by Anton Shilov
07/02/2013 | 11:50 PM
Advanced Micro Devices not only demonstrated engineering sample of its code-named Kaveri accelerated processing unit running a technology demo, but before that it actually started to test the APU in real-world applications. In fact, back in late March AMD tried a Kaveri based-system in cosmology at home volunteer/grid computing application.
An occasional search for various microprocessor models by DresdenBoy revealed quad-core AMD Eng Sample: 2M186092H4467_23/18/12/05_1304 [Family 21 Model 48 Stepping 0] in Cosmology at Home database. It is believed that the chip runs at 1.80GHz default clock-speed, has 2.30GHz Turbo Core frequency and features code-named Spectre graphics processing engine operating at 500MHz clock-rate. The chip is believed to have 35W thermal design power.
The code-named Kaveri APUs are the first to integrate highly-anticipated Steamroller general-purpose x86 cores, hence there are anticipations for extreme performance in applications that rely on x86 processing. Unfortunately, due to very low clock-speeds, measured performance numbers in BOINC whetstone/dhrystone are rather low: 504.7 million ops/s and 2544.64 million ops/s, respectively.
The test system was only used once on March 19, 2013. Given the fact that the chip was an early sample based on stepping 0, it is hard to say whether Kaveri suffers from inability to run at high clock-rates, or is simply clocked at moderate frequencies in order to maintain stability.
AMD Fusion A-series APU code-named Kaveri is projected to feature up to four Steamroller high-performance x86 general-purpose cores as well as GCN architecture-based AMD Radeon HD graphics engine. The Kaveri chip will be AMD’s first high-performance accelerated processing unit with HSA [heterogeneous system architecture] enhancements, such as heterogeneous uniform memory access, CPU and GPU cache coherency and other. Moreover, Kaveri will be AMD’s first high-performance APUs made using 28nm process technology. Finally, the chips will feature new dual-channel memory controller as well as all-new power management.
As a result of massive changes inside Kaveri, the chips will feature new FM2+ form-factor and will only be compatible with new mainboards with FM2+ sockets, according to a new roadmap update issued by AMD. The new chips will therefore be incompatible with existing mainboards, which means that there will be no upgrade path for systems based on A-series “Trinity” and “Richland” APUs.
Given the fact that Kaveri will feature a number of “firsts” for AMD, a new socket was something logical to expect. What is unclear at this point is whether FM2+ mainboards will have any specific requirements and whether they will be more expensive than existing motherboards with FM2 sockets.
AMD did not comment on the news-story.