The answer: Combination of upcoming massive jump in CPU FP peak performance, and maturing of the add-on accelerators, are what should enable us to see the world's first 100 PFLOP supercomputers some two years from now, and a further 10 times speedup not much more than two years after that.
On the CPU front, from Haswell generation onwards, all Intel CPUs will incorporate fused multiply add (FMA) instructions, allowing for up to 16 double precision on 32 single precision FP ops per core per cycle. On a, say, 10 core Haswell-EP Xeon (or similar Core iXX desktop variant) at 3.2 GHz, that would give you 500 GFLOPs in double precision, or whole round 1 TFLOPs in single precision FP peak performance. Haswell EP processors should be available by early 2014.
1 exaflop supercomputers by 2017?
Posted on Friday, May 25 2012 @ 18:46 CEST by Thomas De Maesschalck
VR Zone reports the first supercomputer with 100 petaflops of computing power may arrive in 2014, and that a further tenfold speedup could arrive by 2017. Full details over here.