Feeds

Articles about Gpu

Meet the 'smallest GPU' for wearable gizmos ... wait, where did it go?

The official launch of Android Wear was less than a month ago, but Imagination Technologies has this week unveiled a tiny graphics processor that it reckons will be just the thing for your snazzy new smartwatch. The single-core PowerVR GX5300 GPU is just 0.55mm2 – apparently the "world's smallest" – and squeezes in full OpenGL …
Iain Thomson, 18 Jul 2014
Thing

Teeny GPU targets wearables, Things

This GPU isn't going to get Bitcoin enthusiasts worked up, but from a “wow that's small” point of view it's interesting: Vivante is shipping a range of GPUs that ranges from 0.3 mm2 up to 1.6 mm2 in size for IoT and wearables applications. The four devices the company's announced include two VGA/WVGA devices (the 100-200 MHz GC …
Block diagram of Imagination Technologies PowerVR GX6650

Imagination details mucho macho PowerVR GX6650 mobile GPU

At last month's Consumer Electronics show, UK chip designer Imagination Technologies unveiled its new PowerVR Series6XT Rogue GPU architecture for SoCs. On Monday at the Mobile World Congress in Barcelona, it released details of what it calls "the shining star of the PowerVR Series6XT," the PowerVR GX6650. Block diagram of …
Rik Myslewski, 25 Feb 2014
AMD FirePro S9150

High five from AMD: New supercomputer GPU maxes out at 5.07 TFLOPS

AMD has upped the ante in its battle with Nvidia for the data center and high-performance computing (HPC) markets, with the launch of two new GPU cards for servers. The company's new big gun is the FirePro S9150 card, which maxes out at a blistering 5.07 TFLOPS peak single-precision floating-point performance and 2.53 TFLOPS …
Neil McAllister, 06 Aug 2014
T Platforms GPU Blade

Sod Bitcoin - solving graph problems is the new GPU-flogger

These GTC conferences, the annual GPU-fest sponsored by NVIDIA, are my favorite events of the year. Why? It’s how the event is organized. At GTC, real-world researchers, analysts, and other customers present the vast majority of sessions, not corporate mouthpieces. They talk about their projects, the challenges they’ve dealt …
Nvidia CEO Jen-Hsun Huang provides details on next-generation GPU architecture, 'Pascal'

Nvidia unveils Pascal, its next-gen GPU with hella-fast interconnects and 3D packaging

Nvidia has announced its next-generation GPU, and with it a new interconnect it dubs NVLink that it says will increase the bandwidth among GPUs – and also CPUs, should a processor designer implement it – over that of PCIe by five to twelve times. Nvidia NVLink block diagram String a bunch of GPUs together with NVLink, and you …
Rik Myslewski, 25 Mar 2014

Microsoft DirectX 12 pushes gaming code closer to GPU bare metal

Microsoft has unveiled DirectX 12, at the heart of which is the Direct3D API, which Redmond promises will enable "richer scenes, more objects, and full utilization of modern GPU hardware" – and which will run on "many" cards that gamers already own. "What makes Direct3D 12 better?" Microsoft's Matt Sandy asked in a blog post. …
Rik Myslewski, 20 Mar 2014

Nvidia reveals CUDA 6, joins CPU-GPU shared memory party

Nvidia has announced the latest version of its GPU programming language, CUDA 6, which adds a "Unified Memory" capability that, as its name implies, relieves programmers from the trials and tribulations of having to manually copy data back and forth between separate CPU and GPU memory spaces. CUDA 6 Unified Memory schematic …
Rik Myslewski, 16 Nov 2013
Die shot of Nvidia's 'Kepler2' GK110 GPU chip

Amazon lashes Nvidia's GRID GPU to its cloud: But can it run Crysis?

