argyros@csi.forth.gr (Argyros Antonis) (02/21/91)
I am trying to run some parallel programs for vision applications on an INTEL's iPSC/2 hypercube machine. My problem is that the machine refuses to cooperate in floating point arithmetic. Every time I try to do an operation as simple as x = y+z between doubles or floats the program terminates with a floating point exception! The programming language is C. Does anybody ever had such a problem? If yes how this problem can be solved? Thanks in advance for any help, Antonis Argyros - University of Crete, Greece. PS : Please forward any hint to: argyros@csi.forth.gr