Posts by Jim O'Reilly

Compress, deduplicate - What price per Terabyte??

At $35 per terabyte, which is Google's price for a 2TB drive, amortized over 4 years, that works out at a drive cost of $0.75 per month.

But it's much better than that! Compression and deduplication reduce stored data size by 85 percent in a business environment, so we are down to around 10 cents cost of the drive per month.

In the consumer space, compression isn't as good, due to the large number of images stored. Deduplication across users, however, is fantastic, if implemented. Reductions of 99 percent are possible.

There are more costs than drives of course, but bottom line, these prices could still go down further!

An IBMer told me a story....

I heard from a director-level IBMer in the PC Division at the time that CPM actually was IBM's first choice, but that it was difficult working with Kildall.

He said, and I have not verified it, that they had arranged to call Kildall with a final decision to go or not, and asked he be by the phone. When they called with the good news, Gary was playing golf, and a call to the clubhouse resulted in a caddy driving the "mobile" phone out to Kildall. He was heard making a comment to "Tell those ******** I'll call them back when I finish my golf." That triggered Plan B at IBM!.

Might be true, might not. But the teller would have been on that call without question.

That could make Stephen fry close to accurate.

Contradict's your own recent article

It seems that you are contradicting your own article of a couple of weeks ago on this subject where the British Antarctic Survey found the PIG had retreated because of the loss of a submerged ridge which allowed warm water in.

Article is at http://www.theregister.co.uk/2014/01/03/antarctic_ice_shelf_melt_lowest_ever_recorded_just_not_much_affected_by_global_warming/

The irreversibility also is in question, since the thermocline has now dropped 750 ft (cold water in this area overlays warm water). This effectively blocks the warm flow, and ice is growing back rapidly. I'd note in passing that the quoted irreversibility is in fact the output of a computer model and follows the "GIGO" rule. This was in the original BBC article.

A job well done!

Thank you, Bill and Melissa!

Where is the Globe Warming?

Gosh, Lewis, when I last wrote on climate, the commentards jammed the Antarctic melt issue down my throat. You mean it's a myth, and those guys stuck in the ice aren't there because of AGW. I suppose the really nasty winters we are having are due to AGW, but I'm straining to find the connection anymore.

CNN ran "March of the Penguins" twice last night, so I'm sensing the Press is preparing us for bad news about Ice Ages. Al Gore may be the first recipient of both a Nobel and an IgNobel for the same work of fiction if this goes on!

Following the pack

In fiddling the model, Mr Stern was just following IPCC precedents. After all, the basic computer model for Global Warming has been revised downward drastically in the last few years, in part because none of the predicted warming has occurred. So just plain guessing of the model parameters by Mr Stern, with judicious insertion of biased assumptions, would be nothing new.

I suppose those sea-based wind turbines could be used to anchor cruise ships and fishing vessels

Old SIGs never die they just fade away!

Why bother? Ethernet has won!

This is a big plus for Intel, even if very belated. They are finally moving from their view that Wintel is the center of the universe to a much more sensible position. Despite the jokes about Chrometel and the rest, their direction is coming together, but they have a lot of ground to make up in some areas.

This will help enliven a computer industry that was rapidly becoming white box and commoditized. In the end, the losers are the proprietary CPU chip makers, and Microsoft.

HMC by another name!

When Intel pulled out of the Hybrid Memory Cube Consortium, the reckoning was that they intended to roll their own version, and this is it! It's probably put together with Micron as a partner, and is close to, but not exactly the same as, HMC.

The high end will be interesting. NVidia is in to HMC, AMD is likely working up the idea, too.

And the idea of memory stacking fits the mobe market as well, so ARM is in the game!.

Roll on persistent carbon nanotube memory. That will upset the applecart again!

HMC talks to Terabyte/second speeds, so it will be a big impactor on performance.

InfiniBand is not an escape route

Mellanox is trying to convert itself to an Ethernet provider with RoCE. I think the writing is on the wall for both FC and IB, as Ethernet surges, and as blockIO gives way to object access modes. Supporting object storage is the only way Brocade could move into a growth area.

IPCC doesn't help

I think Lewis hit the nail on the head. We need nuclear power, though I'd like a push for Thorium-cycle molten salt reactors, because they are cheaper, safer and create almost no long term waste. Thorium supplies run to thousands of years already, which gives us a bit of extra time to do fusion!

