私は最近、Python をいじくり回しており、多数の並列化パッケージを比較していると、シリアルからパラレルへのパフォーマンスの向上は、私の MacBook Pro (OS X 10.8.2) があります。
添付のプロットは、さまざまなタスクのタイミングをプロセス数 (並列または順次) の関数として比較しています。この例では、Python の組み込み ' multiprocessing ' パッケージを使用しています。
8工程以下のトップアウトの原因は？
(「時間」は、プロセス数ごとに 100 回の関数呼び出しを平均したものです)
import multiprocessing as mp
import time
import numpy as np
import matplotlib as mpl
from matplotlib import pyplot as plt
iters = 100
mem_num = 1000
pro_num = 20000
max_procs = 10
line_width = 2.0
legend_size = 10
fig_name = 'timing.pdf'
def UseMemory(num):
test1 = np.zeros([num,num])
test2 = np.arange(num*num)
test3 = np.array(test2).reshape([num, num])
test4 = np.empty(num, dtype=object)
return
def UseProcessor(num):
test1 = np.arange(num)
test1 = np.cos(test1)
test1 = np.sqrt(np.fabs(test1))
test2 = np.zeros(num)
for i in range(num): test2[i] = test1[i]
return np.std(test2)
def MemJob(its):
for ii in range(its): UseMemory(mem_num)
def ProJob(its):
for ii in range(iters): UseProcessor(pro_num)
if __name__ == "__main__":
print '\nParTest\n'
proc_range = np.arange(1,max_procs+1,step=1)
test_times = np.zeros([len(proc_range),2,2]) # test_times[num_procs][0-ser,1-par][0-mem,1-pro]
tot_times = np.zeros([len(proc_range),2 ]) # tot_times[num_procs][0-ser,1-par]
print ' Testing %2d numbers of processors between [%d,%d]' % (len(proc_range), 1, max_procs)
print ' Iterations %d, Memory Length %d, Processor Length %d' % (iters, mem_num, pro_num)
for it in range(len(proc_range)):
procs = proc_range[it]
job_arg = procs*[iters]
print '\n - %2d, Processes = %3d' % (it, procs)
# --- Test Serial ---
print ' - - Serial'
# Test Memory
all_start = time.time()
start = time.time()
map(MemJob, [procs*iters])
ser_mem_time = time.time() - start
# Test Processor
start = time.time()
map(ProJob, job_arg)
ser_pro_time = time.time() - start
ser_time = time.time() - all_start
# --- Test Parallel : multiprocessing ---
print ' - - Parallel: multiprocessing'
pool = mp.Pool(processes=procs)
# Test Memory
all_start = time.time()
start = time.time()
pool.map(MemJob, job_arg)
par_mem_time = time.time() - start
# Test Processor
start = time.time()
pool.map(ProJob, job_arg)
par_pro_time = time.time() - start
par_time = time.time() - all_start
print ' - - Collecting'
ser_mem_time /= procs
ser_pro_time /= procs
par_mem_time /= procs
par_pro_time /= procs
ser_time /= procs
par_time /= procs
test_times[it][0] = [ ser_mem_time, ser_pro_time ]
test_times[it][1] = [ par_mem_time, par_pro_time ]
tot_times[it] = [ ser_time , par_time ]
fig = plt.figure()
ax = fig.add_subplot(111)
ax.set_xlabel('Number of Processes')
ax.set_ylabel('Time [s]')
ax.xaxis.grid(True)
ax.yaxis.grid(True)
lines = []
names = []
l1, = ax.plot(proc_range, test_times[:,0,0], linewidth=line_width)
lines.append(l1)
names.append('Serial Memory')
l1, = ax.plot(proc_range, test_times[:,0,1], linewidth=line_width)
lines.append(l1)
names.append('Serial Processor')
l1, = ax.plot(proc_range, tot_times[:,0], linewidth=line_width)
lines.append(l1)
names.append('Serial')
l1, = ax.plot(proc_range, test_times[:,1,0], linewidth=line_width)
lines.append(l1)
names.append('Parallel Memory')
l1, = ax.plot(proc_range, test_times[:,1,1], linewidth=line_width)
lines.append(l1)
names.append('Parallel Processor')
l1, = ax.plot(proc_range, tot_times[:,1], linewidth=line_width)
lines.append(l1)
names.append('Parallel')
plt.legend(lines, names, ncol=2, prop={'size':legend_size}, fancybox=True, shadow=True, bbox_to_anchor=(1.10, 1.10))
fig.savefig(fig_name,dpi=fig.get_dpi())
print ' - Saved to ', fig_name
plt.show(block=True)