def setUpClass(self):
self.env_orig = os.getenv('OPTKIT_USE_LOCALLIBS', '0')
os.environ['OPTKIT_USE_LOCALLIBS'] = '1'
self.libs = DenseLinsysLibs()
self.A_test = self.A_test_gen
class DenseLibsTestCase(OptkitCTestCase):
@classmethod
def setUpClass(self):
self.env_orig = os.getenv('OPTKIT_USE_LOCALLIBS', '0')
os.environ['OPTKIT_USE_LOCALLIBS'] = '1'
self.libs = DenseLinsysLibs()
@classmethod
def tearDownClass(self):
os.environ['OPTKIT_USE_LOCALLIBS'] = self.env_orig
def test_libs_exist(self):
libs = []
for (gpu, single_precision) in self.CONDITIONS:
libs.append(self.libs.get(
single_precision=single_precision, gpu=gpu))
self.assertTrue( any(libs) )
def test_lib_types(self):
for (gpu, single_precision) in self.CONDITIONS:
lib = self.libs.get(single_precision=single_precision, gpu=gpu)
if lib is None:
continue
self.assertTrue( 'ok_float' in dir(lib) )
self.assertTrue( 'ok_int' in dir(lib) )
self.assertTrue( 'c_int_p' in dir(lib) )
self.assertTrue( 'ok_float_p' in dir(lib) )
self.assertTrue( 'ok_int_p' in dir(lib) )
self.assertTrue( 'vector' in dir(lib) )
self.assertTrue( 'vector_p' in dir(lib) )
self.assertTrue( 'matrix' in dir(lib) )
self.assertTrue( 'matrix_p' in dir(lib) )
self.assertTrue( single_precision == (lib.ok_float == c_float) )
self.assertTrue( lib.ok_int == c_int )
def test_blas_handle(self):
for (gpu, single_precision) in self.CONDITIONS:
lib = self.libs.get(single_precision=single_precision, gpu=gpu)
if lib is None:
continue
handle = c_void_p()
# create
self.assertCall( lib.blas_make_handle(byref(handle)) )
# destroy
self.assertCall( lib.blas_destroy_handle(handle) )
def test_device_reset(self):
for (gpu, single_precision) in self.CONDITIONS:
lib = self.libs.get(single_precision=single_precision, gpu=gpu)
if lib is None:
continue
# reset
self.assertCall( lib.ok_device_reset() )
# allocate - deallocate - reset
handle = c_void_p()
self.assertCall( lib.blas_make_handle(byref(handle)) )
self.assertCall( lib.blas_destroy_handle(handle) )
self.assertCall( lib.ok_device_reset() )
def test_version(self):
for (gpu, single_precision) in self.CONDITIONS:
lib = self.libs.get(single_precision=single_precision, gpu=gpu)
if lib is None:
continue
major = c_int()
minor = c_int()
change = c_int()
status = c_int()
lib.optkit_version(byref(major), byref(minor), byref(change),
byref(status))
version = self.version_string(major.value, minor.value,
change.value, status.value)
self.assertNotEqual( version, '0.0.0' )
if self.VERBOSE_TEST:
print("denselib version", version)
class DenseBLASTestCase(OptkitCTestCase):
@classmethod
def setUpClass(self):
self.env_orig = os.getenv('OPTKIT_USE_LOCALLIBS', '0')
os.environ['OPTKIT_USE_LOCALLIBS'] = '1'
self.libs = DenseLinsysLibs()
self.A_test = self.A_test_gen
@classmethod
def tearDownClass(self):
os.environ['OPTKIT_USE_LOCALLIBS'] = self.env_orig
def setUp(self):
pass
def tearDown(self):
self.free_all_vars()
self.exit_call()
def test_blas1_dot(self):
(m, n) = self.shape
for (gpu, single_precision) in self.CONDITIONS:
lib = self.libs.get(single_precision=single_precision, gpu=gpu)
if lib is None:
continue
self.register_exit(lib.ok_device_reset)
DIGITS = 7 - 2 * single_precision
TOL = 10**(-DIGITS)
hdl = self.register_blas_handle(lib, 'hdl')
v, v_py, v_ptr = self.register_vector(lib, m, 'v')
w, w_py, w_ptr = self.register_vector(lib, m, 'w')
v_py += np.random.rand(m)
w_py += np.random.rand(m)
lib.vector_memcpy_va(v, v_ptr, 1)
lib.vector_memcpy_va(w, w_ptr, 1)
answer = np.zeros(1).astype(lib.pyfloat)
answer_p = answer.ctypes.data_as(lib.ok_float_p)
self.assertCall( lib.blas_dot(hdl, v, w, answer_p) )
self.assertTrue( np.abs(answer[0] - v_py.dot(w_py)) <=
TOL + TOL * answer[0] )
self.free_vars('v', 'w', 'hdl')
self.assertCall( lib.ok_device_reset() )
def test_blas1_nrm2(self):
(m, n) = self.shape
for (gpu, single_precision) in self.CONDITIONS:
lib = self.libs.get(single_precision=single_precision, gpu=gpu)
if lib is None:
continue
self.register_exit(lib.ok_device_reset)
DIGITS = 7 - 2 * single_precision
TOL = 10**(-DIGITS)
hdl = self.register_blas_handle(lib, 'hdl')
v, v_py, v_ptr = self.register_vector(lib, m, 'v')
v_py += np.random.rand(m)
lib.vector_memcpy_va(v, v_ptr, 1)
answer = np.zeros(1).astype(lib.pyfloat)
answer_p = answer.ctypes.data_as(lib.ok_float_p)
self.assertCall( lib.blas_nrm2(hdl, v, answer_p) )
self.assertScalarEqual( answer[0], np.linalg.norm(v_py), TOL )
self.free_vars('v', 'hdl')
self.assertCall( lib.ok_device_reset() )
def test_blas1_asum(self):
(m, n) = self.shape
for (gpu, single_precision) in self.CONDITIONS:
lib = self.libs.get(single_precision=single_precision, gpu=gpu)
if lib is None:
continue
self.register_exit(lib.ok_device_reset)
DIGITS = 7 - 2 * single_precision
TOL = 10**(-DIGITS)
hdl = self.register_blas_handle(lib, 'hdl')
v, v_py, v_ptr = self.register_vector(lib, m, 'v')
v_py += np.random.rand(m)
self.assertCall( lib.vector_memcpy_va(v, v_ptr, 1) )
answer = np.zeros(1).astype(lib.pyfloat)
answer_p = answer.ctypes.data_as(lib.ok_float_p)
self.assertCall( lib.blas_asum(hdl, v, answer_p) )
self.assertScalarEqual( answer[0], np.linalg.norm(v_py, 1), TOL )
self.free_vars('v', 'hdl')
self.assertCall( lib.ok_device_reset() )
def test_blas1_scal(self):
(m, n) = self.shape
v_rand= np.random.rand(m)
for (gpu, single_precision) in self.CONDITIONS:
lib = self.libs.get(single_precision=single_precision, gpu=gpu)
if lib is None:
continue
self.register_exit(lib.ok_device_reset)
DIGITS = 7 - 2 * single_precision
TOL = 10**(-DIGITS)
hdl = self.register_blas_handle(lib, 'hdl')
v, v_py, v_ptr = self.register_vector(lib, m, 'v')
v_py += v_rand
self.assertCall( lib.vector_memcpy_va(v, v_ptr, 1) )
alpha = np.random.rand()
self.assertCall( lib.blas_scal(hdl, alpha, v) )
self.assertCall( lib.vector_memcpy_av(v_ptr, v, 1) )
self.assertVecEqual( v_py, alpha * v_rand, TOL * m**0.5, TOL )
self.free_vars('v', 'hdl')
self.assertCall( lib.ok_device_reset() )
def test_blas1_axpy(self):
(m, n) = self.shape
for (gpu, single_precision) in self.CONDITIONS:
lib = self.libs.get(single_precision=single_precision, gpu=gpu)
if lib is None:
continue
self.register_exit(lib.ok_device_reset)
DIGITS = 7 - 2 * single_precision
TOL = 10**(-DIGITS)
hdl = self.register_blas_handle(lib, 'hdl')
v, v_py, v_ptr = self.register_vector(lib, m, 'v')
w, w_py, w_ptr = self.register_vector(lib, m, 'w')
v_py += np.random.rand(m)
w_py += np.random.rand(m)
alpha = np.random.rand()
pyresult = alpha * v_py + w_py
self.assertCall( lib.vector_memcpy_va(v, v_ptr, 1) )
self.assertCall( lib.vector_memcpy_va(w, w_ptr, 1) )
self.assertCall( lib.blas_axpy(hdl, alpha, v, w) )
self.assertCall( lib.vector_memcpy_av(w_ptr, w, 1) )
self.assertVecEqual( w_py, pyresult, TOL * m**0.5, TOL )
self.free_vars('v', 'w', 'hdl')
self.assertCall( lib.ok_device_reset() )
def test_blas2_gemv(self):
(m, n) = self.shape
for (gpu, single_precision) in self.CONDITIONS:
lib = self.libs.get(single_precision=single_precision, gpu=gpu)
if lib is None:
continue
self.register_exit(lib.ok_device_reset)
DIGITS = 7 - 2 * single_precision
TOL = 10**(-DIGITS)
for order in (lib.enums.CblasRowMajor, lib.enums.CblasColMajor):
hdl = self.register_blas_handle(lib, 'hdl')
# make A, x, y
A, A_py, A_ptr = self.register_matrix(lib, m, n, order, 'A')
x, x_py, x_ptr = self.register_vector(lib, n, 'x')
y, y_py, y_ptr = self.register_vector(lib, m, 'y')
# populate A, x, y (in Py and C)
A_py += self.A_test
x_py += np.random.rand(n)
y_py += np.random.rand(m)
self.assertCall( lib.vector_memcpy_va(x, x_ptr, 1) )
self.assertCall( lib.vector_memcpy_va(y, y_ptr, 1) )
self.assertCall( lib.matrix_memcpy_ma(A, A_ptr, order) )
# perform y = alpha * A * x + beta * y
alpha = -0.5 + np.random.rand()
beta = -0.5 + np.random.rand()
pyresult = alpha * A_py.dot(x_py) + beta * y_py
self.assertCall( lib.blas_gemv(hdl, lib.enums.CblasNoTrans,
alpha, A, x, beta, y) )
self.assertCall( lib.vector_memcpy_av(y_ptr, y, 1) )
self.assertVecEqual( y_py, pyresult, TOL * m**0.5, TOL )
# perform x = alpha * A' * y + beta * x
y_py[:] = pyresult[:]
pyresult = alpha * A_py.T.dot(y_py) + beta * x_py
self.assertCall( lib.blas_gemv(hdl, lib.enums.CblasTrans,
alpha, A, y, beta, x) )
self.assertCall( lib.vector_memcpy_av(x_ptr, x, 1) )
self.assertVecEqual( x_py, pyresult, TOL * n**0.5, TOL )
self.free_vars('A', 'x', 'y', 'hdl')
self.assertCall( lib.ok_device_reset() )
def test_blas2_trsv(self):
(m, n) = self.shape
# generate lower triangular matrix L
L_test = self.A_test.T.dot(self.A_test)
# normalize L so inversion doesn't blow up
L_test /= np.linalg.norm(L_test)
for i in xrange(n):
# diagonal entries ~ 1 to keep condition number reasonable
L_test[i, i] /= 10**np.log(n)
L_test[i, i] += 1
# upper triangle = 0
for j in xrange(n):
if j > i:
L_test[i, j] *= 0
x_rand = np.random.rand(n)
for (gpu, single_precision) in self.CONDITIONS:
lib = self.libs.get(single_precision=single_precision, gpu=gpu)
if lib is None:
continue
self.register_exit(lib.ok_device_reset)
DIGITS = 7 - 2 * single_precision
TOL = 10**(-DIGITS)
for order in (lib.enums.CblasRowMajor, lib.enums.CblasColMajor):
hdl = self.register_blas_handle(lib, 'hdl')
# make L, x
L, L_py, L_ptr = self.register_matrix(lib, n, n, order, 'L')
x, x_py, x_ptr = self.register_vector(lib, n, 'x')
# populate L, x
L_py += L_test
x_py += x_rand
self.assertCall( lib.vector_memcpy_va(x, x_ptr, 1) )
self.assertCall( lib.matrix_memcpy_ma(L, L_ptr, order) )
# y = inv(L) * x
pyresult = np.linalg.solve(L_test, x_rand)
self.assertCall( lib.blas_trsv(hdl, lib.enums.CblasLower,
lib.enums.CblasNoTrans, lib.enums.CblasNonUnit,
L, x) )
self.assertCall( lib.vector_memcpy_av(x_ptr, x, 1) )
self.assertVecEqual( x_py, pyresult, TOL * n**0.5, TOL )
self.free_vars('L', 'x', 'hdl')
self.assertCall( lib.ok_device_reset() )
def test_blas2_sbmv(self):
(m, n) = self.shape
diags = max(1, min(4, min(m, n) - 1))
s_test = np.random.rand(n * diags)
x_rand = np.random.rand(n)
y_rand = np.random.rand(n)
for (gpu, single_precision) in self.CONDITIONS:
lib = self.libs.get(single_precision=single_precision, gpu=gpu)
if lib is None:
continue
self.register_exit(lib.ok_device_reset)
DIGITS = 7 - 2 * single_precision
TOL = 10**(-DIGITS)
hdl = self.register_blas_handle(lib, 'hdl')
# make symmetric banded "matrix" S stored as vector s,
# and vectors x, y
s, s_py, s_ptr = self.register_vector(lib, n * diags, 's')
x, x_py, x_ptr = self.register_vector(lib, n, 'x')
y, y_py, y_ptr = self.register_vector(lib, n, 'y')
# populate vectors
s_py += s_test
x_py += x_rand
y_py += y_rand
self.assertCall( lib.vector_memcpy_va(s, s_ptr, 1) )
self.assertCall( lib.vector_memcpy_va(x, x_ptr, 1) )
self.assertCall( lib.vector_memcpy_va(y, y_ptr, 1) )
# y = alpha
alpha = np.random.rand()
beta = np.random.rand()
pyresult = np.zeros(n)
for d in xrange(diags):
for j in xrange(n - d):
if d > 0:
pyresult[d + j] += s_test[d + diags * j] * x_rand[j]
pyresult[j] += s_test[d + diags * j] * x_rand[d + j]
pyresult *= alpha
pyresult += beta * y_py
self.assertCall( lib.blas_sbmv(hdl, lib.enums.CblasColMajor,
lib.enums.CblasLower, diags - 1, alpha, s, x,
beta, y) )
self.assertCall( lib.vector_memcpy_av(y_ptr, y, 1) )
self.assertVecEqual( y_py, pyresult, TOL * m**0.5, TOL )
self.free_vars('x', 'y', 's', 'hdl')
self.assertCall( lib.ok_device_reset() )
def test_diagmv(self):
(m, n) = self.shape
d_test = np.random.rand(n)
x_rand = np.random.rand(n)
y_rand = np.random.rand(n)
for (gpu, single_precision) in self.CONDITIONS:
lib = self.libs.get(single_precision=single_precision, gpu=gpu)
if lib is None:
continue
self.register_exit(lib.ok_device_reset)
DIGITS = 7 - 2 * single_precision
TOL = 10**(-DIGITS)
hdl = self.register_blas_handle(lib, 'hdl')
# make diagonal "matrix" D stored as vector d,
# and vectors x, y
d, d_py, d_ptr = self.register_vector(lib, n, 'd')
x, x_py, x_ptr = self.register_vector(lib, n, 'x')
y, y_py, y_ptr = self.register_vector(lib, n, 'y')
# populate vectors
d_py += d_test
x_py += x_rand
y_py += 2
self.assertCall( lib.vector_memcpy_va(d, d_ptr, 1) )
self.assertCall( lib.vector_memcpy_va(x, x_ptr, 1) )
self.assertCall( lib.vector_memcpy_va(y, y_ptr, 1) )
# y = alpha * D * x + beta * y
alpha = np.random.rand()
beta = np.random.rand()
pyresult = alpha * d_py * x_py + beta * y_py
self.assertCall( lib.blas_diagmv(hdl, alpha, d, x, beta, y) )
self.assertCall( lib.vector_memcpy_av(y_ptr, y, 1) )
self.assertVecEqual( y_py, pyresult, TOL * m**0.5, TOL )
self.free_vars('x', 'y', 'd', 'hdl')
self.assertCall( lib.ok_device_reset() )
def test_blas3_gemm(self):
(m, n) = self.shape
x_rand = np.random.rand(n)
B_test = np.random.rand(m, n)
C_test = np.random.rand(n, n)
for (gpu, single_precision) in self.CONDITIONS:
lib = self.libs.get(single_precision=single_precision, gpu=gpu)
if lib is None:
continue
self.register_exit(lib.ok_device_reset)
DIGITS = 7 - 2 * single_precision - 1 * gpu
RTOL = 10**(-DIGITS)
ATOLMN = RTOL * (m * n)**0.5
for order in (lib.enums.CblasRowMajor, lib.enums.CblasColMajor):
hdl = self.register_blas_handle(lib, 'hdl')
# allocate A, B
A, A_py, A_ptr = self.register_matrix(lib, m, n, order, 'A')
B, B_py, B_ptr = self.register_matrix(lib, m, n, order, 'B')
C, C_py, C_ptr = self.register_matrix(lib, n, n, order, 'C')
# populate
A_py += self.A_test
B_py += B_test
C_py += C_test
self.assertCall( lib.matrix_memcpy_ma(A, A_ptr, order) )
self.assertCall( lib.matrix_memcpy_ma(B, B_ptr, order) )
self.assertCall( lib.matrix_memcpy_ma(C, C_ptr, order) )
# perform C = alpha * B'A + beta * C
alpha = np.random.rand()
beta = np.random.rand()
pyresult = alpha * B_py.T.dot(A_py) + beta * C_py
self.assertCall( lib.blas_gemm(hdl, lib.enums.CblasTrans,
lib.enums.CblasNoTrans, alpha, B, A, beta,
C) )
self.assertCall( lib.matrix_memcpy_am(C_ptr, C, order) )
self.assertVecEqual( C_py, pyresult, ATOLMN, RTOL )
self.free_vars('A', 'B', 'C', 'hdl')
self.assertCall( lib.ok_device_reset() )
def test_blas3_syrk(self):
(m, n) = self.shape
B_test = np.random.rand(n, n)
