ATI's R600 has 64 real pipes ShockerBy Fuad Abazovic: Friday 18 August 2006, 12:38 WHEN we first time heard that R600 was going to be a big chip we could figure out that ATI wanted to completely redesign the chip and fill it full of lot pipes. We previously wrote that the chip will have sixty four Shader units but we never realised at the time that the design is actually built around a full sixty four physical pipes. That is what various high-ranking sources are telling us. In this scenario, unless Nvidia also managed to triple its pipeline count in the upcoming G80, this chip could lose out big time when put against a 64-pipeline ATI offering. The outcome is still uncertain as we don’t know enough about the G80 to make the final conclusion. The R600 is scheduled for very late 2006, if all goes smoothly. And, if not, you might see this one in January - probably released by AMD's ATI. Remember this is a DirectX 10 chip that is an advanced version of the R500 chip the Vole uses in its Xbox 360. µ
ATI's R600 will consume over 250W Hot Milking FarmerBy Fuad Abazovic: Monday 18 September 2006, 09:08 WE LEARNED that ATI's highly anticipated next GPU will consume up to an incredible 250 W to work. No wonder we reported on many occasions that the chip will be one of the hottest ever.It is the 80 nanometre chip and we talked about it here saying a 65 nanometre chip is simply not possible for such a complex chip. We also said that cards based on it will need a new "super doper" cooler, here. And Charlie D has something to say, here. We can now confirm that the new ATI card will consume around 250W. The currently fastest ATI, R580+ or Radeon X1950 XTX consumes up to 125W i a worst case scenario and heavy 3D while you can suck up 145W out with the dual chip X7950 GX2 card. This means that the R600 will consume twice as much power, and probably will end up close to twice as warm but we also hear it will get much faster then the current cards with sixty four pipelines. It could easily end up twice as fast than the current ATI offerings. It is now a January/February chip, so it will be a while until we have this baby on our desk but after a long time we are getting mildly titillated at the prospect. µ
ATI R600 can only manage 16 pixels per clockPart 1 of 2 16 ROP units only, but is more than equal match to G80By Theo Valich: Wednesday 15 November 2006, 08:52Click here to find out more!MANY THINGS ABOUT ATI's upcoming R600 are surprising, to say the least.First of all, the GPU is a logical development that started with the R500Xenos, or Xbox GPU, but without the 10MB eDRAM part. Unlike the Xbox GPU, the R600 has to be able to support a large number of resolutions and, if we take a look at today's massive 5Mpix resolutions, it is quite obvious that R600 should feature at least five times more eDRAM than Xbox 360 has.DAAMIT kept the RingBus configuration for the R600 as well, but now the number has doubled. The External memory controller is a clear 512-bit variant, while internally you will be treated with a bi-directional bus double the width. The 1024-bit Ringbus is approaching.Since the company believes this is the best way to keep all of the shading units well-fed, the target is to have 16 pixels out in every clock, regardless of how complex the pixel might be. But, don’t think for a second that R600 is weaker than G80 on the account of ROP units alone.We also learned the reason why the product was delayed for so long. It seems that ATI encountered yet another weird bug with the A0 silicon, but this one did not lock the chips at 500MHz, but rather disabled the Multi-sampling Anti-aliasing (MSAA). At press time, we were unable find out if the A1 revision still contains the bug or not. Retail boards will probably run A2 silicon.R600 isn't running on final clocks yet, but the company is gunning for 700 to 800MHz clock for the GPU, which yields pixel a fill rate in the range of G80's or even a bit more. In terms of shading power, things are getting really interesting.Twenty-four ROPs at 575MHz equals 13.8 billion pixels per clock, while 16 ROPs at 750MHz will end up at 12.0 billion pixels. At the same time, expect ATI to far better in more complex Shader-intensive applications.Regarding the number of shaders, expect only marketing wars here. Nvidia has 128 Shader units, while the R600 on paper features "only" 64. However, don't expect ATI's own 64 Shaders to offer half of the performance. In fact, you might end up wildly surprised.ATI's R600 features 64 Shader 4-way SIMD units. This is a very different and complex approach compared to Nvidia's relatively simple scalar Shader units.Since R600 SIMD Shader can calculate the result of four scalar units, it yields with scalar performance of 256 units - while Nvidia comes with 128 "real" scalar units. We are heading for very interesting results in DX10 performance, since game developers expect that NV stuff will be faster in simple instrucions and R600 will excel in complex shader arena. In a way, you could compare R600 and G80 as Athlon XP versus Pentium 4 - one was doing more work in a single clock, while the other was using higher clock speed to achieve equal performance.Regardless of your brand of preference, both G60 and R600 are extremely complex products which deliver hundreds of gigaflops of processing power and addressing wide range of usage models, from games to HDTV broadcasting and new baby named GPGPU usage. µ
