2007
IBM With 32nm Processors
IBM has revealed that it is working on a new 32nm processor manufacturing technique which could make the production of chips more accessible to smaller companies, as well as yielding performance gains. The process works in a similar way to the high-k/metal gate technique that is currently used by both IBM and Intel for their 45nm chips, which replaces some of the silicon in transistors with more efficient materials to pack more components into a single chip. IBM’s new technique uses a modified version of this process known as high-k/gate-first to develop its 32nm chips, which works by focusing on the most advanced components first. Big Blue has already demonstrated a working example of the 32nm technology with prototype static RAM chips, and mass production is expected to begin during the second half of 2009.
Source: MacNN
The lackluster launch of Barcelona earlier this year left us with ambivalent feeling before the launch of Phenom. Up before the launch, numerous rumors of various problems were circulating, and when the launch finally happened and we only had two models to play with, we couldn’t help feeling a bit let down. The performance was good and lived up to what AMD had promised, more or less, but since the frequencies were so low and IPC was more or less the same as Core 2, it was still being outperformed by Intel’s processors. With the recent unveiling of the TLB bug, the crippling BIOS fix and the seized shipments of quad-core processors, the plans for the future has had to be revised. The earlier announced tri-core series is set for arrival in February 2008, and should be available in decent numbers the following month. Two models are currently planned for launch, Phenom 8700 and Phenom 8600 running at 2.4 and 2.3 Ghz respectively. These are disabled quad-core with 512KB L2 cache per core and a shared 2MB L3 cache, not suffering from the TLB errata (B3 stepping).