home *** CD-ROM | disk | FTP | other *** search
- > > I've tested it too, with a program called MEMSPEED.TTP. And in 640x480 2
- > > cols, it says 8 MB/s.
- >
- > > Does it manage to time FX-RAM (TT-RAM) as well? I think I have got the
- > > same program at home. I will try it and see what I get on the AB040.
- >
- > Memspeed works ok, but I'm just a little suspicious of it's testing methods.
-
- Heheeee... why must you guys always be so suspicious? :-)
-
- > I'll be writing a new low-level benchmark program for Nemesis soon, so this
- > should be a bit more accurate and take into account various types of ram
- > and their strengths/weaknesses. This of course will not invalidate GemBench,
- > which is useful for determining relative performance under GEM and real-world
- > effectiveness of accelerators.
-
- Cool. Maybe you could wrap them in a nice shell and include the DSP-bench
- program as well? On the other hand, it's rather pointless to have a nice frontend.
- :-)
-
- To get some more water on the wheel, I tested memspeed yesterday on my Afterburner040.
- It's faster than a standard falcon, but not as fast as GEM-Bench says.
- GEM-bench tells ~1100% faster than a regular falcon.
-
- With memspeed I get 4.9 MB/s to ST-RAM read and slightly less write.
- To TT-RAM I get 35.9 MB/s read and 16 MB/s write.
-
- One interresting thing is that when I run GEM-Bench and test the AB040 against
- the Medusa040 the AB040 is actually more than twice as fast at RAM-Access and
- also faster than MagiC Mac running on a 040 MAC. Not a big difference though.
- Against the Janus card, the PC is _much_ slower. Around the same speed as a
- standrad falcon.
-
- BTW. My program is called memspeed.tos, not ttp. :-)
-
- //Magnus Kollberg
-
-