The Sunway TaihuLight became, as of June 2016, the fastest supercomputer in the world. At this time, the Top 500 ranking was rearranged to put this computer ahead of TianHe-2 (also from China). Sunway TaihuLight clocked in at 93 petaflop/sec (93,000,000,000,000,000 floating point operations per second) using its 10 million cores This performance compares with the 34 petaflop/sec for the 3 million core TianHe-2. An exascale computer would have a performance of 1000 petaflops/sec.
What is maybe even more important, is that the new machine uses 14% less power than TianHe-2 (it uses a mere 15.3 MW), which makes it more than three times as efficient.
As IEEE Spectrum reports, “TaihuLight uses DDR3, an older, slower memory, to save on power“. Furthermore, it tries to use small amounts of local memory near each core instead of a more traditional (and power demanding) memory hierarchy. Other architectural choices aimed at reducing the power while preserving the performance.
It is interesting to compare the power efficiency of this supercomputer with that of the human brain. Imagine that this supercomputer is used to simulate a full human brain (with its 86 billion neurons), using a standard neuron simulator package, such as NEURON.
Using some reasonable assumptions, it is possible to estimate that such a simulation would proceed at a speed about 3 million times slower than real time, and would require about three trillion times more energy than the human brain, to perform equivalent calculations. In terms of speed and power efficiency, it is still hard to compete with the 20W human brain.