As part of the CES cavalcade of announcements, after launching Core-M back in September, Intel is formally releasing their next element of the 14 nanometer story: Broadwell-U. As the iterative naming over Haswell-U suggests, Broadwell-U will focus on dual-core 15W and 28W units from Celeron to Core i7 using 12 to 48 ^A-execution units for the integrated graphics. A Broadwell-U processor should drop into any existing Haswell-U equivalent design (i3 to i3) due to pin and architecture compatibility, albeit with a firmware update.
As with any node change, the reduction to 14nm affords the usual benefits: more transistors per unit area, lower power consumption for a given design, or the potential to increase performance. Ryan covered the details of Intel’s 14nm architecture back as part of the IDF launch, as well as a good deal of the Broadwell architecture itself. The launch today is in essence a specification list with a few extra details, along with potential release dates for Broadwell-U products. The CPUs are already shipping to partners for their designs.
Like the previous item about NVIDIA, yet another excellent AnandTech first look at new processor technology – this time from Intel.
What does this mean for laptops? (I need someone to translate the technical specs announced)
Does it mean retina displays are possible with 12 hour battery life on a possible new macbook Air?
Does it mean better hardware-assisted virtualisation support – eg virtualised GPU?
Does it mean better GPU-compute performance with opencl?
Does it mean hardware assisted audio/video co/decode?
Someone suggested the on-board wireless-ac interfaces are much better at lowering power consumption when idle.
Looking at the raw numbers which I don’t really understand this doesn’t look like a significant step up from the current Broadwell.
The thing that interests me most is the memory coherency between GPU and CPU memory structures.
I wonder if Intel is going to enable true HSA, and if so, if they’re going to adopt AMD’s design (HSA Intermediate Language, or HSAIL), or roll their own.
Well that is an easy one to answer. Intel will use nothing that anyone else has made.
Like how Intel only has 32-bit x86 CPUs since they’d never use a 64-bit technology developed by AMD?
*cough* according to Intel it is called EM64T *cough*
Do not mention ze war!
Originally it was, and it wasn’t that great (they didn’t implement everything correctly, and some things were missing like hybrid mode for running a 64-bit kernel with 32-bit userlane (or was it vice versa?)). Then they got smart and just licensed the AMD64 extensions from AMD and things got much better.
And the name has changed multiple times since the P4 days:
EM64T
IA32e
Intel 64
(There’s another one missing from the middle)
That’s all beside the point, though. The original point was that Intel has used tech developed by competitors in the past, so there’s always a chance (however slim) that they may do so again in the future (with the HSA stuff).
Edited 2015-01-08 17:44 UTC