Intel Arc A770 desktop GPU debuts in the Geekbench database
Future-oriented: Intel has finally started releasing its mobile Arc GPUs and is set to release its first desktop Arc GPUs later this summer. Somewhere near the top of the stack will be the Arc A770, a fully featured part with 512 EUs, a 2-2.5GHz boost clock and 16GB of memory.
Intel first announced the flagship Arc hardware as the ACM-G10 GPU and then launched it on paper as the A770M for mobile. Laptops with the A770M should hit the shelves in the coming months. Its unannounced desktop equivalent is now: found it in the Geekbench OpenCL database.
It’s not a groundbreaking leak because the hardware itself has been leaked so many times, including once before in the Geekbench database. However, it is the first time that it has been officially called the Intel Arc A770 Graphics to give it its full name.
It’s also another dot on the clock speed chart: 2.4GHz. At the end of last year we talked about rumors about 2.5 GHz, then in February we saw 2.4 GHz for the first time. Intel itself teased 2.25 GHz last month, but may have been referring to a different model.
And the crucial point: In line with previous leaks, the A770 achieved an OpenCL score of 85,585 points. Slightly more than the RX 6600 XT, about the same as the RTX 2060 Super and RTX 2070, and a lot less than the RTX 3060. In other words, midrange through and through.
But that’s not the whole story. Geekbench divides the OpenCL score into its component categories, of which there are 11. Some architectures are better at some classes than others. For example, the 6600 XT is about 35% faster than the 3060 in the Gaussian blur test, despite being slower in eight categories and having a worse score overall.
While the 3060 beats the A770 in more than half of the categories, the A770 takes a significant lead in particle physics and Gaussian blur tests. It loses by the widest margins in the Sobel, histogram matching, horizon detection, and Canny testing, all of which are based on computer vision.
You can see a bit of a pattern from this: the A770 does poorly in memory-sensitive tests, but is otherwise computationally powerful.
Considering the paper specifications of the A770M, it’s a surprising result that the A770 supposedly shares: 16 GB GDDR6 clocked at 17.5 Gbps and connected via a 256-bit bus. That’s not a bad memory subsystem, so maybe this is a quirk of OpenCL, or maybe the Alchemist architecture has a memory bottleneck.
Realistically, there would be no significant impact if there were. At worst, it can make the architecture more suitable for lower resolutions than higher resolutions and shorten the lifespan. Nevertheless, it is interesting to see what makes Alchemist architecture different from Ampere and Navi.
In terms of game performance, the OpenCL scores aren’t much. As noted above, the 6600 XT is more than 10,000 points behind the 3060, but in our review we found it to be faster at 1080p and 1440p in most games. Leaked benchmarks from before we knew the name placed the A770 ahead of the 3060 and in the realm of the 3070 Ti.