There seems to be no limit to the complexity of computations that genetic linkage analysts want to do. Two primary factors that increase the length of computations are pedigree loops and unknown genotypes. I describe the implementation in FASTLINK of some algorithmic improvements to partly address the problems of pedigree loops and unknown genotypes. LINKAGE is by far the most popular software package to do lod score computations on disease pedigrees. FASTLINK is derived from LINKAGE 5.1 and compatible with it. In contrast to LINKAGE, FASTLINK has the virtues that it is faster sequentially, runs well in parallel, is more robust against errors, and includes substantial new documentation. One of the new improvements allows the detection of violation of mendelian rules of inheritance in input pedigree files with loops. This error-detection capability was not provided in any previous version of LINKAGE or FASTLINK.