SI
SI
discoversearch

We've detected that you're using an ad content blocking browser plug-in or feature. Ads provide a critical source of revenue to the continued operation of Silicon Investor.  We ask that you disable ad blocking while on Silicon Investor in the best interests of our community.  If you are not using an ad blocker but are still receiving this message, make sure your browser's tracking protection is set to the 'standard' level.
Politics : The Trump Presidency

 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext  
To: TimF who wrote (33456)9/7/2017 9:40:43 PM
From: combjelly  Read Replies (3) of 363008
 
The relevant definition of "near" in this case is based on light speed lag. Anywhere in the same city would be "near",

No and no. The relevant definition of 'near' is number of hops through the various routers and switches. Which increase with distance. That is what determines latency. But even if that wasn't the case, you have a major misconception of how fast modern computers are. Even slow computers exceed a gigahertz these days and execute several instructions per cycle. In one nanosecond, i.e. the time for a cycle at 1Ghz, light travels about 11 inches in a vacuum. Through copper the electrons travel maybe half that distance due to resistance. Grace Hopper used to pass out wires about 11 inches long to illustrate what a nanosecond means to her classes when she gave lectures on computers. And Grace died some years ago. The speed of light is very relevant to modern electronics. It is slow compared to what we can switch circuits at.

I buy little boards out of China. They cost me less than $10 each. They run Linux on a quad core processor running at 1.2Ghz. The point is, the cost of processing power where the speed of light is relevant is really, really low. HFTs spend a lot more than $10 for their systems.

Really Tim, it is all that hard to do a little research before you start spouting off?
Report TOU ViolationShare This Post
 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext