Intel Graphics Media Accelerator 900 and Intel 915G: New Generation of Integrated Graphics

by Tim Tscheblockov
07/12/2004 | 09:12 AM

Intel’s contribution into the sphere of integrated graphics has been rather poor compared to the mighty rivals like RADEON 9x00 PRO and NVIDIA nForce2. The speed and functionality of the Extreme Graphics 2 core from Intel is no match for the current integrated GPUs from NVIDIA and ATI – our recent review of contemporary integrated chipsets confirmed this point.

In spite of the alluring name, Extreme Graphics 2 is obsolete with its one pixel pipeline and two texture-mapping units (I won’t mention VIA or SiS today – their currently available integrated graphics cores are downright hopeless). It is like the long-forgotten TNT chipset from NVIDIA. Like the TNT, Extreme Graphics 2 has no hardware support of T&L as well as shaders.

Intel seemed to give little thought to that; Intel’s integrated chipsets never lose to their competitors in other capabilities, while high-performance integrated graphics must have been less interesting for the company.

This situation has changed after the arrival of LGA755 CPUs and a new family of PCI Express-supporting chipsets: the i915G chipset boasts a new integrated graphics processor called Intel Graphics Media Accelerator 900, and this is the first integrated chipset to have hardware support of DirectX 9 shaders.

Now, let’s discuss this and other facts in more detail.

Intel Graphics Media Accelerator 900: Functionality and Features

So, Graphics Media Accelerator 900 is an integral part of the Intel 915G chipset, which supports the PCI Express bus and DDR2 memory. We tested the i915G chipset using a D915GUX mainboard from Intel:

Data transfers between the graphics core and memory, both on standalone graphics cards and with integrated chipsets, are performed in rather big chunks, so higher memory frequency is more important than the timings. That is, the use of DDR2 memory, which works at higher clock rates compared to DDR SDRAM, provides an additional performance reserve to the integrated graphics processor: as usual, Graphics Media Accelerator 900 uses some part of the system RAM as graphics memory.

The i915G features a dual-channel memory controller, and ideally, when there’s no load from the CPU, GMA 900 can exchange data with the “graphics memory” at a speed of up to 8.5GB/s. The 128-bit “graphics memory bus” and 533MHz memory frequency are good parameters even if we compare them to mainstream discrete graphics.

Let’s now focus on the graphics core alone. The following table compares the two generations of integrated graphics from Intel:

The table doesn’t include the characteristics of the integrated GPUs as concerns video playback and output, but it is anyway clear that Graphics Media Accelerator 900 is not a development of the existing architecture, but a new GPU from ground up.

Some points need comments:

• The core now has four pixel pipelines. To be more exact, GMA 900, like the previous Extreme Graphics 2 core, has only one pixel pipeline, but unlike its predecessor, it processing four pixels at a time – all modern graphics processors use the same organization of the pixel pipework.
• GMA 900’s “four-pixel” pipeline has four texture-sampling units, equivalent to a scheme with four independent pixel pipelines with one texture-mapping unit per each. Graphics Media Accelerator 900 can render one texture on a pixel per cycle, and rendering of each next texture requires an additional cycle. That’s exactly how modern GPUs work.
• GMA 900 features hardware support of DirectX 9 pixel shaders. It means that modern applications using Shader Model 2.0 can start and run on a GMA 900 system without any problems or quality loss. Unfortunately, Intel didn’t publish yet any info about the supported calculation accuracy during execution of shaders, while special-purpose test utilities like Xbitmark, Shademark and others, as if conspiredly, refused to run on the i915G – they all require hardware support of DirectX 9 vertex shaders.
• The new graphics core from Intel has no hardware support of vertex shaders or T&L. All the geometry transformations are calculated by the central processor of the system. The company presents this as an efficient use of system resources and relies on the power of its processors – the user shouldn’t pay for a more complex graphics core if the CPU can handle geometry calculations all right. However, things are not so bright in reality: discrete graphics processors have long had hardware support of vertex shaders and their special-purpose vertex units are no inferiors even to the topmost Intel CPUs as concerns fast shader execution.
• Intel’s GMA 900 employs the tile-based architecture – “Zone Rendering Technology 3” is Intel’s term for it. This technology works like that:
  • Before drawing the image, the driver first waits till the application provides all the polygons necessary for the rendering. Then, for each tile (a “zone” in Intel’s terminology, it is a rectangular fragment of the image) lists of triangles that fully or partially cover it are produced.
  • When rendering a frame, the graphics processor renders tile after tile, using the polygon lists created at Step 1 as source data, until the entire frame is rendered.

