Skip to content
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

[sgemm] Mixed precision with inline function calls #49

Closed

Conversation

s-debadri
Copy link

SGEMM modifications made:

  • Used mixed precision calculations: fp16 multiplications with fp32 additions.
  • Modified function calls to inline calls to reduce register spilling.
  • Temporary fp32 storage used to enhance accuracy.

Self evaluation:

  1. Build test: [X]Passed [ ]Failed [ ]Skipped
  2. Run test: [X]Passed [ ]Failed [ ]Skipped

Signed-off-by:s-debadri [email protected]

Used mixed precision calculations: fp16 multiplications with fp32 additions.
Modified function calls to inline calls to reduce register spilling.
Temporary fp32 storage used to enhance accuracy.

**Self evaluation:**
1. Build test:	 [X]Passed [ ]Failed [ ]Skipped
2. Run test:	 [X]Passed [ ]Failed [ ]Skipped

Signed-off-by: Debadri Samaddar <[email protected]>
Used dynamic fp32 array to avoid reaching stack limit.

Signed-off-by: Debadri Samaddar <[email protected]>
@s-debadri s-debadri changed the title [WIP][sgemm] Mixed precision with inline function calls [sgemm] Mixed precision with inline function calls Oct 10, 2023
@s-debadri s-debadri closed this May 23, 2024
@s-debadri s-debadri deleted the jjm_qin4_inline_mixed_precision branch May 23, 2024 07:43
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.

1 participant