The “R600″ is the first personal computer graphics processing unit (GPU) from
ATI based on a unified shader architecture. It is ATI’s second generation
unified shader design and is based on the “Xenos” GPU implemented in the Xbox
360 game console, which used the world’s first such shader architecture.
Previous GPU architectures implement separate processors for each type of
graphics function. A unified architecture leverages many flexible processors
which can be scheduled to process a variety of shader types, thereby
significantly increasing GPU throughput (dependent on application instruction
mix as noted below). The R600 core processes vertex, geometry, and pixel shaders
as outlined by the Direct3D 10.0 specification for Shader Model 4.0 in addition
to full OpenGL 3.0 support.
The new unified shader functionality is based upon a Very long instruction
word (VLIW) architecture in which the core executes operations in parallel.
A shader cluster is organized into 5 stream processing units. Each stream
processing unit (except the 5th) can retire a finished single precision floating
point MAD (or ADD or MUL) instruction per clock, dot product (dp, and special
cased by combining ALUs), and integer ADD. The 5th unit is more complex and can
additionally handle special transcendental functions such as sine and cosine.
Each shader cluster can execute 6 instructions per clock cycle (peak),
consisting of 5 shading instructions plus 1 branch .
Notably, the VLIW architecture brings with it some classic challenges
inherent to VLIW designs, namely that of maintaining optimal instruction flow.
Additionally, the chip cannot co-issue instructions when one is dependent on
the results of the other. Performance of the GPU is highly dependent on the
mixture of instructions being used by the application and how well the real-time
compiler in the driver can organize said instructions.
R600 core includes 64 shader clusters, while RV610 and RV630 cores have 8 and
24 shader clusters respectively.
See also: Very long instruction word
Hardware tessellation
The GPU is equipped with an extra feature which is not part of the current
DirectX 10.0 specification. It contains programmable tessellation units, similar
to those within the Xenos GPU (codenamed “C1″) also developed by ATI. This unit
allows a developer to take a simple polygon mesh and subdivide it based on a
curved surface evaluation function, with different tessellation forms as Bzier
surfaces with N-patches, B-splines and NURBS, and even some subdivision surface
techniques, which usually comes with a displacement map texture. Essentially,
this allows a simple, low-polygon model to be increased dramatically in polygon
density in real-time with minimized performance loss. Scott Wasson of Tech
Report noted during an AMD demo of the technology that the resulting model was
so dense with millions of polygons that it appeared to be solid.
This unit is reminiscent of ATI’s earlier “TruForm” technology, used
initially in the Radeon 8500, which performed a similar function in hardware.
While this tessellation hardware is not part of the current OpenGL or Direct3D
requirements, and competitors such as the GeForce 8 series lack similar
hardware, Microsoft has included Tessellation as part of their D3D10.1 future
plans. The “TruForm” technology from the past received little attention from
software developers and was only utilized in a few game titles (such as Madden
NFL 2004, Serious Sam, Unreal Tournament 2003 and 2004, and unofficially
Morrowind), because it was not a feature shared with NVIDIA GPUs which had a
competing Tessellation solution using Quintic-RT patches which met with even
less support from developers. Since the Xenos contains similar hardware, and
Microsoft sees hardware surface tessellation as a major GPU feature with
proposed implementation of hardware tessellation support in future DirectX
releases (presumably DirectX 11), dedicated hardware tessellation units may
receive increased developer awareness in future titles. It remains to be seen
whether ATI’s implementation will be compatible with the eventual DirectX
standard.
Ultra threaded dispatch processor
Although the R600 is a significant departure from previous designs, it still
shares many features with its predecessors. The “Ultra-Threaded Dispatch
Processor” is a major architectural component of the R600 core, just as it was
with the Radeon X1000 GPUs. This processor manages a large number of in-flight
threads of three distinct types (vertex, geometry, and pixel shaders) and
switches amongst them as needed. With a large number of threads being managed
simultaneously it is possible to reorganize thread order to optimally utilize
the shaders. In other words, the dispatch processor evaluates what goes in the
other parts of the R600 and attempts to keep processing efficiency as high as
possible. There are lower levels of “management” as well; each SIMD array of 80
stream processors has its own sequencer and arbiter. The arbiter decides which
thread to process next, while the sequencer attempts to reorder instructions for
best possible performance within each thread.
