Slashdot Mirror
Samsung Begins Mass Production of World's Fastest DRAM (hothardware.com)
MojoKid writes: Late last year marked the introduction of High Bandwidth Memory (HBM) DRAM courtesy of AMD's Fury family of graphics cards, each of which sports 4GB of HBM. HBM allows these new AMD GPUs to tout an impressive 512GB/sec of memory bandwidth, but it's also just the first iteration of the new memory technology. Samsung has just announced that it has begun mass production of HBM2. Samsung's 4GB HBM2 package is built on a 20 nanometer process. Each package contains four 8-gigabit core dies built on top of a buffer die. Each 4GB HMB2 package is capable of delivering 256GB/sec of bandwidth, which is twice that of first generation HBM DRAM. In the example of NVIDIA's next gen GPU technology, code named Pascal, the new GPU will utilize HBM2 for its frame buffer memory. High-end consumer-grade Pascal boards will ship with 16GB of HBM2 memory (in four, 4GB packages), offering effective memory bandwidth of 1TB/sec (256GB/sec from each HMB2 package). Samsung is also reportedly readying 8GB HBM2 memory packages this year.
You are the underdog and the warrior that has stood the wrath of Nvidia! I will keep buying your products until the bitter end!
AMD is now just another ARM maker, they lost the x86x64 war, now they're going to lose the ARM war too (too many competitors in the ARM market), AMD also lost the GPU war.
Where do AMD belong? The only place I see AMD, is on support forums with people crying things are not working, or they cannot upgrade, my drivers are rubbish or some other broken reason.
that's NVIDIA-ah to you.
Great, just what we need, more ads on Slashdot. Weren't these Slashvertisements supposed to have different colors to distinguish them from real stories? Is DICE so desperate for money that they have to run ad after ad as stories like the previous one and this one? Geez! I remember when Slashdot used to talk about open source, Linux, and stuff that mattered, not ads.
The initial AMD Fury card was a bit of a disappointment, I mean it is quite fast for it's size and it's also quite fast for only 4GB memory onboard, but it didn't thrash the nvidia 980Ti it competes with, despite being a newer technology with more memory bandwidth. /precisely/ why, but it may be the AMD GPU itself is simply not powerful enough to use that bandwidth effectively or the 4GB holding it back due to texture size.
I haven't investigated (nor do I care to) as to
*THAT* being said, that's phase 1 of HBM, phase 2 is about to kick in this year for both AMD and nvidia and premium video cards will be utilising this technology in the high end for certain.
The other thing that's frequently mentioned when these are brought up is that this on chip (or is it on package?) memory is going to be utilised in some of AMD's mid tier APU chips (the CPU / GPU combined ones) which should make some onboard video surprisingly damn good in the coming future. Perhaps not dedicated GPU good but may compete well with low to mid tier dedicated GPU's now.
Also for compute functions for scientific stuff or whatever people use all that number crunching stuff with dedicated GPU's for, this will be far better. (Apparently it's similar to Intel Xeon Phi or some such? (Knights landing) https://en.wikipedia.org/wiki/...
I guess ultimately what has enabled this technology to exist is stacking ram (?) since they can fit 4GB of memory inside a single, very small chip.
(Here you can see the existing stuff, 1GB in a single chip, the 4 smaller chips around the GPU) https://www.google.com.au/sear... soon to be 4GB in presumably the same physical space and 8GB shortly
It looks to me like stacked ram is the future in many things (SSD capacity booming due to this)
It's all pretty exciting for the future of bandwidth, 1TB/s is pretty nice and I imagine it'll only go up from there.
(I read some theories recently about 'stacking' CPU's too, although the heat may become an issue? but if they can lay out 48 layers of memory inside a chunk of silicon, why not lay out multiple processors) however that's for the smart people to figure out.
Please read the replies to this post as I don't follow as closely as I used to and several pieces of information here might be slightly off.
What I want is a Motherboard that will use one of these stacks to feed my 4-channel Intel socket 2011-3 processor.
The current max for memory is ~25Gb/s/channel, so 4 channels from one device still leaves a lot on the table for improvement.
Two processors could keep one busy... :)
Truth isn't Truth - Guliani
I found out the hard way that memory bandwidth was the bottleneck for this activity.
1TB/sec = approx. 34.7 hours of 8KB 1080p porn videos per second...
for use in high performance computing (HPC), advanced graphics and network systems, as well as enterprise servers
Samsung’s 4GB HBM2 also enables enhanced power efficiency by doubling the bandwidth per watt over a 4Gb-GDDR5-based solution, and embeds ECC (error-correcting code) functionality to offer high reliability.
The latency for HBM and other technologies of its ilk are no better (even slightly worse) than DDR3.
It's no good for large last level caches -- but 8 of those 8 TB stacks would make for a nice 64GB of RAM with 2TB/sec bandwidth. I'd like to see that connected to a good CPU.
Ian Ameline
cache lines are 64 bytes on any intel cpu made in the last 100 years.
I wonder how many kludges and "offloads" amd/nvidia will be able to pull off with this sort of external bandwith, increasing the performance/lowering costs in the process.
It has been said that Pascal GP104 will use GDDR5X. If Nvidia repeats the cycle GP104 will be their flagship and big Pascal GP110 wont be GeForce ready until next cycle some time in 2017.
Which would make sense, considering that nVidia has no experience with HBM.
AMD - Hynix collaboration on HBM started a while ago, by the end of 2013 they've only "finalized HBM 3D memory", it took 2 more years to ship Fury series GPUs with HBM::
http://linustechtips.com/main/...
After price drop on Fury Nano, it costs like 980 (non TI) (499$) while handily beating it in most games, tiny form factor.
Reading anything about HBM always makes me want to do a facepalm! The reason is that HBM is NOT fast... per say. It is only really fast BECAUSE IT HAS A 1024BIT BUS! Any DRAM riding on such a freaking wide bus will technically be "fast" If we actually cut down the bus width, we find that HBM is actually slower bit-per-bit than say a modern DDR5 equipped video card. Example, Nvidia GT 730 (DDR5 version) video card uses DDR5 on a 64bit bus and achieves 40GB's a second at 1250Mhz. HBM on the other hand at 64 bits wide achieves 32GB's a second.
In short, any video card OEM can widen the bus width of their product and achieve the same or higher results. So I ask, what's the point to HBM? Placing it on, or near the die package so there's less room for heat to dissipate so it either fails prematurely, or runs into a TDP ceiling? I just don't get it.