InfiniBand: a proprietary standard? [LWN.net]

Greg Kroah-Hartman recently expressed some concerns about the InfiniBand specification. It seems that, if you are not a member of the InfiniBand Trade Association, a copy of the specification will cost $9500 - and it requires signing a license which reads:

Upon receipt by IBTA of payment for a single copy license to the Specification, you are entitled to possess one physical copy of the Specification in the form provided to you by IBTA, and to make internal, noncommercial use of the Specification within your organization.

Such language raises the obvious question: how can anybody write or distribute a free InfiniBand implementation after having signed that sort of license? Things get worse when one looks at the IBTA membership agreement (PDF):

When the member or its Affiliates makes a Contribution or when the Steering Committee adopts and approves for release a Specification, the Member and its Affiliates hereby agree to grant to other members and their affiliates under reasonable terms and conditions that are demonstrably free of any unfair discrimination, a nonexclusive, nontransferable, worldwide license under its Necessary Claims to allow such Members to make, have made, use, import, offer to sell, lease, and sell and otherwise distribute Compliant Portions ....

The Member and its Affiliates retain the independent right to grant or withhold a nonexclusive license or sublicense of patents containing Necessary Claims to non-Members on such terms as the Member may determine.

(Emphasis added). The InfiniBand standard, in other words, is allowed to contain patented technology, only IBTA members must be given the opportunity to license any patented technology, and only under "reasonable terms and conditions." If said "reasonable terms and conditions" included the right to distribute code under a free license, one would assume those who wrote the agreement would have seen fit to say so.

The end result is that InfiniBand looks like a closed, proprietary standard, and not something which can be supported in free software. Greg asked, flat out:

So, OpenIB group, how to you plan to address this issue? Do you all have a position as to how you think your code base can be accepted into the main kernel tree given these recent events?

In response, there have been some "we don't think it's a problem" mumblings, but nothing that looks like a real answer to this question. Until this all gets straightened out, anybody considering using InfiniBand with free software may well want to think about alternatives.

Index entries for this article
Kernel	InfiniBand

to post comments

InfiniBand: a proprietary standard?

Posted Oct 14, 2004 21:10 UTC (Thu) by mongre26 (guest, #4224) [Link]

Time for the Infiniband group to move out of the dark ages.

The type of environments that could make the best use of Infiniband are exactly the environments most likely to use huge amounts of OSS.

Given that so many problems in that space today can be solved with standard Copper Gigabit, and that fiber 10 gigabit is continually getting cheaper I do not see how this group hopes to see IBT can see a future for their technology.

Sure, there are situations where infiniband is superior to Ethernet, but those spaces will continue to shrink, just like commodity clusters have shrunk the space of problems that absolutely need a traditional vector supercomputer.

Open, low per unit cost solutions dominate cluster computing. The IBT is unecessarily limiting themselves to niche where they could show leadership and grab hold of a market ready for higher interconnect speeds with reasonable terms.

It is a real shame when good technology has to be ignored because of archaic and narrow minded limitations of licenses prevent wide spread distribution.

The IBT would do well to change its policies to support OSS implementations of their technology, they have everything to gain and nothing to loose.

Licensing agreement?

Posted Oct 15, 2004 15:48 UTC (Fri) by joedrew (guest, #828) [Link] (1 responses)

I fail to see how the licensing agreement quoted makes anybody believe that you can't distribute or develop free software support of Infiniband. Greg K-H's messages make it a little more clear that non-members can be sued, but the article doesn't say that at all.

Licensing agreement?

Posted Oct 21, 2004 14:32 UTC (Thu) by alext (guest, #7589) [Link]

If at a later stage patents are included in the standard Free Software cannot fully implement the standard without knowingly infringing patents. Is that the problem?

Download InfiniBand specification for free

Posted Oct 26, 2004 16:11 UTC (Tue) by gbayer (subscriber, #25665) [Link] (1 responses)

Looks like the InfiniBand Trade Association reacted.

Today, I was able to download the latest version 1.2 of the InfiniBand specification here after a simple name and email registration. I did not have to sign any licence, nor did the specification itself contain anything beyond a copyright statement.

Download InfiniBand specification for free

Posted Oct 27, 2004 6:14 UTC (Wed) by Ross (guest, #4065) [Link]

That's good for the trade secret / NDA aspect but the potential patent
minefield still remains.