bowden@gumby.cc.wmich.edu (Michael L. Bowden) (10/25/89)
Someone recently stated some performance figures regarding the 286, 386SX, and 386 processors, but unfortunately I missed it. The understanding I had was that the 386SX doesn't run DOS applications as fast as an equivalent speed 286. Is this right? If so, how much faster is the 286, and more importantly, *why* is it faster? -- Michael L. Bowden Internet: bowden@gumby.cc.wmich.edu Western Michigan University bowden@gw.wmich.edu Academic Computer Center Voice: (616) 387-5448 Kalamazoo, MI 49008
davidsen@crdos1.crd.ge.COM (Wm E Davidsen Jr) (10/25/89)
The 286 executes a few instructions in one less clock cycle than the 386. It is technically "faster" but I think you would be hard pressed to even measure it, much less notice. I believe that some benchmarks which heavily use these instructions may run 1-2% soler on a 386. Programs which use the 386 instructions will run MUCH faster than the same program using the 286 instructions. I measured 4:1 faster for some benchmarks I just posted, and I see 2:1 on production programs. I believe Phil Katz mentioned ZIP runs 40% faster on a 386. The bottom line is that you might lose up to 2% on some programs with a 386, and gain up to 200% (real programs, not benchmarks). You will be able to run new software as it comes out. -- bill davidsen (davidsen@crdos1.crd.GE.COM -or- uunet!crdgw1!crdos1!davidsen) "The world is filled with fools. They blindly follow their so-called 'reason' in the face of the church and common sense. Any fool can see that the world is flat!" - anon
pa1632@sdcc13.ucsd.edu (Robert Kim) (10/28/89)
In article <904@gumby.cc.wmich.edu> bowden@gumby.cc.wmich.edu (Michael L. Bowden) writes: >Someone recently stated some performance figures regarding the >286, 386SX, and 386 processors, but unfortunately I missed it. The >understanding I had was that the 386SX doesn't run DOS applications >as fast as an equivalent speed 286. Is this right? If so, how much >faster is the 286, and more importantly, *why* is it faster? I also hear that Harris came out with a 20MHz 286, and according to them, it's supposed to be about n times faster (I forgot how much) than the 20MHz 386. So again, why is it faster? -- Robert W. Kim rkim@ucsd.edu University of California, San Diego Home of the Price Club Center "So what? It's my opinion...ouch! Hey, stop that clubbing...ouch!"
wsinrn@eutrc3.urc.tue.nl (Rob J. Nauta) (10/31/89)
Hello Basically it is true, but the 386 is probably a few percent slower than a 286 at the same speed. But don't forget a 386 or 386 SX often has memory interleaving, or better memory caching. And software that can take advantage of the 386 will use the 32 bits bus, loading 4 bytes at once in a register instead of 2 times a 2byte integer. Plus the fact that the 386 has memory mapping capabilities that can make your PC a lot more useful, for example with programs like QEMMS or 386-to-the-max. Buy a 386, it's worth it... Rob