Amazon has chugged Nvidia's new virtualized GPU technology to spin-up a new class of rentable instances for 3D visualizations and other graphics-heavy applications. The "G2" instances, announced by Amazon on Tuesday, is another nod by a major provider to the value of Nvidia's GRID GPU adapters, which launched in 2012. These …
Jack Clark, 05 Nov 2013
Broadcom

Get Quake III running on Raspberry Pi using Broadcom's open-source GPU drivers, earn $10K

Broadcom has released open-source drivers and documentation for the graphics processor that's used in the Raspberry Pi microcomputer, among other devices. "To date, there's been a dearth of documentation and vendor-developed open source drivers for the graphics subsystems of mobile systems-on-a-chip (SoC)," Eben Upton, a …
Neil McAllister, 28 Feb 2014

Hey coders – get a sense of hUMA: AMD to free GPU from CPU slavery

AMD is to manufacture microprocessors that connect their on-board CPU and GPU components more intelligently than ever before. The upcoming chips will utilise a technique AMD calls Heterogeneous Queuing (hQ). This new approach puts the GPU on an equal footing with the CPU: no longer will the graphics engine have to wait for the …
Tony Smith, 22 Oct 2013

Nvidia uncloaks GeForce 800M GPU series for gaming notebooks

Nvidia has completely revamped its notebook graphics line with a seven-GPU launch of the new GeForce 800M series, four bearing the GeForce GTX moniker and three sans GTX. Performance-improvement chart comparing Nvidia GeForce GTX 7xx series to GeForce GTX 8xx series The further down the ladder of oomph, the greater the …
Rik Myslewski, 13 Mar 2014
Bird's eye view of the proposed new Nvidia HQ

GPU secrets unveiled for student cluster warriors

We’re less than two weeks away from the start of the SC13 Student Cluster Competition in Denver. Right now, the 12 student teams are turning over every rock they can find in their hardware and software stack in an effort to eke (and geek) out every last bit of performance. Time is short. In a week or less, they’ll be packing up …

Intel: 'Y'know that GPU-accelerated computing craze? Fuggedaboutit'

From Intel's point of view, today's hottest trend in high-performance computing – GPU acceleration – is just a phase, one that will be superseded by the advent of many-core CPUs, beginning with Chipzilla's next-generation Xeon Phi, codenamed "Knights Landing". "Tomorrow looks quite fundamentally different," Rajeeb Hazra, VP of …
Rik Myslewski, 19 Nov 2013
Die shot of AMD's Kabini APU

AMD joins LibreOffice, adds GPU grunt to free software suite

LibreOffice, the open source office suite created by disaffected Oracle developers, has signed up Advanced Micro Devices to the free software cause and plans to add the chip company's GPU acceleration system to the code base. The Document Foundation (TDF), which produces LibreOffice, already has Intel on-side for silicon and …
Iain Thomson, 03 Jul 2013

AMD's 'Revolution' will be televised ... if its CPU-GPU frankenchip Kaveri is a hit

AMD has released its long-awaited Kaveri processor, the first accelerated processing unit (APU) to incorporate both on-die CPU and GPU cores in a heterogeneous system architecture (HSA) with a shared memory architecture. AMD Kaveri - overview Behold Kaveri, in which CPUs and GPUs are equal 'compute unit' partners (click to …
Rik Myslewski, 14 Jan 2014
AMD and Nvidia extreme GPUs

Swinburne flicks switch on $AU3 million GPU

Swinburne University has brought a new 120 teraflop GPU-based supercomputer from SGI to help cope with astronomers' ever-increasing need for lots of computing power. The 636 Intel GPU, 121 NVIDIA GPU, quad-InfiniBand machine, gSTAR, is one of just six similar grunt-boxes in Australia. The power boost over Swinburne’s previous …
The Tesla K20 GPU coprocessor card

Nvidia stretches Tesla GPU coprocessors from HPC to big data

Graphics chip maker Nvidia has barely begun to put a dent in the traditional high performance computing segment with its Tesla GPU coprocessors and it is already gearing up to take on new markets. The next target is big data, and as with parallel supercomputing, Nvidia is hoping to get the jump on rivals Intel and AMD, which …
The Register breaking news

GPU-powered Chrome lets you watch YouTube longer

Google has pushed version 23 of its Chrome web browser to the Stable release channel, bringing GPU-accelerated video playback to the Windows platform and giving users finer control over what data that sites can collect about their browsing habits. Chrome has been able to use the GPU to accelerate web-page rendering for some time …
Neil McAllister, 06 Nov 2012
The Register breaking news

