by Anton Shilov
06/13/2012 | 11:06 PM
Advanced Micro Devices has officially published specifications of some of its A-series Fusion "Trinity" accelerated processing units (APUs) for desktops. However, according to media reports, AMD plans to delay its highly-anticipated desktop APUs to Fall, which means that only mobile versions will be available this Summer.
While at Computex Taipei 2012 trade-show numerous mainboard makers demonstrated systems running AMD Fusion "Trinity" A10-5800K APUs, many of manufacturers complained about AMD's plans to delay launch of the desktop chips to September or October, reports TechReport web-site. The reasons for the delay are unclear, but Globalfoundries, the contract maker of semiconductors that produces both Llano and Trinity APUs using 32nm process technology, claims that there are no yield issues related to AMD's products.
Despite of the alleged launch delay, AMD did publish specifications of its next-generation A-series 5000-family APUs on its web-site. The specs reaffirm details published by X-bit labs back in February, 2012, and hence are nothing new.
It is noteworthy that despite of the fact that AMD intended to release its highly-anticipated Trinity products in around the middle of the year, it only launched several mainstream mobile chips in mid-May and delayed high-performance and ultra low-power mobile APUs to a later date. Moreover, the company also plans to postpone the release of desktop versions of its second-generation Fusion APUs to late-Q3 or early-Q4. Such a delay will negatively impact AMD's ability to compete on the market of performance desktops and notebooks as its arch-rival Intel has already rolled-out a broad family of its Core i-series 3000-family "Ivy Bridge" central processing units.
The AMD A-series "Trinity" APUs feature up to four x86 cores powered by enhanced Bulldozer/Piledriver architecture, AMD Radeon HD 7000-series graphics core with DirectX 11-class graphics support, DDR3 memory controller and other improvements, such as new dynamic acceleration Turbo Core technology, improved video playback engines and so on. The new chip is made using 32nm process technology at Globalfoundries, just like its predecessor code-named Llano, but thanks to architectural improvements it is projected to be 25% - 50% faster - depending on the task - than the first-gen A-series APU.
AMD did not comment on the news-story.