def _PUTS():
"""output a word string"""
i = reg_read(Registers.R0)
ch = mem_read(i)
while chr(
ch) != '\0': # check if the char is not null then print this char
sys.stdout.write(ch)
i += 1
ch = mem_read(i)
sys.stdout.flush() # equal to fflush() in c
def _LDI(instruction):
# Destenation Register.
DR = (instruction >> 9) & 0x7
# the value of what called an offset (embedded within the instruction code).
PCoffset = sign_extend(instruction & 0X1ff, 9)
# the address of the address of the desired data.
address = reg_read(Registers.PC) + PCoffset
# write the data (its address is explained in the previous line) in the register (DR).
reg_write(DR, mem_read(mem_read(address)))
# store the sign of the last excuted instruction data (which is in the DR).
update_flags(DR)
def _PUTS():
"""output a word string"""
for i in range(reg_read(Registers.R0), 2**16):
ch = mem_read(i)
if ch == 0: # check if the char is not null then print this char
break
sys.stdout.write(chr(ch))
sys.stdout.flush() # equal to fflush() in c
def _STI(instruction):
# Source Register (the register containing the data).
SR = (instruction >> 9) & 0x7
# the value of what called an offset (embedded within the instruction code).
PCoffset = sign_extend(instruction & 0x1ff, 9)
# the address of the address that the data will be stored at.
address = reg_read(Registers.PC) + PCoffset
# write the data (stored in the SR) into the memory (the address is explained in the previous line).
mem_write(mem_read(address), reg_read(SR))
def _PUTSP():
"""output a byte string"""
for i in range(reg_read(Registers.R0), 2**16):
c = mem_read(i)
if c == 0:
break
sys.stdout.write(chr(c & 0xFF))
char = c >> 8
if char:
sys.stdout.write(chr(char))
sys.stdout.flush()
def _PUTSP():
"""output a byte string"""
for i in range(Registers.R0, (2**16)):
c = mem_read(ushort(i))
if chr(c) == '\0':
break
sys.stdout.write(chr(c & 0xFF))
char = c >> 8
if char:
sys.stdout.write(chr(char))
sys.stdout.flush()
def main():
reg_write(Registers.PC, PC_START)
rom = read_Rom_file(input('Enter filename: '))
load_image(rom)
try:
while True:
pc = reg_read(Registers.PC)
instruction = mem_read(pc)
execute(instruction)
except Halt: # TODO
print('Halted.')
def _LDR(instruction):
"""load register"""
# compute the index of distination register
dis_reg = (instruction >> 9) & 0x0007
# compute the index of BaseR register
BaseR = (instruction >> 6) & 0x0007
# compute and extention offset6 value
offset6 = sign_extend(instruction & 0x003F, 6)
# compute memory addresse
mem_addresse = reg_read(BaseR) + offset6
# read the memory storage value
value = mem_read(mem_addresse)
# write value to distination register
reg_write(dis_reg, value)
# update flags
update_flags(dis_reg)
def main():
if len(sys.argv) < 2:
print('Usage: python3 lc3.py [obj-file]')
exit(2)
reg_write(Registers.PC, PC_START)
read_Rom_file(sys.argv[1])
try:
while True:
pc = reg_read(Registers.PC)
instruction = mem_read(pc)
# increment PC by #1.
reg_write(Registers.PC, reg_read(Registers.PC) + 1)
execute(instruction)
except Halt: # TODO
print('Halted.')
def _LD(instruction):
"""load"""
DR = (instruction >> 9) & 0x7
pc_offset = sign_extend(instruction & 0x1ff, 9)
reg_write(DR, mem_read(reg_read(Registers.PC) + pc_offset))
update_flags(DR)
def _OUT():
"""output a character"""
sys.stdout.write(chr(mem_read(reg_read(Registers.R0))))
sys.stdout.flush()
def process_step(self, external_input, memory, read_vectors,
previous_weights):
"""
NTM.process(external_input, read_vector, previous_weights) -> new_memory, new_read_vectors, new_weights, output
the main method of this entire program. Processes the data with a NTM.
