If this is your first visit, be sure to check out the FAQ by clicking the link above. You may have to register before you can post: click the register link above to proceed. To start viewing messages, select the forum that you want to visit from the selection below. |
|
|
Thread Tools | Display Modes |
#52
|
|||
|
|||
Intel working on Z-RAM too
In article om,
says... Northstar had one form of multithreading, the one that could be added economically. It was enough of a win that it was carried forward for several generations of processors. Absolutely. I'm not denigrating SoEMT; I'm just pointing out that it's not SMT, and Keith should know better than to try to foist that fallacy on us. You're a piece of work. What about the /195 and /95 (known as dual I-stream then)? Interesting, I hadn't heard of either. You've ignored every previous comment I've made about these, dismissing them as "PowerPC" products boggle. Clearly you have no clue and refuse to buy one. I tried searching and I found this: http://www-03.ibm.com/ibm/history/ex...me_PP2195.html Could you provide a link that might have more technical details? I'd be interested in learning about the 195. This stuff wasn't much ballyhooed in the '60s. No one would have understood it. Perhaps you want to ask more on an appropriate forum? Keith, you are making a rather extraordinarily claim. SMT became a well defined term in the mid 1990's due to the work of the SMT group at UW. I have read several of their research and I haven't found a single reference to such a beast. Certainly, academics have a responsibility when submitting refereed papers to cite and discuss prior work. New terms are what academia is all about. Have you researched the /195? I suggest that you do. "New" things tend not to be so new, just the costs come down. If you look at "simultaneous multithreading: maximizing on-chip parallelism", the seminal paper, particularly section 7, I see no mention of such a processor from IBM (although I did not read all the papers referenced, merely looked for titles indicating IBM or the 195). Given the folks that the SMT group collaborated (including Joel Emer of DEC), I have a hard time believing that they simply 'forgot' the existence of a prior processor which implemented all the key features of SMT. There were some processors that implemented SMT, but they were special purpose (ray tracing), lacking caches, etc. etc. Why not look at the "micro"-architecture of the /195? The Dual I- Stream isn't so much different. Two instructions streams from the I-box being fed into the E-box so it had something to do if either 'I's took a branch. All together, it seems to me that the burden of proof rests upon your shoulders to show: 1. What the 195 is. WOW If you have to ask this, clearly you're not capable of holding up your end of any such argument. ...not to mention the /95. 2. That it actually implemented SMT Do some more research. SMT, as you narrowly define it? Maybe not. here is little new under the sun though. Perhaps you'd like to follow Intel's SMT patents backwards? You have done neither, and rather indicated that "I need to ask elsewhere". It seems to me that if you wish to debunk what seems to be reasonably well accepted truth, you should be willing to back up, with references...rather than simply claim the existence of a counter example without substantiation. No, I'm calling out your typical technology "expertise" crap and telling you to look further. You can't, not that you'd understand it anyway. -- Keith |
#53
|
|||
|
|||
Intel working on Z-RAM too
krw wrote: In article . com, says... Del Cecchi wrote: David Kanter wrote: Yousuf Khan wrote: David Kanter wrote: My apologies if I mischaracterized your statement. The point remains: certain elements within IBM clearly did not believe that SOI was worth it, and wanted to stick with bulk. You still can't get it right! You certainly are blind. According to Del "As Keith knows, there was a heated debate within IBM over the merits of SOI. And today the IBM Fab manufactures both bulk and SOI." That there was a debate clearly means that some folks had differing views on the merits of SOI. Now at the conclusion of the debate, the doubters were either overruled or convinced of the merits of SOI. However, just because the outcome went one way at IBM does not guarantee that the outcome will go the same at Intel. There are plenty of companies that design MPUs, DSPs, etc. etc. and their processes vary quite a bit. Some have more metal layers, some have less, some use SOI, some don't. If you think I'm so