Amiga.org
Amiga computer related discussion => Amiga Hardware Issues and discussion => Topic started by: Damion on December 09, 2007, 03:25:03 AM
-
I had some spare time today, so I thought I'd run some "bustest" (http://aminet.net/package/util/moni/bustest) benchmarks at various clockspeeds.
All tests were performed in WB, 640x512, 32 colors. (Pal High Res Laced.)
Hardware is an A1200, Escom 1D4 motherboard (timing fixes already done by Escom), Apollo 1260 with Rev 6 68060 (from PG) .
Bustest result at 50MHz:
BusSpeedTest 0.19 (mlelstv) Buffer: 262144 Bytes, Alignment: 32768
========================================================================
memtype addr op cycle calib bandwidth
fast $01460000 readw 86.9 ns normal 23.0 * 10^6 byte/s
fast $01460000 readl 154.2 ns normal 25.9 * 10^6 byte/s
fast $01460000 readm 153.5 ns normal 26.1 * 10^6 byte/s
fast $01460000 writew 113.2 ns normal 17.7 * 10^6 byte/s
fast $01460000 writel 227.5 ns normal 17.6 * 10^6 byte/s
fast $01460000 writem 225.1 ns normal 17.8 * 10^6 byte/s
chip $00060000 readw 1006.4 ns normal 2.0 * 10^6 byte/s
chip $00060000 readl 1007.7 ns normal 4.0 * 10^6 byte/s
chip $00060000 readm 1006.9 ns normal 4.0 * 10^6 byte/s
chip $00060000 writew 916.7 ns normal 2.2 * 10^6 byte/s
chip $00060000 writel 917.5 ns normal 4.4 * 10^6 byte/s
chip $00060000 writem 914.9 ns normal 4.4 * 10^6 byte/s
@ 64MHz:
BusSpeedTest 0.19 (mlelstv) Buffer: 262144 Bytes, Alignment: 32768
========================================================================
memtype addr op cycle calib bandwidth
fast $01440000 readw 67.8 ns normal 29.5 * 10^6 byte/s
fast $01440000 readl 119.9 ns normal 33.4 * 10^6 byte/s
fast $01440000 readm 118.8 ns normal 33.7 * 10^6 byte/s
fast $01440000 writew 88.3 ns normal 22.7 * 10^6 byte/s
fast $01440000 writel 176.1 ns normal 22.7 * 10^6 byte/s
fast $01440000 writem 175.8 ns normal 22.8 * 10^6 byte/s
chip $00058000 readw 1005.1 ns normal 2.0 * 10^6 byte/s
chip $00058000 readl 1006.4 ns normal 4.0 * 10^6 byte/s
chip $00058000 readm 1004.0 ns normal 4.0 * 10^6 byte/s
chip $00058000 writew 613.4 ns normal 3.3 * 10^6 byte/s
chip $00058000 writel 613.7 ns normal 6.5 * 10^6 byte/s
chip $00058000 writem 614.2 ns normal 6.5 * 10^6 byte/s
@ 66.6MHz
would not boot -- tried two separate oscillators
@ 70 MHz:
BusSpeedTest 0.19 (mlelstv) Buffer: 262144 Bytes, Alignment: 32768
========================================================================
memtype addr op cycle calib bandwidth
fast $01408000 readw 61.8 ns normal 32.4 * 10^6 byte/s
fast $01408000 readl 109.4 ns normal 36.6 * 10^6 byte/s
fast $01408000 readm 108.6 ns normal 36.8 * 10^6 byte/s
fast $01408000 writew 80.9 ns normal 24.7 * 10^6 byte/s
fast $01408000 writel 161.3 ns normal 24.8 * 10^6 byte/s
fast $01408000 writem 161.7 ns normal 24.7 * 10^6 byte/s
chip $00058000 readw 1006.1 ns normal 2.0 * 10^6 byte/s
chip $00058000 readl 1005.6 ns normal 4.0 * 10^6 byte/s
chip $00058000 readm 1005.6 ns normal 4.0 * 10^6 byte/s
chip $00058000 writew 613.0 ns normal 3.3 * 10^6 byte/s
chip $00058000 writel 613.3 ns normal 6.5 * 10^6 byte/s
chip $00058000 writem 613.6 ns normal 6.5 * 10^6 byte/s
@ 72MHz -- would not boot, may be a faulty/poorly seated oscillator
@ 73MHz
