Continued work on my constant reuse optimizations. Not too much this
week though. I've now fixed some issues with the ARM size-costs code
that was causing it to wildly over-estimate the cost of a MOVT
instruction. I'll have to post this upstream sometime soon.
Took another look at the shift-amount bug. Discussed the issue with Paul
Brook. I've now fixed the original bug, and fixed the new bug introduced
by Paul's original fix, and committed that upstream. I still need to
backport it to Linaro GCC though, and the latent bug that Richard S
spotted is still being analysed.
Did a merge from FSF 4.5 & 4.6 to Linaro, and pushed them the Launchpad
branches for testing.
Begun work benchmarking different setups for the generic tuning patches.
I had a lot of trouble trying to set up SPEC2000 though. Hopefully these
issues are now resolved, with some help from Michael, and I have
established some baseline figures on both A8 and A9 to work from.
No progress on native tuning. I'm still waiting for upstream review.
In other news: Mentor's contract with Linaro has now been extended for
another 6 months. :)
_______________________________________________
linaro-toolchain mailing list
linaro-toolchain@lists.linaro.org
http://lists.linaro.org/mailman/listinfo/linaro-toolchain
