The GF110 chip shares a lot of its roots with the GF100 core. The GPU still packs an impressive 3.2 billion transistors in a die seize 520mm squared. Its default internal configuration has been ported from GF100 in that the GPU features 512 CUDA cores or shader processors as we are more accustomed to. There are organised in a 4x16x32 block where 16 denotes the number of stream multi-processors (SM) and 32 being the number of cores on each SM. Each SM has its own L1 Cache and a common L2 Cache is shared by all 16. The GPU is still manufactured on the 40nm process.

With the GTX480, only 15 of the total 16 SM were enabled to give it 480 CUDA cores and consequently, it boasted 60 texture units. The GTX580 uses a fully-fledged GF110 GPU and thus retains all 16 SM with none being disabled. The result is 512 fully operational CUDA cores and since the number of texture units is based on the number of stream-multiprocessors, the GTX580 sports 64 units instead of the 60. The number of ROPs has remained the same at 48 and the L2 Cache is still 768 KB. In terms of shader and texturing power, having 512 CUDA cores boosts performance by 6.6% over 480 CUDA cores. Nvidia have gone further with the GTX580 though. Not only have they increased the clock speed on the GTX580 compared to the GTX480, but they have also employed the GF104’s superior texture filtering capabilities in their tweaked GF110 GPU. Improvements have also been done to the tessellation engine so the already very capable performance that is expectant of the Fermi architecture has gone a step further.



MSI nGTX580 Lightning Xtreme Edition

MSI raised the bar with the Lightning Edition overclocking the core to 832MHZ as opposed to 772MHz on the reference card. This in turn raised the shader processing clockspeed 100MHz over stock to 1664MHz. Memory clockspeed had also been tweaked by just under 200MHz from 4008 to 4200 MHz (QDR). The Xtreme Edition of the lightning we are reviewing today keeps the same clockspeeds of the original lightning, indeed it utilizes the same PCB design. Perhaps the biggest difference between the two cards is the addition of a further 1.5GB of GDDR5 making a whopping 3GB total, the highest amount a single core card carries. The MSI GTX280 Xtreme Edition (or XE as known in the U.S) is not however the fastest clocked (core) GTX580 at present, that banner is held by the Gigabyte S0C version but the additional memory should in theory make the card a serious player for those who game at the highest resolutions.
High resolutions, especially when coupled with filters such as Anti-Aliasing, require huge amounts of memory bandwidth and with the average screen size being reported (by Steam) as 1920x1080 it is clear why cards with a 2GB framebuffer are rapidly becoming the norm. Adding huge amounts of memory though does not always solve this issue as the core architecture also needs to have the power to make use of the masses of bandwidth available. We will see later in the review whether the MSI card has got the core power/memory bandwidth balanced later in the review although I fear even a massive 2560x1600 resolution won't be enough to fully saturate the 3GB framebuffer of the MSI card.