BusSpeedTest 0.19 (mlelstv) Buffer: 262144 Bytes, Alignment: 32768
========================================================================
memtype addr op cycle calib bandwidth
fast $01460000 readw 58.9 ns normal 33.9 * 10^6 byte/s
fast $01460000 readl 104.8 ns normal 38.2 * 10^6 byte/s
fast $01460000 readm 105.3 ns normal 38.0 * 10^6 byte/s
fast $01460000 writew 77.4 ns normal 25.8 * 10^6 byte/s
fast $01460000 writel 153.5 ns normal 26.1 * 10^6 byte/s
fast $01460000 writem 154.1 ns normal 26.0 * 10^6 byte/s
chip $00060000 readw 1003.3 ns normal 2.0 * 10^6 byte/s
chip $00060000 readl 1004.4 ns normal 4.0 * 10^6 byte/s
chip $00060000 readm 1005.8 ns normal 4.0 * 10^6 byte/s
chip $00060000 writew 613.6 ns normal 3.3 * 10^6 byte/s
chip $00060000 writel 615.1 ns normal 6.5 * 10^6 byte/s
chip $00060000 writem 612.9 ns normal 6.5 * 10^6 byte/s
@ 80MHz
BusSpeedTest 0.19 (mlelstv) Buffer: 262144 Bytes, Alignment: 32768
========================================================================
memtype addr op cycle calib bandwidth
fast $01458000 readw 53.7 ns normal 37.2 * 10^6 byte/s
fast $01458000 readl 95.5 ns normal 41.9 * 10^6 byte/s
fast $01458000 readm 95.6 ns normal 41.8 * 10^6 byte/s
fast $01458000 writew 70.5 ns normal 28.4 * 10^6 byte/s
fast $01458000 writel 140.9 ns normal 28.4 * 10^6 byte/s
fast $01458000 writem 141.1 ns normal 28.3 * 10^6 byte/s
chip $00060000 readw 968.1 ns normal 2.1 * 10^6 byte/s
chip $00060000 readl 970.0 ns normal 4.1 * 10^6 byte/s
chip $00060000 readm 970.3 ns normal 4.1 * 10^6 byte/s
chip $00060000 writew 613.1 ns normal 3.3 * 10^6 byte/s
chip $00060000 writel 614.0 ns normal 6.5 * 10^6 byte/s
chip $00060000 writem 614.1 ns normal 6.5 * 10^6 byte/s
Some PCMCIA tests (performed with nothing in the slot, after a reboot or after running "cardreset"):
@ 50MHz
BusSpeedTest 0.19 (mlelstv) Buffer: 262144 Bytes, Alignment: 32768
========================================================================
memtype addr op cycle calib bandwidth
user $00628000 readw 702.2 ns normal 2.8 * 10^6 byte/s
user $00628000 readl 1264.5 ns normal 3.2 * 10^6 byte/s
user $00628000 readm 1263.6 ns normal 3.2 * 10^6 byte/s
user $00628000 writew 702.2 ns normal 2.8 * 10^6 byte/s
user $00628000 writel 1263.9 ns normal 3.2 * 10^6 byte/s
user $00628000 writem 1262.8 ns normal 3.2 * 10^6 byte/s
@ 80MHz
BusSpeedTest 0.19 (mlelstv) Buffer: 262144 Bytes, Alignment: 32768
========================================================================
memtype addr op cycle calib bandwidth
user $00628000 readw 692.9 ns normal 2.9 * 10^6 byte/s
user $00628000 readl 1259.8 ns normal 3.2 * 10^6 byte/s
user $00628000 readm 1259.7 ns normal 3.2 * 10^6 byte/s
user $00628000 writew 692.8 ns normal 2.9 * 10^6 byte/s
user $00628000 writel 1259.6 ns normal 3.2 * 10^6 byte/s
user $00628000 writem 1259.5 ns normal 3.2 * 10^6 byte/s
When I have time again, I'll post similar results from an '030 card I have. IIRC the "chip" results are comparative (or better) due to faster bus access. I'd also like to try my unfixed C= 2B board (which seems to work with fine with this 1260 card), and check for any notable differences. If this CPU can be clocked further, I will post findings as soon as I acquire more oscillators.
