The Intel® Math Kernel Library (Intel® MKL) LAPACK domain provides a huge variety of routines. To see what routines are recommended for a particular use case, specify the parameters in the drop down lists below. For detailed description of a routine in the Intel MKL Developer Reference, click the routine name in the resulting list.
It is certainly provocative to say that CPUs will dominate any part of visualization - but I say it with confidence that the data supports why this is happening. The primary drivers are (1) data sizes, (2) minimizing data movement, and (3) ability to change to O(n log n) algorithms.
Finding vulnerabilities in code is part of the constant security game between attackers and defenders. An attacker only needs to find one opening to be successful, while a defender needs to search for and plug all or at least most of the holes in a system. Thus, a defender needs more effective tools than the attacker to come out ahead.