The GeForce 200 Series is the tenth generation of NVIDIA's GeForce graphics processing units. The series also represents the continuation of the company's unified shader architecture introduced with the GeForce 8 Series and the GeForce 9 Series.
The GeForce GTX 280 and 260 are based on the same processor core. During the manufacturing process, GTX chips are binned and separated through defect testing of the core's logic functionality. Those that fail to meet the GTX 280 hardware specification are re-tested and binned as GTX 260 (which is specified with fewer stream processors, less ROPS and a narrower memory bus). In late 2008, in order to create more parity between the GTX 260 and the competing HD 4870, Nvidia re-released the GTX 260 with 216 stream processors up from 192. Effectively, there are two GTX 260 cards in production with non-trivial performance differences.
As of June 2008[update], the G200 is the largest commercial GPU ever constructed. It consists of 1.4 billion transistors covering a 576mm2 die surface area built on a 65nm process.[1] To date, the G200 is the largest CMOS-logic chip that has been fabricated at the TSMC foundry.
| NVIDIA GeForce 200 Series | |
|---|---|
| Codename(s) | G92a/b, G200a/b |
| Release date | 2008/2009 |
| Mid-Range GPU | GTS 250, GTX 260, GTX 260 Core 216 |
| High-end GPU | GTX 275, GTX 280, GTX 285, GTX 295 |
| Direct3D and Shader version | D3D 10.0, Model 4.0 |
Contents
- 1 Technical summary
- 2 Future
- 3 See also
- 4 References
- 5 External links
Technical summary
- 1 Unified Shaders (Vertex shader / Geometry shader / Pixel shader) : Texture mapping unit : Render Output unit
- 2 The theoretical shader performance in single-precision floating point operations [FLOPSsp, GFLOPS] of the graphics card with shader count [n] and shader frequency [f, GHz], is estimated by the following: FLOPSsp ≈ f × n × 3.
Model Year Code name Fab (nm) Transistors (Billion) Die Size (mm 2) Bus interface Memory min (MiB) Config core 1 Reference clock rate Fillrate Reference Memory Configuration Graphics library support (version GFLOPs2 (MADD+MUL) TDP (Watts) Comments Core (MHz) Shader (MHz) Memory (MHz) Pixel (GP/s) Texture (GT/s) Bandwidth (GiB/s) DRAM type Bus width (bit) DirectX OpenGL GeForce GTS 250 March 3, 2009 G92a/b 65/55 0.754 324/230 PCIe x16 2.0 512 or 1024 128:64:16 738 1836 2200 11.808 47.232 70.4 GDDR3 256 10 3.1[2] 705 145 Some 512MB cards are rebranded GeForce 9800 GTX and GTX+ cards GeForce GTX 260 June 26, 2008 G200 65 1.4 576 PCIe x16 2.0 896 192:64:28 576 1242 1998 16.128 36.864 111.9 GDDR3 448 32x14 10 3.1[2] 715 182 GeForce GTX 260 216SP[3] September 16, 2008 G200 65 1.4 576 PCIe x16 2.0 896 216:72:28 576 1242 1998 16.128 41.472 111.9 GDDR3 448 32x14 10 3.1[2] 805 182 GeForce GTX 260 216SP 55nm[4] December 22, 2008 G200b 55 1.4 470 PCIe x16 2.0 896 216:72:28 576 1242 1998 16.128 41.472 111.9 GDDR3 448 32x14 10 3.1[2] 805 171 GeForce GTX 275[5] April 2, 2009 G200b 55 1.4 470 PCIe x16 2.0 896 240:80:28 633 1404 2268 17.724 50.6 127.0 GDDR3 448 32x14 10 3.1[2] 1010.88 219 GeForce GTX 280 [6][7] June 17, 2008 G200 65 1.4 576 PCIe x16 2.0 1024 240:80:32 602 1296 2214 19.264 48.16 141.7 GDDR3 512 32x16 10 3.1[2] 933 236 GeForce GTX 285 [8] [9] January 15, 2009 G200b 55 1.4 470 PCIe x16 2.0 1024 240:80:32 648 1476 2484 20.736 51.84 159.0 GDDR3 512 32x16 10 3.1[2] 1062.72 183 GeForce GTX 295 January 8, 2009 G200b 55 2x 1.4 2x 470 PCIe x16 2.0 2x 896 2x 240:80:28 576 1242 1998 2x 16.128 2x 46.08 2x 111.9 GDDR3 2x 448 32x14 10 3.1[2] 1788.48 289 Future
According to Expreview and other sources, Nvidia plans to release a single PCB version of the GTX 295 graphics card. The performance specifications of the new card will be identical to the dual PCB version. Improvements however, are speculated to be better power consumption, better thermal performance as well as cheaper manufacturing costs. The single PCB version of the GTX 295 is expected to be released in late May, 2009. The first confirmed model will be from Inno3D and is named the "GTX 295 Platinum Edition". EVGA will also release a single PCB model of the GTX 295 nicknamed the "GTX 295 Co-op Edition".[10]
At CES 2009, Nvidia announced the low-end mobile version of the GTX 200 series, known as the G 100M series. Preliminary benchmarks have found that some chips are up to 50% faster than the GeForce 9 that precede them. The first three chips are the G 105M which replaces the 9300M GS, the G 110M which compares to the recently announced 9400M G, and the GT 130M which replaces the 9600M GT.
Nvidia has also released OEM budget and mainstream cards under the 100 series with similar naming schemes to the mobile cards. Current cards include the G 100, GT 120, GT 130 and GTS 150. The GT 120 is a rebranded 9500 GT with improved thermal designs while the GT 130 is a modified version of the 9600 GSO. The GTS 150 is an OEM version of the GTS 250 with some slight changes.
Nvidia also have announced plans to launch a revision and rebrand of the 9800 GT (8800 GT) which is based on the G92 chipset, slated for an April release called the GTS 240. The GTS 240 was to have been an overclocked version of the 9800 GT but there are reports that the GTS 240 has been cancelled. The GTS 250 is basically a 55nm G92b based 9800 GTX+ GPU on a new P361 PCB and internally Nvidia calls it D10P2. The differences are mainly on the power design; the core and ram speeds are identical to the 9800 GTX+ but power consumption has been lowered. All of the GTX 200 series cards support OpenGL 3.0.
Even more recently, Nvidia has launched the high-end mobile version of the GTX 200 series. The first two chips are the GTX 260M and the GTX 280M, which are fabricated at a smaller 55nm process allowing for 128 stream processors, up from the 9800M GTX's maximum of 112 stream processors. Also, Nvidia has released more midrange versions of the GT200s for mobiles. These include the GT 210M, GT 230M, GT 240M, GTS 250M, and GTS 260M. It is hard to place where these cards will slot in compared to the lower end GT100Ms, but it is believed these mobile cards will eventually completely erase the GT100s.
Nvidia will be launching a GTX 300 series GPU as its flagship model. The GTX 300 series is projected to launch in Q4 of 2009, with the first products to be fabricated on TSMC's 45 nanometer manufacturing process. It is rumored to be DirectX 11 compatible, and like AMD's recent GPUs, use GDDR5 RAM to reduce manufacturing cost. According to information released by The Bright Side of News on April 22 2009, the G300 architecture will feature a cGPU design. The cGPU is much closer to traditional CPUs and will be radically different from previous generations. The G300 chipset will use MIMD instead of SIMD.
0 comments:
Post a Comment