The NVIDIA GeForce GTX 750 Ti and GTX 750 Review: Maxwell Makes Its Move
by Ryan Smith & Ganesh T S on February 18, 2014 9:00 AM ESTGeForce GTX 750 Ti & GTX 750 Specifications & Positioning
Having finally covered the architecture and design choices of Maxwell in-depth, let’s talk about the retail hardware itself. As me mentioned in our introduction NVIDIA’s first play with Maxwell will be the high volume markets that GK107 resides in. Ultimately this means we should end up seeing GM107 in mobile GeForce and in server GRID products too, but first NVIDIA is starting with the desktop video card market. The desktop market affords NVIDIA the chance to take more direct control, so while server and mobile products go through additional phases of OEM/partner validation, desktop can be the first up to bat.
In a move a bit different from usual for an NVIDIA desktop video card launch, NVIDIA is launching multiple GM107 cards at once. Typically they’d stretch this out over a couple of weeks, but with the 700 series already on the market (and nothing better to do with salvaged chips) there’s little reason to wait.
| NVIDIA GPU Specification Comparison | ||||||
| GTX 660 | GTX 750 Ti | GTX 750 | GTX 650 | |||
| CUDA Cores | 960 | 640 | 512 | 384 | ||
| Texture Units | 80 | 40 | 32 | 32 | ||
| ROPs | 24 | 16 | 16 | 16 | ||
| Core Clock | 980MHz | 1020MHz | 1020MHz | 1058MHz | ||
| Boost Clock | 1033MHz | 1085MHz | 1085MHz | N/A | ||
| Memory Clock | 6GHz GDDR5 | 5.4GHz GDDR5 | 5GHz GDDR5 | 5GHz GDDR5 | ||
| Memory Bus Width | 192-bit | 128-bit | 128-bit | 128-bit | ||
| VRAM | 2GB | 2GB | 1GB | 1GB | ||
| FP64 | 1/24 | 1/32 | 1/32 | 1/24 | ||
| TDP | 140W | 60W | 55W | 64W | ||
| Transistor Count | 2.54B | 1.87B | 1.87B | 1.3B | ||
| Manufacturing Process | TSMC 28nm | TSMC 28nm | TSMC 28nm | TSMC 28nm | ||
| Architecture | Kepler | Maxwell | Maxwell | Kepler | ||
| GPU | GK106 | GM107 | GM107 | GK107 | ||
| Launch Date | 09/13/12 | 02/18/14 | 02/18/14 | 09/13/12 | ||
| Launch Price | $229 | $149 | $119 | $109 | ||
Starting with the GeForce GTX 750 Ti, this is NVIDIA’s flagship GM107 product. GTX 750 Ti packs a complete GM107 implementation, comprising 5 SMMs, 640 CUDA cores, 16 ROPs, and 40 texture units, and fed by 2MB of L2 cache. In terms of design GM107 is a clear successor to GK107, as evidenced by use of just 16 ROPs.
Nevertheless it’s very important to keep in mind that thanks to the Maxwell architecture GM107 hits well above its weight, so the CUDA core count difference between the GTX 750 Ti and GTX 660 makes these parts look much farther apart than they actually are. At least so long as we’re comparing Kepler and Maxwell parts, the product number is going to be the more meaningful designation as specs alone will not capture the relative power and efficiency of these designs.
GTX 750 Ti Block Diagram
GTX 750 Ti’s GM107 GPU is in turn paired with 2GB of GDDR5, on a 128-bit bus. The use of 2GB of VRAM is common for cards at this price range, whereas the 128-bit bus is narrower than competing cards, but something NVIDIA doesn’t expect to be badly hindered by due to their efficiency improvements elsewhere. On the other hand the company also expects some of its partners to roll out a smaller numbers of 1GB cards in the near future, and while these will be $10 cheaper we’re of the opinion that there’s no reason to have less than 2GB of VRAM on a card in this price range.
