Version française
Home     About     Download     Resources     Contact us    
Browse thread
Performance of threaded interpreter on hyper-threaded CPU
[ Home ] [ Index: by date | by threads ]
[ Search: ]

[ Message by date: previous | next ] [ Message in thread: previous | next ] [ Thread: previous | next ]
Date: -- (:)
From: Stefan Monnier <monnier@i...>
Subject: Re: Performance of threaded interpreter on hyper-threaded CPU
> | 3.0 GHz Pentium 4, hyper-threaded |   2.62 |     3.46 | 0.75723 |
> | dual 3.0 GHz Xeon, hyper-threaded |   3.36 |     2.59 |  1.2973 |

> | 3.0 GHz Pentium 4, hyper-threaded |   2.51 |     6.15 | 0.40813 |
> | dual 3.0 GHz Xeon, hyper-threaded |   3.32 |     3.58 | 0.92737 |

> | 3.0 GHz Pentium 4, hyper-threaded |   2.37 |     4.75 | 0.49895 |
> | dual 3.0 GHz Xeon, hyper-threaded |   3.91 |     3.56 |  1.0983 |

"Xeon" and "Pentium 4" are marketing names that refer to two different
packaging of basically the same set of processors (depending on whether
it's targetted at servers or at desktops/laptops).  Worse, the set of
processors covered by each name is actually pretty large with some
significant differences in their internal pipeline (some specifically
targetted at making hyperthreading suck less).

Have you tried to turn HT off and run your tests again?

What OS was used?  Were there other processes active at the same time?

Maybe people on comp.arch can slove this puzzle,


        Stefan