6200 TurboCache - IntroductionIntroduction
Not that long ago, nVidia announced its value orientated GeForce 6 video card, entitled the GeForce 6200 and value was definitely the key to this card. Designed on the PCI Express bus with a 128-bit memory and GPU bus, you certainly aren't going to find this card in the Doom 3 enthusiast machines, however, you are most likely to see this card being used in the low-end systems from Dell, HP and Compaq with their I9xx series PC's.Now nVidia has taken a bit of a side turn with its latest instalment to the 6200 line. With the PCI Express bus for graphics, a whole new way of addressing memory faster has come. AGP even at its full 8x speed simply can't keep up. AGP 8x only gives a maximum of 2.1GB/s, with a 90/10 split in bandwidth, you are receiving more than you transmit on the AGP protocol. While good for cards like dedicated video cards, onboard graphics simply were not an option, as the limited bandwidth of the AGP bus couldn't handle the memory transfers to system RAM.PCI Express on the other hand has its superior 50/50 split of the data. In a PCI Express x16 slot there is a total of 8GB/s transfer, 4GB for transmit and 4GB/s for receiving. With PCI Express now comes with the option for storing additional texture data in memory, and nVidia has the first video card to do it.The new "TurboCache" as nVidia calls it makes full use of the PCI Express bus to use system memory as its frame buffer, with a maximum of 64MB of onboard cache memory to store local decoded data.Today we pit the reference GeForce 6200 TubroCache model with 32MB of onboard memory against the reference 6200 video card to see just what is on offer.
6200 TurboCache - The ArchitectureThe TurboCache Architecture
When nVidia brought the original 6200 core out, the simple fact was that this video processor was simply a 6600 core with four of the pixel pipelines disabled but the 6200 TurboCache (aka TC) is a totally different kettle of fish. The NV44 core is actually a full redesign in order to remove the additional memory channel that gives the 6200 its 128-bit memory interface. Also in order to reduce the price by reducing the die side, the extra four pipelines that aren't needed are removed to save on space and silicon usage.
Apart from the removed unused components, the TC uses the same memory management that Intel uses for its onboard graphics, that being Dynamic Memory Assignment. The TurboCache 16 and TurboCache 32 can have up to a maximum of 128MB frame buffer. This means that a 16MB model will use 112MB and the 32MB model will use 96MB system memory in order to make up the full 128MB - the system automatically assigns a total of 128MB for the video card. The 64MB model can have up to 256MB frame buffer, sucking 192MB of system memory. Like Intel, nVidia has a MMU or Memory Management Unit that interfaces with the Forceware drivers. When the system is running only Windows or any 2D application, only the onboard cache memory is used, leaving the system memory free for the CPU to use. When a 3D application is loaded, the MMU removes the extra memory from the system RAM in order to increase the framebuffer size, when the application finishes, the memory is released back to the system to use as usual.Now we have seen this technology before used by nVidia with the nForce 2 onboard graphics, VIA with its S3 integrated graphics chipset as well as Intel on its Express graphics system, however, performance has been somewhat lax and this has been because of two major issues - Firstly the graphics core on the Intel and VIA systems has been extremely value based, the only real solution that showed promise was the nForce 2 with the GeForce 4MX controller built in, on graphics cards this chip produced reasonable graphics scores however the major problem is the memory bandwidth.System memory is extremely slow compared to that of the video cards. Graphics cards use up to a 256-bit memory bus delivering bandwidths over 30GB/s, where as system memory even to this point using DDR-2 can only go as high as 8.5GB/s. Accessing this memory is also an extremely painful affair. AGP even at its full 8x capabilities can only handle 2.1GB/s, with some of the bandwidth being used to transfer data to the GPU processor, leaving around 1GB/s free when you count the overheads. This means that you have to push all this data to and from system memory using about 1GB/s and this is simply not going to give the greatest performance.The TC uses the new PCI Express x16 link to transfer data to the GPU as well as access system memory. Using a full duplex 4GB/s (8GB/s total) you are looking at about 6GB/s of usable bandwidth, while this isn't as good and the 6200 with dedicated memory, it certainly does give it a bit more to play with when it comes to transferring data to and from the card and memory.
6200 TurboCache - The CardnVidia 6200 TurboCache Reference Card
The nVidia reference card is actually a lot smaller than that of the 6200 dedicated memory card, simply due to the reduced size of the die and the removal of the memory chips. One thing that was interesting was the fact that nVidia only needs to use a passive cooling solution. When testing, even under extreme 3D applications, the heatsink only became warm; leading us to hope that overclocking would be possible on this card. On the I/O panel there are no differences between the TC and dedicated card. The card by default supports a built in TV output encoder along with a HDTV support chip.
The core we received on the reference card is still in its final beta stage. The size of the die is no bigger than that of an Australia 10c coin, or a US dime. This shows just how small nVidia has been able to make this core by removing the unused components rather than just disabling the additional pixel pipelines and memory channels.