# make B symmetric
B_test = B_test.T.dot(B_test)
for (gpu, single_precision) in self.CONDITIONS:
lib = self.libs.get(single_precision=single_precision, gpu=gpu)
if lib is None:
continue
self.register_exit(lib.ok_device_reset)
DIGITS = 7 - 2 * single_precision
TOL = 10**(-DIGITS)
for order in (lib.enums.CblasRowMajor, lib.enums.CblasColMajor):
hdl = self.register_blas_handle(lib, 'hdl')
# allocate A, B
A, A_py, A_ptr = self.register_matrix(lib, m, n, order, 'A')
B, B_py, B_ptr = self.register_matrix(lib, n, n, order, 'B')
# populate
A_py += self.A_test[:, :]
B_py += B_test
self.assertCall( lib.matrix_memcpy_ma(A, A_ptr, order) )
self.assertCall( lib.matrix_memcpy_ma(B, B_ptr, order) )
# B = alpha * (A'A) + beta * B
alpha = np.random.rand()
beta = np.random.rand()
pyresult = alpha * A_py.T.dot(A_py) + beta * B_py
self.assertCall( lib.blas_syrk(hdl, lib.enums.CblasLower,
lib.enums.CblasTrans, alpha, A, beta, B) )
self.assertCall( lib.matrix_memcpy_am(B_ptr, B, order) )
for i in xrange(n):
for j in xrange(n):
if j > i:
pyresult[i, j] *= 0
B_py[i, j] *= 0
self.assertVecEqual( B_py, pyresult, TOL * n, TOL )
self.free_vars('A', 'B', 'hdl')
self.assertCall( lib.ok_device_reset() )
def test_blas3_trsm(self):
(m, n) = self.shape
# make square, invertible L
L_test = np.random.rand(n, n)
for i in xrange(n):
L_test[i, i] /= 10**np.log(n)
L_test[i, i] += 1
for j in xrange(n):
if j > i:
L_test[i, j]*= 0
for (gpu, single_precision) in self.CONDITIONS:
if gpu:
continue
lib = self.libs.get(single_precision=single_precision, gpu=gpu)
if lib is None:
continue
self.register_exit(lib.ok_device_reset)
DIGITS = 7 - 2 * single_precision
RTOL = 10**(-DIGITS)
ATOLMN = RTOL * (m * n)**0.5
for order in (lib.enums.CblasRowMajor, lib.enums.CblasColMajor):
hdl = self.register_blas_handle(lib, 'hdl')
# allocate A, L
A, A_py, A_ptr = self.register_matrix(lib, m, n, order, 'A')
L, L_py, L_ptr = self.register_matrix(lib, n, n, order, 'L')
# populate
A_py += self.A_test
L_py += L_test
self.assertCall( lib.matrix_memcpy_ma(A, A_ptr, order) )
self.assertCall( lib.matrix_memcpy_ma(L, L_ptr, order) )
# A = A * inv(L)
pyresult = A_py.dot(np.linalg.inv(L_test))
self.assertCall( lib.blas_trsm(hdl, lib.enums.CblasRight,
lib.enums.CblasLower, lib.enums.CblasNoTrans,
lib.enums.CblasNonUnit, 1., L, A) )
self.assertCall( lib.matrix_memcpy_am(A_ptr, A, order) )
self.assertVecEqual( A_py, pyresult, ATOLMN, RTOL )
self.free_vars('A', 'L', 'hdl')
self.assertCall( lib.ok_device_reset() )
class DenseLinalgTestCase(OptkitCTestCase):
@classmethod
def setUpClass(self):
self.env_orig = os.getenv('OPTKIT_USE_LOCALLIBS', '0')
os.environ['OPTKIT_USE_LOCALLIBS'] = '1'
self.libs = DenseLinsysLibs()
self.A_test = self.A_test_gen
@classmethod
def tearDownClass(self):
os.environ['OPTKIT_USE_LOCALLIBS'] = self.env_orig
def setUp(self):
pass
def tearDown(self):
self.free_all_vars()
self.exit_call()
def test_cholesky(self):
(m, n) = self.shape
mindim = min(m, n)
# build decently conditioned symmetric matrix
AA_test = self.A_test.T.dot(self.A_test)[:mindim, :mindim]
AA_test /= np.linalg.norm(AA_test) * mindim**0.5
for i in xrange(mindim):
# diagonal entries ~ 1 to keep condition number reasonable
AA_test[i, i] /= 10**np.log(mindim)
AA_test[i, i] += 1
# upper triangle = 0
for j in xrange(mindim):
if j > i:
AA_test[i, j] *= 0
AA_test += AA_test.T
x_rand = np.random.rand(mindim)
pysol = np.linalg.solve(AA_test, x_rand)
pychol = np.linalg.cholesky(AA_test)
for (gpu, single_precision) in self.CONDITIONS:
lib = self.libs.get(single_precision=single_precision, gpu=gpu)
if lib is None:
continue
self.register_exit(lib.ok_device_reset)
for order in (lib.enums.CblasRowMajor, lib.enums.CblasColMajor):
hdl = self.register_blas_handle(lib, 'hdl')
# allocate L, x
L, L_py, L_ptr = self.register_matrix(
lib, mindim, mindim, order, 'L')
x, x_py, x_ptr = self.register_vector(lib, mindim, 'x')
# populate L
L_py *= 0
L_py += AA_test
self.assertCall( lib.matrix_memcpy_ma(L, L_ptr, order) )
# cholesky factorization
self.assertCall( lib.linalg_cholesky_decomp(hdl, L) )
self.assertCall( lib.matrix_memcpy_am(L_ptr, L, order) )
for i in xrange(mindim):
for j in xrange(mindim):
if j > i:
L_py[i, j] *= 0
imprecision_factor = 5**(int(gpu) + int(single_precision))
atol = 1e-2 * imprecision_factor * mindim
rtol = 1e-2 * imprecision_factor
self.assertVecEqual( L_py.dot(x_rand), pychol.dot(x_rand),
atol, rtol )
# populate x
x_py *= 0
x_py += x_rand
self.assertCall( lib.vector_memcpy_va(x, x_ptr, 1) )
# cholesky solve
self.assertCall( lib.linalg_cholesky_svx(hdl, L, x) )
self.assertCall( lib.vector_memcpy_av(x_ptr, x, 1) )
self.assertVecEqual( x_py, pysol, atol * mindim**0.5, rtol )
self.free_vars('L', 'x', 'hdl')
self.assertCall( lib.ok_device_reset() )
def test_row_squares(self):
m, n = self.shape
for (gpu, single_precision) in self.CONDITIONS:
lib = self.libs.get(single_precision=single_precision, gpu=gpu)
if lib is None:
continue
self.register_exit(lib.ok_device_reset)
DIGITS = 7 - 5 * lib.FLOAT - 1 * lib.GPU
RTOL = 10**(-DIGITS)
ATOLM = RTOL * m**0.5
ATOLN = RTOL * n**0.5
for order in (lib.enums.CblasRowMajor, lib.enums.CblasColMajor):
# allocate A, r, c
A, A_py, A_ptr = self.register_matrix(lib, m, n, order, 'A')
c, c_py, c_ptr = self.register_vector(lib, n, 'c')
r, r_py, r_ptr = self.register_vector(lib, m, 'r')
A_py += self.A_test
self.assertCall( lib.matrix_memcpy_ma(A, A_ptr, order) )
py_rows = [A_py[i, :].dot(A_py[i, :]) for i in xrange(m)]
py_cols = [A_py[:, j].dot(A_py[:, j]) for j in xrange(n)]
# C: calculate row squares
self.assertCall( lib.linalg_matrix_row_squares(
lib.enums.CblasNoTrans, A, r) )
self.assertCall( lib.vector_memcpy_av(r_ptr, r, 1) )
# compare C vs Python results
self.assertVecEqual( r_py, py_rows, ATOLM, RTOL )
# C: calculate column squares
self.assertCall( lib.linalg_matrix_row_squares(
lib.enums.CblasTrans, A, c) )
self.assertCall( lib.vector_memcpy_av(c_ptr, c, 1) )
# compare C vs Python results
self.assertVecEqual( c_py, py_cols, ATOLN, RTOL )
# free memory
self.free_vars('A', 'r', 'c')
self.assertCall( lib.ok_device_reset() )
def test_broadcast(self):
(m, n) = self.shape
for (gpu, single_precision) in self.CONDITIONS:
lib = self.libs.get(single_precision=single_precision, gpu=gpu)
if lib is None:
continue
self.register_exit(lib.ok_device_reset)
DIGITS = 7 - 5 * lib.FLOAT - 1 * lib.GPU
RTOL = 10**(-DIGITS)
ATOLM = RTOL * m**0.5
for order in (lib.enums.CblasRowMajor, lib.enums.CblasColMajor):
hdl = self.register_blas_handle(lib, 'hdl')
# allocate A, d, e, x, y
A, A_py, A_ptr = self.register_matrix(lib, m, n, order, 'A')
d, d_py, d_ptr = self.register_vector(lib, m, 'd')
e, e_py, e_ptr = self.register_vector(lib, n, 'e')
x, x_py, x_ptr = self.register_vector(lib, n, 'x')
y, y_py, y_ptr = self.register_vector(lib, m, 'y')
A_py += self.A_test
d_py += np.random.rand(m)
e_py += np.random.rand(n)
x_py += np.random.rand(n)
self.assertCall( lib.matrix_memcpy_ma(A, A_ptr, order) )