blind perhaps you could enlighten us all with your knowledge and explain what I'm missing? [snip] http://www.realworldtech.com/page.cf...005001504&p=14 This article, written by David Wang, shows a cross comparison of different process technologies. In looking at the 65nm nodes, we can compare the IBM process to the joint IBM/AMD/Toshiba/Sony. It appears that the Ion for ITSA is slightly higher, while Intel's Ioff is about 2x lower. Of course, Intel's high Vt transistors have substantially less leakage (factor of ~10) than the low Vt, at the cost of worse Ion performance. Do you know what this means? I didn't think so. Keith, most of the terms are defined (perhaps informally, but defined nonetheless) earlier in the article. If I made any errors in reading the chart, I'd be more than happy to accept corrections. Also, for those who were curious about SRAM cell sizes, they are included in the chart. Different strokes for different folks. This point went back to earlier in the thread when discussing SRAM density. Myself, I really don't know the numbers for SOI advantage at 65 or 45nm process nodes. The chart above does have some information, and the rest of the article has more. One caveat is that I'm not sure whether these numbers include the later modifications to the process. Of course you don't know. You have no degree in anything relevant, remember? You know, some of the best computer architects I've spoken with don't have relevant degrees. Take John McCalpin; he got a PhD in Physical Oceanography. Now that sounds irrelevant to computer architecture, but last time I heard he did some good things at SGI, at IBM and now at AMD. Besides, I rather doubt you know enough about my academic background to make judgments. DK |
#54
|
|||
|
|||
Intel working on Z-RAM too
krw wrote: In article om, says... Northstar had one form of multithreading, the one that could be added economically. It was enough of a win that it was carried forward for several generations of processors. Absolutely. I'm not denigrating SoEMT; I'm just pointing out that it's not SMT, and Keith should know better than to try to foist that fallacy on us. You're a piece of work. What about the /195 and /95 (known as dual I-stream then)? Interesting, I hadn't heard of either. You've ignored every previous comment I've made about these, dismissing them as "PowerPC" products boggle. Clearly you have no clue and refuse to buy one. I tried searching and I found this: http://www-03.ibm.com/ibm/history/ex...me_PP2195.html Could you provide a link that might have more technical details? I'd be interested in learning about the 195. This stuff wasn't much ballyhooed in the '60s. No one would have understood it. Perhaps you want to ask more on an appropriate forum? Keith, you are making a rather extraordinarily claim. SMT became a well defined term in the mid 1990's due to the work of the SMT group at UW. I have read several of their research and I haven't found a single reference to such a beast. Certainly, academics have a responsibility when submitting refereed papers to cite and discuss prior work. New terms are what academia is all about. Have you researched the /195? I suggest that you do. "New" things tend not to be so new, just the costs come down. I tried looking into the /195, but there's not much online about it. The only reference I can find is a paper: JO Murphey, RM Wade - Datamation, 1970 Which is not available online. Given the date, it's clearly a dead tree journal, and probably one that hasn't been OCRed. If you look at "simultaneous multithreading: maximizing on-chip parallelism", the seminal paper, particularly section 7, I see no mention of such a processor from IBM (although I did not read all the papers referenced, merely looked for titles indicating IBM or the 195). Given the folks that the SMT group collaborated (including Joel Emer of DEC), I have a hard time believing that they simply 'forgot' the existence of a prior processor which implemented all the key features of SMT. There were some processors that implemented SMT, but they were special purpose (ray tracing), lacking caches, etc. etc. Why not look at the "micro"-architecture of the /195? The Dual I- Stream isn't so much different. Two instructions streams from the I-box being fed into the E-box so it had something to do if either 'I's took a branch. So the idea is that on a long latency event, you switch to another process or thread? This sounds like a precursor to switch on event multithreading. All together, it seems to me that the burden of proof rests upon your shoulders to show: 1. What the 195 is. WOW If you have to ask this, clearly you're not capable of holding up your end of any such argument. ...not to mention the /95. 