AMD Radeon HD 6790 1GB Review

[SKYMTL]

When NVIDIA introduced their GTX 550 Ti, the reaction of the market and most of the mainstream press was relatively mixed. At $150 it fell into a price bracket where AMD had very little to answer with but at the same time, we felt that it was overpriced and really didn’t bring anything new to the table. Both of these points are now being covered since AMD is now releasing their own $150 graphics card and in order to cope with a potential competitor, the GTX 550 Ti has seen its price drop to between $130 and $145.

The aptly named HD 6790 1GB will be gunning for a number of cards in NVIDIA’s current lineup while sitting between the older HD 5830 and HD 5770 cards. Contrary to what many believed, the first of AMD’s lower-end lineup isn’t based off of the Turks or Caicos architectures but rather a revised Barts-series core which is dubbed the Barts LE.

If the right kind of card is offered, the $125 to $175 price range can be highly profitable for a company like AMD since the vast majority of non-integrated GPU volume comes from here. However, by and large the most important aspect of this market is its appeal to large system builders like Dell, HP and Lenovo who often draw upon sub-$200 cards for their performance-oriented products. We’re sure to see the HD 6790 alongside the OEM-only HD 6770 being offered in a number of systems soon after launch.

Even though the HD 6790 will be retailing for a mere $150, we have some high expectations for it. With the inclusion of technologies like UVD3, AMD’s APP and Eyefinity, a small amount of money can potentially go a long way.

AMD’s target for the HD 6790 is quite obviously the GTX 550 Ti but the potential for performance that equals some of the many GTX 460 versions is also a real possibility. Upon first glance it seems like AMD is introducing the card many wished the GTX 550 Ti would have been but it will be interesting to see where it ultimately lands once the dust settles.

 

[SKYMTL]

Diving into the Barts LE Core

Diving into the Barts LE Core

Unlike what they did with the Evergreen series, AMD isn’t trying to rewrite the book on performance or push new boundaries with their “refreshed” cards. Rather, the dual engine architecture which distinguished Cypress has been generally carried over with a few modifications made along the way. Barts isn’t the focus of a fundamental architectural change in any way, shape or form. It is all about the gradual refinement of an existing design into something with with a smaller die size and superior performance per watt. The end result is that AMD can now push a more affordable high performance solution to end users without sacrificing profit margins.

Cypress Core​

At first glance, there isn’t all that much to distinguish the full Barts XT core from the outgoing Cypress other than the obvious change in the number of SIMDs, which results in less overall SPs (or Stream Cores as AMD calls them). In order to achieve high end performance which is optimized for efficiency, the engineers started with the basic back-end of the Cypress XT and built up from there. This means the graphics engine including the fixed function stages, L2 cache, ROP arrays and memory controllers have gone largely untouched. There were some changes to improve tessellation performance and communication between the different stages within the rendering pipeline but the vast majority of tweaks happened within the SIMD engine layout.

Since the Cypress Pro (which AMD replaced with the Barts XT) used a full Cypress XT core with a few disabled SIMDs, it was inherently inefficient from a number of perspectives. In order to increase performance per watt, the HD 5850 was taken as a benchmark and the engineers set about trying to match the “sweet spot” it occupied in the market with a slightly revised layout.

The Barts core in its XT, Pro and LE forms retains the same 80 SPs along with four texture units, 32KB of Local Data Share and 16KB of L1 texture cache per SIMD as the Cypress series. However, where things have changed lies in the total quantity of SIMDs per core which has shrunk from 20 down to the 14 we now see in Barts. This in effect lowers the maximum possible SPs from 1600 down to 1120 and the number of TMUs from 80 to 56. However, since the render back-ends aren’t touched, the Barts XT has a full 32 ROPs. The memory interface also remains at 256-bit for the GDDR5 which is actually a first for an architecture that is aimed exclusively at the sub-$250 market.

The Barts LE however is a different animal from a number of perspectives. In order to further increase yields and reduce the overall price per core, AMD has eliminated an additional two SIMD engines on top of the two already cut from the Barts Pro. The result is 10 SIMD engines totaling 800 cores and 40 Texture Units but the cutting didn’t just stop there. With the higher clock speeds these changes allowed, some separation between the Pro and LE was needed so a full half of the Barts ROPs were disabled. This change also affects the number of colour ROPs and L2 cache available on the LE.

