 | This article needs to beupdated. The reason given is: Requiring reliable non-social media sources. Please help update this article to reflect recent events or newly available information.(October 2024) |
 ATI Radeon X1950XTX | |
| Release date | October 5, 2005; 19 years ago (2005-10-05) |
|---|---|
| Codename | Fudo (R520) Rodin (R580) |
| Architecture | Radeon R500 |
| Transistors | 107M 90nm (RV505)
|
| Cards | |
| Entry-level | X1300, X1550 |
| Mid-range | X1600, X1650 |
| High-end | X1800, X1900 |
| Enthusiast | X1950 |
| API support | |
| DirectX | Direct3D 9.0c Shader Model 3.0 |
| OpenGL | OpenGL 2.0 |
| History | |
| Predecessor | Radeon X800 series |
| Successor | Radeon HD 2000 series |
| Support status | |
| Unsupported | |
TheR520 (codenamedFudo) is agraphics processing unit (GPU) developed byATI Technologies and produced byTSMC. It was the first GPU produced using a90 nm photolithography process.
The R520 is the foundation for a line ofDirectX 9.0c andOpenGL 2.0 3D accelerator X1000video cards. It is ATI's first major architectural overhaul since theR300 and is highly optimized forShader Model 3.0. TheRadeon X1000 series using the core was introduced on October 5, 2005, and competed primarily against Nvidia'sGeForce 7 series. ATI released the successor to the R500 series with theR600 series on May 14, 2007.
ATI does not provide official support for any X1000 series cards forWindows 8 orWindows 10; the lastAMD Catalyst for this generation is the 10.2 from 2010 up toWindows 7.[1] AMD stopped providing drivers for Windows 7 for this series in 2015.[2]
A series of open sourceRadeon drivers are available when using aLinux distribution.
The same GPUs are also found in someAMD FireMV products targetingmulti-monitor set-ups.
 | This sectiondoes notcite anysources. Please helpimprove this section byadding citations to reliable sources. Unsourced material may be challenged andremoved. Find sources: "Radeon X1000 series" – news ·newspapers ·books ·scholar ·JSTOR(September 2024) (Learn how and when to remove this message) |
The Radeon X1800 video cards that included an R520 were released with a delay of several months because ATI engineers discovered a bug within the GPU in a very late stage of development. This bug, caused by a faulty 3rd party 90 nm chip design library, greatly hampered clock speed ramping, so they had to "respin" the chip for another revision (a newGDSII had to be sent toTSMC). The problem had been almost random in how it affected the prototype chips, making it difficult to identify.
The R520 architecture is referred to by ATI as an "UltraThreaded Dispatch Processor", which refers to ATI's plan to boost the efficiency of their GPU, instead of going with a brute force increase in the number of processing units. A centralpixel shader "dispatch unit" breaks shaders down into threads (batches) of 16 pixels (4×4) and can track and distribute up to 128 threads per pixel "quad" (4 pipelines each). When a shader quad becomes idle due to a completion of a task or waiting for other data, the dispatch engine assigns the quad with another task to do in the meantime. The overall result is theoretically a greater utilization of the shader units. With a large number of threads per quad, ATI created a very largeprocessor register array that is capable of multiple concurrent reads and writes, and has a high-bandwidth connection to each shader array, providing the temporary storage necessary to keep the pipelines fed by having work available as much as possible. With chips such as RV530 and R580, where the number of shader units per pipeline triples, the efficiency of pixel shading drops off slightly because these shaders still have the same level of threading resources as the less endowed RV515 and R520.[3]