2. That it actually implemented SMT Do some more research. SMT, as you narrowly define it? Maybe not. here is little new under the sun though. Perhaps you'd like to follow Intel's SMT patents backwards? The SMT research at UW clearly was influenced by prior efforts. They cited quite a few of them in the paper I mentioned. I didn't see anything on the 195 in their paper. Now perhaps the connection is 2nd degree or 3rd degree. However, it seems to me that SMT likely focuses on addressing different performance issues than what the 195 was faced with. Are the ideas similar? Somewhat. But AFAICT they are quite different beasts. It sounds like the dual istream is far more similar to SoEMT than SMT. DK |
#55
|
|||
|
|||
Intel working on Z-RAM too
On 16 Dec 2006 17:49:19 -0800, "David Kanter" wrote:
Del Cecchi wrote: David Kanter wrote: Yousuf Khan wrote: David Kanter wrote: You heard Del say no such thing. I said there was a heated debate, which is a long way from "huge fight". Back in the day there was honest disagreement over the magnitude of the power and performance difference. My apologies if I mischaracterized your statement. The point remains: certain elements within IBM clearly did not believe that SOI was worth it, and wanted to stick with bulk. And SOI is not just being used for "high end stuff". It just isn't being used for Standard Cell ASIC chips. Perhaps our definition of high end vary... SOI adds substantial costs, it would also force Intel to totally rework their circuit stuff, etc. etc. And frankly, SOI is worth less and less performance at every node. Gee, I haven't heard that. Who told you that? Have you done measurements? Run 3D field simulations? Or was this Intel spin? Remember sometimes spin is true and sometimes it isn't. This was information from an engineer in Canada who used to post to comp.arch. I have no particular reason to disbelieve what he said, although I'm certainly open to listening to other POVs. I believe I've already indicated that I'm not an EE, physicist nor do I run sims. I would point out that there is some information on the relative merits of the different processes: If you look back at what you posted, Intel is apparently considering SOI for the 32nm and 22nm nodes. Ther appears to be a umm, dichotomy in your reasoning here. http://www.realworldtech.com/page.cf...005001504&p=14 This article, written by David Wang, shows a cross comparison of different process technologies. In looking at the 65nm nodes, we can compare the IBM process to the joint IBM/AMD/Toshiba/Sony. It appears that the Ion for ITSA is slightly higher, while Intel's Ioff is about 2x lower. Of course, Intel's high Vt transistors have substantially less leakage (factor of ~10) than the low Vt, at the cost of worse Ion performance. With all due respect to Dave Wang, somtime around the time of that article, Dave stated categorically right in this NG that we would never see SOI 65nm from Chartered... and now?? Sure, I can buy a cell phone for 20 dollars at walmart and it provides a useful service to the average person, even in a LDC. What use is a PC to the average person in a LDC? It's a rather useful educational tool. Word processing, spread sheets, email, wikipedia, developing. All sorts of things you can do. From what I've observed, the most useful part of PCs/Internet for students is as a tool for plagiarism...and theft.:-( -- Rgds, George Macdonald |
#56
|
|||
|
|||
Intel working on Z-RAM too
George Macdonald wrote:
On 16 Dec 2006 17:49:19 -0800, "David Kanter" wrote: Del Cecchi wrote: David Kanter wrote: Yousuf Khan wrote: David Kanter wrote: You heard Del say no such thing. I said there was a heated debate, which is a long way from "huge fight". Back in the day there was honest disagreement over the magnitude of the power and performance difference. My apologies if I mischaracterized your statement. The point remains: certain elements within IBM clearly did not believe that SOI was worth it, and wanted to stick with bulk. And SOI is not just being used for "high end stuff". It just isn't being used for Standard Cell ASIC chips. Perhaps our definition of high end vary... SOI adds substantial costs, it would also force Intel to totally rework their circuit stuff, etc. etc. And frankly, SOI is worth less and less performance at every node. Gee, I haven't heard that. Who told you that? Have you done measurements? Run 3D