News Posts matching "AMD"

Return to Keyword Browsing

AMD to Skip 20 nm, Jump Straight to 14 nm with "Arctic Islands" GPU Family

AMD's next-generation GPU family, which it plans to launch some time in 2016, codenamed "Arctic Islands," will see the company skip the 20 nanometer silicon fab process from 28 nm, and jump straight to 14 nm FinFET. Whether the company will stick with TSMC, which is seeing crippling hurdles to implement its 20 nm node for GPU vendors; or hire a new fab, remains to be seen. Intel and Samsung are currently the only fabs with 14 nm nodes that have attained production capacity. Intel is manufacturing its Core "Broadwell" CPUs, while Samsung is manufacturing its Exynos 7 (refresh) SoCs. Intel's joint-venture with Micron Technology, IMFlash, is manufacturing NAND flash chips on 14 nm.

Named after islands in the Arctic circle, and a possible hint at the low TDP of the chips, benefiting from 14 nm, "Arctic Islands" will be led by "Greenland," a large GPU that will implement the company's most advanced stream processor design, and implement HBM2 memory, which offers 57% higher memory bandwidth at just 48% the power consumption of GDDR5. Korean memory manufacturer SK Hynix is ready with its HBM2 chip designs.Source: Expreview

CyberPowerPC Announces Trinity Gaming Desktop

CyberPower Inc., a global manufacturer of custom gaming PCs, gaming laptops, and performance workstations, today announced it is taking orders for its Trinity gaming PC, a striking new concept in gaming PC design that splits the common hulking tower enclosure into three distinct "blades."

The CYPOWERPC Trinity is both an exercise in radical case design and a case study on the benefits of component compartmentalization. While the case defies imagination, there is a method to the madness of segregating certain components from others in order to dissipate heat while not sacrificing performance.

AMD Reports 2015 First Quarter Results

AMD today announced revenue for the first quarter of 2015 of $1.03 billion, operating loss of $137 million and net loss of $180 million, or $0.23 per share. Non-GAAP operating loss was $30 million and non-GAAP net loss was $73 million, or $0.09 per share.

"Building great products, driving deeper customer relationships and simplifying our business remain the right long-term steps to strengthen AMD and improve our financial performance," said Dr. Lisa Su, AMD president and CEO. "Under the backdrop of a challenging PC environment, we are focused on improving our near-term financial results and delivering a stronger second half of the year based on completing our work to rebalance channel inventories and shipping strong new products."

Arctic Announces M1 Series CPU Coolers for AMD Socket AM1

Arctic announces the M1 and M1-Passive CPU coolers for AMD socket AM1. The Alpine M1 & Alpine M1-Passive replace the noisy stock cooler. Building a quiet PC system with a low budget? Yes it is possible! The Alpine M1 & Alpine M1-Passive were specifically designed for the AMD AM1 platform and are the ideal alternative to the noisy stock cooler.

The cooling performance of the whisper quiet Alpine M1 is more than sufficient to keep every AM1 CPU at bay by margin. An 80 mm low speed fan delivers the desired airflow and pressure without producing any audible noise. Even under full load it generates only 0.1 Sone which makes it twice as quiet as the stock cooler.

AMD Releases Catalyst 15.4 Beta for Grand Theft Auto V

AMD released its latest driver with optimizations for the season't hottest game Grand Theft Auto V. Catalyst 15.4 is released as a Beta. The company is yet to launch a WHQL-signed driver this year. Catalyst 15.4 Beta adds game-specific optimizations for GTA V, and CrossFire profiles. It also adds CrossFire profiles for Dying Light, MGS V: Ground Zeroes, Sleeping Dogs: Definitive Edition, and Mortal Combat X. CrossFire profiles are improved for Battlefield Hardline, Far Cry 4, and Middle Earth: Shadow of Mordor. Grab the driver from the links below.
DOWNLOAD: AMD Catalyst 15.4 Beta for Grand Theft Auto V, for Windows 8.1/7 64-bit | Windows 8.1/7 32-bit

AMD "Zen" A Monolithic Core Design

AMD's upcoming "Zen" architecture will see a major change in the way the company designs its CPU cores. It will be a departure from the "module" core design introduced with "Bulldozer," in which two cores with shared resources constitute the indivisible unit of a multi-core processor. A "Zen" core will have dedicated resources in a way things used to be before "Bulldozer," and only the last-level cache (L3 cache), will be shared between cores. "Zen" will also implement SMT, much in the same way as Intel processors do, with HyperThreading Technology.

