Search results

Hiya, I wrote a short tutorial on how to get the best float point performance from the ARM Cortex A8: http://www.pandorawiki.org/Floating_Point_Optimization It's targetting GCC (I used CodeSourcery 2007q3) and i tried to make it understandable to most C programmers. I'll probably add to it as...

Its definitely not hugely faster than a P3, clock for clock, but i wouldn't go that far. The NEON unit is probably better than the MMX + SSE in P3. The main thing x86 has over it is out-of-order execution and 10-stage vs 13-stage. The omap3 has a better memory configuration and the nbench result...

maciek_urbanski was reverse engineering the SGX, but i highly doubt we'll get an OpenGL 2.0 driver. Maybe a low level API, but not a driver. Even if maciek does manage to fully document the SGX, writing a decently performing compliant OpenGL 2.0 driver is a huge amount of work, and your unlikely...

Also, I'm pretty sure the 1Ghz chips are with a different manufacturing process. Heat is rarely a problem with ARM devices. Its more likely clock skew / timing delays causing components to get out of sync.

Game Maker is not supported on GP2X (or Linux), and will likely never be. It is commercial and closed source. Your probably thinking of something else.

Yeah, thats what i was thinking. ssvb on the beagleboard irc kindly tested it for me. Heres the results: http://pastebin.ca/1495517 Basically it confirms what i thought. The VMOV instruction produces a stall, while the VSTR / LDR pair is worse when they occur directly after one another but...

Ahhh Ye olde grill Laurent for answers game. :) Just posting to say i've entered this library in the Beagleboard sponsored projects scheme. If they're interested they'll send me a beagleboard, which will be highly useful considering my Pandora looks to be ~3 month away (I'm near the end of the...

Yea i know, my comment wasn't directed at anyone in particular. I'm basically using this thread to document what i learn as a go. One question that is crucial to how i implement my functions, is what's an acceptable accuracy? 0.5% ? Not sure if this is of any interest but I'll document some of...

To clarify, The Devs I'm referring to are paying customers. I don't expect anyone, beyond the most core developers (which already have hardware), to get them for free (at this stage). I would suspect most of that will not come into circulation until a later date, once some major projects have...

....

....

The major point, that many seem to be missing, for sending out to developers first is that it improves the relationship between the developers and the OpenPandora project as a whole. Its a gesture of good will. Even if they don't achieve a lot in first few weeks, it will set a precedent that may...

Yea good point, to make it easy for the developer i will write drop in replacements for cmath.... but i'll add additional functions suited to the NEON. Presumably vector versions of the base functions would be a good optimisation, like a sinfv_neon(float *x, int n) that's unrolled to calculate...

The memory subsystem of the Wiz is most likely the bottleneck. The Wiz has the same cache sizes and effectively the same RAM bandwidth as the GP2X (which is already fairly memory constrained). Your also forgetting that the GP2X has two 200mhz CPUs, although i don't think those emulators utilized...

Woops sorry about that, i was thinking there was a pairwise multiply.... but there's only a pairwise add. Clearly the VFP could do it but that would be slow. BTW i think there is a slight error in your code, The 2nd last line should read: VMLA.F32 D0, D2, D1. It appears the range reduction and...

Maybe their posting from a rocket traveling near the speed of light, an "hour" may not have passed in their frame of reference. :)

QUOTE well at least, I agree with you if you're saying the posted algorithm may not be optimal for NEON. Yea thats because in that code i'm using the Horner method to evaluate the polynomial which doesn't vectorise very well, the alternative is Estrins method: z = ax * ax; a = __sinf_lut[3] +...

Hmm had a quick look in glibc and most the math functions call another function like: __ieee754_sinh(x).... i haven't been able to locate the c files for these functions. Anyway i wrote a sinf algorithm: CODE const float __sinf_range = M_PI / 2.0; const float __sinf_invrange = 2.0 / M_PI...

I'm off uni for a few weeks, so i thought i might look into beginning the development of a math library similar to the standard c library utilising the NEON coprocessor. Anyway heres some questions / thoughts: 1. Has anyone done anything similar for NEON and are willing to share? 2. Is it...

Chads back. :wacko: Solution: iPhone / Pre are not "Handhelds".