gary@logico.UUCP (Gary Vrooman) (12/08/88)
Cumulus Corp has announced a 386SX card for the PC/AT. It snaps into the motherboard rather than using up a slot. It costs around $600 but only provides roughly a 15% speedup over an AT. The card that we all really want for $600 would include an 82385 cache controller and 32K of static RAM. This should provide nearly double the speed of a PC/AT. Cumulus can be reached at 216-464-2211.
ray@micomvax.UUCP (Ray Dunn) (12/15/88)
In article <1031@logico.UUCP> gary@logico.UUCP (Gary Vrooman) writes: >....has announced a 386SX card for the PC/AT. >....but [it] only provides roughly a 15% speedup over an AT. The 386SX should *not* be regarded as a performance enhancer over 286 machines, indeed at the same clock speed, the 386SX performs slower than a 286. The 386SX is only cost-effective (if at all) as the low end of the 386 family - running 386 based software - rather than the high end of the 286 family running 80286 or 8088 based code. The 386SX provides extra functionality over the 286, not extra performance. The 386SX is what the 80286 *should* have been, and allows you to run full blown protected UNIX etc, and, eventually, the 386 version of OS/2. Moral: Don't buy a 386SX machine to run DOS! >The card that we all really want for $600 would include an 82385 cache >controller and 32K of static RAM. At 16Mhz, this would have an insignificant affect on the performance. -- Ray Dunn. | UUCP: ..!philabs!micomvax!ray Philips Electronics Ltd. | TEL : (514) 744-8200 Ext: 2347 600 Dr Frederik Philips Blvd | FAX : (514) 744-6455 St Laurent. Quebec. H4M 2S9 | TLX : 05-824090
toma@tekgvs.GVS.TEK.COM (Tom Almy) (12/20/88)
In article <1550@micomvax.UUCP> ray@micomvax.UUCP (Ray Dunn) writes: >The 386SX provides extra functionality over the 286, not extra performance. > >The 386SX is what the 80286 *should* have been, and allows you to run full >blown protected UNIX etc, and, eventually, the 386 version of OS/2. > >Moral: Don't buy a 386SX machine to run DOS! But you can still get make use of the extra functionality of the 386 with DOS: 1. For Microsoft Windows, Windows 386 is much better than 286 in its handling of DOS applications. 2. Descview is somewhat better with a 386. 3. If for some reason you have extended memory rather than expanded memory, QEMM or 386-TO-THE-MAX can be used to emulated expanded memory. Also, extended memory ram-disks are much faster with a 386 because the 386 can leave protected mode without resetting the processor. 4. Assuming the 80387SX (?) chip is based on the 80387, the 80387 is much faster than the 80287, and has increased functionality. This could make floating point intensive programs faster, even if the 80386SX is no faster than the 80286. Also, there are some DOS applications that run in 386 protected mode. It makes sense to me to upgrade to the 386SX, but new systems should all be 80386 (and not 80386SX) based. Tom Almy toma@tekgvs.TEK.COM Standard Disclaimers Apply
gary@logico.UUCP (Gary Vrooman) (12/20/88)
In an earlier posting, I suggested that the ideal CPU add-in card for PC/AT owners would be a 16MHZ 386SX with an Intel 82385 cache controller and 32K of static Ram. The reason for this configuration would be to maximize performance without sending cost through the roof. The key idea is that this tiny add-in card would not contain any system memory - you could continue to use the slow (150 nanosecond) DRAMs sitting on the 16 bit AT expansion bus. If the cache controller can maintain a cache hit rate of 90-95%, then the 16 MHZ 386SX should provide roughly double the performance of an 8 MHZ AT. This configuration is the ideal situation for an AT like mine which has 3.5 Megabytes of slow DRAMs installed - I don't want to have to replace this RAM at today's prices.
davidsen@steinmetz.ge.com (William E. Davidsen Jr) (12/20/88)
In article <1550@micomvax.UUCP> ray@micomvax.UUCP (Ray Dunn) writes: | The 386SX should *not* be regarded as a performance enhancer over 286 | machines, indeed at the same clock speed, the 386SX performs slower than a | 286. Running 8088 code (like MS-DOS), this might be true, although I wouldn't want to have to measure the performance and swear that it was one way or the other. Some instructions are a little faster, some a little slower, and the prefetch queue is the same size as the 386 (I believe, I have to rely of a magazine article). | The 386SX provides extra functionality over the 286, not extra performance. | | The 386SX is what the 80286 *should* have been, and allows you to run full | blown protected UNIX etc, and, eventually, the 386 version of OS/2. | | Moral: Don't buy a 386SX machine to run DOS! I agree with that, however, if you buy a 386 compiler such as Phar Lap, you should see a large improvement in performance. On an 80386 changing from 286 to 386 instructions gives 2-3 improvement in most cases, I would expect about 2:1 faster for a 386SX. -- bill davidsen (wedu@ge-crd.arpa) {uunet | philabs}!steinmetz!crdos1!davidsen "Stupidity, like virtue, is its own reward" -me
jim@belltec.UUCP (Mr. Jim's Own Logon) (12/20/88)
> I agree with that, however, if you buy a 386 compiler such as Phar > Lap, you should see a large improvement in performance. On an 80386 > changing from 286 to 386 instructions gives 2-3 improvement in most > cases, I would expect about 2:1 faster for a 386SX. > -- > bill davidsen (wedu@ge-crd.arpa) > {uunet | philabs}!steinmetz!crdos1!davidsen > "Stupidity, like virtue, is its own reward" -me The simplest 386SX upgrade is a daughter card that plugs into the 286 socket. Runs at the same clock rate. Still is 16 bits. Still has the same performance (within a few percent). Doesn't matter which compiler you use, the hardware fetch of instructions is the same rate. And 16 bit code is 16 bit code (this does sound a lot like a hardware geek putting down the software, but in this case the point is true). A 386 compiler will not buy you any more than a few percent improvement because of the instructions that a 386 has and a 286 doesn't have. The original poster had the right idea for real speed up. The SX runs at the 16MHz speed of the CPU and has a local cache to support that speed. Only for cache misses (you will be lucky to get anywhere near 90% for UNIX) do you slow down for the regular speed of the 286 memory fetches. A company already makes a board just like this. Aox Inc. of Waltham Mass., no phone number in the article. My favorite line in the add/article: "Cost of the board is determined case by case". Anyway all of the speed stuff is right from the Intel application notes. Running at the same speed of the 286, the most you'll see is 15% speed up, and when you talk to real Intel engineers they say that is a max theoretical number and the real number is more like 5% for real applications. -Jim Wall Bell Technologies, Inc.