The x86 Power Myth Busted: In-Depth Clover Trail Power Analysis
by Anand Lal Shimpi on December 24, 2012 5:00 PM ESTWebXPRT
I also included Principled Technologies' new HTML5/js web test suite WebXPRT in our power analysis. Like the rest of the tests, Intel already outperforms NVIDIA here but does so with lower power consumption. A big part of the advantage continues to be lower power consumption on the GPU rail, surprisingly enough.
TouchXPRT
As our first native client test, we turned to PT's TouchXPRT 2013. As there is no "run-all" functionality in the TouchXPRT benchmark, we had to present individual power curves for each benchmark. The story told here is really more of the same. On the CPU side, Intel is able to deliver better performance at lower power consumption. On the GPU side, performance is good enough for these tasks but once again, is delivered at lower power consumption.
163 Comments
View All Comments
yyrkoon - Tuesday, December 25, 2012 - link
same OS, different HAL.Krysto - Monday, December 24, 2012 - link
Good job comparing a last-gen chip like Tegra 3 with Intel's latest Atom chip, Anand. Just because Microsoft is too slow to adopt a cutting edge ARM chip for Windows, doesn't mean Intel is now "toe to toe" with ARM.Compare Nexus 10 and iPad 4 with Clover Trail in GPU performance and price, and then let me know how it went.
croc - Monday, December 24, 2012 - link
People that tend to use terms like 'fact' also seem to be such complete tools...Barnassey - Monday, December 24, 2012 - link
My main thing is why is anand comparing a QUAD core cpu to a DUAL core With hyper-threading cpu? Of course the hyperthreading cpu will use less power.Reikon - Monday, December 24, 2012 - link
Because the dual core CPU still outperforms the quad core one?Barnassey - Monday, December 24, 2012 - link
No because the power consumption will be different. Thats the point im trying to make. Plus anand has shown hes a little biased over the years.r1cky4n - Monday, December 24, 2012 - link
a single atom core is not equivalent to a single a9 coreThe important metric is performance/watt, not watt/core
sseemaku - Tuesday, December 25, 2012 - link
So you want them to disable one of the channels in memory controller and reduce the cache size to match tegra3 for a fair comparison?tempestglen - Monday, December 24, 2012 - link
It seems that "GPU Workload" and ""Photo Enhance" CPU consumption on summary table are inconsistent with diagrams.tempestglen - Monday, December 24, 2012 - link
It also seems that Kraken test diagram of total platform power is just same as cpu only diagram. I guess anandtech posted a wrong picture.Merry Christmas!