Of course, IPCC's fatuous insistence that we are heading toward climate disaster misses the point. We'll run out of oil and gas first. Their insistence on orthodoxy in thinking is constipating the debate. We need to talk to the fuel supply issues and not to Gaia-centric irrelevances.

I'll end with the standing disclaimer, cos I don't want to lose my grants. "Irrespective of any facts, and based on a model that is known to be totally inaccurate, Anthropogenic Global Warming will possibly happen sometime on a planet near Earth."

It's all politics

IPCC has demonstrated that it isn't really a scientific body. They are intensely partisan on AGW, cherry-pick data to support it, and have a huge reluctance, to the point of malevolence, to accept alternative data and theories.

This is the type of science where you decide waht you want to prove, then "fix" the experimental results to prove it. All it takes to understand this is to follow the money. No-one will pay for climate non-events. We need a dire prognostication to raise the cash to the current levels. This debate is all about rice-bowls, and not the ones people eat from!

Super-fast hard drive? Now that's an oxymoron!

Seagate had me cheering right up to the point where they said they are developing a new fast drive for enterprise blade servers. Despite their bluster, that market is heading to flash fast, simply because of raw performance.

A new 10K RPM drive aimed at being a market segment leader doesn't make any sense. It's like GM announcing today that they've just developed the world's biggest steam-driven truck!

Temp data is "adjusted"

It seems that there are serious aberrations caused by thermometers near cities, which report higher temperatures due to local heating from power output and more importantly the concrete surfaces. The siting of these might account for a good portion of the world-wide warming,

Older measurement sites would not be changed by citification, and many of the European sites would fall into this category. What the study is saying is that the new city sites in the developing world may be biasing the data to appear like warming.

What's wrong with the IPCC model:

Doesn't handle current hiatus in warming

Over-estimates carbon dioxide impact

Over-estimates ice melt/sea level rise

Over-estimates warming rate (by own admission)

Doesn't handle Sun variations

Period of warming used to justify story is shorter than the hiatus

The head of IPCC makes $5million per year from consulting...go figure!

Nile is two years out!

Nile is a pre-announcement. It's two years out. In that time, expect 10TB drives and perhaps more. Seagate is working on shingle and HAMR, and may have "2D" storage too. WD is working on technologies as well. Helium-filled drives may have 50% more platters, and they are looking at shingle and HAMR.

Furthermore, the Nile architecture will involve a lot of head nodes on those VNX arrays. I'm going to predict that exabyte-class systems are almost all Ethernet-accessed Object storage, with localized zones of BlockIO. They won't be jumbo SANs.

Selling noodles

HP epitomizes what happens when you just become a rice-box reseller. All the big customers buy direct, then the noodle stores open up in the US and sell to the smaller fry. Then you end up boasting about turn-rounds with software and services.

Painful, but the only way out is to figure a new architecture and make it yourself!

And the polar ice caps growing didn't help?

The two polar ice caps have shown strong growth, reversing recent trends, especially in the Arctic.

We may indeed be tipping over into a Little Ice Age, and this could account for the reversal of sea-level rise.

Blame it on the Sun, which is running cool!

Time to bring manufacturing home?

With all these negatives from Foxconn, Apple needs to work on their image -a lot!

Since Foxconn is going to roboticise away it's workforce. This might be a good time for Apple to move manufacturing back to robot factories in the US, where the higher standards will protect their name.

Maybe the Feds will give them a tax break on all that foreign cash if they do that?!!?

Let's stay scientific!

Recent reports indicate major back-pedalling on AGW by its supporters, and the predicted "ENDOFTHEWORLD" has been delayed a few centuries. Sea levels will rise inches not feet, and the computer models appear to be a little less than accurate, with nearly 20 years of predicted temperature rises missing from the world-wide actual record.

Perhaps it was those apocalyptic predictions that triggered Sen Inhofe's bible-waving rant.

Personally, I'd rather stick with facts, and even IPCC's error prone predictions beat out 4000 year old mythology any time!

No Radiation?

Since Fukushima, we've discovered that the number of deaths expected is ZERO.

Nuclear fusion is getting a lot safer, and these new designs look much better still.

We can expect the thorium cycle version of the molten salt reactor to work just as well, and we have fuel for thousands of years. No more wind power systems. Let's do this right!