Want to read Slashdot from your mobile device? Point it at m.slashdot.org and keep reading!

 



Forgot your password?
typodupeerror

Slashdot videos: Now with more Slashdot!

  • View

  • Discuss

  • Share

We've improved Slashdot's video section; now you can view our video interviews, product close-ups and site visits with all the usual Slashdot options to comment, share, etc. No more walled garden! It's a work in progress -- we hope you'll check it out (Learn more about the recent updates).

×

Comment: Rewards (Score 3, Insightful) 184

by byennie (#40670483) Attached to: Why We Should Remain Skeptical of the Ouya Android Console

I'd be worried they completely overextended on the Kickstarter rewards. They may have raised $5M so far, but they also owe:

* About 8% of that to Kickstarter & Amazon (= $400,000)
* 35,000 consoles and controllers to their backers

Manufacturing and fulfillment on 35,000 consoles is going to take an awfully large bite out of their (so far) $4.6M net from Kickstarter.

Comment: Get More Creative with AWS (Score 1) 264

by byennie (#37407922) Attached to: Ask Slashdot: Clusters On the Cheap?

I see a lot of people suggesting the use of cluster instances on AWS. At first blush this is what they are built for, but it's not a gimme that they are the most cost-efficient option. From the description, the job is not targeting GPU, and it's also not network-bound. Some of the high-cpu instances are more economical if you don't need the gobs of RAM or 10 Gigabit pipes. The cluster instances do have somewhat faster CPUs.

AWS offers a MapReduce layer that supports all of these instance types (http://aws.amazon.com/elasticmapreduce/).

Cluster xLarge (GPU) = $2.10 / hour = $0.26 / hour / core = $0.063 / hour / cpu unit
Cluster xLarge = $1.60 / hour = $0.20 / hour / core = $0.048 / hour / cpu unit
High CPU - medium = $0.17 / hour = $0.085 / hour / core = $0.034 / hour / cpu unit
High CPU - large = $0.68 / hour = $0.085 / hour / core = $0.034 / hour / cpu unit

Throw in:

* Spot instances are discounted by over 50%. If your jobs can work on a range of instances, bid on a variety of cheap CPUs first.

* Reserved instances come out ahead after about 6 months of 24/7 usage, if you're going to use it that way.

All together, you could do something like this, with many possible variation. This gets you roughly 10 CPUs running 24/7 for 6 months, plus 3 hours a day of cluster compute time. And of course you don't pay for any time that you're not running so that could be reallocated.

5000 hours High CPU (medium) = $850 = 10,000 CPU hours
5000 hours High CPU (large) = $3400 = 40,000 CPU hours
250 hours spot instance (Cluster) = $150 = 2,000 CPU+ hours
250 hours spot instance (Cluster GPU) = $200 = 2,000 CPU+ hours
---
Roughly 55,000 CPU hours for $4500, leaving about $1800 for bandwidth, storage, or more compute time.

Point being, just like you can customize the heck out of box to buy, you can carefully craft a cloud approach more efficiently that just buying cluster time. If you just throw it at GPU cluster boxes, you could get half the work done (or less)...

Comment: Re:Woefully inefficient... (Score 1) 111

by byennie (#23865055) Attached to: Robotic Aircraft To Supply Troops

That 400 lbs of cargo isn't flown in by magical faeries.


Really?

Hauling in a truck-load of fuel, to move 400 lbs of water, to supply a few soldiers for a day or two, is going to kill FAR more people than just having someone transport supplies to those soldiers by traditional means, or avoiding putting those soldiers so far out there in the first place that they get cut off.


1) Your truck load of fuel can be up to 1000 miles away from your soldiers. Kind of a big deal when you are worried about the danger of "forward positions".

2) You're the only one saying this is just going to carry water. It's not.

3) If you're afraid of risking more soldiers, why are you willing to send them on manned delivery runs, but afraid of the risk of them trucking in fuel 1000 miles away?

And besides lives, you have all kinds of questions of COST, MAINTENANCE, RELIABILITY, etc. If one of these ridiculously low-capacity supply planes means that a dozen Humvees don't get armor because of cost or lack of manpower, then you're making an incredibly stupid mistake.


Well no shit maintenance is an issue. And it's not with Humvees? And who said we were going to make dumb ass judgements on when to use these and when to spend on something else? That's just an assumption based on the idea that they are useless. A bit of a self-fulfilling argument.

In addition, I specifically pointed out that there are alternatives which could do the job INFINITELY better than this far-fetched creation.


This creation doesn't exist yet, so that remains to be seen. You said use one of the vehicles from DARPA. Right. Show me the DARPA vehicle that is going to navigate 1000 miles of a war zone and deliver a 400 lb + payload right now.

Real Users find the one combination of bizarre input values that shuts down the system for days.

Working...