Register for free to join our community of investors and share your ideas. You will also get access to streaming quotes, interactive charts, trades, portfolio, live options flow and more tools.
Register for free to join our community of investors and share your ideas. You will also get access to streaming quotes, interactive charts, trades, portfolio, live options flow and more tools.
<Ii> Next, we loaded up another CSA Research tool, Clarity Studio. With Clarity Studio, we simulated multiple, concurrent workloads running in parallel -- the kind of complex, data-intensive multitasking that's becoming commonplace in emerging workstation markets (see "How we put the workstations under pressure"). "
Then my question would be did they benchmark those multiple concurrent workloads? If they didn't the AMD processor could have been getting more processing done but still get a lower benchmark score. The benchmark can get one virtual processor on an HT enabled processor and thus get higher priority, meaning that the Xeon would spend less time processing the background tasks.
If you want to see how much work a CPU gets done under "simulated multiple, concurrent workloads running in parallel" then you should benchmark the "simulated multiple, concurrent workloads running in parallel" and I don't think they did.
Tim
A hacker deliberately created a work-around for NX. It's not a stretch to suggest that more will follow.
Its not a work around to NX. Its just a different type of attack. Its not something new to get around what NX protects against, it something old that NX was never meant to protect against. Its no more a work around of NX then someone gaining direct physical access to your server is a work around of your firewall.
Tim
OK so maybe he's emotional or even not objective. Now what part of his description of the benchmark is innacurate? If the answer is no part then his personal biases or other qualities don't matter.
Tim
I think it is down. I haven't been able to access SI for hours.
Tim
"...OK, to be fair, here is what PressHot is too cold to do:
# Boil water
# Fry eggs
# Melt solder
# Burn paper
# Melt lead
# Weld steel
# Trigger fusion reactions
It is also almost 400°C colder than the surface of Venus, and over 5400°C colder than the surface of the Sun!
This is one cool customer we're talking about!"
http://www.overclockers.com/tips00548/
Also see
http://bbspot.com/News/2000/7/heatsink_homes.html
No mas, the laugh is on you and the rest of the fanboys. Even Opteron is now using an IHS.
My understanding is that the main reason for it in the Opteron is to physically protect the expensive processor from getting chiped or crushed, not to help dissipate heat.
Tim
The latency to make one HT hop looks to be about 40 ns. Intel's northbridge latency is probably also in that vicinity. But now, here's the rub. HT needs to be converted into PCI Express. There's a translation latency as well as the standard PCI Express latency. In other words, Opteron has more latency when outputting a PCI Express signal than Intel's system.
I don't think Intel's Northbridge talks to the CPU in "PCI Express". Just as the signal on PCI-E needs to be converted to the type of signal used in HT the signal on PCI-E needs to be converted to whatever method or protocol Intel uses to communicate from the northbridge to the CPU.
Tim
I thought the orange was for K8.
That was my original opinion but everyone here seems to think it means SOI.
Also see
http://www.siliconinvestor.com/stocktalk/msg.gsp?msgid=19475988
Ok, I guess it's official, Paris is a 32 bit, SOI processor, for whatever reason. To add insult to injury, it's also going to introduce at 130nm, at a time where 90nm is coming out.
Where does the new road map indicate that Paris is a 32bit processor? All it says is 130nm SOI.
On this version of the new road map its in Orange like the other 64 bit chips. The 32bit chips are in purple.
http://www.amd.com/us-en/Processors/ProductInformation/0,,30_118_608,00.html
I don't think I have all the info I need to have an educated opinion in this area. What I would have is an unsupported guess and I'm not even sure what thay would be at the moment.
Tim
I'm more interested in this part
"An interesting tidbit on the side is that Intel's P4 architecture, using all kinds of optimizations, including hardware-based dynamic speculative precomputing for branch-prediction and prefetching will be hurt less than AMD by the high latencies of DDR II. To spin this a bit further, the main advantage of AMD's Hammer architecture is the integration of the memory controller onto the CPU with the goal of reducing chipset-related (control and address decode) latencies. It only requires second grade math skills to see that shaving off one cycle out of nine (1/9) on the controller level for an initial access will yield less performance gain than reducing latencies by one cycle out of five (1/5) ."
What's your opinion?
Tim
And old article but I'm still interested in hearing if people think this is accurate -
Between Intel And AMD
An interesting tidbit on the side is that Intel's P4 architecture, using all kinds of optimizations, including hardware-based dynamic speculative precomputing for branch-prediction and prefetching will be hurt less than AMD by the high latencies of DDR II. To spin this a bit further, the main advantage of AMD's Hammer architecture is the integration of the memory controller onto the CPU with the goal of reducing chipset-related (control and address decode) latencies. It only requires second grade math skills to see that shaving off one cycle out of nine (1/9) on the controller level for an initial access will yield less performance gain than reducing latencies by one cycle out of five (1/5) .
