AMD's Athlon 64 X2 series Dual Core launch back in May, along with Intel's Pentium 840 launch in April, underscored an industry-wide move toward a completely new Desktop Processor architecture, one that affects virtually all facets of Personal Computing from code-base, applications and software, to the platforms and technology that support these new multi-core CPUs. With Intel taking the first step with their Pentium 8XX series, and AMD stepping up with the X2, the tide has officially shifted, and the industry and community are ready to catch the wave. However, as with any major redirection in architecture, "the wave" doesn't just appear out of nowhere. There is typically a gradual transition involved, which is where we are today, as both Intel and AMD drive what are essentially parallel efforts launching new single core Desktop processors as well.
While Intel may be heading down the Dual Core path more definitively, with their roadmaps cutting over completely to Dual Core CPUs, AMD appears to be stepping into the Dual Core area as market requirement develops, versus firmly driving the market toward one initiative over the other. And as Damon Muzny of AMD Public Relations likes to claim, "when you've got more MHz in the can" there is flexibility in being able to offer whatever CPU architecture best hits the market's sweet spot at the time, especially with all the single threaded applications that exist today. For example, if you're a Gamer, there are virtually zero game titles currently available that'll truly benefit from Dual Core architectures. That may change in the next year or so, but for now, the faster single core processors take all the top spots performance-wise in many gaming / multimedia related scenarios.
Which brings us to our spotlight product we have for you here, the Athlon FX-57. What does a 200MHz speed bump, a few tweaks to optimizing the memory controller and couple of new SSE3 instructions thrown in, do for what is already a blazingly fast single-core CPU? That's what we're going to show you in the pages ahead.
|AMD64 Feature Set-
•_Support for 64-bit operating systems to provide full, transparent, and simultaneous 32-bit and 64-bit platform application multitasking.
•_A physical address space that can support systems with up to one terabyte of installed RAM, shattering the 4 gigabyte RAM barrier present on all current x86 implementations.
•_Sixteen 64-bit general-purpose integer registers that quadruple the general purpose register space available to applications and device drivers.
•_Sixteen 128-bit XMM registers for enhanced multimedia performance to double the register space of any current SSE/SSE2/SSE3 implementation.
Integrated DDR memory controller:
•_Allows for a reduction in memory latency, thereby increasing overall system performance.
An advanced HyperTransport link:
•_This feature dramatically improves the I/O bandwidth, enabling much faster access to peripherals such as hard drives, USB 2.0, and Gigabit Ethernet cards.
•_HyperTransport technology enables higher performance due to a reduced I/O interface throttle.
Large level one (L1) and level 2 (L2) on-die cache:
•_With 128 Kbytes of L1 cache and 512K of L2 cache, the AMD Athlon 64 processor is able to excel at performing matrix calculations on arrays.
•_Programs that use intensive large matrix calculations will benefit from fitting the entire matrix in the L2 cache.
•_A 64-bit address and data set enables the processor to process in the terabyte space.
•_Many applications improve performance due to the removal of the 32-bit limitations
|Processor core clock-for-clock improvements:
•_Including larger TLB (Translation Look-Aside Buffers) with reduced latencies and improved branch prediction through four times the number of bimodal counters in the global history counter, as compared to seventh-generation processors.
•_These features drive improvements to the IPC, by delivering a more efficient pipeline for CPU-intensive applications.
•_CPU-intensive games benefit from these core improvements.
•_Introduction of the SSE3 instruction set, which along with support of 3DNow! Professional, (SSE2, SSE and 3DNow! Enhanced) completes support for all industry standards.
•_32-bit instruction set extensions.
•_AMD's Fab 30 wafer fabrication facility in Dresden, Germany
•_.09 micron SOI (silicon-on-insulator) - San Diego Core
• San Diego Core - 115mm2
•_San Diego Core - Approximately - 114 million
Other than the branding and product codes etched into its IHS (Integrated Heat Spreader), there's nothing new to point out with regard to the FX-57's physical appearance. But this isn't simply a speed bump. The FX-57 is based on a totally new processor core, that's got some distinct advantages over it's predecessor's design, and older version FX processors.
The Athlon 64 FX-57 is based on the relatively new "San Diego" core. If you've followed the recent progression of new Athlon 64 cores to come from AMD, you're probably familiar with the "Venice" core, which we evaluated a few weeks back (see here). The San Diego core used on the Athlon 64 FX-57 is the same process geometry and architecture as the Venice core, but with an additional 512K of L2 cache for a total of 1MB. The San Diego core incorporates all of the same tweaks to the memory controller as well. Also AMD has integrated SSE3 multimedia instruction sets into the Athlon 64 FX-57, and have made some other additions and enhancements as well which include:
·_Mismatched DIMM support (ability to configure and use different size DIMMs on the same channel)
·_Improved memory mapping (more efficient use of memory space)
·_Improved memory loading (can fully populating the memory with double-bank DIMMs with no slow down)
The Athlon 64 FX-57 is also the first processor in the "FX" line to be built using AMD's .09 micron SOI manufacturing process. By moving to the smaller, more advanced .09 micron manufacturing process, AMD was able to shrink the size of the FX's die (115mm2 vs. 193mm2), while at the same time lowering its voltage requirements and max processor current. As you can see in the chart above, the new FX-57 requires only 1.35v-1.4v and draws a maximum current that's 5.1 Amps lower than the FX-55, which is built on AMD's .13 micron line.