Texturing and anti-aliasing
Texturing and final output aboard the R600 core is similar but also distinct
from R580. R600 is equipped with 4 texture units that are decoupled
(independent) from the shader core, like in the R520 and R580 GPUs.
The render output units (ROPs) of Radeon HD 2000 series now performs the task
of multi-sample anti-aliasing (MSAA) with programmable sample grids and maximum
of 8 sample points, instead of using pixel shaders as in Radeon X1000 series.
Also new is the capability to filter FP16 textures, popular with HDR lighting,
at full-speed. ROP can also perform trilinear and anisotropic filtering on all
texture formats. On R600, this totals 16 pixels per clock for FP16 textures,
while higher precision FP32 textures filter at half-speed (8 pixels per
clock).
Anti-aliasing capabilities are more robust on R600 than on the R520 series.
In addition to the ability to perform 8x MSAA, up from 6x MSAA on the R300
through R580, R600 has a new “custom filter anti-aliasing” (CFAA) mode. CFAA
refers to an implementation of non-box filters that look at pixels around the
particular pixel being processed in order to calculate the final color and
anti-alias the image. CFAA is performed by shader, instead of in the ROPs. This
brings greatly enhanced programmability because the filters can be customized,
but may also bring potential performance issues because of the use of shader
resources. As of launch of R600, CFAA utilizes wide and narrow tent filters.
With these, samples from outside the pixel being processed are weighted linearly
based upon their distance from the centroid of that pixel, with the linear
function adjusted based on the wide or narrow filter chosen.
Memory controllers
Memory controllers are connected via internal bi-directional ring bus wrapped
around the processor. In Radeon HD 2900, it is a 1024-bit bi-directional ring
bus (512-bit read and 512-bit write), with 8 64-bit memory channels for a total
bus width of 512-bits on the 2900 XT.; in Radeon HD 3800, it is a 512-bit ring
bus; in Radeon HD 2600 and HD 3600, it is a 256-bit ring bus; In Radeon HD 2400
and HD 3400, there is no ring bus.
Video processing, display and miscellaneous features
All video cards except the Radeon HD 2900 series include dedicated ATI’s
Unified Video Decoder for hardware decoding of MPEG4, VC-1, H.264 video streams,
which itself being the major part of AVIVO HD technology. In terms of
functionality, NVIDIA’s Purevideo 2 offer similar hardware video acceleration,
with UVD including greater VC-1 offloading.
HDTV encoding support is implemented via the integrated AMD Xilleon encoder;
the companion “Rage Theater” chip used on the Radeon X1000 series was replaced
with the digital “Theater 200″ chip, providing VIVO capabilities.
For display outputs, all variants include two dual-link TMDS transmitters,
except for HD 2400 and HD 3400, which include one single and one dual-link TMDS
transmitters. Each DVI output includes dual-link HDCP encoder with on-chip
decipher key. HDMI was introduced, supporting display resolutions up to
19201080, with integrated HD audio controller with 5.1-channel LPCM and AC3
encoding support. Audio is transmitted via DVI port, with specially designed
DVI-to-HDMI dongle for HDMI output that carries both audio and video.
All variants support CrossFireX technology. CrossFire efficiency was improved
and shows performance approaching the theoretical maximum of twice the
performance of a single card.
While some of the architecture of Radeon HD 2000 family is similar to Xenos,
Radeon HD 2000 family does not have embedded DRAM (eDRAM) frame buffer. Xenos’
eDRAM is designed tightly around the limited resolutions at which the Xbox 360
operates. Personal computers operate at maximum efficiency at a much wider range
of resolutions, which would require a significantly larger amount of eDRAM to be
effective.