This operation scheme has both advantages and shortcomings. The advantages include:

• The use of small fragments, tiles, allows for an efficient use of the GPU’s caches since small amounts of homogenous data are operated upon.
• Having drawn a tile, the GPU never turns back to it in the frame-creation process. Considering that a tile has a small size, the fragments of the frame buffer and the Z-buffer, corresponding to this tile, can be wholly loaded into the GPU’s cache. Thus, the graphics processor does all of its calculations “on-die”, using the cache, rather than system memory. After the tile is drawn, the contents of the tile frame-buffer and the Z-buffer are written into the system RAM. Caching of the frame and Z buffers allows alleviating the load on the memory bus by performing data transfers in larger blocks. This is most important for an integrated chipset, whose graphics core has to share the memory bus with the central processor.
• Intel’s GMA 900 has a special unit for checking the values of Z pixels. If the check says some group of pixels won’t be visible, it is excluded from further processing. This Z-checking helps GMA 900 to avoid performing unnecessary work – like texturing or shader execution – for invisible pixels and to be most efficient at rendering scenes with a high overdraw parameter, which reflects the level of overlapping of the objects (or the number of “redraws” of a pixel).

The disadvantages of a tile-based architecture are mostly related to how it processes geometry data:

• In order to create the polygon lists correctly, the tile-architecture graphics processor has to wait for all the geometry data, necessary to build a frame, to come in, and only then it starts rendering the scene. GPUs of the traditional architecture begin to process streams of geometry data and render the scene right after they start receiving the data.
• The need to sort the polygons and create lists for each tile badly conforms to the well-established stream-n-pipelined operation algorithm of vertex processors. This is probably the reason for GMA 900 to offer no hardware support of T&L and vertex shaders, while all the geometry data as well as the polygons sorting are performed by the central processor.
• Graphics Media Accelerator 900 doesn’t seem to have full-screen antialiasing. At least, the driver’s control panel doesn’t offer this function. Of course, FSAA is not a very important feature for an integrated graphics core, considering its overall low level of performance. However, it would come in handy in simple 3D games where the core would have some performance reserve.
• GMA 900 supports anisotropic texture filtering of up to 4x level. Anisotropic filtering cannot be combined with tri-linear filtering: the latter is disabled when you enable the former.
• GMA 900 supports Dynamic Video Memory Technology version 3.0. Thanks to DVMT, the system memory becomes “graphics memory” when it’s necessary and in the necessary amounts; it is flushed up for the needs of the OS after it is no longer in use by the GPU. Thus, the OS and the GPU share the system memory in the most efficient and balanced way.

  That’s how GMA 900 works with memory:

  The memory amount necessary for the graphics core is divided in two parts. The first and smaller part – Preallocated Memory – is the GPU’s domain; the operating system cannot use it and regards it as regular graphics memory. You can set up the size of this memory area in the BIOS into 1MB or 8MB.

  The other part is provided for GMA 900 by DVM Technology. Three DVMT modes are supported:

  • In the “Fixed” mode, a fixed-size fragment of the system memory is allocated to the graphics core. It can only be used by the graphics core; its size can be set to 64 or 128MB.
  • In the “DVMT” mode, the driver of the graphics core uses the system memory like any other OS component or application does. If a “heavy” 3D game starts up, requiring a lot of memory for textures, geometry data and so on, and there’re no other memory-hungry applications running, the required memory amount is automatically allotted to the graphics core. When the GPU doesn’t need the surplus memory, it automatically hands it over to the OS. The maximum amount of memory, given to the GPU in this mode, is 224MB (the preallocated memory included).
  • In the “Fixed+DVMT” mode, the graphics processor gets a fixed-size chunk of 64MB of memory (preallocated memory included) and up to 64MB of dynamically-allotted memory. This mode guarantees that at least 64MB of memory is available to the graphics core, with a possibility to increase this amount to 128MB, if necessary.

