by Anton Shilov
09/30/2006 | 11:44 PM
Intel Corp., the world’s largest chipmaker, will release what is generally called “native” quad-core processor in the third quarter of the year 2007, according to several media reports and rumours circulating around Intel Developer Forum in
The microprocessor code-named Yorkfield will feature single-die design as well as unified level-two (L2) cache, which should boost its efficiency when compared to Intel’s first-generation quad-core offerings that have two-dice design and have to cooperate using processor system bus (PSB). Yorkfield is expected to feature 1333MHz PSB and be compatible with chipsets code-named Bearlake, which also support DDR3 memory.
It is interesting to note that earlier media reports indicated that Yorkfield is a code-name for Intel’s octa-core (eight-core) microprocessor that consists of two dice made using 45nm process technology. Those octa-core (eight-core) were originally expected to be released in 2008 or beyond. Meanwhile, Intel's first single-die quad-core chip was earlier rumoured to be code-named Bloomfield. Given that current information comes from unofficial sources and roadmaps tend to be changed rather quickly, it is highly-likely that the chips may have different code-names and/or specifications.
Intel Corp. will commercialize its first quad-core microprocessors as early as in November, 2006, about six months ahead of AMD, which is likely to add competitive pressure on the world’s second largest supplier of x86 microprocessors. But AMD believes that Intel’s approach to put two dice on a single slice of substrate to build a quad-core processor is inefficient and AMD’s “native” single-die quad-core design will provide better performance and scalability for servers. On the other hand, AMD may not hold advantage of having the world’s only x86 single-die quad-core chip, as Intel’s code-named Yorkfield may be launched just several months after, in Q3 2007.
Intel Corp. did not comment on the news-story.