Intel has decided to patent the act of multiplying two numbers.
While this gives Year Four kids names to carve onto their wax effigies, it is not quite who is going to licence the technology.
What the patent really seems to be talking about is something based on the fast Karatsuba algorithm.
This has been around since 1962. What Intel has patented is extremely large numbers for cryptography applications and the bottleneck of 32-bit and 64-bit processors when they are dealing with protocols that include numbers ranging from 1024 to 4096.
The patent says how Intel’s method works when compared to previous approaches. Tests mentioned in the patent suggest that modular reduction approaches can accelerate 512 bit number operations by 27 per cent and up to 177 per cent for 4096 bit numbers.
So, the patent is not for the act of multiplying numbers together, as the header suggests, but some complicated method of adding algorithms. So your kid’s excuse that he can’t remember his seven times tables because an Intel lawyer served him with an IP demand is probably bogus.