HNHacker News
TopNewBestAskShowJobs

hydroreadsstuff

235 karma · joined October 9, 2018

submissionscomments
hydroreadsstuff··on Avoiding Instruction Cache Misses
https://images.anandtech.com/doci/13699/Ronak26.jpg

https://www.anandtech.com/show/13699/intel-architecture-day-...

I believe this shows differences between FP and Integer units. In order to achieve a certain performance goal you don't necessarily need another integer divider when you want a new adder/multiplier. So you add a slimmer unit instead.

I listed this in my original comment, because this is a giant can of worms for the compiler and decision-maker on where to execute what.

hydroreadsstuff··on Avoiding Instruction Cache Misses
The complexity of current hardware is madness.

The performance of software is influenced by the workings of tens of units (+local caches) connected (non-linearly) with fifos, ooo buffers, replay mechanism. There are multiple versions of the same unit to save chip space (like light and heavy Integer/FP). Units/domains have different clock speeds. And from generation to generation port connections and instructions between pipelines can be reshuffled.

I suppose what keeps performance changes relatively straightforward for developers is the set of benchmarks used to evaluate the hardware early on.

I appreciate the article focusing on the I-Cache, and the nice intro to decoding.

I would have preferred having an example, and improving something instead of abstractly talking about problems, effects of code and optimizations and possible workarounds.

Tangent: I wonder if we will be seeing specialized instructions sometime that span multiple units and multiple cores in order to reduce data-movement. Think matrix-matrix multiplication. The potential improvements for power and speed seem huge.

hydroreadsstuff··on How to architect a Qt/C++ Application
How can I follow this blog? I don't see RSS. Feedly doesn't know it. And there seems to be no email option either.

How do you follow blogs in general these days. My twitter is too full of things, so I'd probably miss the posts sometimes.

hydroreadsstuff··on Google's interview system: it's not about solving the problem
I've interviewed three times in the last five or so years there, and I don't get the feeling the depth is as claimed in the article. Perhaps, it's also the interviewers not implementing it as intended.

If these points were indeed important, I'd expect feedback addressing them. All feedback I received was about doing well or not well on certain questions. No meta whatsoever.

I didn't make it for good reasons, but I feel there is a big chance part. I had one onsite interviewer in the first round who was difficult to deal with. He presented a problem I've never seen in my life, nothing close. He interrupted and gave hints in directions that didn't make sense to me, and didn't give me 5 minutes to think without him talking. The second attempt was fair. In the third, the first phone screen's interviewer was constantly typing on his keyboard while I talked, and it was so loud. No real conversation happening. He was just staring in his screen clacking away. I addressed it, but he kept typing loudly while I was talking. So annoying.

On the other hand, the recruiters were always very good.

At another company recruiting was a mess, and only knowing someone inside helped dealing with that, but the interviews were all great.

hydroreadsstuff··on Tesla Third Quarter 2018 Update [pdf]
The revenue for one quarter seems high. Did they carry over some sales from the past or is there something it drawing from future quarters?

Edit: Congratz!

← PreviousPage 3 of 3