self.assertCall( lib.vector_memcpy_va(d, d_ptr, 1) )
self.assertCall( lib.vector_memcpy_va(e, e_ptr, 1) )
self.assertCall( lib.vector_memcpy_va(x, x_ptr, 1) )
# A = A * diag(E)
self.assertCall( lib.linalg_matrix_broadcast_vector(A, e,
lib.enums.OkTransformScale,
lib.enums.CblasRight) )
self.assertCall( lib.blas_gemv(hdl, lib.enums.CblasNoTrans, 1,
A, x, 0, y) )
self.assertCall( lib.vector_memcpy_av(y_ptr, y, 1) )
Ax = y_py
AEx = A_py.dot(e_py * x_py)
self.assertVecEqual( Ax, AEx, ATOLM, RTOL )
# A = diag(D) * A
self.assertCall( lib.linalg_matrix_broadcast_vector(A, d,
lib.enums.OkTransformScale,
lib.enums.CblasLeft) )
self.assertCall( lib.blas_gemv(hdl, lib.enums.CblasNoTrans, 1,
A, x, 0, y) )
self.assertCall( lib.vector_memcpy_av(y_ptr, y, 1) )
Ax = y_py
DAEx = d_py * AEx
self.assertVecEqual( Ax, DAEx, ATOLM, RTOL )
# A += 1e'
self.assertCall( lib.linalg_matrix_broadcast_vector(A, e,
lib.enums.OkTransformAdd,
lib.enums.CblasRight) )
self.assertCall( lib.blas_gemv(hdl, lib.enums.CblasNoTrans, 1,
A, x, 0, y) )
self.assertCall( lib.vector_memcpy_av(y_ptr, y, 1) )
Ax = y_py
A_updatex = DAEx + np.ones(m) * e_py.dot(x_py)
self.assertVecEqual( Ax, A_updatex, ATOLM, RTOL )
# A += d1'
self.assertCall( lib.linalg_matrix_broadcast_vector(A, d,
lib.enums.OkTransformAdd,
lib.enums.CblasLeft) )
self.assertCall( lib.blas_gemv(hdl, lib.enums.CblasNoTrans, 1,
A, x, 0, y) )
self.assertCall( lib.vector_memcpy_av(y_ptr, y, 1) )
Ax = y_py
A_updatex += d_py * sum(x_py)
self.assertVecEqual( Ax, A_updatex, ATOLM, RTOL )
# free memory
self.free_vars('A', 'd', 'e', 'x', 'y', 'hdl')
self.assertCall( lib.ok_device_reset() )
def test_reduce(self):
(m, n) = self.shape
for (gpu, single_precision) in self.CONDITIONS:
lib = self.libs.get(single_precision=single_precision, gpu=gpu)
if lib is None:
continue
self.register_exit(lib.ok_device_reset)
DIGITS = 7 - 5 * lib.FLOAT - 1 * lib.GPU
RTOL = 10**(-DIGITS)
ATOLM = RTOL * m**0.5
ATOLN = RTOL * n**0.5
for order in (lib.enums.CblasRowMajor, lib.enums.CblasColMajor):
hdl = self.register_blas_handle(lib, 'hdl')
# allocate A, d, e, x, y
A, A_py, A_ptr = self.register_matrix(lib, m, n, order, 'A')
d, d_py, d_ptr = self.register_vector(lib, m, 'd')
e, e_py, e_ptr = self.register_vector(lib, n, 'e')
x, x_py, x_ptr = self.register_vector(lib, n, 'x')
y, y_py, y_ptr = self.register_vector(lib, m, 'y')
A_py += self.A_test
self.assertCall( lib.matrix_memcpy_ma(A, A_ptr, order) )
x_py += np.random.rand(n)
self.assertCall( lib.vector_memcpy_va(x, x_ptr, 1) )
# min - reduce columns
colmin = np.min(A_py, 0)
self.assertCall( lib.linalg_matrix_reduce_min(e, A,
lib.enums.CblasLeft) )
self.assertCall( lib.vector_memcpy_av(e_ptr, e, 1) )
self.assertVecEqual( e_py, colmin, ATOLN, RTOL )
# min - reduce rows
rowmin = np.min(A_py, 1)
self.assertCall( lib.linalg_matrix_reduce_min(d, A,
lib.enums.CblasRight) )
self.assertCall( lib.vector_memcpy_av(d_ptr, d, 1) )
self.assertVecEqual( d_py, rowmin, ATOLM, RTOL )
# max - reduce columns
colmax = np.max(A_py, 0)
self.assertCall( lib.linalg_matrix_reduce_max(e, A,
lib.enums.CblasLeft) )
self.assertCall( lib.vector_memcpy_av(e_ptr, e, 1) )
self.assertVecEqual( e_py, colmax, ATOLN, RTOL )
# max - reduce rows
rowmax = np.max(A_py, 1)
self.assertCall( lib.linalg_matrix_reduce_max(d, A,
lib.enums.CblasRight) )
self.assertCall( lib.vector_memcpy_av(d_ptr, d, 1) )
self.assertVecEqual( d_py, rowmax, ATOLM, RTOL )
# indmin - reduce columns
idx, inds, inds_ptr = self.register_indvector(lib, n, 'idx')
self.assertCall( lib.linalg_matrix_reduce_indmin(idx, e, A,
lib.enums.CblasLeft) )
self.assertCall( lib.indvector_memcpy_av(inds_ptr, idx, 1) )
self.free_var('idx')
calcmin = np.array([A_py[inds[i], i] for i in xrange(n)])
colmin = np.min(A_py, 0)
self.assertVecEqual( calcmin, colmin, ATOLN, RTOL )
# indmin - reduce rows
idx, inds, inds_ptr = self.register_indvector(lib, m, 'idx')
self.assertCall( lib.linalg_matrix_reduce_indmin(idx, d, A,
lib.enums.CblasRight) )
self.assertCall( lib.indvector_memcpy_av(inds_ptr, idx, 1) )
self.free_var('idx')
calcmin = np.array([A_py[i, inds[i]] for i in xrange(m)])
rowmin = np.min(A_py, 1)
self.assertVecEqual( calcmin, rowmin, ATOLM, RTOL )
# free memory
self.free_vars('A', 'd', 'e', 'x', 'y', 'hdl')
self.assertCall(lib.ok_device_reset() )
class MatrixTestCase(OptkitCTestCase):
@classmethod
def setUpClass(self):
self.env_orig = os.getenv('OPTKIT_USE_LOCALLIBS', '0')
os.environ['OPTKIT_USE_LOCALLIBS'] = '1'
self.libs = DenseLinsysLibs()
self.A_test = self.A_test_gen
@classmethod
def tearDownClass(self):
os.environ['OPTKIT_USE_LOCALLIBS'] = self.env_orig
def setUp(self):
pass
def tearDown(self):
self.free_all_vars()
self.exit_call()
def test_alloc(self):
(m, n) = self.shape
for (gpu, single_precision) in self.CONDITIONS:
lib = self.libs.get(single_precision=single_precision, gpu=gpu)
if lib is None:
continue
self.register_exit(lib.ok_device_reset)
for order in (lib.enums.CblasRowMajor, lib.enums.CblasColMajor):
A = lib.matrix(0, 0, 0, None, order)
self.assertEqual(A.size1, 0)
self.assertEqual(A.size2, 0)
self.assertEqual(A.ld, 0)
self.assertEqual(A.order, order)
# calloc
self.assertCall(lib.matrix_calloc(A, m, n, order))
self.register_var('A', A, lib.matrix_free)
self.assertEqual(A.size1, m)
self.assertEqual(A.size2, n)
if order == lib.enums.CblasRowMajor:
self.assertEqual(A.ld, n)
else:
self.assertEqual(A.ld, m)
self.assertEqual(A.order, order)
if not gpu:
for i in xrange(m * n):
self.assertEqual(A.data[i], 0)
# free
self.free_var('A')
self.assertCall(lib.ok_device_reset())
def test_io(self):
(m, n) = self.shape
A_rand = self.A_test
x_rand = np.random.rand(n)
for (gpu, single_precision) in self.CONDITIONS:
lib = self.libs.get(single_precision=single_precision, gpu=gpu)
if lib is None:
continue
self.register_exit(lib.ok_device_reset)
DIGITS = 11 - 4 * lib.FLOAT - 1 * lib.GPU
TOL = 10**(-DIGITS)
for order in (lib.enums.CblasRowMajor, lib.enums.CblasColMajor):
A, A_py, A_ptr = self.register_matrix(lib, m, n, order, 'A')
# memcpy_am
# set A_py to A_rand. overwrite A_py with zeros from A
A_py += A_rand
self.assertCall(lib.matrix_memcpy_am(A_ptr, A, order))
for i in xrange(m):
for j in xrange(n):
self.assertEqual(A_py[i, j], 0)
# memcpy_ma
A_py += A_rand
self.assertCall(lib.matrix_memcpy_ma(A, A_ptr, order))
A_py *= 0
self.assertCall(lib.matrix_memcpy_am(A_ptr, A, order))
self.assertVecEqual(A_py, A_rand, TOL, TOL)
# memcpy_mm
Z, Z_py, Z_ptr = self.register_matrix(lib, m, n, order, 'Z')
self.assertCall(lib.matrix_memcpy_mm(Z, A, order))
self.assertCall(lib.matrix_memcpy_am(Z_ptr, Z, order))
self.assertVecEqual(Z_py, A_py, TOL, TOL)
# view_array
if not gpu:
A_py *= 0
B = lib.matrix(0, 0, 0, None, order)
self.assertCall(
lib.matrix_view_array(
B, A_rand.ctypes.data_as(lib.ok_float_p), m, n,
order))
self.assertCall(lib.matrix_memcpy_am(A_ptr, A, order))
self.assertVecEqual(A_py, A_rand, TOL, TOL)
# set_all
val = 2
A_rand *= 0
A_rand += val
self.assertCall(lib.matrix_set_all(A, val))