Other than the obvious changes to the SIMD layout, there has also been some window dressing going on behind the scenes. The main graphics engine which entails the fixed function stages of AMD’s architecture is for the most part carried over from the HD 5800 series without any significant changes but there is one major addition: an enhanced tessellator.

One of the main critiques leveled against Cypress series GPUs was their tendency to choke under heavy tessellation workloads. Through improved thread management in the shader engines as well as enhanced buffering for tessellation draw calls, AMD has been able to manage up to a twofold increase in overall tessellation performance over the HD 5800 cards. We can also see that in an effort to increase rendering efficiency even more, AMD has broken up the Ultra Threaded Dispatch Processor into two with each section having its own instruction and constant cache. This dispatch processor basically acts like a traffic cop, directing draw calls to the SIMD arrays. With each directing its own “half” of the SIMD engine, rendering information can be processed at a much quicker rate without adding to the overall die size of the Barts.

To put this into layman’s terms, the Barts architecture is able to remove the tessellation bottleneck which allows more of the rasterizers and SPs to be used more efficiently and as a result DX11 performance in particular has been increased.

 

[SKYMTL]

The HD 6790 1GB within AMD’s Current Lineup

The HD 6790 1GB within AMD’s Current Lineup

The HD 6790 1GB seems to fit well into AMD’s current lineup while competing with NVIDIA’s GTX 550 Ti. At this point the Barts LE fits right between the HD 6850 and the HD 5770. Also remember that the Juniper XT core is also being used in the OEM-only HD 6770.

Other than the rebranding of the Juniper cores, there really hasn’t been much movement below the $150 price point in either AMD’s or NVIDIA’s lineup over the last few months. Many expected the Turks and Caicos architectures sometime between Q4 2010 and Q1 2011 but other than their use in a few OEM specific scenarios as the HD 6670 and 6450 respectively, we haven’t seen a widespread release. Indeed, it seems like for the time being both every graphics card manufacturer is concentrating upon the $125 and high markets for retail while keeping entry level GPUs for system builders.

One of the more interesting aspects of the HD 6790 is the similarity of its specifications to the old HD 5770. The only real difference between them other than the slightly more advanced architecture present in the Barts core is the memory bus. Thus, we expect performance to be very close between these two GPUs.

When looking at the chart above, a few questions will likely come running into most people’s brains. Even though AMD has drastically cut down on the number of Stream Processors and ROPs, the maximum board power of this card is right up there with the HD 6870. However, it is important to remember that this is how much the card CAN draw rather than how much it WILL draw.

AMD and many of their board partners will be using HD 6870 board designs for the HD 6790 cards. This bodes quite well for overclocking potential even though we will likely see slightly elevated consumption numbers due to the HD 6850’s use of a slightly more efficient on-board PWM. In addition, the HD 6790’s 65Mhz core speed bump and 200Mhz (QDR) GDDR5 increase will also contribute to some differences between its efficiency numbers and those of the HD 6850 1GB.

As we already mentioned, the HD 6790 will fit into the lineup just below AMD’s HD 6850. Surprisingly, the HD 5770 and HD 5750 will continue on well into Q2 2011 and possibly beyond. Many were hoping these cards would eventually be replaced but it looks like that won’t happen for some time as AMD feels they give an excellent option to more budget-minded consumers.

We’re sure that incorrect parallels will likely be drawn between this card and the HD 5830. The HD 5830 ended up being universally lambasted on release due to its price not meshing well with lackluster performance numbers for a 5800-series product. With the HD 6790 on the other hand, there are no illusions of grandeur since it is quite obviously targeted towards a market below the mid-range HD 6800-series and far under the flagship HD 6900-series.

 

[SKYMTL]

AMD EyeSpeed & UVD3

AMD EyeSpeed

The Northern Islands family of GPUs has a whole stable of video playback features, and in order to keep them all under banner AMD created the Eyespeed brand. Eyespeed will be the all-encompassing term given to all of the multimedia enhancing technologies such as pre / post processing, transcoding and HD playback within a unified ecosystem.

