PCTuning fórum

Part of the problem lies with Windows 7. I've heard rumors Microsoft pretty much told AMD "we won't spend resources to fix it in W7". The scheduler is working as intended with Windows 8, but not with Windows 7 or earlier. Final BIOS is out.

THANATOS píše:Youki tie vysledky su na BD :wink

richie08 ja som o HT nic nehovoril vlastne som ani slovko nepovedal
Podla mna to bude ako hovoris, najnarocnejsiemu vlaknu pridelia jeden modul a ten bude spracovavat len jedno vlakno a nebude nic zdielat.

HT je podla mna osetrene uz vo Windows 7, ved Nehalem sa objavil skoro rok pred uvedenim W7, cize nehrozi situacia, ked windows prideli 4 vlakna a rozdeli ich medzi 2 jadra+HT namiesto toho aby vyuzil zvysne 2, navyse HT vyuziva len volne prostriedky, cize len to druhe vlakno by bolo degradovane nedostatkom volnych prostriedkov ale prve by nemalo.

THANATOS píše:HT je podla mna osetrene uz vo Windows 7, ved Nehalem sa objavil skoro rok pred uvedenim W7, cize nehrozi situacia, ked windows prideli 4 vlakna a rozdeli ich medzi 2 jadra+HT namiesto toho aby vyuzil zvysne 2, navyse HT vyuziva len volne prostriedky, cize len to druhe vlakno by bolo degradovane nedostatkom volnych prostriedkov ale prve by nemalo.

Microsoft's forthcoming Windows 7 operating system offers improved support for hyper-threading, according to a company official. "The work that we've done in Windows 7 in the scheduler and the core of the system to take full advantage of those capabilities, ultimately we think we can deliver a great and better experience for you," said Veghte, speaking earlier this week at Microsoft's TechEd conference in Los Angeles.

"Working with Intel, Microsoft implemented a new feature called SMT parking, which provided additional support for the Windows 7 scheduler for Intel Hyper-threading Technology, enabling better performance on hyper-threaded, multi-core Intel processors. This will help users get the maximum benefit from multi-tasking."

The basic notion behind SMT parking is that the Windows scheduler will attempt to schedule threads so that all physical cores are occupied before any core gets two threads scheduled on its two front-ends (or logical cores). Since Hyper-Threading involves some cache partitioning and other forms of resource sharing, this is a potentially important feature. We've seen scheduler quirks cause poor and oddly unpredictable performance on Core i7 processors in the past. Based on our limited experience testing with Windows 7 and a cadre of SMT-enabled processors for this review, our initial impressions of SMT parking are positive. We've seen performance results for executables that rely on the Windows scheduler for thread allocation that match the performance of executables with explicit, SMT-aware thread affinity built in. Our initial sense is that SMT parking blunts some potential disadvantages of Hyper-Threading, making it more of an unqualified win, even on the desktop.

maltra píše:@flanker: no az taky lol by to nebol , uz mam cakania celkom dost, tak snad to naozaj bude ten buduci tyzden. V tom grafe co si postol niekto prehodil FX s 2600K a tazko je povedat ktory slajd je pravdivy, ci ten povodny alebo tento novsi. Zase sa len niekto nudil vo PhotoShope.