Parallelize a C code for 6 processors

Protein Shapes Knowing the shapes of proteins is of primordial importance in understanding their biological functions. "Protein Folding" is the problem of modeling proteins in order to predict their native shapes. It is a very difficult problem that still escapes the best approaches. One such approach is to represent the amino-acids as "beads" in a chain and to allow the beads of the chain to occupy the intersections on a square lattice. In this model one first finds all the unique shapes of a protein of a given number of beads on a lattice. The model can be further simplified by assuming only two types of amino-acids, hydrophobic, H, and polar, P. The interaction between the amino-acids are assumed to be of contact (short-range) types. The energy of a given protein shape is therefore given by the number of contact interactions. The native state is then obtained by applying Statistical Physics arguments to find the most favored states. The code protein.c solves the first part of the problem, i.e., finds the unique shapes of a protein with a given number of beads constrained to have a given number of contacts between beads and with an arbitrary distribution of H and P amino-acids. The code protein.c finds the unique shapes of the bead chain on the lattice with a given number of contacts populates the chain with H and P amino-acids The code uses a recursive approach to find the shapes. It stores the unique shapes in a linked list. It populates the H and P amino-acids via a recursive routine and store these in a separate linked list. The code "draws" the shapes in strings and print these via simple printf() statements.. The code is built via gcc protein.c -lm -o protein Please take a look at the source code to understand the argument list. ## Deliverables I have the code, is nice, works, ut I don't know how to: Write a parallel version of the serial code (in MPI - MPI provides an automated environment to build a virtual parallel machine, launch an executable on a specified number of nodes, and to supervise all management and communication tasks for the diverse processes.) Explain the advantage of the parallel algorithm you have chosen to implement Study the scalability of the code as a function of the number of processors ## Platform LINUX This program must work on a cluster of 32 nodes. It consisted of dual motherboard with (32x2) PIII 450mhz processing elements onboard. The main console has 2 SMC 10/100 fast ethernet cards connected to the nodes by 3COM switches. The switches have become necessary due to the high volume of network traffic brought about by node-to-node communication.