* Posts by PracticalApplications

18 publicly visible posts • joined 19 Feb 2011

RISC-V business: Tech foundation moving to Switzerland because of geopolitical concerns

PracticalApplications

This is just the beginning

I encourage all standards bodies to consider relocating somewhere more neutral as well. JEDEC, PCISIG, and so on.

Europe seems to be the level headed choice. Look at France for example. ETSI in Nice.

Let's face it, the US is at the point of throwing hissy fits and acting like a spoiled middle schooler when they don't get their way. Diplomatic relations are now held when a US opponent (or friend) is held over a barrel with a gun to their head.

Technology standards help lower costs and create higher quality goods in an open capital market system. I for one applaud RISC-V Foundation for being the first. Line forms behind them now.....

Alibaba sketches world's 'fastest' 'open-source' RISC-V processor yet: 16 cores, 64-bit, 2.5GHz, 12nm, out-of-order exec

PracticalApplications

Here's the funny part...

RISC-V, the toolchain and ecosystem comes from Hennessy and Patterson's life's work at Berkeley. So isn't it kinda ironic that the world is actually still reliant on US origin tech. There's a lot of folks that put a lot of money, time and effort into research for these processors. I'm glad there is an open source option here. When you really think everything should be free, ask yourself if you would work for free? Meanwhile, the intention of RISC-V is to democratize processor development and allow the potential for more efficient fit-for-purpose highly efficient processors for cheap. I wonder if non-democratic states will respect that intent, or start making highly efficient missile control systems quickly and cheaply.

ITU's latest specs show that 5G is not just a wireless network

PracticalApplications

Re: 5G was never really about faster Mobile

Who said phones were the target for 5G? Much easier and faster to deploy / retrofit a neighbourhood for gig connections over the air vs trying to run GPON. Think how fast India rolled out comma by focussing on MBB delivery.

This is a tired argument that says we will never need more of 'x'. Of course we will need 5G bandwidth. It opens up what could be invented in the future. Period. If the tech industry didn't blindly push forward with "faster, better" most of the tech we enjoy today simply wouldn't exist.

Reg snaps moment when Facebook turned air Blu: 1PB box for unloved pics

PracticalApplications

Re: 1PB !!?

1PB in 42U is nothing spectacular. The article missed the main point of the solution.

It's 1PB with almost zero POWER!!!

One can quite easily stuff 3+PB into a 42U cabinet with COTS solution, but it takes 2+kW of Power to do that. Facebook faces (sic!) a problem that most companies won't: WORN (write once, read never)... i.e. the multitudes of drooling slobs taking selfies that auto-upload to their favourite social drama website.

XOXOXO to the fans

Why Flash storage will be fast and furious in 2014

PracticalApplications

Re: Patents more harm than good

You're joking, right? Gluing NAND onto a DDR3 interface is just a matter of a couple of alligator clips and spit, right?

There is significant innovation involved in creating a device that physically talks laid/store hardware protocol off a memory controller @ 1600 MT/s, represented in the OS as a block device.

I guess there is a significant amount of disrespect for the difficult process of innovation and R&D required to make something like this go from an idea to product.

Diablo's strength is the ridiculously low latency write perf. Read perf is pretty much on par with any NAND flash. Flash is flash after all.

I take my hat off to the amazing team at diablo.

Intel's taking a serious look at object storage. What's their game?

PracticalApplications
Thumb Up

Re: Intel is padding their silicon

@Hcobb - very nice, progressive thinking. Certainly not in Intel's best interest. Pretty difficult to pull off. It's one small dynamic of Netezza "secret sauce".

OpenStack head unworried by Dell, IBM, reversals

PracticalApplications
Thumb Up

Re: wouldn't read much into IBM's purchase

Agree with Nate here. IBM has a well defined history of "blue-washing" acquisitions, meaning they use what they've already invested in and built capabilities around. What I do see is a bunch of assertions on what IBM will do, yet no statement from IBM on what they will do. As in all M&A, the period of time after the announcement is filled with deep due diligence, operations systems integration and migration (like ordering systems, etc).

More of the same "press trying to make a story" when there's nothing really to talk about.

IBM is a HUGE contributor to OpenStack. I wouldn't count on them walking away from that investment.

Object Storage: A solution in search of a problem?

PracticalApplications
FAIL

Article FAILS to launch

Chris, this is a hack job of an article and it reflects poorly on you.

"IBM - nothing, zip, nada except maybe vague hints of GPFS having object connections " - REALLY?? You couldn't have googled "IBM Object Storage" and looked at the copious Product, Research and information? Let's have some basic research completed before putting mis-truths out there.

The net of the problem is simple: Object storage, when properly used will require application (re-)design changes. I'm fond of the phrase: "the only human that likes change is a baby with a dirty diaper". 99% of software developers are used to working with a file system and don't know how to design an app using object storage or better.. don't care to get off that really comfy broken (in) file system. This creates a natural barrier for mass adoption (which according to this article is a failure on vendors part to put out object storage). Instead, developers would rather go to great lengths to do things like write algorithms to generate long, random file names for uniqueness (so there's no collisions and over-writing failures) for things like log files. Dealing with OS and file system differences generates bloated and brittle code. Why wouldn't someone want to reference storage via a URI?