ATI AMD's R600 board is a monsterPart 2 Most complex PCB and the heaviest 3D card everBy Theo Valich: Wednesday 15 November 2006, 13:07Click here to find out more!IT SEEMS the board which will DAAMIT will use as a host for its R600 GPU and corresponding components features a number of innovations and improvements that are interesting, to say the least.First of all, you need to know that this PCB (Printed Circuit Board) is the most expensive one that DAAMIT has ever ordered. It's a complex 12-layer monster with certain manufacturing novelties used in order to support the requirements of the R600 chip, most notably the 512-bit memory controller and the distribution of power to the components.The memory chips are arranged in a similar manner as on the G80, but each memory chip has its own 32-bit wide physical connection to the chip's RingBus memory interface. Memory bandwidth will therefore range from anywhere between 115 (GDDR3 at 8800GTX-style 900MHz in DDR mode - 1.8GHz) and 140.1GB/s (GDDR4 at 1.1GHz DDR, or 2.2GHz in marketingspeak).This will pretty much leave the Geforce 8800 series in the dust, at least as far as marketing is concerned. O course, 86GB/s sounds pretty much like nothing when compared to 140GB/s - at least expect to see that writ large on the retail boxes.The R600 board is HUGE but funnily enough, biot in length. Even though the very first revision of the board was as long as the 7900GX2, back in late August/early September engineers pulled a miracle and significantly reduced the size of the board. Right now, they are working on even further optimisations of components, but, from what we saw, this is the most packed product in history of 3D graphics.The PCB will be shorter than 8800GTX's in every variant, and you can compare it to X1950XT and 7900GTX. The huge thing is the cooler. It is a monstrous, longer-than-the-PCB quad-heat pipe, Artic-Cooling style-fan on steroids looking beast, built from a lot of copper. Did we say that it also weighs half a ton?This is the heaviest board that will hit the market and you will want to install the board while holding it with both hands. The cooler actually enhances the structural integrity of the PCB, so you should be aware that R600 will bring some interesting things to the table.If you ask yourself why in the world AMD would design such a thing, the answer is actually right in front of you. Why is it important that a cooler is so big? Well, it needs to dissipate heat from practically every element of the board: GPU chip, memory chips and the power regulation unit.There will be two versions of the board: Pele comes with GDDR4 memory, and UFO has GDDR3 memory, as Charlie already wrote here. DAAMIT is currently contemplating one and two gigabyte variants, offering a major marketing advantage over Graphzilla's "uncomputerly" 640 and 768MB.Did we mention two gigabytes of video memory? Yup, insane - though perhaps not in the professional world, where this 2GB board will compete against upcoming G80GL and its 0.77/1.5GB of video memory. We do not expect that R600 with 2GB will exist in any other form than in FireGL series, but the final call hasn't been made yet.The original Rage Theatre chip is gone for good. After relying on that chip for Vivo functions for almost a decade, the company decided to replace the chip with the newer digital Rage Theatre 200. It is not decided what marketing name will be used, but bear in mind that the R600 will feature video-in and video-out functions from day one. The death of the All-in-Wonder series made a big impact on many people inside the company and now there is a push to offer biggest support for HD in and out connectors.When we turn to power, it seems the sites on-line are reporting values that are dead wrong, especially when mentioning the special power connectors which were present on the A0 engineering sample. Our sources are claiming they are complying to industry standards and that the spec for R600 is different that those rumoured. Some claim half of the rumours out there began life as FUD from Nvidia.For starters, the rumour about this 80nm chip eating around 300W is far from truth. The thermal budget is around 200-220 Watts and the board should not consume more power than a Geforce 8800GTX. Our own Fudo was right in a detail - the R600 cooler is designed to dissipate 250 Watts. This was necessary to have an cooling headroom of at least 15 per cent. You can expect the R680 to use the same cooler as well and still be able to work at over 1GHz. This PCB is also the base for R700, but from what we are hearing, R700 will be a monster of a different kind.As far as the Crossfire edition of the board goes, we can only say: good bye and good riddance.Just like RV570, the X1900GT board, the R600 features new dual-bridge connector for Crossfire capability. This also ends nightmares of reviewers and partners, because reviewing Crossfire used to be such a pain, caused by the rarily of the Crossfire edition cards.Expect this baby to be in stores during Q1'07, or around January 30th. You may be able to guess why this date is the target. µ
Expect this baby to be in stores during Q1'07, or around January 30th. You may be able to guess why this date is the target. µ
