Originally posted by: openwheelformula1
lmao I learn something new every day from hardcore fans. I didn't know Prescott was an "ENTIRELY NEW" chip. Maybe they abandoned netburst and gave us more IPC. To both Intel fanatics hans007 and dmens, I was showing a big discrepency between the each company's development and improvement. Don't get offended if you thought I discredited hyperthreading. I loved my 2.8c, but it was short lived and quickly displaced by a Newcastle. BTW hans007, not "any process shrink" will "dramatically increase efficiency the way Winchester did after Newcastle. Especially near the ceiling of an archtecture such as netburst. There are VERY good reasons why Intel is abandoning netburst you know. I bet you haven't seen power consumption differences from reputable sites such as spcr. At least dmens passion for Intel is backed up by knowledge. Enjoy your Prescott/Smithfield/Presler, and I'll probably be joining you once Conroe hits the shelves. At the mean time I'll stick to my efficient and powerful X2 and Venice (Relatively to netburst that is). Ciao.
Hypothetically, if Intel suddenly decided to impliment integrated memory controller and hyper transport. Can you honestly tell me you wouldn't like it?
AMD PR hype? What? AMD has a PR department?
Am I a wannabe engineer? LMAO hell yeah, graduate student at UCSB-Material.
ok, i majored in computer science and spent time optimizing instruction paths and learning about pipelining, branch prediction and latencies and why hyperthreading actually works. yes i will admit i'm a software engineer. but whatever i think i am just as justified in saying what i have said. at least i did not resort to calling anyone a fanatic. i am just trying to present what i believe is a better representation of why intel has done what they have done.
amd does have a pr department, its called the law team that is trying to get into the news every other week with their antitrust case. now i am not calling the lawsuit completely baseless, as there is likely some merit in it, though 90% of what they are doing is just to get their name in the news and keep intel on their toes.
and yes it would be good if intel had an integrated memory controller and hypertransport. and i probably would like it if it were free. unfortunately they already had a working chipset foundation and fsb, and the amoutn of r&d/testing for all new stuff would probably raise the price of all their products. perhaps they decided the cost / benefit for most systems was not enough. a nice corollary would be the ddr2 support for the athlon64. if i had asked you ayear ago if you would like it you'd probably have said sure.. and then i'd have to tell you it'd take a year to come out, all new motherboards, heatsinks and a 10% increase in die space, as well as costs that would be paid by you.
as for your process shrink "idea" the shrink did increase the efficiency of the prescott from 90nm to 65nm. the 130nm to 90nm was not a shrink as it was a completely different core design.
yonah is proof of why you do not need an on die controller. i know you like the venice design, but give intel some credit their mobile cpus , including even the dothan and banias are clock for clock with anything amd makes, and use even less power with no on die controller. the yonah chips even only have 2mb of cache for 2 cores which is a much more advanced shared cache design compared to the non shared caches in the x2 chips.
also i owned a winchester AND several newcastles. that was a direct shrink with no real optimizations, which is why it also only was used in up to 3500+ speed grades. you have already said that shrinking the prescott being an "end of life" proces was not worth while. but it has in fact given it better energy efficiency from 90nm to 65nm. the heat difference was comparable to the smithfield -> presler in percentage probably even less of a difference.
and as to your "ceiling of an architecture" statment, the newcastle hit 2.6 ghz fine in the fx55. does this mean that the process shrink to .90nm on the athlon 64 also "is near the cieling of an architecture", seeing as the highest rated single core 90nm cpu amd made was the fx57 , at a mere 200mhz higher clock speed. no. by your own words, you say they are retiring prescott because of heat. and yeah that sprobably true. but your own justification would say that the dual core athlon 64 should be retired, since its top end cpus such as the fx60 are putting out presler-like heat. so i am expecting you to call the fx62 a furnace whenever it comes out. it would only be fair.
the amd 64 architecture by your own definition woudl then also be classified as "near the ceiling" would it not? face it, a shrink is energy efficient. amd's shrink is no better than intels shrink . they both increased mainly energy efficiency and did not really increase top end clock speeds. amd and intel have both used shrinks mainly to pack more cores and cache. shrinsk are not giving higher clocks now, that doesnt mean any architecture is at its cieling.
.
Facebook
Twitter