The next major change to the core is to its memory bus.R420 andR300 had nearly identical memory controller designs, with the former being a bug fixed release designed for higher clock speeds. R520's memory bus differs with its central controller (arbiter) that connects to the "memory clients". Around the chip are two 256-bit ring buses running at the same speed as theDRAM chips, but in opposite directions to reduce latency. Along these ring buses are four "stop" points where data exits the ring and goes into or out of the memory chips. There is a fifth, significantly less complex stop that is designed for thePCI Express interface and video input. This design allows memory accesses to be quicker though lower latency from the smaller distance the signals need to move through the GPU, and by increasing the number of banks per DRAM. The chip can spread out memory requests faster and more directly to the RAM chips. ATI claimed a 40% improvement in efficiency over older designs. Smaller cores such as RV515 and RV530 received cutbacks due to their smaller, less costly designs. RV530, for example, has two internal 128-bit buses instead. This generation has support for all recent memory types, includingGDDR4. In addition to a ring bus, each memory channel has the granularity of 32-bits, which improves memory efficiency when performing small memory requests.[3]
The vertex shader engines were already at the requiredFP32 precision in ATI's older products. Changes necessary for SM3.0 included longer instruction lengths, dynamic flow control instructions, with branches, loops and subroutines and a larger temporary register space. The pixel shader engines are actually quite similar in computational layout to their R420 counterparts, although they were heavily optimized and tweaked to reach high clock speeds on the 90 nm process. ATI has been working for years on a high-performance shader compiler in their driver for their older hardware, so staying with a similar basic design that is compatible offered obvious cost and time savings.[3]
At the end of the pipeline, the texture addressing processors are decoupled from pixel shaders, so any unused texturing units can be dynamically allocated to pixels that need more texture layers. Other improvements include 4096x4096 texture support and ATI's 3Dcnormal map compression saw an improvement in compression ratio for more specific situations.[3]
The R5xx family introduced a more advanced onboard motion-video engine. Like the Radeon cards since the R100, the R5xx can offload almost the entire MPEG-1/2 video pipeline. The R5xx can also assist in Microsoft WMV9/VC-1 and MPEGH.264/AVC decoding, by a combination of the 3D/pipeline's shader-units and the motion-video engine. Benchmarks show only a modest decrease in CPU-utilization for VC-1 and H.264 playback.
A selection of real-time 3D demonstration programs was released at launch. ATI's development of their "digital superstar", Ruby, continued with a new demo named The Assassin. It showcased a highly complex environment, withhigh-dynamic-range lighting (HDR) and dynamicsoft shadows. Ruby's latest competing program, Cyn, was composed of 120,000 polygons.[4]
The cards support dual-linkDVI output andHDCP. However, using HDCP requires external ROM to be installed, which were not available for early models of the video cards. RV515, RV530, and RV535 cores include a single and a double DVI link; R520, RV560, RV570, R580, R580+ cores include two double DVI links.
AMD released the final Radeon R5xx Acceleration document.[5]
The lastAMD Catalyst version that officially supports the X1000 series is 10.2, display driver version 8.702.
This series is the budget solution of the X1000 series and is based on the RV515 core. The chips have fourtexture units, fourROPs, four pixel shaders, and 2vertex shaders, similar to the olderX300 – X600 cards. These chips use one quad of an R520, whereas the faster boards use just more of these quads; for example, the X1800 uses four quads. This modular design allows ATI to build a "top to bottom" line-up using identical technology, saving research, development time, and money. Because of its smaller design, these cards offer lower power demands (30 watts), so they run cooler and can be used in smaller cases.[3] Eventually, ATI created the X1550 and discontinued the X1300. The X1050 was based on the R300 core and was sold as an ultra-low-budget part.
Early Mobility Radeon X1300 to X1450 are based around the RV515 core as well.[6][7][8][9]
Beginning in 2006, Radeon X1300 and X1550 products were shifted to the RV505 core, which had similar capabilities and features as the previous RV515 core, but was manufactured byTSMC using an 80 nm process (reduced from the 90 nm process of the RV515).[10]
X1600 uses the M56[1] core which is based on the RV530 core, a core similar but distinct from RV515.