Half-generation update
The series saw a half-generation update with die shrink (55 nm) variants:
RV670, RV635 and RV620. All variants support PCI Express 2.0, DirectX 10.1 with
Shader Model 4.1 features, dedicated ATI Unified Video Decoder (UVD) for all
models and PowerPlay technology for desktop video cards.
Except the Radeon HD 3800 series, all variants supported 2 integrated
DisplayPort outputs, supporting 24- and 30-bit displays for resolutions up to
25601600. Each output included 1, 2, or 4 lanes per output, with data rate up to
2.7 Gbps per lane.
ATI claimed that the support of DirectX 10.1 can bring improved performance
and processing efficiency with reduced rounding error (0.5 ULP compared with
average error 1.0 ULP as tolerable error), better image details and quality,
global illumination (a technique used in animated films, and more improvements
to consumer gaming systems therefore giving more realistic gaming experience.
)
Desktop products
The R600 family is called the Radeon HD 2000 series, with the enthusiast
segment being the “Radeon HD 2900 series” which originally comprised the Radeon
HD 2900 XT with GDDR3 memory released on May 14, and the higher-clocked GDDR4
version in early July.
The mainstream and budget segment products were the Radeon HD 2600 and Radeon
HD 2400 series respectively, both launched June 28, 2007.
Previously there were no HD 2000 series products being offered in the
performance segment while ATI used models from the previous generation to
address that target market; the situation was not changed until the release of
variants of the Radeon HD 2900 series, the Radeon HD 2900 Pro and GT, which
filled the gap of the performance market for a short period of time.
Radeon HD 2900
The Radeon HD 2900 series was based on the codenamed R600 GPU, packed 700
million transistors on an 80 nm fabrication process and had a 420mm die size.
The Radeon HD 2900 XT was the first graphics card product to implement digital
PWM onboard, specifically 7-phase PWM. The first product of the line, the Radeon
HD 2900 XT, was launched on May 14, 2007.
The Radeon HD 2900 Pro was clocked lower at 600 MHz core and 800 MHz memory
(1600 MHz effective), configured with 512 MiB or 1 GiB (GDDR3/GDDR4) of video
memory and the same 512-bit memory controller as the Radeon HD 2900 XT instead
of the previously rumored 256-bit memory controller.
The Radeon HD 2900 GT was a 48-shader cluster variant clocked the same as the
HD 2900 Pro with 256 MB of video memory on a 256-bit interface.
Radeon HD 2600
The Radeon HD 2600 series was based on the codenamed RV630 GPU and packed 390
million transistors on a 65 nm fabrication process. The Radeon HD 2600-series
video cards included GDDR3 support, a 128-bit memory ring bus and 4-phase
digital PWM, spanning a die size of 153 mm. Neither of the GDDR3 reference PCI-E
designs required additional power connectors whereas the HD 2600 Pro and XT AGP
variants required additional power through either 4-pin or 6-pin power
connectors. Official claims state that the Radeon HD 2600 series consumes as
little as 45 W of power.[citation needed]
Radeon HD 2600 X2
The Radeon HD 2600 X2 is a dual-GPU product which includes 2 RV630 cores onto
a single PCB with a PCI-E bridge splitting the PCI-E x16 bandwidth into two
groups of PCI-E x8 lanes (each 2.0 Gb/s). The card provides 4 DVI outputs or
HDMI outputs via dongle and supports CrossFire configurations. AMD calls this
product the “Radeon HD 2600 X2″ as seen by some vendors and as observed inside
the INF file of Catalyst 7.9 version 8.411. Sapphire and other vendors including
PowerColor and GeCube have either announced or demonstrated their respective
“CrossFire on a card” products. Catalyst 7.9 added support for this hardware in
September 2007. However, AMD did not provide much publicity to promote it. A
vendor may offer cards containing 256 MB, 512 MB, or 1 GB of video memory.
Although the memory technology utilized is at a vendor’s discretion, most
vendors have opted for GDDR3 and DDR2 due to lower manufacturing cost and
positioning of this product for the mainstream rather than performance market
segment.
