Slashdot Mirror
NVIDIA Launches New Midrange Maxwell-Based GeForce GTX 960 Graphics Card
MojoKid writes NVIDIA is launching a new Maxwell desktop graphics card today, targeted at the sweet spot of the graphics card market ($200 or so), currently occupied by its previous gen GeForce GTX 760 and older GTX 660. The new GeForce GTX 960 features a brand new Maxwell-based GPU dubbed the GM206. NVIDIA was able to optimize the GM206's power efficiency without moving to a new process, by tweaking virtually every part of the GPU. NVIDIA's reference specifications for the GeForce GTX 960 call for a base clock of 1126MHz and a Boost clock of 1178MHz. The GPU is packing 1024 CUDA cores, 64 texture units, and 32 ROPs, which is half of what's inside their top-end GeForce GTX 980. The 2GB of GDDR5 memory on GeForce GTX 960 cards is clocked at a speedy 7GHz (effective GDDR5 data rate) over a 128-bit memory interface. The new GeForce GTX 960 is a low-power upgrade for gamers with GeForce GTX 660 class cards or older that make up a good percentage of the market now. It's usually faster than the previous generation GeForce GTX 760 card but, depending on the game title, can trail it as well, due to its narrower memory interface.
There are other, better reviews for this card, for instance Tom's hardware, but every single hardware review story on Slashdot seems to be obliged to link to Hothardware.
So, which editor own's Hothardware shares?
You might be able to find a Geforce 750 for $125 or so. They're adequate but definitely not ideal for 1920x1080 in most PC games. They're also ridiculously efficient; they don't even need an extra PCIe power connection.
If anyone tells me they want to game on a PC and don't immediately mention a game with a more serious demand, that's the hardware I use.
I generally prefer ATI hardware because I think nVidia's stock cooling kills graphics cards and I'd rather deal with crappy drivers, but the current ATI hardware is a complete non-starter. There's really no level at all where it can be justified.
-- I wanna decide who lives and who dies - Crow T. Robot, MST3K
Personally I love the GTX 750. It gives the biggest bang-for-the-buck and running at about 55 watts max or so it usually doesn't require a larger power supply. It can run completely off motherboard power going to a 16-lane 75 watt PCIe slot.
It's the perfect card for rescuing old systems from obsolescence, IMO.
The only trouble you might have is finding a single-slot-wide card if your system doesn't have room for a double slot card, though in my case I found a double-slot card that I could modify to fit in a single-slot of an old Core 2 Duo E8500 system.
And heat doesn't seem to be a problem at all, even with the mod I did. The low power of the card means less heat. Even if heat becomes a problem, the card is capable of slowly clocking itself down, though I've never seen that yet, even running Furmark.
nVidia's been using that for years to keep their mid range from biting into their high end. At those price points I wish I was confident enough in AMD's driver stability to buy an R9 270X. 256 bit interface + 1500 mhz core clock for $210 bucks.
Hi! I make Firefox Plug-ins. Check 'em out @ https://addons.mozilla.org/en-US/firefox/addon/youtube-mp3-podcaster/
That is because its Unity. Unity doesn't run well on anything.
And I do mean anything. No hardware in the world runs Unity well. Not because hardware is bad, but because Unity is a buggy piece of shit that won't run well even on SLI 980s.
As for "playing games released on the same year", I'm yet to find a game that won't work with my 560Ti. Though many of these releases I had to bump quality down to medium to get solid frame rate.
I never said that I'm using 4k.
After your response I think my original comment might make me look like a resolution whore.
My point was NOT that the card should be labeled low end because of 4k. Rather, it should be labeled high end.
I play at 1920x1080 resolution. So from my perspective, the card is high end.
It's just that cards get labeled based on series (like Nvidia x60 series is mid-end) which is primarily based on price.
When there are graphics cards available from $30-3000, the low, mid and high end will be different based on a person's usage and perspective.
My point was that for vast majority of people (according to Steam Hardware survey: > 98%) who would be gaming at 1920x1080 or less, this card would be high end.
(Note to self: Well done on conveying exactly opposite of what you are trying to say without using sarcasm, negation or typos)
Yes, if you're happy chugging along at 20-35fps with dips into the low teens.
You lost me at "used".
A Pirate and a Puritan look the same on a balance sheet.
It might be an old meme, but it's still true, especially for opengl. Their d3d is ok if you plan to run the games tweaked in that particular version of the driver.
No, a CUDA core is better thought of an ALU or sub-ALU, speaking in terms of cores is clear abuse because AMD or nvidia once started to use that term. As a limited analogy, the original Pentium has two integer pipelines but is not called a dual-core CPU.
"CUDA cores" are organised into units that house 128 of them here, called an "SMM". But to understand how things are dealt with from the software point of view (threads, warps) some extensive reading is needed.
As a former ATI employee, I think many will join me in lamenting its demise. Was a great place to work, and I enjoyed contributing to some cool products.
As a former AMD employee (as per the buy-out), all I can say is AMD sucked. First the "green" management couldn't get a product to production, year after year after year. Now they're trying to play as a mostly "red" team, and unfortunately don't have half the staff that made ATI work well. Rory was just weirdly goofy, and sometimes bizarrely candid with the staff ("we're thinking of laying a bunch of you off" [paraphrase]). He even told Jensen that he was "going to kick [his] ass" in the market. Yeah, that happened... Lisa always talked the good talk (to the staff) as GM, but somehow always things came up a bit short, and after noticing that for a few quarters, it started to seem as if she was stretching the truth and double-talking a bit. Since she was largely driving things as GM, expect little to change with her as CEO. AMD still sucks
As a current nVidia employee, I look back fondly and wistfully at my time at ATI, but recognize that nothing lasts forever. nVidia is where ATI friends and fans should end up, IMHO. It's far closer to the ATI spirit than AMD ever was or could ever be. And to folks who keep referring to AMD's graphics group as ATI, know that we all wish it were so, but you've got to accept reality. ATI is dead, and AMD really hasn't picked up the torch.
Ok, done rambling, it's bedtime...
This is incorrect. CUDA cores are at a higher level than ALUs or FPUs; they're like small, simple cpu cores. They can do integer and floating point arithmetic, and they have hardware support for thread context switching, which they can generally do in a single clock tick. There can be varying numbers of CUDA cores in a streaming multiprocessor, but CUDA thread blocks are arranged in groups of 32 ("warps") which share a scheduling unit and which execute the same instruction in lock-step on different memory addresses. When threads running on adjacent CUDA cores read and write adjacent memory addresses, memory access is very efficient ("coalescing").
CUDA cores aren't as capable or powerful as CPU cores; they don't have things like branch prediction or preemptive execution, but they are cores none the less. They achieve high performance via sheer numbers - thousands of cores on top-end GPUs - and they're very good at streaming, which consists of doing the same operation in parallel on many array elements when each operation is independent of all the others.
Chuck Norris: Socialism == a thousand years of darkness.