Without making any public announcement (because it’s not meant for retail sale), NVIDIA listed its GeForce GT 420 graphics card. This product is available to OEMs only. The GT 420 is derived from the Fermi architecture, and is fully compliant with the latest PC graphics technologies, including DirectX 11 and OpenGL 4. NVIDIA’s reference design is low-profile and single-slot, it draws all its power from the PCI-Express slot.

Under the hood is a 40 nm graphics core (perhaps GF108), it has 48 CUDA cores, and connects to 2 GB of memory across a 128-bit wide DDR3 memory interface, with 28.8 GB/s of memory bandwidth. The core is clocked at 700 MHz, CUDA cores at 1400 MHz, and memory at 900 MHz (1800 MHz effective). Display outputs include DVI, HDMI (full-size), and a detachable D-Sub connector. The card has a maximum power draw of 50W. Later down the line, one can expect NVIDIA to make a consumer GeForce SKU with the same specifications.

Well placed sources seem to have finally pieced together specifications of NVIDIA’s GeForce GTS 450 graphics card, the company’s mid-range offering that competes with ATI Radeon HD 5700 series products. In the run up to this, we’ve come across reports showing that the SKU is based on a GPU codenamed GF106, then we came across NVIDIA reference design PCB drawings, followed by clock speeds, and finally, pictures of the GPU itself revealing quite a bit about the die size. The most recent report affirms the specs we know till now, plus revealed the CUDA core count, which is 192. The CUDA cores are clocked at 1566 MHz, and that the memory is clocked at 902 MHz (3608 MHz effective).

So as a quick recap of the tech specs of the GeForce GTS 450, it’s based on the new 40 nm GF106 silicon, the die area is roughly 240 mm². The GPU has 192 CUDA cores, and a 128-bit wide GDDR5 memory interface holding 1 GB of memory. The core is clocked at 789 MHz, and memory at 902 MHz (3608 MHz effective), translating into 57.8 GB/s of memory bandwidth, CUDA cores at 1566 MHz. It supports 2-way SLI, and gives you access to the latest PC graphics technologies, including support for DirectX 11 and OpenGL 4.x, along with support for a wide range of NVIDIA-exclusive technologies. NVIDIA’s GeForce GTS 450 will be released by mid-September.

Source: Heise.de

With its launch reportedly scheduled for 12th July, certain European etailers just can’t resist listing it on their sites to pool in prospective buyers or pre-orders. Price aggregator Geizhals.at compiled a list of stores that have already listed the ASUS GeForce GTX 460 768MB (part number 90-C3CHB0-P0UAY0KZ). Prices of this part range start at 204.51 EUR. Another source reports that NVIDIA is targeting the US $199 price point with the GeForce GTX 460 768MB variant, and $229 price point with the 1 GB variant. The 25% more higher memory amount isn’t the only thing that warrants the $30 increase in price, the 1 GB variant also has 25% higher memory bandwidth.

The GeForce GTX 460 is NVIDIA’s latest product in the making, it is based the new GF104 core, that packs 336 CUDA cores, 256-bit GDDR5 memory interface (192-bit on the 768 MB variant), and has all the features of the GeForce 400 series, including advanced tessellation, DirectX 11, CUDA, PhysX, and 3D Vision Surround.

Sources: Geizhals.at, VR-Zone

The much talked about upcoming GeForce GTX 460 GPU from NVIDIA was recently pictured and detailed. Out of its first, grainy pictures, it became clear that the GF104 core it’s based on indeed supports a 256-bit wide GDDR5 memory interface, but that only six of its eight 32-bit wide channels were occupied (192-bit), yielding 768 MB of memory. Fresh reports suggest that NVIDIA indeed will release the GeForce GTX 460 in two variants, a 768 MB one, and a 1024 MB (1 GB). The 1 GB variant by design will be faster, even if an application doesn’t need all its video memory, because it will have a wider 256-bit memory interface, that’s 25% higher memory bandwidth. Both variants will have the same memory clock speed of 900 MHz (3600 MHz effective). The GF104 core will be clocked at 675 MHz on both models, with 336 CUDA cores. Built on the 40 nm process at TSMC, the GeForce GTX 460 768 MB will have a TDP of 150W, while the 1 GB model will have a TDP of 160W. New reports suggest that the 768 MB model will be priced at less than $200. NVIDIA will release the GeForce GTX 460 on the 12th of July.

Source: DonanimHaber

HIS today unveiled low-profile graphics cards based on the Radeon HD 5550 and Radeon HD 5570 that make use of GDDR5 memory that doubles the memory bandwidth available to the GPU. The cards come in both 512 MB and 1 GB variants. Both have memory operating at 1000 MHz (4 GHz effective). Based on the 40 nm Redwood core, the HD 5550 card has 320 stream processors, is DirectX 11 compliant, and has a 128-bit wide memory interface that normally holds GDDR3 or DDR2 memory for the HD 5500 series SKUs. HIS went beyond the specs, using GDDR5 (which the GPU supports in its HD 5600 series SKUs). The HD 5570 has 400 stream processors, with the GPU operating at 650 MHz, while on the HD 5550, it runs at 550 MHz. The low-profile cards are also silent, with a passive cooler that occupies a single expansion slot doing the job of cooling the memory and GPU. The HD 5550 512 MB GDDR5 card goes for 89 EUR, while the 1 GB variant at 99 EUR. Pricing of the HD 5570 cards are yet to be known.

