Partners Showcase AMD RD790 Motherboards

ASUS, DFI and Gigabyte prepare RD790, RD780 and RX780 motherboards.

AMD motherboard partners displayed RD790-based motherboards at Computex 2007. ASUS, DFI and Gigabyte have RD790 motherboards on display. Gigabyte is the only partner to have a live demonstration of RD790, from what we have seen. The Gigabyte GA-M790-DQ6 features four PCIe 2.0 x16 slots capable of dual x16 or quad x8 configurations.

The live demo of the Gigabyte GA-M790-DQ6 did not have two ATI Radeon GPUs operating in CrossFire. Instead, Gigabyte equipped the RD790 demo system with a single ATI Radeon HD 2600 XT.

The Gigabyte GA-M790-DQ6 does not have any PCIe x1 slots. However, the GA-M790-DQ6 features two standard PCI slots. Gigabyte also equips the GA-M790-DQ6 with a Realtek ALC889 high-definition audio codec capable of 106dB signal-to-noise ratios.

ASUS had the M3A32-MVP Deluxe on display. The upcoming ASUS M3A32-MVP Deluxe supports Socket AM2+ processors with HyperTransport 3.0, or HT3. The board features dual PCIe 2.0 x16, three PCI and one PCIe x1 slots. The ASUS M3A32-MVP Deluxe will also support DDR2-1066 memory.

ASUS equips the M3A32-MVP Deluxe with an elaborate heat-pipe cooling setup. The heat-pipe cools the RD790, SB600 and accompanying system memory.

DFI had the LANPartyUT RD790-M2R on display. The LANPartyUT RD790-M2R features four PCIe 2.0 x16, two PCI and one PCIe x1 slots. DFI only claims HyperTransport 1.0 support with the LANPartyUT RD790-M2R. Nevertheless, the LANPartyUT RD790-M2R features a six-phase Vcore and one-phase digital PWM. Additionally, the DFI LANPartyUT features dual Gigabit Ethernet ports with teaming technology and DFI Bernstein eight-channel audio.

ASUS had additional AMD 7-series motherboards on display – the M3A-MVP and M3A. The ASUS M3A-MVP features the mainstream RD780 chipset with a cut-down PCIe lane configuration. ASUS equips the M3A-MVP with two physical PCIe 2.0 x16 slots. The PCIe 2.0 x16 slots default to dual eight-lane configurations when both slots are occupied.

The ASUS M3A-MVP also features three PCIe x1 and two PCI slots for expansion. The vanilla M3A-MVP does not receive the elaborate heat-pipe setup as its deluxe brethren.

Lastly is the value-level ASUS M3A. The ASUS M3A features the AMD RX780 chipset paired with the SB600. The AMD RX780 does not support CrossFire. The ASUS M3A features one PCIe 2.0 x16, three PCIe x1 and three PCI slots.

Expect AMD RD790, RD780 and RX780 motherboards later this year.

NVIDIA Partners Quietly Rollout Retail GeForce 8400GS

NVIDIA takes on the entry-level DirectX10 market with a sub-$100 retail graphics card.

Graphic card manufacturers silently launched retail GeForce 8400GS-based add-in boards this week. The GeForce 8400GS is NVIDIA’s newest retail entry-level offering, slotting below the GeForce 8500GT. NVIDIA previously released the GeForce 8400GS a couple months ago to OEMs only.

The retail GeForce 8400GS arrives ready to take on AMD’s upcoming ATI Radeon HD 2400-series. The entry-level offering introduces DirectX and shader model 4.0 to a sub-$100 price point. NVIDIA also packs the GeForce 8400GS with PureVideo HD for hardware accelerated video decoding, which accelerates decoding of H.264, VC-1 and MPEG2 high-definition video formats.

GeForce 8400GS-based cards feature 16 stream processors clocked at 900 MHz with a 450MHz core clock – similar to the GeForce 8500GT. NVIDIA pairs the GeForce 8400GS with 256MB of 400 MHz, 800 MHz effectively, DDR2 memory as with the GeForce 8500GT. However, NVIDIA has castrated the memory interface, leaving the GeForce 8400GS with a 64-bit interface instead of the 128-bit interface found on the 8500GT.

Expect GeForce 8400GS-based cards to start popping up in retail within the coming weeks. A quick search reveals MWAVE is the only retailer with a GeForce 8400GS in stock for $70.

INTEL DETAILS LONG-TERM XEON,ITANIUM PLANS

Intel says Itanium will continue to sail for the long run.

Intel this week revealed new details about where it plans to take its server processor business, specifically with the Itanium processor. As many know, Intel took a gamble on the Itanium when it was released several years ago. Intel's use of a then uncommon Explicitly Parallel Instruction Computing (EPIC) architecture left the majority of the industry unsure of Itanium's practicality in an x86-dominated world. Today however, the Itanium family brings in roughly $3.5 billion per annun for Intel.

