PCHardCores: Update on Xeon W: Turbo Tables

Tuesday, 7 August 2018

Update on Xeon W: Turbo Tables

https://ift.tt/2vq08PX

Last week we published our Xeon W review - Xeon W is the new name for Intel's Xeon E3-1600 series, but effectively replaces both the E3-1600 and E3-2600 chips that were commonly used in workstations. The new Xeon W line uses Skylake-X equivalent CPUs but enables ECC support for up to 512 GB of DRAM in a system, and while it uses the same LGA2066 socket as Skylake-X, due to product segmentation, Intel requires that the processors be used in a motherboard with an enterprise-grade C422 chipset.

You can read our full review here, where we tested a high, medium, and low-end CPU from the range, as well as the two quad-core parts that are officially 'off-roadmap'. In the review we go into what exactly 'off-roadmap' means.

The Intel Xeon W Review: W-2195, W-2155, W-2123, W-2104 and W-2102 Tested

One of the questions that came out of that review were the per-core turbo values for each processor. Intel has of late had a bifurcated strategy when it comes to disclosing turbo values: on the consumer line it does not disclose any turbo values any more, except single-core turbo, and on the enterprise lines they have fortunately been forthcoming with the data when asked. Although it isn't an automatic process to get the data, we are thankful that it does turn up. The point of this article is to state we finally have the turbo values for Xeon W.

Intel's per-core turbo data for these workstation parts are split up into three sections, due to the instruction sets they have. On the 'hardest' instructions, Intel uses special turbo values for AVX-512, as due to the way these instructions are processed, more heat is generated on chip. The chip has to balance frequency and power draw, so the AVX-512 data comes in at a lower frequency in order to keep the turbo in check.

The first thing to notice with this data is that for most CPUs, when the whole CPU is using AVX-512 instructions, the frequency will drop below the base frequency. For chips like the Xeon W-2123 and W-2133, even single core loading of AVX-512 will drop the frequency below the base frequency. Intel's base frequency does two things: first, it tells you the frequency at which TDP is applicable, and second it is the guaranteed minimum frequency for regular non-AVX instructions.

Behind AVX-512 is AVX2, which is still somewhat of a strain on the processor beyond regular instructions, but not as much. Where AVX-512 requires dedicated die area for support of the vector units, AVX2 is built into the back-end of the standard core design.

For AVX2, the W-2133 and W-2123 still end up below the base frequency of the processor. But for the big ones, like the W-2195, the full 18-core loading of AVX2 is 500 MHz faster than AVX-512. This is just an indication that users that are fine-tuning code should think about how much of the AVX-512 unit they can keep fed - the AVX-512 unit despite the 500 MHz difference is expected to be faster no doubt, but a half-fed AVX-512 might get trumped by a full AVX2.

For the regular instructions, turbo goes a bit like this:

For a number of users, the key metrics here are the all-core turbos, with the 18-core part having an all-core turbo of 3.2 GHz. Interestingly the W-2155 and W-2145 sits well here: for any code that can't reliably go beyond 12-14 threads, having the higher frequency but lower core count part might actually perform better. We saw a bit of this in our review, with the variable threaded loads executing somewhat better on the W-2155 than the W-2195.

Buy Intel Xeon W-2155 on Amazon.com

We'll add this analysis to our main Xeon W review, but for those that requested the data, here it is! :)