Radeon HD 2400
The Radeon HD 2400 series was based on the codenamed RV610 GPU. It had 180
million transistors on a 65 nm fabrication process. The Radeon HD 2400 series
used a 64-bit-wide memory bus. The die size is 85 mm. The official PCB design
implements only a passive-cooling heatsink instead of a fan, and official claims
of power consumption are as little as 35 W.[citation needed] The core has 16 KB
unified vertex/texture cache away from dedicated vertex cache and L1/L2 texture
cache used in higher end model.
Reports has that the first batch of the RV610 core (silicon revision A12),
only being released to system builders, has a bug that hindered the UVD from
working properly, but other parts of the die operated normally. Those products
were officially supported with the release of Catalyst 7.10 driver, which the
cards were named as Radeon HD 2350 series.
Radeon HD 3800
The Radeon HD 3800 series was based on the codenamed RV670 GPU, packed 666
million transistors on a 55 nm fabrication process and had a die size at 192 mm,
with the same 64 shader clusters as the R600 core, but the memory bus width was
reduced to 256 bits.
The RV670 GPU is also the base of the FireStream 9170 stream processor, which
uses the GPU to perform general purpose floating-point calculations which were
done in the CPU previously.
The Radeon HD 3850 and 3870 became available mid-November 2007.
Radeon HD 3690/3830
The Radeon HD 3690, which was limited only to the Chinese market where it was
named HD 3830, has the same core as the Radeon 3800 series but with only a
128-bit memory controller and 256MB of GDDR3 memory. All other hardware
specifications are retained.
A further announcement was made that there would be a Radeon HD 3830 variant
bearing the same features as Radeon HD 3690, but with a unique device ID that
does not allow add-in card partners in China to re-enable the burnt-out portion
of the GPU core for more memory bandwidth.
The Radeon HD 3690 was released early February 2008 for the Chinese market
only.
Radeon HD 3800 X2
Radeon HD 3870 X2
Radeon HD 3870 X2 (codenamed R680) was released on January 28, 2008,
featuring 2 RV670 cores with a maximum of 1024 MB GDDR3 SDRAM, targeting the
enthusiast market and replacing the Radeon HD 2900 XT. The processor achieved a
peak single-precision floating point performance of just over 1 TFLOPS (1.06
TFLOPS), being the world’s first single-PCB graphics product breaking the 1
TFLOP mark.
The Radeon HD 3870 X2 uses the same approach for communications between the
two GPU cores as the Sapphire Radeon X1950 Pro Dual and Radeon HD 2600 X2. The
GPU cores communicate to each other through an onboard PCI-E switch, providing
each core with x8 (Radeon X1950 Pro Dual) to x16 (Radeon HD 2600 X2) PCI-E
bandwidth and becoming a software CrossFire setup, supporting two extra hardware
CrossFire bridges. The Radeon HD 3870 X2 uses PEX8547 PCI-E switch,, but each
core shares x16 PCI-E bandwidth. The card only sees one CrossFire bridge being
placed onboard and between the cores, thus only allowing one CrossFire bridge to
be plugged onto the card.
AMD stated the possibility of supporting 4 Radeon HD 3870 X2 cards, allowing
8 GPUs to be used on several motherboards, including the MSI K9A2 Platinum and
Intel D5400XS, because these motherboards have sufficient spaces between PCI-E
slots for dual-slot cooler video cards, presumably as a combination of two
separate hardware CrossFire setups with a software CrossFire setup bridging the
two, but currently with no driver support.
Radeon HD 3600
The Radeon HD 3600 series was based on the codenamed RV635 GPU, packed 378
million transistors on 55 nm fabrication process, and had 128-bit memory bus
width. The support for HDMI and D-Sub ports is also achieved through separate
dongles. Beside the DisplayPort implementations, there also exists other display
output layouts as dual DVI port or DVI with D-Sub display output layout.
The only variant, the Radeon HD 3650, was released on January 23, 2008.
