blombardi@x102c.ess.harris.com (Bob Lombardi 44139) (07/11/90)
My posting "QEMM 5.0 Sl-o-o-ows Down DMA" generated several E-Mail replies and started a line of discussion. I thought I'd follow-up to the net with what my conclusions are. In twenty-five words or less, the discrepancy is coming from Checkit itself, not from running QEMM. Every other test I can run shows a marginal slowdown at worst, nothing that comes close to the 15 times slowdown in DMA that Checkit claims. Quarterdeck customer service had no existing answer to the question, but did say that they've seen some benchmarks act strangely in virtual 86 mode. None of their suggestions yielded any improvement to Checkit. I have run other benchmarks, including the PC Magazine Benchmarks, and find no difference of any significance bewteen QEMM/noQEMM configuration results. I am a double E, so I don't expect to get something for nothing; the apparent 15 times slowdown was a bit expensive, though. (I don't _do_ bits, though, I'm a Microwave/RF guy. It seems that the system could really slow down that much, if they didn't know what they were doing.) Thanks to all who replied.... Bob ~a Bob Lombardi WB4EHS /-/-/ |Internet: blombardi@x102c.ess.harris.com Mail Stop 102-4826 | |phone: (407) 729-6360 Harris Corporation GASD | |The legal system is the epoxy glue that P.O.B. 94000, Melbourne FL 32902 |oils the wheels of American society.