I think it would be great to see some results from other hardware! Anything is welcome, though a 68060 equipped A4000 would be of particular interest to me. Screenmode alters the results somewhat... as do certain sw patches. ;-) Simply download the archive, make sure you're in 640x512x32 screenmode, and run bustest with "chip" and "fast" tags. ("rom" test is kind of worthless, since it is usually mirrored anyway.)
A few predictions:
Blizz 1260 cards (at least) will return better "fast" benchmarks at the same clock, since memory and CPU are synchronous. (My Apollo card runs at 1/2 divider to achieve <50MHz overclock.)
Some "big-box" accelerators take advantage of EDO, this would be a cool benchmark to compare.
A4000 machines will have generally faster chipmem access?
Maybe this particular benchmark is worthless??? Comments welcome.
-
Just for kicks, a few SysInfo results:
Disk read with an "IDE Fix Express":
50MHz: 3.38 MB/s
64MHz: 3.81 MB/s
70MHz: 4.13 MB/s
73MHz: 4.29 MB/s
80MHz: 4.39 MB/s
Mips @ 50 MHz 39.06, 62.42 @ 80MHz.
(I actually like SysSpeed best for more "in depth" CPU/disk benchmarks, but don't have it installed yet. Maybe I'll start another silly thread about it someday. :lol:)
-
I have a bunch of timing tests that Team Chaos ppl did for me years ago on various hardware. But they are all 640x512x256 colors.
-
A4000 w/CSMK3 68060/50MHz. I'll see if I can hook up the A1200 with Blizzard or my A3000 with CSMK2 68060/66MHz in a week or so.
BusSpeedTest 0.19 (mlelstv) Buffer: 262144 Bytes, Alignment: 32768
========================================================================
memtype addr op cycle calib bandwidth
fast $08718000 readw 64.2 ns normal 31.2 * 10^6 byte/s
fast $08718000 readl 107.8 ns normal 37.1 * 10^6 byte/s
fast $08718000 readm 108.9 ns normal 36.7 * 10^6 byte/s
fast $08718000 writew 72.3 ns normal 27.7 * 10^6 byte/s
fast $08718000 writel 144.9 ns normal 27.6 * 10^6 byte/s
fast $08718000 writem 150.2 ns normal 26.6 * 10^6 byte/s
chip $00130000 readw 1005.6 ns normal 2.0 * 10^6 byte/s
chip $00130000 readl 1006.3 ns normal 4.0 * 10^6 byte/s
chip $00130000 readm 1005.7 ns normal 4.0 * 10^6 byte/s
chip $00130000 writew 612.7 ns normal 3.3 * 10^6 byte/s
chip $00130000 writel 612.9 ns normal 6.5 * 10^6 byte/s
chip $00130000 writem 614.4 ns normal 6.5 * 10^6 byte/s
-
This is the output of BusSpeed on my A4000T with Apollo 4060 @ 100 MHz, I have a Picasso IV but set the screen to 640x512 32 colors for comparison with the other tests.
