def benchmark_cg(ctx, timer):
print "#worker:", ctx.num_workers
l = int(math.sqrt(ctx.num_workers))
n = 2000 * 16
#n = 4000 * l
la = 20
niter = 5
tile_hint = (n, n/ctx.num_workers)
#nonzer = 7
#nz = n * (nonzer + 1) * (nonzer + 1) + n * (nonzer + 2)
#density = 0.5 * nz/(n*n)
A = expr.rand(n, n, tile_hint=tile_hint)
A = (A + expr.transpose(A))*0.5
I = expr.sparse_diagonal((n,n), tile_hint=tile_hint) * la
I.force()
A = expr.eager(A - I)
#x1 = numpy_cg(A.glom(), niter)
util.log_warn('begin cg!')
t1 = datetime.now()
x2 = conj_gradient(A, niter).force()
t2 = datetime.now()
cost_time = millis(t1,t2)
print "total cost time:%s ms, per iter cost time:%s ms" % (cost_time, cost_time/niter)
def benchmark_naive_bayes(ctx, timer):
print "#worker:", ctx.num_workers
#N = 100000 * ctx.num_workers
N = 10000 * 64
D = 128
# create data
data = expr.randint(N, D, low=0, high=D, tile_hint=(N, D/ctx.num_workers))
labels = expr.shuffle(expr.ndarray((data.shape[0], 1), dtype=np.int), _init_label_mapper,
kw={'data': data}, shape_hint=(data.shape[0], 1),
cost_hint={hash(data):{'00': 0, '10': np.prod(data.shape)}}
)
#util.log_warn('data:%s, label:%s', data.glom(), labels.glom())
util.log_warn('begin train')
t1 = datetime.now()
model = fit(data, labels, D)
t2 = datetime.now()
util.log_warn('train time:%s ms', millis(t1,t2))
correct = 0
for i in range(10):
new_data = expr.randint(1, D, low=0, high=D, tile_hint=(1, D))
new_label = predict(model, new_data)
#print 'point %s, predict %s' % (new_data.glom(), new_label)
new_data = new_data.glom()
if np.isclose(new_data[0, new_label], np.max(new_data)):
correct += 1
print 'predict precision:', correct * 1.0 / 10
def benchmark_naive_bayes(ctx, timer):
print "#worker:", ctx.num_workers
N = 100000 * ctx.num_workers
D = 128
# create data
data = expr.randint(N, D, low=0, high=D, tile_hint=(N/ctx.num_workers, D))
labels = expr.eager(expr.shuffle(data, _init_label_mapper))
#util.log_warn('data:%s, label:%s', data.glom(), labels.glom())
util.log_warn('begin train')
t1 = datetime.now()
model = fit(data, labels, D)
t2 = datetime.now()
util.log_warn('train time:%s ms', millis(t1,t2))
correct = 0
for i in range(10):
new_data = expr.randint(1, D, low=0, high=D, tile_hint=(1, D))
new_label = predict(model, new_data)
#print 'point %s, predict %s' % (new_data.glom(), new_label)
new_data = new_data.glom()
if np.isclose(new_data[0, new_label], np.max(new_data)):
correct += 1
print 'predict precision:', correct * 1.0 / 10
def benchmark_lda(ctx, timer):
print "#worker:", ctx.num_workers
NUM_TERMS = 160
NUM_DOCS = 200 * ctx.num_workers
#NUM_DOCS = 10 * 64
# create data
# NUM_TERMS = 41807
# NUM_DOCS = 21578
# terms_docs_matrix = from_file("/scratch/cq/numpy_dense_matrix", sparse = False, tile_hint = (NUM_TERMS, int((NUM_DOCS + ctx.num_workers - 1) / ctx.num_workers))).evaluate()
terms_docs_matrix = expr.randint(NUM_TERMS, NUM_DOCS, low=0, high=100)
max_iter = 3
k_topics = 16
t1 = datetime.now()
doc_topics, topic_term_count = learn_topics(terms_docs_matrix,
k_topics,
max_iter=max_iter)
doc_topics.optimized().evaluate()
topic_term_count.optimized().evaluate()
t2 = datetime.now()
time_cost = millis(t1, t2)
util.log_warn('total_time:%s ms, train time per iteration:%s ms',
time_cost, time_cost / max_iter)
def benchmark_cholesky(ctx, timer):
print "#worker:", ctx.num_workers
#n = int(math.pow(ctx.num_workers, 1.0 / 3.0))
n = int(math.sqrt(ctx.num_workers))
#ARRAY_SIZE = 1600 * 4
ARRAY_SIZE = 1600 * n
util.log_warn('prepare data!')
