User Profile

[coder]

I thought I read it came from Google. Anyway, it's what they use in their TPU2's.

I'm skeptical it's really any faster than half-precision...

[coder]

Lol. Show me a consumer with all in-order cores who feels like they've "won". You're still spinning, which was my core complaint.
...

[coder]

Sure, but foregoing OoO isn't the only way to mitigate against them.

IMO, the obvious reason it's in-order is that it wasn't feasible for...

[coder]

This is called spinning a weakness into a strength.

A better way to mitigate against side-channel attacks is to make a fast out-of-order...

[coder]

You forget about:

https://www.nvidia.com/en-us/design-...zation/quadro/

Many of their visualization users are Linux-based....

[coder]

Well, the reviewers can see which are the better quality patch authors. Perhaps they can promote some of them to be additional reviewers. I feel like...

[coder]

That's pretty sad, really, when the best a site like Newegg can do is tell you to get on Twitter.

Newegg should suspend order placement to...

[coder]

It's not likely to see the memory consistency model of a given ISA change within its lifetime. That's the sort of thing which can seriously break backward...

[coder]

Then here's a request: please don't try to school me on CPU architectures....

[coder]

Protip: try reading the article we're talking about. You might not waste time making irrelevant comments.


Now, does that not sound...

[coder]

Very cool. This might be something towards what I was talking about - reducing dependence on speculative execution and perhaps even the cache hierarchy....

[coder]

Yeah, it's silly to think that ISA design is at a dead end. With process-lead performance improvements hitting a wall, there's too much to be gained by...

[coder]

I see value in it, but then there's value in Windows and a lot of sub-optimal things that people use.

The biggest problem is the way it's...

[coder]

Octave == MATLAB (i.e. #11, up from #13 last year)....

[coder]

I'll repeat: "most people seriously involved in Linux cannot completely avoid them."

If I try to find a Linux job where I don't...

[coder]

Okay, so everyone should just stop what they're doing and flush their current non-RISC V developments down the toilet, even if it's viable and suits its...

[coder]

When they started C-SKY, RISC-V certainly didn't have the same traction as now. As for ARM, don't forget that every ARM core costs royalties.
...

[coder]

Ah, but when budget and sales pressures trickle down from above, that will be the real test.

They will also be pressured to prioritize IBM's...

[coder]

Yes and no. While I'm not in favor of killing them, I do see the complaints as somewhat legit, considering how dominant they are in the Linux ecosystem....

[coder]

IBM has been having trouble re-inventing itself and investors are losing patience.

Worst case scenario is that Red Hat could get dragged...