Archives Discussions

[chrisjp]

Hey all,

We are developing a integer-heavy kernel which relies on multiplication quite heavily.

We currently allow for carries, etc, using a 28-bit wide integer inside of the 32-bit registers.  Looking to the 58XX series, our question is if it is possible to use the 24-bit multiplications available in the cores.  I'm happy to "post-process" the 32-bit multiplication calls to 24-bit equivalents.

Is the 5870 assembly produced by stream kernel analyzer the same version run by a kernel execution?

Any other suggestions?

[hazeman]

24-bit multiplication isn't available in IL. So atm there is no possibility to access those operations.

[chrisjp]

Ah, thank you very much, I assumed mul_uint24 from the evergreen doc was exposed in IL.

Sigh   That'd be a great feature!