The first implementation of "Zen" will be an insanely powerful APU (on paper anyway), featuring 16 physical "Zen" CPU cores, 32 logical CPUs enabled with SMT, 512 KB dedicated L2 cache per core, and 32 MB of shared L3 cache. The CPU's ISA instruction set will see a spring-cleaning, with the removal of underused instruction-sets, and the introduction of new ones. Other features on this APU are equally surprising - a quad-channel DDR4 integrated memory controller, a separate HBM (high-bandwidth memory) controller dedicated to the integrated graphics, with up to 512 GB/s bandwidth, and an integrated graphics core featuring "Greenland-class" stream processors. Given that AMD is able to build 7-billion transistor GPUs on existing 28 nm processes, building an APU with these chops doesn't sound far-fetched. The company could still have to rely on a newer fab.

Source: FudZilla

AMD Embedded R-Series APU Powers Samsung Electronics Digital Signage Systems

AMD today announced that the AMD Embedded R-Series accelerated processing unit (APU), previously codenamed "Bald Eagle," is powering the latest set-back-box (SBB) digital media players from Samsung Electronics, Co., Ltd. With high performance, low power, and broad connectivity, the new Samsung SBB-B64DV4 is an ideal fit for demanding signage applications that transform Samsung SMART Signage Displays into inclusive digital tools for a wide range of business needs.

Using AMD's Embedded R-Series APUs, Samsung SBB media players for digital signage deliver breakthrough HD graphics performance and support multi-video stream capabilities up to two displays, all in a power efficient and ultra-compact form factor.

"Digital signage is a key vertical for the AMD Embedded business," said Scott Aylor, corporate vice president and general manager, AMD Embedded Solutions. "The AMD Embedded R-Series APU enables leading digital signage providers to harness high levels of compute and graphics performance within a low-power design envelope. AMD Embedded Solutions help designers at Samsung achieve aggressive form factor goals and drive down system costs while providing the rich multimedia their digital signage customers' demand."

AMD Faces Securities Fraud Lawsuit

Over-promising and under-delivering with its very first accelerated processing units (APU), codenamed "Llano," is coming back to haunt AMD, with a US District Court ruling that the company must face claims from investors over potential securities fraud. Launched in Q3-2012, AMD's A-series "Llano" APUs went largely unsold due to various factors including lack of product appeal, competition from Intel, forcing AMD to pull in its second-generation "Trinity" APU too soon. The related development first took shape in January 2014.

The swelling unsold "Llano" inventory forced an inventory writedown of $100 million, reducing the company's worth by nearly that much overnight, and tanking the value of the AMD stock. While AMD talked about the concept of an APU for years, Intel was the first to come out with a processor that integrates a graphics processor, with its Core i3 and Core i5 "Clarkdale" processors. The suit claims that AMD misrepresented production of "Llano" chips to its investors despite supply issues from its foundry partner GlobalFoundries, artificially inflating the value of the company in 2011-12. By the time production finally caught up, it ended up overproducing resulting in unsold inventory, and in consequence, the $100 million writeoff.


Source: Reuters

NVIDIA to Launch GeForce GTX 980 Ti After Summer

NVIDIA reportedly adjusted launch of the GeForce GTX 980 Ti, to after Summer, 2015. The company could be using the time to let the market digest existing inventories of the GTX 980 (and avoid the repeat of slow sales on its GTX 770), particularly in the early-Summer season, when PC enthusiasts and gamers tend to upgrade or build afresh. The time could also be spent to watch what AMD comes up with, for its Radeon R9 390X.

The R9 390X, scheduled for a June-July launch, is based on a silicon that looks competitive with the GM200 on paper, and introduces a few new features, such as high-bandwidth memory (HBM). The GTX 980 Ti could feature an identical core-configuration to the GTX TITAN X, but feature half the memory amount at 6 GB, different clock speeds, and freedom for add-in card (AIC) partners to innovate custom-design cards.

Source: SweClockers

Futuremark Releases 3DMark Update with API Overhead Feature-set

Futuremark is excited to introduce our new 3DMark API Overhead feature test - the world's first independent test for measuring differences in DirectX 12, DirectX 11 and Mantle API performance. It's also the very first public application to use DirectX 12 full stop. This is cutting edge stuff! Developed with input from AMD, Intel, Microsoft, NVIDIA, and the other members of our Benchmark Development Program, the 3DMark API Overhead feature test lets you compare the performance of DirectX 12, DirectX 11, and Mantle.

