NVIDIA’s GeForce GTX Titan Review, Part 2: Titan's Performance Unveiled
by Ryan Smith & Rahul Garg on February 21, 2013 9:00 AM ESTSynthetics
As always we’ll also take a quick look at synthetic performance to get a better look at Titan’s underpinnings. These tests are mostly for comparing cards from within a manufacturer, as opposed to directly comparing AMD and NVIDIA cards. We’ll start with 3DMark Vantage’s Pixel Fill test.
Pixel fill is a mix of a ROP test and a test to see if you have enough bandwidth to feed those ROPs. At the same time the smallest increase in theoretical performance for Titan over GTX 680 was in ROP performance, where a 50% increase in ROPs was met with a minor clockspeed reduction for a final increase in ROP performance of 25%.
The end result is that with gains of 28%, Titan’s lead over GTX 680 is just a hair more than its increase in theoretical ROP performance. Consequently at first glance it looks like Titan has enough memory and cache bandwidth to feed its 48 ROPs, which given where we’re at today with GDDR5 is good news as GDDR5 has very nearly run out of room.
Moving on, we have our 3DMark Vantage texture fillrate test, which does for texels and texture mapping units what the previous test does for ROPs.
Oddly enough, despite the fact that Titan’s texture performance improvements over GTX 680 were only on the range of 46%, here Titan is measured as having 62% more texturing performance. This may be how Titan is interplaying with its improved bandwidth, or it may be a case where some of the ancillary changes NVIDIA made to the texture paths for compute are somehow also beneficial to proper texturing performance.
Finally we’ll take a quick look at tessellation performance with TessMark.
Unsurprisingly, Titan is well ahead of anything else NVIDIA produces. At 49% faster it’s just a bit over the 46% theoretical performance improvement we would expect from the increased number of Polymorph Engines the extra 6 SMXes bring. Interestingly, as fast as GTX 580’s tessellation performance was, these results would indicate that Titan offers more than a generational jump in tessellation performance, nearly tripling GTX 580’s tessellation performance. Though at this time it’s not at all clear just what such tessellation performance is good for, as we seem to be reaching increasingly ridiculous levels.
Facebook
Twitter
RSS
337 Comments
View All Comments
CeriseCogburn - Tuesday, February 26, 2013 - link
Yes, and this is the core situation the radical chizow and others like him have chosen to completely ignore.Ivy is 22nm and only 14nm now appears to be possible as approx. 30 atoms are channel widths, with electromigration/plasma leakage hits a critical stage.
So the slowdown has already occurred, Moore's law is broken (decelleration has been occurring for a long time) , and the reality is near present with the "largest possible" die at Titan's node.
The number of atoms across in the "electric wire channel" and insulator sides width is down to countable on fingers and toes and it appears there's nearly no place to go.
That's why we keep hearing about quantum computing dreams, and why shrinkage steps have been less beneficial toward this wall.
So, expect the crybabies to be taking up a few notches more into an ever higher pitch the next couple of releases. It's coming, or rather it's here.
vanwazltoff - Friday, February 22, 2013 - link
the 690, 680 and 7970 have had almost a year to brew and improve with driver updates, i suspect that after a few drivers and an overclock titan will creep up on a 690 and will probably see a price deduction after a few months. dont clock out yet, just think what this could mean for 700 and 800 series cards, its obvious nvidia can deliverinitialised - Friday, February 22, 2013 - link
When are you guys going to start posting 4K performance for high end graphics?iceman-sven - Friday, February 22, 2013 - link
I am also wondering. Anandtech need to buy the Sharp PN-K321 fast. I will upgrade from my 2560x1600 to 4k in the next 12 months.I hope Anandtech does a rerun of some benchmarks with 4k and Titan SLI configurations. I am planning to buy 2 Titan for this.
Ryan Smith - Monday, February 25, 2013 - link
When someone releases a suitable desktop monitor and we can acquire it on a long-term basis. Something like Sharp's 32-incher is the right resolution, but it really pushes the boundary for what can be called a "desktop" monitor.ElminsterTCOM - Friday, February 22, 2013 - link
I was wondering if you could pop this card into a Mac Pro and let us know if it is compatible? This would be a great card for 3D modeling!Saxie81 - Friday, February 22, 2013 - link
I'm wondering why the other websites that give reviews, benchmarks etc, have missed the mark with this card. Everywhere I look, they are posting nothing but game benchmarks, this is why I keep coming to Anandtech. This clearly is meant for more than that. I'm looking @ it for gaming and 3d rendering. I would have loved to have seen maybe Rendering times on a simple image in Blender etc, but the compute benchmarks gives a pretty good indication of what the Titan is capable of. Great article as always, Ryan, and welcome Rahul!Zoeff - Friday, February 22, 2013 - link
Looking at the Crysis 1080p at highest settings benchmark. I guess they're the wrong way around? :)Ryan Smith - Monday, February 25, 2013 - link
Do'h. Fixed.realneil - Friday, February 22, 2013 - link
Seems like whenever `anyone` releases the ~newest/best~ video card, they always price it at a grand. So this isn't surprising to me at all. How much were the Matrix cards from ASUS when they were new?I just can't see spending that much for it though. A pair of 680s or 7970s would get the job done for me.