@param external_input: a batchsize x input_size matrix that represents the data for this timestep
@param memory: a batchsize x N x M memory 3-tensor from the previous timestep
@param read_vector: a self.read_heads x batchsize x N 3-tensor that represents all of the read vectors produced by read heads
@param previous_weights: a 1 + self.read_heads x batchsize x M 3-tensor that represents all of the weightings produced by all heads in the previous timestep
"""
# concatenated_read_vector -> batchsize x self.slot_size * read_vector
concatenated_read_vector = T.concatenate(
[read_vectors[head] for head in range(len(self.read_heads))],
axis=1)
# concatenated_input -> batchsize x self.slot_size * read_vector + external_input_length
concatenated_input = T.concatenate(
[concatenated_read_vector, external_input], axis=1)
# controller_output -> batchsize x self.controller_size
controller_output = T.nnet.relu(
self.controller.forward(concatenated_input))
# Represents NTM's actual output for this timestep
# ntm_output -> batchsize x self.output_size
ntm_output = T.dot(controller_output, self.output_weight)
# let's get reading out of the way first
for head in range(len(self.read_heads)):
key, shift, sharpen, strengthen, interpolation = self.read_heads[
head].produce(controller_output)
# preprocess the values in preparation for mem_focus
# key -> batchsize x 1 x N
# strengthen -> batchsize x 1 (already good)
key = key.dimshuffle([0, 'x', 1])
# Focus by content + strengthen
# preliminary_weight -> batchsize x M
preliminary_weight = mem_focus(memory, key, strengthen)
# Focus by location
interpolated_weight = interpolation * preliminary_weight + (
1 - interpolation) * previous_weights[head]
# Shift
# Both arguments are batchsize x M, first being weighting, second being shift
shifted_weight = focus_shift(interpolated_weight, shift,
self.memory_slots)
# Sharpen
# We added broadcasted the second axis of sharpen, remember? :))))))))))))))))))))))))))
# sharpened_weight -> batchsize x M
sharpened_weight = shifted_weight**sharpen
# Normalize
# T.sum(...) -> batchsize x 1
final_weight = sharpened_weight / (T.sum(
sharpened_weight, axis=1, keepdims=True) + SMALL_CONSTANT)
# read, read, read!
# read_vec -> batchsize x N x 1, so we gotta flatten to batchsize x N
read_vec = mem_read(memory, final_weight)
read_vectors = T.set_subtensor(read_vectors[head],
T.flatten(read_vec, outdim=2))
previous_weights = T.set_subtensor(previous_weights[head],
final_weight)
# let's write now!
key, add, erase, shift, sharpen, strengthen, interpolation = self.write_head.produce(
controller_output)
# preprocess the values in preparation for mem_focus
# key -> batchsize x 1 x N
# strengthen -> batchsize x 1 (already_good)
key = key.dimshuffle([0, 'x', 1])
# Focus by content + strengthen
# preliminary_weight -> batchsize x M
preliminary_weight = mem_focus(memory, key, strengthen)
# Focus by location
interpolated_weight = interpolation * preliminary_weight + (
1 - interpolation) * previous_weights[-1]
# Shift
shifted_weight = focus_shift(interpolated_weight, shift,
self.memory_slots)
# Sharpen
sharpened_weight = shifted_weight**sharpen
# Normalize
# T.sum(...) -> batchsize x 1
final_weight = sharpened_weight / (
T.sum(sharpened_weight, axis=1, keepdims=True) + SMALL_CONSTANT)
previous_weights = T.set_subtensor(previous_weights[-1], final_weight)
# preprocess the values in preparation for mem_write
# weighting -> batchsize x 1 x M
# erase_vector -> batchsize x N x 1
# add_vector -> batchsize x N x 1
final_weight = final_weight.dimshuffle([0, 'x', 1])
erase = erase.dimshuffle([0, 1, 'x'])
add = add.dimshuffle([0, 1, 'x'])
new_memory = mem_write(memory, final_weight, erase, add)
# phew, almost done!
return new_memory, read_vectors, previous_weights, ntm_output
