I hope someone can do the math and tell me how much more power it required to sort the 11 items in that list? how much more instruction (CPU/GPU) it required?

How much it will require if the list had 100 or 1000 items?

Thanks,

Comments URL: https://news.ycombinator.com/item?id=46900066

Points: 2

# Comments: 0

And I think Solzhenitsyn is wrong. There are psychopathic people that have no good in their hearts. Sure, with the right upbringing that could be kind and good but at a given moment they are what they are... psychopaths.

It seems obvious to me that AWS using their market dominance to shift workloads to Graviton.

I love it so much, it has a great balance between: readability, fast write/compile/debug cycle and great performance.

On tip: LLM is God send for it. So many times I find what I was looking for written in some other language and the LLM does the conversion.

How would you feel? Insulted?

My understanding that it is a standard feature, this is how earthquake warning works in Japan.

Point being there is no "hacking" involved. Standard feature

It amazes me how the legend of ARM being more efficient than x86 took hold. I'm not saying that we don't have a more efficient ARM processors BUT it has nothing to do with the ISA. What you gain with a simple encoder (ARM) you gain with code density (x86) and after that it is converted to microcode. You wouldn't gain more than single percent if any.

Process node is by far more important (5nm , 3nm, etc) and usually Apple gets access to them first. Also placing the memory in the CPU package also proved to be great for efficiency (case of point is Intel's Lunar lake that can last like forever) and last but the least is the intergraded GPU that no one seems to talk about and their respective efficiency (cause there are like 30 people in the whole world that can truly make and educated talk about them and their ISA)