Imagination unleashes two new GPU IP cores
Add to 
del.icio.us
 Digg this
Get a great Ubuntu Linux dedicated server for less than $3 a day!
Share on Twitter
Jan. 13, 2012
Imagination Technologies has unleashed two new GPU IP cores that it claims will deliver new levels of performance
to the likes of Apple, TI, Samsung and others who use the company's low-power graphics cores.
"From a gigaflop point of view, you are now talking about supercomputing in the hundreds of milliwatts," said
Imaginations's vice president of marketing, Tony Smith.
The first in the PowerVR Series 6 of GPU IP cores were announced at CES this week, and they are the PowerVR G6200 and
the G6400, which are both based upon Imagination's new architecture that the company calls "Rogue". Strictly speaking,
Rogue isn't new. It's an evolution, but there are actually a lot of new features involved.
Harold told us that there's been a "shift in the dialog" about GPU IP cores, from considering just the more traditional
metrics of how many polygons a GPU core can push, to how the GPU's compute capability can supplement the CPU in a heterogeneous
CPU/GPU system.
"We're talking about computing that matters the most," Harold said, "So the architecture we're defining is about
these computer clusters – these arrays of computer elements that go together." The G6200 comes with two of these computer
clusters, and the G6400 has four.
"Within a Rogue core," King-Smith told us, "there's two or four clusters of execution elements, and each execution
cluster is actually an array execution units. You're building basically layers of hierarchy."
"In Imagination's earier PowerVR SGX Series 5 GPU IP core family, Smith explained, the model was execution pipelines,
with each being essentially a data path. We're talking about our lowest building block, instead of a single pipeline or
data path, it's now an execution cluster. It is an array of pipelines as the lowest building block," he added.
According to Smith, "The big thing about Series 6 and the GPUs is that they are parallel processors – true parallel
processors, not just parallel pipelines, and this is what makes all the difference," he said.
"This is why they're taking over from the CPU. If you're doing anything that's computer-intensive, you do it on the
GPU, not on the CPU, because the horsepower – the raw density of processing per square millimeter and per milliwatt –
is vastly different," he explained.
And there are, of course, some coding trade-offs that still need to be made to harness this horsepower. "You don't
take C code and put it on a GPU," Smith said. "We keep talking with these people who say, 'We've got these tools that'll
analyze you C code, and identify the parallelism.' No. That isn't the way that this is going to work."
To really take advantage of all the parallel-processing capabilities of the Rogue architecture, software developers
will need to design algorithims to take advantage of it, but they have help in the form of the Khronos Group's open
standard, Open CL.
"The fundamental is simply that what you run on the GPU is low-level. Think of it more like a DSP," Smith said,
giving workload examples of an audio codec, a cryptography task, or what he referred to as "the classic" function,
image processing.
"Most of your code will actually stay in C on the CPU," he said, "except the heavy lifting stuff. If you're trying
to optimize on the CPU, that's increasingly the wrong way to do it." Instead, developers will use OpenCL APIs to offload
parallel tasks to the GPU.
Imagination has developed a full set of OpenCL drivers for not only the new Series6, but also for its predecesor
Series 5 GPU IP cores, which have been around for about three years now.
"Series 5 wasn't designed for GPU computing, but the Series 6 most definitely is – without losing the fact that it's
a great graphics engine, as well," Smith was quick to point out.
So how well does all this cluster-based chippery perform? Quite well actually, Imagination says. "We're talking about
cores using the Rogue architecture – part of our Series 6 – which start from around 100 gigaflops and go up into the
teraflops territory," as cores are added, Harold said.
Smith emphasized that overall performance in the range of a couple of hundred gigaflops could be easily achieved at
mobile power-consumption levels, which is fairly dramatic, he said.
That drama comes from performance increases that a company estimates as 20 times or more of the performance of
current-generation GPU cores targeting comparable markets, and enabled by an architecture that is around 5 times more
efficient than previous generations.
But while those numbers may seem rather extreme, Smith assured us that they weren't. "We're always trying to be very
conservative about the numbers that we talk about. These numbers are very, very real, realized in a real benchmark running
on a real chip," he said.
This very, very real performance will show up in both tablets and smartphones, but Harold emphasized that the designs'
power profiles are suitable for smartphones. "Smartphones are the core market. We would not design anything that is not
for smartphones."
To find a home for the Rogue architecture in power-sipping smartphones, Harold told us that the company is aiming for
the same level of power hunger per millimeter squared as achieved by previous Imagination GPU IP cores – with one caveat--
the Series6 is bigger than its predecessors, so the number of square millimeters is greater, process size being equal.
But process sizes are shrinking, and if Imagination's real numbers are indeed real, then a Series6 core can get a lot
more work done per watt than the Series5 and earlier, so it should be able to snuggle into smartphones quite comfortably.
Source: Gartner Market Research.
Add to
del.icio.us
Digg this
Get a great Ubuntu Linux dedicated server for less than $3 a day!
Share on Twitter
| 