The purpose of the test is to compare the relative performance of different APIs on a single system, rather than the absolute performance of different systems. The API Overhead feature test is not a general-purpose GPU benchmark, and it should not be used to compare graphics cards from different vendors. (We are working on a DirectX 12 benchmark with game-like workloads, which we expect to release soon after the public launch of Windows 10.)

DOWNLOAD: Futuremark 3DMark v1.5.884

ASRock Also Announces 970M Pro3 Micro-ATX Socket AM3+ Motherboard

In addition to the high bang-for-buck Fatal1ty 970 Performance, ASRock announced one of the very few AMD 9-series chipset based socket AM3+ motherboards in the micro-ATX form-factor, the 970M Pro3. Based on the AMD 970 chipset, and built to be priced well under $99, the 970M Pro3 supports AMD FX processors with TDP of up to 125W (that excludes FX-9000 series). Drawing power from a 24-pin ATX and 8-pin EPS, the board offers a 5-phase CPU VRM. Expansion slots include one PCI-Express 2.0 x16, one PCIe 2.0 x16 (electrical x4, wired to the southbridge), and one each of PCIe 2.0 x1 and legacy PCI. Storage connectivity on the 970M Pro3 includes six SATA 6 Gb/s ports. 6-channel HD audio with ELNA capacitors, gigabit Ethernet, and four USB 3.0 ports (two on the rear panel, two by header), make for the rest of its modern connectivity. The board is driven by UEFI BIOS.

ASRock Unveils Fatal1ty 970 Performance Socket AM3+ Motherboard

ASRock unveiled its newest socket AM3+ motherboard for gamers with on a budget, the Fatal1ty 970 Performance. Based on the AMD 970 chipset with SB950 southbridge, this board offers a slick feature-set for its potentially two-figure price. Built in the ATX form-factor, the board draws power from a combination of 24-pin ATX and 8-pin EPS power connectors. An optional 4-pin Molex power connector is required, if you have two cards that rely solely on the expansion slot power. The board features a 10-phase CPU VRM, and supports 220W TDP chips such as the FX-9370 and FX-9590.

Expansion slots include two PCI-Express 2.0 x16 (x8/x8 when both are populated), a third PCI-Express 2.0 x16, which is electrical x4 and wired to the southbridge, a legacy PCI, and two PCI-Express 2.0 x1 slots. Storage connectivity includes six SATA 6 Gb/s ports, and an M.2 slot (electrical PCIe 2.0 x4). Other modern connectivity includes six USB 3.0 ports (four on the rear panel, two by headers), an electrically-reinforced Fatal1ty Mouse port, ASRock Purity Sound 2 on-board audio with a 115 dBA SNR CODEC, audio-grade electrolytic capacitors, headphones amp, and ground-layer isolation, and gigabit Ethernet (Realtek-made controller). The board is driven by UEFI BIOS, and supports Windows 8.1 features such as Secure Boot and Fast Boot. Expect this board to be priced at $99.

MSI Announces First AMD Motherboard with USB 3.1, the 970A SLI Krait Edition

MSI, world leading in motherboard technology, is proud to announce world's first USB 3.1 featured AMD motherboard, the classy black & white 970A SLI Krait Edition. Delivering blazing fast USB performance, up to 2 times faster than USB 3.0, the new 970A SLI Krait Edition motherboard offers two USB 3.1 ports, which are fully backwards compatible with USB 3.0 and USB 2.0 devices. Copying files from your external hard disk or USB pen drive will be faster than ever. Offering reliable and fast Gigabit LAN together with Nvidia SLI and AMD CrossFire support for enthusiasts looking to pair up multiple graphics cards, the new classy black & white 970A SLI Krait Edition motherboard is a testament of quality. Military Class 4 provides all the stability you need through carefully selected and thoroughly tested components and materials.

"AMD and MSI strive to deliver innovation and great products that provide cutting edge features and capabilities for all users," said Darren Grasby, AMD Corporate VP, Global Channel Sales. "We are very excited to partner with MSI on the launch of the new USB 3.1 powered 970A SLI Krait Edition Motherboard - a highly optimized, feature-rich platform that unleashes the full potential of AMD processors in a powerful solution that also delivers great value and customer experience." The 970A SLI Krait Edition motherboard perfectly caters to those AMD fans who are looking for something different in terms of design and latest specification, but desire nothing but the best in terms of features and power.

