This site may earn affiliate commissions from the links on this page. Terms of use.

HBM-Feature-Intel

E'er since Intel and AMD confirmed that they'd be bringing a new chip to marketplace with an Intel CPU and AMD GPU, in that location's been speculation nearly where we might come across these parts. The higher power consumption on AMD's Vega, relative to a simpler, lower-end integrated GPU, suggested the AMD+Intel solution might exist confined to small desktops or larger laptops. Now, there's at least a risk that we'll see the chip in a socket form cistron, or at the very least, that it might exist used a bit more than broadly.

Leaked roadmaps from earlier this year suggested that Intel'due south Hades Canyon platform would include 2 SKUs — a 66W role with an integrated Vega GPU and a locked clock speed, and a 100W TDP part with a "Chiliad" suffix (visible below, barely, at the tiptop line) marketed as existence VR-capable and sitting at the superlative of Intel's production stack.

HadesCanyon

New data from Intel'southward overclocking website (screenshotted in example they remove it) now shows a new, unlaunched CPU — the Core i7-8809G — as being on Intel's listing of overclocking chips. The i7-8809G is a quad-core/eight-thread CPU with a base clock of 3.1GHz, and a (rumored) boost clock of 4.1GHz. The 4GB HBM2 buffer on the Core i7-8809G is rumored to be clocked at 800MHz vs. the 700MHz on the (not listed) Core i7-8705G that supposedly fills in the lesser of the roadmap.

Roadmap1

If we plug these figures in, the Cadre i7-8705G would have 180GB/s of memory bandwidth for its GPU, while the Core i7-8809G would offering 204GB/s. That'd put the upper-cease GPU on the 8809G in range of the full-size RX 470 (211GB/s). The rest of the chip is firmly anchored to Kaby Lake, non Coffee Lake, with a quad-core CPU, 8 threads, and formal support for DDR4-2400 as opposed to DDR4-2666.

What we've seen at this point suggests that earlier rumors were on-rail. A 3.1GHz base/iv.1GHz turbo clock on an unlocked quad-cadre CPU with a 100W target TDP matches the specs that leaked in early on November. If this flake proves to have the 24 CUs it'south supposed to pack, that works out to an on-dice GPU with ane,536 GPU cores. No, it won't take on a $200+ midrange GPU, but it could easily compete with hardware beneath that point, and a quad-cadre/eight-thread CPU will take few problems with gaming workloads that adapt its on-board GPU. Also, interestingly, this CPU will apparently ship with both Intel integrated and AMD's on-board GPU solutions, which could make this the first CPU to back up hooking up six monitors out of the box.

I doubtable there's a great deal of marvel from Intel and AMD alike near whether customers will bite on this sort of GPU configuration. Integrated graphics occupies a catchy spot in company product stacks. Consumers want the advantages an on-die GPU delivers, especially in mobile, where the power savings are almost welcome. Only attempts to create a specific premium market for iGPUs oasis't had skilful results, and in that location are primal limits to how much power you tin can pack into an integrated GPU when it's sharing a socket with the CPU. If these Intel chips accept off, it could spur new interest in the product category from both companies.