It was a big focus of the Mach kernel in the early 90s. It was a microkernel, meaning that they moved as much functionality as possible out of the kernel and into user processes. For example, to access the file system each call (open, read, write) was really a message to a file system server process. So IPC performance mattered a lot.
Here's an example some heroic attempts to make it fast, getting down to about 50 uS on a 1991 CPU: http://homes.cs.washington.edu/~bershad/Papers/p175-bershad....