Object storage is a fine technology (/religion?) with the promise of something great. I find it odd and interesting that OpenStack and Swift aren't called out in this article.

Come on El Reg... if you're going to take on a topic, do it right and stop the vendor bashing and focus in on the problem.

How the iPad ruined the lives of IT architects

PracticalApplications
WTF?

You're kidding me right? April fools was the day BEFORE!

I had to stop reading after the first paragraph. There's too many issues that are well represented in the comments. What's apparent is the absolute lack of respect for those in the IT profession that have to keep up with a very rapidly changing (and accelerating) technology landscape at the same time they do their day jobs and provide 24/7/365 coverage. Do you see the same rate & pace of 'learning and doing' in other professional fields?

Let's get some respect for the individual and balance, yes?

Nutanix server-storage half-bloods armed with Xeon E5s

PracticalApplications
FAIL

Really? Wow!.... so what?

it's an x86 server. I fail to see any innovation worth mentioning. They package a hypervisor with some flash and claim massive over-committed VMs, which I'm calling Raspberries on.

With hyper-threading turned on that's 32 HW threads - or simple arithmetic shows 1 VM: 0.08 HW threads (or 0.04 without).

Memory: (256GB - ~24 Hypervisor overhead) / 400 = 580MB avg.. Tell me what modern OS or app can run in that?

Storage? Presuming 100% raw space available (5.7TB) which would be absolute lunacy to run JBOD, that's ~14GB per VM on average.

So what's the innovation here, and why should we care? You could get a jr. admin to put this together.

Can a 'one-trick' software firm survive in era of converged engorgement?

PracticalApplications
FAIL

Cute .. but

"if the promise of FCoE is realised, will have a limited future, possibly, as an in-Fibre Channel fabric SAN virtualisation device."

What exactly *is* the promise of FCoE? Higher latency access than traditional FC? lower bandwidth reservation vs FC in a 10Gb CEE fabric? This is the exact opposite of the performance curve that client applications demand of today's storage.

I'm not sure why Chris would couple the notion that an access and transport change would spell the demise of block storage virtualization.

HP test pilots fly secret four-socket Xeon E5 blade in public

PracticalApplications
FAIL

These tests are (of course) bogus

EX & EP is a ridiculous comparison. Cache structures, cores, just about everything is different and integer sensitive workloads will fly on EP and do worse on EX. Where's the compare to the other 4 Socket E5-4600 EP's? Like the IBM x440 (http://www-01.ibm.com/common/ssi/cgi-bin/ssialias?infotype=AN&subtype=CA&htmlfid=897/ENUS112-099&appname=USN). So the net result is that HP is using an exceptionally defective method of comparison. Huh... where's the Itanium compares? <crickets>

Oracle cranks Exalogic software stack up to 2

PracticalApplications
Alert

Tim - did you mean "Exalogic" servers? Best of my knowledge, Exadata is not virtualized.

Palmeter also says that it was always Oracle's intent to virtualize the underlying Exadata servers, and that was one of the reasons why it was called the Exalogic Elastic Cloud, to use the product's full name

New PCIe drive chip lives life in the flash lane

PracticalApplications
Thumb Up

Hear Hear!

this comment ABSOLUTELY has it right.

Cisco, HP bury hatchet for server, switch hookup

PracticalApplications
Thumb Down

Makes sense

It's like watching two awkward teens making out. Of course the two struggling Titans of Tech <sic> would find each other good company. However, there's little to be had by this great announcement, no innovation, just simply 1+1=2.

Big Blue 'made a move to buy BlueArc'

PracticalApplications
Holmes

You did see the IBM V7000 Unified Disk System (filer) announcement?

http://www-03.ibm.com/systems/storage/disk/storwize_v7000/

Realizing that it's a big industry, the Reg can't follow it all :)

Platform wants to out-map, out-reduce Hadoop

PracticalApplications
FAIL

Platform is not IBM Einstein

Perhaps the suggestion to do homework is best prescribed as "physician heal thyself."

Bravo, your anger and ego got the better of you on this post.

LOL

Watson? Commercial – not super – computer

PracticalApplications
Linux

Of course Watson is about commercialization

Sure - showing the world what's happening in research labs is best done with glam and flair.

Watson wasn't just a well timed expo of incredible technology toppling meager humans. Nor is it the start of the end of humanity.

Technology companies will always paint the 'art of the possible' in the public mind because it gets folks excited. When the first caveman invented knife technology, you can imagine the excitement around the cave fire, unless you were the first test case of course.

IBM has always pushed the boundaries of material science and continued to drive innovation. Their patent records year on year speak to that. The fact that they have the largest dedicated math department in any private company means they are dedicated to solving problems.

Let's be pragmatic however - IBM's a company that is in business to make money. They have stock holders that want a good return on their investment. Clients of IBM enjoy a trust relationship and value assurances that what happens in the Research and Development Labs will make it's way into commercial applications that will give them an edge in their market.

Think of IBM's leading thought campaign with "Smarter Planet". It's not rocket science to associate the demo of Watson's incredible data crunching and accuracy that could very well lead to the next generation of medical diagnosis tooling, better decision support systems for critical infrastructure (emergency services, energy and water management systems, etc).

I for one am excited about the possibility of potential new applications of the technology developed during the creation of Watson.