So, the new graphics processor from Intel is an ambiguous figure that combines an efficient tile-based architecture, support of DirectX 9 pixel shaders and flexible control over memory with such deficiencies as the lack of hardware support of T&L and vertex shaders, unavailable FSAA and high texture filtering modes (tri-linear plus anisotropic filtering).

Today I’m going to test Graphics Media Accelerator 900 and compare it to potential and actual competitors. The description of our testbed and testing methodology follows.

Testbed and Methods

The i915G-based system was configured as follows:

• Intel Pentium 4 Extreme Edition 3400MHz CPU (800MHz FSB);
• Intel D915GUX mainboard (Intel 915G chipset);
• 2x512MB Micron DDR2 SDRAM, 533MHz.

I’ll compare the i915G chipset with available integrated chipsets for Socket 479 and Socket A platforms that I reviewed in the previous article: ATI RADEON 9100 IGP, RADEON 9000 PRO IGP, SiS661 FX, Intel 865G, NVIDIA nForce2 IGP, SiS741 GX and VIA KM400. I tested these chipsets using a Pentium 4 3000MHz (800MHz FSB) and Athlon XP 3000+ (333MHz FSB) CPUs and 2x512MB TwinMOS PC3200 (CL2) memory.

Like in the previous review, I didn’t ask for the impossible from the integrated graphics by using extreme gaming modes. I just used the games’ medium and low image-quality settings in 800x600 and 1024x768 resolutions:

• The “Medium Quality” mode uses average graphics quality settings and 32-bit color depth of the frame buffer. This is a compromise between speed and image quality in games.
• The second or “Low Quality” mode uses the lowest graphics quality settings and 16-bit color (in games that allow setting this color depth) to achieve the maximum fps rates.

When running synthetic tests and games that use DirectX 9 shaders, we took the cheapest of the available DirectX 9-compatible graphics cards from ATI and NVIDIA: RADEON 9600, RADEON 9550 with a 64-bit memory bus, GeForce FX 5200 and GeForce FX 5200 with a 64-bit memory bus.

Unfortunately, PCI Express analogs of these cards were unavailable as of the time of our tests, so we tested AGP products – it is clear that the results of the cards will be mostly determined by the performance of their GPUs and memory, rather than by the speed of the CPU or the system overall since we used very powerful configurations.

The i915G-based mainboard doesn’t support the AGP, so we plugged those graphics cards into a differently configured system:

• AMD Athlon 64 3400+ CPU;
• ASUS K8V-SE mainboard;
• 2x512MB TwinMOS PC3200 CL2.5.

I’d like to emphasize the fact that the tested graphics cards vary greatly in their performance level among themselves: RADEON 9600/9550 compete with GeForce FX 5700/5700LE in the market, rather than with the GeForce FX 5200. However, we chose these cards since they are the cheapest products from ATI and NVIDIA with hardware support of DirectX 9 shaders and are potential rivals of the i915G on the transition to the PCI Express bus. My point is that you shouldn’t compare the cards among themselves: they are potential competitors to the i915G, not to each other.

Now, the testing environment is clear – let’s proceed to the benchmarks.

Synthetic Benchmarks: Pixel Performance

Thanks to the four pixel pipelines and increased clock rate, the pixel output rate and the texturing speed grew manifold on GMA 900 compared to the previous core, Extreme Graphics 2. The fill-rate tests of 3DMark 2001 SE confirm this fact:

Intel’s GMA 900 is very close to its maximum theoretical texturing speed, both when rendering one and several textures – the texturing speed is 80% and 96% of the maximum, respectively, in the hardest mode.

