Table time
Knowing that the GeForce GTX 285 is a die-shrunk successor to the GeForce GTX 280, we'll get stuck straight into a tabulated comparison. Those interested in finding out what makes a GTX 200-series GPU tick can refer to Tarinder's prior in-depth analysis.
| Graphics cards | NVIDIA GeForce GTX 295 | NVIDIA GeForce GTX 285 1,024MB |
NVIDIA GeForce GTX 280 1,024MB | NVIDIA GeForce GTX 260 896MB (new) | AMD Radeon HD 4870 X2 2,048MB | AMD Radeon HD 4850 X2 2,048MB | AMD Radeon HD 4870 512MB | AMD Radeon HD 4850 512MB |
|---|---|---|---|---|---|---|---|---|
| PCIe | PCIe 2.0 | |||||||
| GPU(s) clock | 576MHz | 648MHz | 602MHz | 576MHz | 750MHz | 625MHz | 750MHz | 625MHz |
| Shader clock | 1,242MHz | 1,476MHz | 1,296MHz | 1,242MHz | 750MHz | 625MHz | 750MHz | 625MHz |
| Memory clock (effective) | 1,998MHz | 2,484MHz | 2,214MHz | 1,998MHz | 3,600MHz | 1,986MHz | 3,600MHz | 1,986MHz |
| Memory interface and size | 448-bit (per GPU), 1,792MB, GDDR3 | 512-bit, 1,024MB, GDDR3 | 512-bit, 1,024MB, GDDR3 | 448-bit, 896MB, GDDR3 | 512-bit (2x 256-bit), 2,048MB, GDDR5 | 512-bit (2x 256-bit), 2,048MB, GDDR3 | 256-bit, 512MB, GDDR5 | 256-bit, 512MB, GDDR3 |
| Memory bandwidth | 223.8GB/sec | 159GB/sec | 141.7GB/sec | 111.9GB/sec | 230GB/sec | 127GB/sec | 115GB/sec | 63.5GB/sec |
| Manufacturing process | TSMC, 55nm | TSMC, 55nm | TSMC, 65nm | TSMC, 65nm | TSMC, 55nm | TSMC, 55nm | TSMC, 55nm | TSMC, 55nm |
| Transistor count | TBC | TBC | 1,408M | 1,408M | 1,930M | 1,930M | 965M | 965M |
| Die size | TBC | TBC | 576mm² | 576mm² | 520mm² (2 x 260mm²) | 520mm² (2 x 260mm²) | 260mm² | 260mm² |
| Double-precision support | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes |
| DirectX/ Shader Model | DX10, 4.0 | DX10, 4.0 | DX10, 4.0 | DX10, 4.0 | DX10.1, 4.1 | DX10.1, 4.1 | DX10.1, 4.1 | DX10.1, 4.1 |
| Vertex, fragment, geometry shading (shared) | 480 FP32 scalar ALUs, MADD dual-issue + MUL (unified) | 240 FP32 scalar ALUs, MADD dual-issue + MUL (unified) | 240 FP32 scalar ALUs, MADD dual-issue + MUL (unified) | 216 FP32 scalar ALUs, MADD dual-issue + MUL (unified) | 1,600 FP32 scalar ALUs, MADD dual-issue (unified) | 1,600 FP32 scalar ALUs, MADD dual-issue (unified) | 800 FP32 scalar ALUs, MADD dual-issue (unified) | 800 FP32 scalar ALUs, MADD dual-issue (unified) |
| Peak GFLOPS | 1,788 | 1,063 | 933 | 805 | 2,400 | 2,000 | 1,200 | 1,000 |
| Data sampling and filtering | 160ppc address and 160ppc bilinear INT8/80ppc FP16 filtering, max 16xAF | 80ppc address and 80ppc bilinear INT8/40ppc FP16 filtering, max 16xAF | 80ppc address and 80ppc bilinear INT8/40ppc FP16 filtering, max 16xAF | 72ppc address and 72ppc bilinear INT8/36ppc FP16 filtering, max 16xAF | 80ppc address and 80ppc bilinear INT8/40ppc FP16 filtering, max 16xAF | 80ppc address and 80ppc bilinear INT8/40ppc FP16 filtering, max 16xAF | 40ppc address and 40ppc bilinear INT8/20ppc FP16 filtering, max 16xAF | 40ppc address and 40ppc bilinear INT8/ 20ppc FP16 filtering, max 16xAF |
| Peak fillrate Gpixels/s | 32.256 | 20.736 | 19.264 | 16.128 | 24 | 20 | 12 | 10 |
