Pushing atoms versus pushing bits

Cloud computing is driving a disruptive change through a number of market places. It started long before virtualization, but virtualization really enabled much of what we have now.
Remember, at the end of the day, the entire process is economic in nature. Cost per cycle does matter.
When a vendor sells hardware, they are selling all the cycles of that hardware over the usable lifetime of the hardware. They push the atoms at the customer, and let the customer manage the economics of utilization.
When a vendor sells cycles, they are selling what is used. Nothing more. They push bits at the customer, and manage the economics of utilization, without handing this over to the customer.
There are two diametrically opposite views of this. First, if you will have a very high utilization rate for your system(s), then the better cost option is an acquisition of atoms, as the cost per cycle used will be extremely low relative to the cost of buying the same cycles.
The crossover point varies, but we’ve found it to be between 1/10th and 1/5th utilization. So if you use your systems less than say 1/5th the time, it might be more economical for you to buy the cycles and ignore the machines.
Which is having an impact in the market.
Call this a no good deed goes unpunished type moment. Well, no, thats not correct. This is more along the lines of mourning the loss of buggy whips as horse drawn carriages gave way to automobiles.
Basically, computer resellers are discovering that they are have a much harder time … selling.

The cloud-computing boom is bad news for channel organizations, according to analyst firm Frost & Sullivan.
At a media trends briefing in Sydney yesterday, the analyst Arun Chandrasekaran said cloud computing squeezed resellers from both ends: software vendors offering SaaS cut into boxed application sales, while the concentration of compute power into the cloud cuts out the local hardware channel.

Yes, thats right. Buy cloud computing and you’ll put a small company out of business.
Or something like this.
What we see is a more pronounced tendency for vendors to compete with their channels, which results in a channel less interested in selling their gear. And Cloud computing, with the inroads its making into SME and related … yeah, we do see this as being potentially profoundly impactful in the HPC space.
A while ago, we talked about a bi/tri-furcation of the market. End users would love to spend less per cycle, and accelerators let them do that. Also less for power, etc. And they want a seamless push of applications to the occasional large run in many use cases we see. Which involves fast desktops, and big fast remote clusters paid for by the cycle. For occasional use, this model works very well.
The model that has been in place for a long while have been resellers pushing vendor product to a larger customer base. This provided a magnification effect for the vendor, they didn’t need to hire as large an expensive sales force. And they got sales for a price.
Now, the cost of sales has been driven into the ground. Swipe your own credit card. Get your systems right away. Its a no-brainer. It pulls cost out of the system.
And this directly impacts the ability of a sales team to sell product, as you have to compete with a much lower cost mechanism.

With their logistical role (forgive the pun) under a cloud, channel organizations will have little choice but to save what they can and run like hell learn to pitch their service offerings more widely and aggressively.
The loss of revenue is most likely to bite as cloud services take hold among SMEs, Chandrasekaran said. ?For enterprises, systems integrators can do the value add work of integration and security.? SMEs, on the other hand, are more likely to buy and use cloud services ?as is?, with less integration.

Yup. There is some specialist value in the HPC side, but the rest of the folks? They are gonna have more issues over time. Not that HPC won’t, but the issues will be somewhat different.

1 thought on “Pushing atoms versus pushing bits”

  1. Hmmm. Cloud today is kinda at the same level of maturity as Windows 1.0 was. Our current expectations are different and much higher because we’ve experienced a hardware and software revolution on our desktops, so that Windows 1.0 experience isn’t as amazing as we’d like. As the Cloud matures and improves and more services are offered there’s going to be more hardware sold (remember that there’s only a global market for five computers…). “OK, who will get to sell the hardware?” is a fair question, smaller channels can’t always deliver the scale-out volumes that a new Cloud installation might require, and those server atoms aren’t the same as desktop atoms. Longer-term it might look like the Utility model, everything so standardised that cycles can be sold like electricity.
    Your crossover point analysis is really on the mark for HPC though. If HPC can grow enough and become mainstream, maybe that crossover point remains the same and that hardware market grows. Should be good for those small vendors with really good storage performance/$…

Comments are closed.