According to the architecture each core does n't have it's own memory other than the L2 & L1 caches. How the memory is mapped per core is arbitary, there is nothing stopping you from having for exampe a shared data set using 4GB and using 64MB per core for a raytracer where the scene data is stored in the shared memory and each core works on part of scene. So no, you don't have to limit memory per thread to fully use the architecture properly.
I'm assuming you got the 128MB number from dividing 8GB by 64 cores, I have n't seen anything to indicate that a core is limited in that way, in fact Knights Corner caches are coherent.
Ooops, scratch that miss-read the summary. There probably is n't a need for that much memory because the kind of problems they are most likely to be dealing with will have massive datasets that don't fit in memory anyway. The limiting factory will be CPU and node interconnect bandwidth so adding extra memory wont make much if any difference to performance.
One big problem is that many of these so called "Rockstars" are too interested in the technology rather than getting the job done. Technology to them is like fashion, you have to use the latest simply for bragging rights and ego when a proven more mature solution would be the correct descision to take.
This video is funny but makes a simpliar point, the irony being he's promoting mysql as the solution when mysql itself was in itself once an object of ridicule by peoeple who knew what they where doing:
Samsung is their biggest threat and that is why they have gone after them first, should it verdict be held up after appeal I have no doubt they will go after the rest.
until all the facts are in, but I'm guessing that the $1bn number is the least of Samsungs and other smartphone manufacturers problems. Apple will now go after everyone else and I'm sure they wont be licensing anything to their competitors. Of course however an appeal is 100% guarenteed.
This is just part of FB' continous mutations. Remember what FB was like before twitter became popular? Then they "twitterised" it, added news feeds, timeline and other nonsense. However now post IPO the pressure is on and people are realising that FBs model for making money does n't make any sense, so you get crazyness like buying instagram, constant talk about making money from mobile and now payments.
In the end FB will probably get into a feedback loop where they have to become more and more obnoixious chasing revenue from users whilst turning off those users at the same time.
I dont think FB will die because ultimately they will always have their core users but in the same way that Myspace does.
This should be obvious to anyone who has done any realtime/interactive graphics programing. As the frame rate gets higher the amount of time the CPU has to process the next frame gets smaller. It also becomes more diffcult to properly utilise the CPU fully unless you are willing to add a couple of frames of latency to generate frames in the future which I'd speculate is not ideal for a game type application.
Slashdot Mirror
According to the architecture each core does n't have it's own memory other than the L2 & L1 caches. How the memory is mapped per core is arbitary, there is nothing stopping you from having for exampe a shared data set using 4GB and using 64MB per core for a raytracer where the scene data is stored in the shared memory and each core works on part of scene. So no, you don't have to limit memory per thread to fully use the architecture properly.
I'm assuming you got the 128MB number from dividing 8GB by 64 cores, I have n't seen anything to indicate that a core is limited in that way, in fact Knights Corner caches are coherent.
Ooops, scratch that miss-read the summary. There probably is n't a need for that much memory because the kind of problems they are most likely to be dealing with will have massive datasets that don't fit in memory anyway. The limiting factory will be CPU and node interconnect bandwidth so adding extra memory wont make much if any difference to performance.
The Knights Corner chips use GDDR5 memory, bandwidth is a big problem when you have 50+ cores to feed.
Granted it's built to more demanding specifications, but something lasting 35 years in deep space is quite an achievement.
One big problem is that many of these so called "Rockstars" are too interested in the technology rather than getting the job done. Technology to them is like fashion, you have to use the latest simply for bragging rights and ego when a proven more mature solution would be the correct descision to take.
This video is funny but makes a simpliar point, the irony being he's promoting mysql as the solution when mysql itself was in itself once an object of ridicule by peoeple who knew what they where doing:
http://www.youtube.com/watch?v=b2F-DItXtZs
AFAIK non-compete contracts are not legal in the UK.
Samsung is their biggest threat and that is why they have gone after them first, should it verdict be held up after appeal I have no doubt they will go after the rest.
until all the facts are in, but I'm guessing that the $1bn number is the least of Samsungs and other smartphone manufacturers problems. Apple will now go after everyone else and I'm sure they wont be licensing anything to their competitors. Of course however an appeal is 100% guarenteed.
This is just part of FB' continous mutations. Remember what FB was like before twitter became popular? Then they "twitterised" it, added news feeds, timeline and other nonsense. However now post IPO the pressure is on and people are realising that FBs model for making money does n't make any sense, so you get crazyness like buying instagram, constant talk about making money from mobile and now payments.
In the end FB will probably get into a feedback loop where they have to become more and more obnoixious chasing revenue from users whilst turning off those users at the same time.
I dont think FB will die because ultimately they will always have their core users but in the same way that Myspace does.
This should be obvious to anyone who has done any realtime/interactive graphics programing. As the frame rate gets higher the amount of time the CPU has to process the next frame gets smaller. It also becomes more diffcult to properly utilise the CPU fully unless you are willing to add a couple of frames of latency to generate frames in the future which I'd speculate is not ideal for a game type application.
Well as a politician I'm pretty sure he had one eye on the free publicity for him this would cause, seems to have worked I'd say.