AMD Bets on DirectX 12 for Not Just GPUs, but Also its CPUs

In an industry presentation on why the company is excited about Microsoft's upcoming DirectX 12 API, AMD revealed its most important feature that could impact on not only its graphics business, but also potentially revive its CPU business among gamers. DirectX 12 will make its debut with Windows 10, Microsoft's next big operating system, which will be given away as a free upgrade for _all_ current Windows 8 and Windows 7 users. The OS will come with a usable Start menu, and could lure gamers who stood their ground on Windows 7.

In its presentation, AMD touched upon two key features of the DirectX 12, starting with its most important, Multi-threaded command buffer recording; and Asynchronous compute scheduling/execution. A command buffer is a list of tasks for the CPU to execute, when drawing a 3D scene. There are some elements of 3D graphics that are still better suited for serial processing, and no single SIMD unit from any GPU architecture has managed to gain performance throughput parity with a modern CPU core. DirectX 11 and its predecessors are still largely single-threaded on the CPU, in the way it schedules command buffer.

GIGABYTE Intros 990XA-UD3 R5 Socket AM3+ Motherboard

GIGABYTE introduced its latest socket AM3+ motherboard, and its first in a long while, the 990XA-UD3 R5. Built in the standard ATX form-factor, the board draws power from a combination of 24-pin ATX and 8-pin EPS connectors, and conditions it using a 10-phase CPU VRM. The board, however, does not support FX-9000 series chips. Based on AMD 990X chipset, featuring AMD SB950 southbridge, expansion slots of the board include two PCI-Express 2.0 x16 (x8/x8 when both are populated), supporting NVIDIA SLI and AMD CrossFireX, a third PCIe 2.0 x16 slot (electrical x4, wired to the southbridge), and two each of PCIe 2.0 x1 and legacy PCI slots.

Storage connectivity on the 990XA-UD3 R5 include six SATA 6 Gb/s ports. The board's onboard audio solution features a Realtek ALC1150 CODEC, offering 115 dBA SNR, audio-grade electrolytic capacitors on the audio circuit, a TI-made headphones amplifier with support for headphones impedance as high as 600Ω, and PCB ground-layer isolation. Also on offer are a gigabit Ethernet connection, driven by a Realtek-made controller, four USB 3.0 ports (two on the rear panel, two by headers), and PS/2 mouse/keyboard combo port. The board is driven by AMI UEFI BIOS, and supports Windows 8 SecureBoot and FastBoot. Expect this board to be priced around US $130.

AMD Announces FreeSync, Promises Fluid Displays More Affordable than G-SYNC

AMD today officially announced FreeSync, an open-standard technology that makes video and games look more fluid on PC monitors, with fluctuating frame-rates. A logical next-step to V-Sync, and analogous in function to NVIDIA's proprietary G-SYNC technology, FreeSync is a dynamic display refresh-rate technology that lets monitors sync their refresh-rate to the frame-rate the GPU is able to put out, resulting in a fluid display output.

FreeSync is an evolution of V-Sync, a feature that syncs the frame-rate of the GPU to the display's refresh-rate, to prevent "frame tearing," when the frame-rate is higher than refresh-rate; but it is known to cause input-lag and stutter when the GPU is not able to keep up with refresh-rate. FreeSync works on both ends of the cable, keeping refresh-rate and frame-rates in sync, to fight both page-tearing and input-lag.

More Radeon R9 390X Specs Leak: Close to 70% Faster than R9 290X

Earlier today, AMD reportedly showed its industry partners (likely add-in board partners) a presentation, which was leaked to the web as photographs, and look reasonably legitimate, at first glance. If these numbers of AMD's upcoming flagship product, the Radeon R9 390X WCE (water-cooled edition) hold up, then it could spell trouble for NVIDIA and its GeForce GTX TITAN X. To begin with, the slides confirm that the R9 390X will feature 4,096 stream processors, based on a more refined version of Graphics CoreNext architecture. The core ticks at speeds of up to 1050 MHz. The R9 390X could sell in two variants, an air-cooled one with tamed speeds, and a WCE (water-cooled edition) variant, which comes with an AIO liquid-cooling solution, which lets it throw everything else out of the window in psychotic and murderous pursuit of performance.

