Odpověď na názor

Jak je videt, tonouci se stebla chyta :D

Chci rozporovat vyssi IPC. Je krasny, jak jsi zapomnel zminit podstatny veci z toho Anandtechu:

"Moving on to the 2017 suite, we have to clarify that we’re using the Rate benchmark variations. The 2017 suite’s speed and rate benchmarks differ from each other in terms of workloads. The speed tests were designed for single-threaded testing and have large memory demands of up to 11GB, while the rate tests were meant for multi-process tests. We’re using the rate variations of the benchmarks because we don’t see any large differentiation between the two variations in terms of their characterisation and thus the performance scaling between the both should be extremely similar."

"Unfortunately I’m not quite as familiar with the exact characteristics of these tests as I am with the 2006 suite, so a more detailed analysis should follow in the next few months as we delve deeper into microarchitectural counters." :D

Vzhledem k temhle faktum a tomu miniaturnimu rozdilu se da tezko mluvit o nejakym vitezstvi :D

A co se tyce efektivity - Techspot? Jeden z nejvic AMD-biased webu? (kdyz nepocitame to cesky trio tady) Prekvapi vubec nekoho, ze si na ten test vybrali Blender s jeho pristupem k pameti? Hmm, co takhle Cinebench (kterej je u AMD fans tak oblibenej, protoze ma taky dost AMD bias)?

Multi-threaded efektivita:
10.2kJ vs 10.8kJ coz je opet v ramci chyby mereni, navic v testu, kterej favorizuje AMD a jeste podle vseho AMD rozeslalo vzorky, ktery boostujou vic nez realny kusy:
https://tpucdn.com/review/amd-ryzen-9-3900x/images/efficiency-multithread.png


Ale co takhle single-threaded spotreba? Intel 12.1kJ, AMD 21.9kJ coz je skoro dvakrat lepsi efektivita pro Intel.
https://tpucdn.com/review/amd-ryzen-9-3900x/images/efficiency-singlethread.png

https://www.techpowerup.com/review/amd-ryzen-9-3900x/18.html


Podtzeno secteno, kdyz se jedna o maximalni zatez vsech jader na dlouhou dobu a to jeste v AMD-biased testu, tak se AMD na Intel dotahne. Diky masivne lepsi efektivite jednovlaknovy zateze ale bude jakejkoliv mensi workload znamenat stale vetsi a vetsi vitezstvi pro Intel - cim mensi zatez, tim lepsi vysledek a vetsi rozdil.

A to jeste nezapominat na to, ze Ryzeny se prakticky nedaji taktovat:
"Overclocking the Ryzen 9 3900X proved difficult because its heat output is so high. Even with a 240 mm all-in-one water cooler, we couldn't even get close to what it can do. We had to lower our voltage over and over again to keep it from overheating when fully loaded on all cores. In the end, our maximum overclock of 4 GHz is disappointing compared to what (low-threaded) boosts we would see from even the stock processor."

Zato i9-9900K/KF taktujou uplne paradne. Takze pro dobrym vzduchovym nebo vodnim chlazenim je u Intelu jeste docela slusnej bonus navrch ;)

Ryzen 3900x - zakladni takt 3.8GHz, max. OC na vsech jadrech 4.0GHz
https://www.techpowerup.com/review/amd-ryzen-9-3900x/21.html


Intel i9-9900K - zakladni takt 3.6GHz, max. OC na vsech jadrech na vzduchu 5.0GHz, na vode 5.1GHz
https://www.techpowerup.com/review/intel-core-i9-9900k/18.html


Ryzen? Diky ne ;)