When it comes to clockspeeds NVIDIA will be shipping GTX 750 Ti and its GM107 GPU at slightly higher clockspeeds than its Kepler counterparts. NVIDIA is putting the core clock at 1020MHz with an official boost clock of 1085MHz; and as this is a GPU Boost 2.0 we’ll see the highest boost bins top out well over 1100MHz. The VRAM on the other hand will be clocked at 5.4GHz, which on a 128-bit bus is enough to provide 86.4GB/sec of memory bandwidth. The use of 5.4GHz RAM here is a bit off an oddity since no one produces GDDR5 RAM at that speed bin – these cards will have to be equipped with 6GHz RAM in order to meet the required specifications – so we strongly suspect this is a board limitation, especially since the board is virtually identical to NVIDIA’s board design for GTX 650 Ti, which also has the same 5.4GHz memory clock.
Switching gears for a moment, let’s now cover the GTX 750. GTX 750 is based on a cut-down/salvaged GM107 GPU, utilizing just 4 of GM107’s 5 SMMs. This reduces the CUDA core count to 512 and the number of texture units to 32, but it leaves the ROP/L2/memory partitions fully intact. GPU clockspeeds are identical to GTX 750 Ti – 1020MHz base, 1085MHz boost – while the memory subsystem is further reduced to 1GB of GDDR5 running at 5GHz. As such, the GTX 750 will fall behind the 750 Ti by anywhere between 8% and 20%, depending on whether the workload being measured is memory bound or shader/texture bound.
GTX 750 Block Diagram
But perhaps the most impressive metric is power consumption. Due to NVIDIA’s optimizations efforts and 2x perf-per-watt goal for Maxwell, power consumption is way down versus the GK106 based parts that the GTX 750 and GTX 750 Ti will be replacing. NVIDIA’s official TDP – which is generally comparable within the NVIDIA product lineup – is just 60W for GTX 750 Ti, and a lower still 55W for GTX 750. For the sake of comparison this is a bit lower than either GTX 650 or GT 640 (the desktop GK107 parts), and more importantly these new GTX 750 series cards are quite a bit more powerful than the GK107 cards at similar TDPs.
The end result is that we’re looking at either a significant reduction in power consumption for similar performance to GK106, or a massive increase in performance as compared to GK107. Given the power limited nature of mobile in particular, this makes GM107 an especially potent GPU for NVIDIA.
With that in mind, it’s interesting to note that all of this comes despite the fact that both transistor counts and die sizes are up compared to GK107. GK107 was 118mm2 for 1.3 billion transistors, and meanwhile GM107 is 148mm2 for 1.87B transistors. The fact that NVIDIA was able to increase their transistor count by 43% has a lot to with how much faster GM107 is than GK107, but at the same time the fact that die size itself is only up by 25% showcases those die size optimizations we talked about earlier.
Ultimately when we’re on a single node – this is all TSMC 28nm HP, not HPM – there’s typically a loose correlation between die size and power consumption in a chip stack, which is something NVIDIA has been able to dodge with GM107. Due to all of their power optimizations NVIDIA has been able to grow GK107 to GM107 essentially for free, and this still doesn’t take into account the higher IPC of Maxwell.
NVIDIA's Product Positioning
With up to 640 CUDA cores that hit above their weight and a TDP below 75W, GTX 750 Ti and GTX 750 will be filling a duo of roles in the NVIDIA lineup. From a performance and price standpoint NVIDIA is placing them between the GK106 flagship GTX 660 and the GK107 flagship GTX 650. GTX 750 Ti isn’t quite fast enough to displace GTX 660, so GTX 660 continues to live for another day while NVIDIA uses GTX 750 Ti to retire GTX 650 Ti Boost, and GTX 750 to retire GTX 650 Ti. Both of those were based on cut-down GK106 GPUs, so there’s an immediate benefit to NVIDIA of reducing production costs, and for consumers these new GTX 750 series cards will be faster than the cards they replace by roughly the same performance factor as we’ve seen elsewhere for GTX 700 series cards. Elsewhere GTX 650 and below will also live for another day as budget offerings, due to GK107’s smaller die size and lower production costs.
Meanwhile these sub-75W TDPs means that the GTX 750 series are now going to be NVIDIA’s best cards for the sub-75W PCIe bus powered only market. GTX 650, despite its TDP, required a 6pin PCIe power connector, so in that space the GTX 750 series is replacing the even slower GT 640 (GK107 + DDR3) as NVIDIA’s top card. For the purposes of the desktop video card space this puts the GTX 750 series squarely in the middle of the HTPC space and OEM upgrade space.