Radeon HD 3400
AMD Radeon HD3450
The Radeon HD 3400 series was based on the codenamed RV620 GPU, packed 181
million transistors on a 55 nm fabrication process, and had 64-bit memory bus
width. Products were available in full height ATX cards and low-profile
cards.
One of the notable features is that the Radeon HD 3400 series (including
Mobility Radeon HD 3400 series) video cards support ATI Hybrid Graphics.
The Radeon HD 3450 and Radeon HD 3470 were released on January 23, 2008.
Mobile products
All Mobility Radeon HD 2000/3000 series share the same feature set support as
their desktop counterparts, as well as the addition of the battery-conserving
PowerPlay 7.0 features, which are augmented from the previous generation’s
PowerPlay 6.0.
The Mobility Radeon HD 2300 is a budget product which includes UVD “in
silica” but lacks unified shader architecture and DirectX 10.0 / SM 4.0 support,
limiting support to DirectX 9.0c / SM 3.0 using the more traditional
architecture of the previous generation. A high-end variant, the Mobility Radeon
HD 2700, with higher core and memory frequencies than the Mobility Radeon HD
2600, was released in mid-December 2007.
The Mobility Radeon HD 2400 is offered in two model variants; the standard HD
2400 and the HD 2400 XT.
The Mobility Radeon HD 2600 is also available in the same two flavors; the
plain HD 2600 and, at the top of the mobility lineup, the HD 2600 XT.
The half-generation update treatment had also applied to mobile products.
Announced prior to CES 2008 was the Mobility Radeon HD 3000 series. Released in
the first quarter of 2008, the Mobility Radeon HD 3000 series consisted of two
families, the Mobility Radeon HD 3400 series and the Mobility Radeon HD 3600
series. The Mobility Radeon HD 3600 series also featured the industry’s first
implementation of on-board 128-bit GDDR4 memory.
About the time of late March to early April, 2008, AMD renewed the device ID
list on its website with the inclusion of Mobility Radeon HD 3850 X2 and
Mobility Radeon HD 3870 X2 and their respective device IDs. Later in Spring IDF
2008 held in Shanghai, a development board of the Mobility Radeon HD 3870 X2 was
demonstrated alongside a Centrino 2 platform demonstration system. The Mobility
Radeon HD 3870 X2 was based on two M88 GPUs with the addition of a PCI Express
switch chip on a single PCB. The demonstrated development board is on PCI
Express 2.0 x16 bus, while the final product is expected to be on AXIOM/MXM
modules.
Driver support
Main article: ATI Catalyst Drivers
Windows
The Purple Pill tool issue, which could allow unsigned drivers to be loaded
into Windows Vista and tamper with the operating system kernel, was resolved in
the Catalyst 7.8 release (version 8.401). The AVIVO video converter for Windows
Vista, and color temperature control in Catalyst Control Center was added with
the release of Catalyst 7.9, package version 8.411. Software CrossFire was
enabled for HD 2600 and HD 2400 series video cards with the release of Catalyst
7.10 (package version 8.421)
The Catalyst 8.1, package version 8.451, supports for MultiView technology
for accelerated OpenGL rendering on multiple video card setup (CrossFire). The
driver also allows CrossFire configurations for Radeon HD 3850 and HD 3870 video
cards.
The Catalyst 8.3 is described by AMD as a milestone release, supporting
DirectX 10.1, ATI CrossFire X technology and allowing the mixing of different
Radeon HD 3800 series video cards to form a CrossFire X setup with 2 to 4 GPUs.
Catalyst 8.3 introduced to new video controls to further enhance the video
playback quality, these controls includes edge enhancement and noise reduction
settings. There is also the support for extended desktop in CrossFire X mode.
The anti-aliasing support for Unreal Engine 3.0 in DirectX 9.0 games, support
for CFAA filters (wide tent and box tent) to be enabled when Super AA is
enabled, and other features as developer support for Hardware surface
tessellation, hardware accelerated wide aspect ratio LCD scaling, HydraVision
support for Windows Vista allowing to add maximum 9 virtual desktops and new
Folding@Home client (version 6.10) are also officially supported in this
release.
