7 Compare with parallel implementation rather than best serial | 11 Show Pretty Pictures | 21 We'll demonstrate that it works next year | 14 We've never had parallel systems before | 15 Programmers are lazy |
20 Our ideas are so revolutionary, we can't even simulate them | 3 Scale up the problem size | 12 AI | 0 Quote 32-bit as 64 | 2 Compare assembly to Fortran or C |
18 This new architecture will fix everything | 8 Quote processor utilization | FREE | 9 Mutilate the algorithm to match the architecture | 24 We don't have any other choice |
23 Everyone will encode video 24 hours a day | 16 The previous generation didn't know about Moore's Law | 22 All computing tasks are just like ray tracing | 6 Compare with old, obsolete system | 5 Compare to scalar unoptimized Cray |
1 Inner kernel, not the system | 19 This new programming language will fix everything | 17 Transistors are free | 4 Project linearly | 13 Universities don't teach parallel programming |
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: