GlobalFoundries offers a little preview at one of the upcoming Fusion processors from AMD, the Orochi based on the Bulldozer architecture as Softpedia reports.

Bobcat’s firstborn will be the 40nm Ontario mobile chip and comes with embedded DirectX 11 graphics. is intended for desktops and servers with Orochi being one of the flagship chips.

No real information was provided on this 8-core product besides that it will be the second 32nm-based product and will be built immediately after the Llano. The Orochi will feature a set of 4 Bulldozer modules, which provide 8 cores and 8 threads, and will probably have an AM3+ package with an integrated DDR3 memory controller.

On the other hand, the individual L2 caches will be of 1MB and will support dual-channel DDR3 and will, of course, have its own built-in graphics with support for DirectX 11.The APU should also feature an integrated northbridge, integrated PCI Express root complex, a HyperTransport interface to the chipset and an integrated SIMD array with 480 stream processors.

The Llano will have to compete with the Sandy Bridge processors from Intel, which also have integrated graphics and will feature better performance than the current Core series [via Softpedia / PCPer].

Crazy just crazy, so this news is obviously for the server-market but apparantly Samsung can cram 32GB memory on a DIMM module.

Samsung Electronics announced today that it has begun shipping samples of the industry’s highest-density memory module for server systems. The 32 gigabyte (GB) module has been designed for use in advanced servers, which require high-density and high-performance features at low-power consumption levels.

Samsung is using the industries highest-density monolithic DDR3 device – a 40-nanometer (nm) class, four gigabit (Gb) DDR3 chip – as the building block for the new 32GB module. This comes just one year after the company announced its 50nm-class 2Gb based, 16GB registered dual inline memory module (RDIMM) last March.

The highly-efficient 32GB RDIMM consists of 36 dual-die 40nm-class 4Gb DDR3 chips that can perform at equal or greater levels to a 40nm-based 16GB RDIMM with no increase in power consumption. By equipping a dual CPU, two-way server with 32GB modules, a server system can have up to 384GB of memory. This allows for doubling the previously largest density of 192GBs per server with a power increase of less than five percent over that needed for a 16GB module-based system.

In addition, replacing 12 DRAM modules of 16GB density with just six 32GB modules would achieve a 192GB total density, while allowing the DRAM operating speed in a two-way server system to rise by 33 percent from 800 megabit per second (Mbps) to 1,066 Mbps, as power is cut by 40 percent.

In high-performance, four-way servers using 16GB modules, one terabyte of DRAM would be commonplace.By using 32GB RDIMMs, Samsung is moving toward providing four-way servers with 2TB of DRAM each, a migration that it believes will spur introduction of diverse software and a broader scale of server applications.

Mass production of the 32GB RDIMM is slated to begin next month.

Rumors are all over the web regarding the pending release of ATI’s Radeon 5800 series DX11 class graphics cards. We ‘think’ that the first released card will be the Radeon HD 5870 which is developed under codename Cypress.

From what we heard is that this card will be lined up directly against the GeForce GTX 285 pricing wise, the rumor is that this high-end DX11 class graphics card will get a price tag of 299 USD.

Though I personally doubt it a little given the issues with the 40nm node, there is a a rumor that this graphics card would be based on a 40nm fabrication process.

* 1GB GDDR5 memory
* ATI Eyefinity technology with support for up to three displays
* ATI Stream technology
* Designed for DirectCompute 5.0 and OpenCL
* Accelerated Video Transcoding (AVT)
* Compliant with DirectX 11 and earlier revisions,supports OpenGL 3.1
* ATI CrossFireX multi-GPU support for highly scalable performance
* ATI Avivo HD video and display technology
* Dynamic power management with ATI PowerPlay technology
* 2x DL-DVI, DisplayPort, HDMI
* PCI Express 2.0 interface

Once thing is certain, we look very much forward to this new product release, whatever and how fast it may be, it looks like the shader processor count might be doubled up by the way.

We heard all about nVidia’s 40nm roadmap and plans at Computex. We all know that 40nm is the new battle ground for your gaming dollars. But we have not really seen much from nVidia on the 40nm process.

That is until now, TechConnect Magazine has some great images of the low-end 40nm desktop card from nVidia. The new G210 and GT 220 will feature some new stuff (besides the 40nm shrink). The G210 will have 16 sores, a 64-Bit memory interface, DX 10.1 support and 512MB of memory. The GT 220 will have 48 Cores, 128-Bit memory interface and double the memory.

While pricing is not known they should hit the shelves sometime in Q3, while some OEMs will have access to them sooner.

With the announcement at Computex that AMD has working DX11 silicone we started to wonder if nVidia would have a comeback of its own but so far we only hear rumors of the GT300 in late 2009 or early 2010.

In fact the first 40nm GPUs from the green team will only be DX10.1. This is sort of odd as for years nVidia has claimed there was no advantage to using the DX stopgap. They have held firm that they were going to wait until DX11 to make the move.

But as of this writing the GT216 and GT218 will be DX10.1 parts. For all of the nVidia fans out there, it looks like you will have to wait on the GT300 for your DX11 gaming fix. But then again, as of this writing there are no DX11 games on the shelves and Windows 7 is still in the RC stage.

ATI has been preaching that DirectX 10.1 is a good thing for years now and Nvidia jumping on the DirectX 10.1 bandwagon just months before Microsoft is set to reveal DirectX 11 is quite strange. Nvidia was a very opponent of DirectX 10.1 since all of its currently shipping generation doesn’t have support for DirectX 10.1 and all the sudden, they are announcing a new generation that will completely support DirectX 10.1

Since mobile and desktop chips from both Nvidia and ATI are usually the same thing, Nvidia wanted to offer DirectX 10.1 check box technology to its potential users and with Calpella, Intel’s Nehalem – Clarksfield quad core for notebooks platform. Nvidia expects many Calpella design wins for its 40nm DirectX 10.1 GPUs and most probably Nvidia customers simply wanted to have DirectX 10.1 and not DirectX 10, something that Nvidia offers for years.

nVidia is preparing to launch their new 40nm GPUs at Computex 2009 which kicks off tomorrow.

The new 40nm GPUs will be mobile GPUs and not the high end monsters that most will be looking for this year. nVidia has finally decided to get on the DX 10.1 bandwagon though with these new chips.

According to Fudzilla ATi might miss the boat despite having 40nm mobiles out first. The issues at TSMC seem to work against them here as there is a shortage of the ATi mobile 40nm GPUs right now.

If you remember RV740 in mobile variation 40nm was out in March at Cebit, but so far we haven’t seen a single notebook shipping with it.

Nvidia’s 40nm notebook stuff is DirectX 10.1 and you can expect very good performance per watt, something that is very important for notebook users. Many Calpella notebooks will jump for Nvidia’s 40nm as Calpella has to have discrete graphics to work as its P55 mobile chipset doesn’t have any integrated graphics.

There’s a lot of activity among graphics chipset designers for sure lately. Nvidia sets GPU outsourcing to TSMC and UMC for 2Q09, says paper.

Nvidia recently set its outsourcing schedule with Taiwan Semiconductor Manufacturing Company (TSMC) and United Microelectronics Corporation (UMC) for the second quarter, according to a Chinese-language Commercial Times report.

In addition to expanding its 55nm GT200b GPU outsourcing, the company will also start mass production of the 40nm entry-level GT218, high-end mobile GT215 and mainstream GT214 and GT216 GPUs in mid to late second quarter, according to the paper.