It's the memory, where AMD appears to be an early adopter (as its HD 4870 was the first to run the faster GDDR5). The R9 390X features a 4096-bit wide HBM memory bus, holding up to 8 GB of memory. The memory is clocked at 1.25 GHz. The actual memory bandwidth will yet end up much higher than the 5.00 GHz 512-bit GDDR5 on the R9 290X. Power connectors will be the same combination as the previous generation (6-pin + 8-pin). What does this all boil down to? A claimed single-precision floating point performance figure of 8.6 TFLOP/s. Wonder how NVIDIA's GM200 compares to that. AMD claims that the R9 390X will be 50-60% faster than the R9 290X, and we're talking about benchmarks such as Battlefield 4 and FarCry 4. The expectations on NVIDIA's upcoming product are only bound to get higher.


Source: VideoCardz

Scythe Announces the Kodati Rev. B CPU Cooler with AM1 Support

Japanese cooling expert Scythe announces a new revision of its Kodati CPU Cooler. Scythe is one of the first manufacturers to announce a special solution to the market for the socket AM1 (FS1b). Users have finally the chance to exchange the stock AM1 CPU cooler against the much more powerful Kodati Rev. B. The new revision furthermore inherits the socket support to the common sockets from AMD and Intel, which is very typical for Scythe products.

Scythe Kodati CPU Cooler aims specifically at the HTPC and Mini-ITX market, where size and weight is crucial. Thanks to its total heights of mere 34 millimeters and weight of 180 grams, Kodati Rev. B CPU cooler is able to fit to basically every compact system. This has been achieved by implementing the Stealth Fan Mounting Structure (S.F.M.S), where the pre-installed fan is located between the aluminum fin-structure and copper-baseplate. Fast heat dissipation is assured thanks to the two copper-heatpipes with 6 mm thickness. Users are able to control the supplied 80 mm fan in the range between 800 and 3.300 RPM thanks to the PWM support. The airflow varies between 10,2 and 42,2 m3/h (6,0~24,82 CFM), depending on the fan speed. The specified noise level during operation starts at inaudible 8,2 dBA and goes up to merely audible 32.5 dBA.

TechPowerUp GPU-Z 0.8.2 Released

TechPowerUp released the latest version of GPU-Z, the popular video hardware information and diagnostic utility. Version 0.8.2 brings with it a vast number of changes, support for new hardware, and bug-fixes. To begin with, the user-interface of GPU-Z received a major update, with the addition of a "Lookup" button that takes you to our GPU Database page corresponding to your GPU. The app can now tell you if your drivers are WHQL-signed. GPU manufacturer logos are updated.

Among the new hardware supported includes NVIDIA GeForce TITAN-X, GTX 980M, GTX 970M, GGTX 965M, GTX 845M, GTX 760 Ti OEM, GTX 660 (960 shaders), GT 705, GT 720, GT 745M, NVS 310, and Grid; AMD Radeon R9 255, FirePro W7100, HD 8370D, AMD R9 M280X, and R9 M295X; and Intel "Broadwell" integrated graphics. Specifications are revised for GeForce GTX 970.

A large number of bugs were fixed, and overall usability improved, including notably GPU-Z now supports Windows 10. We implemented a new working way of extracting BIOS from NVIDIA GPUs on systems with WIndows 8 and higher, to avoid a system hang. A large number of bugs were fixed, and overall usability of the app improved, as detailed in the change-log.
DOWNLOAD: TechPowerUp GPU-Z 0.8.2 | GPU-Z 0.8.2 ASUS ROG-themed

The Change-log follows.

BIOSTAR Reveals the TA970 Plus AMD Mainboard with ACC

BIOSTAR has released an AMD socket AM3+ motherboard, the TA970 Plus with AMD OverDrive and the ACC (Advanced Clock Calibration) feature. This AMD 970 chipset board supports AMD multi-Core (x8, x6) and Socket AM3 processors including the AMD FX/ Phenom II and Athlon II versions. This is a powerful platform for gamers and enthusiasts.

