Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

7nm AMD EPYC “Rome” CPU with 64C/128T to Cost $8K (56 Core Intel Xeon: $25K-50K)

techquila.co.in

Post reply on HN
Print view View original

141–150 of 160 posts

Re: 7nm AMD EPYC “Rome” CPU with 64C/128T to Cost $8K (56 Core Intel Xeon: $25K-50K)

#141

Post by metildaa »

tmd83 wrote: post #100
piinbinary wrote: post #99

I'm curious why they aren't charging more for it. Wouldn't that be free profit margin? Or perhaps they are trying to hurt Intel by selling it at a price where Intel can't make a profit if they lower their prices to be competitive? Or, maybe it has to do with trying to quickly grab market share. Maybe AWS and other purchases of servers have a somewhat fixed budget, so cheaper chips translates directly to more chips so…

Only AMD execs truly knows but I think there might be two factors involved. They really want to attract new customers and build echo system and the second part is hard when everyone has been buying almost entirely intel. The second is their cost for such a cheap should be enormously cheaper than intel because of chiplet design. A single chip die for the intel chip is way bigger and yield and cost dramatically increas…

Note that this chip cost increase is due to silicon defects, a larger chip has more defects, thus your failure rate significantly increases with each increase in chip area.

AMD is working around this by using 8 separate CPU chips, wired together with one interconnect chip.

Re: 7nm AMD EPYC “Rome” CPU with 64C/128T to Cost $8K (56 Core Intel Xeon: $25K-50K)

#142

Post by ianai »

sitkack wrote: post #138
api wrote: post #129

Earlier quoted context omitted.

You are in the minority. Most IT and devops people are massively change averse and tend to blame all problems on the most recent change. They would rather pay more for a known quantity. This is even more the case for non technical management.

In 2 to 3 cycles it won't be in their control. We are riding the buggies right now while ICE cars are blasting right past us.

My suspicion is it matters a great deal on OS stack until Microsoft supports ARM in Server. I’m sure the bsd/Linux OSes will have a much easier time transitioning.

Edit-I’m seeing some articles that make it look like arm might already be usable on Windows. There’s still legacy software issues though.

Re: 7nm AMD EPYC “Rome” CPU with 64C/128T to Cost $8K (56 Core Intel Xeon: $25K-50K)

#143

Post by cududa »

ComputerGuru wrote: post #130
rolleiflex wrote: post #56

Earlier quoted context omitted.

No, generally if you're doing the Hackintosh the modern way, you pick your components beforehand from those supported by Mac OS natively (which are excellent components you should already be picking regardless, with the exception of GPUs), and then the only thing you need is the SMC driver I mentioned. I didn't build this machine for Hackintosh, so I have a few drivers (4-5 I think? It tends to need fewer and fewer e…

> My understanding is that it's a standoff between NVidia and Apple largely due to NVidia's poor behaviour the last time NVidia was included in Macbook Pros around 2012. Yes, I have one of those famed 15” rMBPs that many devs say “over my dead body” when you suggest upgrading to a newer model. Zero GPU complaints after the initial bugs were ironed out (and the bad batches replaced). Note that AMD offered virtually no…

A drunk coworker threw my (personal) bag with one of those in a lake. I despise my 2018 MBP.. I miss that thing so much

Re: 7nm AMD EPYC “Rome” CPU with 64C/128T to Cost $8K (56 Core Intel Xeon: $25K-50K)

#144

Post by cududa »

tmd83 wrote: post #100
piinbinary wrote: post #99

I'm curious why they aren't charging more for it. Wouldn't that be free profit margin? Or perhaps they are trying to hurt Intel by selling it at a price where Intel can't make a profit if they lower their prices to be competitive? Or, maybe it has to do with trying to quickly grab market share. Maybe AWS and other purchases of servers have a somewhat fixed budget, so cheaper chips translates directly to more chips so…

Only AMD execs truly knows but I think there might be two factors involved. They really want to attract new customers and build echo system and the second part is hard when everyone has been buying almost entirely intel. The second is their cost for such a cheap should be enormously cheaper than intel because of chiplet design. A single chip die for the intel chip is way bigger and yield and cost dramatically increas…

Your ecosystem argument really holds a lot of water with me. AMD said they wouldn’t be introducing a new socket type until 2021

Re: 7nm AMD EPYC “Rome” CPU with 64C/128T to Cost $8K (56 Core Intel Xeon: $25K-50K)

#145

Post by cududa »

themgt wrote: post #5

Back in the early 2000s Apple was getting crushed because Moto/IBM's PowerPC couldn't keep up with the 880lb gorilla Intel. Who could have predicted even a few years ago Apple would wind up in a similar situation, yet this time for having bet on Intel? Could the 8 core Mac Pro have been $3650 with a $650 Rome CPU, vs. the reality of $6k with a $3k Xeon?

