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

Power 9 May Dent X86 Servers: Alibaba, Google, Tencent Test IBM Systems

eetimes.com

Post reply on HN
Print view View original

81–90 of 156 posts

Re: Power 9 May Dent X86 Servers: Alibaba, Google, Tencent Test IBM Systems

#81

Post by ethbro »

newman314 wrote: post #78
Twirrim wrote: post #13

One thing I think IBM has failed to grasp about POWER architecture is how to get people to use it. Lots of people in tech talk about being interested in trying it, it has a number of interesting characteristics, but the barrier for entry is fairly high. It's possible to get a POWER8 based server on Softlayer, IBM's cloud product, but not as a VM. You can get one as a bare metal server, but you can't get one for an ho…

So... I sit on the POWER Customer Advisory Board, what you have raised has certainly been something I've told IBM multiple times over the last few meetings I've had with them. I plan to continue pushing on this front.

From IBM's history, I'd assume this is chalked up to IBM institutional inertia (enterprise customers make big deployments, nothing else matters) than willfully doing it for some other profit-oriented purpose?

Re: Power 9 May Dent X86 Servers: Alibaba, Google, Tencent Test IBM Systems

#82

Post by newman314 »

ethbro wrote: post #81
newman314 wrote: post #78

Earlier quoted context omitted.

So... I sit on the POWER Customer Advisory Board, what you have raised has certainly been something I've told IBM multiple times over the last few meetings I've had with them. I plan to continue pushing on this front.

From IBM's history, I'd assume this is chalked up to IBM institutional inertia (enterprise customers make big deployments, nothing else matters) than willfully doing it for some other profit-oriented purpose?

There are NDA items I can't get into but certainly it's not the case where I've just been shouting into the wind.

Re: Power 9 May Dent X86 Servers: Alibaba, Google, Tencent Test IBM Systems

#83

Post by jacques_chester »

kev009 wrote: post #36
rwmj wrote: post #31

Earlier quoted context omitted.

Come on, you can buy a load of ARM 64 bit development boards starting from just a few tens of dollars. There is no problem at all getting access to ARM. And from there you can scale up to Cavium 2 or Amberwing which have Xeon-like performance (better than Xeon in some ways). If there's a problem with ARM I'd say it's still the lack of standardization, and also very few mid-range servers. POWER is nothing like this. T…

You can't actually buy TX2. I don't know about market availability of Amberwing either (if you know please let me know). There is an abundance of arm stuff in the embedded space where it is king, and it's true you can pick them up for next to nothing but somewhat orthogonal to servers (flattened device trees vs ACPI/UEFI etc) You can web buy an S821LC straight from IBM for $5k for the past couple years. The AC922 is…

> Not directly related to your comment but I get the feeling a lot of people complaining about price are navel gazing and have no idea how much a production server costs and how the costs break down.

They're not asking for production servers.

$5k for a workstation, for a minority architecture, is basically a fancy way of saying "no" to the army of tinkerers you need to widen the base.

Re: Power 9 May Dent X86 Servers: Alibaba, Google, Tencent Test IBM Systems

#84

Post by opencl »

dragontamer wrote: post #44
opencl wrote: post #38

Earlier quoted context omitted.

The mobo+single quad core CPU is $2,475, that's way more than the threadripper setup and the threadripper has 4x the core count.

Threadripper also only has 8MB of L3 cache per CCX, and you can't hold more than 8MB of data. (true, there are 4x CCX per chip, but you can't "combine" the datasets. You're effectively limited to 8MB per 4-cores. To communicate cross-CCX requires an expensive ping to main-memory) Its a great architecture, but cross-CCX communication is relatively slow and definitely is a concern for some work problems. Power9 has 120…

That's a dual socket system with 16 cores per socket. Dual socket Epyc 7351 (also 16 core per socket) is faster and more power efficient than that. 3200H/s at 332W.

https://www.youtube.com/watch?time_continue=226&v=CS7M392Ia_...

I'm sure there are workloads that really do benefit from the huge unified L3, but it seems like a pretty small niche.

Re: Power 9 May Dent X86 Servers: Alibaba, Google, Tencent Test IBM Systems

#85

Post by PedroBatista »

newman314 wrote: post #78
Twirrim wrote: post #13

One thing I think IBM has failed to grasp about POWER architecture is how to get people to use it. Lots of people in tech talk about being interested in trying it, it has a number of interesting characteristics, but the barrier for entry is fairly high. It's possible to get a POWER8 based server on Softlayer, IBM's cloud product, but not as a VM. You can get one as a bare metal server, but you can't get one for an ho…

So... I sit on the POWER Customer Advisory Board, what you have raised has certainly been something I've told IBM multiple times over the last few meetings I've had with them. I plan to continue pushing on this front.

