Let me get this straight. You're saying that in 1953, the US sponsored a coup which deposed a the democratically elected Mohammed Mossadegh, a man with no ties to the Soviet Union or to Communism in any form, on the basis of what was going to happen in a country which would not exist for another twenty-seven years?
No, he's referencing Domino theory. We didn't care about democracy (we still don't), we just wanted an ally.
Absolutely right. Neither Iran nor North Korea have waged wars of aggression in the past 50 years. If you're alleging that the US hasn't done so, you're being extremely naïf.
You're right, sort of. Iran was invaded and fought with Iraq for 8 years. North Korea didn't exist until after the Korean war, and is held in check by the USA. They do, however, kidnap people from Japan and Korea as a matter of course. Sure, they haven't invaded anybody, but it's mainly because they haven't had the chance.
Huh, those are softballs. The routing thing, I only have a couple ways, but that's because I do software dev, not system admin. My only real interview stories are things like people with 5 years of programming experience who can't do a reasonable atoi() or the open ended 'the website is slow' problem. Also fun is getting someone to design an addressbook for a cell phone.
This is true - 100 worker threads can service 10k http requests (generally) - but for small scale MT, 1 thread per job (with pooling) is simple to implement.
Modern x86 CPUs have (SSE) instructions that load 128-bits at once. This means you really need a 128-bit connection to your memory. Your CPU has instructions that load 1024 bits at once, meaning you need eight times as wide a connection to memory.
No you don't. You only need to make it as wide as the memory is (usually 64 or 128 bit), then pipeline the data back. This is why ram is rated as 3-1-1-1.
If you want to implement these on an x86 core, you need to do one of two things. Your first option is just to make them take 8 cycles.
The main research lines of programming languages have for a long time abandoned the initial pursuit for user-friendly languages, their last successes being in BASIC, Logo and the Fourth Generation Languages (i.e. SQL).
We have Ruby, which is friendly as you should expect. Programming is hard, and it's nothing to do with syntax.
Once you start giving each CPU its own memory, you're wasting most of the physical memory on cores that need very little, just because a few cores might need a lot of memory.
No you aren't. The non local ram is just slower.
Please note, that cores have not successfully improved that much in raw GHz, the last few years (the P4 was not a success))
Not relevant. Recent processors are faster than older ones, even with lower clocking.
Mote ALU's on a die makes multi-threading and inter-dependency exponentially more complex.
Compared to what? It's just physical packaging, with possible sharing of cache.
Programmers have gotten lazier and since roughly 2000 (at least from my perspective, likely before that) have come to rely on the ever increasing sizes of hard drives, RAM, and Clock Frequency.
It's called proper allcoation of resources. hardware is cheap and engineers are not, so why optimize if it's fast enough or if you can just toss another box at the problem?
but if I can get 300mb/sec with fake raid and a handful of cheap drives, I would expect at least double that from server-class gear, like it used to be in SCSI's glory days.
Can you get 300M/sec on RAID5? Also, what's the system load?
As for the K10-based Opterons, they're just too weak! The original single and dual core Opterons were awesome because they beat the Xeon across the board: better performance per clock, lower power draw, better pricing and mass availability. It was a no-brainer! The new quad core AMDs just can't keep up, they're not all that much cheaper than quad core Xeons but most importantly: they're clocked too low.
AMD has better memory architecture, so it'll outperform Xeons at 4x because the Xeons will choke on memory (usually).
doesn't work that way - they show up here, get trained, then go back home and compete with us. Meanwhile, we aren't willing to grow our own experts, so the brain drain goes the other way.
But IT has nothing to do with it's core business. Long before computers were commonplace, Allstate's business model existed, and Allstate made money.
This is true, however, it can drive efficiency, make or break the company based on information leakage, and certainly isn't a candidate for outsourcing - your core business processes are likely computerized and it's a lot easier to maintain good info security when you control who gets to look at your info. Using a plumbing analogy, you don't care if the plumber takes pipes out of your building because you don't care about what's in them.
And to every Exec (with the possible exception of a CTO), one IT guy is as good as any other IT guy. As long as the servers are running nobody cares./Truth
Kinda sorta. Some execs lump software dev in with IT. For instance, Atari.
If your services are truly equally valuable then you need to be prepared to offer the same level of service for the same pay.
Management gets the level of service they're willing to pay for. This isn't just salaries, but equipment - I'm not buying the company new hardware on my dime.
But does the plumbing infrastructure need to be redone every few years?
Let's try and think in those terms: back in the 80s, employees dribbled crap down the pipes at a snail's pace - think soda straws. Over time, that has grown by 2-3 orders of magnitude, so now they each have a pet elephant producing shit for others' consumption. the volume is quite a bit higher, and it has to be transported all over the world. Of course you're going to need an upgrade.
I don't see why - they reserve the right to shut down sites they think are up to no good (in their judgement). This is reason enough never to use them.
Slashdot Mirror
Let me get this straight. You're saying that in 1953, the US sponsored a coup which deposed a the democratically elected Mohammed Mossadegh, a man with no ties to the Soviet Union or to Communism in any form, on the basis of what was going to happen in a country which would not exist for another twenty-seven years?
No, he's referencing Domino theory. We didn't care about democracy (we still don't), we just wanted an ally.
Absolutely right. Neither Iran nor North Korea have waged wars of aggression in the past 50 years. If you're alleging that the US hasn't done so, you're being extremely naïf.