(sidenote- I extremely appreciated the 880 pound gorilla joke)

Re: 7nm AMD EPYC “Rome” CPU with 64C/128T to Cost $8K (56 Core Intel Xeon: $25K-50K)

#146

Post by cududa »

agloeregrets wrote: post #35
themgt wrote: post #5

Back in the early 2000s Apple was getting crushed because Moto/IBM's PowerPC couldn't keep up with the 880lb gorilla Intel. Who could have predicted even a few years ago Apple would wind up in a similar situation, yet this time for having bet on Intel? Could the 8 core Mac Pro have been $3650 with a $650 Rome CPU, vs. the reality of $6k with a $3k Xeon?

In fairness, they are in a much better situation. They could swap to AMD with no real arch changes but I imagine they also would prefer their own CPUs. The fact of the matter is that these CPUs are built on the same exact process as the A12 by the same fab. I would expect, at the scale they are working, a next Apple ARM cpu could be scaled to Rome core counts and have “close” performance at hilariously lower prices.

That’s not really true. Most of MacOS is optimized for intel processors. Things like branch prediction and media encoding/ deciding are extremely different at a low level on AMD/ Intel, and Apple would need to make an enormous investment to rewrite all their perf specific components for AMD.

Re: 7nm AMD EPYC “Rome” CPU with 64C/128T to Cost $8K (56 Core Intel Xeon: $25K-50K)

#147

Post by bitminer »

kjTAB wrote: post #40

I don't believe 64 core, 3.35GHz at 200 Watt. Previous numbers for 64 core were around 2.2GHz. Looks like clickbait to me.

They offering a very wide range of core counts but only a narrow range of watts per socket.

Question: for single threaded performance (*n where threads are independent) do I want higher watts per core or higher number of cores? By "performance" I mean throughput.

Re: 7nm AMD EPYC “Rome” CPU with 64C/128T to Cost $8K (56 Core Intel Xeon: $25K-50K)

#148

Post by jammygit »

rolleiflex wrote: post #98
nottorp wrote: post #95

Earlier quoted context omitted.

Pray tell, where are the docs for AMD hackintoshes? Running on Intel atm but the time for an upgrade is coming close. Do you have power management (and sleep) working on amd?

Start from https://amd-osx.com/ . > Do you have power management (and sleep) working on amd? Yes (null-power-mgmt.kext) and yes. Though mind that this is a desktop, so power mgmt. / sleep needs are much less demanding than a laptop. Specifically, the kext works by disabling power management from within OS X. However I have a kill-a-watt and the the power from the plug varies based on the CPU load, so it seems to be b…

Out of curiosity, what tasks do you use those Xeon/thread ripper CPUs for?

Re: 7nm AMD EPYC “Rome” CPU with 64C/128T to Cost $8K (56 Core Intel Xeon: $25K-50K)

#149

Post by fgonzag »

FireBeyond wrote: post #104
Tuna-Fish wrote: post #75

Earlier quoted context omitted.

Black market, not grey market. QS are loaned on terms that explicitly prohibit resale. If you buy them, you are purchasing stolen goods.

No, you are not. You voiding your contract with Intel does not make me a criminal. At best this is a civil tort.

The person selling you the chip is not the owner of the chip, they were loned to them by Intel, and they didn't pay a dime. You are buying stolen merchandise.

It's exactly the same as if I were to lend you my bike and you were to sell it to someone else. That someone else is buying stolen merchandise.

Re: 7nm AMD EPYC “Rome” CPU with 64C/128T to Cost $8K (56 Core Intel Xeon: $25K-50K)

#150

Post by rolleiflex »

jammygit wrote: post #148
rolleiflex wrote: post #98

Earlier quoted context omitted.

Start from https://amd-osx.com/ . > Do you have power management (and sleep) working on amd? Yes (null-power-mgmt.kext) and yes. Though mind that this is a desktop, so power mgmt. / sleep needs are much less demanding than a laptop. Specifically, the kext works by disabling power management from within OS X. However I have a kill-a-watt and the the power from the plug varies based on the CPU load, so it seems to be b…

Out of curiosity, what tasks do you use those Xeon/thread ripper CPUs for?

Kubernetes, Minikube, Skaffold, Docker. Skaffold especially hits you very hard, because it effectively compiles a docker image, sticks it into Kubernetes, and refreshes the Kubernetes cluster on every save. This is the only sane way to build a distributed app on K8s locally, but doing it for more than an hour legitimately increases the temperature in my flat by a degree or two.
Post reply on HN