Earlier quoted context omitted.
Well depending on if the rumors about the 64 core Threadripper are true you could do that later this year or maybe early next year
and still have some I/O operation block your entire GUI/OS :D
elaborate?
AMD EPYC “Rome” Server Processors to Feature 8 to 64 Cores
31–40 of 115 posts
Re: AMD EPYC “Rome” Server Processors to Feature 8 to 64 Cores
#32Does anyone have an idea how many different processors tapeouts are needed to create this line? It seems reasonable to assume that 48-core chip is just 64-core chip with few defective cores. A lower clocked version is the same ship that high clocked that did not pass some test.
There's 9 different independent pieces of silicon on the 64-core chip. It looks like this: https://images.anandtech.com/doci/13561/amd_rome-678_678x452... ( source https://www.anandtech.com/show/13561/amd-previews-epyc-rome-... )
Each of those smaller dies is 8 cpu cores. So 8x8 = 64. The 48-core one could either be 6 full-yield chiplets, or 8 partially defective ones with just 6 cores active. I'd guess it's 8 chiplets with 6 cores each just because that seems like it'd be more balanced, but I don't think we'll know for sure until someone de-lids a shipping one.
Re: AMD EPYC “Rome” Server Processors to Feature 8 to 64 Cores
#33What's stopping them from creating 1000 core cpus?
Re: AMD EPYC “Rome” Server Processors to Feature 8 to 64 Cores
#34What's stopping them from creating 1000 core cpus?
Heat, energy usage.
Re: AMD EPYC “Rome” Server Processors to Feature 8 to 64 Cores
#35Earlier quoted context omitted.
Intel chips are still significantly better than AMD for many common workloads. If you are running SpecCPU or Cinebench in production then AMD might be right for you; in all other cases I urge you to run your own realistic benchmarks before buying. Intel’s “response” to Rome came out in April. It’s a 28-core chip that costs $12k. The reason Intel doesn’t feel price pressure here is they are still way ahead in performa…
Rome is Zen 2. You have absolutely no clue whatsoever how it performs. It may still have the weaknesses of Zen 1, but it very well might not. AMD made a bunch of changes, including a complete overhaul of the memory system (no more NUMA). We'll know for sure when the product is actually out and we have independent benchmarks, but at this point you're just making things up and stating them as facts. That aside Epyc was…
Don’t assume everyone suffers from the same ignorance that you suffer. All buyers in a position to order large quantities of CPUs have Rome samples and have had them for a long time, yet Intel price doesn’t budge. Why?
Re: AMD EPYC “Rome” Server Processors to Feature 8 to 64 Cores
#36The real question for me with all these AMD releases, what's Intel gonna release? It's surprising to me that Apple didn't announce an AMD based Mac Pro-- the chip Intel gave them must really be something. Too bad though because there could be a lot more of them (eventual Mac Pros) out there I'm guessing if they were using these Rome chips.
Intel chips are still significantly better than AMD for many common workloads. If you are running SpecCPU or Cinebench in production then AMD might be right for you; in all other cases I urge you to run your own realistic benchmarks before buying. Intel’s “response” to Rome came out in April. It’s a 28-core chip that costs $12k. The reason Intel doesn’t feel price pressure here is they are still way ahead in performa…
> on real high-end workloads like DBMSs
DBMSs are normally IO constrained or memory constrained, or lack-of-index index constrained or query-plan-gone-mental-from-cardinality-misestimation constrained, or others. It's very unusual IME to find one that is CPU constrained. Bringing up DBs in this context is peculiar to say the least.
I've literally just lost 20 hours trying to debug a query that intermittently ran many times too slow. It was a memory misconfiguration. Extra CPU is at best a bandage over these kinds of problems, at worst, just wasted.
Re: AMD EPYC “Rome” Server Processors to Feature 8 to 64 Cores
#37The real question for me with all these AMD releases, what's Intel gonna release? It's surprising to me that Apple didn't announce an AMD based Mac Pro-- the chip Intel gave them must really be something. Too bad though because there could be a lot more of them (eventual Mac Pros) out there I'm guessing if they were using these Rome chips.
There's probably bit of hardware lot it with Intel chips. Since they control the hardware, Apple probably has invested quite a bit into hardware specific optimizations that won't readily port to AMD chipsets. Also, AMD is only recently been a performance front runner - they might not hold on to that for long. In the short term it doesn't make sense to jump ship. For for general computation/ecosystems or for generatio…
Since they control the hardware, Apple probably has invested quite a bit into hardware specific optimizations that won't readily port to AMD chipsets.
It's in Apple's history to be able to move on from hardware. It's also in their history to make the wrong choices, necessitating the move.
Re: AMD EPYC “Rome” Server Processors to Feature 8 to 64 Cores
#3864 cores but 128 with simultaneous multithreading. And in a 2C configuration, you get 256 threads. That is a beautiful thing.
I had a quad CPU Dell server. Imagine 512 threads :-0
Re: AMD EPYC “Rome” Server Processors to Feature 8 to 64 Cores
#39The real question for me with all these AMD releases, what's Intel gonna release? It's surprising to me that Apple didn't announce an AMD based Mac Pro-- the chip Intel gave them must really be something. Too bad though because there could be a lot more of them (eventual Mac Pros) out there I'm guessing if they were using these Rome chips.
Apple, like all big vendors, is trapped by the mobile processors. There is still no way around Intel there. Until they are willing to get rid of Intel Chips in their whole lineup, they can't offer AMD chips in their desktop machines. For the same reason, AMD didn't gain dominance in the times the Opteron ran circles around the Intel chips.