self.assertCall(lib.matrix_memcpy_am(A_ptr, A, order))
self.assertVecEqual(A_py, A_rand, TOL, TOL)
self.free_vars('A', 'Z')
self.assertCall(lib.ok_device_reset())
def test_slicing(self):
""" matrix slicing tests """
(m, n) = self.shape
A_rand = self.A_test
x_rand = np.random.rand(n)
for (gpu, single_precision) in self.CONDITIONS:
lib = self.libs.get(single_precision=single_precision, gpu=gpu)
if lib is None:
continue
self.register_exit(lib.ok_device_reset)
DIGITS = 7 - 2 * lib.FLOAT - 1 * lib.GPU
TOL = 10**(-DIGITS)
for order in (lib.enums.CblasRowMajor, lib.enums.CblasColMajor):
pyorder = 'C' if order == lib.enums.CblasRowMajor else 'F'
A, A_py, A_ptr = self.register_matrix(lib, m, n, order, 'A')
# set A, A_py to A_rand
A_py += A_rand
self.assertCall(lib.matrix_memcpy_ma(A, A_ptr, order))
# submatrix
m0 = m / 4
n0 = n / 4
msub = m / 2
nsub = n / 2
Asub = lib.matrix(0, 0, 0, None, order)
Asub_py = np.zeros((msub, nsub),
order=pyorder).astype(lib.pyfloat)
Asub_ptr = Asub_py.ctypes.data_as(lib.ok_float_p)
self.assertCall(
lib.matrix_submatrix(Asub, A, m0, n0, msub, nsub))
self.assertCall(lib.matrix_memcpy_am(Asub_ptr, Asub, order))
A_py_sub = A_py[m0:m0 + msub, n0:n0 + nsub]
self.assertVecEqual(Asub_py, A_py_sub, TOL, TOL)
# row
v = lib.vector(0, 0, None)
v_py = np.zeros(n).astype(lib.pyfloat)
v_ptr = v_py.ctypes.data_as(lib.ok_float_p)
self.assertCall(lib.matrix_row(v, A, m0))
self.assertCall(lib.vector_memcpy_av(v_ptr, v, 1))
self.assertVecEqual(A_py[m0, :], v_py, TOL, TOL)
# column
v_py = np.zeros(m).astype(lib.pyfloat)
v_ptr = v_py.ctypes.data_as(lib.ok_float_p)
self.assertCall(lib.matrix_column(v, A, n0))
self.assertCall(lib.vector_memcpy_av(v_ptr, v, 1))
self.assertVecEqual(A_py[:, n0], v_py, TOL, TOL)
# diagonal
v_py = np.zeros(min(m, n)).astype(lib.pyfloat)
v_ptr = v_py.ctypes.data_as(lib.ok_float_p)
self.assertCall(lib.matrix_diagonal(v, A))
self.assertCall(lib.vector_memcpy_av(v_ptr, v, 1))
self.assertVecEqual(np.diag(A_py), v_py, TOL, TOL)
self.free_var('A')
self.assertCall(lib.ok_device_reset())
def test_math(self):
""" matrix math tests """
(m, n) = self.shape
A_rand = self.A_test
for (gpu, single_precision) in self.CONDITIONS:
lib = self.libs.get(single_precision=single_precision, gpu=gpu)
if lib is None:
continue
self.register_exit(lib.ok_device_reset)
DIGITS = 7 - 2 * lib.FLOAT - 1 * lib.GPU
RTOL = 10**(-DIGITS)
ATOLMN = RTOL * (m * n)**0.5
for order in (lib.enums.CblasRowMajor, lib.enums.CblasColMajor):
A, A_py, A_ptr = self.register_matrix(lib, m, n, order, 'A')
# set A, A_py to A_rand
A_py += A_rand
self.assertCall(lib.matrix_memcpy_ma(A, A_ptr, order))
# scale: A = alpha * A
alpha = np.random.rand()
A_rand *= alpha
self.assertCall(lib.matrix_scale(A, alpha))
self.assertCall(lib.matrix_memcpy_am(A_ptr, A, order))
self.assertVecEqual(A_py, A_rand, ATOLMN, RTOL)
# scale_left: A = diag(d) * A
d, d_py, d_ptr = self.register_vector(lib, m, 'd')
d_py[:] = np.random.rand(m)
for i in xrange(m):
A_rand[i, :] *= d_py[i]
self.assertCall(lib.vector_memcpy_va(d, d_ptr, 1))
self.assertCall(lib.matrix_scale_left(A, d))
self.assertCall(lib.matrix_memcpy_am(A_ptr, A, order))
self.assertVecEqual(A_py, A_rand, ATOLMN, RTOL)
# scale_right: A = A * diag(e)
e, e_py, e_ptr = self.register_vector(lib, n, 'e')
e_py[:] = np.random.rand(n)
for j in xrange(n):
A_rand[:, j] *= e_py[j]
self.assertCall(lib.vector_memcpy_va(e, e_ptr, 1))
self.assertCall(lib.matrix_scale_right(A, e))
self.assertCall(lib.matrix_memcpy_am(A_ptr, A, order))
self.assertVecEqual(A_py, A_rand, ATOLMN, RTOL)
# abs: A_ij = abs(A_ij)
A_rand -= (A_rand.max() - A_rand.min()) / 2
A_py *= 0
A_py += A_rand
A_rand = np.abs(A_rand)
self.assertCall(lib.matrix_memcpy_ma(A, A_ptr, order))
self.assertCall(lib.matrix_abs(A))
self.assertCall(lib.matrix_memcpy_am(A_ptr, A, order))
self.assertVecEqual(A_py, A_rand, ATOLMN, RTOL)
# pow
p = 3 * np.random.rand()
A_rand **= p
self.assertCall(lib.matrix_pow(A, p))
self.assertCall(lib.matrix_memcpy_am(A_ptr, A, order))
self.assertVecEqual(A_py, A_rand, ATOLMN, RTOL)
self.free_vars('d', 'e', 'A')
self.assertCall(lib.ok_device_reset())
class VectorTestCase(OptkitCTestCase):
@classmethod
def setUpClass(self):
self.env_orig = os.getenv('OPTKIT_USE_LOCALLIBS', '0')
os.environ['OPTKIT_USE_LOCALLIBS'] = '1'
self.libs = DenseLinsysLibs()
@classmethod
def tearDownClass(self):
os.environ['OPTKIT_USE_LOCALLIBS'] = self.env_orig
def tearDown(self):
self.free_all_vars()
self.exit_call()
def test_alloc(self):
for (gpu, single_precision) in self.CONDITIONS:
lib = self.libs.get(single_precision=single_precision, gpu=gpu)
if lib is None:
continue
self.register_exit(lib.ok_device_reset)
len_v = 10 + int(10 * np.random.rand())
v = lib.vector(0, 0, None)
self.assertEqual(v.size, 0)
self.assertEqual(v.stride, 0)
self.assertCall(lib.vector_calloc(v, len_v))
self.register_var('v', v, lib.vector_free)
self.assertEqual(v.size, len_v)
self.assertEqual(v.stride, 1)
if not gpu:
for i in range(v.size):
self.assertEqual(v.data[i], 0)
self.free_var('v')
self.assertEqual(v.size, 0)
self.assertEqual(v.stride, 0)
def test_io(self):
for (gpu, single_precision) in self.CONDITIONS:
lib = self.libs.get(single_precision=single_precision, gpu=gpu)
if lib is None:
continue
self.register_exit(lib.ok_device_reset)
len_v = 10 + int(1000 * np.random.rand())
DIGITS = 7 - 2 * single_precision
RTOL = 10**(-DIGITS)
ATOL = RTOL * len_v**0.5
v, v_py, v_ptr = self.register_vector(lib, len_v, 'v')
w, w_py, w_ptr = self.register_vector(lib, len_v, 'w')
# set_all
set_val = 5
self.assertCall(lib.vector_set_all(v, set_val))
# memcpy_av
self.assertCall(lib.vector_memcpy_av(v_ptr, v, 1))
for i in range(len_v):
self.assertEqual(v_py[i], set_val)
# memcpy_va
w_rand = np.random.rand(len_v)
w_py[:] = w_rand[:]
self.assertCall(lib.vector_memcpy_va(w, w_ptr, 1))
w_py *= 0
self.assertCall(lib.vector_memcpy_av(w_ptr, w, 1))
self.assertVecEqual(w_py, w_rand, ATOL, RTOL)
# memcpy_vv
self.assertCall(lib.vector_memcpy_vv(v, w))
self.assertCall(lib.vector_memcpy_av(v_ptr, v, 1))
self.assertVecEqual(v_py, w_rand, ATOL, RTOL)
# view_array
if not gpu:
u_rand = np.random.rand(len_v).astype(lib.pyfloat)
u_ptr = u_rand.ctypes.data_as(lib.ok_float_p)
u = lib.vector(0, 0, None)
self.assertCall(lib.vector_view_array(u, u_ptr, u_rand.size))
self.assertCall(lib.vector_memcpy_av(v_ptr, u, 1))
self.assertVecEqual(v_py, u_rand, ATOL, RTOL)
# DON'T FREE u, DATA OWNED BY PYTHON
self.free_vars('v', 'w')
self.assertCall(lib.ok_device_reset())
def test_subvector(self):
for (gpu, single_precision) in self.CONDITIONS:
lib = self.libs.get(single_precision=single_precision, gpu=gpu)
if lib is None:
continue
self.register_exit(lib.ok_device_reset)
len_v = 10 + int(10 * np.random.rand())
v, v_py, v_ptr = self.register_vector(lib, len_v, 'v')
offset_sub = 3
len_sub = 3
v_sub = lib.vector(0, 0, None)
self.assertCall(lib.vector_subvector(v_sub, v, offset_sub,
len_sub))
self.assertEqual(v_sub.size, 3)
self.assertEqual(v_sub.stride, v.stride)