field simulations? Or was this Intel spin? Remember sometimes spin is true and sometimes it isn't. This was information from an engineer in Canada who used to post to comp.arch. I have no particular reason to disbelieve what he said, although I'm certainly open to listening to other POVs. I believe I've already indicated that I'm not an EE, physicist nor do I run sims. I would point out that there is some information on the relative merits of the different processes: If you look back at what you posted, Intel is apparently considering SOI for the 32nm and 22nm nodes. Ther appears to be a umm, dichotomy in your reasoning here. http://www.realworldtech.com/page.cf...005001504&p=14 This article, written by David Wang, shows a cross comparison of different process technologies. In looking at the 65nm nodes, we can compare the IBM process to the joint IBM/AMD/Toshiba/Sony. It appears that the Ion for ITSA is slightly higher, while Intel's Ioff is about 2x lower. Of course, Intel's high Vt transistors have substantially less leakage (factor of ~10) than the low Vt, at the cost of worse Ion performance. With all due respect to Dave Wang, somtime around the time of that article, Dave stated categorically right in this NG that we would never see SOI 65nm from Chartered... and now?? Sure, I can buy a cell phone for 20 dollars at walmart and it provides a useful service to the average person, even in a LDC. What use is a PC to the average person in a LDC? It's a rather useful educational tool. Word processing, spread sheets, email, wikipedia, developing. All sorts of things you can do. From what I've observed, the most useful part of PCs/Internet for students is as a tool for plagiarism...and theft.:-( And spread sheets and english word processing, english wikipedia, all big help to joe dugan in LDC, eh? -- Del Cecchi "This post is my own and doesn’t necessarily represent IBM’s positions, strategies or opinions.” |
#57
|
|||
|
|||
Intel working on Z-RAM too
George Macdonald wrote: On 16 Dec 2006 17:49:19 -0800, "David Kanter" wrote: Del Cecchi wrote: David Kanter wrote: Yousuf Khan wrote: David Kanter wrote: You heard Del say no such thing. I said there was a heated debate, which is a long way from "huge fight". Back in the day there was honest disagreement over the magnitude of the power and performance difference. My apologies if I mischaracterized your statement. The point remains: certain elements within IBM clearly did not believe that SOI was worth it, and wanted to stick with bulk. And SOI is not just being used for "high end stuff". It just isn't being used for Standard Cell ASIC chips. Perhaps our definition of high end vary... SOI adds substantial costs, it would also force Intel to totally rework their circuit stuff, etc. etc. And frankly, SOI is worth less and less performance at every node. Gee, I haven't heard that. Who told you that? Have you done measurements? Run 3D field simulations? Or was this Intel spin? Remember sometimes spin is true and sometimes it isn't. This was information from an engineer in Canada who used to post to comp.arch. I have no particular reason to disbelieve what he said, although I'm certainly open to listening to other POVs. I believe I've already indicated that I'm not an EE, physicist nor do I run sims. I would point out that there is some information on the relative merits of the different processes: If you look back at what you posted, Intel is apparently considering SOI for the 32nm and 22nm nodes. Ther appears to be a umm, dichotomy in your reasoning here. Not really. When I say SOI, I mean PD-SOI. Intel plans to use FD-SOI, which is a rather different beast. No dichotomy there... http://www.realworldtech.com/page.cf...005001504&p=14 This article, written by David Wang, shows a cross comparison of different process technologies. In looking at the 65nm nodes, we can compare the IBM process to the joint IBM/AMD/Toshiba/Sony. It appears that the Ion for ITSA is slightly higher, while Intel's Ioff is about 2x lower. Of course, Intel's high Vt transistors have substantially less leakage (factor of ~10) than the low Vt, at the cost of worse Ion performance. With all due respect to Dave Wang, somtime around the time of that article, Dave stated categorically right in this NG that we would never see SOI 65nm from Chartered... and now?? How does that matter? David's numbers can all be checked against the IEDM presentations/papers AFAIK. The numbers say it all... DK |
#58
|
|||
|
|||
Intel working on Z-RAM too
Bet Rambus tries to stick thier little dicks in this too.
