Direct3D 10.1: What’s new
Let’s be clear right from the start; the new things brought by this new API aren’t revolutionary. Direct3D 10 was a big makeover and as always with such endeavors, there are small errors. Thus Direct3D 10.1 must be seen as an incremental update, correcting, thanks to time and distance, small holes in the previous API, and bringing a few add-ons in order to erase some of the restrictions that still existed.
All the improvements may be summed up in three categories:
- Stricter specifications in order to limit discrepancies between multiple implementations
- A handful of new features
- A clear focus on rendering quality and more precisely, antialiasing
Stricter specifications
Microsoft has taken advantage of Direct3D 10.1 to make its API even more orthogonal by cancelling particular situations; hence it is now compulsory to support FP32 textures’ filtering, while it was only optional in Direct3D 10 (though all Direct3D 10 GPUs from both manufacturers were already supporting it anyway). In a similar fashion, blending in 16 bits integer buffers is now obligatory when its implementation was only a choice with Direct3D 10.
Microsoft has also strengthened specifications with regard to computational precision, whether in blending or in-shaders operations. Thus, many operations (addition, subtraction, multiplication and division) are now in line with the IEEE-754 norm, which, one must admit, isn’t really exciting for gamers, but will surely please researchers fond of GPGPU.
New features
Microsoft managed to be reasonable when it came to the new API add-ons. Developers are still assimilating the new features brought by Direct3D 10 and figuring what they can really do with them. It was, therefore, out of question to drown them every year under the flow of new add-ons.
First of all, we find Cube Map Arrays. With Direct3D 10, Microsoft had introduced Texture Arrays, tables of textures that could be indexed directly in the shaders. At first, Texture Arrays resemble 3D textures, which have been around for a long time, but practically, their behavior is very different. Ergo, when accessing an element of a 3D texture, a filtering occurs between the different layers, which is normal as a 3D texture is voluminal. On the contrary, textures stocked in a table may not have any connection between them. Consequently there isn’t any filtering between neighboring elements. Furthermore, when using mipmapping, a 3D texture is divided by 2 according to its 3 dimensions, which isn’t the case with Texture Arrays; if the different textures composing it see their size decreasing, the size of the table remains the same.
Direct3D 10.1 generalizes those Texture Arrays by adding support for Cube Maps tables whereas, until now, only 1D and 2D texture tables were supported.

Shader Core wise, Direct3D 10.1 introduces Shader Model 4.1 which brings a couple of new things like the Gather-4, which is another name for Fetch-4 (introduced with ATI’s previous generation of cards). To quickly refresh your memory, this instruction allows retrieving 4 unfiltered elements of a single-channel texture with just one texture fetch, which permits a more efficient implementation of personalized filters in shaders.
Another instruction added to Shader Model 4.1 enables it to recuperate the level of detail (mipmap level) during a texture sampling. Microsoft has also upgraded certain limits, especially the number of vertex shaders’ input and output elements as we go from 16 vectors of 128-bit (4 floating simple precision) to 32.
With regard to blending, we’ve already mentioned the new supported format: Int. 16, but it’s not the only new thing; Direct3D 10.1 now enables specification of independent blending modes during a simultaneous rendering in more than one buffer (MRT: Multiple Render Targets).
- Previous page Direct3D 10.1: Incompatible?
- Next page Direct3D 10.1: Quality, practically
- BIOS Flash - Overclock Your Graphics Card in 5 Minutes
- Six Graphics Cards with Luxury Trimmings
- Workstation-Shootout: ATi FireGL V7600 vs. Nvidia Quadro FX 4600
- AMD HD 3800 To Support DX 10.1
- Nvidia's GeForce 8800 GT Reviewed
- DirectX 10 Shootout: Geforce 8x00 vs. Radeon 2x00
- DirectX 10 Cards on a Budget
- The Best Gaming Graphics Cards For Your Money: October 2007
- Can Integrated Graphics Cut It For Gaming Or HTPC?
- ATI's Radeon 2600 XT Remixed


Personally I'd be happy with that as it means my £400+ investment will last me a good number of years.
If you're disappointed that there's games you can't play I have a 6800 Ultra I'll happily swap for your 8800 GTX
:|
I have an 8800GTX SLI system and I struggle with Crysis on medium settings @2560x1600.
I'm waiting for something faster... whether it is from ATI or nVidia.
ATI continue to disappoint.
On a more important note: where are the Crossfire and SLI scores? The great thing about these new cards (both the 8800GT and the 3850/3870) are the fact that you're getting what, just months ago, was enthusiast-level performance for mainstream-level pricing. This makes SLI and Crossfire immensely much more affordable than they have ever usefully been before.
Previously it was always the case that you got better price/performance from a single high-end card than you got from two mid-range ones. Now, for the first time, that may no longer be true: 3850s in Crossfire might even outperform 8800GTX some of the time, and they're actually *cheaper* than single GTX.
So, come on: where are the benchmarks?
Finally, your noise level measurements are obviously flawed: you've got a 43dB noise floor, resulting from components other than the graphics card, or possibly from stuff going on outside the case. So it doesn't matter how quiet the GPU fan goes, you'll always read ~43dB. The cooler on the 3850 is rated at just 31dB, which is *miles* below the noise level you get from an 8800GT. Your figures are misleading.
At least I want to know if it's as good as the 1900 at crunshing lifesaving data!
With AMD/ATI going down the toilet Nvidia is not getting enough pressure to move on the next generation (1Gb+ cards with enough horsepower to handle HD gaming). Rebranding 2xxx cards as 3xxx is pretty desperate!! That is the bottom line... Even with VERY deep pockets you will still struggle to get high quality textures running @1920x1200 (native 1080p the true resolution of BD and HDDVD disks).
I have a feeling that AMD/ATI may not be around much longer. If a company isn't diversified (like Sun) then a failure in your core business means you are pretty screwed. If ATI didn't have products like the X1950Pro they would be in real trouble already...
nicolasb -> Previous comment about Crossfire. THG said the driver was unstable for the new 3xxx cards in the introduction. Perhaps you have problems reading??
Ah well, have to wait till 2009 for that monitor upgrade!!
Bob
I look forward to seeing what kind of scaling these will produce, because that does seem to be their main selling point. As the previous guy said, you can get 2 of these cards for less than a GTX, and potentially equal perfomance, while still leaving room for another 2 cards =)
The HD 2900 XT's scaling results were actually pretty impressive, SLI showing a 50% boost at best, while crossfire showing as good as 90% in some games.