Skip to main content
  1. Home
  2. Computing
  3. Mobile
  4. News

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

Add as a preferred source on Google

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…
Microsoft has begun rolling out Copilot Code for building apps with natural language
The workplace-focused vibe coding tool can pull context from emails, documents, meetings, and chats.
Microsoft Copilot code logo

Microsoft introduced Code last month as one of the three core parts of its revamped Copilot app. The app was pitched as an easy-to-use coding agent that lets users describe what they want to build in natural language, like an app, a tracker, a dashboard, an automation, or a workflow, and Copilot would build it for them.

Essentially, it's a workplace-focused vibe-coding app that turns existing work into a functional app, and Microsoft has begun rolling it out through the Frontier program.

Read more
AI agents are acting like rogues and causing a huge headache for US banks
US banks block AI agents over fears they could make unauthorised financial moves
Banking

US banks are facing a new kind of digital headache: artificial intelligence agents attempting to access customer accounts and perform actions that may go beyond what users intended. As AI tools become more capable of navigating websites and carrying out tasks independently, financial institutions are scrambling to prevent them from crossing security boundaries.

According to a report published by Axios on October 22, major US banks have detected third-party AI agents operating inside customer accounts without authorisation. Some agents reportedly appeared to attempt actions independently of user instructions. The banks involved have not publicly detailed every incident, and there is no evidence that the reported activity resulted in widespread theft of customer funds.

Read more
Canva enters the AI image generation race with Craft, and it’s thinking beyond pretty pictures
The new model plans layouts before generating images, with precise editing and support for 30 aspect ratios.
Canva Craft Featured Image

AI can generate all kinds of pretty pictures, but getting it to spell a headline correctly or keep a poster's layout intact can be another story. Canva wants to fix that with Canva Craft, its first in-house image generation model. Rather than focusing primarily on photographs, Craft is designed around the posters, presentations, social media graphics, and other visual content people actually create. The goal is simple: spend less time fixing AI's mistakes and more time making something useful.

Canva Craft plans before it generates

Read more