C70:info-cpm (05/13/82)
>From W8SDZ@Mit-Mc Thu May 13 00:20:33 1982
Date: 12 May 82 13:09:20-EDT (Wed)
From: decvax!harpo!duke!hes at Berkeley
To: info-micro at mit-ai
Re: IBM PC Benchmark
Article-I.D.: duke.2129
Via: news.usenet; 12 May 82 12:08-PDT
Benchmarking the IBM PC
As an example of a heavily computational program, I wrote a
Basic program which fills two 10x10 matrices with values, and
then multiplies them together. It is all done in single precision,
with essentially no I/O.
It took 18-19 seconds. (Same with disk and advanced BASICs.)
I then ran it on a TRS-80 Model I Level II (unmodified with the
normal 1.77 MHz clock) and it took 36-37 seconds. (Note that 2x or
greater clock speed ups are available.)
I also ran it on a standard North Star Horizon, with and
without the floating point hardware board. Without the
board it took 18 seconds and with the board it took 14 sec.
(The Horizon has a Z-80 with a 4 MHz clock.)
Several other cpu intensive programs gave the same relative
performances.
From these tests it appears that the IBM PC runs BASIC
programs at a comparable speed to an 8080/Z-80 family
cpu with a 4 MHz clock.
Since the IBM PC is supposed to have its 8088 running with
a 4.88 (?) MHz clock, it would appear that the present
generation of IBM PC software does not take advantage of the
internal 16 bit architecture of the 8088. (Or perhaps is
just not as efficient as some older, more polished software.)
--henry schafferC70:info-cpm (05/15/82)
>From W8SDZ@Mit-Mc Sat May 15 00:19:34 1982
Date: 05/13/82 04:01:58
From: POURNE
Re: [decvax!harpo!duke!hes: IBM PC Benchmark]
It would be interesting to see what times you get on a Godbout
8085/8088 machine for your program. The BIOS for that wuld also
be significant my engineers just chopped the Godbout BIOS by
about a .33 and lo! it speeds all sort of things up, not merely
disk io.C70:info-cpm (05/15/82)
>From W8SDZ@Mit-Mc Sat May 15 00:51:16 1982
Date: 13 May 1982 18:18:53 EDT (Thursday)
From: Carl D. Howe <cdh at BBN-UNIX>
To: decvax!harpo!duke!hes at Berkeley
cc: info-micro at mit-ai
Re: IBM PC Benchmark
From: decvax!harpo!duke!hes at Berkeley
....
" Since the IBM PC is supposed to have its 8088 running with
a 4.88 (?) MHz clock, it would appear that the present
generation of IBM PC software does not take advantage of the
internal 16 bit architecture of the 8088. (Or perhaps is
just not as efficient as some older, more polished software.)"
I suspect that the current generation of IBM software uses the 16 bit
architecture of the 8088 extensively, and therein lies the performance
problem. When you assume that 16 bit operations are the right thing
ON AN 8-BIT BUS, you end up doing a lot of back-to-back bus
cycles, many of them needlessly. If IBM was using an 8 bit bus that
was capable of doing twice as many transactions per second as the rest
of the industry, then the 16 bit architecture would be a big performance
improvement. As it is, the fact that the machine has an 8 bit bus and
runs it at a comparable speed to all the rest of the 8 bit machines dictates
that the machine has the performance of an 8 bit micro.
In short, chip architecture performance is often dominated by how fast
you can get items into and out of memory. You should view the use of an
8088 in the IBM PC as a feature to aid software development,
not as a feature to improve performance. The IBM PC is still an 8 bit micro,
despite the 8088's 16 bit architecture.
Carl