The NVIDIA GeForce GTX 970 Review: Featuring EVGA
by Ryan Smith on September 26, 2014 10:00 AM ESTSynthetics
As always we’ll also take a quick look at synthetic performance. These tests mainly serve as a canary for finding important architectural and configuration changes.
Tessellation performance has scaled very closely with the change in SMMs and clock speeds, just as we would expect here.
Texel throughput has also taken a hit in accordance with the loss of SMMs and clock speed. Based on gaming performance the GTX 970 doesn’t appear to be too badly handicapped here, but it definitely doesn’t have much in the way of texel throughput to spare.
Pixel throughput on the other hand ends up being extremely odd and not at all what we were expecting. The GTX 970 takes an incredible dive here, with its pixel fillrate dropping by 26%. At a high level this test is bounded by memory bandwidth and ROP throughput, and both of these factors should be identical between GTX 980 and GTX 970. Instead we see GTX 970 lose more performance than should theoretically be possible, as the 26% drop is more than the accumulated difference between the clock speed and SMM differences.
At this point we’re still trying to figure out exactly what’s going on. We have no other evidence that there’s a difference in ROP throughput or memory bandwidth between the GTX 980 and GTX 970 so it is not clear to us where the difference lies. One possibility is that this is somehow bottlenecked at the Raster Engine level – where each of the four engines accounts for 25% of the work – but the pigeonhole principle means that NVIDIA can’t disable a GPC since at least 1 SMM must be active in each GPC partition. This matter will require further research.
Facebook
Twitter
RSS
155 Comments
View All Comments
Kalessian - Friday, September 26, 2014 - link
Is it really safe to overclock the memory like that when there aren't any heatsinks on them?Also, 1st?
Ryan Smith - Friday, September 26, 2014 - link
As long as you're not giving them additional voltage (which you can't do on this card): yes. GDDR5 does not consume all that much power, even if it is relatively more than DDR3. The airflow off of the fans is plenty for stock voltage.Viewgamer - Friday, September 26, 2014 - link
Why no Mantle benchmarks for Thief ?winterspan - Friday, September 26, 2014 - link
I'm assuming because this is an Nvidia review...eanazag - Friday, September 26, 2014 - link
No mantle is likely because it didn't give a great showing last time in the AMD mantle review. If I remember correctly, Thief maybe even had a performance regression with Mantle being used.Ammaross - Thursday, October 2, 2014 - link
Because Mantle only has benefit in CPU-capped performance. When you run benchmarks on an i7 or better, Mantle has no tangible benefit and sometimes has regressions.Viewgamer - Friday, September 26, 2014 - link
Or even Mantle benchmarks for BF4 for that matter ?Ryan Smith - Friday, September 26, 2014 - link
Apologies. The Mantle results have to be added manually since our graphing system can't handle multiple results for the same card automatically. I had actually entered in the data but neglected to regenerate the graphs.SeanJ76 - Monday, February 9, 2015 - link
Sounds like your not using EVGA PrecisonX 4.2.1, you can add as much voltage as you like to the 970 GTX FTW.........idiot.....P39Airacobra - Sunday, November 29, 2015 - link
Ok first of all EVGA Precision or the type of software has nothing to do with that, Also he has a valid concern about the V-Ram temps and the VRM. Also don't call people idiots! That's my Job! IDIOT!