GPU-stuffed monster cracks Windows passwords in minutes

Security researchers have put together a monster number-crunching rig capable of cracking strong passwords by brute force in minutes. Jeremi Gosney (aka epixoip) demonstrated a machine running the HashCat password cracking program across a cluster of five servers equipped with 25 AMD Radeon GPUs at the Passwords^12 conference in …
John Leyden, 07 Dec 2012
The Register breaking news

Scan your branes LIVE IN REAL-TIME, thanks to GPU-surfin' boffins

Let’s say you’re at a gathering – maybe a cocktail party or a crowded club – and some buff athlete shows up on crutches. He immediately becomes the center of attention as he recounts the story of his injury. “Dude, it was gnarly," he bellows so that everyone can hear. "A totally sick shred. Now I’m waitin’ on the MRI results. …
The FirePro S10000 dual-GPU card

AMD fires off crazy-fast FirePro double-whammy GPU card

AMD, a company that knows a thing or two about building powerful graphics processors, has whipped out a card that has more flops than either Nvidia's K20 high-end GPUs or Intel's x86-based Xeon Phi coprocessors. That's one sure way to cut through all the noise that Nvidia and Intel are making about their just-released offerings …
Open-mouthed Burmese python

Nvidia, Continuum team up to sling Python at GPU coprocessors

The Tesla GPU coprocessor and its peers inside your Nvidia graphics cards will soon speak with a forked tongue. Continuum Analytics has been working with the GPU-maker to create the NumbaPro Python-to-GPU compiler. We all call it the LAMP stack, but it should really be called LAMPPP or LAMP3 or some such because it is Linux, …
The Register breaking news

Intel pays Creative $50m for ZiiLabs GPU licence, people

Creative Labs is to all sell parts of its graphics chip wing, ZiiLabs, to Intel for $50 million (£31.4 million). The deal involves a $30 million payment for “certain engineering resources and assets” from ZiiLabs' UK operation and a further $2 million for “the licensing of certain technologies... relating to ZiiLabs' high …
Tony Smith, 21 Nov 2012
Nvidia Tegra 4 mobile chip

Mobes with monster 72-core GPU to debut in China

Nvidia’s supercharged quad-core Tegra 4 SoC, which packs a mighty 72 GPU cores, has finally found a mobile home after handset maker ZTE announced new smartphones featuring the chip will debut in China in the first half of 2013. The Tegra 4 was unveiled last month at CES but has so far been left to stand at the altar by the …
Phil Muncaster, 21 Feb 2013
Nvidia supercomputing pipeline

Nvidia puts Tesla K20 GPU coprocessor through its paces

Back in May, when Nvidia divulged some of the new features of its top-end GK110 graphics chip, the company said that two new features of the GPU, Hyper-Q and Dynamic Parallelism, would help GPUs run more efficiently and without the CPU butting in all the time. Nvidia is now dribbling out some benchmark test results ahead of the …
OpenJDF logo

AMD, Oracle tag-team on GPU acceleration for Java apps

The offloading loading of calculations from CPUs to external accelerators such as GPU coprocessors is not just something that is restricted to supercomputer applications. Anything with lots of calculation that can exploit parallelism is a candidate for acceleration, and that means Java applications, not just Fortran or C++ code …

GPU Tech Conference - Tuesday show recap

We had NVIDIA's Ujesh Desai give us a recap of the day's events at the GPU Technology Conference. He's the VP of product marketing for all NVIDIA products - we covered that topic in detail right off the bat. In the accompanying video, we talked about how the GPU conference has taken off this year, hit on some of the …
channel

Nvidia hit by GPU slump, too

Microprocessor and GPU maker Advanced Micro Devices said yesterday that its financial results had been whacked by an unexpected downturn in discrete graphics processor sales in the fourth quarter, and Nvidia now says it had the same problem. In a statement, Nvidia put the blame squarely on the disk shortage that has been caused …
DVD it in many colours

Nvidia shows off superjuiced Kepler GPU

There were quite a few surprises in today’s GTC12 keynote by NVIDIA CEO and co-founder Jen-Hsun Huang. If NVIDIA were just introducing a new and faster rev of its latest GPU processor, one that brings three times the performance without breaking the bank on energy usage, that would be a solid win, and in line with expectations. …
The Tesla K20 GPU coprocessor card

Nvidia launches not one but two Kepler2 GPU coprocessors

The wait for the "Kepler2" GPU coprocessors based on the company's GK100 GPUs is over. That's the good news. The bad news is that you may have to hurt someone – or call in a favor at Nvidia – to get your hands on one, because so many people are going to be looking for one to goose their number-crunching. And you'll have to get …

Can't wait for Nvidia? Try these Italian baby ARM clusters with GPU options

Nvidia has made no secret about wanting to be a player in the supercomputer racket both on the GPU and CPU sides of a hybrid system. The company launched "Project Denver" nearly two years ago to create a Nvidia-branded chip, which will see Denver ARM processors timed to market with the future "Maxwell" GPUs two years from now. …
Cat 5 cable

AMD claims 'world's fastest GPU' title

AMD has unveiled its first graphics card based on its Graphics Core Next architecture, which The Reg told you about in excruciating detail this summer. According to AMD, the card – the Radeon HD 7970 – is also the only GPU to be built using a 28-nanometer process. "This graphics card represents a revolution in the graphics …
Rik Myslewski, 22 Dec 2011

CSIRO orders 2,144 core, 174,720 GPU upgrade

The CSIRO has announced an upgrade to its GPU cluster to a hefty 134 nodes powered by 268 Intel E5-2650 processors and 390 NVidia Tesla 2050 GPU cards. The 2,144 CPU core, 174,720 GPU core thumper will, according to the science agency’s head of Computation and Simulation Sciences Dr John Taylor, deliver up to 120 Teraflops of …

Nvidia's new CUDA 6 has the 'most significant new functionality in the history of CUDA'

Nvidia has released CUDA 6, an upgrade to its proprietary GPU programming language that it says "includes some of the most significant new functionality in the history of CUDA." For our money, the most important aspect of CUDA 6 is its unified memory scheme, which The Reg described in some detail when the CUDA Toolkit 6.0 was …
Rik Myslewski, 16 Apr 2014
Nvidia

Nvidia upgrades PGI 2014 accelerator compile suite

Just a few months after first releasing its PGI 2014 set of compilers and tools, Nvidia subsidiary The Portland Group (PGI) has expanded OpenACC C++ support in the high-performance computing compile suite, and put older versions of Windows on the EOL list. The PGI 2014 release back in February added support for the latest …
SGI logo hardware close-up

ARM unleashes 8-core Mali 450 GPU, heads down both forks in road

ARM is doubling the punch of its Mali 400 graphics processors with extra cores for tablet, phone and TV makers that are not ready for combined graphics and compute chips. The microprocessor architect has announced the Mali 450 GPU, featuring eight cores instead of four. ARM said the 450 showed it remains committed to the 400 …
Gavin Clarke, 19 Jun 2012
Nvidia

GAME ON: NVIDIA brings GPUs to 64-bit ARM servers

ARM's march into data centres and the world's most demanding applications has taken a major stride forward with GPU king NVIDIA throwing its weight behind ARM server-makers by releasing a version of its CUDA parallel programming platform that works with the architecture. HPC types have, in recent years, increasingly turned to …
Simon Sharwood, 24 Jun 2014

ARM rolls out new GPU, loses head

One of ARM's founders, not to mention a co-designer of the eponymous chip, will be retiring from his presidential role next year to spend more time with his money, though not until May. Tudor Brown has been at ARM 21 years, and was at Acorn before that, where he worked on the ARM chip. That chip was designed for the Archimedes …
Bill Ray, 10 Nov 2011
Infosec

