Comment by camel-cdr
1 month ago
> The Tenstorrent Ascalon is supposed to be as fast as AMD Ryzen 5
Don't set your self up for dissapointment. Ascalon is supposed to match Zen5 performance per clock, but at 2.5GHz, so will still be at a minimum 2x slower.
Additionally, the announces Ascalon devboard is supposed to be on an older node and have an ever lower frequency due to that. (the 2.5GHz were on SF4X, the devboard may be on something like 12nm)
You are right to be cautious.
Ryzen 5 is not Zen 5. So I am not predicting Zen 5 level performance for Ascalon.
I am expecting Zen 3 level performance which is to say about as fast as laptops from 2017 to 2020 or so. That is better than what I am typing on now.
So, not crushing Apple Silicon just yet but "usable" for the first time. Instead of "there are no RISC-V chips as fast as a Raspberry Pi", it will be "Intel is still faster". It may not even be that ARM is faster anymore. It will be more of a chip by chip comparison. At least people will have to admit that it is a race.
I am not looking for RISC-V to be "best in the world" in 2026. Rather, I want to stop hearing that it will never get there. After Ascalon, you will not be able to make the blanket statement that RISC-V is not good enough. It will be good enough in some markets and not in others. It will have a seat at the table.
And I want to be able to use RISC-V. Ascalon bring RISC-V into "good enough for me" territory.
And RISC-V will only get better. It is getting better faster than other chips are. My thesis is that this will continue (though that is certainly a bold prediction).
Even just looking at Tenstorrent, Babylon is not far behind Ascalon. And there is SciFive. And there is Andes. And there is SpaceMIT. And there is Alibaba. And there is Qualcomm. And there are companies I do not know about yet. And there are nation-states. There is a pretty big tidal wave headed for ARM (and maybe even AMD/Intel).
First they laugh at you. And then you win.