Eyespeed is split within two main spheres of influence: leveraging parallel processing for improved performance and video decoding through AMD’s UVD3.

UVD3; UVD2 on Steroids

As many of you probably already know, AMD’s Universal Video Decoder has been around for years and is known as one of the most capable video processing platforms currently available. UVD is now taking the next logical step forward with an expanded list of accelerated codecs in addition to the ones which were already compatible with past iterations.

One of the main features which have been added to the newly minted UVD3 is the ability to decode videos which use MVC encoding. As part of the H264 / MPEG-4 AVC codec, MVC is responsible for creating the dual video bitstreams which are essential for stereoscopic 3D output. Supporting this standard brings AMD’s GPUs the ability to process Blu Ray 3D movies through a HDMI 1.4a connector.

MPEG-4 Part 2 hardware acceleration for DivX and Xvid codecs has also been added but there is no mention made about the Nero Digital codec. For the time being, we’ll assume that Nero Digital acceleration will be added at a later date.

AMD’s main focus for these new graphics cards and for future products is to go beyond simply decoding HD content and instead add high end image quality improvements prior to the signal reaching the display. Through the use of the compute resources within a given system, additional pre and post-processing can be done before outputting an HD video stream.

AMD claims the additional processing their products can accomplish will significantly boost overall image quality whether it is for a simple upscale standard definition image or a true high definition video stream. The HQV benchmark is a highly, highly, highly subjective metric in which to determine image quality but supposedly the HD 6000 series will simply destroy the competition once all of its video processing features are enabled.

 

[SKYMTL]

From ATI Stream to AMD APP Technology

From ATI Stream to AMD APP Technology

As AMD is moving to all but abolish the ATI brand, a number of technologies are being renamed and rationalized. The Stream name was once given to ATI’s GPGPU compute initiative to differentiate it from NVIDIA’s highly successful CUDA environment. Things are about to change….a bit.

In order to carry on Stream’s torch, AMD Accelerated Parallel Processing or APP has been created. Yes, the whole “App” moniker has been used so much that it’s now becoming a bit of a cliché but in this case, it seems to be aptly translated. This is now an all-encompassing term which can be used for graphics cards as well as AMD’s new upcoming generation of Fusion APUs.

AMD’s new APP SDK v2.2 is about to hit developers’ doorsteps and with it will come the integration of OpenCL computing for both x86-based CPUs and GPUs. This is one of APP’s major benefits over NVIDIA’s competing solution as it can be leveraged for a heterogeneous environment where specific tasks are sent towards the processor which will complete them most efficiently.

From our understanding, Stream’s name may have changed but its goal to deliver high performance computing on the GPU through OpenCL, DirectCompute and other APIs is still very much alive and well. If anything, it has actually expanded now that AMD is able to leverage both their CPUs and GPUs under the same programming umbrella.

 

[SKYMTL]

A Closer Look at the Reference HD 6790 1GB

A Closer Look at the Reference HD 6790 1GB

​

The reference HD 6790 1GB which was sent to us is based off of a HD 6870 PCB which makes it a good 9 ¾” long. Otherwise, there really isn’t anything particularly remarkable about this card since it uses the same basic blower-style heatsink setup as nearly all other HD 6000-series products. It highlights this design with a ribbed side extrusion boasting red inserts.

​

Much like the HD 6870, the HD 6790 1GB uses a pair of 6-pin power connectors which is interesting considering the amount of cutting which has gone into the Barts LE core. Since AMD is using a HD 6870 PCB, they decided to retain the normal dual 6-pin setup and high end PWM of the HD 6870 in order to give this lower end card some additional overclocking headroom.

As a side note, some of AMD’s board partners will be using standard PCBs which only include a single PCI-E power connector and supposedly slightly lower power consumption numbers.

​

The display connector selection on this card is identical to that of nearly every other AMD card with a pair of DisplayPort outputs, two DVI connectors and a single HDMI 1.3 connector. This means a single HD 6790 has support for AMD’s Eyefinity technology in a 3x1 setup…though we can’t imagine that it would offer enough performance to properly play games at such ultra high end resolutions.