The RV530 has a 3:1 ratio of pixel shaders to texture units. It possesses 12 pixel shaders while retaining RV515's four texture units and four ROPs. It also gains three extra vertex shaders, bringing the total to 5 units. The chip's single "quad" has 3 pixel shader processors per pipeline, similar to the design of R580's 4 quads. This means that RV530 has the same texturing ability as the X1300 at the same clock speed, but with its 12 pixel shaders it is on par with the X1800 in shader computational performance. Due to the programming content of available games, the X1600 is greatly hampered by lack of texturing power.[3]
The X1600 was positioned to replaceRadeon X600 andRadeon X700 as ATI's mid-range GPU. The Mobility Radeon X1600 and X1700 are also based on the RV530.[11][12]
The X1650 series has two parts: the X1650 Pro uses the RV535 core (which is a RV530 core manufactured on the newer 80 nm process), and has both a lower power consumption and heat output than the X1600.[13] The other part, the X1650XT/X1650GT, uses the newer RV570 core (also known as the RV560) though it has lower processing power (note that the fully equipped RV570 core powers the X1950Pro, a high-performance card) to match its main competitor, Nvidia's 7600GT.[14] There's also Radeon X1650, which technically belongs to the previous generation of X1600, because it uses old 90nm RV530 core. If you look closely at the specs, it's basically renamed Radeon X1600 Pro with DDR2 memory.
Originally the flagship of the X1000 series, the X1800 series was released with mild reception due to therolling release and the gain by its competitor at that time, NVIDIA'sGeForce 7 series. When the X1800 entered the market in late 2005, it was the first high-end video card with a 90 nm GPU. ATI opted to fit the cards with either 256 MB or 512 MB on-board memory (foreseeing a future of ever growing demands on local memory size). The X1800XT PE was exclusively on 512 MB on-board memory. The X1800 replaced the R480-basedRadeon X850 as ATI's premier performance GPU.[3]
With R520's delayed release, its competition was far more impressive than if the chip had made its originally scheduled spring/summer release. Like its predecessor, the X850, the R520 chip carries 4 "quads", which means it has similar texturing capability at the same clock speed as its ancestor and the NVIDIA 6800 series. Unlike the X850, the R520's shader units are vastly improved: they areShader Model 3 capable, and received some advancements in shader threading that can greatly improve the efficiency of the shader units. Unlike the X1900, the X1800 has 16 pixel shader processors and equal ratio of texturing to pixel shading capability. The chip also increases the vertex shader number from six on the X800 to eight. With the 90 nmlow-K fabrication process, these high-transistor chips could still be clocked at very high frequencies, which allows the X1800 series to be competitive with GPUs with more pipelines but lower clock speeds, such as the NVIDIA 7800 and 7900 series that use 24 pipelines.[3]
The X1800 was quickly replaced by the X1900 because of its delayed release. The X1900 was not behind schedule, and was always planned as the "spring refresh" chip. However, due to the large quantity of unused X1800 chips, ATI decided to kill one quad of pixel pipelines and sell them off as the X1800GTO.
The X1900 and X1950 series fixed several flaws in the X1800 design and added a significant pixel shading performance boost. The R580 core is pin-compatible with the R520PCBs, which meant a redesign of the X1800 PCB was not needed. The boards carry either 256 MB or 512 MB of onboardGDDR3 memory depending on the variant. The primary change between the R580 and the R520 is that ATI changed the pixel shader processor-to-texture processor ratio. The X1900 cards have three pixel shaders on each pipeline instead of one, giving a total of 48 pixel shader units. ATI took this step with the expectation that future 3D software will be more pixel shader intensive.[15]
In the latter half of 2006, ATI introduced the Radeon X1950 XTX, which is a graphics board using a revised R580 GPU called R580+. R580+ is the same as R580 except it supports GDDR4 memory, a new graphics DRAM technology that offers lower power consumption per clock and offers a significantly higher clock rate ceiling. The X1950 XTX clocks its RAM at 1 GHz (2 GHz DDR), providing 64.0 GB/s of memory bandwidth, a 29% advantage over the X1900 XTX. The card was launched on August 23, 2006.[16]
The X1950 Pro was released on October 17, 2006, and was intended to replace the X1900GT in the competitive sub-$200 market segment. The X1950 Pro GPU is built off of the 80 nm RV570 core with only 12 texture units and 36 pixel shaders, and is the first ATI card that supports native Crossfire implementation by a pair of internal Crossfire connectors, which eliminates the need for the unwieldy external dongle found in older Crossfire systems.[17]
The following table shows features ofAMD/ATI'sGPUs (see also:List of AMD graphics processing units).
| Name ofGPU series | Wonder | Mach | 3D Rage | Rage Pro | Rage 128 | R100 | R200 | R300 | R400 | R500 | R600 | RV670 | R700 | Evergreen | Northern Islands | Southern Islands | Sea Islands | Volcanic Islands | Arctic Islands/Polaris | Vega | Navi 1x | Navi 2x | Navi 3x | Navi 4x | |||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Released | 1986 | 1991 | Apr 1996 | Mar 1997 | Aug 1998 | Apr 2000 | Aug 2001 | Sep 2002 | May 2004 | Oct 2005 | May 2007 | Nov 2007 | Jun 2008 | Sep 2009 | Oct 2010 | Dec 2010 | Jan 2012 | Sep 2013 | Jun 2015 | Jun 2016, Apr 2017, Aug 2019 | Jun 2017, Feb 2019 | Jul 2019 | Nov 2020 | Dec 2022 | Feb 2025 | ||
| Marketing Name | Wonder | Mach | 3D Rage | Rage Pro | Rage 128 | Radeon 7000 | Radeon 8000 | Radeon 9000 | Radeon X700/X800 | Radeon X1000 | Radeon HD 2000 | Radeon HD 3000 | Radeon HD 4000 | Radeon HD 5000 | Radeon HD 6000 | Radeon HD 7000 | Radeon 200 | Radeon 300 | Radeon 400/500/600 | Radeon RX Vega, Radeon VII | Radeon RX 5000 | Radeon RX 6000 | Radeon RX 7000 | Radeon RX 9000 | |||
| AMD support |  |  | |||||||||||||||||||||||||
| Kind | 2D | 3D | |||||||||||||||||||||||||
| Instruction set architecture | Not publicly known | TeraScale instruction set | GCN instruction set | RDNA instruction set | |||||||||||||||||||||||
| Microarchitecture | Not publicly known | GFX1 | GFX2 | TeraScale 1 (VLIW5) (GFX3) | TeraScale 2 (VLIW5) (GFX4) | TeraScale 2 (VLIW5) up to 68xx (GFX4) | TeraScale 3 (VLIW4) in 69xx[18][19] (GFX5) | GCN 1st gen (GFX6) | GCN 2nd gen (GFX7) | GCN 3rd gen (GFX8) | GCN 4th gen (GFX8) | GCN 5th gen (GFX9) | RDNA (GFX10.1) | RDNA 2 (GFX10.3) | RDNA 3 (GFX11) | RDNA 4 (GFX12) | |||||||||||
| Type | Fixed pipeline[a] | Programmable pixel & vertex pipelines | Unified shader model | ||||||||||||||||||||||||
| Direct3D | — | 5.0 | 6.0 | 7.0 | 8.1 | 9.0 11 (9_2) | 9.0b 11 (9_2) | 9.0c 11 (9_3) | 10.0 11 (10_0) | 10.1 11 (10_1) | 11 (11_0) | 11 (11_1) 12 (11_1) | 11 (12_0) 12 (12_0) | 11 (12_1) 12 (12_1) | 11 (12_1) 12 (12_2) | ||||||||||||
| Shader model | — | 1.4 | 2.0+ | 2.0b | 3.0 | 4.0 | 4.1 | 5.0 | 5.1 | 5.1 6.5 | 6.7 | 6.8 | |||||||||||||||
| OpenGL | — | 1.1 | 1.2 | 1.3 | 2.1[b][20] | 3.3 | 4.5[21][22][23][c] | 4.6 | |||||||||||||||||||
| Vulkan | — | 1.1[c][d] | 1.3[24] | 1.4[25] | |||||||||||||||||||||||
| OpenCL | — | Close to Metal | 1.1 (not supported byMesa) | 1.2+ (onLinux: 1.1+ (no Image support on clover, with by rustiCL) with Mesa, 1.2+ on GCN 1.Gen) | 2.0+ (Adrenalin driver onWin7+) (onLinux ROCM, Mesa 1.2+ (no Image support in clover, but in rustiCL with Mesa, 2.0+ and 3.0 with AMD drivers or AMD ROCm), 5th gen: 2.2 win 10+ and Linux RocM 5.0+ | 2.2+ and 3.0 windows 8.1+ and Linux ROCM 5.0+ (Mesa rustiCL 1.2+ and 3.0 (2.1+ and 2.2+ wip))[26][27][28] | |||||||||||||||||||||