v_sub_py = np.zeros(len_sub).astype(lib.pyfloat)
v_sub_ptr = v_sub_py.ctypes.data_as(lib.ok_float_p)
self.assertCall(lib.vector_memcpy_av(v_ptr, v, 1))
self.assertCall(lib.vector_memcpy_av(v_sub_ptr, v_sub, 1))
for i in range(len_sub):
self.assertEqual(v_sub_py[i], v_py[i + offset_sub])
self.free_var('v')
self.assertCall(lib.ok_device_reset())
def test_math(self):
for (gpu, single_precision) in self.CONDITIONS:
lib = self.libs.get(single_precision=single_precision, gpu=gpu)
if lib is None:
continue
self.register_exit(lib.ok_device_reset)
val1 = 12 * np.random.rand()
val2 = 5 * np.random.rand()
len_v = 10 + int(1000 * np.random.rand())
# len_v = 10 + int(10 * np.random.rand())
DIGITS = 7 - 2 * lib.FLOAT - 1 * lib.GPU
RTOL = 10**(-DIGITS)
ATOL = RTOL * len_v**0.5
v, v_py, v_ptr = self.register_vector(lib, len_v, 'v')
w, w_py, w_ptr = self.register_vector(lib, len_v, 'w')
# constant addition
self.assertCall(lib.vector_add_constant(v, val1))
self.assertCall(lib.vector_add_constant(w, val2))
self.assertCall(lib.vector_memcpy_av(v_ptr, v, 1))
self.assertCall(lib.vector_memcpy_av(w_ptr, w, 1))
self.assertVecEqual(v_py, val1, ATOL, RTOL)
self.assertVecEqual(w_py, val2, ATOL, RTOL)
# add two vectors
self.assertCall(lib.vector_add(v, w))
val1 += val2
self.assertCall(lib.vector_memcpy_av(v_ptr, v, 1))
self.assertCall(lib.vector_memcpy_av(w_ptr, w, 1))
self.assertVecEqual(v_py, val1, ATOL, RTOL)
self.assertVecEqual(w_py, val2, ATOL, RTOL)
# subtract two vectors
self.assertCall(lib.vector_sub(w, v))
val2 -= val1
self.assertCall(lib.vector_memcpy_av(v_ptr, v, 1))
self.assertCall(lib.vector_memcpy_av(w_ptr, w, 1))
self.assertVecEqual(v_py, val1, ATOL, RTOL)
self.assertVecEqual(w_py, val2, ATOL, RTOL)
# multiply two vectors
self.assertCall(lib.vector_mul(v, w))
val1 *= val2
self.assertCall(lib.vector_memcpy_av(v_ptr, v, 1))
self.assertCall(lib.vector_memcpy_av(w_ptr, w, 1))
self.assertVecEqual(v_py, val1, ATOL, RTOL)
self.assertVecEqual(w_py, val2, ATOL, RTOL)
# vector scale
scal = 3 * np.random.rand()
val1 *= scal
self.assertCall(lib.vector_scale(v, scal))
self.assertCall(lib.vector_memcpy_av(v_ptr, v, 1))
self.assertVecEqual(v_py, val1, ATOL, RTOL)
# make sure v is strictly positive
val1 = 0.7 + np.random.rand()
self.assertCall(lib.vector_scale(v, 0))
self.assertCall(lib.vector_add_constant(v, val1))
# divide two vectors
self.assertCall(lib.vector_div(w, v))
val2 /= float(val1)
self.assertCall(lib.vector_memcpy_av(v_ptr, v, 1))
self.assertCall(lib.vector_memcpy_av(w_ptr, w, 1))
self.assertVecEqual(v_py, val1, ATOL, RTOL)
self.assertVecEqual(w_py, val2, ATOL, RTOL)
# make w strictly negative
w_max = w_py.max()
val2 -= (w_max + 1)
self.assertCall(lib.vector_add_constant(w, -(w_max + 1)))
# vector abs
self.assertCall(lib.vector_abs(w))
val2 = abs(val2)
self.assertCall(lib.vector_memcpy_av(w_ptr, w, 1))
self.assertVecEqual(w_py, val2, ATOL, RTOL)
# vector recip
self.assertCall(lib.vector_recip(w))
val2 = 1. / val2
self.assertCall(lib.vector_memcpy_av(w_ptr, w, 1))
self.assertVecEqual(w_py, val2, ATOL, RTOL)
# vector sqrt
self.assertCall(lib.vector_sqrt(w))
val2 **= 0.5
self.assertCall(lib.vector_memcpy_av(w_ptr, w, 1))
self.assertVecEqual(w_py, val2, ATOL, RTOL)
# vector pow
pow_val = -2 + 4 * np.random.rand()
self.assertCall(lib.vector_pow(w, pow_val))
val2 **= pow_val
self.assertCall(lib.vector_memcpy_av(w_ptr, w, 1))
self.assertVecEqual(w_py, val2, ATOL, RTOL)
# vector exp
self.assertCall(lib.vector_exp(w))
val2 = np.exp(val2)
self.assertCall(lib.vector_memcpy_av(w_ptr, w, 1))
self.assertVecEqual(val2, w_py, ATOL, RTOL)
# min / max
w_py *= 0
w_py += np.random.rand(len(w_py))
self.assertCall(lib.vector_memcpy_va(w, w_ptr, 1))
# vector argmin
wargmin = np.zeros(1).astype(c_size_t)
wargmin_p = wargmin.ctypes.data_as(lib.c_size_t_p)
self.assertCall(lib.vector_indmin(w, wargmin_p))
self.assertScalarEqual(w_py[wargmin[0]], w_py.min(), RTOL)
# # vector min
wmin = np.zeros(1).astype(lib.pyfloat)
wmin_p = wmin.ctypes.data_as(lib.ok_float_p)
self.assertCall(lib.vector_min(w, wmin_p))
self.assertScalarEqual(wmin[0], w_py.min(), RTOL)
# # vector max
wmax = wmin
wmax_p = wmin_p
self.assertCall(lib.vector_max(w, wmax_p))
self.assertScalarEqual(wmax[0], w_py.max(), RTOL)
self.free_vars('v', 'w')
self.assertCall(lib.ok_device_reset())
def test_indvector_math(self):
for (gpu, single_precision) in self.CONDITIONS:
lib = self.libs.get(single_precision=single_precision, gpu=gpu)
if lib is None:
continue
self.register_exit(lib.ok_device_reset)
val1 = 12 * np.random.rand()
val2 = 5 * np.random.rand()
len_v = 10 + int(1000 * np.random.rand())
# len_v = 10 + int(10 * np.random.rand())
DIGITS = 7 - 2 * lib.FLOAT - 1 * lib.GPU
RTOL = 10**(-DIGITS)
w, w_py, w_ptr = self.register_indvector(lib, len_v, 'w')
# min / max
w_py *= 0
w_py += (30 * np.random.rand(len(w_py))).astype(w_py.dtype)
self.assertCall(lib.indvector_memcpy_va(w, w_ptr, 1))
# vector argmin
wargmin = np.zeros(1).astype(c_size_t)
wargmin_p = wargmin.ctypes.data_as(lib.c_size_t_p)
self.assertCall(lib.indvector_indmin(w, wargmin_p))
self.assertScalarEqual(w_py[wargmin[0]], w_py.min(), RTOL)
# # vector min
wmin = wargmin
wmin_p = wargmin_p
self.assertCall(lib.indvector_min(w, wmin_p))
self.assertScalarEqual(wmin[0], w_py.min(), RTOL)
# vector max
wmax = wmin
wmax_p = wmin_p
self.assertCall(lib.indvector_max(w, wmax_p))
self.assertScalarEqual(wmax[0], w_py.max(), RTOL)
self.free_var('w')
self.assertCall(lib.ok_device_reset())
class MatrixTestCase(OptkitCTestCase):
@classmethod
def setUpClass(self):
self.env_orig = os.getenv('OPTKIT_USE_LOCALLIBS', '0')
os.environ['OPTKIT_USE_LOCALLIBS'] = '1'
self.libs = DenseLinsysLibs()
self.A_test = self.A_test_gen
@classmethod
def tearDownClass(self):
os.environ['OPTKIT_USE_LOCALLIBS'] = self.env_orig
def setUp(self):
pass
def tearDown(self):
self.free_all_vars()
self.exit_call()
def test_alloc(self):
(m, n) = self.shape
for (gpu, single_precision) in self.CONDITIONS:
lib = self.libs.get(single_precision=single_precision, gpu=gpu)
if lib is None:
continue
self.register_exit(lib.ok_device_reset)
for order in (lib.enums.CblasRowMajor, lib.enums.CblasColMajor):
A = lib.matrix(0, 0, 0, None, order)
self.assertEqual( A.size1, 0 )
self.assertEqual( A.size2, 0 )
self.assertEqual( A.ld, 0 )
self.assertEqual( A.order, order )
# calloc
self.assertCall( lib.matrix_calloc(A, m, n, order) )
self.register_var('A', A, lib.matrix_free)
self.assertEqual( A.size1, m )
self.assertEqual( A.size2, n )
if order == lib.enums.CblasRowMajor:
self.assertEqual( A.ld, n )
else:
self.assertEqual( A.ld, m )
self.assertEqual( A.order, order )
if not gpu:
for i in xrange(m * n):
self.assertEqual( A.data[i], 0 )
# free
self.free_var('A')
self.assertCall( lib.ok_device_reset() )
def test_io(self):
(m, n) = self.shape
A_rand = self.A_test
x_rand = np.random.rand(n)
for (gpu, single_precision) in self.CONDITIONS:
lib = self.libs.get(single_precision=single_precision, gpu=gpu)
if lib is None:
