Loading recent posts...

Jun 25, 2012

AMD Fusion APUs 500% is Faster than Intel’s CPUs in Musemage

When it comes to photo processing, GPU accelerated compute power has a very high performance potential. Depending on the architecture in question and the API used, the result can be amazing.

AMD’s Llano seems to be a very capable APU, and despite the fact that it can already be called “last year technology” it demonstrates nice results. Software developers preference for open source APIs also puts AMD’s OpenCL capabilities in a better position than Nvidia’s CUDA. During this year’s AFDS, AMD posted some nice short videos exemplifying the performance improvement offered by the company’s GPU architecture. What the video doesn’t show is the impressive performance results that are achieved in real benchmarking.

William Van Winkle from Tom’s Hardware put AMD’s A8-3850 APU to the test and the result was that the Llano APU is over 5 times faster than Intel’s Core i5 Sandy Bridge processor using HD 2500 iGPU. The more impressive part is the fact that AMD’s Radeon HD 7970 GPU is over 25 times faster than the same Core i5 CPU.

Accelerated by the AMD Radeon™ HD GPUs, Musemage enables ultra-fast speed and real-time visual feedback. Its powerful batch processing tool makes it incredibly easy to process multiple pictures at one time, including adjusting, resizing and applying filters!
Video credits: AMD

AMD G-T16R Shows 300% Performance of the GeodeLX, Consume Less Power

Fabless CPU and GPU designer, Texas-based company AMD has launched today the company’s new G-T16R embedded processor, on its official website. The new wonder consumes an average power of 2.3 watts and offers over three times the performance of Geode LX.

Many of our readers will remember AMD’s Geode line of embedded processors that the company acquired from National Semiconductor. Back in 2002, AMD needed to buy a whole CPU team from National Semiconductor to be able to offer processors that were proper to fit thin industrial clients and manifested a power consumption of less than 10 watts. Now, AMD is able to offer APUs that consume roughly less than quarter of that value and offer 300% the performance. We should not forget that AMD’s Geode LX was a significantly improved version of AMD’s Geode GX2 and also has AES Encryption. A 3-fold performance improvement along with a 7% decrease in average power consumption and a 58% in chip footprint is quite amazing.

AMD’s Embedded G-T16R APU support Windows Embedded Compact 7, Green Hills INTEGRITY and Express Logic ThreadX operating systems and have enhanced connectivity option such as VGA and LVDS support for legacy applications and DVI, HDMI along with DisplayPort. The maximum TDP of the platform is 4.5 watts, and this includes the APU and the associated chipset. Both chips occupy only 890 square millimeters, which is about a quarter of a square inch. AMD’s older Geode LX embedded processors are supposedly going to be available until 2015 while the team that designed them was relocated from Longmont, Colorado to the new development facility in Fort Collins, Colorado.

AMD's G-T16R Embedded Platform
Image credits: AMD

AMD's G-T16R Embedded Platform
Image credits: Advantech

AMD's G-T16R Embedded Platform Diagram
Image credits: AMD

This is it, HP’s First AMD “Trinity” Desktop System

HP has been a strong supporter of AMD during the last years.  Now, the company is among the first big OEM builders to launch “Trinity”-based desktop computer systems.

HP has chosen AMD GPUs as their main 3D processing solution in the company’s mobile systems for years now.  Even Nvidia was telling us at a Kepler presentation some months ago that they were very happy HP decided to finally use Nvidia GPUs again. They were proud to include HP on Nvidia’s design wins board, but the thing is that the first Ivy Bridge notebooks launched by HP were still using AMD GPUs. HP’s SleekBook is one of AMD’s best examples of how a “Trinty” UltraBook can be better than an Intel-based one. Of course, the UltraBook moniker is only reserved for Intel-based mobile systems, but we must accept that HP’s “SleekBook” brand is simply cooler. After all these pro-AMD moves, it is no wonder that HP is one of the first big computer builders to launch AMD “Trinity”-based desktop personal computer systems.

The system is called HP Pavilion P7-1269C and is already available for $820. That’s about €653 for the European buyers, and it’s just the starting price for a whole range of various configurations. There are many hardware combinations available, such as AMD APU-5800K A10, A10-5700, 5600K-A8, A8-5500, A6-A4-5300 and 5400K when the CPU is involved. The motherboard is an MSI MS-7778 (Jasmine) FM2 Socket micro-ATX based on AMD’s A75 chipset. It is actually manufactured by Pegatron for MSI, and it’s quite strange for HP to provide such detailed info on the insides of its new system. The system comes equipped with 8GB of DDR3-1600 RAM memory. Here are the complete system specifications on HP’s own official website.

HP Pavilion P7-1269C Desktop Computer System (AMD "Trinity" based)

All Images credits to HP

AMD Fusion Server Brings 252% of MATLAB Performance Using OpenCL

AFDS 2012 event is proving to be very interesting and is clearly has much more serious impact on the computing industry as last year.

Now we even have AMD APU based  professional servers from Penguin Computing fited with proper software that will take advantage of the iGPU inside AMD’s Fusion APUs and offer considerable better results. In this case the demonstration is done on a Penguin Computing Altus 2A00 server that you can read full story in Penguin Computings' Website.

The system is powered by AMD’s Llano APUs, but we can expect Trinity versions to appear soon. In this particular case, Penguin uses Accelereyes’ software called “Jacket” that allows MATLAB to run on but the x86 core and the iGPU at the same time. The iGPU is able to deliver 52% better performance, but as the speaker emphasizes, the server is actually running two threads at the same time offering a combined performance of 252% the performance of just the x86 cores.

The user will be able to run two different threads in MATLAB at the same time. One will use the x86 cores and the other will use the OpenCL capabilities of the iGPU with the help of Accelereyes’ “Jacket” software. The demo is impressive as practically the productivity of the system is increased almost three times while there is a single APU inside.

AMD's Sasa Marinkovic and AccelerEyes' John Melonakos demo Matlab on OpenCL and the AMD Trinity APU, from the Experience Zone at AFDS 2012. 

For more information, visit: http://bit.ly/AFDS-D and http://www.accelereyes.com/

Twitter Delicious Facebook Digg Stumbleupon Favorites More

Design by Free WordPress Themes | Bloggerized by Lasantha - Premium Blogger Themes | coupon codes