Libjava failures status

Thu Mar 7 09:26:00 GMT 2002

Jan Hubicka wrote:
>> Hi,
> The yesterday libjava failures are caused by my sanity checking I added
> to verify_flow_info. I must say I don't understand how the patch has regtested
> for me before I commited it, perhaps I disabled checking :(
> I've fixed all the failures that happends on i386/PPC compilation today,
> all of them latent bugs.

I haven't had a chance to dig through all the 39 cross builds I
ran overnight for failures, but the mcore-elf and sh-* failed 
building newlib's strftime.c with an ICE in verify_local_live_at_start 
at flow.c:591. Is this somehow related?
> So i386 should compile fine now, PPC requires my last patch to gcc-patches I
> don't feel certain about to commit as obvious. I will read my email tomorrow
> evening, but not earlier, so in case you run into some problems, just disable
> the sanity check aborting. In case you want to debug the problem usually
> it is enought to breakpoint on "error" see what instruction got after the
> one with REG_EH_REGION and avoid that.
>> I apologize for so many failures.
>> In hope the java EH will now be considerably more reliable at least,
> Honza

-- 
Joel Sherrill, Ph.D. Director of Research & Development
joel@OARcorp.com On-Line Applications Research
Ask me about RTEMS: a free RTOS Huntsville AL 35805
Support Available (256) 722-9985