The Catalyst 8.5, package version 8.493 brought new features include
component video with 480i and 480p resolutions, SECAM TV output support, 1080p
HDTV custom mode via HDMI, 1080p24 (1080p resolution at 24 frame/s) support,
HDMI Audio for non-standard TV modes (CEA 861b), support for adaptive
anti-aliasing under OpenGL, Windows XP SP3 support and un-install utility
enhancements. The driver also includes performance improvements and fixes some
instability issues and rendering issues on some games.
It should be note that current Catalyst drivers do not support the AGP
versions of Radeon HD 2000/3000 series cards with RIALTO bridge. Installing
Catalyst drivers on those cards will yield the following error message: “setup
did not find a driver compatible with your current hardware or operating
system.” or simply fail outright. The AGP cards in question are supported
unofficially by ATI/AMD with a “hotfixed” Catalyst driver-set each month since
May 2008 with the Catalyst 8.5 hotfix . Their PCI vendor IDs are listed
below:
GPU core
Product
PCI device ID
RV610
Radeon HD 2400 Pro
94C4
RV620 (M82SE)
Radeon HD 3430
95C2
RV620
Radeon HD 3450
94C6
RV630
Radeon HD 2600 Pro
9587
RV630
Radeon HD 2600 XT
9586
Linux
The official closed-source ATI Linux driver was named fglrx, then renamed as
Catalyst drivers for Linux, currently version 9.12. In the past there was no
support for the AGP versions of the HD 2400 and HD 2600, but support was added
in version 8.5 of fglrx.
Another Linux driver is the RadeonHD driver, an open-source ATI R500/600
display driver, it is developed in part by specifications that AMD has openly
published. To date, AMD has released register specifications for M56, M76, RV630
and RS690 GPUs and 3D programming guide for the R500 family of GPUs. AMD has
committed to releasing their R500 and R600 GPU documentation along with
publishing their specifications for past generations of GPUs.
Documentation release
AMD committed to releasing register documentations for each generations of
GPU to support the open source community and an open source driver RadeonHD for
Linux. Initial register documentation and parser code to execute the AtomBIOS
ROM routines were released in September 2007. The R600 family Instruction Set
Architecture guide was released on June 11, 2008. Sample code and register
headers for the R600 and R700 3D engines were released in December 2008. AMD
released the specifications for both the r6xx and r7xx families on January 26,
2009.
Marketing
New model numbering scheme
The numbering schemes for Radeon HD 3000 series as well as Mobility Radeon HD
3000 series were notably changed. While previous PRO, XT, GT, and XTX suffixes
were eliminated, products were differentiated by changing the last two digits of
the product model number (for instance, HD 3850 and HD 3870, giving the
impression that the HD 3870 model having higher performance than HD 3850). While
for dual-GPU products, a new suffix “X2″ will be used to identify its nature as
dual-GPU on one PCB solution. Similar changes to the IGP naming were spotted as
well, for the previously launched AMD M690T chipset with side-port memory, the
IGP is named “Radeon X1270″, while for the AMD 690G chipset, the IGP is named
“Radeon X1250″, as for AMD 690V chipset, the IGP is clocked lower and having
fewer functions and thus named “Radeon X1200″. The new numbering scheme of video
products are shown below:
Product Category
Model number
range (steps of 10)1
Price range
(USD)
Shader amount
(VS/PS/SPU)2
Memory
Outputs
Product(s)
Type
Width
(bit)
Size (MiB)
Enthusiast
Dual GPU
800 X2-990 X23
>$250
200%
GDDR3,
GDDR4
2x 256-bit
512/1024
2 DVI,
HDMI, DP (Dongle)
HD 3870 X2/HD 3850 X2
Enthusiast
/high-end
800-990
>$150
75-100%
GDDR3,
GDDR4
256-bit
256/512/1024
2 DVI,
HDMI, DP (Dongle)
HD 3870/3850
Mainstream
600-790
$100$150
37.5-75%
DDR2,
GDDR3,
GDDR4
128-bit
128/256/512
D-Sub, DVI
HD 3650/3690
DVI, 2 DP,
HDMI (Dongle)
Budget/Value
350-590
25-50%
DDR2,
GDDR3
64-bit
64/128
(HM: 768/1024)
D-Sub, DVI,
HDMI, DP (Dongle)
HD 3450/3470
IGP
000-300
N/A
25-50%
UMA,
side-port memory
(GDDR2/GDDR3)
UMA + 32-bit
(side-port) 4
64/1284 + UMA
(OS dependent)
D-Sub, DVI,
HDMI, DP
Component (YCbCr)
X1270/X1250/X1200
HD 3200/HD 3100/2100
1 The last two digits denotes variant, similar to the previous suffixes,
which “70″ is in essence the “XT” variant while “50″ is actually the “Pro”
variant , while “90″ appeared once in the lineup and can be seen as the “XTX”
variant.
