Follow Slashdot blog updates by subscribing to our blog RSS feed

 



Forgot your password?
typodupeerror
Compare cell phone plans using Wirefly's innovative plan comparison tool ×

Comment Re:massive parallel processing=limited application (Score 1) 102

On a 8-core machine, a processor will be placed into a wait queue roughly 7 out of 8 times that it needs access.

You just snuck into your analysis the assumption that every core is memory saturated, and I don't think that all the memory path aggregates in many designs until the L3 cache (usually L1 not shared, L2 perhaps shared a bit). The real bottleneck ends up being the cache coherency protocol, and cache snoop events, handled on a separate bus, which might even have concurrent request channels.

I think in Intel's Xeon E5 line-up there are single-ring and bridged double-ring SKUs for forwarding dirty cache lines from one cache to another (and perhaps all memory requests). This resource can also drown for many workloads.

In many systems, you have all these cores running tasks which are fairly well isolated (not much cache conflict), except they all want to be able to allocate as much memory as they need from a giant memory space (e.g. a TB of DRAM) so they fundamentally have to fall through to a shared memory allocation framework.

You can learn a lot about the challenges involved by following the winding path of something like jemalloc as increasing concurrency levels expose yet another degeneracy.

The real problem with this field is that there isn't a single, simple story like the one you tried to tell. There are usually dozens of ways to skin the cat, each with completely different scaling stories, with different sets of engineers who are good as tweaking or debugging those stories.

At this point, what you have is a fragile coordination problem between your solution space, your architecture, and the engineers you employ, forcing ambitious ventures to crack out the golden recipe: pour in seven cement mixers full of head hunters, one 55-gallon oil drum of exclamation marks, a metric butter tonne of job perks, and agitate appropriately.

Comment Re:Followed by: (Score 1) 423

I think scientists can make some larger statements on the impacts. No one can tell you what exactly it would be like at any particular location, But what you're doing is exaggerating the amount of uncertainty, and then trying to defend warming trends by invoking even less certain predictions. It's hard not to see how you aren't just being a contrarian simply because you don't like the answers science can provide.

When rain belts shift northward in North America, arid conditions will begin to become the norm in large parts of the American Midwest, and that will mean American food security will become, at some point over the next century so, one of the most serious issues the US has ever had to face. And this isn't a matter if whether it will happen or not, the debate is over WHEN it will happen.

Pumping vast amounts of formerly sequestered CO2 into the atmosphere is just plain bad. We should be moving at all speed to alternative energy sources, and either leaving the oil and coal in the ground, or finding some other use for it that doesn't involve releasing CO2 into the atmosphere.

Comment Re: Followed by: (Score 1) 423

You do understand, I trust, that different countries have different birth rates, right, so while one country may have a very high birth rate, another country may have a very low one. You know, how Japan's population is shrinking, and India's is growing?

It often makes me wonder if being a political partisan either causes stupidity, or political partisans are just inherently stupid people.

Comment Re: Pierson's Puppeteers (Score 1) 643

And there is a remarkable lack of evidence that you understand the issue of anthropogenic global warming well enough to make a qualified judgment about it.

If you want to discuss that. We can. There's a lot I don't know about the issue. But I can read scientific literature and it doesn't say what the various chicken littles in this thread have claimed.

Comment Re:Big surprise some jackhole Silicon Valley (Score 1) 234

Many lawyers give horrible self-serving "advice", and will rarely take small cases on contingency. If they were honest, decent people, then they wouldn't have become lawyers in the first place.

That's why you consult several of them.

Why would the algorithm be any different?

1. It is free.
2. It has no vested interest in lying to you.

Neither would be true.

Comment Re:This is the year of the extreme climate claims (Score 1) 410

"But they call us names!" Science doesn't work that way.

Who said it did?

Let's look at the post I replied to again.

You call them corrupt fascists. They call you stupid frauds. Let's not pretend you're here for a serious discussion.

It's like you're not even reading this thread. Look at the above name calling rationalization. That AC just said it.

The point is when you keep treating people like crap and not talk science, some people are eventually going to just give up talking science to you.

When are you or other ACs in this thread going to start talking science? It's evidence-based not name calling-based.

And why should such complaints appear in this thread? The earlier poster that I originally replied to and the article they linked to just irrationally libeled people (and the poster didn't even have the right target libeled). This isn't science. It's noise. It's not going to convince anyone. It's not going to save the Earth.

Comment Is this Project Fi? (Score -1, Offtopic) 190

This Google Fiber they're talking about has nothing to do with the Project Fi wireless service, does it? I've been using Project Fi after dumping AT&T, and I'm really liking it. But then, after AT&T, I'd probably be really liking two tin cans connected by a string, so the bar is pretty low.

Comment Re:Democrats too (Score 2) 74

Here's cash flowing into the Clinton Foundation from corporations benefiting from selling dual use technology [nypost.com] (private and military uses) to Russia.

In case you haven't noticed, most of our "dual use" technology has been shared with the Russians for a long time already. For example, the decimal number system.

In some instances, we might even consider ourselves better off if the Russians did choose to adopt our technologies, such as fail-safe command and control systems responsible for nuclear weapons (supposing our technology is actually better; I suspect the Russians have had 8" floppy disk drives for quite a while already).

Just about any improvement in the Russian commercial space would probably trickle down to the Russian military (trickle down seems to work much better in some directions than others). Are we still in the middle of a 1950s-style total economic blockade? Not that I've heard. Our bigger technical battles are with countries who have not yet produced thousands of nuclear warheads.

In summary, all of this is all a lot of hand-wavy durf, durf, durf.

Point to a real technology and describe an actual scenario where the Russian military benefits, and then explain how the Russian benefit A) is a serious NATO concern, and B) wasn't going to happen anyway sooner rather than later. Having met that bar, then maybe this issue will start to seem important to people outside your particular Kool-Aid enclave.

Hint #1: you might need to avail yourself of sources other than wnd.

Hint #2: just about every dollar given to a politician comes from someone with an interest who wants something.

Arguably the Saudi's and their Wahhabist agenda have done more damage to American foreign interests over the last thirty years than anything the Russians have done. That line of thinking would probably lead you straight back to the Bush Foundation.

Bush's Newest Secret: Who's Funding His Library?

In this piece, Mother Jones at least displays the decency to tar the Democrats and the Republicans with the same brush.

Slashdot Top Deals

He's dead, Jim.

Working...