Intel Nehalem vs. Ice Lake Benchmarks - Including Clock + Power + Thermal Metrics

Written by Michael Larabel in Computers on 27 November 2019 at 03:47 PM EST. Page 1 of 9. 21 Comments.

As part of the exciting benchmark week and our ongoing tests of Intel Ice Lake on Linux, this next piece has been driven out of curiosity... While recently I posted new benchmark results of Intel Haswell to Ice Lake laptop performance, what about going further back like to the days of Nehalem? Here is that comparison of Core i7 Nehalem to Core i7 Ice Lake including power / performance-per-Watt data, thermal, and performance-per-MHz data too. Enjoy this fun comparison for how the Intel mobile performance on Ubuntu has evolved over the past decade.

The Nehalem part used is the ten-year-old Core i7 720QM "Clarksfield" processor. This CPU offers four cores / eight threads, 1.6GHz base frequency, 2.8GHz turbo frequency, a 6MB cache, and a 45 Watt TDP. Clarksfield is the mobile variants while Lynnfield made up the desktop side for the 45nm Nehalem microarchitecture.

In comparison, the Core i7 1065G7 Ice Lake part has the same four cores / eight threads but with a 1.3GHz base frequency and 3.9GHz turbo frequency, 8MB cache, and all with a 15 Watt TDP. That's also in addition to other advantages like a 2.5 vs. 4 GT/s bus speed, DDR3 vs. DDR4/LPDDR4 memory, AVX2 + AVX-512 support and other instruction set extensions like AES-NI, and the Ice Lake part featuring Gen11 Iris Plus Graphics.

The Core i7 720QM was tested within a Lenovo ThinkPad W510 bearing 4GB of RAM, 160GB Fujitsu HDD, and NVIDIA NVA5 graphics. The Core i7 1065G7 was within the Dell XPS 7390 with 16GB of RAM, 512GB Toshiba NVMe SSD, and Intel Iris Plus graphics.

Both notebooks were tested on Ubuntu 19.10 x86_64 while running with the Linux 5.3 kernel. Via the Phoronix Test Suite a wide range of CPU/system benchmarks were carried out followed by tests after switching over to battery power for looking at the power consumption and performance-per-Watt plus CPU thermal metrics followed by doing some performance-per-clock metrics too.


Related Articles