SILICON? CHECK. HSA? CHECK. ALL DONE? WRONG!
TONY KING-SMITH EXECUTIVE VP MARKETING, IMAGINATION TECHNOLOGIES
| SILICON? CHECK. HSA: CHECK. ALL DONE? WRONG! | NOVEMBER 12, 2013 2
FROM MOBILE TO DATACENTER, IT ALL STARTS WITH THE SOC…
PowerVR GPU
Graphics processor
PowerVR VPU Video & Vision processor
Ensigma RPU
Radio comms processor
MIPS CPU General
processor
| SILICON? CHECK. HSA: CHECK. ALL DONE? WRONG! | NOVEMBER 12, 2013 3
THEN WE NEED A WAY FOR PROCESSORS TO COMMUNICATE…
PowerVR GPU
Graphics processor
PowerVR VPU Video & Vision processor
Ensigma RPU
Radio comms processor
MIPS CPU General
processor
Unified Memory
Flow Cloud
technologies
Bus Fabric
| SILICON? CHECK. HSA: CHECK. ALL DONE? WRONG! | NOVEMBER 12, 2013 4
AND WE WRITE APPS THAT USE ALL THESE RESOURCES – THANKS TO HSA
PowerVR GPU
Graphics processor
PowerVR VPU Video & Vision processor
Ensigma RPU
Radio comms processor
MIPS CPU General
processor
Unified Memory
The Cloud Bus Fabric
GPU Kernel
GPU Kernel
GPU Kernel
HW Kernel?
VLIW Kernel?
Clever HSA-aware app
| SILICON? CHECK. HSA: CHECK. ALL DONE? WRONG! | NOVEMBER 12, 2013 5
HOORAY!
ALL THE WORLD’S PROBLEMS SOLVED…?
| SILICON? CHECK. HSA: CHECK. ALL DONE? WRONG! | NOVEMBER 12, 2013 6
DREAM ON…
Many questions to be answered ‒ Portability ‒ Scalability ‒ Simulation & modelling ‒ Power Management
This is complex stuff – so it will take time to learn how to use it
But the most important question is: relevance to developers ‒ Will developers actually be able to use HSA? ‒ Does HSA address the needs of tomorrow’s applications?
| SILICON? CHECK. HSA: CHECK. ALL DONE? WRONG! | NOVEMBER 12, 2013 7
TARGET MARKETS
Fact: ‒ The highest volume market by unit volume is smartphones and tablets
Fact: ‒ Developers need to make money; they enjoy eating and drinking
Fact: ‒ More and more applications that are engaging consumers are on mobile
platforms from consumer to enterprise ‒ So that’s where more and more developers are focused
Fact: ‒ The SoC platforms being used in these markets are changing so rapidly,
optimising for any one platform makes little or no sense for developers
If HSA does not target these markets, it will only be relevant to high performance developers – a vital community, but a specialised one
HSA must address mobile platforms and developers!
IS HSA ADDRESSING THE RIGHT ONES?
| SILICON? CHECK. HSA: CHECK. ALL DONE? WRONG! | NOVEMBER 12, 2013 8
ALL PLATFORMS BY OS
0
500,000
1,000,000
1,500,000
2,000,000
2,500,000
3,000,000
2010 2011 2012 2013 2014 2015 2016 2017
OthersWindowsSymbianRIMMeeGoLiMo FoundationiOS/MacOSChromeBadaAndroid
Source: Imagination
| SILICON? CHECK. HSA: CHECK. ALL DONE? WRONG! | NOVEMBER 12, 2013 9
GPUS SCALE WITHIN ONE GENERATION
PERFORMANCE ENVELOPE GROWING WITH EACH SOC GENERATION
Mob
ile G
PU p
roce
ssin
g po
wer
(log
)
Time
12GFLOPs
2013
128GFLOPs
2014 2015
256GFLOPs
24GFLOPs
48GFLOPs
Widening GPU performance
envelope – but power budget remains static!
| SILICON? CHECK. HSA: CHECK. ALL DONE? WRONG! | NOVEMBER 12, 2013 10
PORTABILITY AND SCALABILITY
APIs are intended to aid portability ‒ But HSAIL isn’t the easiest thing to code with; neither is OpenCL,
or OpenGL ES, or…
Apps must now scale over a very broad range of performance at any given point in time ‒ Todays leading edge smartphones are tomorrow’s commodity
The reality is the numbers of developers actually skilled in using these APIs is relatively small compared to the much broader community ‒ So middleware is essential, e.g. games engines, UI engines, function libraries
We need to stimulate the middleware community to get traction for HSA Writing a portable, scalable app is an emerging art form!
CAN MORE THAN A HANDFUL OF DEVELOPERS HANDLE SCALABLE HETEROGENEOUS APPS?
| SILICON? CHECK. HSA: CHECK. ALL DONE? WRONG! | NOVEMBER 12, 2013 11
OTHER ISSUES ABOUND
Simulation and modeling ‒ Getting harder all the time! ‒ App understanding of the underlying SoC platform has increasingly
dramatic implications on system performance
Power management ‒ The application needs to control this, not just rely on the OS
Processing profiles are increasingly dynamic ‒ Dynamically varying voltage, clock, thermal ‒ Switching in and out of GPU and CPU cores; shared resources
If we’re not careful, we end up with the perfect solution that’s far too clever for mere mortals to use!
HOW WILL DEVELOPERS GET TO GRIPS WITH THE COMPLEXITIES OF HETEROGENEOUS PLATFORMS?
| SILICON? CHECK. HSA: CHECK. ALL DONE? WRONG! | NOVEMBER 12, 2013 12
CHALLENGING CONVENTIONAL WISDOM
Myth: Desktop apps will move to mobile ‒ No they won’t! Look at all the successful mobile apps… ‒ Mobile apps are different - touch-based, highly interactive,
and designed to scale across a wide range of platforms
Myth: High performance apps will move to mobile ‒ Why should they? They’re best suited to cloud servers
Myth: Cloud computing will kill serious computing on mobile ‒ No, they will co-exist, and the smart money is on those that use both
HSA must not ignore the power and influence of mobile platforms
OR…WHERE’S THE MONEY?
| SILICON? CHECK. HSA: CHECK. ALL DONE? WRONG! | NOVEMBER 12, 2013 13
HOW DEVELOPER COMMUNITIES ARE PARTITIONED…
Mobile App Developers
Immediate response Always available
Instant/short timeframe
Cloud Server App Developers
Big data QoS depends on link
Medium-long timeframe
| SILICON? CHECK. HSA: CHECK. ALL DONE? WRONG! | NOVEMBER 12, 2013 14
BUT THIS IS HOW IT WILL EVOLVE, AND QUICKLY…
Immediate response
Cloud-based analysis
Heterogeneous App Developers
Immediate response Always available
Instant to long timeframe
| SILICON? CHECK. HSA: CHECK. ALL DONE? WRONG! | NOVEMBER 12, 2013 15
SO IF YOU HAVE A GREAT LINK…
Immediate response
Cloud-based analysis
Heterogeneous App Developers
Immediate response Always available
Instant to long timeframe
| SILICON? CHECK. HSA: CHECK. ALL DONE? WRONG! | NOVEMBER 12, 2013 16
BUT IF IT’S A BIT DODGY…
Immediate response
Local analysis
Cloud-based analysis
Heterogeneous App Developers
Immediate response Always available
Instant to long timeframe
| SILICON? CHECK. HSA: CHECK. ALL DONE? WRONG! | NOVEMBER 12, 2013 17
OR DIES ALTOGETHER…
Immediate response
Local short and longer timframe analysis
Heterogeneous App Developers
Immediate response Always available
Instant to long timeframe
| SILICON? CHECK. HSA: CHECK. ALL DONE? WRONG! | NOVEMBER 12, 2013 18
CONCLUSIONS
HSA is great – but it must target both mobile and performance SoCs in order for it to be widely adopted
High volume mobile platforms will always be cost-sensitive ‒ So you can never assume high end capabilities will migrate onto them
Mobile platforms mean much more than smartphone app processors ‒ Data center computing will increasingly rely on low power SoC technologies derived from mobile ‒ Mobile chips will be used in ever broader markets ‒ The Internet of Things will be a key source of data essential for rich analytics – low cost, low power again
The best developers will go where the money is ‒ If HSA is to be successful, it must target volume markets, not start at the high end
Apps, not just SoCs, are going to be heterogeneous in many ways ‒ Partitioned across mobile and datacenter platforms, dynamically reconfiguring in response to environment