Forgot your password?
typodupeerror

Comment: Re:Still 28nm (Score 4, Informative) 124

by edxwelch (#47954593) Attached to: NVIDIA Launches Maxwell-Based GeForce GTX 980 and GeForce GTX 970 GPUs

I doubt that.
TSMC 20nm will be ready for GPUs a lot sooner than their 16nm process. The only reason there are no 20nm GPUs yet is because the initial ramp was fully booked out by Apple.
Meanwhile, a comparison of Apple's 20nm A8 density versus 14nm Core M, indicates Intel's 14nm may not have such a density advantage as they claim: https://www.semiwiki.com/forum...

Comment: Interesting article on Semiaccurate about this (Score 5, Interesting) 110

by edxwelch (#47833567) Attached to: NVIDIA Sues Qualcomm and Samsung Seeking To Ban Import of Samsung Phones

Previously, Nvidia said that it would license it's Kepler GPU cores to third parties. Semiaccurate maintains that this licensing program was in fact bogus and was conceived purely to justify future patent trolling activities. Semiaccurate also claims that
Nvidia tried to "shakedown" Apple with the same patents and Apple subsequently gave the contract for the Mac Pro GPU to AMD as punishment.

Comment: Re:The article is bad - mfg technology dominates (Score 1) 161

by edxwelch (#47776087) Attached to: Research Shows RISC vs. CISC Doesn't Matter

From the origonal paper www.cs.wisc.edu/vertical/papers/2013/hpca13-isa-power-struggles.pdf (which ExtremeTech does not link to):

Technology scaling and projections:
Since the i7 processor is 32nm and the Cortex-A8 is 65nm, we use technology node characteristics from the 2007 ITRS tables to normalize to the 45nm technology node in two results where we factor out tech-
nology; we do not account for device type (LOP, HP, LSTP).
For our 45nm projections, the A8â(TM)s power is scaled by 0.8Ã-- and
the i7â(TM)s power by 1.3Ã--. In some results, we scale frequency
to 1 GHz, accounting for DVFS impact on voltage using the
mappings disclosed for Intel SCC [5]. When frequency scal-
ing, we assume that 20% of the i7â(TM)s power is static and does
not scale with frequency; all other cores are assumed to have
negligible static power. When frequency scaling, A8â(TM)s power is
scaled by 1.2Ã--, Atomâ(TM)s power by 0.8Ã--, and i7â(TM)s power by 0.6Ã--.
We acknowledge that this scaling introduces some error to our
technology-scaled power comparison, but feel it is a reasonable
strategy and doesnâ(TM)t affect our primary findings (see Table 4).

"I'm a mean green mother from outer space" -- Audrey II, The Little Shop of Horrors

Working...