Diane Bryant, vice president of Intel's enterprise group, revealed several details that indicate Intel will push forward with Itanium development for the foreseeable future.

Currently, Intel's flagship Itanium 2 processor is the Montecito core. Intel announced Montecito last July, marking the company's first dual-core enterprise and mainframe processor. Until now, Montecito ran on a 533MHz front-side bus but will soon make the transition a 667MHz front-side bus processor in Q4 2007, dubbed Montvale. According to Bryant, Montvale will consist of minor updates, improving bus speed but also improving overall stability.

Recent Intel roadmaps indicate that Montvale will consist of roughly 25 percent of Intel's Itanium business in Q4 2007. By Q1 2008, Intel guidance suggests Montvale will take up a whopping 40 percent of all Itanium 2 sales. Despite Intel's desktop processors currently seeing day light at 65nm, Itanium 2 processors will still be on 90nm manufacturing technology. Montvale will also top out at a core speed of 1.66GHz with a total of 24MB of L3 cache.

Intel's next major milestone in the Itanium family will come with the arrival of Tukwila, a quad-core processor due sometime in late 2008. According to Bryant, Tukwila will be roughly twice as fast as Montecito and feature an on-die memory controller.

This will be a turning point for Intel because with Tukwila's need for a discrete memory controller gone, the company will introduce its long waited common system interface (CSI). Tukwila's use of CSI will be a direct response to AMD's HyperTransport technology. Intel previously stated it will not restrict CSI to the Itanium family, but will eventually use the technology as the main transport bus for the Xeon family as well.

Tukwila will also come with even larger caches and a new reliability feature called double device data correction (DDDC). DDDC acts as a failsafe mechanism to protect system memory failures from bringing down a live system. In a hardware failure where a memory chip on a memory module fails, DDDC will be able to mark that chip as unusable without compromising system stability. DDDC differs from traditional ECC and parity technology due to its capability to withstand more than one chip failure.

Bryant went on to reveal details about the future release of an entirely new Itanium architecture code-named Poulson. With Poulson, Bryant claims Intel will introduce even more cores; greater scalability and the introduction of 32nm die fabrication for its enterprise segment. The company will skip 45nm technology altogether for Itanium. Bryant did not give details on a possible release date for Poulson although Intel is expecting to introduce 32nm processors in approximately two years.

PANASONIC ANNOUNCES NEW 45nm LSI FOR DIGITAL AV DEVICES

Matsushita develops UniPhier system LSI using a 45-nm process.

Matsushita Electric Industrial, best known for its Panasonic brand, has recently developed a new-generation of its “UniPhier” LSI system that integrates new AV data compression/decompression (codec) technology. The company started mass-production of the new 250 million transistor chip this month on a 45nm process.

The UniPhier system is already widely used in many Panasonic digital AV devices, though the updated LSI adds an AV codec that responds to the next-generation image data compression standard, such as H.264, ideal for handling high-definition images.

Matsushita says that the chip features multi-decoding technology that enables two 1080p (1920X1080) high-definition (HD) screens to be processed simultaneously, and a high image quality encoding technology to compress 1080p HD images to a one third to half the size of conventional methods.

The additional circuitry required to process high-definition streams, which posed manufacturing challenges on the 65nm level, was more easily achieved at 45nm. Additionally, using the 45nm process reduced the device’s overall power requirements and heat output.

Matsushita is the latest to announce LSI technology using a 45nm semiconductor process. Earlier this week, Fujitsu revealed its own 45nm LSI for mobile applications.

---

Intel Prepares New Value Chipset

Intel G31 and P31 Express to replace 946GZ, 946PL and 046G ExpressIntel plans to release two value-level chipsets next quarter – the G31 and P31 Express.

The new G31 and P31 Express chipsets replace the current 946GZ, 946PL and 945G Express offerings. The G31 and P31 Express slot below the G33 Express, but are not Bearlake derivatives. The Intel G31 and P31 Express chipsets are actually 945-generation derivatives with added support for Yorkfield and Wolfdale processors.Features of the G31 and P31 Express chipsets remain similar to the 945GZ, 945PL and 945G Express chipsets. The G31 and P31 Express support Intel processors with a 1066 MHz front-side bus. Official support for 1333 MHz front-side bus processors will not arrive until Q1’2008, after Intel completes validation. The new value chipsets support DDR2-800 memory. Additionally, Intel pairs the G31 and P31 Express chipsets with the ICH7, ICH7R and ICH7DH south bridges. Differentiating the G31 and P31 Express chipsets is the integrated graphics core found on the G31 Express. Intel equips the G31 Express with a Graphics Media Accelerator 3100, or GMA 3100, graphics core. The GMA 3100 graphics core is essentially the previous GMA 950 rehashed and improved with a new name. The GMA 3100 graphics core lacks hardware T&L and Intel Clear Video Technology. Pixel and vertex shader functions are purely software-based on the GMA 3100. Expect Intel to unveil the G31 and P31 Express chipsets next quarter.