to add to my own comment. this problem with manufacturing costs is surely the reason AMD has spun off their fabs into a separate company. It will be interesting to see if they can be more successful now that they do not have to directly maintain their own fabs.

Back in the Athlon days, AMD lacked the manufacturing capacity to control 50% of the market. If all their fabs were running at 100% at that time, and every chip they made was being sold, the total number of chips sold wouldn't have been anywhere near 50% of the market. Intel doesn't actually have to do anything illegal or sleezy to stay ahead on market share. The fact is that no matter how bad their chips might suck the big manufacturers like Dell et. al. will still have to use Intel chips in the majority of the machines they sell because AMD isn't physically capable of making enough. That is the fine line AMD has to tread. They have to constantly stay ahead in performance while slowly growing their market share and then use the profits to invest in increased manufacturing capacity. It takes years to build a new plant afterall, and if you build too many too quickly, you'll end up with manufacturing capacity you cannot use and you lose tons of money because maintaining a microprocessor manufacturing plant is enormously expensive.

It's about programmers lacking basic knowledge (or at least failing to take account) of how a computer works internally. well written and well validated software doesn't have problems like this.

You need to keep in mind the reason that CPUs are not designed the way that GPUs are designed. GPUs are very good at easily parallelizable repetitive computations. GPU performance grinds to a snails pace as soon as you have to take a branch.

Unless you are writing the kind of code in which if statements are nearly non-existent, you are not likely to find programming for a GPU-style pipeline to be very palatable.

You do need to keep in mind one of the primary reasons CPUs are designed the way that GPUs are designed. GPUs are very good at doing massively parallel repetitive computations like what you need to do when processing an image for a display or like some small segments of the HPC market regularly do. But GPU performance grinds to a halt as soon as your code needs to take a branch.

Unless you write the kind of code in which if statements are nearly non-existent, you are likely to find programming for a GPU-style architecture to be unhelpful.

agreed. which suggests the companies problem, if there really is one, is that they are not buying the machines that best fit the needs of their software stack.

You are probably right. It'd be nice if he could say what precisely he thinks they are lying about. I mean, I know marketing is always exaggerated to some degree, but as rule, it seems to me that AMD and Intel processors do generally perform the way the companies claim they will if you look past the hype at the technical details.

lenovo is really just trying to motivate me to stop being lazy and finally uninstall all the software they pre-installed on the laptop I purchased earlier this year. ;)

I'm bemused that he implies the problems with his servers are due to Intel and AMD no delivering with their chips, yet at the same time he admires google for how good a job they do in building out their machines.

he must be aware that google uses Intel and AMD chips.

his reasoning just doesn't square.

while it is true that "beaming" broadband into Iran is absurd. as others have said, whomever asked the press secretary that question is ignorant of how broadband works and deserves to be laughed at soundly by their peers. :p

that said, your characterization of Iran is way off. Iran is considerably more civilized then what you think it is. Electricity, cell phones, computers, and internet access are all relatively common place in Iran.

The place that you are describing is called Afghanistan.

The user's perception of the performance differences between older CPUs running Win95 and newer CPUs running modern OS's has nothing to do with the processors that AMD and Intel are selling. It is the software. it is partly the operating system. it's partly the fact that people run a lot more junk in the background then they used to.

it is also sometimes the OEM's fault unfortunately.

amusing antectode: a friend of mine was recently having serious performance problems with his new laptop. I spent half a day trying to figure out why and discovered that the OEM had installed a "power saving" application on the machine that was performing registry reads 20-100 times per second. The only thing the application had in the registry was its configuration settings. Needless to say, the OEM, who shall go unnamed clearly has an utterly incompetent software engineering team. The application was suppossed to detect when to throttle down the CPU frequency and thereby save battery life, but the application was drawing more power all by itself then anything else in the system and was causing performance on this otherwise excellent piece of hardware be horrible.

In that case, I uninstalled all OEM supplied software from the system and it became quite snappy.

Actually, acceleration is not an issue at all. If a warp bubble was ever made to work, the acceleration for the people on the ship would be zero.

Acceleration is a change in velocity. In a warp bubble, if you could make one, there is no change in velocity because the ship does not move. The space behind the ship is stretched and the space in front of the ship is contracted. The ship itself doesn't move.

I agree that it is way to soon to be talking about engineering designs for a warp drive as anything more than speculative curiosities. But that said, if such a drive works, it isn't time that will be warped. It is space.

The basic theory behind how that could be done was worked out in a physic's paper published in the 1990s. It requires a large source of negative energy to sustain the warp "bubble" though, and its not clear how or even if that is possible. I presume this is why "dark energy" is being brought into the picture with the proposals linked by this slashdot article. Since the understanding is that if dark energy really does exist, it has a large negative magnitude.

The other problem with that initial paper that I'm aware of (there may be others) is that the paper showed that a moving bubble in space time that gets between two locations at a speed that exceeds the speed of light can exist as a valid solution to the equations of general relativity in a universe in which negative energy exists. The paper didn't demonstrate though that such a bubble could be constructed from a region of space that didn't already have one. For such a bubble to be usable as a means of transportation, even in theory, you need to demonstrate not only that "warp bubbles" can exist, you need to also demonstrate that they can be constructed at the source, and then deconstructed at the destination.

Maybe follow-up papers have discussed those details and shown that construction/deconstruction are also theoretically possible? I haven't followed up on it. But even if they do, we still require large amounts of negative energy to do this and negative energy, if it really exists at all, is not well understood.

I'm also not clear on what kind of radiation such a bubble would give off, but it's possible it would be intense enough to fry anything inside...

It is exciting to see astrophysics beginning to point at the idea notion that negative energy might actually be real though. It means that things such as warp ships are not complete fantasy. They are way, way off though, if possible at all. We likely won't know for sure for quite a long time. :)

I was with you until you turned to ranting about schools becoming more about prepping for standardized tests.

A programming assignment in which a student is assigned to create a piece of software that solves an assigned task is not a standardized test. There's no basis for a comparison.

More generally, its also not reasonable to assume reusing old testing materials on the part of a teacher is new. Your average person tends to be rather lazy about how they do their job and will frequently take the path that involves less effort if they believe the end result still sufficiently (what ever they define to be sufficient in their own minds) gets the job done. A study of history suggests this has always been true. There's no reason to think teachers are any different. Recycling of old testing materials has likely been going on amongst the less inspired of the teaching profession for as long as teachers have existed.

True. Those Intel chips do not have integrated memory controllers.

All the chips from both companies potentially get a boost from DDR3 memory over DDR2 memory. But, as the article demonstrates on the other pages, for the benchmarks they are looking at, the sensitivity going from DDR2->DDR3 is small.

I only talked about it in terms of integrated memory controllers because you brought up the idea that Intel parts have always been "memory starved". That statement is what I was contesting. Intel parts have only been memory starved on some workloads, relative to AMD, when AMD had an integrated memory controller, and Intel didn't. The blanket statement that this has always been the case is not true.

As to your point that you want to see data justifying the claims that DDR2 vs DDR3 in their study isn't all that relevant, the article provides that data. One may question the workloads they chose, but the data justifying the claim within the scope of the workloads that they did choose is there.