Jump to content
Main menu
Main menu
move to sidebar
hide
Navigation
Main page
Recent changes
Random page
freem
Search
Search
Appearance
Create account
Log in
Personal tools
Create account
Log in
Pages for logged out editors
learn more
Contributions
Talk
Editing
Openai/6936bc88-f39c-800d-8af0-70d83304b81c
(section)
Add languages
Page
Discussion
English
Read
Edit
Edit source
View history
Tools
Tools
move to sidebar
hide
Actions
Read
Edit
Edit source
View history
General
What links here
Related changes
Special pages
Page information
Appearance
move to sidebar
hide
Warning:
You are not logged in. Your IP address will be publicly visible if you make any edits. If you
log in
or
create an account
, your edits will be attributed to your username, along with other benefits.
Anti-spam check. Do
not
fill this in!
=== 2οΈβ£ What does this mean for MI450X specifically? === Given its architecture: * extremely large shared memory * monstrous internal L2 bandwidth * flexible wavefront scheduling * massive FP8/FP6 throughput * better occupancy in odd shapes vs H100/B100 Auto-tuned kernels will get even more uplift on MI450X than on Nvidia Blackwell. Why? β‘οΈ Search space is wider NvCUDA is rigid β MI450βs CDNA has more flexibility (especially for SRAM and tiles). β‘οΈ FP6/FP4 are native, not emulated Auto-generated kernels can lean into FP6/FP4 acceleration. β‘οΈ HBM4 is faster & lower latency Memory-bound kernels dominate the next generation of models. So yes β MI450X is the perfect target for kernel-auto-tuning systems.
Summary:
Please note that all contributions to freem are considered to be released under the Creative Commons Attribution-ShareAlike 4.0 (see
Freem:Copyrights
for details). If you do not want your writing to be edited mercilessly and redistributed at will, then do not submit it here.
You are also promising us that you wrote this yourself, or copied it from a public domain or similar free resource.
Do not submit copyrighted work without permission!
Cancel
Editing help
(opens in new window)
