Slashdot Mirror
ARMs Race: Licensing vs. Manufacturing Models In the Mobile Era
MojoKid writes "The semiconductor market for mobile and hand-held devices has changed dramatically in the past six years and ARM has had to evolve along side it. ARM's IP focus allows it to dedicate all its resources to building a great design rather than committing to any single manufacturing process node, customer, or foundry. Architectural design and implementation is done very much in partnership with both foundries (TSMC, GlobalFoundries) and licensees like Samsung or Qualcomm. The difference between the way Intel goes to market and ARM's model is more nuanced than the simple ownership of manufacturing facilities. Owning its own fab means that Intel can tweak process technology to match the particulars of a given architecture (and vice-versa). It also gives the company far more flexibility when planning future nodes. If Intel feels that integrating Peanut Butter Silicon on Insulator (PB-SOI) is the best way to hit its performance and power consumption targets at 14nm, for example, it can make that happen internally. ARM, in contrast, is limited by the decisions of the foundry manufacturers it partners with."
intel still retains the royalty-free license it obtained from ARM when ARM were running out of cash. the deal was that intel would feed back any improvements made. unfortunately, just as my associate told ARM when he was working for LSI Logic - advice which ARM completely ignored - the designs ARM had at the time were so poor that intel was forced to use their *own* super-scalar Harvard architecture and to put an ARM-compatible front-end on it. intel never gave back any modifications to the design.... because they never made any. ARM were pissed, Intel were embarrassed at having a non-x86 SoC that outperformed both their own cores *and* ARM's, so sold it to Marvell... *minus* the royalty-free license. Marvell had absolutely no qualms about out-performing ARM and immediately ramped it up to 1ghz.
Spend some time looking through the Linux kernel archives, or actually USING one, and you'll see that quite the opposite is true.
What was a tolerable architecture for low-complexity embedded designs has serious flaws in cache coherency and clock-for-clock is painfully slow compared to a 464 (or, even, 440) PowerPC.
Because the ARM lacks the useful complexity for cache coherency and memory, and memory-mapped IO, barriers, and a quite small page table entry cache, it does have a power consumption advantage over the PPC, though.
Maybe (hopefully, really) the 64-bit versions won't be quite so crippled.
Owning its own fab means that Intel can tweak process technology to match the particulars of a given architecture (and vice-versa)
That may be understood as an Intel exclusive, but it's not entirely true. Even in the fabless world the big shots (Qualcomm, NVidia, AMD & co) have very early access to new process nodes and can certainly tune their design to it, and have their own specifics tweaks made. So they can do both kind of adaptation too, although it's not as integrated as for Intel. If you draw a line, Intel is at one extreme being able to have close integration, the small fabless companies are at the other extreme taking the stock TSMC or GF or UMC or else offering as-is. But the big fabless guys are somewhat in the middle.
ARM, in contrast, is limited by the decisions of the foundry manufacturers it partners with.
It's also a bit misleading. ARM has early access to all big fabs (Globalfoundries and TSMC), and because ARM is so pervasive there is a very very high pressure for a fab to provide the best ARM implementations on their process. So sure, it's the fab making the decisions on their process in the end. But you can bet they will pay a lot of attention to any ARM feedback gained during the early access co-work.
ARM doesn't only provide processor IP, they do the whole range now from memory cells to GPUs to interconnect to memory controllers. And they work with the fabs to optimize their design for them and provide their customers "Process Optimization Packages" (POPs) that summarize how to get the best of a process for their IP. So ARM has the know-how, the access and the pull to have a big say in what happens in the fabs roadmaps.