| Peak Gtexel/s (bilinear) | 92.2 | 51.84 | 48.16 | 41.472 | 60 | 50 | 30 | 25 |
| Peak Gtexel/s (FP16, bilinear) | 46.1 | 25.92 | 24.09 | 20.736 | 30 | 25 | 15 | 12.5 |
| ROPs | 56 | 32 | 32 | 28 | 32 | 32 | 16 | 16 |
| Peak TDP (claimed) | 289 | 183 | 236 | 182 | 289 | - | 160 | 110 |
| Power connectors (default clocked) | 8-pin + 6-pin | 6-pin + 6-pin | 8-pin + 6-pin | 6-pin + 6-pin | 8-pin + 6-pin | 8-pin + 6-pin | 6-pin + 6-pin | 6-pin |
| Multi-GPU | SLI - quad | SLI - three-board | SLI - three-board | SLI - three-board | CrossFire - two-board | CrossFire - two-board | CrossFire - four-board | CrossFire - four-board |
| Outputs | 2 x dual-link DVI w/HDCP, 1 x HDMI | 2 x dual-link DVI w/HDCP, native HDMI 5.1 (via S/PDIF) | 2 x dual-link DVI w/HDCP, HDMI 7.1 (native, on GPU) | 4 x dual-link DVI w/HDCP, HDMI 7.1 (native, on GPU) | 2 x dual-link DVI w/HDCP, HDMI 7.1 (native, on GPU) | 2 x dual-link DVI w/HDCP, HDMI 7.1 (native, on GPU) | ||
| Hardware-assisted video-decoding engine | NVIDIA's PureVideo HD - full H.264 decode and partial VC-1 decode, plus dual-stream decode | AMD UVD 2 - full H.264 and VC-1 decode, plus dual-stream decode | ||||||
| Reference cooler | dual-slot | dual-slot | dual-slot | dual-slot | dual-slot | dual-slot | dual-slot | single-slot |
As expected, the transition to half-node 55nm provides notable benefits across the board. The GeForce GTX 285's maximum power draw is listed at 183W, significantly lower than the 236W consumed by the already-ageing and power-hungry GeForce GTX 280.
Consequently, the card is comfortably able to raise frequencies without so much as breaking a sweat. We see GPU clock speed bumped up from 602MHz on the GeForce GTX 280 to 648MHz on the GeForce GTX 285, with shader and memory clocks rising to 1,476MHz and 2,484MHz, respectively.
It's a healthy increase, sure, but it's worth noting that it isn't a whole lot different in terms of frequencies when compared to a heavily-overclocked GeForce GTX 280, ala BFG's OCX. On the other hand, the new-and-improved GeForce GTX 280 should reach those previously-overclocked speeds with ease, whilst remaining cool and hopefully quiet, too.
Aside from GPU, shader and memory frequencies, not a whole lot else has changed. The GPU has access to 1,024MB of GDDR3 memory via a 512-bit interface, providing 159GB/sec of bandwidth, and it becomes the first stock-clocked single-GPU offering from NVIDIA to break the 1,000 GFLOPS mark.
Further examining the numbers, we see that NVIDIA's range-topping single-GPU card is capable of a bilinear-filtering capacity of 51.84Gtexel/s, that's more than a dual-GPU Radeon HD 4850 X2.
For the well-off SLI faithful, NVIDIA's Big Bang II drivers open a world of mind-boggling combinations. A GeForce GTX 295 and a GeForce GTX 285 is likely to be a popular combination in ultra-high-end systems, with the latter GPU dedicated solely to PhysX.
With an estimated MSRP of around £315, however, the GeForce GTX 285 is far and away the most expensive single-GPU solution on the market today. Is it worth it?
