From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Luck, Tony" Date: Tue, 31 Jan 2006 18:08:57 +0000 Subject: Re: [patch 5/5] fix sn rw_mmr.h to use intrinsic Message-Id: <20060131180857.GA8442@agluck-lia64.sc.intel.com> List-Id: References: <200601270137.k0R1big21236@unix-os.sc.intel.com> In-Reply-To: <200601270137.k0R1big21236@unix-os.sc.intel.com> MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit To: linux-ia64@vger.kernel.org On Tue, Jan 31, 2006 at 11:19:35AM +0000, Christoph Hellwig wrote: > Agreed. Obsfucating for a propritary and pretty much irrelevant (for the > kernel) compiler is a horrible thing to do. And the only reason we do that > at all is that the compiler is from the same company that's behind ia64. > Please fix up your damn compiler. Even SGI managed to add proper inline > as?embly support to Pro64, and they had much less ressources. How about we un-obfuscate the code by moving these three functions to a ".S" file? They are reading from uncached physical memory, and are packed full of "srlz.i" and ".acq"/".rel" options, so it doesn't appear that moving them from inline to a full procedure call would make any measurable difference to performance (at least not for any macrobenchmark). pio_phys_read_mmr() isn't even used anyplace, so we could further clarify the code by dropping it altogether. -Tony