A500 cp2 need help

[sandruzzo]

I need to perform nibble rotation as fast as is possible. Can someone help me?

from:

a-b-c-d
e-f-g-h
i-l-m-n
o-p-q-r

to

a-e-i-o
b-f-l-p
c-g-m-q
d-h-n-r

is it possible to do it faster than 68000 with blitter?

Thanks to all

[Samurai_Crow]

Don't we all wish that chunky to planar conversions were blitter accelerated? If it were possible, interleaved bitplanes would be interchangeable with chunky modes quite quickly! Isn't that what you're trying to do?

Edit: I see it is just a typo in the title of your post. That is why I ask.

[sandruzzo]

Originally Posted by Samurai_Crow

Don't we all wish that chunky to planar conversions were blitter accelerated? If it were possible, interleaved bitplanes would be interchangeable with chunky modes quite quickly! Isn't that what you're trying to do?

Edit: I see it is just a typo in the title of your post. That is why I ask.

I don't need to perform full cp2, but exchange only nibbles

[britelite]

Originally Posted by sandruzzo

is it possible to do it faster than 68000 with blitter?

It's faster with the blitter than with the cpu, for example my OCS c2p is blitter only. You might need to have a scrambled chunky buffer for optimal performance though.

Taking a look at Kalms' cpu+blitter c2p's might be a good place for you to start.

[sandruzzo]

Originally Posted by britelite

It's faster with the blitter than with the cpu, for example my OCS c2p is blitter only. You might need to have a scrambled chunky buffer for optimal performance though.

Taking a look at Kalms' cpu+blitter c2p's might be a good place for you to start.

Thanks. I need only to exchange nibbles, not full c2p: Any helps?

[britelite]

Originally Posted by sandruzzo

Thanks. I need only to exchange nibbles, not full c2p: Any helps?

You could post here how you're currently doing it, and I'll be happy to give some pointers on how to improve it.

[sandruzzo]

Originally Posted by britelite

You could post here how you're currently doing it, and I'll be happy to give some pointers on how to improve it.

Thanks for your help. I would like to have a good help from you and others, instead doing it again. I need this operation just cos want to test a possible way to do cp2, not for fast reasons, just to test...

[chb]

Originally Posted by sandruzzo

I need to perform nibble rotation as fast as is possible. Can someone help me?

from:

a-b-c-d
e-f-g-h
i-l-m-n
o-p-q-r

to

a-e-i-o
b-f-l-p
c-g-m-q
d-h-n-r

is it possible to do it faster than 68000 with blitter?

You can use blitter merge (two blits with shift by 8 left resp. right for one source, mask 0xFF00 and 0x00FF) to get the following intermediate matrix:

a-b-i-l
e-f-o-p
c-d-m-n
g-h-q-r

then shift by 4 left / right, mask 0xF0F0/0x0F0F to get your result. So just the first passes of ordinary blitter c2p. Don't know if it is faster than with the CPU, but I'd think so.