LONDON – Intel's Z2580 application processor, which was codenamed as CloverTrail prior to launch, outperformed competitors' processors in a benchmarking exercise, according to Allied Business Intelligence Inc., which trades as ABI Research.
ABI Research concluded that Intel Corp. (Santa Clara, Calif.) has succeeded in reducing significantly the power consumption of its smartphone application processor and it now rivals and is often lower than equivalents based on the ARM architecture licensed from ARM Holdings plc (Cambridge, England).
Since high-end smartphones require this level of performance ABI said it considers Intel is "well positioned for strong growth over the next few years."
The benchmarks were done by comparing the performance of the Lenovo K900 smartphone, powered by Intel's Z2580 application processor and supporting XMM6360 chipset, with a series of Samsung smartphones that are based on ARM-based application processors from Nvidia, Qualcomm and Samsung.
"The benchmarks were impressive but the real surprise was the current consumption recorded during the benchmarks; the new processor not only outperformed the competition in performance but it did so with up to half the current drain," said Jim Mielke, vice president of engineering at ABI research, in a statement.
"Intel did significant work to bring the current drain down on their well-recognized high-performance processors but the competitors did not help themselves. The ARM architecture used by nearly all of Intel's competitors is well known for its low power performance but in bringing the processing power up closer to PC levels, the current drain has taken a significant hit," Mielke added. He continued: "Combining the high-end modems – the XMM6360 is used in both the Lenovo K900 and the Samsung Galaxy S4 i9500 – with their application processors for high- to mid-tier solutions and single-chip EDGE chips for low-cost phones makes Intel a rare full portfolio provider."
Details of the results are included in the table below.
Click on image to enlarge.
Comparison of mobile phone performance. Source: ABI Research
The geekbench scores are not that accurate in projecting performance for Atom devices. If you look up the scores for the Motorola Razor I and Razor M, they will show a large performance gap favoring the Razor M. Actual comparisons of the phones showed the Razor I was as fast if not faster while using 15 percent less energy.
The AnTuTu bench showed near equal performance
Unfortunately most of the popular benchmarks for mobiles are rubbish - including AnTuTu.
Based on my experience with benchmarking I'd say the scores in your link are not at all an accurate representation of actual CPU performance. If the source code was available I could explain why.
Besides SPEC, reasonably good CPU benchmarks are Geekbench and Phoronix with results available for a wide range of CPUs - not just mobiles.
Because I can show independent benchmarks between S4 and K900 that prove my point:
Also if you understand microarchitectures then you'd be very very sceptical of any claims that a 2-way in-order CPU outperforms a 3-way out-of-order one, especially when it is 2 vs 4 cores as well...
David Patterson, known for his pioneering research that led to RAID, clusters and more, is part of a team at UC Berkeley that recently made its RISC-V processor architecture an open source hardware offering. We talk with Patterson and one of his colleagues behind the effort about the opportunities they see, what new kinds of designs they hope to enable and what it means for today’s commercial processor giants such as Intel, ARM and Imagination Technologies.