On 17 September 2012 14:56, Richard Earnshaw <rearn...@arm.com> wrote: > On 05/09/12 23:14, Christophe Lyon wrote: >> Hello, >> >> Although the recent optimization I have committed to use Neon vext >> instruction for suitable builtin_shuffle calls does not support >> big-endian yet, I have written a patch to the existing testcases such >> they now support big-endian mode. >> >> I think it's worth improving these tests since writing the right masks >> for big-endian (such that the program computes the same results as in >> little-endian) is not always straightforward. >> >> In particular: >> * I have added some comments in a few tests were it took me a while to >> find the right mask. >> * In the case of the test which is executed, I had to force the >> noinline attribute on the helper functions, otherwise the computed >> results are wrong in big-endian. It is probably an overkill workaround >> but it works :-) >> I am going to file a bugzilla for this problem. >> >> I have checked that replacing calls to builtin_shuffle by the expected >> Neon vext variant produces the expected results in big-endian mode, >> and I arranged the big-endian masks to get the same results. >> >> Christophe.= >> >> >> neon-vext-big-endian-tests.patch >> >> >> N ¬n‡r¥ªíÂ)emçhÂyhi× ¢w^™©Ý >> > > > I'm not sure about this. Looking at the documentation in the manual for > builtin_suffle makes no mention of the results/behaviour being endian > dependent, which makes me wonder why this test needs to be. > > R.
Indeed, but I had to modify the mask value in order to get the same results in big and little-endian. If the mask should be the same (it would be much more confortable for the developers indeed), then GCC needs to be changed/fixed. Christophe.
