The first official die-shots of the first Bulldozer architecture derivative, the eight-core “Orochi” Opteron die was displayed at Global Technology Conference, by GlobalFoundries, AMD’s principal foundry-partner. While AMD did not give out a die-map to go with it, the structures we can make out are four Bulldozer modules holding two cores and a shared L2 cache each, a L3 cache spread across four blocks that’s shared between all cores, the northbridge-portion cutting across the die at the center, and the integrated memory controller along its far-right side. Various I/O portions are located along the other three sides.

Next up is the Llano die. This is AMD’s very first Fusion APU (accelerated processing unit) die. It is based on the K10 architecture and integrates a graphics processor and northbridge completely into one die. It precedes APUs based on the Bobcat architecture. Fortunately, there is a die-map at hand, which shows four K10 cores with dedicated 1 MB L2 caches per core, no L3 cache, an integrated SIMD array that holds 480 stream processors. The GPU component is DirectX 11 compliant. Other components include an integrated northbridge, integrated memory controller, integrated PCI-Express root complex, and HyperTransport interface to the chipset.

AMD rolled out a reference-design DisplayPort to DVI active adapter today, that lets the masses create Eyefinity setups on existing monitors easier. The adapter plugs into full-sized and mini DisplayPort connectors on ATI Radeon graphics cards, and gives out a single-link DVI signal. The conversion between DP to DVI is active, and conserves video quality, as well as other features such as content protection. This is because when Eyefinity-ready graphics cards with DisplayPorts from AMD came to be, some manufacturers sold cheap $10 DP-DVI dongles that pass DVI signals from the DP directly (passive conversion). Such dongles more often don’t work, because Radeon GPUs don’t give out DVI signals from DP. Active adapters (those which actively convert DP signals to DVI) were sold at the time in upwards of $100.

AMD has managed to bring the price of such active adapters down to $30. There however, is a limitation. The output is a single-link DVI, meaning that it will support digital resolutions only up to 1920 x 1200 @ 60 Hz (1080p is supported). It shouldn’t matter for the target users, because the DisplayPort on ATI Radeon HD 5000 graphics cards conveys only one TMDS link, so even with a DVI dual-link capable adapter, it would only give out single-link output. At least a bulk of the users are covered, at a very affordable price point. AMD will market this adapter directly, and through its growing network of add-in board partners (in bundles with graphics cards, or directly). PowerColor beat AMD to today’s announcement, and released PowerColor-branded AMD-reference DP-DVI adapter last week.

Source: HardwareCanucks

This had to happen eventually, and it did just happen: AMD has dissolved the ATI brand completely, and consolidated ATI brands, such as Radeon and FirePro under the AMD main brand. Under the new branding scheme, new graphics products AMD launches (such as the upcoming Radeon HD 6000 series), will do away with “ATI” completely from the logo, marketing material, and so on, and the market will, as it already has been doing since the AMD-ATI merger, albeit informally, refer to Radeon/FirePro products as “AMD Radeon” and “AMD FirePro”.

AMD explains its move as an “evolution of the AMD brand portfolio”, saying that consolidation of ATI-branded products under the main brand results in reduced marketing overhead. It claims to have surveyed several thousand discrete graphics-aware users in in the U.S., U.K., Germany, China, Japan, Brazil, and Russia. The survey revealed that when made aware of ATI-AMD merger, AMD preference triples; AMD brand is stronger than ATI (against graphics competitors); and that people see Radeon and FirePro product names more conspicuous than ATI, indicating a “permission” to consolidate ATI into AMD. The survey was conducted entirely by AMD.

AMD is finally going to embrace a truly next generation x86 processor architecture that is built from ground up. AMD’s current architecture, the K10(.5) “Stars” is an evolution of the more market-successful K8 architecture, but it didn’t face the kind of market success as it was overshadowed by competing Intel architectures. AMD codenamed its latest design “Bulldozer”, and it features an x86 core design that is radically different from anything we’ve seen from either processor giants. With this design, AMD thinks it can outdo both HyperThreading and Multi-Core approaches to parallelism, in one shot, as well as “bulldoze” through serial workloads with a broad 8 integer pipeline per core, (compared to 3 on K10, and 4 on Westmere). Two almost-individual blocks of integer processing units share a common floating point unit with two 128-bit FMACs.

AMD is also working on a multi-threading technology of its own to rival Intel’s HyperThreading, that exploits Bulldozer’s branched integer processing backed by shared floating point design, which AMD believes to be so efficient, that each SMT worker thread can be deemed a core in its own merit, and further be backed by competing threads per “core”. AMD is working on another micro-architecture codenamed “Bobcat”, which is a downscale implementation of Bulldozer, with which it will take on low-power and high performance per Watt segments that extend from all-in-One PCs all the way down to hand-held devices and 8-inch tablets. We will explore the Bulldozer architecture in some detail.

AMD today announced the appointment of Donald Newell as vice president and Chief Technology Officer (CTO), Server. A distinguished engineer with more than 20 patents filed, Newell previously served as a senior principle engineer leading the System-on-Chip (SoC) and datacenter networking architecture groups within Intel Labs before joining AMD to lead its server roadmap and platform design programs.

As AMD Server CTO, Newell is responsible for the concept and definition of AMD’s long-term server roadmap based on current conditions, expected demand and long-term server trends. He is leading multiple worldwide teams and working alongside other AMD design and development teams to ensure successful transition of programs from design to market availability. Newell reports to Rick Bergman, senior vice president and general manager, AMD Products Group.

AMD today announced the appointment of Donald Newell as vice president and Chief Technology Officer (CTO), Server. A distinguished engineer with more than 20 patents filed, Newell previously served as a senior principle engineer leading the System-on-Chip (SoC) and datacenter networking architecture groups within Intel Labs before joining AMD to lead its server roadmap and platform design programs.

As AMD Server CTO, Newell is responsible for the concept and definition of AMD’s long-term server roadmap based on current conditions, expected demand and long-term server trends. He is leading multiple worldwide teams and working alongside other AMD design and development teams to ensure successful transition of programs from design to market availability. Newell reports to Rick Bergman, senior vice president and general manager, AMD Products Group.

Come this Winter, and things will heat up once again in the graphics card industry, with GPU vendors battling it out for the crucial Holidays shopping season. While AMD did not introduce any new GPUs after completing its ATI Radeon HD 5000 series launch itinerary, it did manage to grab significant amount of sales from its graphics rival NVIDIA. For this Winter, AMD and its partners will be in a position to launch the ATI Radeon HD 6000 series graphics processors, according to DigiTimes, citing sources from graphics card vendors.

It is also said that the Radeon HD 6000 series, codenamed “Southern Islands” (members of which are codenamed after islands in the Mediterranean Sea), will be built on TSMC’s 40 nm manufacturing process. AMD had originally planned to build Southern Islands on TSMC’s 32 nm process, but with the foundry skipping 32 nm bulk for 28 nm which will start operations only by the end of the year, AMD redrew its plans and stuck to the now-mature (stable) 40 nm process. Perhaps AMD learned a thing or two from a wide range of teething problems that plagued the 40 nm production line.

Source: DigiTimes

AMD today announced the availability of the ATI Stream Software Development Kit (SDK) v2.2 with full OpenCL 1.1 support to provide developers with the tools they need to build incredible next-generation applications. By taking advantage of both CPU and GPU processing power in a given system, applications like 3D video, HD video chat and multi-display 3D gaming are possible.

A development platform created by AMD, the ATI Stream SDK v2.2 brings a wide range of tools to the developer community including support for OpenCL 1.1, in addition to Ubuntu 10.04 and Red Hat Enterprise Linux 5.5. This updated development platform empowers the developer community to accelerate applications on the CPU and GPU quickly and efficiently. The new version is available for download here.

Following AMD’s recent announcement of a tie-up with Apple over supply of ATI Radeon graphics processors to be pre-fitted on iMac and Mac Pro product lines, news is surfacing that the engagement between the two will get even deeper. The next version of Apple TV will feature AMD’s Fusion APU (accelerated processing units), making it the first Apple product to use an AMD processor. An APU is technically identical to the Intel Core i3 or Core i5 dual-core processors found in the market today (that have the CPU and an IGP in the same package), except that the first Fusion APUs will have the processor cores and an ATI Radeon GPU on the same die, and more importantly, the GPU will be DirectX 11 and OpenGL 4.1 compliant, and have performance on par with the ATI Radeon HD 5500 series discrete GPUs.

For Apple TV this means that it will have a GPU that’s powerful enough to run a more complex, higher resolution user interface, and make use of AMD’s advanced HD video acceleration features, while literally 60% of the vital components are contained within one chip (CPU, IMC, GPU, northbridge). Apple TV is a device that plugs into HDTVs, providing interactive TV and video streaming features over the iTunes store service. It can also connect to your media collection over a wireless network.

Source: DigiTimes

AMD has finally surpassed NVIDIA in terms of shipments of discrete graphics (graphics cards), according to market research firm Mercury Research, in a report released on Wednesday. AMD’s discrete graphics products held 51% of the discrete graphics market, with NVIDIA slipping down to 49%, in terms of discrete graphics products shipments in Q2 2010. For the same quarter last year, the two were poised at 41% for AMD and 59% for NVIDIA, indicating a significant growth, fruition of AMD’s DirectX 11 push of deploying a new-generation lineup that spans all price-points in a span of four months.

For the overall GPU industry, with integrated graphics included, the picture for Q2 2010 looks like Intel holding 54.3%, AMD holding 24.5%, and NVIDIA with 19.8%. Last year, in Q2 2009, NVIDIA held 29.6% versus AMD’s 18.2%. NVIDIA’s deployment of a DirectX 11 compliant GPU lineup has been rather slow, with only two GPUs and four SKUs deployed so far, starting at $199. NVIDIA does not have the fastest graphics card. On Wednesday, the Santa Clara based company warned that its revenue would fall short of earlier projections (set at the time of Fermi’s launch). This announcement came after Apple announced a series-wide transition of graphics chips inside its Macbooks, iMac, and Mac Pro computers to AMD’s ATI Radeon from NVIDIA GeForce.

Source: CNET