| HSA /ROCm | — | | ? | ||||||||||||||||||||||||
| Video decodingASIC | — | Avivo/UVD | UVD+ | UVD 2 | UVD 2.2 | UVD 3 | UVD 4 | UVD 4.2 | UVD 5.0 or6.0 | UVD 6.3 | UVD 7[29][e] | VCN 2.0[29][e] | VCN 3.0[30] | VCN 4.0 | VCN 5.0 | ||||||||||||
| Video encodingASIC | — | VCE 1.0 | VCE 2.0 | VCE 3.0 or 3.1 | VCE 3.4 | VCE 4.0[29][e] | |||||||||||||||||||||
| Fluid Motion[f] | | | | ? | |||||||||||||||||||||||
| Power saving | ? | PowerPlay | PowerTune | PowerTune &ZeroCore Power | ? | ||||||||||||||||||||||
| TrueAudio | — | Via dedicatedDSP | Via shaders | ||||||||||||||||||||||||
| FreeSync | — | 1 2 | |||||||||||||||||||||||||
| HDCP[g] | — | ? | 1.4 | 2.2 | 2.3[31] | ||||||||||||||||||||||
| PlayReady[g] | — | 3.0 | | 3.0 | |||||||||||||||||||||||
| Supported displays[h] | 1–2 | 2 | 2–6 | ? | 4 | ||||||||||||||||||||||
| Max.resolution | ? | 2–6 × 2560×1600 | 2–6 × 4096×2160 @ 30 Hz | 2–6 × 5120×2880 @ 60 Hz | 3 × 7680×4320 @ 60 Hz[32] | 7680×4320 @ 60 HzPowerColor | 7680x4320 @165 Hz | 7680x4320 | |||||||||||||||||||
/drm/radeon[i] | | — | |||||||||||||||||||||||||
/drm/amdgpu[i] | — | Optional[33] | | ||||||||||||||||||||||||
Note that ATI X1000 series cards (e.g. X1900) do not have Vertex Texture Fetch, hence they do not fully comply with the VS 3.0 model. Instead, they offer a feature called "Render to Vertex Buffer (R2VB)" that provides functionality that is an alternative Vertex Texture Fetch.
| Model | Launch | Code name | Fab (nm) | Transistors (million) | Die size (mm2) | Bus interface | Clock rate | Core config | Fillrate | Memory | TDP (Watts) | API support (version) | Release Price (USD) | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Core (MHz) | Memory (MHz) | MOperations/s | MPixels/s | MVertices/s | MTexels/s | Size (MB) | Bandwidth (GB/s) | Bus type | Bus width (bit) | Max. | Direct3D | ||||||||||
| Radeon X1300 | October 5, 2005 (PCIe) December 1, 2005 (AGP) | RV515 | 90 | 107 | 100 | AGP 8× PCI PCIe ×16 | 450 | 250 | 4:2:4:4 | 1800 | 1800 | 225 | 1800 | 128 256 | 8.0 | DDR DDR2 | 128 | 9.0c | 2.1 | $99 (128MB) $129 (256 MB) | |
| Radeon X1300 HyperMemory | October 5, 2005 | PCIe ×16 | 128 256 512 | 4.0 | DDR2 | 64 | $ | ||||||||||||||
| Radeon X1300 PRO | October 5, 2005 (PCIe) November 1, 2006 (AGP) | AGP 8× PCIe ×16 | 600 | 400 | 2400 | 2400 | 300 | 2400 | 128 256 | 12.8 | 128 | 31 | $149 | ||||||||
| Radeon X1300 XT | August 12, 2006 | RV530 | 157 | 150 | 500 | 12:5:4:4 | 6000 | 2000 | 625 | 2000 | 22 | $89 | |||||||||
| Radeon X1550 | January 8, 2007 | RV516 | 107 | 100 | AGP 8x PCI PCIe x16 | 4:2:4:4 | 2200 | 2200 | 275 | 2200 | 128 256 512 | 27 | $ | ||||||||