The HTPC space has long favored sub-75W cards for noise and space reasons, and NVIDIA’s video decode power improvements should be further welcome in this space. In this sense NVIDIA’s petite products for smaller form factor computers will be an interesting split between the reference GTX 780 and the GTX 750 series. Reference GTX 780 being well suited for small form factor designs due to its well-constructed blower, and the GTX 750 series being well suited for very low power designs or designs that don’t meet the air intake requirements for a blower.
As for the OEM upgrade space, this is a fairly straightforward but large market. The two sweet spots for video card upgrades for OEM systems are sub-150W cards for the OEMs that supply a single PCIe power plug (some of them), and sub-75W cards for OEMs that don’t supply a PCIe power plug, or even a very powerful PSU in the first place (more of them). These scenarios are fundamentally power limited – not unlike mobile – so having the fastest card at sub-150W and sub-75W is potentially very good for business. In NVIDIA’s case they are making a clear play for the sub-75W market with these cards, and one of their marketing pushes will be to go after OEM upgrades.
That said, whenever we’re talking about mainstream cards the Asia-Pacific (APAC) market becomes especially important due to its size and higher price sensitivity. Countries like China have been strong markets for cards like the GTX 750 series, so NVIDIA is expecting much of the same here. Once again NVIDIA’s strongest play will be the sub-75W market given their power advantage, as in unrestricted power scenarios AMD will have the upper hand. The wild card factor here will be APAC’s far greater use of internet cafes and LAN gaming centers, as operators are likely to be more interested in power consumption when it’s spread out over numerous computers.
Pricing & Competitive Landscape
Wrapping things up, the GTX 750 series will be a hard launch with immediate availability on a global scale. NVIDIA is placing the MSRP for the GTX 750 Ti at $149 and the MSRP for the GTX 750 at $119, right between the GTX 660 and GTX 650, while pushing GTX 650 Ti out of the picture entirely. From a performance perspective these cards won’t offer the kind of performance that will entice most 600 series owners to upgrade (though the performance gains against GT 640 are striking), but NVIDIA is making a major effort to target GTX 550 Ti and GTS 450 owners as those cards turn 3-4 years old, with the GTX 750 series able to easily double their performance while reducing power consumption.
AMD’s competition for the GTX 750 series will be the recently launched Radeon R7 265, and the recently price dropped Radeon R7 260X, which are set to go for $149 and $119 respectively. Unfortunately R7 265 was not a hard launch and is not expected until the end of this month, so NVIDIA is going to have roughly two weeks of availability ahead of AMD at $149, and meanwhile at $119 we’re still waiting to see the announced price cuts take effect.
From a price/performance standpoint NVIDIA is not going to be especially competitive, and this is similar to how NVIDIA handled the mainstream cards in the 600 series. NVIDIA is content to take second place on a price/performance basis, relying on their stronger brand name and greater brick & mortar retail presence to make up for what they lose from lower performance, a strategy that apparently worked well for the 600 series. Accordingly, once they hit the market (and assuming they stay at MSRP), R7 265 and R7 260X will be faster than their GTX 750 series’ counterparts, as AMD is just outright throwing more hardware at the problem. But as a result AMD will not be able to compete with NVIDIA’s power efficiency; in those sub-75W markets NVIDIA will have the more powerful (and more expensive) options.