The share of read/write operations with the frame and Z buffers is much higher at single-texturing than at multi-texturing, so the tile-based GMA 900 processor, employing caching of the Z-buffer and the frame-buffer, should be similarly efficient at single- and multi-texturing. It is a notable fact that GMA 900 has a higher efficiency at multi-texturing, though, which is a trait of classic-architecture GPUs. At the same time, in spite of the limited memory bus bandwidth, this GPU is rather indifferent to the changes in the precision of the frame buffer, Z-buffer, which is a feature of tile-based processors.

Now let’s see the new graphics processor handling pixel shaders. Specialized test suites like Xbitmark or ShaderMark wouldn’t run on GMA 900, finding no hardware support of vertex shaders, so we’ll limit ourselves with the results of 3DMark 2001 SE and 3DMark03 only:

Like all modern graphics processors with hardware support of DirectX 9 pixel shaders, GMA 900 finds it no problem to do DirectX 8 shaders. It runs a simple DirectX 8 shader fast enough, being just a little slower than the RADEON 9600.

The efficiency of Graphics Media Accelerator 900 declines at rendering a scene with a more complex shader. Considering the difference in frequencies between the RADEON 9600 and GMA 900, I can say that GMA 900 is nearly twice slower. On the other hand, it keeps its advantage over the GeForce FX 5200.

Running a complex DirectX 9 pixel shader, rich in mathematical calculations, the new graphics core from Intel finds itself behind the GeForce FX 5200, not even mentioning the RADEON 9600/9550.

So, GMA 900 is quite efficient at texturing but execution of complex DirectX 8 and 9 pixel shaders doesn’t seem to be among its strong points.

Synthetic Benchmarks: Vertex Performance

Well, we can’t actually talk about vertex performance of Graphics Media Accelerator 900 itself: in Intel’s scheme all the geometry calculations are performed by the central processor. Intel relies on the might of its CPUs, and we’ve got a fast and very expensive one in our testbed, with 2MB of cache and 3.4GHz clock rate. In the opposite camp, we have ordinary middle and low-range standalone graphics cards on chips from ATI and NVIDIA.

Take note of a curious fact: the results of the graphics cards decline greatly as we switch from one to eight light sources, while the results of Graphics Media Accelerator 900 only go down by a third.

Both tests – with one and eight light sources – have the same number of polygons, and the small performance hit that GMA 900 suffers on turning on eight lights makes me suspect that GMA 900 spends more time on sorting the polygons, rather than on their transformation and lighting – the scene is polygon-rich, and “tying” a polygon to a tile involves a lot of calculations.

GMA 900 coupled with a Pentium 4 Extreme Edition executes DirectX 8 vertex shaders as fast as the GeForce FX 5200 does, at least in this test.

When it comes to advanced DirectX 9 vertex shaders, the Accelerator is twice slower than the slowest graphics cards from ATI and NVIDIA.

Overall, the geometry performance of Graphics Media Accelerator 900 (teamed with Intel Pentium 4 Extreme Edition CPU) doesn’t impress. We also see that the graphics core has problems with polygon-heavy scenes, and they are due to the time-consuming operations of sorting polygons by tiles, rather than due to a low speed of geometry processing by the CPU.

So, GMA 900 has displayed nothing exceptional compared to cheap DirectX 9-comaptible graphics cards in synthetic tests. Let’s see if this will also be so in real games, in comparison to graphics chipsets of the last generation.

Performance in Gaming Benchmarks

Unreal Tournament 2004 Demo

The new chipset from Intel runs Unreal Tournament 2004 Demo at the medium settings well enough, outperforming the i865G by a factor of 2.5 or 3 – it hits the level of the RADEON 9100 IGP and nForce2 IGP.

At the low graphics quality settings, enabled for the maximum speed, the results of the i915G seem to be limited by the speed of geometry processing and polygons sorting, since the chipset doesn’t practically lose its speed switching from 800x600 to 1024x768. Accordingly, the i915G is noticeably slower than the leader, the nForce2 IGP, in the first resolution, but matches it in the second.