The card we received was the 32MB model - both the 16MB and 32MB versions of the TC use Samsung 2ns F-BGA GDDR memory modules. On the 32MB model there are two chips, one on the front and one of the back of the card and the 16MB model only has a single chip on the front. The 64MB models have four modules, two front and two on back but use the older TSOP-II design to save on money. The 32MB uses a 64-bit bus to connect the modules, while the 16MB only uses a 32-bit bus.Overclocking
While we attempted to overclock the card, we ran into a huge amount of trouble with our reference drivers.When Coolbits was installed, Windows would continually lock up, leading us to believe that the drivers are simply not really ready for overclocking the 6200TC but when we get a new card and drivers we will come back to this section and re-visit.
6200 TurboCache - Benchmarks - Test System Setup and 3DMark03Test System SetupProcessor
: Intel Pentium 4 560 (800MHz FSB) (Supplied by Intel
: 2x 512MB DDR2-533 Micron Hard Disk
: 2x Maxtor Maxline III 250GB (RAID 0)Motherboard
: Intel reference I915G (Supplied by Intel
: Microsoft Windows XP SP2Drivers
: nVidia Forceware 70.46 and DX9c3DMark03Version and / or Patch Used:
Build 350Developer Homepage: http://www.futuremark.comProduct Homepage: http://www.futuremark.com/products/3dmark03/Buy It Here
3DMark03 is the latest version of the highly favored 3DMark series. By combining full DirectX9.0 support with completely new tests and graphics, 3DMark03 continues the legacy of being industry standard benchmark.Please Note: Due to recent events with the 3DMark03 series, we are adding results purely for those who are still in favor of 3DMark03. These results should not be taken too seriously and are only added for interest sakes.
Here we can see that the TurboCache model is able to outperform the Intel onboard GMA900, however, it falls quite short of the 6200 with dedicated 128MB of memory.
6200 TurboCache - Benchmarks - 3DMark053DMark05 Version and / or Patch Used:
Build 110Developer Homepage: http://www.futuremark.com Product Homepage: http://www.futuremark.com/products/3dmark05/ Buy It Here
3DMark05 is the latest version in the popular 3DMark "Gamers Benchmark" series. It includes a complete set of DX9 benchmarks which tests Shader Model 2.0 and higher. For more information on the 3DMark05 benchmark, we recommend you read our preview here
Here the TurboCache falls even further behind the 8 ball.
6200 TurboCache - Benchmarks - Doom 3Doom 3Version and / or Patch Used:
UnpatchedTimedemo or Level Used:
Custom TimedemoDeveloper Homepage: http://www.idsoftware.com Product Homepage: http://www.doom3.comBuy It Here
Doom 3 is the latest game to hit our test lab and is one of the most intensive games to dates. With our own custom time demo we are able to give a realistic rating on what kind of FPS you will be achieving.For more information on benchmarking Doom 3 we recommend you check out our extensive article regarding it here
Doom 3 simply isn't playable on the TurboCache at all at this resolution.
6200 TurboCache - Benchmarks - Half Life 2Half Life 2Version and / or Patch Used:
UnpatchedTimedemo or Level Used:
Custom TimedemoDeveloper Homepage: http://www.valvesoftware.com Product Homepage: http://www.half-life2.comBuy It Here
By taking the suspense, challenge and visceral charge of the original, and adding startling new realism and responsiveness, Half-Life 2 opens the door to a world where the player's presence affects everything around him, from the physical environment to the behaviors even the emotions of both friends and enemies.We benchmark Half Life 2 with our own custom timedemos as to avoid possible driver optimizations using the "record demo_name" command and loading the timedemo with the "timedemo demo_name" command - For a full list of the commands, click here
HL2 is playable with the TC but remember the score listed is an average so it will drop into unplayable levels during certain points of the game.
6200 TurboCache - Benchmarks - Far CryFar CryVersion and / or Patch Used:
1.3Timedemo or Level Used:
DefaultDeveloper Homepage: http://www.crytek.comProduct Homepage: http://www.farcrygame.comBuy It Here
There is no denying that Far Cry is currently one of the most graphic intensive games on the market, utilizing PS2.0 technology (the latest versions support Shader Model 3.0 with DX9c) and offering an exceptional visual experience there is no denying that even some of the faster graphics cards struggle.
Far Cry at 1024x768 is only just playable but moving to 1600x1200 simply means death to the cards frame rate.
6200 TurboCache - Final ThoughtsFinal Thoughts
After all is said and done, TurboCache definitely doesn't live up to its name. Designed as a replacement for the Intel I915G graphics core, its power over this chip is somewhat better, however, the price to add this card to a simple office system would be too great to warrant the use of this card, as the Intel GMA900 is simply able to cope quite easily with these tasks.Where this chip would come in handy would be built into the nVidia NF4 or NF5 chip as a graphics competition to the Intel GMA900, as the performance of its DX9 engine as well as all the features that the GeForce 6 series brings would make this chipset a much more attractive option for OEM and budget systems.With the price of the 6200 with a dedicated 128MB of GDDR memory running at a 128-bit bus and much higher bandwidth being quite competitive, it's hard to justify the use of the TurboCache model. On the other hand though, our stats through our shopping comparison website
show the 6200 Turbo Cache being around 40% cheaper than the 6200 with dedicated memory which may prove as a better option for some users.- Pros
Cheaper than 6200 with dedicated memoryGeForce 6 ArchitectureDX9.0c compliant- Cons
Limited onboard memoryUses system memory for frame bufferNo compression technology to increase the performance of the DRAMRating - 7 out of 10