continue
self.register_exit(lib.ok_device_reset)
DIGITS = 11 - 4 * lib.FLOAT - 1 * lib.GPU
TOL = 10**(-DIGITS)
for order in (lib.enums.CblasRowMajor, lib.enums.CblasColMajor):
A, A_py, A_ptr = self.register_matrix(lib, m, n, order, 'A')
# memcpy_am
# set A_py to A_rand. overwrite A_py with zeros from A
A_py += A_rand
self.assertCall( lib.matrix_memcpy_am(A_ptr, A, order) )
for i in xrange(m):
for j in xrange(n):
self.assertEqual( A_py[i, j], 0)
# memcpy_ma
A_py += A_rand
self.assertCall( lib.matrix_memcpy_ma(A, A_ptr, order) )
A_py *= 0
self.assertCall( lib.matrix_memcpy_am(A_ptr, A, order) )
self.assertVecEqual( A_py, A_rand, TOL, TOL )
# memcpy_mm
Z, Z_py, Z_ptr = self.register_matrix(lib, m, n, order, 'Z')
self.assertCall( lib.matrix_memcpy_mm(Z, A, order) )
self.assertCall( lib.matrix_memcpy_am(Z_ptr, Z, order) )
self.assertVecEqual( Z_py, A_py, TOL, TOL )
# view_array
if not gpu:
A_py *= 0
B = lib.matrix(0, 0, 0, None, order)
self.assertCall( lib.matrix_view_array(B,
A_rand.ctypes.data_as(lib.ok_float_p), m, n, order) )
self.assertCall( lib.matrix_memcpy_am(A_ptr, A, order) )
self.assertVecEqual( A_py, A_rand, TOL, TOL )
# set_all
val = 2
A_rand *= 0
A_rand += val
self.assertCall( lib.matrix_set_all(A, val) )
self.assertCall( lib.matrix_memcpy_am(A_ptr, A, order) )
self.assertVecEqual( A_py, A_rand, TOL, TOL )
self.free_vars('A', 'Z')
self.assertCall( lib.ok_device_reset() )
def test_slicing(self):
""" matrix slicing tests """
(m, n) = self.shape
A_rand = self.A_test
x_rand = np.random.rand(n)
for (gpu, single_precision) in self.CONDITIONS:
lib = self.libs.get(single_precision=single_precision, gpu=gpu)
if lib is None:
continue
self.register_exit(lib.ok_device_reset)
DIGITS = 7 - 2 * lib.FLOAT - 1 * lib.GPU
TOL = 10**(-DIGITS)
for order in (lib.enums.CblasRowMajor, lib.enums.CblasColMajor):
pyorder = 'C' if order == lib.enums.CblasRowMajor else 'F'
A, A_py, A_ptr = self.register_matrix(lib, m, n, order, 'A')
# set A, A_py to A_rand
A_py += A_rand
self.assertCall( lib.matrix_memcpy_ma(A, A_ptr, order) )
# submatrix
m0 = m / 4
n0 = n / 4
msub = m / 2
nsub = n / 2
Asub = lib.matrix(0, 0, 0, None, order)
Asub_py = np.zeros(
(msub, nsub), order=pyorder).astype(lib.pyfloat)
Asub_ptr = Asub_py.ctypes.data_as(lib.ok_float_p)
self.assertCall( lib.matrix_submatrix(Asub, A, m0, n0, msub,
nsub) )
self.assertCall( lib.matrix_memcpy_am(Asub_ptr, Asub, order) )
A_py_sub = A_py[m0 : m0+msub, n0 : n0+nsub]
self.assertVecEqual( Asub_py, A_py_sub, TOL, TOL )
# row
v = lib.vector(0, 0, None)
v_py = np.zeros(n).astype(lib.pyfloat)
v_ptr = v_py.ctypes.data_as(lib.ok_float_p)
self.assertCall( lib.matrix_row(v, A, m0) )
self.assertCall( lib.vector_memcpy_av(v_ptr, v, 1) )
self.assertVecEqual( A_py[m0, :], v_py, TOL, TOL )
# column
v_py = np.zeros(m).astype(lib.pyfloat)
v_ptr = v_py.ctypes.data_as(lib.ok_float_p)
self.assertCall( lib.matrix_column(v, A, n0) )
self.assertCall( lib.vector_memcpy_av(v_ptr, v, 1) )
self.assertVecEqual( A_py[: , n0], v_py, TOL, TOL )
# diagonal
v_py = np.zeros(min(m, n)).astype(lib.pyfloat)
v_ptr = v_py.ctypes.data_as(lib.ok_float_p)
self.assertCall( lib.matrix_diagonal(v, A) )
self.assertCall( lib.vector_memcpy_av(v_ptr, v, 1) )
self.assertVecEqual( np.diag(A_py), v_py, TOL, TOL )
self.free_var('A')
self.assertCall( lib.ok_device_reset() )
def test_math(self):
""" matrix math tests """
(m, n) = self.shape
A_rand = self.A_test
for (gpu, single_precision) in self.CONDITIONS:
lib = self.libs.get(single_precision=single_precision, gpu=gpu)
if lib is None:
continue
self.register_exit(lib.ok_device_reset)
DIGITS = 7 - 2 * lib.FLOAT - 1 * lib.GPU
RTOL = 10**(-DIGITS)
ATOLMN = RTOL * (m * n)**0.5
for order in (lib.enums.CblasRowMajor, lib.enums.CblasColMajor):
A, A_py, A_ptr = self.register_matrix(lib, m, n, order, 'A')
# set A, A_py to A_rand
A_py += A_rand
self.assertCall( lib.matrix_memcpy_ma(A, A_ptr, order) )
# scale: A = alpha * A
alpha = np.random.rand()
A_rand *= alpha
self.assertCall( lib.matrix_scale(A, alpha) )
self.assertCall( lib.matrix_memcpy_am(A_ptr, A, order) )
self.assertVecEqual( A_py, A_rand, ATOLMN, RTOL )
# scale_left: A = diag(d) * A
d, d_py, d_ptr = self.register_vector(lib, m, 'd')
d_py[:] = np.random.rand(m)
for i in xrange(m):
A_rand[i, :] *= d_py[i]
self.assertCall( lib.vector_memcpy_va(d, d_ptr, 1) )
self.assertCall( lib.matrix_scale_left(A, d) )
self.assertCall( lib.matrix_memcpy_am(A_ptr, A, order) )
self.assertVecEqual( A_py, A_rand, ATOLMN, RTOL )
# scale_right: A = A * diag(e)
e, e_py, e_ptr = self.register_vector(lib, n, 'e')
e_py[:] = np.random.rand(n)
for j in xrange(n):
A_rand[:, j] *= e_py[j]
self.assertCall( lib.vector_memcpy_va(e, e_ptr, 1) )
self.assertCall( lib.matrix_scale_right(A, e) )
self.assertCall( lib.matrix_memcpy_am(A_ptr, A, order) )
self.assertVecEqual( A_py, A_rand, ATOLMN, RTOL )
# abs: A_ij = abs(A_ij)
A_rand -= (A_rand.max() - A_rand.min()) / 2
A_py *= 0
A_py += A_rand
A_rand = np.abs(A_rand)
self.assertCall( lib.matrix_memcpy_ma(A, A_ptr, order) )
self.assertCall( lib.matrix_abs(A) )
self.assertCall( lib.matrix_memcpy_am(A_ptr, A, order) )
self.assertVecEqual( A_py, A_rand, ATOLMN, RTOL )
# pow
p = 3 * np.random.rand()
A_rand **= p
self.assertCall( lib.matrix_pow(A, p) )
self.assertCall( lib.matrix_memcpy_am(A_ptr, A, order) )
self.assertVecEqual( A_py, A_rand, ATOLMN, RTOL )
self.free_vars('d', 'e', 'A')
self.assertCall( lib.ok_device_reset() )
class VectorTestCase(OptkitCTestCase):
@classmethod
def setUpClass(self):
self.env_orig = os.getenv('OPTKIT_USE_LOCALLIBS', '0')
os.environ['OPTKIT_USE_LOCALLIBS'] = '1'
self.libs = DenseLinsysLibs()
@classmethod
def tearDownClass(self):
os.environ['OPTKIT_USE_LOCALLIBS'] = self.env_orig
def tearDown(self):
self.free_all_vars()
self.exit_call()
def test_alloc(self):
for (gpu, single_precision) in self.CONDITIONS:
lib = self.libs.get(single_precision=single_precision, gpu=gpu)
if lib is None:
continue
self.register_exit(lib.ok_device_reset)
len_v = 10 + int(10 * np.random.rand())
v = lib.vector(0, 0, None)
self.assertEqual( v.size, 0 )
self.assertEqual( v.stride, 0 )
self.assertCall( lib.vector_calloc(v, len_v) )
self.register_var('v', v, lib.vector_free)
self.assertEqual( v.size, len_v )
self.assertEqual( v.stride, 1 )
if not gpu:
for i in xrange(v.size):
self.assertEqual( v.data[i], 0 )
self.free_var('v')
self.assertEqual( v.size, 0 )
self.assertEqual( v.stride, 0 )
def test_io(self):
for (gpu, single_precision) in self.CONDITIONS:
lib = self.libs.get(single_precision=single_precision, gpu=gpu)
if lib is None:
continue
self.register_exit(lib.ok_device_reset)
len_v = 10 + int(1000 * np.random.rand())
DIGITS = 7 - 2 * single_precision
RTOL = 10**(-DIGITS)
ATOL = RTOL * len_v**0.5
v, v_py, v_ptr = self.register_vector(lib, len_v, 'v')
w, w_py, w_ptr = self.register_vector(lib, len_v, 'w')
# set_all
set_val = 5
self.assertCall( lib.vector_set_all(v, set_val) )
# memcpy_av
self.assertCall( lib.vector_memcpy_av(v_ptr, v, 1) )
