ia64: Don't use static branch prediction

Chris G. Demetriou cgd@sibyte.com
Sat Oct 28 09:54:00 GMT 2000


bernds@redhat.co.uk (Bernd Schmidt) writes:
>  	    /* Guess top and bottom 10% statically predicted.  */

does this comment deserve updating?  (I'd guess so.)


> -	    else if (pred_val < REG_BR_PROB_BASE * 9 / 10)
> +	    else if (pred_val < REG_BR_PROB_BASE / 100 * 98)

in practice, the ordering here is OK because of the (large-ish) value
of REG_BR_PROB_BASE...  but why switch it around?



cgd


More information about the Gcc-patches mailing list