My go to is Programming Massively Parallel Processors by Wen-Mei Hwu, excellent really approachable introduction. [0]
Amazon search brought up the following two interesting books, perhaps somebody who has browsed/read them can chime in;
1) Advanced GPU Assembly Programming: A Technical Reference for NVIDIA and AMD Architectures by Gareth Thomas.
2) Numerical Computations with GPUs edited by Volodymyr Kindratenko.