- Mar 3, 2017
- 1,777
- 6,791
- 136
From this patch, Zen 5 seems to have at most 1x ALU sched + 1x AGU sched (if not 1x ALU/AGU sched), more Golden Cove like (1x Math + 1x Load + 1x Store sched)
Z1 (4x ALU + 2x AGU sched), Z2 (4x ALU + 1x AGU sched), Z3/4 (4x ALU/AGU sched)
Additionally, they have prefetching updates for L1/L2 instead of just stream, stride, burst, nextline
They changed the core a lot.
Yeah indeed he has real info.MLID with a Zen 5 video:
He also shared another Z5 slide
The Steves are vocal, but they aren't particularly the problem.Apologies in advance for getting a bit snarky but I have to be honest...... This section of your post comes off as a long winded way to call the Aussie Steve and Tech Jesus' of the world disingenuous shills. Yawn. AM4 's longevity/compatibility has been, and continues to be, good for consumers. Your unfalsifiability fallacy doesn't change that.
heheYeah indeed he has real info.
he put out real slides. The slides has been corroborated with patches.hehe
🤐he put out real slides. The slides has been corroborated with patches.
I don't see that from anyone. Do you think he has wrong slides?
He has old af infosYeah indeed he has real info.
Same thing I found in the patches on the 1x ALU sched + 1x AGU sched
I am inclined to believe the ~20% IPC on his slide with few % (+3% or +4% ??) clocks
However I am not sure even partners knows exactly the specific IPC number that will be claimed at launch, pretty easy to block some prefetchers or perf enhancing chicken bits with firmware too.
Dawn of the Second Month.he put out real slides. The slides has been corroborated with patches.
I don't see that from anyone. Do you think he has wrong slides?
You don’t have to zip your mouth, you can tell us and share the info you got.
Indeed.Whoever turns out dead wrong, it'll be a show to see.
Don't wanna act like his fanboy, but Kepler wasn't wrong. Everyone was wrong. Azor and Sherkelman went up the stage and dropped the "50% more perf, 50% better perf/W" a month before the hungry wattsucker was dropped in your PCIe slots.Indeed.
Kepler has to redeem himself this time. His poor RNDA3 showing still taints his reputation.
Took an L n X like a champ though.
The RDOA3 stuff is also hilarious when people see RDNA3.5. Vindication feels nice.Don't wanna act like his fanboy, but Kepler wasn't wrong. Everyone was wrong. Azor and Sherkelman went up the stage and dropped the "50% more perf, 50% better perf/W" a month before the hungry wattsucker was dropped in your PCIe slots.
Everyone was wrong. AMD lied bold face to us, or somehow thought they would fix something within the last month.
Incidentally this is also an event that cut the wheat from the chaff for me, in terms of leakers. Some took the L, some threw the L at everyone but them to save face.
I just complimented you, don't start saying stuff that makes you sound like one of the "Battlemage will save ARC guys!!!"The RDOA3 stuff is also hilarious when people see RDNA3.5. Vindication feels nice.
Do we have to wait for Zen 5.5+ before these new predictions are also proven correct?The RDOA3 stuff is also hilarious when people see RDNA3.5. Vindication feels nice.
Don't wanna act like his fanboy, but Kepler wasn't wrong. Everyone was wrong. Azor and Sherkelman went up the stage and dropped the "50% more perf, 50% better perf/W" a month before the hungry wattsucker was dropped in your PCIe slots.
The RDOA3 stuff is also hilarious when people see RDNA3.5. Vindication feels nice.
In laptops. I want it in ma 8750G yo!Cheap but good WGPs for the people.
Strix is right around the corner.Do we have to wait for Zen 5.5+ before these new predictions are also proven correct?
Without divulging your sources, can you tell us if it is coming from the same avenue as the RDNA3 information? Presumably it must be different or you wouldn't trust them again.Strix is right around the corner.
I thought it was paper launch Q4??Strix is right around the corner.
Q3I thought it was paper launch Q4??
His source is the drainage pipe that he puts his ear to that leads directly to the AMD brass meeting room.Without divulging your sources, can you tell us if it is coming from the same avenue as the RDNA3 information? Presumably it must be different or you wouldn't trust them again.
I was thinking that if they wanted that, they'd be pushing a lot more volume already...I just think they want to enjoy their supremacy in CPUs as early as possible.Mobile and desktop launching together??? What? They wanna bankrupt Intel???
One will be a paper launch (and it's not Granite Ridge).Mobile and desktop launching together??? What? They wanna bankrupt Intel???
funny amirite brother.hehe
Stx1 is >$1200 srp lappies, expensive shebangs.Mobile and desktop launching together???
it wasn't his problem.His poor RNDA3 showing still taints his reputation or at least people's perception of info he put out.
Once ARL is out, we should return to this post...you are all wrong, IPC uplift is 37% for AMD and for Intel it’s 3.7%.