As others have said, we can no longer effectively cool CPUs if we were to push the voltage required for the same relative clock rate increases in the past. There was a time (P4 era and prior) when you could purchase a new CPU and see an "immediate" gain is speed because the clock rate was significantly increased compared to the previous generation. Now we have hit a thermal wall, of sorts.
Each new modern generation of processors is very slightly increasing in clock rate, but this is also relative to the ability to cool them appropriately. Chip makers, such as Intel, are continually focusing on shrinking the die size of the CPU to both make them more power efficient and produce less heat at the same clocks. As a side note, this shrinking die size makes these makes modern processors more prone to die from over-volting rather than overheating. This means that it is also limiting the ceiling clock rate of any current generation CPU without other optimizations made by the chip maker.
Another area that is being heavily focused on by chip makers is increasing the number of cores on chip. This does factor into significant increases in computational power, but only when using software that takes advantage of multiple cores. Note the difference between computational power and speed here. Simply put, speed refers to how quickly a computer can execute a single instruction, whereas computational power refers to how many computations a computer can make in a given amount of time. Modern day operation systems, and much modern software does take advantage of multiple cores. The problem is that concurrent/parallel programming is more difficult than the standard, linear programming paradigm. This increased the time it took for many programs on the market to take full advantage of these newer processors power because many developers were not used to writing programs this way. There are still some programs on the market today (either modern or legacy) that do not take advantage of multiple cores or multi-threading. The encryption program that you cited is one such example.
These two areas of focus by chip makers are intrinsically connected. By reducing both the die size and power consumption of a chip, they are then able to increase the number of cores on said chip. Eventually though, this too will hit a wall, causing another, more drastic, paradigm shift.
The reason for this paradigm shift is due to us coming close to the limits of silicon as a base material for chip production. This is something that Intel and others have been working on solving for some time. Intel has stated that it has an alternative to silicon in the works, and we will likely start seeing it sometime after 2017. In addition to this new material, Intel is also looking into 3D transistors that could "effectively triple the processing power". Here is an article mentioning both of these ideas: http://apcmag.com/intel-looks-beyond-silicon-for-processors-past-2017.htm