Who needs hackers? 'Password1' opens a third of all biz doors

Hundreds of thousands of hashed corporate passwords have been cracked within minutes by penetration testers using graphics processing units. The 626,718 passwords were harvested during penetration tests over the last two years conducted across corporate America by Trustwave infosec geeks. The firm's threat intelligence manager …
Darren Pauli, 15 Aug 2014
Broken CD with wrench

Real-time drone videos get GPU-tastic

Here at the GPU Technology Conference (GTC 2012), you see a lot of things that you didn’t think were quite possible yet. Case in point: cleaning up surveillance video. The standard scene in “24” or any spy thriller is of agents poring over some grainy, choppy, barely-lit video that’s so bad you can’t tell whether it’s four …
HummingBoard SBC from SolidRun

SolidRun pitches upgradeable SBC into the IoT fray

Another single-board contender has emerged to challenge the Raspberry Pi's title as lightweight champion of the world, with a pitch that it supports processor and memory upgrades in a single-board-computer form factor. SolidRun is offering a 1 GHz ARM v7 processor as the base level CPU on a new HummingBoard board, which it says …

AMD demos 'Berlin' Opteron, world's first heterogeneous system architecture server chip

AMD will give the first public demo of its second-generation Opteron X-Series server processor, code-named "Berlin", at the Red Hat Summit in San Francisco on Wednesday. The company tells The Reg that the demo will consist of X2100 Series Opteron running a Linux environment based on the Fedora Project. Berlin is not one of your …
Rik Myslewski, 16 Apr 2014
Nvidia GeForce 8700M GT

Gamers save Nvidia's bacon in storming fourth quarter

Nvidia has reported better-than-expected fourth quarter financial results, with revenues of $1.14bn over the three months ending January 26, up 9 per cent on the last quarter and 3 per cent on the year-ago period. "Quarterly revenue came in well above our outlook, driven by PC gaming, capping an outstanding year for our GPU …
Iain Thomson, 12 Feb 2014
Nvidia Tegra K1 die

Nvidia slips love letter to open source driver devs

Nvidia is cozying up just a little with the open source community, with it emerging in late January that it's kicked some driver code into the Nouveau open source graphics driver project. The company has previously been the recipient of hate mail from the open source community as being difficult to work with. However, with a new …
SGI logo hardware close-up

Imagination uncloaks 'over 20X faster' smartphone GPU

Imagination Technologies has revealed a pair of new GPU IP cores that it claims will supply new heights of performance to the likes of Apple, TI, Samsung and others who use the UK company's low-power graphics cores. "You are now talking about, from a gigaflop point of view, supercomputing in hundreds of milliwatts," Imaginations …
Rik Myslewski, 12 Jan 2012
Nvidia Shield Tablet

Shields up! Nvidia crams Tegra K1 into gaming slab to rival your PS3

Nvidia is touting a new 8-inch, Tegra K1-powered Android tablet as a gaming gadget for hardcore players. The graphics biz said its Shield slab was designed to offer punters high-end games performance on the move, with support for Android games and streaming PC titles when connected to desktops with Nvidia's GameStream tech. …
Shaun Nichols, 22 Jul 2014

Get ready for software-defined RADAR: Jam, eavesdrop, talk and target ... simultaneously

With a big RF transmitter and enough fast computing power, you have the ability to do a lot of different things, as evidenced by a General Electric presentation on "software-defined radar" at the GPU conference this year. At GTC 13 last year, GE gave a standing-room-only presentation about how it's using RDMA (Remote Direct …
server room

SoftLayer tailors HPC clouds with GPU lining

Hosting and cloud computing service provider SoftLayer is getting into the modern hybrid supercomputer racket with the launch of GPU-enhanced server instances. SoftLayer, which is based in Dallas, was founded in 2005 and merged with hosting rival The Planet before being bought up by GI Partners, in 2010. GI Partners is a private …

IBM opens up vast market for GPU computing

Another action-packed day at the 2010 GPU Tech conference in San Jose. We sat down with Andy Keane, NVIDIA's GM of the Tesla GPU business unit and in our few minutes together, we talked about how the HPC system vendor announcements from IBM, Cray and T-Platform put the NVIDIA GPU in a different light for many potential buyers. …