Back in 2003, AMD introduced the Opteron processor, world’s first 64-bit x86 processor capable of addressing more than 4GB of memory (32-bit) – no less than massive 1TB of memory, courtesy of its 40-bit allocation table. Processors of today are capable of addressing up to 8TB of SDRAM memory thanks to extended (46-bit) allocation table. However, until now, finding a high-capacity memory module with 32GB density was as rare as finding hen’s teeth and usually you would pay top dollar for it.

Upcoming 20nm manufacturing process enabled the creation of ultra-dense memory modules and with SK.Hynix launching its 20nm 8Gbit memory chip, there was no doubt something special was in the works.

SK.Hynix 128GB 64×8 PC4-2133P-L80-19 – World’s first 128GB DIMM memory

For SK.Hynix, the end result is world’s first 128GB memory module, designed for the new DDR4 memory standard. While there is no way that this memory would become a mainstream part (at 20nm node), it shows that the DRAM industry is ready to offer something special for the upcoming server processors from Intel and AMD. This memory module also makes the first time TSV (Through Silicon Via) technology was used, utilizing vertical DRAM silicon stacking, e.g. 3D chips (not transistors).

If a typical server CPU comes with eight DIMM slots, with this module you will be able to pair each processor with 1TB of DDR4-2133 memory, resulting in 68GB/s of available bandwidth. While this is ways away from a high-end desktop / workstation usage, the existence of 128GB module will drive the price of 8GB, 16GB and 32GB modules down, with 64GB modules expected to drop down in price by over a half.

There’s also a matter of the way how DDR4 works, reducing the voltage from 1.35V or even 1.5V (initial DDR3 modules) to 1.2V. The current (A) did go up, so do not expect great power savings coming from the memory side of things, but the sheer capacity should make up for it.

We expect this memory in working demo systems at the upcoming ISC’14 supercomputing conference (June 22-26), which takes place in Leipzig, Germany.

The post SK.Hynix Enables 1TB of Processor Memory with a 128GB DDR4 Module appeared first on VR World.

But one of main building block was launched yesterday, in 2008. Hynix introduced a chip with a friendly and “easily understandable” name: H5GQ1H24AFR. Even though the name looks like something that ENIGMA would encrypt, we’re talking about 128MB (1Gbit) memory chip that operates at the clock of 1.75 GHz in QDR mode, resulting in 7 GigaTransfers per second (7 GT/s or 7 “GHz”). Currently, ATI Radeon 4870 and 4870X2 come with 900 MHz chips that offer 3.6 GT/s, so we’re talking about doubling the memory bandwidth per chip.

This means that a GPU with a 256-bit memory controller would have roughly 219 GB/s of bandwidth, while 512-bit memory controller and these Hynix chips would result almost  A GPU with 256-bit memory controller and 438 GB/s. These numbers are astonishing and quite frankly, will open the doors for higher performance jump than previously imagined.

Best thing of them all: due to new manufacturing process, Hynix 2nd Gen GDDR5 chips at 1.75 GHz works at 1.35V rail, and consumes less power than initial 900 MHz chips (3.6 GT/s ones). Yep, the power consumption will go down, and performance per chip is now doubling. Who says you can’t have “wolves stuffed, and all sheep numbered” as the old Croatian saying go (english version: have your cake and eat it too)?

Now you know. Nvidia’s GT212, or the 40nm shrink of GT200 chips consumes around 25% of power eaten by the original 65nm chip, can have double the bandwidth and GDDR5 memory that eats less power than GDDR3 memory present on GTX280 cards. As far as ATI is concerned, the upcoming RV870 will be in the same boat as Nvidia.

Can you say, 8-pin power connector is going the way of do-do birds? Well, I would say yes, but don’t forget that GPU makers will use these power savings to clock their cards to absolute physical limits.
H1 2009 will see $299 parts that enable 1920×1200 in 16x AA/AF at 120 fps with no sweat.
If you thought that GTX280 and 4870X2 are incredible… well, we haven’t seen anything yet. Now, will the game designers finally follow the path set by Race Driver GRID, Unreal Tournament III, Far Cry 2, Fallout 3 and offer absolutely fantastic gaming experience without constant crying that “hardware isn’t powerful enough”. Or at least, prove that it really isn’t.

P.S. Before you ask.. this is still single-ended GDDR5. Still waiting for that Differential GDDR5 to show up…of course, we need Differential GDDR5-capable memory controllers too.

The post ATI and Nvidia cards for 2009 will be monsters appeared first on VR World.