Hacker Read top | best | new | newcomments | leaders | about | bookmarklet login

I'm pretty sure they're suggesting doing it all in hardware, not more clever software


sort by: page size:

If someone asks for a software/OS recommendation, "get better hardware" is generally not the right advice.

You're right. I was thinking of it from the point of lowering it from a hypothetical hardware device to the manual process instead of raising it from the current system.

No, I'm arguing against a universality of such a claim. There is a performance/complexity threshold above which hardware or hybrid solution is a way easier than a purely software one.

It is not just silly, it's the most stupid suggestion of the year. If you are happy to use half-working, half-baked products, feel free. I will choose those, where software is finely tuned to the hardware and this combination makes pleasurable experience.

"If you are serious about software you should make your own hardware" © Alan Kay.


The point is so people don't have to do all that work. Why do in software what you can do in hardware?

I agree... what I think they meant to say is something along the lines of software defaults are already optimized to maximize and take advantage of the hardware's abilities so work is completed faster. The 'with the software baked in' should be changed to reflect the value proposition that Oxide is alluding to.

No, it's just complicated - easier to implement it on a reasonably general purpose core with firmware than to bet on getting it right first time in dedicated hardware.

I don’t think the author was meaning to cut out hardware all together, more that he is becoming hardware agnostic. Upgrading his hardware means nothing since he has virtualized everything and is probably pretty quick.

>If that was true then first party software would support it well

No no no no no. Hardware adoption has comes first, followed by the optimized software functionality.

Just look at SSD and TRIM.


Pro tip: avoid hardware, stick to software. Just kidding.

I think the lines between software and hardware-based are a little blurred these days with accelerator cards and whatnot. It's just a lot harder to come with the same level of guarantees when you're basically running a hypervisor on top of it.

What you describe sounds like a "throw a lot of hardware at it" approach. What often matters in the real world is how you integrate and use the hardware, not how powerful the hardware is.

That's too much effort, don't you think.Maybe not for you but for general tech folks.

This is also, what this article is actually about. It's just from a more "hermeneutic" perspective, rather than a bottom-up approach based on an analysis of the hardware.

How would you do it in hardware otherwise?

You're right in most cases, although it's doable on very old hardware. Depending on your use case that may be an acceptable tradeoff.

If the same machine can do it without hanging with better coded software, the hardware obviously isn't the problem.

From a hardware POV. In software, I agree. Should have been clear.

So here's how I summarise the whole essay: "Hardware is cheap. Instead of making your software perform well, why not just throw more hardware at the problem."

Well, I've tried this before and it didn't work.

next

Legal | privacy