You're right, sort of. Iran was invaded and fought with Iraq for 8 years. North Korea didn't exist until after the Korean war, and is held in check by the USA. They do, however, kidnap people from Japan and Korea as a matter of course. Sure, they haven't invaded anybody, but it's mainly because they haven't had the chance.
Huh, those are softballs. The routing thing, I only have a couple ways, but that's because I do software dev, not system admin. My only real interview stories are things like people with 5 years of programming experience who can't do a reasonable atoi() or the open ended 'the website is slow' problem. Also fun is getting someone to design an addressbook for a cell phone.
I wonder if you can go to prison for unpaid fines of that magnitude? Anyway, the big cheese has a lifetime ban, he'll need a new scam.
Wait, are you for or against the illegal spying on US citizens for unspecified purposes, with the cover of ZOM!! Terrorism!
Have you seen this? Looks like you can beat 175MB/s in a raid5 config, depending on file access patterns, of course.
This is true - 100 worker threads can service 10k http requests (generally) - but for small scale MT, 1 thread per job (with pooling) is simple to implement.
What are you talking about? I'd hate to have to change hardware just for an OS upgrade.
Modern x86 CPUs have (SSE) instructions that load 128-bits at once. This means you really need a 128-bit connection to your memory. Your CPU has instructions that load 1024 bits at once, meaning you need eight times as wide a connection to memory.
No you don't. You only need to make it as wide as the memory is (usually 64 or 128 bit), then pipeline the data back. This is why ram is rated as 3-1-1-1.
If you want to implement these on an x86 core, you need to do one of two things. Your first option is just to make them take 8 cycles.
loading memory takes way more than 8 cycles.
You won't be able to do anything in OCaml.Net that you can't already do in C#, so why bother with .Net?
The main research lines of programming languages have for a long time abandoned the initial pursuit for user-friendly languages, their last successes being in BASIC, Logo and the Fourth Generation Languages (i.e. SQL).
We have Ruby, which is friendly as you should expect. Programming is hard, and it's nothing to do with syntax.
That's because no-one's really put much time/effort into making "Idiot-Capable(TM)" programming systems.
Are you joking? We can't make idiot capable people for the most part, so why do you expect computers to do better?
According to windows task manager I'm running 35 processes right now.
And 32 of them are idle. It's always been like that.
Once you start giving each CPU its own memory, you're wasting most of the physical memory on cores that need very little, just because a few cores might need a lot of memory.
No you aren't. The non local ram is just slower.
Please note, that cores have not successfully improved that much in raw GHz, the last few years (the P4 was not a success))
Not relevant. Recent processors are faster than older ones, even with lower clocking.
Mote ALU's on a die makes multi-threading and inter-dependency exponentially more complex.
Compared to what? It's just physical packaging, with possible sharing of cache.
Programmers have gotten lazier and since roughly 2000 (at least from my perspective, likely before that) have come to rely on the ever increasing sizes of hard drives, RAM, and Clock Frequency.
It's called proper allcoation of resources. hardware is cheap and engineers are not, so why optimize if it's fast enough or if you can just toss another box at the problem?
but if I can get 300mb/sec with fake raid and a handful of cheap drives, I would expect at least double that from server-class gear, like it used to be in SCSI's glory days.
Can you get 300M/sec on RAID5? Also, what's the system load?
As for the K10-based Opterons, they're just too weak! The original single and dual core Opterons were awesome because they beat the Xeon across the board: better performance per clock, lower power draw, better pricing and mass availability. It was a no-brainer! The new quad core AMDs just can't keep up, they're not all that much cheaper than quad core Xeons but most importantly: they're clocked too low.
AMD has better memory architecture, so it'll outperform Xeons at 4x because the Xeons will choke on memory (usually).
doesn't work that way - they show up here, get trained, then go back home and compete with us. Meanwhile, we aren't willing to grow our own experts, so the brain drain goes the other way.
what sort of questions do you typically ask? I'm sort of curious, although I don't really want to move to NYC.
I thought their approach was the busload of kiddies.
But IT has nothing to do with it's core business. Long before computers were commonplace, Allstate's business model existed, and Allstate made money.
This is true, however, it can drive efficiency, make or break the company based on information leakage, and certainly isn't a candidate for outsourcing - your core business processes are likely computerized and it's a lot easier to maintain good info security when you control who gets to look at your info. Using a plumbing analogy, you don't care if the plumber takes pipes out of your building because you don't care about what's in them.
And to every Exec (with the possible exception of a CTO), one IT guy is as good as any other IT guy. As long as the servers are running nobody cares. /Truth
Kinda sorta. Some execs lump software dev in with IT. For instance, Atari.
No way, man. The pit crew is far too respected to be representative of IT.
If your services are truly equally valuable then you need to be prepared to offer the same level of service for the same pay.
Management gets the level of service they're willing to pay for. This isn't just salaries, but equipment - I'm not buying the company new hardware on my dime.
My message light has been red for months, it doesn't flash, so I can pretty much ignore the always-on light
Electrical tape solves this problem.
But does the plumbing infrastructure need to be redone every few years?
Let's try and think in those terms: back in the 80s, employees dribbled crap down the pipes at a snail's pace - think soda straws. Over time, that has grown by 2-3 orders of magnitude, so now they each have a pet elephant producing shit for others' consumption. the volume is quite a bit higher, and it has to be transported all over the world. Of course you're going to need an upgrade.
I don't see why - they reserve the right to shut down sites they think are up to no good (in their judgement). This is reason enough never to use them.