| Winter 2014 GPU Pricing Comparison | |||||
| AMD | Price | NVIDIA | |||
| Radeon R9 270 | $250 | GeForce GTX 760 | |||
| $190 | GeForce GTX 660 | ||||
| Radeon R7 265 | $150 | GeForce GTX 750 Ti | |||
| Radeon R7 260 | $130 | ||||
| Radeon R7 260X (New MSRP) | $120 | GeForce GTX 750 | |||
| Radeon R7 250X | $100 | GeForce GTX 650 | |||
| Radeon R7 250 | $90 | GeForce GT 640 | |||
Facebook
Twitter
RSS
177 Comments
View All Comments
TheJian - Wednesday, February 19, 2014 - link
You are only able to say AMD is winning with 265 because of magical pricing that probably won't exist, just like 290x/290 are not $550/400, which we now know are really $709/550 (amazon's lowest pricing, which is below newegg on 290, about even on 290x - amazon has 290x in stock). At least most are out of stock now, so maybe they're selling better or it really is just a shortage of chips like PNY says. I'm guessing the shortage of chips that can run 1ghz is causing problems and higher pricing on 290/290x, not selling like crazy. If they were selling like crazy to miners etc AMD would have had a quarter like NV had where GPU revenues rose 14% on the backs of HIGH-END gpu sales in a 11% down PC market. The 290/290x are AMD's high end, yet selling out means zero profits? So High-End isn't selling much and is just a shortage of 1ghz chips then right? 10mil console chips were all of AMD's gpu profits (10mil x $12 each=120mil pretty much exactly AMD's profits).I don't see how Anandtech etc can say crypto mining is insane, when AMD's quarterly report shows miners must not be buying them much at all after the first rush at launch. Otherwise they would have made more than just console money. AMD said they get low double digits on consoles now (so not mid which would be 15%, if closer to 15% profits would be like 150mil), which is 8.2mil units already purchased in retail consoles, and another ~2mil in transit or already in MS/Sony being boxed up for more retail boxes. AMD gets their money long before we see it on the shelf in a console (hence the ~2mil in transition). MS/Sony don't pay AMD AFTER the console sales, they pay them BEFORE it gets anywhere near a box on a shelf. So AMD has already sold more than the shelf sales show.
On the flipside, NV has a quarter with ~$145mil in profits and basically ALL of that is from GPU's. So again, if AMD is selling out (in any volume that is) how come they didn't have $240mil in profits or something like this? Why no profits from GPU's showing up? There must be a real shortage that isn't due to them selling out like crazy, but instead due to manufacturing chips that can do 1ghz without throttling. This is the ONLY assumption that fits the financial data. Miners are NOT buying these in massive quantities. AMD just can't make enough to satisfy anyone, thus the price goes through the roof and companies like PNY say they can't get chips. In turn this causes AMD's MSRP to basically be magical fairy dust pricing which may not be REALITY for many months to come :( Your price perf story doesn't fit. AMD is winning nothing.
Let me know when you can buy a 290 or 290x for $400 or $550. Let me know when you can buy a 265 for $149. This may turn out to be real for 265 but it isn't now and Anandtech shouldn't be comparing cards that don't even exist yet and pricing is unknown. I mean the reviews of 290/290x said "these are awesome buys", blah blah, but at $709 for 290x isn't it a terrible deal with 780TI OC models going for the same exact price but winning by 20%?
http://hardocp.com/article/2014/02/10/msi_geforce_...
OC 290x vs. OC 780ti.
"The current street price of the ASUS R9 290X DirectCU II OC is $699.99 at several etailers (if you can find it in stock), representing a significant bump from its MSRP of $569.99. If you were to compare the two cards at MSRP, then the 20% performance difference between these could easily be accounted for with the 20% difference in price. However, at the current street pricing, the MSI GeForce GTX 780 Ti GAMING 3G simply slaps the ASUS R9 290X DirectCU II OC around with a large rainbow trout."
Slaps AMD around like a rainbow trout? OK, OC & price contest settled then. Custom cooling won't magically trump 780TI and MSRP for 290x of $550 and reality for a card that can actually do AMD's magical ref speeds and up is a $150 difference. I don't know why anyone would buy a 265 for compute (or any card in this category, stupid to benchmark this for these low end models), so maybe AMD will actually get to $150 on them. But giving reviews based on pricing we now know may not happen on cards that aren't even available yet vs. a HARD LAUNCH with OC models already out far above what is tested here by anandtech is a bit of a pipe dream at best.
http://www.tomshardware.com/reviews/radeon-r7-265-...
"In short, you'll have to pardon our skepticism that Radeon R7 265 will show up on time and at the price point AMD is claiming. We've seen fingers pointed at gun-shy add-in board partners, performance-thirsty cryptocurrency miners, price-gouging retailers, and foundries unable to keep up with supply. But at the end of the day, we're left wondering why AMD is setting prices if it can't control what you pay for its hardware? After piling praise onto the Radeon R9 280X at $300 and 290X at $550, it's our credibility on the line now, and we've been burnt too many times to give you guidance on a card you can't buy yet."
