Date: Fri, 10 Oct 2003 00:57:14 -0700 From: Tim Kientzle <kientzle@acm.org> To: Terry Lambert <tlambert2@mindspring.com> Cc: freebsd-hackers@freebsd.org Subject: Re: Dynamic reads without locking. Message-ID: <3F86665A.8050209@acm.org> In-Reply-To: <3F8527E1.26ED0CF6@mindspring.com> References: <20031008083059.GA520@garage.freebsd.pl> <20031008114506.I63940@beagle.fokus.fraunhofer.de> <3F8527E1.26ED0CF6@mindspring.com>
next in thread | previous in thread | raw e-mail | index | archive | help
Terry Lambert wrote: > For certain uses, however, it's safe to not lock before the > read *on Intel architectures*. This can go out the window on > SPARC or PPC, or any architecture where there is no guarantee > that there won't be speculative execution or out-of-order > execution without explicit synchronization. Even on Intel architectures, the compiler can and will reorder operations. Hardware-level issues are only a part of the story. I followed the Java Memory Model mailing lists for a while. A lot of very bright, very experienced people thought they had found ways to avoid locking and were wrong. This stuff is hard. Do NOT underestimate it. Tim
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?3F86665A.8050209>