#A = np.random.randn(ARRAY_SIZE, ARRAY_SIZE)
#A = np.dot(A, A.T)
#A = expr.force(from_numpy(A, tile_hint=(ARRAY_SIZE/n, ARRAY_SIZE/n)))
#A = expr.randn(ARRAY_SIZE, ARRAY_SIZE, tile_hint=(ARRAY_SIZE/n, ARRAY_SIZE/n))
A = expr.randn(ARRAY_SIZE, ARRAY_SIZE)
# FIXME: Ideally we should be able to get rid of tile_hint.
# However, current extent.change_partition_axis relies on the
# information of one-dimentional size to change tiling to grid tiling.
# It assumes that every extent should be partitioned in the same size.
# Trace extent.pyx to think about how to fix it!
A = expr.dot(A,
expr.transpose(A),
tile_hint=(ARRAY_SIZE, ARRAY_SIZE / ctx.num_workers)).force()
util.log_warn('begin cholesky!')
t1 = datetime.now()
L = cholesky(A).glom()
t2 = datetime.now()
assert np.all(np.isclose(A.glom(), np.dot(L, L.T.conj())))
cost_time = millis(t1, t2)
print "total cost time:%s ms, per iter cost time:%s ms" % (cost_time,
cost_time / n)
def benchmark_svm(ctx, timer):
print "#worker:", ctx.num_workers
max_iter = 2
#N = 200000 * ctx.num_workers
N = 1000 * 64
D = 64
# create data
data = expr.randn(N, D, dtype=np.float64, tile_hint=(N, util.divup(D, ctx.num_workers)))
labels = expr.shuffle(data, _init_label_mapper, shape_hint=(data.shape[0], 1))
t1 = datetime.now()
w = fit(data, labels, T=max_iter).force()
t2 = datetime.now()
util.log_warn('train time per iteration:%s ms, final w:%s', millis(t1,t2)/max_iter, w.glom().T)
correct = 0
for i in range(10):
new_data = expr.randn(1, D, dtype=np.float64, tile_hint=[1, D])
new_label = predict(w, new_data)
#print 'point %s, predict %s' % (new_data.glom(), new_label)
new_data = new_data.glom()
if new_data[0,0] >= new_data[0,1] and new_label == 1.0 or new_data[0,0] < new_data[0,1] and new_label == -1.0:
correct += 1
print 'predict precision:', correct * 1.0 / 10
def benchmark_cg(ctx, timer):
print "#worker:", ctx.num_workers
l = int(math.sqrt(ctx.num_workers))
#n = 2000 * 16
n = 500 * ctx.num_workers
la = 20
niter = 5
#nonzer = 7
#nz = n * (nonzer + 1) * (nonzer + 1) + n * (nonzer + 2)
#density = 0.5 * nz/(n*n)
A = expr.rand(n, n)
A = (A + expr.transpose(A)) * 0.5
I = expr.sparse_diagonal((n, n)) * la
A = A - I
#x1 = numpy_cg(A.glom(), niter)
util.log_warn('begin cg!')