NVIDIA made its GeForce GTX 480M GPU official today. The DirectX 11 compliant GPU is based on the GF100 core and packs all the features of its desktop counterpart, such as decentralized hardware tessellation, next-generation CUDA and DirectCompute 5.0. The GF100 core has a configuration similar to the GeForce GTX 465 desktop GPU. It has three of its four graphics processing clusters (GPCs), and 11 out of 16 streaming multiprocessors (SMs) enabled, giving a CUDA core count of 352. To reduce the overall board footprint, the GPU makes do with a 256-bit wide GDDR5 memory interface, with 1 GB of memory.

To make keep up with the electrical constraints of notebooks, the GTX 480M uses much lower clock-speeds than any desktop product that uses GF100. The core is clocked at 425 MHz, shader domain at 850 MHz, and memory at 600 MHz (real) or 2.40 GHz (effective), which gives a memory bandwidth of 76.8 GB/s. As mentioned earlier, the full feature-set of its desktop counterparts is packed with the GTX 480M, including support for NVIDIA 3D Vision, PureVideo HD, PhysX, and CUDA. It can pair with up to two boards of its kind in 2-way SLI. Constraints of the notebook form-factor won’t allow any more boards, anyway. The GPU is open to Notebook manufacturers to plan their designs around. NVIDIA claims the GTX 480M to be the fastest notebook GPU. It finds direct competition in the ATI Mobility Radeon HD 5870, which is based on the 800 stream processor-laden Juniper core.

Transcend Information, Inc., a global leader in storage and multimedia products, today announced the expansion of its aXeRam product line with the introduction of 6GB DDR3-2000 triple-channel and 4GB DDR3-1600 dual-channel kits. Featuring unparalleled overclocking performance with an exceptionally low voltage of just 1.6V, both new memory kits are designed to meet the strict RAM requirements of gamers and enthusiasts.

Transcend’s aXeRam DDR3-2000 memory is now available in triple-channel configuration, designed specifically for high-end motherboards sporting Intel’s X58 chipset, including the ASUS P6X58D PREMIUM and Gigabyte’s GA-X58A-UD3R. The 6GB DDR3-2000 kit consists of three 2GB modules rated at 2000MHz with timings of 9-9-9-24 and an operating voltage of a mere 1.6V, offering memory bandwidth up to an incredible 48GB/s-an increase of 35% compared to standard 1333MHz memory. Thanks to Transcend’s adoption of high thermal efficiency aluminum heat sinks with cooling fins, the aXeRam DDR3-2000 memory kit gives enthusiasts a performance advantage through optimized heat diffusion while overclocking and gaming.

TechPowerUp today released version 0.4.2 of the GPU-Z graphics subsystem information and monitoring utility. This release comes quicker than its typically one-month development cycle, as it fixes some important issues. Version 0.4.2 resolves an issue with some NVIDIA GeForce graphics cards where GPU-Z may affect fan-speed control. It fixes a rare crash on MSI R5830 Twin Frozr II graphics card, and reverts to its old method of calculating graphics card memory bandwidth which caused some confusion among the enthusiast community. The ongoing Hardware Giveaway stays, giving you a chance to win some groovy ASUS Republic of Gamers series graphics cards and motherboards.

DOWNLOAD: TechPowerUp GPU-Z 0.4.2

A complete list of changes (changelog) follows.

Transcend Information, Inc., a global leader in storage and multimedia products, today announced that its aXeRam DDR3-2000 memory kits have been officially certified under the Intel Extreme Memory Profile (XMP) validation program. Fully compatible with Intel Core i7 processors, the XMP-certified DDR3 kits are designed to operate at a blazing-fast clock frequency of 2000 MHz with an exceptionally low voltage of just 1.6V.

Intel XMP is a performance-packed expansion of the standard DDR3 memory specification. Featuring memory bandwidth up to an incredible 32GB/s, Transcend`s aXeRam DDR3-2000 dual-channel memory kit is rated at 2000MHz with timings of 9-9-9-24, allowing performance enthusiasts and gamers to take their Intel Core i7 platform to the next level of memory overclocking performance. The aXeRam DDR3-2000 memory modules have been certified for use on Intel P55-based motherboards, including Gigabyte GA-P55A-UD3, MSI P55-GD80 and Asus P7P55D Deluxe.

TechPowerUp today introduced version 0.4.0 of GPU-Z, the popular graphics-subsystem information and monitoring utility. The release comes in the midst of a number of new graphics processors from various vendors, and hence adds support for most of them. To begin with GPU-Z now supports NVIDIA GeForce GTX 480, GeForce GTX 470 GPUs (launched today), it adds voltage monitoring support for ATI Radeon HD 5750, ATI Radeon HD 5830, and MSI R5870 Lightning. It supports Intel “Pineview” Atom processors with embedded graphics processors. It correctly reads memory actual clock speeds for NVIDIA GPUs with GDDR5 memory interface, adds tooltip language support for Traditional Chinese and Albanian, and more standards-compliant method of calculating memory bandwidth.

With this release, ASUS and TechPowerUp team up for a special Hardware Giveaway, a simple form to fill, and you will stand a chance to win some epic pieces of hardware from ASUS’ elite Republic of Gamers series. To participate, complete and submit a simple questionnaire in the “Hardware Giveaway” tab of GPU-Z 0.4.0. The giveaway is open to GPU-Z users of all nationalities, participation is free of charge. More details such as what prizes are up for grabs, and terms and conditions can be found in that tab.

DOWNLOAD: TechPowerUp GPU-Z 0.4.0

A complete list of changes (changelog) follows: