AMD, building on its leadership in graphics and gaming, announced its 2014 mobile Accelerated Processing Unit (APU) product roadmap at the APU13 Developer Conference today. Raising the performance bar across fanless tablets, 2-in-1s and ultrathin notebooks, the APUs codenamed "Mullins" and "Beema" are projected to deliver more than 2x the performance-per-watt of the previous generation.

The latest AMD APUs also support Microsoft InstantGo for faster wake times and to ensure data such as email actively refresh in standby. Both new processor families are also the first to integrate an AMD-developed platform security processor based on the ARM Cortex-A5 featuring ARM TrustZone technology for enhanced data security. The new low-power APUs join the previously disclosed high-performance notebook APU, codenamed "Kaveri," in AMD's 2014 mobile lineup.Image courtesy of Computerbase.de

A HIS-branded AMD reference design Radeon R9 290X graphics card was taken apart by Expreview, revealing its cooling solution, the PCB, the VRM, and the star attraction, the company's new 28 nm "Hawaii" silicon. The pictures match with an earlier, blurrier leak from September. The cooling solution is typical AMD fare, with its copper plate covering the GPU, memory, and VRM areas, aluminium channels, and a lateral-flow fan. The PCB features the swanky new 7.08 billion-transistor chip from AMD, sixteen GDDR5 memory chips (all of which are on the obverse side), and the 5+1+1 phase VRM, which uses CPL-made chokes, IR-made DirectFETs, and a new IR-made VRM controller. The first reviews of the Radeon R9 290X should be published later this month. Find more pictures at the source.

AMD's next-generation flagship graphics card, the Radeon R9 290X, could strike a US $599.99 (or 499.99€, £399.99 before taxes) price-point, turning up the heat on the more expensive offerings by NVIDIA - GeForce GTX 780 and GTX TITAN. The card should be available from mid-October. Based on the new 28 nm "Hawaii" silicon, the card is expected to feature 2,816 GCN stream processors, spread across 44 SIMDs (11 computing units). Other specifications include 172 TMUs, 44 ROPs, and a 512-bit wide GDDR5 memory interface, holding 4 GB of memory, which likely achieves its >300 GB/s memory bandwidth with a 5.00 GHz memory clock. The company is expected to launch 6 GB variants of the card a little later.

GLOBALFOUNDRIES and Fuzhou Rockchip Electronics Co., Ltd. today announced that Rockchip's next-generation mobile processors are ramping to production on GLOBALFOUNDRIES' 28 nm High-K Metal Gate (HKMG) process technology. Based on a multi-core ARM Cortex-A9 design, the RK3188 and RK3168 chips are optimized for tomorrow's high-performance, low-cost tablets that require long-lasting battery life (see product specifications in annex).

The combination of Rockchip's design and GLOBALFOUNDRIES' 28 nm HKMG process technology resulted in a mainstream tablet System-on-Chip (SoC) capable of operating at up to 1.8 GHz performance, while still maintaining the power efficiency expected by mobile device users. The chips began sampling to OEMs in early 2013 and are now ramping to support a wide range of manufacturers.

ECS unveiled one of the very few mini-ITX motherboards to ship with an AMD "Kabini" A6-5200. The chip integrates both the APU and FCH, making it a true system-on-chip (SoC). It packs four x86-64 "Jaguar" CPU cores, a Radeon HD 8400 series GPU with 128 stream processors, a dual-channel DDR3 memory controller, and a modern FCH chipset. On the KBN-I, the 28 nm chip is cooled by a small fan-heatsink. The PCB area gained by the single-chip solution is used to create two mPCIe expansion slots, in addition to the PCI-Express 2.0 x16. The board draws power from just a 24-pin ATX connector. Connectivity include two SATA 6 Gb/s ports, 6-channel HD audio, D-Sub and HDMI display outputs, four USB 3.0 ports, and a gigabit Ethernet connection.

NVIDIA launched the business-end of its GeForce GTX 700 series, launching the GeForce GTX 770. Tough to make apart from GeForce GTX 780 and GeForce GTX TITAN visually, the GTX 770 is based on the 28 nm GK104 silicon, configured similarly to the GeForce GTX 680 from the previous generation, albeit with higher clock speeds, GPU Boost 2.0, and a stronger VRM to sustain those higher clock speeds. The card ships with 1046 MHz core, 1085 MHz GPU Boost, and a blistering 7010 MHz (GDDR5-effective) memory. It features 2 GB of memory, 4 GB variants could launch soon.

The GeForce GTX 770 packs 1,536 CUDA cores, 128 TMUs, and 32 ROPs, and a 256-bit wide GDDR5 memory interface. At its given memory speeds, it could belt out 224 GB/s of memory bandwidth. To support these higher clock speeds, the card draws power from a combination of 8-pin and 6-pin PCIe power connectors. Display outputs include a pair of DVI, an HDMI, and DisplayPort. The card can pair with three more of its kind, for 4-way SLI. As predicted, the GeForce GTX 770 starts at US $399. NVIDIA's partners could come out with custom-design cards from day-one.

NVIDIA announced the GeForce GTX 780, the first addition to its desktop GeForce GTX 700 series. Pictured below, the card is as close as it gets to owning a GeForce GTX TITAN, at two-thirds the price. It's based on the same 28 nm GK110 chip, but configured with 2,304 CUDA cores and 192 TMUs, compared to the 2,688 cores and 224 TMUs of the GTX TITAN. The card retains the 384-bit wide GDDR5 memory interface, but holds 3 GB of memory. In that sense, all its key faculties are an exact 50 percent increase over is predecessor, the GeForce GTX 680.

NVIDIA completely recycled the design of GeForce GTX TITAN, down to the PCB and cooler. The only way you can make the two cards out is the lack of memory chips on the GTX 780's back. The card features GPU Boost 2.0, a technology that debuted with the GTX TITAN, boosts clocks and voltage, taking temperatures into account. The GPU core is clocked at 863 MHz, GPU Boost at 900 MHz, and memory at 6.00 GHz (GDDR5-effective). NVIDIA is allowing its partners to launch products with custom design air cooling solutions. Prices should start at $649.99.Read our reviews:

• NVIDIA GeForce GTX 780 (reference)
• GIGABYTE GeForce GTX 780 WindForce OC
• GeForce GTX 780 SLI

AMD today launched three new additions to its 2013 A-Series and E-Series Mobile Accelerated Processing Unit (APU) lineup -- delivering solutions ideally positioned to address today's evolving PC market with dramatically increased performance and power efficiency, as well as a portfolio of unique user experiences, and superior gaming and graphics:

• The 2013 AMD Elite Mobility APU (formerly codenamed "Temash") -- the world's first 28nm, quad-core x86 system-on-a-chip (SoC) APU designed for touch small form-factor notebooks, tablets, and hybrids 13-inches and below;
• The 2013 AMD Mainstream APU (formerly codenamed "Kabini") -- the first and only quad-core x86 SoC solution for entry-level and small-form factor touch notebooks;
• New, low power versions of the 2013 AMD Elite Performance APU (formerly codenamed "Richland") -- offer the best graphics and compute in a performance APU for premium ultrathin notebooks.

Albeit a wee bit late, GIGABYTE joined the Radeon HD 7990 launch party with a card of its own (model: GV-R799D5-6GD-B). Pictured below, GIGABYTE's offering is no different from any of the HD 7990 cards launched this Wednesday, except the company decals on the card. It sticks to AMD reference clock speeds of 1000 MHz core, and 6.00 GHz memory, featuring 6 GB of it. The dual-GPU graphics card runs a pair of 28 nm "Tahiti" GPUs, each featuring 2048 stream processors, 128 TMUs, 32 ROPs, and 384-bit wide memory interfaces. The card draws power from two 8-pin PCIe power connectors, outputs include four mini-DisplayPort and a dual-link DVI. On par with every other card, GIGABYTE's HD 7990 will cost $999.

Market launch of AMD's Radeon HD 7990 "Malta" dual-GPU graphics card is less than a week away, according to an OCaholic report. Sources told the publication that AMD plans to launch its flagship graphics card on the 24th of April, 2013. According to it, reviews of the card should already be underway. AMD Radeon HD 7990 is the company's flagship graphics card, featuring a pair of 28 nm "Tahiti" GPUs. According to specifications derived from older reports, it packs a total of 4096 stream processors, and 6 GB of GDDR5 memory across two 384-bit wide memory interfaces. What sets this card apart from the HD 7990 "New Zealand" launched last year by AMD's partners is the power-optimizations AMD put into it, leaving the card to draw power from "just" two 8-pin PCIe power connectors, and make do with a dual-slot cooling solution.

ASUS is ready with its third "Dragon Edition" graphics card, after launching ones based on GeForce GTX 660 Ti and Radeon HD 7850. The GTX 660 Dragon Edition (model: GTX660Ti-DP-2GD5) from ASUS is a premium custom-design implementation that's a couple of notches above its DirectCU II TOP (DCU2T). The card features a cooling solution largely identical to DirectCU II, with the exception of those blue stripes, and an aluminum back-plate to cool memory chips on the reverse side of the PCB. It also features ASUS' Direct Power vGPU passive signal-noise dampener that's found on the company's GTX 670 DirectCU Mini.

The GTX 660 Dragon Edition features GPU clock speeds above those of the DirectCU II TOP, with GPU Boost speed of 1150 MHz (compared to the DCU2T's 1135 MHz). Strangely, despite better memory cooling, it features NVIDIA-reference memory clock speeds of 6.00 GHz, even as the DCU2T offers 6.10 GHz. Based on the 28 nm GK106 silicon, the GeForce GTX 660 feature 960 CUDA cores, and a 192-bit wide GDDR5 memory interface, holding 2 GB of memory. Based on what we learned about availability of the other Dragon Edition cards, it would be safe to conclude that this card will be sold only in the Greater China region (PRC, ROC, HK, MO).

PNY launched two GeForce GTX 650 Ti Boost graphics cards under its XLR8 (accelerate) brand. The base model (VCGGTX650TBQXPB) sticks to NVIDIA reference clock speeds of 980 MHz core, 1033 MHz GPU Boost, and 6.00 GHz memory; while an OC variant (VCGGTX650TBQXPB-OC) features factory-overclocked speeds of 1006 MHz core, 1072 MHz GPU Boost, and 6.00 GHz memory.

Both cards appear to be based on designs originally made by Palit. Based on the 28 nm GK106 silicon, the GeForce GTX 650 Ti Boost packs 768 CUDA cores, 56 TMUs, 24 ROPs, and a 192-bit wide GDDR5 memory interface, holding 2 GB of memory. The base model PNY XLR8 GTX 650 Ti Boost is priced at US $169.99, while the OC variant goes for $179.99.

GIGABYTE announced a pair of custom-design graphics cards based on NVIDIA GeForce GTX 650 Ti Boost, the N65TBWF2-2GD, which sticks to NVIDIA-reference clock speeds of 980 MHz core, 1033 MHz GPU Boost, and 6008 MHz memory; and the factory-overclocked N65TBOC-2GD, which ships with 1033 MHz core, 1098 MHz GPU Boost, and 6008 MHz memory.

Both cards are based on a blue GIGABYTE custom-design PCB that uses an UltraDurable VGA construction; and a WindForce 2X parallel-inclined cooling solution, which uses a pair of 90 mm fans to ventilate a heatpipe-fed aluminum fin array. Based on the 28 nm GK106 silicon, the GeForce GTX 650 Ti from NVIDIA features 768 CUDA cores, and a 192-bit wide GDDR5 memory interface, holding 2 GB of memory. The N65TBWF2-2GD is expected to be priced around US $170, while the N65TBOC-2GD could scrape the $190 price point.

MSI kicked off its GeForce GTX 650 Ti Boost lineup with two no less than four models, two of which are based on its 100 mm Propeller Blade cooling solution; and two on its Twin Frozr III cooler, which are branded under its Gaming Series. The series begins with the N650Ti-2GD5 BE, which features NVIDIA-reference clock speeds of 980/1033/6008 MHz (core/GPU Boost/memory), and the N650Ti-2GD5/OC BE, which ups clock speeds to 1006/1072/6008 MHz, while retaining the Propeller Blade cooling solution. The Gaming Series variants consist of the N650Ti TF 2GD5 BE, which sticks to NVIDIA-reference clock speeds; and the N650Ti TF 2GD5/OC BE, with a significant factory-overclock of 1033/1098/6008 MHz.

Based on the 28 nm GK106 silicon, the GeForce GTX 650 Ti Boost features 768 CUDA cores, 64 TMUs, 24 ROPs, and a 192-bit wide GDDR5 memory interface, holding 2 GB of memory. The company did not release pricing.

Galaxy announced its sole GeForce GTX 650 Ti Boost graphics card model, which makes use of custom-design cooler and PCB. The cooler uses an 80 mm fan to ventilate an aluminum fin heatsink. Galaxy's card sticks to NVIDIA-reference clock speeds of 980 MHz core, 1033 MHz GPU Boost, and 6.00 GHz memory. Based on the 28 nm GK106 silicon, the GeForce GTX 650 Ti Boost features 768 CUDA cores, 64 TMUs, 24 ROPs, and a 192-bit wide GDDR5 memory interface, holding 2 GB of memory. The card is expected to be priced at an aggressive US $169.99.

ASUS today announced the GeForce GTX 650 Ti BOOST DirectCU II, which features an overclocked 1085MHz NVIDIA GTX 650 Ti GPU paired with 2GB GDDR5 on a 192-bit interface. The card offers a combination of DirectX 11.1-compatible power and value, expanding the range of ASUS graphics cards that cater to gamers and DIY enthusiasts.

ASUS-exclusive features improve GeForce GTX 650 Ti BOOST DirectCU II performance. They include the DirectCU II cooler, which maintains 20% lower temperatures than a reference GTX 650 Ti BOOST, long-lasting Super Alloy Power components, and user-friendly GPU Tweak graphics card tuning.

Here are the first pictures of an MSI-branded GeForce GTX 650 Ti Boost graphics card. The card features MSI's Gaming Series branding, a custom board design with Twin Frozr III cooling solution, and what could be a non-reference design PCB. As details emerge, the GTX 650 Ti Boost is turning out to be more of a competitor for AMD's Radeon HD 7850 than its recently launched HD 7790. Based on the 28 nm GK106 silicon, it reportedly features 768 CUDA cores, a 192-bit wide GDDR5 memory interface holding 2 GB of memory (memory size printed on MSI's box), GPU Boost, core clock speeds in the neighborhood of 1030 MHz; and 6.00 GHz memory (144 GB/s). It is expected to come out a little later this month.

GIGABYTE rolled out a pair of Radeon HD 7790 graphics cards, the GV-R779-1GI, which sticks to AMD reference clock speeds of 1000 MHz core and 6000 MHz memory, and the factory-overclocked GV-R779OC-1GI, featuring 1075 MHz core, and 6400 MHz memory. The two offer GIGABYTE's UltraDurable VGA PCB, and its Triangle Cool fan-heatsink that pairs a large 100 mm fan to a copper-embedded aluminum heatsink. Based on the 28 nm "Bonaire" silicon, the Radeon HD 7790 packs 896 stream processors, dual tessellation units, 56 TMUs, 16 ROPs, and a 128-bit GDDR5 memory interface holding 1 GB of memory; and a brand new dynamic-clock technology. The base model is priced at US $149.99, and the OC model at $159.99.

AMD announced its Radeon HD 7790 mid-range graphics card, with which the company plans to fill a gap in its product-stack, between the Radeon HD 7770 GHz Edition, and the Radeon HD 7850. Based on the brand new 28 nm "Bonaire" silicon, the HD 7790 features 896 stream processors based on the Graphics CoreNext architecture, dual-independent tessellation units, 56 TMUs, 16 ROPs, and a 128-bit wide GDDR5 memory interface, holding 1 GB of memory. The core is clocked at 1.00 GHz, and memory at 6.00 GHz, churning out a memory bandwidth of 96 GB/s.

With the HD 7790, AMD is introducing an updated dynamic clock adjustment technology, which works to give games more access to the set 1.00 GHz core clock speed, which working to reduce power draw further. The technology should make the current and future AMD Radeon chips as energy-efficient as NVIDIA's. The card draws power from a single 6-pin power connector, its TDP is rated at 85W. Display outputs should typically include one or two DVI connectors, and one each of HDMI and DisplayPort. AMD is targeting a price-point of $149.99, its add-in board partners are free to launch custom-design products from day one.