t1 = datetime.now()
x2 = conj_gradient(A, niter).force()
t2 = datetime.now()
cost_time = millis(t1, t2)
print "total cost time:%s ms, per iter cost time:%s ms" % (
cost_time, cost_time / niter)
def benchmark_ssvd(ctx, timer):
DIM = (1280, 1280)
#A = expr.randn(*DIM, dtype=np.float64)
A = np.random.randn(*DIM)
A = expr.from_numpy(A)
t1 = datetime.now()
U, S, VT = svd(A)
t2 = datetime.now()
cost_time = millis(t1, t2)
print "total cost time:%s ms" % (cost_time)
def benchmark_canopy_clustering(ctx, timer):
# N_PTS = 60000 * ctx.num_workers
N_PTS = 30000 * 64
N_DIM = 2
pts = expr.rand(N_PTS, N_DIM, tile_hint=(N_PTS / ctx.num_workers, N_DIM)).evaluate()
t1 = datetime.now()
cluster_result = canopy_cluster(pts).evaluate()
t2 = datetime.now()
print "canopy_cluster time:%s ms" % millis(t1, t2)
def benchmark_ssvd(ctx, timer):
DIM = (1280, 1280)
#A = expr.randn(*DIM, dtype=np.float64)
A = np.random.randn(*DIM)
A = expr.from_numpy(A)
t1 = datetime.now()
U,S,VT = svd(A)
t2 = datetime.now()
cost_time = millis(t1, t2)
print "total cost time:%s ms" % (cost_time)
def benchmark_pca(ctx, timer):
DIM = (1280, 512)
data = np.random.randn(*DIM)
A = expr.from_numpy(data)
#A = expr.randn(*DIM, dtype=np.float64)
t1 = datetime.now()
m = PCA(N_COMPONENTS)
m.fit(A)
t2 = datetime.now()
cost_time = millis(t1, t2)
print "total cost time:%s ms" % (cost_time)
def benchmark_canopy_clustering(ctx, timer):
#N_PTS = 60000 * ctx.num_workers
N_PTS = 30000 * 64
N_DIM = 2
pts = expr.rand(N_PTS, N_DIM,
tile_hint=(N_PTS / ctx.num_workers, N_DIM)).force()
t1 = datetime.now()
cluster_result = canopy_cluster(pts).force()
t2 = datetime.now()
print 'canopy_cluster time:%s ms' % millis(t1, t2)
def benchmark_pca(ctx, timer):
DIM = (1280, 512)
data = np.random.randn(*DIM)
A = expr.from_numpy(data)
#A = expr.randn(*DIM, dtype=np.float64)
t1 = datetime.now()
m = PCA(N_COMPONENTS)
m.fit(A)
t2 = datetime.now()
cost_time = millis(t1, t2)
print "total cost time:%s ms" % (cost_time)
def benchmark_qr(ctx, timer):
M = 1280
N = 1280
Y = np.random.randn(M, N)
Y = expr.from_numpy(Y)
#Y = expr.randn(M, N)
t1 = datetime.now()
Q, R = qr(Y)
t2 = datetime.now()
cost_time = millis(t1, t2)
print "total cost time:%s ms" % (cost_time)
def benchmark_knn(ctx, timer): print "#worker:", ctx.num_workers N_SAMPLES = ctx.num_workers * 300 N_QUERY = ctx.num_workers * 2 N_DIM = ctx.num_workers * 2 X = expr.rand(N_SAMPLES, N_DIM) Y = expr.rand(N_QUERY, N_DIM) t1 = datetime.now() dist2, ind2 = NearestNeighbors().fit(X).kneighbors(Y) t2 = datetime.now() cost_time = millis(t1, t2) print "total cost time:%s ms" % (cost_time)
def benchmark_kmeans(ctx, timer): print "#worker:", ctx.num_workers N_PTS = 1000 * 256 N_CENTERS = 10 N_DIM = 512 ITER = 1 pts = expr.rand(N_PTS, N_DIM) k = KMeans(N_CENTERS, ITER) t1 = datetime.now() k.fit(pts) t2 = datetime.now() cost_time = millis(t1, t2) print "total cost time:%s ms, per iter cost time:%s ms" % (cost_time, cost_time/ITER)
