Patent Troll Kills Open Source Project On Speeding Up The Computation Of Erasure Codes

from the promoting-the-progress dept

Via James Bessen, we learn of how a patent trolling operation by StreamScale has resulted in an open source project completely shutting down, despite the fact that the patent in question (US Patent 8,683,296 for an "Accelerated erasure coding system and method") is almost certainly ineligible for patent protection as an abstract idea, following the Supreme Court's Alice ruling and plenty of prior art. Erasure codes are used regularly today in cloud computing data storage and are considered to be rather important. Not surprisingly, companies and lawyers are starting to pop out of the woodwork to claim patents on key pieces. I won't pretend to understand the fundamental details of erasure codes, but the link above provides all the details. It goes through the specific claims in the patents, breaking down what they actually say (basically an erasure code on a computer using SIMD instructions), and how that's clearly an abstract idea and thus not patent-eligible. Furthermore, it details the relevant prior art:

The most prominent prior art invalidating this patent is the RAID6 (one of the most commonly used Erasure Code) implementation of the linux kernel. In an article dated 2004 (i.e. ten years before the patent was granted to StreamScale) it is described to be optimized as follows : For additional speed improvements, it is desirable to use any integer vector instruction set that happens to be available on the machine, such as MMX or SSE-2 on x86, AltiVec on PowerPC, etc. Where SSE2 is the acronym of Streaming SIMD Extensions 2. The patent cites Anvin aticle’s but only to state the problem and does not acknowledge it also contains the solution.

Even so, StreamScale apparently bullied the open source project's creator, Professor James Plank, into removing his repositories and saying he is no longer working on the software project. No lawsuit was filed, but Plank posted a statement that makes it clear he was threatened by StreamScale and agreed to do this to avoid a lawsuit. Apparently, StreamScale also threatened USENIX for merely publishing a paper by Plank detailing the concepts in his software.

After a failed attempt to bully USENIX, StreamScale  intimidated (i.e. there was no lawsuit and therefore no ruling) James Plank, a known researcher in the field, also author of widely used Free Software libraries using the same techniques as those described in the linux kernel. James Plank agreed to publish the following on his web site as part of a settlement, presumably in exchange for a promise from StreamScale to not threaten to sue him in the future.

On this page I (James Plank) am providing notice that:

• GF-Complete and Jerasure versions 2.0 and later are no longer supported.
• StreamScale, Inc. offers a similar solution for commercial purposes.
• I offer no representations or warranties in general about StreamScale’s products.
• I have verified that StreamScale’s solution is faster than GF-Complete or Jerasure in at least some respects.
• StreamScale, Inc. asserts that the use of GF-Complete (particularly as part of Jerasure 2.0 or later) or any similar software, method or code for erasure coding infringes StreamScale’s issued United States Patent No. 8,683,296.
• I express no opinion on StreamScale’s claims, but I believe that parties should be aware that StreamScale asserts such claims.

The repositories on which James Plank published the software implementing the ideas from his research papers ( gf-complete and jerasure ) have been removed the same day, meaning James Plank had to agree to never work on implementing erasure coded software in the future.

There is the only marginally complicating factor that Plank, apparently, was a consultant for StreamScale a few years ago -- leading the company to argue that his research, publications and code pulled from information he had learned while working with the company. But, again, these ideas both have clear and known prior art and do not appear to be patentable subject matter. And the end result: less ability to innovate (or even research!) these sorts of things, and some important open source code no longer being supported.

Filed Under: abstract ideas, erasure codes, james plank, patent troll, patentable subject matter, patents, prior art
Companies: streamscale