2 Stream Processors only applicable to Direct3D 10-class video components
(Radeon HD 2000/3000 series).
3 All Dual-GPU solutions will have an X2 suffix after the model number.
4 Side-port memory as local frame buffer is only available on selected IGP
models, not all IGP models have this feature.
Product confusions
When Radeon HD 2900 was first released, there was much confusion as to
whether or not the product included dedicated video processor hardware, due in
part to statements that it supported the software program AVIVO HD. Many
reviewers and subsequent readers/consumers interpreted this as meaning the
HD2900 incorporated the same UVD hardware as found in the HD 2400 & HD 2600
series, despite some sites noting this difference at launch time, weeks before
the issue first gained traction as a result of a TechReport article. This
confusion and subsequent discussions prompted AMD to make a formal statement
designed to clarify exactly what UVD was available in which models. The HD 2900
XT video playback capabilities are similar to those of the previous X1000 cards
with AVIVO capabilities.
Starting August, 2007 some system builders including Falcon Northwest
received the 1 GB GDDR4 (with Samsung 0.9 ns (K4U52324QE-BC09) GDDR4) version of
the Radeon HD 2900 XT. Falcon Northwest incorrectly referred the product as the
“Radeon HD 2900 XTX”.
It should be noted that several products, branded the Mobility Radeon X2000
series, are in fact based on the older R520 architecture and spotting the
support of DirectX 9.0c only and do not have UVD on die.
Chipset table
Main article: Comparison of ATI Graphics Processing Units
See also
Video card
Graphics processing unit
GeForce 8 series
FireStream 9170, the GPGPU version of Radeon HD 3870 graphics card
AMD graphics products (ATI Technologies)
ATI consumer graphics processors
2D rendering
Direct3D 3-6
Direct3D 7
Direct3D 8
Direct3D 9
Direct3D 10
Direct3D 11
Mach
Rage
Radeon R100
Radeon R200
Radeon R300 R420 R520
Radeon R600 R700
Evergreen Northern Islands1
Chipsets
ATI chipsets
AMD chipsets
IGP 300 series / RX380 Radeon Xpress 200 CrossFire Xpress 3200 Radeon
Xpress 1250
480X / 570X / 580X 690 Series 7-Series 8-Series
Other ATI products and technologies
Multi-GPU
ATI Multi Rendering CrossFire X
GPU technologies
TruForm HyperMemory HyperZ PowerPlay AVIVO ATI Hybrid Graphics XGP
Workstations and HPC
FireGL FireMV FirePro 3D FireStream (Close to Metal)
Drivers and software
Catalyst fglrx (Linux) Hydravision HLSL2GLSL
Multimedia and handheld
All-in-Wonder Imageon2 Xilleon2
Video game console GPU
Top 7 Best Gaming Laptops Under 600 2017
4. HP laptop 17.3
5. Acer Aspire E 15 E5-575G-57D4 Laptop – SSD and Dedicated 2GB DDR5 RAM
6. ASUS P-Series P2540UA-AB51
7. Acer Aspire E5-575G-53VG