The TA970 Plus is a full sized ATX board with 4 DDR3 DIMM slots and mSATA/Mini PCI-E combo connector. It supports SATA 6Gb/s speeds, which are two times the speed of current SATA 3G. Of course there is USB 3.0 support as well. Powerful graphics are supported with AMD's CrossfireX capability. To get every power advantage the TA970 Plus features the AMD OverDrive and the ACC (Advanced Clock Calibration) function. This allows power users to overclock their system by precisely calibrating the clock timings between the processor and RAM chips. These timings are critical in maintaining system stability when overclocking, otherwise you will end up with a system that crashes often. As they say, "Timing is Everything" and the TA970 Plus allows you to get it right.

AMD R9 390 Series To Launch Alongside Computex 2015

AMD is preparing to time the launch of its next-generation Radeon R9 300 series with that of Computex 2015, in early June. The company had earlier planned to launch some products that are essentially price-adjusted rebrands of existing ones, such as the R9 380 series (being rebrands of R9 290 series on a slightly improved silicon), and the R9 370 series (being based on the "Tonga" silicon); but has decided to launch the two along with its flagship R9 390 series, based on a brand new silicon, around the same time. AMD's answer to the GTX TITAN-X from NVIDIA, the R9 390X will feature around 4,096 stream processors based on the Graphics CoreNext 1.3 architecture, and will implement an HBM (high-bandwidth memory) interface, with bandwidths in excess of 600 GB/s.

Source: Kitguru

AMD Announces New LiquidVR Technology

AMD announced an initiative to deliver the best possible VR experience for developers and users through new AMD technologies and partnerships. The first output of AMD's initiative is LiquidVR, a set of innovative technologies focused on enabling exceptional VR content development for AMD hardware, improved comfort in VR applications by facilitating performance, and plug-and-play compatibility with VR headsets. The upcoming LiquidVR SDK makes a number of technologies available which help address obstacles in content, comfort and compatibility that together take the industry a major step closer to true, life-like presence across all VR games, applications, and experiences.

In virtual reality, the concept of 'presence' is described as the perception of being physically present in a simulated, nonphysical world in a way that fully immerses the user. A key obstacle to achieving presence is addressing motion-to-photon latency, the time between when a user moves their head and when his or her eye sees an updated image reflecting that new position. Minimizing motion-to-photon latency is critical to achieving both presence and comfort, two key elements of great VR.

AMD Releases Mantle Programming Guide and Reference API

AMD announced that it published the complete 450-page programming guide for its Mantle 3D graphics API, and the reference API itself. The two can be accessed from here. In the run up to its GDC 2015 presentation, in a blog post written by the company's top technology exec Raja Koduri, the company said it will talk about the future of Mantle in its GDC presentation. The company intends to develop, maintain and support Mantle and its eco-system, while maintaining that it will participate in the development and support of industry-standard APIs such as DirectX 12 and GLnext (the next major version of OpenGL).

Source: AMD Gaming (blog)

Announcing the TechPowerUp Winter's End WCG Challenge

With spring nearly upon us, it's time to give the old horses crunching overclocked through the winter one grand, last run. TechPowerUp World Community Grid (WCG) team, one of the world's top-10 teams, with over 4,000 years of aggregate CPU time, and over 20 million results submitted; brings to you the Winter's End WCG Challenge.

Simply crunch for the TechPowerUp WCG Team between 26th Feb (00:00 UTC) and 6th Mar (00:00 UTC), and multiple winners along the leaderboard stand to win some sick community-sponsored prizes, including an AMD FX-8350 CPU + ASUS Crosshair V Formula motherboard combo, a fully-built crunching rig, numerous SSDs, CPU coolers, and more. So what are you waiting for?! For more information, and to participate, visit this page.

AMD's Excavator Core is Leaner, Faster, Greener

AMD gave us a technical preview of its next-generation "Carrizo" APU, which is perhaps the company's biggest design leap since "Trinity." Built on the 28 nm silicon fab process, this chip offers big energy-efficiency gains over the current-generation "Kaveri" silicon, thanks to some major under-the-hood changes.

The biggest of these is the "Excavator" CPU module. 23 percent smaller in area than "Steamroller," (same 28 nm process), Excavator features a new high-density library design, which reduces die-area of the module. Most components are compacted. The floating-point scheduler is 38% smaller, fused multiply-accumulate (FMAC) units compacted by 35%, and instruction-cache controller compacted by another 35%. The "Carrizo" silicon itself uses GPU-optimized high-density metal stack, which helps with the compaction. Each "Excavator" module features two x86-64 CPU cores, which are structured much in the same way as AMD's previous three CPU core generations.
Return to Keyword Browsing