Wahoo: ↑
07.08.2024 17:37
Чет читаю я форум и недоумеваю.
Жрет меньше, стоит меньше. Плевать насколько, но всё-равно везде быстрее.
Казалось бы.
Не, облом, недовольны...
Там все прозаїчніше
https://chipsandcheese.com/2024/07/15/a ... en-at-amd/
George Cozma: Speaking of those, [Zen 5 is] now 6 ALUs why the move from 4 to 6? What was the reason for that?
Mike Clark: Yeah, as we think of Zen 5 we needed a new foundation for more compute to drive future workloads that continue to stay on this cadence of double digit IPC per generation. So you know we have been at the original Zen was 4-wide [dispatch and] 6 ALU’s and we had done a lot of innovation to really you know leverage all those resources [in] Zen, Zen 2, Zen 3, Zen 4. But we really we’re not to be able to keep that up, so we really needed to reset that foundation of a wider unit, more ALUs, more multiplies, more branch units, and then be able to leverage that like we did with the originals then to provide innovation going forward.
Another key point I’d like to hit on is it’s also hard for software trying to leverage, let’s say something that has 6 ALUs and 8-wide dispatch, they don’t get the payback when they run it on our older architecture. So even if they’re you know trying to tune their code and building smarter algorithms, there’s no payback for them so they don’t end up doing it. Whereas now that we’ve built it, they’ll start innovating on the software side with it [and they’ll go], “Holy cow look what I can do, I’ll do this, and I can do that” and you’ll see the actual foundational lift play out in the future on Zen 6 even though it was really Zen 5 that set the table for that and let software innovate.
Грубо говорячи в них є ідеї розвитку зену, і зен 5 це нові перша іттерація рішеннь які будуть вилизувати в майбутньому... Хоча в цілому +60% PTW/W на рівному місці це бомба, так як в нас є немошні ноутбуки і компактні ПК які від зменшення жору тільки будуть раді
![rotate :rotate:](./images/smilies/rotate.gif)