NVIDIA Releases the GeForce GTX 1050 3GB: More RAM, Fewer ROPs?
by Nate Oh on May 21, 2018 5:15 PM EST- Posted in
- GPUs
- GeForce
- NVIDIA
- Pascal
- GeForce GTX 1050
Adjusting their GeForce GTX 1050 Family info page over the weekend, NVIDIA quietly announced that the expansion of the GeForce 10-series of cards with another entry: the GeForce GTX 1050 3GB. Slotting between the GeForce GTX 1050 Ti and original GeForce GTX 1050 (2GB), the GTX 1050 3GB is, despite the name, not actually equal to the original GTX 1050 2GB. Instead it features 768 CUDA cores but on a smaller 96-bit memory bus.
If this story sounds familiar, it’s because it is. After launching the GTX 1060 in July 2016, NVIDIA followed up with the GTX 1060 3GB, which featured 1152 CUDA cores to the GTX 1060 6GB’s 1280.
| NVIDIA GPU Specification Comparison | |||||||
| GTX 1060 3GB | GTX 1050 Ti | GTX 1050 3GB | GTX 1050 (2GB) | GT 1030 GDDR5 | |||
| CUDA Cores | 1152 | 768 | 768 | 640 | 384 | ||
| Texture Units | 72 | 48 | 48 | 40 | 24 | ||
| ROPs | 48 | 32 | 24? | 32 | 8 | ||
| Core Clock | 1506MHz | 1290MHz | 1392MHz | 1354MHz | 1227MHz | ||
| Boost Clock | 1709MHz | 1392MHz | 1518MHz | 1455MHz | 1468MHz | ||
| Memory Clock | 8Gbps GDDR5 | 7Gbps GDDR5 | 7Gbps GDDR5 | 7Gbps GDDR5 | 6Gbps GDDR5 | ||
| Memory Bus Width | 192-bit | 128-bit | 96-bit | 128-bit | 64-bit | ||
| VRAM | 3GB | 4GB | 3GB | 2GB | 2GB | ||
| FP64 | 1/32 | 1/32 | 1/32 | 1/32 | 1/32 | ||
| TDP | 120W | 75W | 75W | 75W | 30W | ||
| GPU | GP106 | GP107 | GP107 | GP107 | GP108 | ||
| Transistor Count | 4.4B | 3.3B | 3.3B | 3.3B | 1.02B | ||
| Manufacturing Process | TSMC 16nm | Samsung 14nm | Samsung 14nm | Samsung 14nm | TSMC 16nm | ||
| Launch Date | 08/18/2016 | 10/25/2016 | 5/2018 | 10/25/2016 | 5/2017 | ||
| Launch Price | $199 | $139 | - | $109 | $80 | ||
Going down to the silicon, the GeForce GTX 1050 3GB does indeed feature 3GB of VRAM, an extra GB over the original GTX 1050, which in turn only ever came in a 2GB version in the desktop space. But ultimately, the GTX 1050 3GB is another GPU configuration: the card has an extra enabled SM – now matching the GTX 1050 Ti at 6 SMs/768 CUDA cores – while also equipped with a cut-down 96-bit bus as opposed to the 128-bit bus of its other desktop GTX 1050 series siblings. In actual memory bandwidth numbers, this translates to 84 GB/s as opposed to 112 GB/s.
Otherwise, the raster engine and TMU counts are presumably identical to the GTX 1050 Ti, as the SM count requires the frontend to be a fully enabled GP107 part. As for clockspeeds, the GTX 1050 3GB features faster base and boost than both GTX 1050 Ti and GTX 1050 2GB.
Things get a bit trickier on the backend though. While NVIDIA's published specifications don't offer clarity on this, the company's designs normally have a 1:1 ratio between ROP partitions and memory controllers. Meaning that as this configuration has a 96-bit memory bus – and thus only 3 out of 4 memory controllers are enabled – then it has almost certainly lost a ROP partition as well. This also means that a quarter of the GPU's L2 cache (256KB) has also been shut off, leaving the chip with just 768KB of L2.
This is a prime example of why unusual memory configurations are more important than they may seem at first, as several parts of the GPU are strongly bound to the size of the memory bus. It also means that estimating the card's performance based on just clockspeeds and functional block counts is harder than it may seem, as now one needs to take into account memory bandwidth, ROP throughput, and cache hits.
Unofficial GTX 1050 3GB Block Diagram
All told, the existence of this card is not entirely unexpected, but it is odd. That NVIDIA is going with a 3 memory channel configuration stongly implies that the company has built up a stockpile of GP107 parts with one bad ROP/L2/MC partition, which is not unusual but GP107 is also a small enough die that the need to salvage to this level isn't quite as great. Otherwise, NVIDIA could have produced a 3GB card with a 128-bit memory bus and unbalanced memory configuration (2x1GB + 2x0.5GB), which brings its own tradeoffs but is generally the more straightforward option. At any rate, it's rare to see a salvage part like this enter the retail market this late in the cycle.
In total, NVIDIA cited the performance difference to PCWorld as averaging out to around 10% uplift of the GTX 1050 3GB over the 2GB. And so once again, we are now looking at multiple GPU configurations being sold at retail under a GTX 10x0 banner.
Contextually speaking, this new SKU comes in at a time of cryptocurrency mining demand, which has inflated prices and reduced availabilities for video cards all around. In that sense, where there may not have been room for an in-between GTX 1050 SKU, there is now. Or given diminishing cryptodemand, silicon that could be re-configured for consumer GeForce use. And in terms of competition, the GTX 1050 series match up with the AMD Radeon RX 560 (16 and 14 CU variants), a nominally single SKU which amusingly has had its own share of naming troubles. Lastly, recent NVIDIA GeForce launch cadence would suggest that the post GeForce GTX 10-series are on the horizon, a situation where Pascal-based lower-end product launches are easily compatible with.
And for NVIDIA’s part, a quick look at their own Linux driver documentation of supported GPUs by PCI ID shows the amount of variants and configurations for GP107 and GP106, with some device IDs implying GP104-based GTX 1060 cards. Though not all of the PCI IDs may reflect a currently-selling product, some might be regional or simply unpublicized; for the rumored GTX 1060 5GB, it had already found itself on NVIDIA’s driver support lists earlier this year. So the appearance of another configuration isn’t necessarily out of the blue. For the GTX 1050 3GB today, it may not be based on GP107, and given that most manufacturers rarely, if ever, comment on the lowest performing parts in their stack, future clarification is unlikely.
But while strange GPU configurations at the lower-half of performance brackets are not uncommon, as is the dearth of clear specification documentation, the obfuscating nomenclature is less palatable. As mentioned at the time of the GTX 1060 3GB launch, NVIDIA hadn’t had multiple GPU configurations selling under a single retail GTX model number for some years now, but now they’ve done it again – excluding the recent naming shenanigans with entry-level GT 1030 GDDR5/DDR4 as well as the MX150 variants. Keeping the different GPU configurations separate to the memory configuration like with the GTX 1060 is still unintuitive or misleading for most consumers, who may not research entry-level components or be unaware of how GPUs are configured. It appears that NVIDIA has no intention of changing from its ongoing nomenclature philosophy.
Going forward, however, this approach hardly educates the consumer. For one, all previous references to the “GTX 1050” would need to be updated; on the GTX 1050 Family page, the performance graphs still refer to the “GTX 1050,” something that undiscerning readers would not pick up on.
As noted to PCWorld in response to availability and pricing, the GeForce GTX 1050 3GB will be in the same price bracket as the GTX 1050 Ti and GTX 1050 2GB.
Source: NVIDIA
Facebook
Twitter
RSS
49 Comments
View All Comments
Samus - Tuesday, May 22, 2018 - link
The memory capacity shouldn't be used to designate a COMPLETELY DIFFERENT GPU.MrSpadge - Tuesday, May 22, 2018 - link
To be fair, the first thing after "Geforce is good" that the average target buyer of this knows is that "more GBs is better". So 2 - 3 - 4 GB for the cards works out as indicator for their performance. And 10% more or less performance doesn't matter for these cards, because they're all slow anyway and require serious compromises inimage quality. So yes, the amount of memory may be the single most important spec after the "GTX 1050".kpb321 - Monday, May 21, 2018 - link
It's interesting that this changes the compute to memory bandwidth ratio and presumably the ROPS. That should mean this should handle higher complexity things that are compute bound better but do even worse at higher resolutions where memory bandwidth and ROPS become more important. The computer side of things should have been ~25% higher on the new card due to the increased number of shaders and slight overclock. NVIDIA claiming a ~10% improvement on average clearly indicates there are some cases where the new card will be memory/rop bottle-necked compared to the 1050 2gb and will not see much benefit or even potentially small losses in performance. It shouldn't be major losses in performance otherwise they wouldn't be able to get a 10% average with a max theoretical boost of 25%.On a separate note I HATE crap like this where the 1050 2GB and 1050 3gb have other differences than just the amount of memory. I hated it on the 1060. I hated it on the 560. Just add some random letters to it so that it immediately makes people wonder what's different. Call it the 1050 Se or 1050 BFC or 1050 WTF or what ever just give more indication that there is something else different besides the amount of memory.
bji - Monday, May 21, 2018 - link
I guess I don't get the complaint. Let's say the card only had an additional 1 GB of memory and no other differences. Would you know implicitly how much faster it should then be in a given game or in a given benchmark? Maybe if you are a benchmark junkie you might be able to estimate it, but most people wouldn't, and almost no one would be able to say without testing exactly what the effect would be in a given game because of the emergent effects of having an extra 1 GB of memory to use.So for most users in most situations, there would be no clear 'expected' speed increase from the extra 1 GB. A user who understands how card speeds are measured and pays attention to benchmarking sites will find the benchmarking details for this card just as readily available whether there were architectural changes within the card or not. A user who does not understands benchmarking or how to estimate the value of a card, well, I don't know how they would understand the difference between a 2 GB card and a 3 GB card, except to expect that the 3 GB card would be "better", which this one clearly is.
Oxford Guy - Monday, May 21, 2018 - link
"I guess I don't get the complaint."Different products should be sold under different names.
bji - Monday, May 21, 2018 - link
I believe they are. One is called "GTX 1050" and the other is called "GTX 1050 3 GB".$ [ "GTX 1050" = "GTX 1050 3 GB" ] || echo "They are different products, Oxford Guy"
They are different products, Oxford Guy
$
Oxford Guy - Monday, May 21, 2018 - link
It's a very poor naming scheme that sows confusion.The number should be changed. Each card design should have its own number. It's clear that if the product is in the 1050 series it will be 1050-something.
There is no need to confuse people with RAM trickery. And yet, this is an old marketing tactic — like putting large amounts of RAM on cards that can't utilize it, running the RAM slower, having less RAM bandwidth due to a smaller bus, having lower clocks, having more disabled parts, etc.
This fraud has a long history. Good luck making high-quality excuses for it because there aren't any.
bji - Monday, May 21, 2018 - link
It has slight internal architectural differences that go along with having a different amount of memory. It will have slightly different performance, likely faster than the 2GB card on some workloads and slower on others. It has a different name to distinguish its performance profile from the 2 GB card. Consumers who care about the minor overall differences will be well informed by the reviews which will certainly be readily available once the card is launched. Consumers who don't understand the technical differences likely won't be able to tell the difference anyway.It's probably the case that NVidia doesn't want to further expand its product numbering schemes because this could cause more confusion for the uninformed consumer than anything else.
I mean if you really think NVidia is trying to "trick" consumers into buying one $100 card over another ... think harder. Big companies don't operate on such a petty level.
Oxford Guy - Monday, May 21, 2018 - link
"I mean if you really think NVidia is trying to "trick" consumers into buying one $100 card over another ... think harder. Big companies don't operate on such a petty level."Wow. I guess none of them have marketing departments.
After all, instead of trying to trick people into buying from emotion instead of logic (the entire point of marketing), all big corporations do is release the specs and a simple, unemotional, press release.
Call me when the shuttle lands.
Oxford Guy - Monday, May 21, 2018 - link
"It's probably the case that NVidia doesn't want to further expand its product numbering schemes because this could cause more confusion for the uninformed consumer than anything else."Ridiculous. If Nvidia wanted clarity, it wouldn't use "3 GB" as a naming scheme. It would give each product a clear differentiation, like changing the number or sticking on a letter suffix.
What's next? Labeling the product by ROP count?