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

IBM Launches Z13 Mainframe

www-03.ibm.com

Post reply on HN
Print view View original

61–70 of 104 posts

Re: IBM Launches Z13 Mainframe

#61

Post by JoachimS »

trsohmers wrote: post #32
jacquesm wrote: post #6

Earlier quoted context omitted.

How so? How does an ARM powered smartphone or tablet trace back to IBM?

It's a lot easier to claim that all modern processors (that are based on a load/store architecture... All RISC chips, basically... and that includes x86) trace back to the CDC 6600, probably Seymour Cray's most direct and influential gift to the world of computing.

And the IBM reference would be IBM 801 by John Cocke:

http://en.wikipedia.org/wiki/IBM_801 http://en.wikipedia.org/wiki/John_Cocke

Dunno how much it actually influenced the Archimedes though.

Re: IBM Launches Z13 Mainframe

#62

Post by DonHopkins »

chime wrote: post #41
ivansavz wrote: post #31

The part about the in-memory analytics reminds me a lot of the SAP HANA spiel: Transaction Database --> copy --> analytics db = slow In-memory transactions with built-in analytics = fast I totally understand the value of analytics and BI applications, but does it all have to be realtime? And what "mobile analytics" are they going to compute exactly? Forget analytics, I can tell you what mobile users are doing right n…

Their customers are not King.com or most techie startups. Their customers are insurance companies, banks, and other financial behemoths. My bank recently alerted me because I swiped my credit card at one gas station away from home but did not buy gas (the pump was out of gas) and then swiped again at another gas station in a 3mi radius within 30 minutes (obviously since I needed gas). Their system picked up these two…

I thought the customer was always king, and nobody ever got fired for choosing IBM.

Re: IBM Launches Z13 Mainframe

#63

Post by DonHopkins »

halayli wrote: post #34
jacquesm wrote: post #22

Earlier quoted context omitted.

http://en.wikipedia.org/wiki/Transaction_processing_system

I know that but this is a very general definition of TPS. How many CPU cycles a transaction requires? It varies on the transaction of course. So I am wondering why they use TPS as a unit when it can be anything.

How many TPS Reports per second can it issue?

Re: IBM Launches Z13 Mainframe

#64

Post by pbourke »

drKarl wrote: post #59

While it's an undeniable technological achievement, I don't think it's a good strategical one. Nowadays you don't create a single monolithic system, really expensive too, which is capable of processing all of your transactions, as it says, like 100 cybermondays every day. Instead, you have a distributed system, with many cheap, geographically distributed servers, each one capable of a much lower number of transaction…

Computers, even these, are cheaper than development and opportunity costs for a complex system. Especially if that system has been around for 30+ years and lies at the core of a large business.

Re: IBM Launches Z13 Mainframe

#65

Post by brudgers »

drKarl wrote: post #59

While it's an undeniable technological achievement, I don't think it's a good strategical one. Nowadays you don't create a single monolithic system, really expensive too, which is capable of processing all of your transactions, as it says, like 100 cybermondays every day. Instead, you have a distributed system, with many cheap, geographically distributed servers, each one capable of a much lower number of transaction…

The CAP theorem suggests some limits on a distributed systems approach. These matter very much in industries like banking and others involving financial transactions. It's no accident that checking each transaction for credit card fraud is listed as a feature. If there's float, there's an opportunity for arbitrage.

IBM is full of really smart people some of whom work on really hard problems using the principles of Computer science. The z13 wasn't the result of two recent grads pivoting a Yelp for Rabbits startup and the z13 isn't for companies hoping to do a billion transactions a day. It's for those doing it.

Re: IBM Launches Z13 Mainframe

#66

Post by qznc »

Normati wrote: post #58
m_mueller wrote: post #54

Earlier quoted context omitted.

> It's not just learnability. In some cases, Fortran can be considered to be faster than C since it can apply something like -fno-strict-alisasing by default. Yes. In my experience, you can make C as fast as Fortran, but it will be a lot more work (and you need more knowledge about the machine). Fortran's defaults are very strong when it comes to crunching numbers as quickly as possible. Multidimensional arrays with…

I always wonder why you can't just add a library to another language to get most of the features of somebody else's favorite language. If not a library, couldn't any other language add matlab style matrices and end up being as good as it, fortran, etc? Do we really need a whole different language with a whole different set of arbitrary rules just so a few features are easier or faster?

Sure. That is what you get e.g. with NumPy in Python. However, as you already said you only get "most" of it. The remaining niche is still large enough that Fortran has lots of users.

http://www.numpy.org/

Re: IBM Launches Z13 Mainframe

#67

Post by dagw »

Normati wrote: post #58
m_mueller wrote: post #54

Earlier quoted context omitted.

> It's not just learnability. In some cases, Fortran can be considered to be faster than C since it can apply something like -fno-strict-alisasing by default. Yes. In my experience, you can make C as fast as Fortran, but it will be a lot more work (and you need more knowledge about the machine). Fortran's defaults are very strong when it comes to crunching numbers as quickly as possible. Multidimensional arrays with…

I always wonder why you can't just add a library to another language to get most of the features of somebody else's favorite language. If not a library, couldn't any other language add matlab style matrices and end up being as good as it, fortran, etc? Do we really need a whole different language with a whole different set of arbitrary rules just so a few features are easier or faster?

couldn't any other language add matlab style matrices and end up being as good as it, fortran, etc?

In theory, sure. In practice a bunch of languages have tried and yet Fortran is still the king.

Re: IBM Launches Z13 Mainframe

#68

Post by 7952 »

drKarl wrote: post #59

While it's an undeniable technological achievement, I don't think it's a good strategical one. Nowadays you don't create a single monolithic system, really expensive too, which is capable of processing all of your transactions, as it says, like 100 cybermondays every day. Instead, you have a distributed system, with many cheap, geographically distributed servers, each one capable of a much lower number of transaction…

Distributed systems as a whole can still suffer from the same kind of issues that you would expect to see in a monolithic system. Look at how a single bad software update can take down Google or AWS.

At a basic level this kind of sytem gives you lots of low latency bandwidth connecting CPUs to each other and CPUs to storage. That is a useful quality to have and not neccessarily easily repoducible using network and internet connections between servers and data centers.

Re: IBM Launches Z13 Mainframe

#69

Post by qznc »

wmf wrote: post #38
noahdesu wrote: post #36

Earlier quoted context omitted.

I'm curious what one might expect something like this to cost.

For the previous generation: "IBM doesn’t publish prices for mainframes but the word on the street is that it is around $80,000 per core for a [Linux/Java core] compared to $400,000 per core for regular [cores] that mostly run z/OS" http://www.enterprisetech.com/2013/10/09/ibm-slashes-hardwar... I'm not sure whether that's the amortized total price or just the activation after you've already bought the machine.

Also the per-core licence is not the only position. You have to add a maintenance contract, buying the machine, firmware licence (which in this case is afaik a big Java application running on its own core), OS licence, setup, and probably more.

This really is a cashcow of IBM, mostly because they own the "mainframe" trademark/monopoly and everybody who wants to sell a "mainframe" is sued out of the market. Without the "mainframe" title, you are dead in this market of ultra-conservative customers (banks,airlines,etc).

Post reply on HN