GeForce GTX 570 review - The GeForce GTX 570 graphics processor

The GeForce GTX 570 graphics processor

So we already stated that the same GPU being used in the GeForce GTX 580 is also located in the GTX 570, though limited in several ways. A new revision GPU based on the GF100 ASIC, now labeled as the GF110.

NVIDIA now has a full range of products out on the market from top to bottom. All the new graphics adapters are of course DirectX 11 ready. With Windows 7 and Vista also being DX11 ready all we need are some games to take advantage of DirectCompute, multi-threading, hardware tessellation and new shader 5.0 extensions. DX11 is going to be good and once tessellation kicks into games, much better looking.

• GeForce GTX 580 : 512 SP, 384-bit, 243W TDP
• GeForce GTX 570 : 480 SP, 320-bit, 219W TDP
• GeForce GTX 480 : 480 SP, 384-bit, 250W TDP
• GeForce GTX 470 : 448 SP, 320-bit, 225W TDP

The GPU that empowers it all has small architectural changes, some stuff was stripped away and some additional functional units for tessellation, shading and texturing have been added. Make note that the GPU still is big, as the fabrication node is still 40nm. TSMC canceled the 32nm fab node preventing this chip from being smaller.

Both the GF100 and GF110 graphics processors have sixteen shader clusters embedded in them (called SMs aka Streaming Multiprocessors). The GTX 580 has 16 of these active, the GTX 570 will have 15 SMs active, boiling down to 480 active shader processors.

The GeForce GTX 570 card is clocked at 732 MHz with it's shader processors being clocked at 1464 MHz.

Graphics memory wise NVIDIA has large expensive memory volumes due to their architecture, we pass 1 GB as standard these days for most of NVIDIA's series 400 and 500 graphics cards.

Remember this, each memory partition utilizes one memory controller on the respective GPU, which will get 256MB of memory tied to it.

• The GTX 470 has five memory controllers (5x256MB) = 1280 MB of GDDR5 memory
• The GTX 480 has six memory controllers (6x256MB) = 1536 MB of GDDR5 memory
• The GTX 570 has five memory controllers (5x256MB) = 1280MB of GDDR5 memory
• The GTX 580 has six memory controllers (6x256MB) = 1536 MB of GDDR5 memory

Five memory controllers at 64-bits each then accumulated to a 320-bit wide memory bus for the GeForce GTX 570. As you can understand, the massive memory partitions, bus-width and combination of GDDR5 memory (quad data rate) allow the GPU to work with a very high framebuffer bandwidth (effective). The effective reference data-rate for memory will be 3800 MHz.

Let's put most of the data in a chart to get an idea and overview of changes:

So we talked about the core clocks, specifications and memory partitions. Obviously there's more to talk through. Now, at the end of the pipeline we run into the ROP (Raster Operation) engine, the GTX 580 again has 48 units for features like pixel blending and AA. The GTX 570 however has 8 ROP engines cut away, this will definitely have an adverse impact on performance.

There's a total of 6 texture filtering units available for the GeForce GTX 570. The math is simple here, each SM has four texture units tied to it.

• GeForce GTX 470 has 14 SMs X 4 Texture units = 56 
• GeForce GTX 480 has 15 SMs X 4 Texture units = 60
• GeForce GTX 570 has 15 SMs X 4 Texture units = 60
• GeForce GTX 580 has 16 SMs X 4 Texture units = 64

Though still a 40nm based chip, the GF110 GPU comes with almost 3 billion transistors embedded into it. The TDP sits at roughly 219 Watts, while performance is equal with the GTX 480, that's a good 30W of power consumption shaved off.

TDP = Thermal Design Power. Roughly translated, when you stress everything on the graphics card 100%, your maximum power consumption is the TDP.

The GeForce GTX 570 comes with two 6-pin connector to get its current. This boils down as: 150W over the two 6-pin PEG + PCIe slot = 75W is 225 available (in theory). That is quite limited, though the amount of current that can pass over the 6-pin PEG headers is more of a spec than a limitation.