-
Notifications
You must be signed in to change notification settings - Fork 97
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
Fix transpose HC interleaved row major PCC issues when reading from DRAM #14372
Comments
sjameelTT
added a commit
that referenced
this issue
Oct 28, 2024
- Restriction was on alignment, which was hard coded to 16 for L1, which caused PCC issues when read from DRAM #14370: add basic N-d permute code and support both N-d transpose and permute - TODO: make multicore, single-core for now
sjameelTT
added a commit
that referenced
this issue
Oct 28, 2024
- Restriction was on alignment, which was hard coded to 16 for L1, which caused PCC issues when read from DRAM #14370: add basic N-d permute code and support both N-d transpose and permute - TODO: make multicore, single-core for now
sjameelTT
added a commit
that referenced
this issue
Oct 28, 2024
- Restriction was on alignment, which was hard coded to 16 for L1, which caused PCC issues when read from DRAM #14370: add basic N-d permute code and support both N-d transpose and permute - TODO: make multicore, single-core for now
sjameelTT
added a commit
that referenced
this issue
Oct 30, 2024
- Restriction was on alignment, which was hard coded to 16 for L1, which caused PCC issues when read from DRAM #14370: add basic N-d permute code and support both N-d transpose and permute - TODO: make multicore, single-core for now
sjameelTT
added a commit
that referenced
this issue
Oct 31, 2024
- Restriction was on alignment, which was hard coded to 16 for L1, which caused PCC issues when read from DRAM #14370: add basic N-d permute code and support both N-d transpose and permute - TODO: make multicore, single-core for now
sjameelTT
added a commit
that referenced
this issue
Oct 31, 2024
- Restriction was on alignment, which was hard coded to 16 for L1, which caused PCC issues when read from DRAM #14370: add basic N-d permute code and support both N-d transpose and permute - TODO: make multicore, single-core for now
sjameelTT
added a commit
that referenced
this issue
Oct 31, 2024
…ngle core implementation (#14388) #14372: fix transpose hc RM pcc errors - Restriction was on alignment, which was hard coded to 16 for L1, which caused PCC issues when read from DRAM #14370: add basic N-d permute code and support both N-d transpose and permute - TODO: make multicore, single-core for now
o2buzzle
pushed a commit
that referenced
this issue
Nov 4, 2024
…ngle core implementation (#14388) #14372: fix transpose hc RM pcc errors - Restriction was on alignment, which was hard coded to 16 for L1, which caused PCC issues when read from DRAM #14370: add basic N-d permute code and support both N-d transpose and permute - TODO: make multicore, single-core for now
ct-clmsn
pushed a commit
to ct-clmsn/tt-metal
that referenced
this issue
Nov 12, 2024
… permute single core implementation (tenstorrent#14388) tenstorrent#14372: fix transpose hc RM pcc errors - Restriction was on alignment, which was hard coded to 16 for L1, which caused PCC issues when read from DRAM tenstorrent#14370: add basic N-d permute code and support both N-d transpose and permute - TODO: make multicore, single-core for now
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Currently we fallback to tiled when not aligned to 16, we should probably base that on buffer alignment.
The text was updated successfully, but these errors were encountered: