Skip to main content

Intel and AMD's love/hate relationship spilled in benchmarks detailing two chips

Earlier this week, Intel and AMD revealed a rejuvenated love-hate relationship that will see Intel’s Kaby Lake processor cores married with AMD’s recent Polaris graphics cores in one eighth-generation Kaby Lake-G package. The two didn’t disclose any hardware details, but that didn’t stop benchmarks from appearing to temporarily satisfy our palate.

What Intel and AMD are bringing to the market isn’t exactly the typical processor. It’s a multi-chip module (MCM) cramming processor and graphics cores together along with HBM2 memory that’s dedicated to the graphics portion. All three are connected by a special “bridge” inside the module for extremely fast data transfers between the three components.

Recommended Videos

Intel is expected to initially produce two modules: The Core i7-8705G and the Core i7-8809G. The “G” in both the code name and model number supposedly means graphics, as these modules will have extremely more graphical power than the GPU cores typically crammed into Intel’s processors.

Here are the rumored specifications:

Core i7-8705G Core i7-8809G
Board number: 694E:C0 694C:C0
CPU core architecture: Kaby Lake Kaby Lake
Cores: 4 4
Threads: 8 8
Base speed: 3.1GHz 3.1GHz
Boost speed: 4.1GHz 4.1GHz
Polaris compute units: 24 24
Polaris stream processors: 1,536 1,536
Base speed: 1,000MHz 1,190MHz
HBM2 memory amount: 4GB 4GB
Memory speed: 700MHz 800MHz

The hardware specifications listed for each module in the table above were pulled from various benchmark software including GFXBench, GeekBench, 3DMark 11, SiSoftware Sandra Platinum, and the PC game Ashes of the Singularity. The source appears to be Tum Apisak’s YouTube channel that is currently displaying several videos regarding the two modules, such as the i7-8809G clearly listed in 3DMark 11 in one clip, and both modules detailed in other benchmarks in another.

But the information is a little confusing. In one instance, Geekbench first appears to provide conflicting data regarding board number and clock speeds. Specifically, it’s the Core i7-8809G in question, and appears to be throttled back with a CPU base speed of 2.81GHz, and a GPU base speed of 1,000MHz. This may be due to power restrictions and thermal limitations in the host PC.

In GFXBench, the board numbers appear to be backward. In Car Chase, the “slower” 694E hit an average rate of 12.3 frames per second while the “faster” 694C only managed 6.8 frames per second. In Manhattan, the 694E achieved an average of 27.4 frames per second while the 694C managed 11 frames per second. Again, based on information provided in other benchmarks, those results should be reversed.

Meanwhile, SiSoftware’s Sandra Platinum lists the Core i7-8705G with the Polaris graphics cores throttled back at 550MHz, and the HBM2 memory throttled back at 500MHz. As before, this may be due to the parent PC, preventing the module from reaching its peak performance due to cooling (thermal) issues.

As always, you cannot take everything you read here as official information. There are obvious inconsistencies across the multiple benchmarks, and we’re not entirely sure the part numbers are correctly matched with the model numbers. But at least we now have some idea of what is going on until Intel and AMD come clean with the details.

Kevin Parrish
Kevin started taking PCs apart in the 90s when Quake was on the way and his PC lacked the required components. Since then…
A major era in Intel chip technology may be coming to an end
An Intel processor over a dark blue background.

Intel's next-generation Arrow Lake chips are said to be coming out later this year, but we don't know much about them just yet. However, a new leak shows us that two crucial features may be missing from the next-gen CPU lineup: hyperthreading and support for the AVX-512 extension. If Intel is ditching hyperthreading, it's not entirely unexpected, but it might make it trickier for even its best processors to beat AMD.

Hyperthreading allows physical cores in Intel processors to perform two tasks simultaneously, improving efficiency and performance in multi-threaded applications. Intel first introduced it in 2002, but it hasn't used the technology in every generation of its CPUs between then and now. The tech was all but gone from client processors for many years following its launch, although it was still present in certain models. Since then, Intel has selectively implemented HT across its product stack. In the last few years, it became a staple, especially in midrange and high-end chips.

Read more
Intel’s new Core Ultra chips needed to be more than this
The Acer Swift Go 14 on a table in front of a window.

A lot has been made of Intel's new Meteor Lake chips. They have a new brand, naming scheme, and even new technology in the form of the NPU (neural processing unit).

And they come at an important time. The stakes have never been higher for Intel, as it faces competition from all sides. They're also an important litmus test for the idea of the NPU, or neural processing unit.

Read more
AMD might finally beat Intel for the fastest mobile gaming CPU
AMD Ryzen 6000 laptop chip.

AMD's Ryzen 9 7945HX, the mobile flagship for this generation, was just spotted in some early benchmarks. The test results show that AMD might be really competitive in gaming laptops this year.

The CPU outpaced its last-gen equivalents by miles, and it kept up with Intel's best processors despite having far fewer cores.

Read more