Max Payne 2

The test scene from Max Payne 2 demands no extraordinary texturing speed, but likes hardware T&L. The results of the i915G don’t differ much in the two resolutions, so the non-standard approach to processing geometry is again a brake to GMA 900. As a result, Intel’s new GPU lost its leadership to the graphics cards and integrated chipsets from ATI and NVIDIA that have hardware T&L and vertex shaders support.

The situation doesn’t change as we switch to the “speedy” settings: again, GMA 900 is impeded by its geometry processing speed.

IL-2 Sturmovik: Aces

There are not very many polygons in Sturmovik at medium graphics quality settings, so the i915G does well here: a little slower than the RADEON 9100 IGP and a bit faster than the nForce2 IGP.

There are even fewer polygons in the scene at the speedy settings, so GMA 900 boasts all the advantages of a tile-based graphics processor, considerably outpacing the chipsets from ATI and NVIDIA in the 1024x768 resolution.

C&C Generals: Zero Hour

Even medium graphics quality settings of this game seem to be rendering more than two textures on some surfaces. In this case, the i915G and the RADEON 9100 IGP that support rendering of up to 8 and 6 textures per pass, respectively, receive an advantage over other integrated chipsets by drawing the scene in a single pass.

GMA 900 has a higher pixel performance than the RADEON 9100 IGP, but produces smaller numbers in this test, however. Its performance is about the same in the two resolutions, so once again geometry processing becomes the bottleneck of Intel’s new integrated graphics.

At the “speedy” settings, we have the leaders (RADEON 9100 IGP and Intel 915G) approached by the nForce2 IGP. This is because the number of texture layers in the landscape details diminishes at low graphics quality settings.

Serious Sam: The Second Encounter

The i915G outperforms the i865G and the chipsets from VIA and SiS, but loses to the integrated graphics as well as standalone graphics cards from ATI and NVIDIA.

We see the same leaders: the RADEON 9100 IGP and the nForce2 IGP, which is far ahead of the others.

Quake 3: Arena

The numbers in Quake 3: Arena are determined mostly by the fill-rate speed and the memory bus bandwidth, and these are the winning aspects of the GMA 900 architecture. As a result, the i915G leaves behind all of its integrated competitors as well as 64-bit versions of the standalone graphics cards in 1024x768.

The “fast” settings are on, and we see that the i915G suffers but a small performance hit on switching from 800x600 to 1024x768. Again, this is an indication that the performance of GMA 900 is limited by its geometry-processing speed.

Anyway, the nForce2 IGP suffers a greater performance hit on switching to 1024x768 and yields its lead to the i915G in the second resolution.

Far Cry

The “gaming tests” section of this review ends with the most visually advanced games that make an extensive use of DirectX 9 shaders. Far Cry employs DirectX 9 shaders, so we exclude the previous-generation chipsets from our tests, leaving only the graphics cards with GPUs from ATI and NVIDIA.

Intel Graphics Media Accelerator 900 suffers a bitter defeat. Considering that its results in the two resolutions differ but slightly, the problem is not in the speed of execution of pixel shaders. GMA 900 just finds itself smothered under the huge amount of polygons Far Cry throws at the graphics processor.

The situation improves considerably in the “speedy” mode, but the i915G is still slower than its rivals.

Halo

Halo is not generous in fine-tuning settings, most of them have two positions only: On and Off. That’s why I couldn’t select settings that would be “medium”. So we have two modes in Halo: maximum quality and minimum quality:

The i915G did quite well in the high quality mode, falling just a little behind the RADEON 9550. Halo has fewer polygons per scene and is overall a CPU-dependent game, and the power of the Pentium 4 Extreme Edition 3.4GHz came in handy here.

It’s the same at the “speedy” settings: Graphics Media Accelerator 900 with a Pentium 4 Extreme Edition outperforms the GeForce FX 5200 and is just slightly slower than the RADEON 9550.

3D Image Quality

Shaders put aside, I would say that Intel’s new graphics processor is not much better than Extreme Graphics 2: there’s still no full-screen antialiasing, and the maximum level of anisotropic filtering has increased only from 2x to 4x. In this aspect, Graphics Media Accelerator 900 loses unconditionally even to the cheapest modern processors from ATI and NVIDIA.

As for the support of pixel shaders, I’m not yet certain. In some games, GMA 900 works blamelessly, yielding a picture quite undistinguishable from one we get on modern standalone graphics cards, but sometimes the new GPU from Intel is incorrect.

Let’s have a brief test: we take a modern game (Far Cry), run it on the i915G (left) and RADEON 9600 (right) and compare:

Intel 915G	ATI RADEON 9600

The mini-radar has disappeared in the bottom left corner of the screen in the i915G’s screenshot, but otherwise the screens look much alike. However, there is a difference: the i915G only produces a reflection on the water surface, while the RADEON 9600 makes the water both reflect and refract!

Now, medium image-quality settings:

Intel 915G	ATI RADEON 9600

The shaders have disappeared on the water surface produced by Intel GMA 900. But you can just slightly change your position for them to reappear:

Intel 915G	ATI RADEON 9600

And the “speedy” settings:

Intel 915G	ATI RADEON 9600

Once again, water is rendered right most of the time, but sometimes the GPU falters. All returns to the norm after the player changes his position.

Intel 915G	ATI RADEON 9600

Shader surfaces are displayed incorrectly in Halo: Intel GMA 900 is to the left, and the RADEON 9600 is to the right.

Intel GMA 900	ATI RADEON 9600

So, there are problems with pixel shaders, which will be hopefully corrected in the future versions of the driver. Besides that, some games like IL-2 Sturmovik just don’t see hardware pixel shader support in the i915G – this should be corrected, too.

DVD, MPEG4, HDTV Playback

The next round of tests is intended to check the ability of the new integrated graphics from Intel to play videos of various formats.

MPEG-4 comes first. I took a copy of the “Shrek” movie (512x384, 130/96kbps video/audio, DIVXMPG4 V3/MPEG Layer-3).

There are no surprises: the i915G with a Pentium 4 EE have no problems playing MPEG-4 video.

Then I took a copy of the “What Dreams May Come” movie as an example of a DVD movie (720x576, 8712/448kbps video/audio, Interlaced MPEG-2/Dolby Digital [AC3]).

DVD playback is no problem for any of the integrated chipsets.

Last goes the hardest version of video, a HDTV “Step into Liquid” clip (1440x1080, 8000/384 kbps video/audio, Windows Media Video/Audio 9 Professional):

The i915G loads the CPU the least of all. This is no wonder considering that the software decoder is best optimized for Intel CPUs, and the i915G works in pair with the most powerful of them.

The average speed of playing HDTV:

The clip is recorded at 24 frames per second, but the statistics provided by Windows Media Player says 23.8 fps rather than 24, although there are absolutely no skipped frames.

Conclusion

The new integrated graphics processor from Intel is undoubtedly a wide step forward over the decrepit Extreme Graphics 2 core: much higher performance, hardware support of DirectX pixel shaders, higher RAMDAC frequency, support of multi-monitor configurations, HDTV video output to appropriate displays and more.

On the other hand, the new Graphics Media Accelerator from Intel cannot do full-screen antialiasing; its anisotropic filtering of the maximum 4x level cannot be combined with tri-linear filtering; it doesn’t support T&L or vertex shaders; the need to sort polygons for the tiles greatly limits the speed in “high-polygon-count” scenes.

These facts suggest that Intel’s attitude towards integrated graphics hasn’t changed in the slightest. The company only gives its graphics the bare minimum of functionality. For example, the support of DirectX 9 pixel shaders in the new GPU is not an attempt to be better than the competitors, but rather the compliance with the requirements to the hardware that the next OS from Microsoft will produce.

Intel still doesn’t think it necessary to develop high-performance and rich-functionality integrated graphics, capable of competing with cheap standalone graphics cards. There’s no doubt that PCI Express versions of inexpensive cards from ATI and NVIDIA, like RADEON X600/X300 and GeForce PCX 5750/5300, will be faster than the new graphics core from Intel.

Anyway, integrated graphics has made a step forward as Intel brings us support of DirectX 9. We’re waiting for responses from ATI with NVIDIA, or maybe even from VIA with SiS. Stay tuned!