Intel's upcoming 14nm product line, Broadwell, is expected to have six categories of increasing performance. Broadwell-Y, later branded Core M, is part of the soldered BGA family at expected TDPs of 3.5 to 4.5W. Above this is Broadwell-U, which are also BGA packages, and thus require soldering by the system builder. VR-Zone China has a list of seemingly every 15W SKU in that category. 28W TDP "U" products are expected to be available in the following quarter, but are not listed.
Image Credit: VR-Zone
As for those 15W parts though, there are seventeen (17!) of them, ranging from Celeron to Core i7. While each product is dual-core, the ones that are Core i3 and up have Hyper-Threading, increasing the parallelism to four tasks simultaneously. In terms of cache, Celerons and Pentiums will have 2MB, Core i7s will have 4MB, and everything in between will have 3MB. Otherwise, the products vary on the clock frequency they were binned (bin-sorted) at, and the integrated graphics that they contain.
Image Credit: VR-Zone
These integrated iGPUs range from "Intel HD Graphics" on the Celerons and Pentiums, to "Intel Iris Graphics 6100" on one Core i7, two Core i5s, and one Core i3. The rest pretty much alternate between Intel HD Graphics 5500 and Intel HD Graphics 6000. Maximum frequency of any given iGPU can vary within the same product, but only by about 100 MHz at the most. The exact spread is below.
- Intel HD Graphics: 300 MHz base clock, 800 MHz at load.
- Intel HD Graphics 5500: 300 MHz base clock, 850-950 MHz at load (depending on SKU).
- Intel HD Graphics 6000: 300 MHz base clock, 1000 MHz at load.
- Intel Iris Graphics 6100: 300 MHz base clock, 1000-1100 MHz at load (depending on SKU).
Unfortunately, without the number of shader units to go along with the core clock, we cannot derive a FLOP value yet. This is a very important metric for increasing resolution and shader complexity, and it would provide a relatively fair metric to compare the new parts against previous offerings for higher resolutions and quality settings, especialy in DirectX 12 I would assume.
Image Credit: VR-Zone
Probably the most interesting part to me is that "Intel HD Graphics" without a number meant GT1 with Haswell. Starting with Broadwell, it has been upgraded to GT2 (apparently). As we can see from even the 4.5W Core M processors, Intel is taking graphics seriously. It is unclear whether their intention is to respect gaming's influence on device purchases, or if they are believing that generalized GPU compute will be "a thing" very soon.
“As we can see from even the
“As we can see from even the 4.5W Core M processors, Intel is taking graphics seriously.”
… compared to 2002.
I was specifically referring
I was specifically referring to how much die space it takes.
If Intel were taking graphics
If Intel were taking graphics seriously, they would not be afraid to post more information about their SOC GPUs. And one thing is for sure you will pay a hefty premium for Intel’s graphics, to get anywhere near AMD’s, or Nvidia’s SOC graphics, at a lower price than Intel’s. And wait for the 20nm process node to reach full production, and the Nvidia custom ARMv8 based SOCs with more new Maxwell GPU cores, or AMD with its x86 based APUs, and more AMD GPU cores. Intel will be bringing up the rear again, at its usual high cost, only the LCD products from Intel are getting the contra revenue. Intel will brag about their graphics, but only the top end top priced will get anywhere near(as in not quite there) AMD or Nvidia.
LCD: Lowest common denominator.
Looking forward to the K and
Looking forward to the K and QM equivalent part lists. Hopefully TDP will take a dive with those as well.
6100 on a i3.
I hope at AMD
6100 on a i3.
I hope at AMD aren’t far away from using HBM memory on their next APUs.
HBM at those speeds, that
HBM at those speeds, that could give the APU graphics one big on die frame buffer, with a little extra for the CPU also, and while you are at it, AMD, let the x86 core, and GPU share a big wide GPU style data bus to the stack of HBM RAM, say at least 256 bits, or better 512bit, an easy thing to do on a silicon substrate. there is no reason the data bus cannot be bigger than the word size of the CPU’s general purpose registers/instruction size while the external bus is narrower. Just put some extra channels to the uncore/module memory, 4, DDR4, or faster, channels. Or go beyond that to a larger mezzanine module type of system. where the mezzanine module rests in a cutout in the motherboard, the connector pins placed around the circumference of the cutout, and HBM dies stacked top and bottom, with everything on module connected with a 512 bit or 1024 bit bus traced out on a silicon substrate.
3.1GHz/3.4GHz boost dual
3.1GHz/3.4GHz boost dual core/4 thread CPU with respectable graphics for 15W. Can we just stop here for a sec and recognize that as pretty darn impressive. (ignoring that you will likely have to sell a kidney to afford it)
Could see some of these chips in Zbox/Brix/NUC type lines. Or will these be more destined for mobile solutions?
Haswell’s 15W lineup is
Haswell's 15W lineup is apparently popular with fanless NUCs.
Both?
Both?
That’s one killer dual core.
That’s one killer dual core. Honestly Intel will smash everything out of the park with this gen. I tested a HD5500 in a Broadwell 5200U recently and it offers the same performance as an Nvidia 820M with dedicated graphics.. it’s computer performance was better as well…. I was like.. whot.
I’m ready for a complete
I’m ready for a complete refresh of the Macbook Pro Retina line in February.