Forward-looking: Intel’s upcoming Arc flagship has actually made its very first look in an online standard database. An unnamed Intel partner took a GPU engineering sample for a try in the Geekbench OpenCL test suite utilizing a somewhat outdated i5-9600 K recognition platform and here’s what we discovered …
In straight-out numbers, the GPU does improperly. The 4 runs attained a typical OpenCL rating of about 67,000 points and its greatest rating was 69,000 points. For contrast, the AMD Radeon RX 6800 XT launches about a year ago beings in the 150,000 to 180,000 point ballpark.
But do not be prevented. Consider this: according to the metadata gathered by Geekbench throughout the runs, the GPU was hovering at around 1.3 GHz. At that frequency, with 512 EUs, the GPU has a theoretical 11 TFLOPS of efficiency.
AMD’s Radeon RX 6600 XT has comparable 11 TFLOPS and ratings in the 60,000 to 70,000 point variety. Intel’s architecture has the exact same per-TFLOPS efficiency in OpenCL as AMD’s does.
So the concern is: can Intel match AMD’s high-end TFLOPS numbers?
According to Geekbench, the GPU had actually a ranked clock speed of 2.1 GHz. If it had actually performed at that speed, and not at 1.3 GHz, then it would’ve had 17 TFLOPS, which is on par with the RX 6800 (non-XT). The response to that concern is, yes, if 2.1 GHz is attainable.
And honestly, 2.1 GHz isn’t that high. If the reports hold true and Intel is utilizing the TSMC N6 node, then they might possibly press the clocks high enough to get into RX 6800 XT and RTX 3080 efficiency area.
Remember that this is pure opinion, however we’re not the very first to declare that Intel’s GPUs will land someplace along with the RTX 3070 or RTX3080 Intel themselves hinted that their flagship will be priced a touch above the latter at $740 to $790 Still, as today’s OpenCL ratings reveal, Intel might still be tough at work to arrive.