def benchmark_qr(ctx, timer):
M = 1280
N = 1280
Y = np.random.randn(M, N)
Y = expr.from_numpy(Y)
#Y = expr.randn(M, N)
t1 = datetime.now()
Q, R = qr(Y)
t2 = datetime.now()
cost_time = millis(t1, t2)
print "total cost time:%s ms" % (cost_time)
def benchmark_fuzzy_kmeans(ctx, timer): #N_PTS = 40000 * ctx.num_workers N_PTS = 1000 * 256 N_DIM = 512 ITER = 5 N_CENTERS = 10 pts = expr.rand(N_PTS, N_DIM) t1 = datetime.now() cluster_result = fuzzy_kmeans(pts, k=N_CENTERS, num_iter=ITER).evaluate() t2 = datetime.now() time_cost = millis(t1, t2) print 'fuzzy_cluster time:%s ms, per_iter:%s ms' % (time_cost, time_cost/ITER)
def benchmark_spectral_clustering(ctx, timer):
#N_PTS = 500 * ctx.num_workers
N_PTS = 50 * 64
N_DIM = 2
ITER = 5
N_CENTERS = 5
pts = expr.rand(N_PTS, N_DIM,
tile_hint=(N_PTS / ctx.num_workers, N_DIM)).evaluate()
t1 = datetime.now()
cluster_result = spectral_cluster(pts, N_CENTERS, ITER).glom()
t2 = datetime.now()
print 'spectral_cluster time:%s ms' % millis(t1, t2)
def benchmark_ib_recommander(ctx, timer):
print "#worker:", ctx.num_workers
N_ITEMS = 800
N_USERS = 8000
rating_table = expr.sparse_rand((N_USERS, N_ITEMS),
dtype=np.float64,
density=0.1,
format="csr")
t1 = datetime.now()
model = ItemBasedRecommender(rating_table)
model.precompute()
t2 = datetime.now()
cost_time = millis(t1, t2)
print "total cost time:%s ms" % cost_time
def benchmark_kmeans(ctx, timer):
print "#worker:", ctx.num_workers
N_PTS = 1000 * 256
N_CENTERS = 10
N_DIM = 512
ITER = 1
pts = expr.rand(N_PTS, N_DIM)
k = KMeans(N_CENTERS, ITER)
t1 = datetime.now()
k.fit(pts)
t2 = datetime.now()
cost_time = millis(t1, t2)
print "total cost time:%s ms, per iter cost time:%s ms" % (
cost_time, cost_time / ITER)
def benchmark_spectral_clustering(ctx, timer):
#N_PTS = 500 * ctx.num_workers
N_PTS = 50 * 64
N_DIM = 2
ITER = 5
N_CENTERS = 5
pts = expr.rand(N_PTS, N_DIM,
tile_hint=(N_PTS / ctx.num_workers, N_DIM)).force()
t1 = datetime.now()
cluster_result = spectral_cluster(pts, N_CENTERS, ITER).glom()
t2 = datetime.now()
print 'spectral_cluster time:%s ms' % millis(t1, t2)
def benchmark_fuzzy_kmeans(ctx, timer):
# N_PTS = 40000 * ctx.num_workers
N_PTS = 1000 * 256
N_DIM = 512
ITER = 5
N_CENTERS = 10
pts = expr.rand(N_PTS, N_DIM)
t1 = datetime.now()
cluster_result = fuzzy_kmeans(pts, k=N_CENTERS, num_iter=ITER).evaluate()
t2 = datetime.now()
time_cost = millis(t1, t2)
print "fuzzy_cluster time:%s ms, per_iter:%s ms" % (time_cost, time_cost / ITER)
def benchmark_ib_recommander(ctx, timer):
print "#worker:", ctx.num_workers
N_ITEMS = 800
N_USERS = 8000
rating_table = expr.sparse_rand((N_USERS, N_ITEMS),
dtype=np.float64,
density=0.1,
format = "csr")
t1 = datetime.now()
model = ItemBasedRecommender(rating_table)
model.precompute()
