andreer

Using the Adafruit breakout board, I had no problems other than an SPI bug in the Arduino core. Be warned that they are fragile when not protected, I sheared off the flex cable on one which was not fun.

Official refresh rate is ~25 hz, unofficially they seem to be able to go a lot faster (2-3X) if you don't mind increasing power consumption. And it's faster if you update only some lines. But by then you have run into a limitation in how fast the liquid crystal can respond.

Yeah that would be another few orders of magnitude smaller power budget. But I love the idea.

My project so AMA (although this doesn't seem to be blowing up here on HN :-)

IPC is still improving, so single thread performance is still increasing, even if clock speeds are not (at least not at the same as before). And new instructions (AVX ect) also help, especially if you can optimize and recompile your code.

It's at least enough that we have to take it into account:

We run our workloads across multiple Intel cpu generations and to be able to optimize utilization we have a "speedup factor" which is currently up to 1.7 for the latest generation we've tuned it for. And the base 1.0 performance is from Ivy Bridge, launched 2013.

There's much in this thread about the helmet absorbing the energy of the impact, but that's far from the whole benefit of wearing one.

The helmet, by conforming to the shape of your head, distributes the energy from the point of impact to a much larger area. So instead of having your head cracked open at the point it hits the tarmac, or pierced by a pointy rock, the force will be evenly distributed across your head.

The helmet also has a low-friction shell that will slide across a surface, which helps avoid head rotation, snapping your neck or getting whiplash, and will protect you from cuts and abrasions.

I've been saved by my helmet many times.

Just an FYI to your last paragraph: The core indexing/ranking/storage components of Vespa are C++, and run in a separate process (no jni).

In my own attempt to compare the two, I found the memory consumption of Vespa was easier to predict and understand (there are formulas for it in the documentation).