Kougar | 14th April 2008 21:19 | Quote:
Originally Posted by jmke
(Post 168066)
doesn't 64-bit improvements come from applications written especially for 64-bit, which take advantage of the upgraded architecture ? | Not sure the program must be natively 64bit to see an improvement. If I understand this Nehalem will simply act upon several specific 64bit instruction sets, and fuse them together for processing in half the time. Same principle as the current 32bit macrofusion. Except with Core 2 Duo 64bit instructions are first split into 32+32, then processed.
64bit applications on 64bit Operating Systems would no longer need to be split into 32bit+32bit. Instead, select 64+64 instruction sets would be processed in the same clock cycle previously taken to process a 32+32bit (A single split 64bit) instruction set. Or am I wrong? ;) |