Just one of 3-4 of their paragraphs outlining the pricing problems and AMD's magical prices :) You get a whole page dedicated to AMD's pricing issues at tomshardware...LOL. Tomshardware is worried about credibility claiming AMD's pricing is real.
Even anandtech says it's probably magical pricing, so why compare the 265 to 750ti as if 265 will actually be $149?
http://www.anandtech.com/show/7754/the-amd-radeon-...
"but unless something changes to bring the other Pitcairn cards back down to their MSRPs, then $149 for 265 may be an unreasonable expectation"
"The lack of selection has done no favors for the pricing, leading to 260 prices starting at $125. This is $15 above MSRP – a significant difference for this segment of the market – and just a stone’s throw away from the 260X at current prices."
More comments about lack of 250's etc also. AMD can't seem to put a card out at MSRP. How do you come to the conclusion AMD wins at price perf, when no card is MSRP? Reality check please pal. If 260x is supposed to be $120 for new MSRP how is this possible given we already have regular 260 at $125? Again magical pricing is used for your statements not REALITY.
Current pricing on 290x/780TI are the same, and 780TI smoke it slapping it around like a rainbow trout. :) Not sure how you get AMD is winning from all of these comments. Yeah if you include magical pricing that may ONE DAY exist, but not REALITY for right now. You keep living in your fantasy world, I'll just stay in reality thanks. I fail to see how AMD will be able to keep up with R&D NV is clearly investing in GPU's. I'm not sure why anandtech even bothered to benchmark the ref design, when they admit NOBODY will be shipping them.
"NVIDIA’s partners will be launching with custom cards from day-one, and while NVIDIA has put together a reference board for testing and validation purposes, the partners will not be selling that reference board. Instead we’ll be seeing semi-custom and fully-custom designs; everyone has their own cooler, a lot of partners will be using the NVIDIA reference PCB, and others will be rolling out their own PCBs too."
So why test them? That isn't reality as they clearly point out.
http://www.anandtech.com/show/7764/the-nvidia-gefo...
I don't get it. Further showing their AMD love they left the Zotac out of most high end benchmarks and only used ref. What? After clearly stating REF won't even be sold why KEY on REF designs in your benchmarks? Oh right, they only have an AMD portal on anandtech...Never mind...LOL. I get it. :)
http://www.newegg.com/Product/ProductList.aspx?Sub...
For $5-10 more over a REAL MSRP on 750ti you get 1176/1255 or 1202/1281 which are both WAY over stock.
If maxwell is designed for mobile gaming so "who cares" then AMD is designed for compute/mining crap that has just about NOTHING to do with gaming so "who cares" too right? I mean if you want to win synthetic crap buy AMD. If you want to win in gaming buy NV. It would seem NV has the right idea for their audience. Also I wasn't aware Intel has ever put anything out in GPU that is damned good. LOL. They can't even catch BROKE AMD's Kaveri.
You're basing your price perf comment on pricing that is not REAL. Get back to us when AMD puts out something that sells at their MSRP. Until then their PRICE is FAKE, and price to performance crap is meaningless unless you talk in terms of REAL pricing. In which case NV looks great as hardocp shows.
"On a pure price/performance basis, the GTX 750 series is not competitive. If you’re in the sub-$150 market and looking solely at performance, the Radeon R7 260 series will be the way to go."
Fantasy pricing makes this comment moot.
"With that said however, we will throw in an escape clause: NVIDIA has hard availability today, while AMD’s Radeon R7 265 cards are still not due for about another 2 weeks. Furthermore it’s not at all clear if retailers will hold to their $149 MSRP due to insane demand from cryptocoin miners; if that happens then NVIDIA’s competition is diminished or removed entirely, and NVIDIA wins on price/performance by default."
That comment is REALITY. We know they won't be MSRP if recent history is any indication. They have been so wrong that tomshardware can't recommend anything on MSRP now. Anyone making comparisons on MSRP for AMD at this point is not credible. Hardocp, tomshardware etc all note it's currently FAKE pricing. Until that changes any site should be writing reviews with REAL pricing in the recommendations/conclusions and people like you should just avoid using phrases like "price performance" ;) AMD is losing everything on price performance when using REAL pricing. I don't know why anyone even quotes MSRP. It's merely a SUGGESTED price. You should just quote the lowest newegg or amazon price as that is the lowest you can get MSRP or not. IF it's NOT a hard launch so you can get that pricing, you shouldn't be reviewing something (since I can't REALLY buy it and have no idea of the REAL price). Get it?
