Monday, September 23, 2013

Book Review: Turing's Cathedral

Recently, I read the work of history, Turing's Cathedral: The Origins of the Digital Universe (Vintage), which is an interesting book that tells of the development of some of the first computers in the United States.  It's particular focus is on the founding of the Institute for Advanced Study (IAS), and then John von Neumann's time there.  Now, the von Neumann architecture is something I regularly conceptualize and use in teaching.  And it was interesting to read of how this architectural model was developed, and why.

In contrast, a significant portion of the book was instead written as a history of the Institute.  Given that the Institute provided access to the records used as a significant part of the source material, it is understandable that the author's focus would be so directed.  However, it adds to the misleading focus that this work follows.

Of perhaps greater slight is that a work titled "Turing's Cathedral" only features Alan Turing for a small part of the writing.  Instead we find greater focus placed on his work and how it fit into the research of that time.  Eventually leading von Neumann to explore the usage of electronic digital computers to solve the US military's problems.  He, like many European scientists, had left his homeland ahead of Hitler, and these scientists supported work leading to Germany's defeat.

The grand development that von Neumann introduced was making a computer, programmable. Beyond just reconfigurable, the project he lead at the IAS was programmable, the electronic device could store both data as well as codes that were instructions for what the device was to do.  Consider that for the next 50 years, programs would be constrained by having to store the instructions in memory, which was often a very limited resource.

So John von Neumann stars in a book titled for Turing, and a book that devotes a third of its pages to references.  A good, interesting work that could probably have been improved by an editor's scissors.  To trim the writing down to the core bits about computers, and set aside so much of the well researched chapters to attain a focus that is lacking.