The aluminum-encased 2big has arrived, with its (up to) 311 MB/s transfer rates scorching the ground behind it. With hot-swappable disks and dual Thunderbolt ports for daisy chaining, the Portal-esque 2big is on sale now from LaCie’s online store with a three-year warranty. Prices start from $649 for 4TB, moving up to $799 for 6TB. Those looking for the king-size 8TB model should hold onto their wallets for now– it’s listed on Lacie’s product page, but apparently not available just yet.

SOURCE via Lacie

As reported on February 7th, we got a first glimpse of the rumored specifications for Nvidia’s Kepler based graphics cards. The leaked specifications were met with mixed feelings from both sides of the comment fence. Now, we are starting to get more pieces of information on the upcoming Kepler series. Based on information coming out of German-based 3dcenter.org, we may have a clearer picture of the true specifications for Kepler GK104.

Outside of the switch to the 28 nm process, one of the major changes in the Kepler architecture is to allow for more CUDA cores. This is achieved by no longer having shader frequency, just GPU frequency. Each Stream Multiprocessor will contain 96 CUDA cores, unlike the 32 – 48 that Fermi had. This change in layout of the CUDA cores will have the GK104 sporting up to 1536 CUDA cores, which is a big boost from GF110 and GTX 580. The numbers of texture units have doubled from 64 to 128 on GK104. The GK104 will only have 32 ROPS versus 48 in GF110 but it shouldn’t affect performance compared to the Fermi.

The above GK104 architectural overview comes from Bright Side of News.

Nvidia Kepler GK104:

• 28nm production at TSMC,
• Die size 340mm²
• 4 Graphics Processing Clusters (GPC)
• 4 Streaming Multiprocessors (SM) per GPC = 16 SM
• 96 Stream Processors (SP) per SM = 1536 CUDA cores
• 8 Texture Units (TMU) per SM = 128 TMUs
• 32 Raster Operation Units (ROPs)
• Chip clock (top model): 950 MHz
• 1250 MHz actual (5.00 GHz effective) memory, 160 GB/s memory bandwidth
• 256-bit DDR memory interface (up to GDDR5)
• 2048 MB (2 GB) memory amount standard
• 2.9 TFLOP/s single-precision floating point compute power
• 486 GFLOP/s double-precision floating point compute power
• Elimination of Hotclocks

The GK104′s performance is expected to exceed the GTX 580 at the $350 to $400 price range. In addition, it is expected to outperform AMD’s HD 7950 at similar price point and challenge the HD 7970 for the performance crown. The GK104 looks to be the similar to the current generation GTX 560 Ti with regards to price to performance in its category.

Please keep in mind, of course, that these specifications are from 3dcenter’s supposed reliable source. We won’t know for sure until Nvidia shows its hand. Stay tuned!

SOURCE via 3dcenter.org

On February 10th, a leaked slide showed Intel’s tick-tock approach in full swing with the Haswell 22nm core-based processor, planned for 2013. With Ivy Bridge nearing release, we are now learning a little more about Haswell’s integrated GPU (iGPU) from a leaked slide by Turkish website DonanimHaber.

Haswell’s iGPU will feature support for DirectX 11.1, which takes advantage of application programming interface (API) optimization to improve performance for users. DirectX 11.1 will be available with the release of Windows 8. Also, it will feature digital display repartition, where digital display ports are wired directly to the CPU and analog displays are handled by a Random Access Memory Digital-to-Analog Converter (RAMDAC) located in the Platform Controller Hub (PCH). With current Intel iGPUs, all display functions are handled by PCH over the Flexible Display Interface (FDI). This design change will help reduce any possible bottlenecks with higher resolution digital outputs while maintaining analog display quality.

In addition, it will support OpenGL 3.2 and OpenCL 1.2, which will improve performance in certain general purpose computing on graphics processing units (GPGPU) supported applications. The iGPU will feature new Auto-Stereoscopic 3D (AS3D), which will provide 3D support that is typically only available through the use of discrete GPUs. It will support up to three independent displays: HDMI 1.4, DVI, Display Port, VGA.

Please keep in mind, of course, that the information is from an unverified source by DonanimHaber. We won’t know for sure until Intel shows its hand. Stay tuned!

