PCI IDE controller on Mediator?

[motorollin]

1. Is it possible?
2. Would it offer a speed improvement over the built in IDE controller of the A1200?
3. Could you boot from it?

Cheers

--
moto

[mboehmer_e3b]

Hi,

ad 1): plugging in, yes. No drivers available though.

ad 2): depends on the driver. It won't reduce CPU load significantly, as one still has to copy all data from/to the GFX card mem to Amiga side by CPU.

ad 3) no. PCI is not active at boot time. You must have some (Flash)ROM and drivers suitable to work at boot time (i.e. no ENV: variables, ...)

Michael

[motorollin]

mboehmer_e3b wrote:
Hi,

ad 1): plugging in, yes. No drivers available though.

Shame :-(

mboehmer_e3b wrote:
ad 3) no. PCI is not active at boot time. You must have some (Flash)ROM and drivers suitable to work at boot time (i.e. no ENV: variables, ...)

I see. In that case, if drivers were available and it was worth doing, then I would probably put a compact flash card on the Amiga's internal IDE controller to load the drivers, then boot from the PCI controller.

Shame there are not more drivers available for the Mediator :-(


--
moto

[x56h34]

Elbox's Eflash product would come in handy (at least for A3000/A4000 owners) in order to pre-load all mediator drivers at boot and allow you to practically autoboot from the PCI IDE controller, however it doesn't look like Elbox will make use of this idea as it's been quite a while since Eflash was released and no new, or should I say useful stuff has come out for it.

[motorollin]

I've just looked at the eflash, and to be honest, I don't see the point. What's wrong with having a small hard disk on the internal IDE channel, or a compact flash -> ide converter, and booting from that with your 3.9 setpatch, Mediator drivers, etc etc?

--
moto

[doctorq]

Ehh, reduced boot time, needed modules available at power up and no need for extra devices. That would be the main point I think.

Btw, nothing wrong in having a device attached to the internal IDE controller; using a flash card would just make a more elegant solution.

[Karlos]

mboehmer_e3b wrote:


ad 2): depends on the driver. It won't reduce CPU load significantly, as one still has to copy all data from/to the GFX card mem to Amiga side by CPU.

That sounds a performance killer. I have yet to see any Voodoo card on any mediator score more than 5MB/s for VRAM -> RAM copy. Without making the area cacheable reading from vram is painful on pretty much all cards, mediator or otherwise.

I'm sure someone we all know and love will dive in soon and point out that on the A4K, a PCI IDE controller would just be able to DMA straight into the motherboard memory.... ;-)

[x56h34]

He will most likely blame it on the poorly written benchmarking software. ;-) :-P

[Karlos]

x56h34 wrote:
He will most likely blame it on the poorly written benchmarking software. ;-) :-P

Exactly. As we all know, it is fundamentally flawed of me to use the CPU to read longwords or move16's in a hand written, icache friendly asm loop to benchmark this, when used inside a locked environment, accumulatively timed and pre calibrated using something as terribly innacurate as the EClock over a several second duration...

The card it self will do it all 10x faster over the exact same bus using Direct Magic Access