The difference between AMD and Intel, though, is that Intel is actively participating in defining (say: "bullying") the memory specifications of the future regardless of the cost concerns of the DRAMurai. AMD, on the other hand, whenever we asked them, appeared to be mostly concerned with staying mainstream and swallowing whatever was served by the DRAM makers as the best roadmap. Clearly, with helping the memory industry to make the cheapest possible DRAM, AMD will not win performance or market share. Intel has learned this lesson many years ago, and even though Rambus faltered in the end, Intel got more mileage out of them than anybody will ever admit. VIA Technologies are pursuing QBM (quad band memory, invented and heralded by Kentron) with high bandwidth and low latencies, and where is AMD?
Realistically, there is a solution for AMD. Low latency processors and controllers require low latency memory. It is as easy as that and we ........ well, we do have some suggestions.
(to be continued some two years down the road)
http://www.lostcircuits.com/memory/ddrii/8.shtml
An argument can be made over some of the statistics. AMD investor relations, for instance, said that the company's net income for 1995 can be listed as $300.5 million. I am using $216.3 million. (Investor relations confirmed all of the other annual net income figures used in the calculation.) The higher figure does not include losses generated by NextGen, a company AMD acquired in January 1996.
I don't think NextGen's losses before AMD bought NextGen should count. Does Intel report a hit on its earnings for all previous losses of unprofitable companies it acquires?
Tim
What access to grandfathered users on IHub get that regular users do not? If your grandfathered on IHub and Lifetime on SI do you get any additional access now?
Tim
In past quarters AMD sold a lot of obsolete CPUs into distribution to such entities as Avnet and Arrow. AMD might have been much better off if it had burned them, since it produced very low cost market overhang that had to degrade AMD's potential market. My guess is that virtually all of these are now gone.
The answer to the questtion if AMD would have been better of just destroying the CPUs depends on what the people who bought them would have bought had no cut rate AMD chips been availalbe. Would they have brought higher end AMD chips, Intel chips, chips by other companies, or nothing?
I think overall AMD did better by selling them then destroying them. I don't think a lot of the people buying these chips would have wanted to pay a lot more for different AMD chips, they went in to the bottom end market.
Tim
The biggest reason for the improved fiscal situation at the time was the general economic growth. The 2nd biggest reason was the Republican congress putting a restraint on spending. Its true that Republicans today seem to have joined Democrats in losing the desire to put a break on spending but in the 90s they did a decent job of it.
Tim
What about the much greater number of Iraqis whose lives where saved by getting rid of Saddam, and also creating the conditions for the removal of sanctions?
Tim
while IBM foots the bill for FAB capacity to saturate the market with Athlon-64s.
Why would they do that unless they where going to make the profit from those Athlon-64s?
Tim
How good is the ATI MOBILITY RADEON video on that laptop. I know it won't compare with modern high end desktop cards but does anyone know hot it compares to say a GeForce 2MX 200?
Tim
"I don't usually come over here to often"
Why is that?
Time. I spend enough of it on SI, that I don't have much left to spend here.
Tim
Several days ago? I thought my inbox was empty the day before yesterday...
And even if it was several days, 24 hours is a lot of downtime.
Tim
I don't usually come over here to often but
"Silicon Investor is down for maintenance for approximately 24 hours beginning at 3pm EST on Friday, May 16th."
24 hours down time with at most minimal warning?? What a way to run a web site.
Tim
If I go to favorites then select a thread with new messages, then start reading that thread, if I stop and later go back to favorites it shows 0 new messages which means if I start reading a thread I have to read all the new messages or lose my place. It would be much nicer if when you stop reading a thread without finishing it I-Hub would remember your place.
Tim
First, full disclosure: I have INTC in my wife's IRA at $33.06. Like I've said before, I'm not the sharpest knife in the investing drawer.
You think you have made some bad investment decisions. At least your INTC can eventually recover. I had about $8k of AMD calls expire worthless.
Tim
How about a show next 10 (or 12 or 20 or whatever) messages button.
Tim
Will AMD's processors catch up with INTC's?
I believe they will soon. AMD is a little behind, but the clocking speeds I believe are faster. AMD is so under
priced right now.
They are behind in max mhz, but it actual performance they are ahead on many benchmarks.
Tim