BusSpeedTest 0.19 (mlelstv) Buffer: 262144 Bytes, Alignment: 32768
========================================================================
memtype addr op cycle calib bandwidth
fast $08348000 readw 47.0 ns normal 42.5 * 10^6 byte/s
fast $08348000 readl 81.0 ns normal 49.4 * 10^6 byte/s
fast $08348000 readm 82.7 ns normal 48.4 * 10^6 byte/s
fast $08348000 writew 61.5 ns normal 32.5 * 10^6 byte/s
fast $08348000 writel 122.5 ns normal 32.7 * 10^6 byte/s
fast $08348000 writem 125.0 ns normal 32.0 * 10^6 byte/s
chip $00050000 readw 633.8 ns normal 3.2 * 10^6 byte/s
chip $00050000 readl 632.4 ns normal 6.3 * 10^6 byte/s
chip $00050000 readm 632.5 ns normal 6.3 * 10^6 byte/s
chip $00050000 writew 596.1 ns normal 3.4 * 10^6 byte/s
chip $00050000 writel 596.1 ns normal 6.7 * 10^6 byte/s
chip $00050000 writem 596.3 ns normal 6.7 * 10^6 byte/s
-
Thanks for the responses so far! Initially, I was attempting to discover why Starstruck ran with such jerky motion and relatively low framerate during its opening sequence (though every other demo runs just fine here), and figured it might be fun to compare benchmarks with other hardware configurations, looking for some kind of obvious disparity on my end.
A4000T with Apollo 4060 @ 100 MHz
:-o
Nice. Is it relatively stable at that speed?
-
-D- wrote:
Just for kicks, a few SysInfo results:
Disk read with an "IDE Fix Express":
50MHz: 3.38 MB/s
64MHz: 3.81 MB/s
70MHz: 4.13 MB/s
73MHz: 4.29 MB/s
80MHz: 4.39 MB/s
Mips @ 50 MHz 39.06, 62.42 @ 80MHz.
(I actually like SysSpeed best for more "in depth" CPU/disk benchmarks, but don't have it installed yet. Maybe I'll start another silly thread about it someday. :lol:)
WOOT! I just tried Piru's "SpeedyIDE" module with RemAPollo, and gained almost 1 MB/s increase in read speed, from 4.39 to 5.2 MB/s!
After the previous tweaking I expected maybe a small improvement (if it even worked at all with RemAPollo), but this certainly exceeded my expectations. Quite a huge increase (considering the hardware) if you ask me -- plus hit the theoretical maximum of the IDE-Fix Express with an 060, which is pretty sweet.
YOU ROCK PIRU! :pint:
-
SpeedyIDE was good up 'til OS 3.1 but it didn't work with OS 3.9 anymore. I think it has to do with the new scsi.device. Don't need it though, BlizzPPC scsi is faster anyway :-).
-
The framerate is not amazing in this demo on 060 amiga. The demo compo entry was made on winuae, and it is much faster. I doubt you can get similar speeds on a real amiga.
-
Bamiga2002 wrote:
SpeedyIDE was good up 'til OS 3.1 but it didn't work with OS 3.9 anymore. I think it has to do with the new scsi.device. Don't need it though, BlizzPPC scsi is faster anyway :-).
Interestingly, scsi.device from 3.9 slows things down quite a bit on my system, and idefix immediately kills device access. (Seems to be something with my CF cards.) I had been using scsi.device from 3.1 ROM, which worked great. I was pretty shocked to see such a large gain with SpeedyIDE, especially since the theoretical maximum of the IDE-Fix Express is said to only be reachable on certain 030 cards.
I agree Blizz SCSI is pretty cool, but all I need this thing for is demos and a little experimentation, so fast 68k is ideal for me.
Buzz wrote:
The framerate is not amazing in this demo on 060 amiga. The demo compo entry was made on winuae, and it is much faster. I doubt you can get similar speeds on a real amiga.
Yeah, I thought that might be the case. The same "jerkiness" and low framerate I'm seeing in the opening sequence is even slightly visible on a fast WinUAE machine, so must be the way it is. :shrug: I guess not everything can run like the second half of Hostyle Takeover. ;-)
-
-D- wrote:
:-o
Nice. Is it relatively stable at that speed?
Well, the system can work for hours before freezing, or it can work for few seconds... I wouldn't define it "stable" but I think it depends on the Apollo hardware being not so good... An idea I have is to build another voltage regulator using a single IC which delivers more current and has higher efficiency (the Apollo one is pretty much copied from a schematic on the 68060 User's Manual and it is rated for 3.3V @ 2 A, while @ 100 MHz the 68060 may need more current).