As the launch of the AMD FX-series microprocessors code-named "Zambezi" gets nearer, more information about the chips powered by Bulldozer micro-architecture emerge on the web. Based on a recent leak, one of AMD's premium eight-core FX chip will operate at 2.80GHz in default mode and will be able to almost match Intel Corp.'s six-core Core i7-980X Extreme Edition processor in terms of performance.

A major maker of mainboards has reportedly released some of the technical specs and benchmark results of AMD FX 8110 microprocessor for internal use. The information somehow leaked to general public and was republished by a number of web sites (1, 2). Although the specifications of the chip as well as its benchmark results come from strictly unofficial sources, there are indirect evidences that confirm that the information published is at least partially correct. Furthermore, certain specifications revealed by the screenshot are confirmed by AMD's internal documents seen by X-bit labs.

Based on the leaked screenshot, eight-core AMD FX8110 microprocessor will work at 2.80GHz in default mode and will be able to overclock itself to 3.80GHz in certain Turbo Core modes. Although 2.80GHz is not exactly high speed, eight x86 cores will help the code-named Zambezi central processing unit (CPU) to demonstrate remarkable results in highly-multithreaded applications, while Turbo Core technology will disable unused cores in a bid to overclock remaining cores and speed up applications that require one to four cores.

^{Please click to enlarge. Image by RumorPedia.}

Based on benchmark results that were leaked, AMD FX 8110 calculates wPrime 1024M benchmark in 166.895 seconds (which is slightly slower compared to the Core i7-980X) and computes SuperPi 32M in 7 minutes 22.885 seconds (which is drastically faster than any CPU in default mode available today). While wPrime and SuperPi benchmarks do not reflect performance in real-world applications, the numbers still seem to be remarkable. The top-of-the-range AMD FX 8130P that will work on higher frequency will offer even more impressive performance numbers and will likely beat Intel's top-of-the-line Core i7-990X chip in a number of benchmarks. Even though technical specs of the chip seem to be correct, benchmark results cannot be verified.

The test programs, based on the screenshot, were ran in late April on Gigabyte GA-990FX-UD5 mainboard based on AMD 990FX chipset (RD990) with F1b UEFI/BIOS, whereas the latest version is F1b. The system was equipped with 8GB of memory and scored 6.8 points in Windows Experience index.

The initial family of AMD FX-series central processing units (CPUs) will feature two eight-core models, one six-core flavour as well as a quad-core version. The chips will support dual-channel DDR3 1866MHz memory, will support Turbo Core dynamic acceleration technology and will come in AM3+ form-factor and will have 125W and 95W TDP. The second "wave" of Bulldozer chips will also include four microprocessors and will improve performance of the initial breed of CPUs.

Four chips are not a large number and they will hardly be able to properly compete against rather huge Intel Core i7-series microprocessors, which includes quad-core and six-core offerings. But this - initial offering by AMD - may not be the "army" to attack Intel, but rather than a lineup to show what AMD is capable of: creation of a competitive high-end microprocessor. The second breed of Bulldozer-based chips due in Q4 is supposed to really improve AMD's positions on the market of expensive central processing units. By the end of the year AMD, based on a document seen by X-bit labs, expects approximately 10% of its CPUs to be FX-series in AM3+ form-factor.

AMD Orochi design is the company's next-generation processor for high-end desktop (Zambezi) and server (Valencia) markets. The chip will feature eight processing engines, but since it is based on Bulldozer micro-architecture, those cores will be packed into four modules. Every module which will have two independent integer cores (that will share fetch, decode and L2 functionality) with dedicated schedulers, one "Flex FP" floating point unit with two 128-bit FMAC pipes with one FP scheduler. The chip will have shared L3 cache, new dual-channel DDR3 memory controller and will use HyperTransport 3.1 bus. The Zambezi chips will use new AM3+ form-factor and will require brand new platforms.

The Sunnyvale, California-based chip designer plans to introduce AMD 900-series chipsets compatible with Zambezi processors in Q2 2011. The Bulldozer processors, Radeon HD 6000 "Northern Islands" discrete graphics cards  and AMD 900-series core-logic sets will power AMD's next-generation enthusiast-class platform code-named Scorpius.

AMD did not comment on the news-story.

Tags: AMD, Bulldozer, Phenom, 32nm, Orochi, Zambezi