| Radeon X1600 PRO | October 10, 2005 | RV530 | 157 | 150 | AGP 8× PCIe ×16 | 390 390–690 | 12:5:4:4 | 6000 | 2000 | 625 | 2000 | 12.48 | DDR2 GDDR3 | 41 | $149 (128MB) $199 (256 MB) | ||||||
| Radeon X1600 XT | October 10, 2005 (PCIe) | 590 | 690 | 7080 | 2360 | 737.5 | 2360 | 256 512 | 22.08 | GDDR3 | 42 | $249 | |||||||||
| Radeon X1650 | February 1, 2007 | 500 | 400 | 6000 | 2000 | 625 | 2000 | 12.8 | DDR2 | $ | |||||||||||
| Radeon X1650 SE | RV516 | 105 | PCIe ×16 | 635 | 4:2:4:4 | 256 | DDR2 | $ | |||||||||||||
| Radeon X1650 GT | May 1, 2007 (PCIe) October 1, 2007 (AGP) | RV560 | 80 | 330 | 230 | AGP 8× PCIe x16 | 400 | 24:8:8:8 | 9600 | 3200 | 800 | 3200 | 256 512 | GDDR3 | $ | ||||||
| Radeon X1650 PRO | August 23, 2006 (PCIe) October 15, 2006 (AGP) | RV535 | 131 | 600 | 700 | 12:5:4:4 | 7200 | 2400 | 750 | 2400 | 22.4 | 44 | $99 | ||||||||
| Radeon X1650 XT | October 30, 2006 | RV560 | 230 | 525 | 24:8:8:8 | 12600 | 4200 | 1050 | 4200 | 55 | $149 | ||||||||||
| Radeon X1700 FSC | November 5, 2007 (OEM) | RV535 | 131 | PCIe ×16 | 587 | 695 | 12:5:4:4 | 7044 | 2348 | 733 | 2348 | 256 | 22.2 | 44 | OEM | ||||||
| Radeon X1700 SE | November 30, 2007 | RV560 | 230 | 500 | 500 | 24:8:8:8 | 12000 | 4000 | 1000 | 4000 | 512 | 16.0 | 50 | $ | |||||||
| Radeon X1800 CrossFire Edition | December 20, 2005 | R520 | 90 | 321 | 288 | 600 | 700 | 16:8:16:16 | 9600 | 9600 | 900 | 9600 | 512 | 46.08 | 256 | 113 | $ | ||||
| Radeon X1800 GTO | March 9, 2006 | 500 | 495 | 12:8:12:8 | 6000 | 6000 | 1000 | 6000 | 256 512 | 32.0 | 48 | $249 | |||||||||
| Radeon X1800 XL | October 5, 2005 | 500 | 16:8:16:16 | 8000 | 8000 | 1000 | 8000 | 256 | 70 | $449 | |||||||||||
| Radeon X1800 XT | 625 | 750 | 10000 | 10000 | 1250 | 10000 | 256 512 | 48.0 | 113 | $499 (256MB) $549 (512 MB) | |||||||||||
| Radeon X1900 CrossFire Edition | January 24, 2006 | R580 | 384 | 352 | 625 | 725 | 48:8:16:16 | 30000 | 512 | 46.4 | 100 | $599 | |||||||||
| Radeon X1900 GT | May 5, 2006 | 575 | 600 | 36:8:12:12 | 20700 | 6900 | 1150 | 6900 | 256 | 38.4 | 75 | $ | |||||||||
| Radeon X1900 GT Rev. 2 | September 7, 2006 | 512 | 18432 | 6144 | 1024 | 6144 | 42.64 | ||||||||||||||
| Radeon X1900 XT | January 24, 2006 | 625 | 725 | 48:8:16:16 | 30000 | 10000 | 1250 | 10000 | 256 512 | 46.4 | 100 | $549 | |||||||||
| Radeon X1900 XTX | R580 | 650 | 775 | 31200 | 10400 | 1300 | 10400 | 512 | 49.6 | 135 | $649 | ||||||||||
| Radeon X1950 CrossFire Edition | August 23, 2006 | R580+ | 80 | 1000 | 31200 | 10400 | 1300 | 10400 | 64 | GDDR4 | $449 | ||||||||||
| Radeon X1950 GT | January 29, 2007 (PCIe) February 10, 2007 (AGP) | RV570 | 330 | 230 | AGP 8x PCIe x16 | 500 | 600 | 36:8:12:12 | 18000 | 6000 | 1000 | 6000 | 256 512 | 38.4 | GDDR3 | 57 | $140 | ||||
