NVIDIA's GeForce 7800 GTX Hits The Ground Running
by Derek Wilson on June 22, 2005 9:00 AM EST- Posted in
- GPUs
Inside The Pipes
The pixel pipe is made up of two vector units and a texture unit that all operate together to facilitate effective shader program execution. There are a couple mini-ALUs in each shader pipeline that allow operations such as a free fp16 normalize and other specialized features that relate to and assist the two main ALUs.
Even though this block diagram looks slightly different from ones shown during the 6800 launch, NVIDIA has informed us that these mini-ALUs were also present in NV4x hardware. There was much talk when the 6800 launched about the distinct functionality each of the main shader ALUs had. In NV4x, only one ALU had the ability to perform a single clock MADD (multiply-add). Similarly, only one ALU assisted in texture address operations for the texture unit. Simply having these two distinct ALUs (regardless of their functionality difference) is what was able to push the NV4x so much faster than the NV3x architecture.
In their ongoing research into commonly used shaders (and likely much of their work with shader replacement), NVIDIA discovered that a very high percentage of shader instructions were MADDs. Multiply-add is extremely common in 3D mathematics as linear algebra, matrix manipulation, and vector calculus are a huge part of graphics. G70 implements MADD on both main Shader ALUs. Taking into account the 50% increase in shader pipelines and each pipe's ability to compute twice as many MADD operations per clock, the G70 has the theoretical ability to triple MADD performance over the NV4x architecture (on a clock for clock basis).
Of course, we pressed the development team to tell us if both Shader ALUs featured identical functionality. The answer is that they do not. Other than knowing that only one ALU is responsible for assisting the texture hardware, we were unable to extract a detailed answer about how similar the ALUs are. Suffice it to say that they still don't share all features, but that NVIDIA certainly feels that the current setup will allow G70 to extract twice the shader performance for a single fragment over NV4x (depending on the shader of course). We have also learned that the penalty for branching in the pixel shaders is much less than in previous hardware. This may or may not mean that the pipelines are less dependent on following the exact same instruction path, but we really don't have the ability to determine what is going on at that level.
Facebook
Twitter
RSS
127 Comments
View All Comments
mrdeez - Thursday, June 23, 2005 - link
also:maybe gaming in hi def......ona big screenmrdeez - Thursday, June 23, 2005 - link
#114Dude just stfu......we are here to comment what we want and say it freely......minus threats and name calling....as i said before this card is not for gamers...maybe elite gamers that have a monitor that does these resolutions but most gamers i know have went to lcd and i have yet to see any lcd[im sure there are some]do these resolutions so this card really is a card for crt elite gamers......lol with those resolutions on a 21 inch monitor you would need binoculars as glasses to play the game....the tanks on bf2 would be ant like small....
bob661 - Thursday, June 23, 2005 - link
#114I am SO glad that Anand remains in business despite all the bitches that are in these comment sections.
Locut0s - Thursday, June 23, 2005 - link
Those who are complaining that they should have reviewed at lower resolutions should think for a minute. First of all you are talking about a 600 buck card, most people who have that kind of money to spend on a card also have a monitor that is capable of 1600x1200 or better. Also benchmarking at any lower resolution on a card like this in todays games is almost pointless as you are almost entirely CPU bound at those resolutions. Do you really want to see page after page of 1024x768 charts that differ by only 4-5 percent at the most?Also give the editors a break when it comes to writing these articles. As others have said this is not a subscription site and given the number of visitors and the quality of the articles I'm amazed, and gratified, that the people of Anandtech keep putting out article after long article despite all the winning that goes on over spelling mistakes and graph errors that more often than not are corrected within a few hours.
SDA - Thursday, June 23, 2005 - link
That's a really great comparison, #112, especially seeing as how we pay for AnandTech and any problems with it could leave us stranded in the middle of nowhere. And so witty, too!Jarred, ah, thanks.
Questar - Thursday, June 23, 2005 - link
"Our Web Editor is on vacation and we are all doing our own HTML and editing for the next 10 days. In our usual process, the article goes from an Editor to the Web Editor who codes the article, checks the grammar, and checks for obvious content errors. Those steps are not in the loop right now."" do know Derek as a very conscientious Editor and I would ask that you please give him, and the rest of us, a little slack this next week and a half"
Dear Mr. Fink,
I am sorry to hear about the problems you have had with your vehicle breakdowns. You see, our quality inspector was on vacation that week, so we just shipped our vehicles strait off the assembly line. Please cut us a little slack, as we usually build much better vehicles.
Sincerly,
Buncha Crap,
CEO
Crappy Moters Inc.
frisbfreek - Thursday, June 23, 2005 - link
my question is how did they do hi res 2048x1536 when the card is only single-link DVI? Shouldn't either an analog connection or dual-link be necessary?yacoub - Thursday, June 23, 2005 - link
#108 - what do you want, a $2000 CPU to go with your $1200 in GPUs? =PCtK - Thursday, June 23, 2005 - link
so dual display is still not available with dual 7800s?!?!?!?!?smn198 - Thursday, June 23, 2005 - link
Come on Intel & AMD. Keep up!