It's been a six months wait, but Fermi is finally here. We've reviewed the GeForce GTX 480 and found that while it is astonishingly fast, it suffered from heat and power consumption issues. This view was echoed by many who have had chance to test the card too.
In football, they say the best strikers hunt in pairs; it's the same with graphics cards too. When NVIDIA launched their new GTX 400 series of cards, the line-up consisted of the GeForce GTX 480 and GTX 470. Being bigger and more powerful, the GeForce GTX 480 naturally hogged the limelight. So today we are going to take a look at its overshadowed sibling and see what it has to offer.
While the GeForce GTX 480 represents NVIDIA's flagship and the absolute pinnacle of graphics performance, the GeForce GTX 470 is a little humbler, positioned by NVIDIA as a slightly more affordable price/performance leader. To put it simply, it is an attempt to compel would-be Radeon HD 5870 and HD 5850 buyers to think twice.
To achieve that, NVIDIA is quick to associate the GeForce GTX 470 to the GeForce GTX 480 for they hope that some of the halo effect in regards to the GeForce GTX 480's blazing performance gets trickled down to the GeForce GTX 470, and in truth, the two SKUs do share much in common.
As a shrunken down GeForce GTX 480, the GeForce GTX 470 is mostly identical to its bigger sibling save for the reduced streaming multiprocessor (SM) count – while its big brother has 15, the GeForce GTX 470 has to make do with one less. Overall, this means it has 448 CUDA cores, 56 texture units, 40 raster operating units and a slightly narrower 320-bit wide memory interface (which also means a smaller frame buffer size too). It also gets lower clock speeds: 607MHz at the core, 1215MHz at the shaders and 3348MHz DDR for the memory. And as you can see from the graph below, this represents quite a big hit as far as paper specifications are concerned. Read on to see how this translates in our performance testing segment.
Here's how the GeForce GTX 470 measures against comparable SKUs.
NVIDIA GeForce GTX 470 1320MB GDDR5
|NVIDIA GeForce GTX 480 1536MB GDDR5||ATI Radeon HD 5870 1GB GDDR5||ATI Radeon HD 5850 2GB||NVIDIA GeForce GTX 285 1GB GDDR3||NVIDIA GeForce GTX 295 1729MB GDDR3|
|Core Code||GF100||GF100||Cypress XT||Cypress Pro||GT200||GT200|
|Transistor Count||3200 million||3200 million||2150 million||2150 million||1400 million||2800 million|
|Stream Processors||448 Stream Processors||480 Stream Processors||1600 Stream processing units||1440 Stream processing units||240 Stream Processors||480 Stream Processors|
|Stream Processor Clock||1215MHz||1401MHz||850MHz||725MHz||1476MHz||1242MHz|
|Texture Mapping Units (TMU) or Texture Filtering (TF) units||56||60||80||72||80||160|
|Raster Operator units (ROP)||40||48||32||32||32||56|
|Memory Clock||3348MHz GDDR3||3696MHz GDDR3||4800MHz GDDR5||4000MHz GDDR5||2484MHz GDDR3||1998MHz GDDR3|
|DDR Memory Bus||320-bit||384-bit||256-bit||256-bit||512-bit||448-bit|
|PCI Express Interface||PCIe ver 2.0 x16||PCIe ver 2.0 x16||PCIe ver 2.0 x16||PCIe ver 2.0 x16||PCIe ver 2.0 x16||PCIe ver 2.0 x16|
|Molex Power Connectors||2 x 6-pin||1 x 6-pin, 1 x 8-pin||2 x 6-pin||2 x 6-pin||2 x 6-pin||1 x 6-pin, 1 x 8-pin|
|Multi GPU Technology||SLI||SLI||CrossFireX||CrossFireX||SLI||SLI|
|DVI Output Support||2 x Dual-Link||2 x Dual-Link||2 x Dual-Link||2 x Dual-Link||2 x Dual-Link||2 x Dual-Link|
|HDCP Output Support||Yes||Yes||Yes||Yes||Yes||Yes|
|Street Price||Launch Price: US$349||Launch Price: US$499||~US$399||~US$259||~US$350||~US$500|