| Radeon X1950 PRO | October 17, 2006 (PCIe) October 25, 2006 (AGP) | 575 | 690 | 20700 | 6900 | 1150 | 6900 | 44.16 | 66 | $199 | |||||||||||
| Radeon X1950 XT | October 17, 2006 (PCIe) February 18, 2007 (AGP) | R580+ | 384 | 352 | AGP 8x PCIe 1.0 x16 | 625 | 700 (AGP) 900 (PCIe) | 48:8:16:16 | 30000 | 10000 | 1250 | 10000 | 44.8 (AGP) 57.6 (PCIe) | 96 | $ | ||||||
| Radeon X1950 XTX | October 17, 2006 | PCIe 1.0 ×16 | 650 | 1000 | 31200 | 10400 | 1300 | 10400 | 512 | 64 | GDDR4 | 125 | $449 | ||||||||
| Model | Launch | Code name | Fab (nm) | Transistors (million) | Die size (mm2) | Bus interface | Core (MHz) | Memory (MHz) | Core config | MOperations/s | MPixels/s | MVertices/s | MTexels/s | Size (MB) | Bandwidth (GB/s) | Bus type | Bus width (bit) | Max. | Direct3D | Release price (USD) | |
| Clock rate | Fillrate | Memory | TDP (Watts) | API support (version) | |||||||||||||||||
1Pixel shaders :Vertex shaders :Texture mapping units :Render output units
| Model | Launch | Model number | Code name | Fab (nm) | Core clock (MHz) | Memory clock (MHz) | Core config1 | Fillrate | Memory | API compliance (version) | Notes | ||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Pixel (GP/s) | Texture (GT/s) | Size (MB) | Bandwidth (GB/s) | Bus type | Bus width (bit) | ||||||||||||
| Mobility Radeon X1300 | January 19, 2006 | M52 | RV515 | 90 | PCIe ×16 | 350 | 250 | 2:4:4:4 | 1.4 | 1.4 | 128 + shared | 8 | DDR DDR2 | 128 | 9.0c | 2.0 | |
| Mobility Radeon X1350 | September 18, 2006 | M62 | 470 | 350 | 1.88 | 1.88 | 11.2 | DDR2 GDDR3 | |||||||||
| Mobility Radeon X1400 | January 19, 2006 | M54 | 445 | 250 | 1.78 | 1.78 | 8 | DDR DDR2 | |||||||||
| Mobility Radeon X1450 | September 18, 2006 | M64 | 550 | 450 | 2.2 | 2.2 | 14.4 | DDR2 GDDR3 | |||||||||
| Mobility Radeon X1600 | February 1, 2006 | M56 | RV530 | 425 450 | 375 470 | 5:12:4:4 | 1.7 1.8 | 1.7 1.8 | 256 | 12.0 15.04 | DDR2 GDDR3 | ||||||
| Mobility Radeon X1700 | M66 | RV535 | 475 | 400 550 | 1.9 | 1.9 | 11.2 17.6 | strained silicon | |||||||||
| Mobility Radeon X1800 | March 1, 2006 | M58 | R520 | 450 | 500 | 8:12:12:12 | 5.4 | 5.4 | 32 | GDDR3 | 256 | ||||||
| Mobility Radeon X1800 XT | M58 | 550 | 650 | 8:16:16:16 | 8.8 | 8.8 | 41.6 | ||||||||||
| Mobility Radeon X1900 | January 11, 2007 | M68 | RV570 | 80 | 400 | 470 | 8:36:12:12 | 4.8 | 4.8 | 30.08 | PowerPlay 6.0 | ||||||
1Vertex shaders :Pixel shaders :Texture mapping units :Render output units.
New VLIW4 architecture of stream processors allowed to save area of each SIMD by 10%, while performing the same compared to previous VLIW5 architecture