Feeds

CUDA daddy muses on future GPUs

'G'bye CPU, we hardly knew ye'

Remote control for virtualized desktops

GTC If you think of Nvidia as a hardware company, you're only three-quarters correct — at least according to Ian Buck, Nvidia's senior director of GPU computing software, who sees an even greater role for software as his company's products evolve.

"It's important to note that software and hardware really are one," Buck told attendees of Nvidia's GPU Technical Conference in San José, California, Wednesday. "I believe Nvidia at this point is one-quarter software engineers, in term of engineering staff. So it's a big part of what we do."

Buck is one of the prime forces behind Nvidia's CUDA (compute unified device architecture) parallel-processing ecosystem, and his focus — as his title suggests — lies heavily on the "C for CUDA" software side.

At its San José conference, Nvidia heavily emphasized its products' applicability to the HPC market. Games got their moments in the sun, but HPC was where the action was — and, for that matter, where Nvidia's execs are steering the company.

And it was towards the multi-node, clustered, GPU-centric HPC world that Buck aimed his remarks — especially after he first gave an overview of Nvidia's past and then settled into talking about its future.

"There's a couple of places we're innovating," he told his audience of engineers, scientists, and deisgners. "One is within the node."

In a single compute node of a multi-node cluster, Buck explained, "OS integration continually challenges how a GPU is a coprocessor to the CPU. How does that boil down into a basic operating system responsibility, now that there's two kinds of processors in the system?"

Buck had a few ideas about how that node-level CPU/GPU communication might be improved: "Scheduling, preemption, virtual memory — [Nvidia CEO] Jen-Hsun hinted at some of that stuff in his keynote."

Buck also discussed simplification of the CUDA programming model: "If we integrate the GPU and its memory and its scheduling more with the CPU," he said, "we can get simplifiction for optimization for the programming model which will make it easier to move code onto the GPU — and we will be doing that in future releases of CUDA."

Beyond improvements within the node, Buck also discussed plans to extend improvements into the cluster. "When you have a cluster of a hundred nodes, or ten-thousand nodes, or a hundred-thousand nodes, how can the GPU better interface with the rest of the infrastructure?"

He answered himself: "We can be doing better on things like MPI and sharing communications. We've taken some good first steps on allowing high-speed network hardware — InfiniBand — to directly access and communicate with GPUs. I expect more things to be happening there, but clearly more of your data is going to be living on the GPU, and we need to make sure that that data can communicate with other GPUs, within the node or across the network."

Buck — unsurprisingly — wants to move more of an average workload onto GPUs: "Think about enhancing the programming model, both at the software and the hardware level, to just simply move more of the data, more of the problem to the GPU."

One of the goals of tweaking the programming model will be to transition code originally designed for CPUs onto GPUs. Or, as Buck described that goal, to "ease some of the transition pains from legacy, 15-year-old, 30-year-old Fortran code onto the GPU."

When asked about tighter hardware integration of the CPU and GPU — putting a CPU on the GPU die, for example, to help ease memory-bandwidth restraints — Buck deflected the query, saying: "Fundamentally I want to be thinking about what parts of my problems are ... serial computation, and [what parts are] data-parallel computation."

This munging of an essentially serial CPU with an essentially parallel GPU, of course, is how Intel has architected its upcoming Sandy Bridge processors, and is also at the heart of AMD's "right around the corner, we promise" Fusion line of APUs — which is how that company dubs its "accelerated processing units".

But Nvidia's target — at least on the level with which Buck and his CUDA team are involved — looks beyond the Intel's weak-sister integrasted graphics or AMD's gamers' delight eyeball-melting graphics cards. Buck's target is HPC.

And for that market, he raised one interesting bit of futuristic conjecture: "Can a GPU be changing its level of parallelism to go more serial [or] to go more parallel as it needs to by nature of the program?"

When or if that should ever happen, and when or if that development migrates down from the petaflop heights of HPC to consumer desktops, our children may chuckle at the days when their forebears called one type of chip — or even one area of a chip — a CPU and another a GPU.

Except, of course, if all they want to do is play Crysis. ®

Choosing a cloud hosting partner with confidence

More from The Register

next story
Euro Parliament VOTES to BREAK UP GOOGLE. Er, OK then
It CANNA do it, captain.They DON'T have the POWER!
Download alert: Nearly ALL top 100 Android, iOS paid apps hacked
Attack of the Clones? Yeah, but much, much scarier – report
NSA SOURCE CODE LEAK: Information slurp tools to appear online
Now you can run your own intelligence agency
Post-Microsoft, post-PC programming: The portable REVOLUTION
Code jockeys: count up and grab your fabulous tablets
Twitter App Graph exposes smartphone spyware feature
You don't want everyone to compile app lists from your fondleware? BAD LUCK
Microsoft adds video offering to Office 365. Oh NOES, you'll need Adobe Flash
Lovely presentations... but not on your Flash-hating mobe
prev story

Whitepapers

Free virtual appliance for wire data analytics
The ExtraHop Discovery Edition is a free virtual appliance will help you to discover the performance of your applications across the network, web, VDI, database, and storage tiers.
Getting started with customer-focused identity management
Learn why identity is a fundamental requirement to digital growth, and how without it there is no way to identify and engage customers in a meaningful way.
The total economic impact of Druva inSync
Examining the ROI enterprises may realize by implementing inSync, as they look to improve backup and recovery of endpoint data in a cost-effective manner.
High Performance for All
While HPC is not new, it has traditionally been seen as a specialist area – is it now geared up to meet more mainstream requirements?
Website security in corporate America
Find out how you rank among other IT managers testing your website's vulnerabilities.