NV needs to say Titan Black is MSRP of $550 I guess and start acting like AMD. Reviews would have to be written with MSRP conclusions for them then too right? Has anyone gotten a 290 for $400 or 290x for $550? Doubtful. Time for NV to join the lying game and soft launches with pricing that may not come for months?
From anandtech's 265 article:
"Finally, for the time being NVIDIA’s competition is going to be spread out, leaving a lack of direct competition for AMD’s latest arrivals. With the retirement of GTX 650 Ti Boost, NVIDIA doesn’t currently have a product directly opposite 265 at $149, with GTX 660 well above it and GTX 650 Ti well below it. On the other hand, NVIDIA’s closest competition for 260 as it stands is GTX 650 Ti, though this would shift if 260X cards quickly hit their new $119 MSRP."
Totally false considering all AMD pricing is fake right? If 260x QUICKLY hits $119 new MSRP? ROFL. Until they HIT that pricing shut up please. NV doesn't have a direct competitor to $149 265? Yeah because it won't REALLY be $149...LOL. 270 shows it, 260 shows it, 290, 290x, 280, 280x...jeez. Does AMD have a card that really is MSRP? So anandtech is comparing the NV stack to a magically priced fairy dust AMD stack right? That seems a bit unfair considering all the data on AMD pricing currently and EVERY site commenting on it. They continue to heap praise on AMD in reviews based on fake pricing. You can't write a whole page on how bad AMD's pricing situation is then go ahead and write conclusions and recommendations on that fake pricing as if it is real or will be real at some point MAYBE. Misleading the public at best, which is why tomshardware/hardocp etc backed off now. NV wins by default, until AMD puts out a real MSRP card. Anandtech still gives AMD the benefit of the doubt giving NV an escape clause...It should be the other way around. AMD needs that clause as no card they've released recently is MSRP.
ninjaquick - Thursday, February 20, 2014 - link
AMD's MSRP is very real, the issue is supply cannot meet demand. AMD only sees the money they make selling cards to vendors, if they had direct supply control (AMD badged products) they could be making money hands over fists with the inflation, but AMD isn't in the position to do that. They sell their chipsets at the stipulated pricepoint to their vendors, and the vendors then either pass on the savings, or squeeze supply and drive up prices for retailers. If they pass on the savings, then ultimately retailers are capitalizing on the consumer's willingness to pay more, but AMD, ultimately, will see no profits from this, and their sales will be hurt by lower flow due to high prices.Plenty of people bought 2XX series cards for their MSRP before LiteCoin made the prices skyrocket. To date, only the 290 series is still hyper inflated. And the MSRPs being determined there are from the vendors, not AMD.
chiechien - Friday, February 28, 2014 - link
The 280x are still priced 50% to 100% over MSRP, too. They're supposed to be $300, but you can't find cheaper than $450, with $5-600 quite common. The R9 270x runs about $50-$100 over MSRP (25-50%).Zetbo - Thursday, February 20, 2014 - link
I just bought 4096MB Asus Radeon R9 290 DirectCU II OC Aktiv PCIe 3.0 x16 for 397,53eur. I think it's fair price. http://www.mindfactory.de/product_info.php/4096MB-...vision33r - Sunday, March 9, 2014 - link
That tiny fraction currently buys more GPUs than the avg consumer. Thus the demand for AMD's high end GPUs.A5 - Tuesday, February 18, 2014 - link
If you really need full FP64, get whoever is paying you to buy a Tesla card.extide - Tuesday, February 18, 2014 - link
Or go with a big-GCN card :)A5 - Tuesday, February 18, 2014 - link
Or that, assuming your code isn't locked in to CUDA.ddriver - Tuesday, February 18, 2014 - link
Thank god it is not. Running about 50 TFLOPS here, nice cheap radeons, no tesla overpriced junk thank you very much nvidia.Morawka - Tuesday, February 18, 2014 - link
where you buying your radeons? they are overpriced price gouged to hell, Steaming hot thermals but sure it does fp 64 great go get em tiger!!!