Hi all,
I have always been interested in what are the tests that the magazines just referred to as BMn.
Finally, in July I found an exact description of them.
I was curious about the performance of SPONZY, so i quickly tried them out using the EO.
Used ROMs for the test:ZX Spectrum, ZX81(in fast/slow), ZX81-SPONZY(in fast/slow/spup)
The outcome is surprising: the ZX81 in fast mode won in the first eight tests! (BM 1-4 video)
(sorry, but i had no patience to wait for the result of the ninth)
Then i modified the first (and renamed it to BM0) and was surprised again.
The results and the programs are in the attachment. Do you know sg about BM10+?
Zsolt
Benchmarks on microcomputers
Benchmarks on microcomputers
- Attachments
-
- BM_0-9.zip
- (194.84 KiB) Downloaded 344 times
ZX81 (8K), ENTERPRISE 128, [ZX SPECTRUM (48K,+,+128K,+2,+2A), TS1000, TS1500, TS2068, Cambridge Z88, PRIMO A64 (red)]
- 1024MAK
- Posts: 5118
- Joined: Mon Sep 26, 2011 10:56 am
- Location: Looking forward to summer in Somerset, UK...
Re: Benchmarks on microcomputers
Interesting
I'm not that surprised that a ZX81 running in FAST mode just beats a 48K ZX Spectrum. The BASIC in the Spectrum is a development and extension of the ZX81 BASIC and on a real machine the first 16k of RAM on the Spectrum is affected by the ULA "pausing" the Z80 MPU so that the display is stable (contented memory).
The ZX81 and ZX Spectrum BASIC interpreters were designed to be compact and easy to use rather than for speed.
Earlier this week I was running a speed test on a BBC Master 128. I did notice that with BBC Basic the number of spaces (32 dec, 20 hex) entered as part of the program listing makes a significant difference when loops are involved.
This goes to show that the speed of interpreted code depends on how the program is written and the coding of the interpreter, just as much as the speed of the hardware
Mark
I'm not that surprised that a ZX81 running in FAST mode just beats a 48K ZX Spectrum. The BASIC in the Spectrum is a development and extension of the ZX81 BASIC and on a real machine the first 16k of RAM on the Spectrum is affected by the ULA "pausing" the Z80 MPU so that the display is stable (contented memory).
The ZX81 and ZX Spectrum BASIC interpreters were designed to be compact and easy to use rather than for speed.
Earlier this week I was running a speed test on a BBC Master 128. I did notice that with BBC Basic the number of spaces (32 dec, 20 hex) entered as part of the program listing makes a significant difference when loops are involved.
This goes to show that the speed of interpreted code depends on how the program is written and the coding of the interpreter, just as much as the speed of the hardware
Mark
ZX81 Variations
ZX81 Chip Pin-outs
ZX81 Video Transistor Buffer Amp
Standby alert
There are four lights!
Step up to red alert. Sir, are you absolutely sure? It does mean changing the bulb
Looking forward to summer later in the year.
ZX81 Chip Pin-outs
ZX81 Video Transistor Buffer Amp
Standby alert
There are four lights!
Step up to red alert. Sir, are you absolutely sure? It does mean changing the bulb
Looking forward to summer later in the year.
Re: Benchmarks on microcomputers
That's why the sponzy was made - to compare the interpreters on same hw.
The Fast mode is ideal for this purpose, no display/keyboard handling.
GZS
The Fast mode is ideal for this purpose, no display/keyboard handling.
GZS
ZX81 (8K), ENTERPRISE 128, [ZX SPECTRUM (48K,+,+128K,+2,+2A), TS1000, TS1500, TS2068, Cambridge Z88, PRIMO A64 (red)]