Southern Islands (GPU family)
Encyclopedia
The Southern Islands series is a family of Radeon
Radeon
Radeon is a brand of graphics processing units and random access memory produced by Advanced Micro Devices , first launched in 2000 by ATI Technologies, which was acquired by AMD in 2006. Radeon is the successor to the Rage line. There are four different groups, which can be differentiated by...

 GPUs
Graphics processing unit
A graphics processing unit or GPU is a specialized circuit designed to rapidly manipulate and alter memory in such a way so as to accelerate the building of images in a frame buffer intended for output to a display...

 developed by Advanced Micro Devices
Advanced Micro Devices
Advanced Micro Devices, Inc. or AMD is an American multinational semiconductor company based in Sunnyvale, California, that develops computer processors and related technologies for commercial and consumer markets...

. Products in the Southern Islands series will be based on the 28 nm manufacturing process. AMD will build 28 nm graphics chips at TSMC
TSMC
Taiwan Semiconductor Manufacturing Company, Limited or TSMC is the world's largest dedicated independent semiconductor foundry, with its headquarters and main operations located in the Hsinchu Science Park in Hsinchu, Taiwan.-Overview:...

.

Early details

In 2010, the Northern and Southern Islands cards adopted the AMD Radeon brand name. The Southern Islands will most likely be named the Radeon HD 7000 Series.

Technical details

Early rumors said that this series would only be a die-shrink of the Radeon HD 6900 (Cayman)
Northern Islands (GPU family)
The Northern Islands series is a family of GPUs developed by Advanced Micro Devices for its Radeon line, based on the 40 nm process.Starting with this family, the former ATI brand was officially discontinued in favor of making a correlation between the graphics products and the AMD branding for...

 architecture. However, later news revealed that the Southern Islands architecture is called Graphics Core Next Gen.
  • Support for x86 addressing with unified address space for CPU and GPU.
    • 64-bit addressing
    • Support for PCI-E 3.0
    • GPU sends interrupts to CPU on various memory errors (such as page faults).
  • Usage of XDR2 DRAM
    XDR2 DRAM
    XDR2 DRAM is a type of Dynamic Random Access Memory that is offered by Rambus. It was announced on July 7, 2005 and the specification for which was released on March 26, 2008...

     instead of GDDR5
    GDDR5
    GDDR5 SDRAM is a type of high performance DRAM graphics card memory designed for computer applications requiring high bandwidth...

     which will result in increasing the bandwidth by 50% while reducing the power consumption by 30%, according to Rambus
    Rambus
    Rambus Incorporated , founded in 1990, is a technology licensing company. The company became well known for its intellectual property based litigation following the introduction of DDR-SDRAM memory.- History :...

    .
  • Usage of RISC MIMD
    MIMD
    In computing, MIMD is a technique employed to achieve parallelism. Machines using MIMD have a number of processors that function asynchronously and independently. At any time, different processors may be executing different instructions on different pieces of data...

     instructions for GPGPU
    GPGPU
    General-purpose computing on graphics processing units is the technique of using a GPU, which typically handles computation only for computer graphics, to perform computation in applications traditionally handled by the CPU...

     instead of VLIW
    Very long instruction word
    Very long instruction word or VLIW refers to a CPU architecture designed to take advantage of instruction level parallelism . A processor that executes every instruction one after the other may use processor resources inefficiently, potentially leading to poor performance...

     SIMD
    SIMD
    Single instruction, multiple data , is a class of parallel computers in Flynn's taxonomy. It describes computers with multiple processing elements that perform the same operation on multiple data simultaneously...

     (Which was only one option in previous AMD GPU-architectures).
  • Support for Partially Resident Textures, which enable virtual memory support through DirectX and OpenGL extensions.
  • PowerTune support, which dynamically adjusts performance to stay within a specific TDP.
  • Usage of Liquid-chamber cooling technology over Vapor chamber.

These changes could lead to better utilization of the GPU for compute along with traditional graphics. This architecture is supposed to be integrated into the next line of AMD Fusion
AMD Fusion
AMD Fusion is the marketing name for a series of APUs by AMD. There are two flavors of Fusion currently available, one with its CPU logic based on the Bobcat core and the other its CPU logic based on the 10h core. In both cases the GPU logic is HD6xxx, which itself is based on the mobile variant of...

 processors.

Release date

The Southern Islands design was reportedly taped out
Tape-out
In electronics design, tape-out or tapeout is the final result of the design cycle for integrated circuits or printed circuit boards, the point at which the artwork for the photomask of a circuit is sent for manufacture....

 in February 2011. AMD gave a preview of the new design at the AMD Fusion Development Summit (June 13-16, 2011). On July 21, 2011, the company confirmed that it has working silicon in-house and it plans to release the first cards before the end of the year, the primary constraint being the stability of the 28 nm process at TSMC
TSMC
Taiwan Semiconductor Manufacturing Company, Limited or TSMC is the world's largest dedicated independent semiconductor foundry, with its headquarters and main operations located in the Hsinchu Science Park in Hsinchu, Taiwan.-Overview:...

. It has been speculated that AMD is to use a version of the 28 nm process that is optimized for low power/low clock chips in order to meet the Q4 2011 target. The primary competitor of Southern Islands, Nvidia
NVIDIA
Nvidia is an American global technology company based in Santa Clara, California. Nvidia is best known for its graphics processors . Nvidia and chief rival AMD Graphics Techonologies have dominated the high performance GPU market, pushing other manufacturers to smaller, niche roles...

 Kepler (also manufactured at TSMC), is not expected to ship until Q1 2012, largely due to the immaturity of the 28 nm process.

Chipset table

External links

The source of this article is wikipedia, the free encyclopedia.  The text of this article is licensed under the GFDL.
 
x
OK