenced
this issue
Sep 12, 2024
mo-tenstorrent
pushed a commit
that referenced
this issue
Sep 13, 2024
Storage cores used to include mailboxes for the L1 barrier L1 barrier is no longer in the mailboxes, so update the base address to the base of the mailboxes
mo-tenstorrent
pushed a commit
that referenced
this issue
Sep 13, 2024
And out of the common runtime address map
mo-tenstorrent
added a commit
that referenced
this issue
Sep 13, 2024
mo-tenstorrent
added a commit
that referenced
this issue
Sep 13, 2024
mo-tenstorrent
added a commit
that referenced
this issue
Sep 13, 2024
mo-tenstorrent
added a commit
that referenced
this issue
Sep 13, 2024
pgkeller
added a commit
that referenced
this issue
Sep 15, 2024
Storage cores used to include mailboxes for the L1 barrier L1 barrier is no longer in the mailboxes, so update the base address to the base of the mailboxes
pgkeller
added a commit
that referenced
this issue
Sep 15, 2024
And out of the common runtime address map
pgkeller
pushed a commit
that referenced
this issue
Sep 15, 2024
pgkeller
pushed a commit
that referenced
this issue
Sep 15, 2024
pgkeller
pushed a commit
that referenced
this issue
Sep 15, 2024
pgkeller
added a commit
that referenced
this issue
Sep 16, 2024
Storage cores used to include mailboxes for the L1 barrier L1 barrier is no longer in the mailboxes, so update the base address to the base of the mailboxes
pgkeller
added a commit
that referenced
this issue
Sep 16, 2024
And out of the common runtime address map
pgkeller
pushed a commit
that referenced
this issue
Sep 16, 2024
pgkeller
pushed a commit
that referenced
this issue
Sep 16, 2024
pgkeller
pushed a commit
that referenced
this issue
Sep 16, 2024
pgkeller
added a commit
that referenced
this issue
Sep 16, 2024
Storage cores used to include mailboxes for the L1 barrier L1 barrier is no longer in the mailboxes, so update the base address to the base of the mailboxes
pgkeller
added a commit
that referenced
this issue
Sep 16, 2024
And out of the common runtime address map
pgkeller
pushed a commit
that referenced
this issue
Sep 16, 2024
pgkeller
pushed a commit
that referenced
this issue
Sep 16, 2024
pgkeller
pushed a commit
that referenced
this issue
Sep 16, 2024
This is effectively done other than the last steps of cleanup w/ the hal. Closing, will open other issues for the remaining work |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Finish cleaning up the address map, started under #403. Including but not limited to:
Also, kernel binaries and local data memory are currently written to the device as 2 separate spans, these could be packed to reduce dispatch overhead
The text was updated successfully, but these errors were encountered: