6 Compare with old, obsolete system | 13 Universities don't teach parallel programming | 0 Quote 32-bit as 64 | 22 All computing tasks are just like ray tracing | 8 Quote processor utilization |
16 The previous generation didn't know about Moore's Law | 14 We've never had parallel systems before | 15 Programmers are lazy | 17 Transistors are free | 18 This new architecture will fix everything |
5 Compare to scalar unoptimized Cray | 12 AI | FREE | 23 Everyone will encode video 24 hours a day | 19 This new programming language will fix everything |
9 Mutilate the algorithm to match the architecture | 2 Compare assembly to Fortran or C | 24 We don't have any other choice | 7 Compare with parallel implementation rather than best serial | 10 Compare dedicated system to multi-user |
1 Inner kernel, not the system | 20 Our ideas are so revolutionary, we can't even simulate them | 21 We'll demonstrate that it works next year | 11 Show Pretty Pictures | 4 Project linearly |
With the end of clock rate scaling, there's been a mad dash towards
multi-core architectures. While not widely known, there has in fact
been prior attempts to use parallel computing. Things have not necessarily
gone well.
To make the impending disaster more entertaining, we can play Parallel
Computing Bingo while listening to technical talks and keynotes; this
is a game similar to WWDC Bingo.
On the bingo card are twelve classic observations from a 1991 paper by
David Blyler, highlighting ways in which the performance of parallel
computers were completely misrepresented. Many of these are alive and
well, and appear on a regular basis. The second set of twelve are the
result of a highly scientific study performed at the 2008 IEEE DATC Electronic
Design Processes workshop. Together, with a center "free" cell, they make
a bingo card that can be played at conferences around the world. Individual
bingo cards can be downloaded from the EDP web site.
For more information about the original 12, please refer to: