# RUN: SUPPORTLIB=%mlir_runner_utils_dir/libmlir_c_runner_utils%shlibext %PYTHON %s | FileCheck %s
import numpy as np
import os
import sys
_SCRIPT_PATH = os.path.dirname(os.path.abspath(__file__))
sys.path.append(_SCRIPT_PATH)
from tools import mlir_pytaco_api as pt
compressed = pt.compressed
passed = 0
all_types = [pt.complex64, pt.complex128]
for t in all_types:
i, j = pt.get_index_vars(2)
A = pt.tensor([2, 3], dtype=t)
B = pt.tensor([2, 3], dtype=t)
C = pt.tensor([2, 3], compressed, dtype=t)
A.insert([0, 1], 10 + 20j)
A.insert([1, 2], 40 + 0.5j)
B.insert([0, 0], 20)
B.insert([1, 2], 30 + 15j)
C[i, j] = A[i, j] + B[i, j]
indices, values = C.get_coordinates_and_values()
passed += isinstance(values[0], t.value)
passed += np.array_equal(indices, [[0, 0], [0, 1], [1, 2]])
passed += np.allclose(values, [20, 10 + 20j, 70 + 15.5j])
# CHECK: Number of passed: 6
print("Number of passed:", passed)
# format) and store it as a compressed sparse fiber tensor. We use a small
# tensor for the purpose of testing. To run the program using the data from
# the real application, please download the data from:
# http://frostt.io/tensors/nell-2/
B = pt.read(os.path.join(_SCRIPT_PATH, "data/nell-2.tns"), csf)
# These two lines have been modified from the original program to use static
# data to support result comparison.
C = pt.from_array(np.full((B.shape[1], 25), 1, dtype=np.float64))
D = pt.from_array(np.full((B.shape[2], 25), 2, dtype=np.float64))
# Declare the result to be a dense matrix.
A = pt.tensor([B.shape[0], 25], rm)
# Declare index vars.
i, j, k, l = pt.get_index_vars(4)
# Define the MTTKRP computation.
A[i, j] = B[i, k, l] * D[l, j] * C[k, j]
##########################################################################
# Perform the MTTKRP computation and write the result to file.
with tempfile.TemporaryDirectory() as test_dir:
golden_file = os.path.join(_SCRIPT_PATH, "data/gold_A.tns")
out_file = os.path.join(test_dir, "A.tns")
pt.write(out_file, A)
#
# CHECK: Compare result True
#
print(f"Compare result {utils.compare_sparse_tns(golden_file, out_file)}")
import sys
import tempfile
_SCRIPT_PATH = os.path.dirname(os.path.abspath(__file__))
sys.path.append(_SCRIPT_PATH)
from tools import mlir_pytaco_api as pt
from tools import testing_utils as utils
# Define the CSR format.
csr = pt.format([pt.dense, pt.compressed], [0, 1])
# Read matrices A and B from file, infer size of output matrix C.
A = pt.read(os.path.join(_SCRIPT_PATH, "data/A.mtx"), csr)
B = pt.read(os.path.join(_SCRIPT_PATH, "data/B.mtx"), csr)
C = pt.tensor([A.shape[0], B.shape[1]], csr)
# Define the kernel.
i, j, k = pt.get_index_vars(3)
C[i, j] = A[i, k] * B[k, j]
# Force evaluation of the kernel by writing out C.
with tempfile.TemporaryDirectory() as test_dir:
golden_file = os.path.join(_SCRIPT_PATH, "data/gold_C.tns")
out_file = os.path.join(test_dir, "C.tns")
pt.write(out_file, C)
#
# CHECK: Compare result True
#
print(f"Compare result {utils.compare_sparse_tns(golden_file, out_file)}")
# RUN: SUPPORTLIB=%mlir_runner_utils_dir/libmlir_c_runner_utils%shlibext %PYTHON %s | FileCheck %s
import filecmp
import numpy as np
import os
import sys
import tempfile
_SCRIPT_PATH = os.path.dirname(os.path.abspath(__file__))
sys.path.append(_SCRIPT_PATH)
from tools import mlir_pytaco_api as pt
from tools import testing_utils as utils
i, j, k, l, m = pt.get_index_vars(5)
# Set up scalar.
alpha = pt.tensor(42.0)
# Set up some sparse tensors with different dim annotations and ordering.
S = pt.tensor([8, 8, 8],
pt.format([pt.compressed, pt.dense, pt.compressed], [1, 0, 2]))
X = pt.tensor([8, 8, 8],
pt.format([pt.compressed, pt.compressed, pt.compressed],
[1, 0, 2]))
S.insert([0, 0, 0], 2.0)
S.insert([1, 1, 1], 3.0)
S.insert([4, 4, 4], 4.0)
S.insert([7, 7, 7], 5.0)
X[i, j, k] = alpha[0] * S[i, j, k]