t2 = datetime.now()
cost_time = millis(t1, t2)
print "total cost time:%s ms" % cost_time
def benchmark_fuzzy_kmeans(ctx, timer):
#N_PTS = 40000 * ctx.num_workers
N_PTS = 20000 * 64
N_DIM = 2
ITER = 5
N_CENTERS = 10
pts = expr.rand(N_PTS, N_DIM,
tile_hint=(N_PTS / ctx.num_workers, N_DIM)).force()
t1 = datetime.now()
cluster_result = fuzzy_kmeans(pts, k=N_CENTERS, num_iter=ITER).force()
t2 = datetime.now()
time_cost = millis(t1, t2)
print 'fuzzy_cluster time:%s ms, per_iter:%s ms' % (time_cost, time_cost/ITER)
def benchmark_streaming_kmeans(ctx, timer):
#N_PTS = 100 * ctx.num_workers
N_PTS = 100 * 64
N_DIM = 2
N_CENTERS = 5
pts = expr.rand(N_PTS, N_DIM,
tile_hint=(N_PTS / ctx.num_workers, N_DIM)).force()
print pts.glom()
t1 = datetime.now()
cluster_result = streaming_kmeans(pts, k=N_CENTERS).glom()
t2 = datetime.now()
#print cluster_result.glom()
time_cost = millis(t1, t2)
print 'streaming_kmeans_cluster time:%s ms' % time_cost
def benchmark_streaming_kmeans(ctx, timer):
#N_PTS = 100 * ctx.num_workers
N_PTS = 100 * 64
N_DIM = 2
N_CENTERS = 5
pts = expr.rand(N_PTS, N_DIM,
tile_hint=(N_PTS / ctx.num_workers, N_DIM)).evaluate()
print pts.glom()
t1 = datetime.now()
cluster_result = streaming_kmeans(pts, k=N_CENTERS).glom()
t2 = datetime.now()
#print cluster_result.glom()
time_cost = millis(t1, t2)
print 'streaming_kmeans_cluster time:%s ms' % time_cost
def benchmark_als(ctx, timer):
print "#worker:", ctx.num_workers
#USER_SIZE = 400 * ctx.num_workers
USER_SIZE = 200 * 64
MOVIE_SIZE = 12800
num_features = 20
num_iter = 5
A = expr.eager(expr.randint(USER_SIZE, MOVIE_SIZE, low=0, high=5, tile_hint=(USER_SIZE/ctx.num_workers, MOVIE_SIZE)))
util.log_warn('begin als!')
t1 = datetime.now()
U, M = als(A, implicit_feedback=True, num_features=num_features, num_iter=num_iter)
U.force()
M.force()
t2 = datetime.now()
cost_time = millis(t1,t2)
print "total cost time:%s ms, per iter cost time:%s ms" % (cost_time, cost_time/num_iter)
def benchmark_als(ctx, timer):
print "#worker:", ctx.num_workers
#USER_SIZE = 100 * ctx.num_workers
USER_SIZE = 320
#USER_SIZE = 200 * 64
MOVIE_SIZE = 12800
num_features = 20
num_iter = 2
A = expr.randint(USER_SIZE, MOVIE_SIZE, low=0, high=5, tile_hint=(USER_SIZE, util.divup(MOVIE_SIZE, ctx.num_workers)))
#A = expr.randint(USER_SIZE, MOVIE_SIZE, low=0, high=5)
util.log_warn('begin als!')
t1 = datetime.now()
U, M = als(A, implicit_feedback=True, num_features=num_features, num_iter=num_iter)
U.force()
M.force()
t2 = datetime.now()
cost_time = millis(t1,t2)
print "total cost time:%s ms, per iter cost time:%s ms" % (cost_time, cost_time/num_iter)
def benchmark_cholesky(ctx, timer):
print "#worker:", ctx.num_workers
#n = int(math.pow(ctx.num_workers, 1.0 / 3.0))
n = int(math.sqrt(ctx.num_workers))
#ARRAY_SIZE = 1600 * 4
ARRAY_SIZE = 900 * n
util.log_warn('prepare data!')
