Unpacking AMD Zen Faster than intel Broadwell Processor

0 223

AMD Zen Faster than intel Broadwell Processor

AMD Zen Faster than intel Broadwell Processor: Last week, AMD revealed about their new upcoming Zen microarchitecture at a satellite event to Intel’s Developer Conference. This was proposed to be a review of tomorrow’s Hot Chips presentation, and we’ve already enclosed the juicier parts of the presentation as far as microarchitecture declarations and also jumping profound into the Server-based Naples usage and what the motherboards let us know from memory and IO support.

As part of the show, AMD compared the performance of their Zen engineering sample to an Intel Broadwell-E processor. This test was about to tell the audience that each system was running eight cores, sixteen threads, and will all cores set to 3 GHz (implying no turbo).

Except disclosing about Memory arrangements and storage audience was told to assume comparable setups. The test was to render using Blender (an open source rendering engine, with a custom multithreaded workload) a mockup of a Zen based desktop CPU, with an effective workload of 50 seconds for these chips. The overall results were

  Blender Time to Render / sec
Intel Broadwell-E
Core i7-6900K
8C / 16T
3 GHz all-core
49.05
AMD ZEN
Engineering Sample
8C / 16T
3 GHz all-core
48.07
(-0.98 sec, 1.998%)

 

This would suggest that an 8-core AMD has a ~2% advantage over Broadwell-E at the same clock speeds. Despite this result, there are a lot of unverifiable parts to the claim which makes an analysis of such a result difficult.

Let us see in order what was presented:

The string of limitation for this benchmark test is fairly long because AMD is vigilant in their words AMD has to set expectations here: if they choose an environment and test that represents the peak, or relies on something special, users will feel burned again. AMD has to temper those expectations but still represent a methodology that is effective to them.

Along with the microarchitecture discussions, it was designed to provide a good stepping stone on to the Hot Chips presentation a few days later.Admonitions are in this way. On the other hand disclaimers not promptly gave. Let’s see from the top:

As expected, the outcomes are not remotely verifiable right now. We were told the setups of the systems being used but were unable to confirm the results manually. This is typically the case with a high level, an early look at performance and other companies do this all the time.

  • Blender Is an Open Source Platform. It can be hard to precisely decide the code base for this test, and is generally difficult to decide the code base of Blender that was accumulated for this test.It also doesn’t help that Blender has elements in the code called ‘AMD’, which relates to a series of internal rendering features not related to the company.
  • The Workload Is Custom. Rendering one scene in a film can take a vastly diverse time to another, yet the results for the ‘benchmark’ are altogether different relying on the architecture (one prefers lighting, another prefers tessellation etc.)
  • Because they are pitching their expectations exactly where they want people to think.
  • AMD has expressed that power utilization and efficiency was an ahead goal as this microarchitecture was created. At the demonstration, we were informed that the frequency of the engineering tests was set at 3 GHz for all center operation. We were told explicitly that these are not the final clock speeds, but it at the very least it puts the lower bound on the highest end processor. We are under the impression that the CPUs will have turbo modes involved, and those could be staggered based on the cores being used.

Also Read: Intel Broadwell-E Core i7-6950X first 10-core desktop processor for consumer

AMD has already stated that general availability for Zen and Summit Ridge will be Q1, which puts the launch at four months away at a minimum. At this stage of the game, while AMD is trying to be competitive with Intel, they don’t want to generate too much hype and give the game away in case it goes incredibly pear-shaped. There’s the added element of the hardware and software being finalized or updated.

Summarizing all just like IQ test, CPU performing a Blender test is only as good as a Blender test, but given what we know about the Zen microarchitecture, it is probably also good at other things. At which level it is righteousness is difficult to say.  AMD has given a look at its performance, and they’ve just said as much as they expected to keep in mind the end goal to get the message over. Nonetheless, it has been up to the media to comprehend the reasons why and clarify what those provisos are.

Comments

comments

Leave A Reply

Your email address will not be published.