Rumor mill: Intel’s upcoming Tiger Lake mobile processors will be the first to showcase the Xe GPU platform. A leaked result from OpenCL Geekbench shows that the mid-range Core i7-1165G7 achieves an impressive score of 59,845, putting it in direct competition with the best AMD and Nvidia in this segment.
In terms of gross power, this Core i7-1165G7 result exceeds the average Nvidia MX350 result by ~ 17%. That’s a pretty ingenious advantage, given that the MX350 has 2GB of VRAM and the G7 has no dedicated memory. Most importantly, they have the same TDP of about 25W (depending on configuration), but the G7 comes connected to a quad-core, eight-wire Willow Cove CPU.
However, it is true that the GeForce MX350 is an unconvincing comparison. AMD killed the MX350 with the launch of Ryzen 4000 APUs, which offer better GPU performance and fantastic CPU performance at the same price. So how does the G7 compare to AMD stuff?
Intel should theoretically win, on paper. AMD GPUs have between 384 and 512 shaders and clock speeds around the 1600 MHz mark. Intel’s Xe GPU has up to 768 shaders and a clock speed of 1,300 MHz.
In the OpenCL benchmark, the Ryzen 4600U achieves an average score of 38,000, the 4700U scores 40,100, and the 4800U scores 44,000. Even if the ~ 60,000 filtered result is a superior performance result, Intel also beats AMD here.
However, both the theoretical performance and the OpenCL benchmark are very general results. Intel has often held a lead in these categories in the past, even when AMD hardware has outperformed them in real-world tests. For now, the evidence suggests that Intel will at least be competitive, but there is no winner right now.
The elephant in the room is the CPU side of these processors. AMD seems to have a clear advantage in CPUs. Ryzen 4000 APUs have up to eight cores, while Tiger Lake has a maximum of four. Can Willow Cove compete with Zen 2 with half the number of cores?