#A = np.random.randn(ARRAY_SIZE, ARRAY_SIZE)
#A = np.dot(A, A.T)
A = expr.randn(ARRAY_SIZE, ARRAY_SIZE)
A = expr.dot(A, expr.transpose(A))
util.log_warn('begin cholesky!')
t1 = datetime.now()
L = cholesky(A).optimized().glom()
t2 = datetime.now()
#assert np.all(np.isclose(A.glom(), np.dot(L, L.T.conj())))
cost_time = millis(t1, t2)
print "total cost time:%s ms, per iter cost time:%s ms" % (cost_time, cost_time/n)
def benchmark_cholesky(ctx, timer):
print "#worker:", ctx.num_workers
# n = int(math.pow(ctx.num_workers, 1.0 / 3.0))
n = int(math.sqrt(ctx.num_workers))
ARRAY_SIZE = 1600 * 4
# ARRAY_SIZE = 1600 * n
util.log_warn("prepare data!")
# A = np.random.randn(ARRAY_SIZE, ARRAY_SIZE)
# A = np.dot(A, A.T)
# A = expr.force(from_numpy(A, tile_hint=(ARRAY_SIZE/n, ARRAY_SIZE/n)))
A = expr.randn(ARRAY_SIZE, ARRAY_SIZE, tile_hint=(ARRAY_SIZE / n, ARRAY_SIZE / n))
A = expr.dot(A, expr.transpose(A)).force()
util.log_warn("begin cholesky!")
t1 = datetime.now()
L = cholesky(A).glom()
t2 = datetime.now()
assert np.all(np.isclose(A.glom(), np.dot(L, L.T.conj())))
cost_time = millis(t1, t2)
print "total cost time:%s ms, per iter cost time:%s ms" % (cost_time, cost_time / n)
def benchmark_cholesky(ctx, timer):
print "#worker:", ctx.num_workers
#n = int(math.pow(ctx.num_workers, 1.0 / 3.0))
n = int(math.sqrt(ctx.num_workers))
#ARRAY_SIZE = 1600 * 4
ARRAY_SIZE = 900 * n
util.log_warn('prepare data!')
#A = np.random.randn(ARRAY_SIZE, ARRAY_SIZE)
#A = np.dot(A, A.T)
A = expr.randn(ARRAY_SIZE, ARRAY_SIZE)
A = expr.dot(A, expr.transpose(A))
util.log_warn('begin cholesky!')
t1 = datetime.now()
L = cholesky(A).optimized().glom()
t2 = datetime.now()
#assert np.all(np.isclose(A.glom(), np.dot(L, L.T.conj())))
cost_time = millis(t1, t2)
print "total cost time:%s ms, per iter cost time:%s ms" % (cost_time,
cost_time / n)
def benchmark_lda(ctx, timer):
print "#worker:", ctx.num_workers
NUM_TERMS = 160
NUM_DOCS = 200 * ctx.num_workers
#NUM_DOCS = 10 * 64
# create data
# NUM_TERMS = 41807
# NUM_DOCS = 21578
# terms_docs_matrix = from_file("/scratch/cq/numpy_dense_matrix", sparse = False, tile_hint = (NUM_TERMS, int((NUM_DOCS + ctx.num_workers - 1) / ctx.num_workers))).force()
terms_docs_matrix = expr.randint(NUM_TERMS, NUM_DOCS, low=0, high=100)
max_iter = 3
k_topics = 16
t1 = datetime.now()
doc_topics, topic_term_count = learn_topics(terms_docs_matrix, k_topics, max_iter=max_iter)
doc_topics.optimized().force()
topic_term_count.optimized().force()
t2 = datetime.now()
time_cost = millis(t1,t2)
util.log_warn('total_time:%s ms, train time per iteration:%s ms', time_cost, time_cost/max_iter)