Radeon X1000 series

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 new GDSII had to be sent to TSMC). The problem had been almost random in how it affected the prototype chips, making it difficult to identify. ==Architecture==

The R520 architecture is referred to by ATI as an "Ultra Threaded 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 central pixel 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 large processor 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. The next major change to the core is to its memory bus. R420 and R300 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 the DRAM 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 the PCI 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, including GDDR4. In addition to a ring bus, each memory channel has the granularity of 32-bits, which improves memory efficiency when performing small memory requests. The cards support dual-link DVI output and HDCP. 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. ==Drivers==

The last AMD Catalyst version that officially supports the X1000 series is 10.2, display driver version 8.702. ==Variants==

X1300–X1550 series This series is the budget solution of the X1000 series and is based on the RV515 core. The chips have four texture units, four ROPs, four pixel shaders, and 2 vertex shaders, similar to the older X300 – 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. 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 by TSMC using an 80 nm process (reduced from the 90 nm process of the RV515). X1600 series X1600 uses the M56 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. X1650 series 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. 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. 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. X1800 series Originally the flagship of the X1000 series, the X1800 series was released with mild reception due to the rolling release and the gain by its competitor at that time, NVIDIA's GeForce 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-based Radeon X850 as ATI's premier performance GPU. 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. 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. == Radeon feature matrix ==

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. 1 Pixel shaders : Vertex shaders : Texture mapping units : Render output units Mobility Radeon X1000 series 1 Vertex shaders : Pixel shaders : Texture mapping units : Render output units. ==See also==