It looks like AMD isn't waiting till the end of March or early April to launch its Radeon HD 7790 performance-segment graphics card. According to a 3DCenter.org report, the new graphics card will launch this week, either on Thursday or Friday, and that press-samples of the card have already shipped out. Based on the brand new 28 nm "Bonaire" silicon, the HD 7790 is expected to capture a price-point competitive to NVIDIA's GeForce GTX 650 Ti, around 135€. NVIDIA isn't sitting idle, and is planning a GTX 650 Ti refresh of its own.

Inno3D rolled out its newest flagship graphics card, the GeForce GTX Titan iChill Black Series. The card ships with Arctic's Accelero Hybrid cooling solution pre-fitted to an NVIDIA reference design GTX Titan PCB. The cooler uses a combination of a closed-loop liquid block to cool the GPU, and fan-heatsink to cool other hot components on the card, such as memory chips and VRM.

The GTX Titan iChill Black series ships with factory-overclocked speeds of 937 MHz core, and 980 MHz GPU Boost, against NVIDIA reference speeds of 837 MHz core and 876 MHz GPU Boost. Memory clock speed stays at 6.00 GHz. Based on the 28 nm GK110 silicon, NVIDIA's GeForce GTX Titan features 2,688 CUDA cores, 224 TMUs, 48 ROPs, and a 384-bit wide GDDR5 memory interface, holding 6 GB of memory. The card draws power from a combination of 6-pin and 8-pin PCIe power connectors, display outputs include a pair of dual-link DVI, HDMI, and DisplayPort. The company did not release pricing or availability information.

Following the launch of its consumer-oriented GeForce GTX Titan, NVIDIA is planning its second graphics card based on the 28 nm GK110 silicon, this one for professionals, and featuring in the Quadro family. Likely bearing the model name Quadro K6000, the card is expected to feature 13 of the GK110's 15 streaming multiprocessors (SMXs), which work out to 2,496 CUDA cores, 208 TMUs, 40 ROPs, and a 320-bit wide GDDR5 memory interface, likely holding 5 GB of memory. The configuration could be just about enough for 1 TFLOP/s double-precision floating-point performance, and could hence offer an upgrade over Fermi-based Quadro 6000.

MSI announced its GeForce GTX Titan graphics card, adding to the list of partners selling the same exact wine in a different bottle. MSI's package includes Live Update and Afterburner overclocking software. The GTX Titan is based on NVIDIA's 28 nm GK110 silicon, featuring 2,688 CUDA cores, 224 TMUs, 48 ROPs, and 6 GB of GDDR5 memory across a 384-bit wide interface. It features NVIDIA-reference clock speeds of 837/876/6008 MHz (core/GPU Boost/memory), draws power from a combination of 6-pin and 8-pin PCIe power connectors, and its display outputs include two dual-link DVI, HDMI, and DisplayPort. MSI's GTX Titan is priced at $1000 before taxes.

One of NVIDIA's highest volume AIC partners, Galaxy, dropped in its GeForce GTX Titan offering, joining other partners in their late-evening launch, even as partners struggle to scrape up inventories. Galaxy's offering is no different from absolutely any other among NVIDIA's partners, who are restricted from modifying the board design, or playing with the reference clock speeds. Partners are allowed to drop in additional items in their packages, and of course their own overclocking software that can take advantage of the card's enthusiast features. Based on the 28 nm GK110 silicon, the GeForce GTX Titan features 2,688 CUDA cores, 224 TMUs, 48 ROPs, and a 384-bit wide GDDR5 memory interface, holding 6 GB of memory. The card features NVIDIA reference clock speeds of 837/876/6008 MHz (core/GPU Boost/memory). It should be priced around $1000 before taxes.

Palit's twin brand Gainward announced its GeForce GTX Titan, too. The card, like every other GTX Titan launched today (and will be), sticks to NVIDIA's reference board design, and reference clock speeds of 837/876/6008 MHz (core/GPU Boost/memory). Based on the 28 nm GK110 silicon, the GeForce GTX Titan features 2,688 CUDA cores, 224 TMUs, 48 ROPs, and a 384-bit wide GDDR5 memory interface, holding 6 GB of memory; and like every other GTX Titan, it is priced at $1000 before taxes.