Point of View GTX 570 TGT Ultra Charged review
Posted by Hilbert Hagedoorn on: 12/12/2010 02:00 PM [ 0 comment(s) ]
The GeForce GTX 570 graphics processor
So we'll first have a word about the reference baseline product; 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.
| GeForce 9800 GTX |
GeForce GTX 285 |
GeForce GTX 295 |
GeForce GTX 470 |
GeForce GTX 480 |
GeForce GTX 570 |
POV GTX 570 TC |
GeForce GTX 580 | |
| Stream (Shader) Processors | 128 | 240 | 240 x2 | 448 | 480 | 480 | 480 | 512 |
| Core Clock (MHz) | 675 | 648 | 576 | 607 | 700 | 732 | 810 | 772 |
| Shader Clock (MHz) | 1675 | 1476 | 1242 | 1215 | 1400 | 1464 | 1620 | 1544 |
| Memory Clock (effective MHz) | 2200 | 2400 | 2000 | 3350 | 3700 | 3800 | 3960 | 4000 |
| Memory amount | 512 MB | 1024 MB | 1792 MB | 1280 | 1536 | 1280 | 1280 | 1536 |
| Memory Interface | 256-bit | 512-bit | 448-bit x2 | 320-bit | 384-bit | 320-bit | 320-bit | 384-bit |
| Memory Type | gDDR2 | gDDR3 | gDDR3 | gDDR5 | gDDR5 | gDDR5 | gDDR5 | gDDR5 |
| HDCP | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes |
| Two Dual link DVI | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes |
| HDMI | No | No | No | Yes | Yes | Yes | yes | Yes |
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:
| Graphics card | GeForce GTX 470 | GeForce GTX 480 | GeForce GTX 570 | GeForce GTX 580 |
| Fabrication node | 40nm | 40nm | 40nm | 40nm |
| Shader processors | 448 | 480 | 480 | 512 |
| Streaming Multiprocessors (SM) | 14 | 15 | 15 | 16 |
| Texture Units | 56 | 60 | 60 | 64 |
| ROP units | 40 | 48 | 40 | 48 |
| Graphics Clock (Core) | 607 MHz | 700 MHz | 732 MHz | 772 MHz |
| Shader Processor Clock | 1215 MHz | 1401 MHz | 1464 MHz | 1544 MHz |
| Memory Clock / Data rate | 837 MHz / 3348 MHz | 924 MHz / 3696 MHz | 950 / MHz 3800 MHz | 1000 MHz / 4000 MHz |
| Graphics memory | 1280 MB | 1536 MB | 1280 MB | 1536W MB |
| Memory interface | 320-bit | 384-bit | 320-bit | 384-bit |
| Memory bandwidth | 134 GB/s | 177 GB/s | 152 GB/s | 192 GB/s |
| Power connectors | 2x6-pin PEG | 1x6-pin PEG, 1x8-pin PEG | 2x6-pin PEG | 1x6-pin PEG, 1x8-pin PEG |
| Max board power (TDP) | 215 Watts | 250 Watts | 219 Watts | 244 Watts |
| Recommended Power supply | 550 Watts | 600 Watts | 550 Watts | 600 Watts |
| GPU Thermal Threshold | 105 degrees C | 105 degrees C | 97 degrees C | 97 degrees C |
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.

Today a review on the ProTAB 2 XXL 10" tablet from Point of View from their Mobi range. With a price of only 169,- EUR the specs are decent enough alright. Interesting enough for graphics, the ProTab2XXL also comes with an additional MALI-400 3D graphics chip. Now we never heard of it before tbh, and very little can found about it on the web. But we can certainly measure it's performance and it does allow for FullHD playback. The Mali graphics chip even allows to drive a mini HDMI v1.4 port.
Point of View GTX 570 TGT Ultra Charged review
Today's offering is of course a GTX 570, we nicked it out of the Eindhoven warehouse from the good people at Point of View. See, their TGT team is chunking out several new SKUs based on the GTX 570. Today we'll have a peek at their Ultra Charged model. The UC version is a guaranteed stable factory overclocked product that is overclocked towards a pretty impressive value. See, the default core clock frequency of the GTX 570 is 732 MHz, the TC version is clocked at a blistering 810 MHz, which is a pretty decent overclock. Memory wise spot an increased clock frequency on that 1.2 GB GDDR5 memory as well, taken from 3800 towards 3960 MHz.
Point of View Ion 330 motherboard review
We test an ION 330 based motherboard - ION is a relatively low cost GPU assisted solution that will allow this industry on very short notice to have netbooks with full HD playback quality, in multi-channel HD audio. A solution that even supports CUDA and therefore some simple PhysX functionality, but since it's CUDA compatible, it'll also allow encoding and acceleration of popular video content. A platform that supports Gigabit Ethernet, dual-link DVI (high resolution monitors), acceleration in Photoshop CS4 and heck... you can even play a couple of games or make a mini HTPC out of it, it's just really interesting as the product might be little, yet offers a lot.
GeForce 9600 GSO 384 MB review | Point of View
NVIDIA replaced the GeForce 8800 GS with the GeForce 9600 GSO. The 9600 GSO is still based on the same G92 core with 96 stream processors that the 8800 GS has, but NVIDIA gave card makers a bit more freedom in their designs in terms of own PCB design to and determine their own clocks. This 'old' card will still have 384 MB of GDDR3 memory over a weird 192-bit memory interface. Cards like these will sell for less than 99 Euro, and considering the performance you get returned for that, you'll love it.