SOURCE via Donanim Haber

In Q4 2011, HDD shipments dropped by 26 percent over the same period in the previous year. Shipments will by 13 percent in Q1 and 5 percent in Q2 on an annual basis, IHS believes. In Q3, the market will stabilize and grow by 2 percent and bounce back with 49 percent in the fourth quarter of this year. Sequentially, HDD shipments are predicted to climb 14 percent in Q1, 11 percent in Q3 and 4 percent in Q4.

“The recovery of global HDD manufacturing has begun and will continue during each quarter of 2012,” noted Fang Zhang, storage analyst for IHS. “However, the recovery will be prolonged for at least two more quarters, as supply constraints keep unit shipments from climbing on an annual basis until third quarter.” The shortage will translate to continued inflated prices throughout 2012, the firm said.

HDD makers and component suppliers have resumed only partial production in Thailand and have shifted some of their manufacturing to other countries to alleviate the impact of the supply shortage.  According to IHS, Western Digital has been the HDD manufacturer most impacted by the floods and is not expected to return to full production until September.

IHS said that the Thailand flood has caused the global average selling price (ASP) for HDDs to jump by 28 percent in Q4 2011. Prices are forecast to decline by 3 percent in Q1 and by 9 percent in Q2. “Prices will remain high for a number of reasons, including the higher costs associated with the relocation of production, as well as higher component costs because of flooding impacts among component makers,” Zhang said. “Furthermore, PC brands have signed annual contacts with HDD makers that have locked them into elevated pricing deals for the rest of the year.”

As report first of February in a leaked roadmap, AMD is set to release its HD 7700 series graphics cards based on the Cape Verde. Based on information coming out of German-based 3dcenter.org, we may have our first glimpse at the full specifications for the new Cape Verde series. The HD 7700 series will utilize AMD’s GCN stream processors seen with the HD 7900 series. With the HD 7770 series, you’ll have a base core-clock speed of 1 GHz, with performance falling between the HD 6850 and HD 6790, at a suggested price around $150 dollars. The HD 7750 should equal performance of the HD 6770/5770 in performance, at a suggested price of around $125 dollars.

Cape Verde Physical

• Built on TSMC 28 nm process, ~1.5 billion transistors
• 10 Graphics CoreNext Compute Units (CUs)
• 640 stream processors
• 40 TMUs, 16 ROPs
• 128-bit wide GDDR5 memory interface

Radeon HD 7770

• All CUs enabled, 640 stream processors
• 1 GB GDDR5 memory
• 40 TMUs, 16 ROPs
• 1000 MHz core clock-speed
• 1125 MHz (actual), 4500 MHz (effective) memory clock-speed
• 72 GB/s memory bandwidth
• 1280 GFLOP/s single-precision floating-point performance
• Typical board power: 80W

Radeon HD 7750

• 8 CUs enabled, 512 stream processors
• 1 GB GDDR5 memory
• 32 TMUs, 16 ROPs
• 800 MHz core clock-speed
• 1125 MHz (actual), 4500 MHz (effective) memory clock-speed
• 72 GB/s memory bandwidth
• 819 GFLOP/s single-precision floating-point performance
• Typical board power: 55W

Please keep in mind, of course, that these specifications are from 3dcenter’s supposed reliable source. We won’t know for sure until AMD shows its hand. Stay tuned!

AMD has released its new entry-level V3900 professional graphics card, which replaces the V3800. The V3900 is priced at $119, which puts it directly up against the Nvidia’s Quadro 400. It sits roughly $50 less than the Nvidia’s Quadro 600 and $20 more than the V3800.

From the specifications, V3900 looks to be a nice update to the V3800 and is basically the business version of the Radeon HD 6570 DDR3. The V3900 has double the memory at 1GB and is based on the “Turks” GPU. The card’s 128-bit DDR3 memory gives it 28.8GB/s of memory bandwidth compared to the V3800, which had a 64-bit interface providing half the bandwidth at 14.4GB/s. It supports the latest versions of OpenGL and OpenCL (4.2 and 1.1, respectively). Based on various test conducted by AMD, the card shows performance increases over both the V3800 and Quadro 400.

Read more…

Some of you thought it would never happen. You thought that these two mortal enemies would spend the rest of their multinational corporate lives alternately at each other throats and eyeing the other with suspicion from across the boardroom. After dropping some claims and winning others, Rambus has signed an agreement with NVIDIA that puts to rest their remaining legal disputes. The deal will allow NVIDIA to use patented Rambus tech in its products for the next five years, without fear of legal action — though, neither side will say how much that privilege cost. Now that the battle between the two, which began way back in 2008, has finally come to a close we can all finally get back to the very important business of forgetting who or what Rambus is.

SOURCE via PC World

AMD has quietly released two additional socket FM1 CPUs that slot in between the Athlon II X4-651 and 631. The new models 638 (2.7 GHz, 65W) and 641 (2.8 GHz, 100W) integrate 32nm Llano cores with inactive graphics units. AMD is selling both processors for a tray price of $81.

In comparison, Intel’s cheapest quad-core CPUs are the i5-2390T (2.7 GHz) and the i5-2400s (2.5 GHz) for $184. AMD is riding the value train as $81 buys at Intel just Pentium processors (G850 with two cores and 2.9 GHz for $75, for example).

AMD is offering Athlon II X4 processors also for socket AM3 at 45nm: the 645 (3.1 GHz, 95W, $102) and 640 (3.0 GHz, 95W, $98).

SOURCE via AMD

Intel officially announced its new 520 Series of solid-state drives on Monday, promising its fastest, most robust client/consumer SSD to date. The drive is produced using Intel compute-quality 25-nm NAND memory process technology and connects via an SATA III 6 Gbps interface, delivering world-class performance “even for the most demanding PC enthusiasts.”

“Any consumer application requiring high throughput and bandwidth, low latencies and accelerated speed will benefit from the Intel SSD 520,” Intel said in a press release. “Software developers, architects, accountants, engineers, musicians, media creators and artists are just some of the professionals that will find that the Intel SSD 520’s full package of features can make a dramatic impact on their productivity. With faster performance for graphic renderings, compiling, data transfers and system boot-ups, users can speed through multi-tasking or once-cumbersome application wait times with an Intel SSD 520 Series.”

Intel reports that the series includes capacities from 60 GB to 480 GB, and packs features such as Advanced Encryption Standard (AES) 256 bit encryption capabilities and stronger password protection for added security in the event of theft or power loss. It also contains an LSI SandForce Flash Storage Processor with an Intel co-defined and validated firmware release.

On a performance level, the 520 Series delivers up to 80,000 maximum 4K random write IOPS and up to 50,000 4K random read IOPS. It also provides sequential read speeds up to 550 MB/s and sequential write speeds up to 520 MB/s. This is backed by thousands of hours of Intel testing and validation, including more than 5,000 individual tests, as well as a 5-year limited warranty, Intel said.

“Our game development workflow involves a combination of large batch process and aggressive interactive pre-visualization, all highly parallelized to the point that the storage performance becomes a major bottleneck,” said id Software’s John Carmack. “For many of our workloads, Intel SSDs have doubled throughput, and in some cases involving mapping tens of gigabytes of image data, we have seen an honest order of magnitude performance improvement, which is a rare and wonderful thing.”

Based on 1,000 unit quantities, the 60 GB model costs $149 per unit, $229 for the 120 GB version, $369 for the 180 GB version, $509 for the 240 GB version and a meaty $999 for the 480 GB version.

According to Nvidia, CUDA-based apps will gain about 10 percent performance as a result.

CUDA 4.1 also includes more than 1,000 new imaging and signal processing functions in the Performance Primitives (NPP) library, which now covers more than 3,200 functions in total. Nvidia claims that the NPP delivers 40 percent greater performance than Intel’s IPP.

The Visual Profiler has been redesigned and now offers an automated expert system to give that provides step-by-step instructions to fine-tune CUDA code. Additionally, the new CUDA toolkit integrates version 2.1 of Parallel Nsight, a collection GPU developer tools for Visual Studio.

CUDA 4.1 can be downloaded from Nvidia’s website. Read more…