Gateswong

# README:
# Copy this file to /usr/lib/systemd/system/
# sudo systemctl daemon-reload
# systemctl enable ipython-notebook 
# systemctl start ipython-notebook
# The WorkingDirectory and ipython-dir must exist
# If you don't want anything fancy, go to http://127.0.0.1:8888 to see your notebook
# wheneber you want it

[Unit]

Gateswong

// =========================================================
//     FSM
// =========================================================

FSM_NULL = 0
FSM_LOGIN_SCREEN = 1
FSM_CHAR_SELECT = 2
FSM_CHAR_CREATE = 3
FSM_LOADING = 4
FSM_NEW_CHAR = 5

Gateswong

// =========================================================
//     FSM
// =========================================================

FSM_NULL = 0
FSM_LOGIN_SCREEN = 1
FSM_CHAR_SELECT = 2
FSM_CHAR_CREATE = 3
FSM_LOADING = 4
FSM_NEW_CHAR = 5

Gateswong

// =====================================================
//     GLOBAL VARIABLES
// =====================================================

// misc

Dim CURSOR_LOOT, LOOT_X, LOOT_Y, SCREEN_WIDTH, SCREEN_HEIGHT

CURSOR_LOOT = 1434778618
LOOT_X = -1

Gateswong

// =================================================
// ¶¨ÒåÔ¤Éè°´¼ü
// =================================================

Dim KEY_OPEN_BAG
Dim KEY_MOUNT
Dim KEY_TARGET_VENDOR
Dim KEY_INTERACT_TARGET

KEY_OPEN_BAG = "1"

Gateswong

#include "MPI.h"	// 扣分点！

float a[200][200], b[200][200], PROD = 1;
int myrank, numproc;

MPI_Init();
MPI_Comm_rank(MPI_COMM_WORLD, &myrank);
MPI_Comm_size(MPI_COMM_WORLD, &numproc);

// MPI-Scatter

Gateswong

// ### Send and Receive
int MPI_Send(void *buf, int count, MPI_Datatype datatype, 
		int dest, int tag, MPI_Comm comm);
		
int MPI_Recv(void *buf, int count, MPI_Datatype datatype, 
		int source, int tag, MPI_Comm comm, MPI_Status *status);

// ### Size and Rank
int MPI_Comm_size(MPI_Comm comm, int *size);
int MPI_Comm_rank(MPI_Comm comm, int *rank);

Gateswong

Gauss Elimination

First let's make some assumptions:

one base op (+, *, -, /) takes 1 unit of time
hypercube SF (ts, tw)
    

Gateswong

HPF Data Mapping

Two-phase data mapping: ALIGN, DISTRUBUTE

Goals

Avoid contention: for rows data, the can be updated in parallel.

Locality of reference: two data always works on the same instructor.

Gateswong

#include <mpi.h>

main() {
    int my_rank, num_proc;
    int a, b, i;        // it depends
    
    
}