ATI R600 is Radeon X2x00 seriesCES 007 R600 to have at least four SKUsBy Theo Valich: Thursday 18 January 2007, 10:11WE MANAGED TO LEARN that the upcoming R600 product exists in four different varieties, and the differences between them aren't small.Unlike Nvidians and their GeForce 8800GTX/GTS, R600 will offer differentiation for ATI partners, not keeping them as sticker-stampers, as some called their Nvidian counterparts.We can now share with you that the engineering teams at AMD created four different PCBs (Printed Circuit Boards) for the R600 GPU. These each target a different set of customers. The leaked drivers and some marketing documents already call for this generation to be called X2000 series, with devices labelled X2200 and X2400 appearing on the map.It is not impossible that R600 just ends up being called X2800, but AMD certainly wants to have a clear branding of the product.Since yours truly has battled with American cuisine for the past 10 days (and even lost 2.1 kilos, thanks to the long walks from LVCC to Venetian to Belaggio and back), we'll disclose the details about the products comparing them to the nation's favourite food - steak.So, the T-bone is full a 12 inches long (30cm). This baby is dubbed XTX, and will feature-top-of-the-line, 1GB GDDR-4 memory from Samsung. You can count on 16 memory chips yielding 1GB of video memory connected to the GPU via 512-bit external bus. Memory chips could do 2.4GHz clock (1.2GHz physical), yielding in yet unseen bandwidth of 153.6 GB/s, dwarfing 8800GTX and its 86.4 GB/s. However, this clock is not guaranteed - not everything is in the bandwidth, but rather in the way you use it.Second variant is in the prime rib categoryL more compact its big T-bone brother, on a size level with R580 (X1950XTX) and G80GTS (8800GTS) boards. We're talking about "X2x00 XT", which is pretty much the same thing as XTX, featuring only a speed downgrade. The speed downgrade enabled DAAMIT to put a more compact PCB, nine inches in length but still featuring the same amount of GDDR-4 memory. Depending on the price and availability of GDDR-4, this one will be available in 512MB variant as well. You know, X1900XT 512/256MB, only one GPU generation ahead.The third one, let's call it sirloin steak, is sort of X1800XL style ("X2x00XL"). We're talking about still GDDR-4 memory, but a new 9-inch PCB. Nope, this is not a downgraded PCB from the already-mentioned XT part, we're talking about a board which will feature "normal" clocks and be available for OEMs to do wonderous display output things with. Multimedia addicts will be happy with the whole array of possibilities, thanks to the fact that ATI killed its decade old ViVo chip. Single-slot ahoy.Fourth class, mignon filet, is dubbed X2000GT, and this is a product which will feature most of the non-100% QA chips around. The PCB is once again new and does not derive from above mentioned three models - but still inside the 9 inches of length (three different 9-inch versions, guys really like the number). This baby was codenamed UFO, and had a very difficult birth: it was introduced, then shafted, then re-introduced into the pipe again – and this is the R600 chip combined with cheap and massively available GDDR-3 memory. This will be the ground for GPGPU boards as well, since AMD plans for both 1GB and 2GB versions of the boards. 2GB versions are of course, reserved for the high-end, professional market.Now, here comes the fun part: of products mentioned here, three require a new power connector, the 8-pin one. The 8-pin was also the reason that ATI managed to get its models in 9-inch size, but we already wrote about that one. Top brass, the XTX - does not care for 8-pins, it wants dual 6-pin rails, just like the 8800GTX. Boards will come with adapters, or you need one of these babies.When it comes to cooling these monsters down, you will be happy to learn that AMD developed a single-slot solution as well, so there should be some cheers going on in the business group of AMD, since Nvidia could not squeeze its 8800GTS into a single slot. Our sources say the single-slot solution is due to the use of an 80nm process and send their cheers to guys'n'gals at TSMC. Still, the high-end models come with a monster cooler indeed.There is also a Dual-HDMI 1.3 option, but we do not reckon on this one seeing the light of the day before mainstream and lower-end components kick in. Although, for a ultimate enthusiast, certainly several thousand boards would find their way home, in ultimate HTPC machines.We have tons of more data for you, to parahprase great Humphrey Bogart: of all the hotel rooms in the world, sll this info had to walk into ours. µ
... we have some time to wait to see if R600 is gonna rock nvidia's world and ours, or if its comparable...
R600 supports Quad setupsQuad Crossfire is on the wayBy Fuad Abazovic: Wednesday 07 February 2007, 12:45Click hereWE LEARNED one more critical detail about the R600. The chip can and will support Quad setups. It will work with four cards. ATI has been working to solve the four card performance problem for a while. Nvidia tried it and we tested the Quad SLI with two 7950 GX2 cards but we got super lame performances out of it.The power supply manufacturers are thrilled about four cards in a high-end machine as such a system will demand a lot of power, probably even more than 1000W.ATI can possibly push a frame or two with its Alternate Frame Rendering marchitecture and make it more efficient than the split screen rendering. We will have to wait and see but it sounds like in March some records are going to get broken. µ
VR-Zone has learned about some new details on 80nm R600 today and there will be 2 SKUs at launch; XTX and XT. There will be 2 versions of R600XTX; one is for OEM/SI and the other for retail. Both feature 1GB DDR4 memories on board but the OEM version is 12.4" long to be exact and the retail is 9.5" long. The above picture shows a 12.4" OEM version. The power consumption of the card is huge at 270W for 12" version and 240W for 9.5" version. As for R600XT, it will have 512MB of GDDR3 memories onboard, 9.5" long and consumes 240W of power. Lastly, there is a cheaper R600XL SKU to be launched at a later date.