All of IBM DNA is structured to sell big contracts and deal with a relative small number of customers with very deep pockets.

Even when they try some new trend ( aka cloud computing for the masses ) the economics aren't that good because the way they are structured, it's a culture thing.

It's like Intel developing ARM CPUs, they have the means, but they can't do it successfully.

Re: Power 9 May Dent X86 Servers: Alibaba, Google, Tencent Test IBM Systems

#86

Post by ramereth »

Twirrim wrote: post #13

One thing I think IBM has failed to grasp about POWER architecture is how to get people to use it. Lots of people in tech talk about being interested in trying it, it has a number of interesting characteristics, but the barrier for entry is fairly high. It's possible to get a POWER8 based server on Softlayer, IBM's cloud product, but not as a VM. You can get one as a bare metal server, but you can't get one for an ho…

We (Oregon State University Open Source Lab) have been working with IBM for the last few years to help with this problem. We host a set of P8 (and soon P9) machines for them so FOSS projects can work on porting issues. You're welcome to sign up if you're interested [1].

[1] http://osuosl.org/services/powerdev/

Re: Power 9 May Dent X86 Servers: Alibaba, Google, Tencent Test IBM Systems

#87

Post by Twirrim »

bluedino wrote: post #11

I can see China running with ARM and POWER, ditching Intel entirely. Google, on the other hand would need a reason to switch. Somewhere there's a spreadsheet with a number for energy cost savings that would make it worth it for Google to switch architectures. I've heard it's as low as 10%.

> https://www.forbes.com/sites/patrickmoorhead/2018/03/19/head...

Google is already at least experimenting with POWER9, but it's not clear just how far that goes.

Re: Power 9 May Dent X86 Servers: Alibaba, Google, Tencent Test IBM Systems

#88

Post by simonebrunozzi »

Twirrim wrote: post #13

One thing I think IBM has failed to grasp about POWER architecture is how to get people to use it. Lots of people in tech talk about being interested in trying it, it has a number of interesting characteristics, but the barrier for entry is fairly high. It's possible to get a POWER8 based server on Softlayer, IBM's cloud product, but not as a VM. You can get one as a bare metal server, but you can't get one for an ho…

I absolutely agree. It baffles me that after TWELVE years from the launch of S3 and EC2, IBM still hasn't understood what made them popular. (hint: the pay-as-you-go model).

Re: Power 9 May Dent X86 Servers: Alibaba, Google, Tencent Test IBM Systems

#89

Post by planteen »

rbanffy wrote: post #77
blattimwind wrote: post #33

Earlier quoted context omitted.

ARM dev boards are generally based on toy-sized SoCs, though.

They are still useful though. If you want to build an 7-node cluster of 2GB nodes on a single Mini ITX motherboard, it's even cheap. And requires no messy cables. https://www.pine64.org/?product=clusterboard-with-7-module-s... and seven https://www.pine64.org/?product=sopine-a64

That's neat. I had heard of the PINE64 board but never the SOPINE. Curious, have you implemented any projects on this? Seems like it might be neat for testing a small distributed system.

Re: Power 9 May Dent X86 Servers: Alibaba, Google, Tencent Test IBM Systems

#90

Post by slededit »

Quequau wrote: post #66
dragontamer wrote: post #52

Earlier quoted context omitted.

For those not in the know: Each Power9 is consisting of either 2-super slices or 4-super slices, depending on which Power9 you get. (Corresponding to 4x SMT or 8x SMT respectively). Threadripper has 4x integer pipelines, 4x floating point pipelines, and 2x load/store units (called AGUs by AMD) and supports 2-threads (aka: 2x SMT). So Threadripper definitely is "broad", but Power9 is "broader". The 8x SMT Power9 can p…

The last presentation on Power at Hotchips left me with the impression that "Core" in IBM terms is 9/10ths marketing speak and whatever Power might have that their engineers might think of as "cores" probably has little to do with what their marketing people are telling their customers and software vendors who do their licensing "per core".

Could you expand a bit on this? Are you saying they are inflating their core count or the reverse? Everything I've looked at indicates significantly more powerful cores.
Post reply on HN