kingsley@hpwrce.HP.COM (Kingsley Morse) (12/11/90)
I heard a rumor that 25 MHZ 486 PCs can be made faster by installing a commercially available product based on a heat sink. Rumor has it that the product allows one to double the speed of the cpu. It's supposed to cost only $50, and is sold by a company called something like SI Labs. Can anyone provide more information on this product?
ekalenda@cup.portal.com (Edward John Kalenda) (12/14/90)
> I heard a rumor that 25 MHZ 486 PCs can be made faster by installing a > commercially available product based on a heat sink. Rumor has it that the > product allows one to double the speed of the cpu. It's supposed to cost > only $50, and is sold by a company called something like SI Labs. > > Can anyone provide more information on this product? The December issue of Byte magazine has an article on the ICECap from Velox Computer Technology. The ICECap keeps the chip at 0 degress Centigrade and adjusts the input voltage to the chip to minimize delays. They had an experimental Everex Step 486/50 based on it. The ICECap is based on the Peltier effect, "a thermoelectric cooling system based on the principle that passing current between two physically connected, dissimilar materials produces cooling on one side and heat on the other". Apparently, the increase in system cost would only be $600 so we should be seeing something based on it. I'd guess late in 1991 for the fisrt units to hit the street. Expect to pay through the nose, they'll charge you for running fast, not just for the cost of the part. Ed ekalenda@cup.portal.com
schow@bcarh185.bnr.ca (Stanley T.H. Chow) (12/15/90)
In article <36894@cup.portal.com> ekalenda@cup.portal.com (Edward John Kalenda) writes: >The December issue of Byte magazine has an article on the ICECap from Velox >Computer Technology. The ICECap keeps the chip at 0 degress Centigrade and >adjusts the input voltage to the chip to minimize delays. They had an >experimental Everex Step 486/50 based on it. Note that having the CPU chip running at 50 MHz is only the first step, the whole motherboard and memory system must then keep up. The Everex actually had a 50 MHz CPU running on a 25 MHz board (by divide the clock at strategic places). >Apparently, the increase in system cost would only be $600 so we should >be seeing something based on it. I'd guess late in 1991 for the fisrt units >to hit the street. Expect to pay through the nose, they'll charge you for >running fast, not just for the cost of the part. Getting a motherboard running at 50 MHz is a lot more difficult, just the faster parts will run you thounsands of dollars; add in the design, manufacture and support costs amortized over a few machines, we are talking major bucks. Stanley Chow BitNet: schow@BNR.CA BNR UUCP: ..!uunet!bnrgate!bcarh185!schow (613) 763-2831 ..!psuvax1!BNR.CA.bitnet!schow Me? Represent other people? Don't make them laugh so hard.
kingsley@hpwrce.HP.COM (Kingsley Morse) (12/18/90)
schow@bcarh185.bnr.ca (Stanley T.H. Chow) writes: >Getting a motherboard running at 50 MHz is a lot more difficult Would it be possible to keep the motherboard at 25 MHz and rely on speeding up the cache on the cpu chip to get some speed increase for small (or local) programs?
schow@bcarh185.bnr.ca (Stanley T.H. Chow) (12/19/90)
In article <2370005@hpwrce.HP.COM> kingsley@hpwrce.HP.COM (Kingsley Morse) writes: >schow@bcarh185.bnr.ca (Stanley T.H. Chow) writes: > >>Getting a motherboard running at 50 MHz is a lot more difficult > >Would it be possible to keep the motherboard at 25 MHz and rely on speeding >up the cache on the cpu chip to get some speed increase for small (or local) >programs? Yes, it is certainly possible. That is how the Everex machine was set up. We also do it in some of our processors in telephone switches. The problem, is of course, Cache Hit-rate. The actual speed up will vary depending on the cache size, cache fill algorithm, cache replacement algorithm, delays caused by interfacing at two speeds, etc. For example, in our product, going from a 68030 at 20 MHz to a 68030 at 40 MHz (with 20 MHz memory, but 512K of 40MHz SRAM) got a factor of 1.5 speed up instead of a factor of two. For most PC compute-intensive applications, the bare i486 runing at double speed is likely to get only a factor of 1.2 speed up. With more cache at 50 MHz, the speed up may get as high as 1.5. On the otherhand, going from 25MHz to 33MHz will get you a factor of 1.3. Stanley Chow BitNet: schow@BNR.CA BNR UUCP: ..!uunet!bnrgate!bcarh185!schow (613) 763-2831 ..!psuvax1!BNR.CA.bitnet!schow Me? Represent other people? Don't make them laugh so hard.
kingsley@hpwrce.HP.COM (Kingsley Morse) (12/20/90)
I've contacted Velox, who sells the ICECap, but it seems they don't have any deliverable product yet. Does anyone else know of any other vendors with similar products?