"YKhan" wrote in message oups.com... Only they call it floating-body RAM. AMD obviously has put a scare into Intel with its well-advanced studies with Innovative Silicon. It would be interesting to see how Intel can get around Innovative's patents in this field. BTW, the "history effect" that Intel is talking about is capacitance, and this indicates that Intel is looking into using SOI as well, because this is the only way it can create a capacitance. Intel talk up Floating Body Cells http://www.theinquirer.net/default.aspx?article=36285 |
#59
|
|||
|
|||
Intel working on Z-RAM too
"don't look" wrote in message news:Ssgmh.1571$IT2.121@trnddc06... Bet Rambus tries to stick thier little dicks in this too. "YKhan" wrote in message oups.com... Only they call it floating-body RAM. AMD obviously has put a scare into Intel with its well-advanced studies with Innovative Silicon. It would be interesting to see how Intel can get around Innovative's patents in this field. BTW, the "history effect" that Intel is talking about is capacitance, and this indicates that Intel is looking into using SOI as well, because this is the only way it can create a capacitance. Intel talk up Floating Body Cells http://www.theinquirer.net/default.aspx?article=36285 There are always 6111778 and 5977578 to keep it interesting. |
#60
|
|||
|
|||
Intel working on Z-RAM too
"Robert Redelmeier" wrote in message
. net... Harrumphff! It seems you used some sort of "Global Search" to find your name. No, actually I subscribed to the group just today after many, many months of not reading. I read a number of threaded conversations, and that particular comment leapt out after reading another one with my name mentioned. The quote you lifted deep out of context was Keith berating David in a long exchange a month ago. AFAICS, "Dean" was a typo. But if the shoe fits ... Actually, there was another post where Keith called David "Dean Jr". So perhaps the 'shoe' that fits is not the one you think it is. As for the ad-hominem, IMHO it was justified by David's obdurancy. An attempt to shake his beliefs (P4 SMT) so he could see. Not always adviseable or polite. Being little more than a dressed-up P1, the dual issue P4 is singularly ill-suited to SMT. It is too starved of issue ports and only can run a thread without slowing the other when one is stalled by RAM-fetch. Which admittedly is fairly long with the poxy (high latency) Intel MCH architecture. When people start claiming that personal attacks are justified, they've simply bought into the bad behavior that has become all too prevalent here and elsewhere. I am ashamed to admit that I was a part of the degradation back during the John Corse years, and it changed the culture of this group irreparably, IMO. I am very happy to see that Tony, yourself and several others have refrained from succumbing to the behavior yourselves - but accepting it and actually justifying it is troubling. Nonetheless, the perusing of the group has done nothing to make me regret my decision to stop reading/posting. I realize nobody else really cares anyway, so enjoy the peace it brings... Regards, Dean -- Robert |
Thread Tools | |
Display Modes | |
|
|
Similar Threads | ||||
Thread | Thread Starter | Forum | Replies | Last Post |
Intel buying Nvidia rumours begin | bbbl67 | General | 33 | October 22nd 06 03:45 AM |
Intel--Nvidia merger or acqusition. unlikely, but possible ? | AirRaid | Intel | 70 | August 3rd 06 02:31 PM |
Intel--Nvidia merger or acqusition. unlikely, but possible ? | AirRaid | Nvidia Videocards | 66 | August 3rd 06 01:09 PM |
Anandtech's Conroe vs. FX60 | Yousuf Khan | General | 58 | April 1st 06 05:19 AM |
Best bang for buck CPU? | Shawk | Homebuilt PC's | 9 | October 5th 03 07:24 PM |