for i in xrange(len_v):
self.assertEqual(v_py[i], set_val)
# memcpy_va
w_rand = np.random.rand(len_v)
w_py[:] = w_rand[:]
self.assertCall( lib.vector_memcpy_va(w, w_ptr, 1) )
w_py *= 0
self.assertCall( lib.vector_memcpy_av(w_ptr, w, 1) )
self.assertVecEqual( w_py, w_rand, ATOL, RTOL )
# memcpy_vv
self.assertCall( lib.vector_memcpy_vv(v, w) )
self.assertCall( lib.vector_memcpy_av(v_ptr, v, 1) )
self.assertVecEqual( v_py, w_rand, ATOL, RTOL )
# view_array
if not gpu:
u_rand = np.random.rand(len_v).astype(lib.pyfloat)
u_ptr = u_rand.ctypes.data_as(lib.ok_float_p)
u = lib.vector(0, 0, None)
self.assertCall( lib.vector_view_array(u, u_ptr,
u_rand.size) )
self.assertCall( lib.vector_memcpy_av(v_ptr, u, 1) )
self.assertVecEqual( v_py, u_rand, ATOL, RTOL )
# DON'T FREE u, DATA OWNED BY PYTHON
self.free_vars('v', 'w')
self.assertCall( lib.ok_device_reset() )
def test_subvector(self):
for (gpu, single_precision) in self.CONDITIONS:
lib = self.libs.get(single_precision=single_precision, gpu=gpu)
if lib is None:
continue
self.register_exit(lib.ok_device_reset)
len_v = 10 + int(10 * np.random.rand())
v, v_py, v_ptr = self.register_vector(lib, len_v, 'v')
offset_sub = 3
len_sub = 3
v_sub = lib.vector(0, 0, None)
self.assertCall( lib.vector_subvector(v_sub, v, offset_sub,
len_sub) )
self.assertEqual( v_sub.size, 3 )
self.assertEqual( v_sub.stride, v.stride )
v_sub_py = np.zeros(len_sub).astype(lib.pyfloat)
v_sub_ptr = v_sub_py.ctypes.data_as(lib.ok_float_p)
self.assertCall( lib.vector_memcpy_av(v_ptr, v, 1) )
self.assertCall( lib.vector_memcpy_av(v_sub_ptr, v_sub, 1) )
for i in xrange(len_sub):
self.assertEqual( v_sub_py[i], v_py[i + offset_sub] )
self.free_var('v')
self.assertCall( lib.ok_device_reset() )
def test_math(self):
for (gpu, single_precision) in self.CONDITIONS:
lib = self.libs.get(single_precision=single_precision, gpu=gpu)
if lib is None:
continue
self.register_exit(lib.ok_device_reset)
val1 = 12 * np.random.rand()
val2 = 5 * np.random.rand()
len_v = 10 + int(1000 * np.random.rand())
# len_v = 10 + int(10 * np.random.rand())
DIGITS = 7 - 2 * lib.FLOAT - 1 * lib.GPU
RTOL = 10**(-DIGITS)
ATOL = RTOL * len_v**0.5
v, v_py, v_ptr = self.register_vector(lib, len_v, 'v')
w, w_py, w_ptr = self.register_vector(lib, len_v, 'w')
# constant addition
self.assertCall( lib.vector_add_constant(v, val1) )
self.assertCall( lib.vector_add_constant(w, val2) )
self.assertCall( lib.vector_memcpy_av(v_ptr, v, 1) )
self.assertCall( lib.vector_memcpy_av(w_ptr, w, 1) )
self.assertVecEqual( v_py, val1, ATOL, RTOL )
self.assertVecEqual( w_py, val2, ATOL, RTOL )
# add two vectors
self.assertCall( lib.vector_add(v, w) )
val1 += val2
self.assertCall( lib.vector_memcpy_av(v_ptr, v, 1) )
self.assertCall( lib.vector_memcpy_av(w_ptr, w, 1) )
self.assertVecEqual( v_py, val1, ATOL, RTOL )
self.assertVecEqual( w_py, val2, ATOL, RTOL )
# subtract two vectors
self.assertCall( lib.vector_sub(w, v) )
val2 -= val1
self.assertCall( lib.vector_memcpy_av(v_ptr, v, 1) )
self.assertCall( lib.vector_memcpy_av(w_ptr, w, 1) )
self.assertVecEqual( v_py, val1, ATOL, RTOL )
self.assertVecEqual( w_py, val2, ATOL, RTOL )
# multiply two vectors
self.assertCall( lib.vector_mul(v, w) )
val1 *= val2
self.assertCall( lib.vector_memcpy_av(v_ptr, v, 1) )
self.assertCall( lib.vector_memcpy_av(w_ptr, w, 1) )
self.assertVecEqual( v_py, val1, ATOL, RTOL )
self.assertVecEqual( w_py, val2, ATOL, RTOL )
# vector scale
scal = 3 * np.random.rand()
val1 *= scal
self.assertCall( lib.vector_scale(v, scal) )
self.assertCall( lib.vector_memcpy_av(v_ptr, v, 1) )
self.assertVecEqual( v_py, val1, ATOL, RTOL )
# make sure v is strictly positive
val1 = 0.7 + np.random.rand()
self.assertCall( lib.vector_scale(v, 0) )
self.assertCall( lib.vector_add_constant(v, val1) )
# divide two vectors
self.assertCall( lib.vector_div(w, v) )
val2 /= float(val1)
self.assertCall( lib.vector_memcpy_av(v_ptr, v, 1) )
self.assertCall( lib.vector_memcpy_av(w_ptr, w, 1) )
self.assertVecEqual( v_py, val1, ATOL, RTOL )
self.assertVecEqual( w_py, val2, ATOL, RTOL )
# make w strictly negative
w_max = w_py.max()
val2 -= (w_max + 1)
self.assertCall( lib.vector_add_constant(w, -(w_max + 1)) )
# vector abs
self.assertCall( lib.vector_abs(w) )
val2 = abs(val2)
self.assertCall( lib.vector_memcpy_av(w_ptr, w, 1) )
self.assertVecEqual( w_py, val2, ATOL, RTOL )
# vector recip
self.assertCall( lib.vector_recip(w) )
val2 = 1. / val2
self.assertCall( lib.vector_memcpy_av(w_ptr, w, 1) )
self.assertVecEqual( w_py, val2, ATOL, RTOL )
# vector sqrt
self.assertCall( lib.vector_sqrt(w) )
val2 **= 0.5
self.assertCall( lib.vector_memcpy_av(w_ptr, w, 1) )
self.assertVecEqual( w_py, val2, ATOL, RTOL )
# vector pow
pow_val = -2 + 4 * np.random.rand()
self.assertCall( lib.vector_pow(w, pow_val) )
val2 **= pow_val
self.assertCall( lib.vector_memcpy_av(w_ptr, w, 1) )
self.assertVecEqual( w_py, val2, ATOL, RTOL )
# vector exp
self.assertCall( lib.vector_exp(w) )
val2 = np.exp(val2)
self.assertCall( lib.vector_memcpy_av(w_ptr, w, 1) )
self.assertVecEqual( val2, w_py, ATOL, RTOL )
# min / max
w_py *= 0
w_py += np.random.rand(len(w_py))
self.assertCall( lib.vector_memcpy_va(w, w_ptr, 1) )
# vector argmin
wargmin = np.zeros(1).astype(c_size_t)
wargmin_p = wargmin.ctypes.data_as(lib.c_size_t_p)
self.assertCall( lib.vector_indmin(w, wargmin_p) )
self.assertScalarEqual( w_py[wargmin[0]], w_py.min(), RTOL )
# # vector min
wmin = np.zeros(1).astype(lib.pyfloat)
wmin_p = wmin.ctypes.data_as(lib.ok_float_p)
self.assertCall( lib.vector_min(w, wmin_p) )
self.assertScalarEqual( wmin[0], w_py.min(), RTOL )
# # vector max
wmax = wmin
wmax_p = wmin_p
self.assertCall( lib.vector_max(w, wmax_p) )
self.assertScalarEqual( wmax[0], w_py.max(), RTOL )
self.free_vars('v', 'w')
self.assertCall( lib.ok_device_reset() )
def test_indvector_math(self):
for (gpu, single_precision) in self.CONDITIONS:
lib = self.libs.get(single_precision=single_precision, gpu=gpu)
if lib is None:
continue
self.register_exit(lib.ok_device_reset)
val1 = 12 * np.random.rand()
val2 = 5 * np.random.rand()
len_v = 10 + int(1000 * np.random.rand())
# len_v = 10 + int(10 * np.random.rand())
DIGITS = 7 - 2 * lib.FLOAT - 1 * lib.GPU
RTOL = 10**(-DIGITS)
w, w_py, w_ptr = self.register_indvector(lib, len_v, 'w')
# min / max
w_py *= 0
w_py += (30 * np.random.rand(len(w_py))).astype(w_py.dtype)
self.assertCall( lib.indvector_memcpy_va(w, w_ptr, 1) )
# vector argmin
wargmin = np.zeros(1).astype(c_size_t)
wargmin_p = wargmin.ctypes.data_as(lib.c_size_t_p)
self.assertCall( lib.indvector_indmin(w, wargmin_p) )
self.assertScalarEqual( w_py[wargmin[0]], w_py.min(), RTOL )
# # vector min
wmin = wargmin
wmin_p = wargmin_p
self.assertCall( lib.indvector_min(w, wmin_p) )
self.assertScalarEqual( wmin[0], w_py.min(), RTOL )
# vector max
wmax = wmin
wmax_p = wmin_p
self.assertCall( lib.indvector_max(w, wmax_p) )
self.assertScalarEqual( wmax[0], w_py.max(), RTOL )
self.free_var('w')
self.assertCall( lib.ok_device_reset() )
