Date: Wed, 14 Apr 2010 19:50:23 -0700 From: Garrett Cooper <yanefbsd@gmail.com> To: Maho NAKATA <chat95@mac.com> Cc: amvandemore@gmail.com, freebsd-stable@freebsd.org, alc@freebsd.org, alan.l.cox@gmail.com, avg@freebsd.org, als@modulus.org Subject: Re: HyperThreading makes worse to me (was Re: How to reproduce: Re: Only 70% of theoretical peak performance on FreeBSD 8/amd64, Corei7 920) Message-ID: <k2x7d6fde3d1004141950t81b4214awddea4563182526c5@mail.gmail.com> In-Reply-To: <n2i7d6fde3d1004141949z2689a81cwf8c48805ea09d68@mail.gmail.com> References: <20100414.082109.29593248145846106.chat95@mac.com> <4BC5DEB4.1090208@freebsd.org> <x2k6201873e1004140934z6f7518b9j72ffd9e1adc1ad49@mail.gmail.com> <20100415.094643.450985660335296086.chat95@mac.com> <n2i7d6fde3d1004141949z2689a81cwf8c48805ea09d68@mail.gmail.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On Wed, Apr 14, 2010 at 7:49 PM, Garrett Cooper <yanefbsd@gmail.com> wrote: > On Wed, Apr 14, 2010 at 5:46 PM, Maho NAKATA <chat95@mac.com> wrote: >> Hi Andry and Adam >> >> My test again. No desktop, etc. I just run dgemm. >> Contrary to Adam's result, Hyper Threading makes the performance worse. >> all tests are done on Core i7 920 @ 2.67GHz. (TurboBoost @2.8GHz) >> >> Turbo Boost off, Hyper threading off: 82% (35GFlops) =A0 =A0[1] >> Turbo Boost off, Hyper threading off: 72% (30.5GFlops) =A0[2] >> >> Turbo Boost on, =A0Hyper threading on: 71% (32GFlops) =A0 =A0[3] >> Turbo Boost off, Hyper threading off: 84-89% (38-40GFlops) [4] > > Doesn't this make sense? Hyperthreaded cores in Intel procs still > provide an incomplete set of registers as they're logical processors, > so I would expect for things to be slower if they're automatically run > on the SMT cores instead of the physical ones. > > Is there a weighting scheme to SCHED_ULE where logical processors > (like the SMT variety) get a lower score than real processors do, and > thus get scheduled for less intensive interrupting tasks, or maybe > just don't get scheduled in high use scenarios like it would if it was > a physical processor? Err... wait. Didn't see that the turbo boost results didn't scale linearly or align with one another until just a sec ago. Nevermind my previous comment. -Garrett
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?k2x7d6fde3d1004141950t81b4214awddea4563182526c5>