​

In terms of overall length, 9 ¾” is much longer than a GTX 550 Ti but in all reality that really shouldn’t matter to most people since the HD 6790 won’t overhang the edge of a standard ATX motherboard. This means case compatibility shouldn’t be an issue unless you’re using a small form factor enclosure.

​

In comparison to other AMD cards, we get what’s expected: the reference HD 6790 is longer than the HD 6850 and the same length as the HD 6870.

 

[SKYMTL]

Test System & Setup

Test System & Setup

Processor: Intel Core i7 920(ES) @ 4.0Ghz (Turbo Mode Enabled)
Memory: Corsair 3x2GB Dominator DDR3 1600Mhz
Motherboard: Gigabyte EX58-UD5
Cooling: CoolIT Boreas mTEC + Scythe Fan Controller (Off for Power Consumption tests)
Disk Drive: Pioneer DVD Writer
Hard Drive: Western Digital Caviar Black 640GB
Power Supply: Corsair HX1000W
Monitor: Samsung 305T 30” widescreen LCD
OS: Windows 7 Ultimate N x64 SP1


Graphics Cards:

HD 6790 1GB (Ref)
HD 6850 1GB (Ref)
HD 5830 1GB (Ref)
HD 5770 1GB (Ref)

GTX 550 Ti 1GB (EVGA, Flashed w/ref. BIOS)
NVIDIA GTX 560 Ti 1GB (Ref)
GTX 460 1GB (Ref)
GTX 460 1GB SE (Gigabyte / Custom Cooled)
GTX 460 768MB (Ref)


Drivers:

NVIDIA 270.51
ATI 11.4 Preview (HD 6790)
ATI 11.4 Preview + CAP 11.2 R4

Note: Even though AMD claims the “AMD Optimized Tessellation” feature in the 11.1a drivers has not yet been implemented, we have changed the setting to “Off” in order to ensure additional, untested optimizations are not enabled.

Applications Used:

3DMark 11
Aliens Versus Predator
Battlefield: Bad Company 2
DiRT 2
F1 2010
Just Cause 2
Lost Planet
Metro 2033
Unigine: Heaven


*Notes:

FOR MORE INFORMATION ABOUT OUR BENCHMARKING PROCESS PLEASE SEE THIS ARTICLE

- All games tested have been patched to their latest version

- The OS has had all the latest hotfixes and updates installed

- All scores you see are the averages after 3 benchmark runs

All game-specific methodologies are explained above the graphs for each game

All IQ settings were adjusted in-game

 

[SKYMTL]

3DMark 11 (DX11)

3DMark 11 (DX11)

3DMark 11 is the latest in a long line of synthetic benchmarking programs from the Futuremark Corporation. This is their first foray into the DX11 rendering field and the result is a program that incorporates all of the latest techniques into a stunning display of imagery. Tessellation, depth of field, HDR, OpenCL physics and many others are on display here. In the benchmarks below we have included the results (at default settings) for both the Performance and Extreme presets.


Performance Preset

Extreme Preset

 

[SKYMTL]

Aliens Versus Predator (DX11)

Aliens Versus Predator (DX11)

When benchmarking Aliens Versus Predator, we played through the whole game in order to find a section which represents a “worst case” scenario. We finally decided to include “The Refinery” level which includes a large open space and several visual features that really tax a GPU. For this run-through, we start from within the first tunnel, make our way over the bridge on the right (blowing up several propane tanks in the process), head back over the bridge and finally climb the tower until the first run-in with an Alien. In total, the time spent is about four minutes per run. Framerates are recorded with FRAPS.


1680 x 1050

1920 x 1200

 

[SKYMTL]

BattleField: Bad Company 2 (DX11)

BattleField: Bad Company 2 (DX11)

To benchmark BF: BC2 we used a five minute stretch of gameplay starting from the second checkpoint (after the helicopter takes off) of the second single player mission up until your battle with the tank commences. Framerates are recorded with FRAPS.


1680 x 1050

1920 x 1200