Google's Urs Hölzle: If you're not breaking your own gear, you aren't ambitious enough

In the past fifteen years Google has gone from being a consumer of tech to an inventor of technologies, and in doing so has had profound effects on the modern web. One of the key people behind that shift has been Urs Hölzle, who joined the company as its eighth employee and now serves as a senior vice president of technical …

[JDX]

Thanks El Reg

Probably the most interesting thing I've read on this site.

[Anonymous Coward]

I don't think that's going to cut any ice

when I take my work laptop back to be changed because after spilling a bottle of water over it yesterday morning half the keyboard doesn't work, currently using a spare USB keyboard. However, on the bright side, I've not been so ambitious for quite a while.

[Leeroy]

praise

For me there was a striking similarly to the AMD article about their aims for power reductions. Using autonomous systems within the cpu to manage heat and improve performance without any outside (os or bios for AMD and manual clicks by Google staff) influence required.

Praise required, we have indeed come a long way baby !

[Charles Manning]

On the FPGA stuff

He is right about FPGA code being slow and hard to develop. That is partially due to compile cycles that are an order of magnitude slower than software and not very parallelisable.

That is why a group I work with pefers to do FPGA design of "co-processor engines" which get configured and sequenced from software. That allows the FPGAs to do what they do best while leaving the more rapidly changing logic to still be in software which is quicker to change and easier to develop.

Soft cores and custom processors can help to wedge software in where you'd not normally think you could.