CPUsNews

AMD Increases Power Efficiency of Mobile Processors by 32x in Six Years

In a record-breaking feat, AMD has announced that it has has exceeded its moonshot 25×20 goal set in 2014 to improve the energy efficiency of its mobile processors 25 times by 2020. The new Renoir based Ryzen 7 4800H chip improves energy efficiency of the 2014 baseline measurement by an insane 31.7 times, making it not only faster than the competing 14nm Intel parts but a lot more power efficient as well.

The energy efficiency of a processor is determined by the amount of work performed per unit of energy consumed. The use of TSMC’s cutting edge 7nm node, along with the CCX architecture paired with the Zen 2 core architecture has enabled AMD to not only achieve the 25×20 goal, but exceed it as well.

We have always focused on energy efficiency in our processors, but in 2014 we decided to put even greater emphasis on this capability. Our engineering team rallied around the challenge and charted a path to reach our stretch goal of 25 times greater energy efficiency by 2020. We were able to far surpass our objective, achieving 31.7 times improvement leading to gaming and ultrathin laptops with unmatched performance, graphics and long battery life. I could not be prouder of our engineering and business teams.

MARK pAPERMASTER, amd cto

AMD reduced the average compute time for a given task by 80% from 2014 to 2020, while also achieving an 84% reduction in energy use. That means an enterprise that upgrades 50,000 AMD laptops from 2014 models to 2020 models would achieve five times more computing performance and reduce associated laptop energy consumption by 84%, which over a three-year service life amounts to saving approximately 1.4 million kilowatt-hours of electricity and 971,000 kg of carbon emissions, equal to 16,000 trees grown for 10 years.

Thanks to data from AnandTech, we can have a closer look at how AMD was able to achieve this feat. Starting off with the lowly Steamroller based Kaveri chip in 2014, we see that the efficiency increased by 3.5x by going to Carrizo and 3.97x to Bristol Ridge. Finally, with the first Zen based SoC, Raven Ridge, the gains started to become more substantial. The jump from Bristol to Raven pushed the efficiency figure to a whopping 8.81.

After that, the next two generations were largely stagnant as they were basically refreshes of the Zen core. Finally with the recently launch 7nm Zen 2 based Renoir parts, we saw a massive boost, allowing AMD to exceed the 25x target.

There were three primary uplifts in efficiency over the course of last six years:

  • Kaveri to Carrizo was 3.5x,
  • Bristol to Raven was 2.2x,
  • then Picasso to Renoir was 2.92x
CPUYearCB15 MC3DMark 11ComputeETECEnergyEfficiency
Kaveri201423221421.000.9311.001.00x
Carrizo201527727091.230.3270.353.50x
Bristol201627932341.360.3180.343.97x
Raven201766744252.470.2610.288.81x
Raven201875448772.760.2610.289.86x
Picasso201977251912.880.2460.2610.88x
Renoir2020172755465.020.1470.1631.77x
Courtesy: AT

The actual performance gain is pegged at around 5X with an idle efficiency of 6.33X. This results in a combined performance efficiency figure or 31.77X.

Areej

Computer Engineering dropout (3 years), writer, journalist, and amateur poet. I started Techquila while in college to address my hardware passion. Although largely successful, it suffered from many internal weaknesses. Left and now working on Hardware Times, a site purely dedicated to. Processor architectures and in-depth benchmarks. That's what we do here at Hardware Times!
Back to top button