How Today's Low-Power X86 & ARM CPUs Compare To Intel's Old NetBurst CPUs

An anonymous reader writes: In trying to offer a unique look at how Intel x86 CPU performance has evolved since their start, Phoronix celebrated their 11th birthday by comparing modern CPUs to old Socket 478 CPUs with the NetBurst Celeron and Pentium 4C on an Intel 875P+ICH5R motherboard. These old NetBurst processors were compared to modern Core and Atom processors from Haswell, Broadwell, Bay Trail and other generations. There were also some AMD CPUs and the NVIDIA Tegra K1 ARM processor. Surprisingly, in a few Linux tests the NetBurst CPUs performed better than AMD E-Series APUs and an Atom Bay Trail. However, for most workloads, the 45+ other CPUs tested ended up being multiple times faster; for the systems where the power consumption was monitored, the power efficiency was obviously multiple times better.

Comments

Not really fair

[Anonymous Coward]

NetBurst CPUs were crappy in their day too. It would be more honest to compare against the Athlon 64 or the Pentium 3.

Re:Not really fair

[hairyfeet]

Ironically that was when the first "crippled" Intel compiler came out. They didn't target AMD chips until the second release, the first release targeted the Pentium III which I would argue is the smoking gun that proves the "Intel knows how to optimize for their own chips" is total horseshit or else they wouldn't have targeted their own CPU for crippling!

If you look up the very first benches of the P IV at release? It was just getting curbstomped by Tualatin, in some areas the P III was winning by nearly 40%, it wasn't even close, then Intel releases their crippled compiler and throws money at the benchmark companies to use it and wadda ya know....the P IV is suddenly beating the exact same chips by nearly 35%! Isn't that amazing?

Everyone here cheered for the MSFT antitrust trial but if there was any company that deserved to get busted right along with MSFT it was Intel. They rigged the benches, bribed OEMs, even stole a page from MSFT's book by offering OEMs discounts and huge kickbacks as long as they only sold a limited number of low end AMD chips instead of the whole lineup. Anybody remember how hard it was to find good AMD systems on store shelves? That was why. Just imagine how much power was wasted thanks to the OEMs shoveling all those millions of power hog P4s, which is why while I have no problem selling early Athlon X2s or Core based if a Pentium D crosses my desk? Into the trash that garbage goes.

As for TFA congrats Phoronix, your site is one of the few places you can get 100% unbiased benchmarks (thanks to their using GCC instead of ICC) which is why you see results like these AMD vs Intel becnhes and wadda ya know, just by using GCC instead of ICC suddenly you have AMD A10-5800K trading blows with the I5 2400S and the FX-8350 trading blows with i5 3470, chips that cost twice as much.....wow the guys that wrote GCC must be the bestest coders on the entire planet to magically get double the performance that the mainstream benchmarks show...ya think?

Calling bullshit

[Anonymous Coward]

Every test was either multithreaded or otherwise accelerated (x264 for example). The Pentium 4 chip was one of the slower CPUs from the 130nm era (SL6WT), and Pentium 4 went into the 65nm era. 2.8 GHz versus 3.8GHz is a big handicap. 1 core versus 2+ cores is a big handicap. No built-in video card for x264 encoding is a big handicap.

Would it break the bank to provide even one non-accelerated single threaded comparison? Just one?