Jump to content
HWBOT Community Forums

Recommended Posts

Posted (edited)

Amazing!!! :)

Is Zambezi still faster than Vishera on SuperPI even using "The Plow of Bulldozer" on both? If the answer is yes, sub-9s with AMD can be a reality eh? :D

Edited by NoMS
Posted

Honestly, I don't know why no company is hiring you as addition to the RD team. You not only managed to "out-code" every single AMD ODM BIOS team, but now also managed to figure out a fix for a benchmark that made AMD look superslow compared to previous products.

 

Have you declined offers? :D

  • Crew
Posted

lol talk about hiring. i was chatting to one of the guys from bios team and she said she was there for "only" 8 years. That's considered a junior position still LOL damn

Posted
lol talk about hiring. i was chatting to one of the guys from bios team and she said she was there for "only" 8 years. That's considered a junior position still LOL damn

 

... and that's why some companies get ahead of others. Same story with Shamino, actually (although his talents are in a different field).

 

No offense to you. I know the people who make these decisions are in completely different departments and there's more than just "enthusiast" as requirement.

Posted
Amazing!!! :)

Is Zambezi still faster than Vishera on SuperPI even using "The Plow of Bulldozer" on both? If the answer is yes, sub-9s with AMD can be a reality eh? :D

 

I'm not sure if the difference is still there after the new AGESA & µCode versions.

If it is, < 9 seconds will happen in no time. In any case < 9 seconds will be easy on Vishera too.

 

The part I was using yesterday was an ultra low leak / ultra high aq specimen, which maxes out at ~ 1.97V on LN2. During the 9.547 second run on the video, the voltage was around 1.89V during the PI. 1.50000V VID + 0.4V offset, loadline set to 0.525mOhm ("Ultra High").

 

The newer (packed >= 44/12) FX-8 -series parts should be able to do SuperPI 1M at 8GHz - 8.2GHz, if you have a good specimen of course. My clocks were ~ 7900MHz (31.5 * 250.8) in the 9.547s run.

 

Also disabling the "slave" cores on Zambesi should still help in SuperPI as the remaining "master" core will have a full L2 cache and L3 partition for it's private disposal.

 

For Trinity and Richland there is no difference any more between the masters and the slaves. Not sure about Vishera as its been a while since I tested it.

 

At some point I will see what happens when you have a 4MB L3 cache per CU instead of the normal 2MB. This naturally requires downcoring as only 8MB of L3 physically exists.

The same configuration is used in some of the Opterons, FX-4350 and partially in FX-6 series (1x 4MB, 2x 2MB).

 

Of course you could set 4MB for the executing CU, 2MB for the seconds CU and 1MB for the remaining two :D

  • Crew
Posted

Incredible result! Nice to see some AMD superpi performance.

 

It seems Im the only one who dont knows the app "The Plow of Bulldozer"? I cant imagine a 2-3sec increasement in sp1m by just manually alter some pstates so it must be the app, or whatever kind of magic you apply here...

 

...and why did the little bulldozer lost its plow? Sorry for asking Im just curios :D

Posted
Incredible result! Nice to see some AMD superpi performance.

 

It seems Im the only one who dont knows the app "The Plow of Bulldozer"? I cant imagine a 2-3sec increasement in sp1m by just manually alter some pstates so it must be the app, or whatever kind of magic you apply here...

 

...and why did the little bulldozer lost its plow? Sorry for asking Im just curios :D

 

Here he explains what is the "Plow of Bulldozer": http://www.xtremesystems.org/forums/showthread.php?286448-The-Book-of-Bulldozer-Revelations-Episode-2-(SuperPI-x87)

Posted
Honestly, I don't know why no company is hiring you as addition to the RD team. You not only managed to "out-code" every single AMD ODM BIOS team, but now also managed to figure out a fix for a benchmark that made AMD look superslow compared to previous products.

 

Have you declined offers? :D

 

Agreed,adding the stilt to a r&d team should make a huge addition to anyone...

Join the conversation

You can post now and register later. If you have an account, sign in now to post with your account.

Guest
Reply to this topic...

×   Pasted as rich text.   Paste as plain text instead

  Only 75 emoji are allowed.

×   Your link has been automatically embedded.   Display as a link instead

×   Your previous content has been restored.   Clear editor

×   You cannot paste images directly. Upload or insert images from URL.

×
×
  • Create New...