Added full support for synthetic matrices and added scaffolding for coo
This commit is contained in:
parent
47995eab85
commit
9aab9b18b9
@ -1,4 +1,4 @@
|
|||||||
from data_stat import Cpu, Format
|
from data_stat import Cpu, Format, MatrixType
|
||||||
|
|
||||||
import argparse
|
import argparse
|
||||||
import glob
|
import glob
|
||||||
@ -9,7 +9,8 @@ import random
|
|||||||
parser = argparse.ArgumentParser()
|
parser = argparse.ArgumentParser()
|
||||||
parser.add_argument('cpu', choices=[x.name.lower() for x in Cpu])
|
parser.add_argument('cpu', choices=[x.name.lower() for x in Cpu])
|
||||||
parser.add_argument('output_dir')
|
parser.add_argument('output_dir')
|
||||||
parser.add_argument('matrix_dir')
|
parser.add_argument('matrix_type', type=str,
|
||||||
|
choices=[t.name.lower() for t in MatrixType])
|
||||||
parser.add_argument('format', type=str,
|
parser.add_argument('format', type=str,
|
||||||
choices=[fmt.name.lower() for fmt in Format])
|
choices=[fmt.name.lower() for fmt in Format])
|
||||||
parser.add_argument('base_iterations', type=int)
|
parser.add_argument('base_iterations', type=int)
|
||||||
@ -17,10 +18,14 @@ parser.add_argument('min_time_s', type=int)
|
|||||||
parser.add_argument('baseline_time_s', type=int)
|
parser.add_argument('baseline_time_s', type=int)
|
||||||
parser.add_argument('baseline_delay_s', type=int)
|
parser.add_argument('baseline_delay_s', type=int)
|
||||||
#parser.add_argument('--perf', action='store_const', const='--perf')
|
#parser.add_argument('--perf', action='store_const', const='--perf')
|
||||||
|
parser.add_argument('-m', '--matrix_dir', type=str)
|
||||||
|
parser.add_argument('-ss', '--synthetic_size', nargs="+", type=int)
|
||||||
|
parser.add_argument('-sd', '--synthetic_density', nargs="+", type=float)
|
||||||
parser.add_argument('--power', action='store_const', const='--power')
|
parser.add_argument('--power', action='store_const', const='--power')
|
||||||
parser.add_argument('--distribute', action='store_true')
|
parser.add_argument('--distribute', action='store_true')
|
||||||
args = parser.parse_args()
|
args = parser.parse_args()
|
||||||
args.cpu = Cpu[args.cpu.upper()]
|
args.cpu = Cpu[args.cpu.upper()]
|
||||||
|
args.matrix_type = MatrixType[args.matrix_type.upper()]
|
||||||
args.format = Format[args.format.upper()]
|
args.format = Format[args.format.upper()]
|
||||||
|
|
||||||
srun_args = {
|
srun_args = {
|
||||||
@ -63,15 +68,28 @@ python = {
|
|||||||
Cpu.XEON_4216: 'python3.11'
|
Cpu.XEON_4216: 'python3.11'
|
||||||
}
|
}
|
||||||
|
|
||||||
def run(run_args, matrix_file: str, srun_args_list: list = None) -> list:
|
def run(
|
||||||
|
run_args,
|
||||||
|
matrix_file: str,
|
||||||
|
synthetic_size: int,
|
||||||
|
synthetic_density: float,
|
||||||
|
srun_args_list: list = None
|
||||||
|
) -> list:
|
||||||
run_args_list = [
|
run_args_list = [
|
||||||
args.cpu.name.lower(),
|
args.cpu.name.lower(),
|
||||||
matrix_file,
|
args.matrix_type.name.lower(),
|
||||||
args.format.name.lower(),
|
args.format.name.lower(),
|
||||||
str(args.base_iterations),
|
str(args.base_iterations),
|
||||||
str(args.min_time_s),
|
str(args.min_time_s),
|
||||||
str(args.baseline_time_s),
|
str(args.baseline_time_s),
|
||||||
str(args.baseline_delay_s)]
|
str(args.baseline_delay_s)]
|
||||||
|
|
||||||
|
if args.matrix_type == MatrixType.SUITESPARSE:
|
||||||
|
run_args_list += ['-m', matrix_file]
|
||||||
|
elif args.matrix_type == MatrixType.SYNTHETIC:
|
||||||
|
run_args_list += ['-ss', str(synthetic_size), '-sd', str(synthetic_density)]
|
||||||
|
else:
|
||||||
|
exit("Unrecognized matrix type!")
|
||||||
# if args.perf is not None:
|
# if args.perf is not None:
|
||||||
# run_args_list += [args.perf]
|
# run_args_list += [args.perf]
|
||||||
if args.power is not None:
|
if args.power is not None:
|
||||||
@ -87,7 +105,15 @@ def run(run_args, matrix_file: str, srun_args_list: list = None) -> list:
|
|||||||
|
|
||||||
processes = list()
|
processes = list()
|
||||||
|
|
||||||
for i, matrix in enumerate(glob.glob(f'{args.matrix_dir.rstrip("/")}/*.mtx')):
|
if args.matrix_type == MatrixType.SUITESPARSE:
|
||||||
|
parameter_list = enumerate(glob.glob(f'{args.matrix_dir.rstrip("/")}/*.mtx'))
|
||||||
|
elif args.matrix_type == MatrixType.SYNTHETIC:
|
||||||
|
parameter_list = enumerate([(size, density)
|
||||||
|
for size in args.synthetic_size
|
||||||
|
for density in args.synthetic_density])
|
||||||
|
|
||||||
|
#for i, matrix in enumerate(glob.glob(f'{args.matrix_dir.rstrip("/")}/*.mtx')):
|
||||||
|
for i, parameter in parameter_list:
|
||||||
#if args.distribute:
|
#if args.distribute:
|
||||||
# if args.cpu == Cpu.ALTRA:
|
# if args.cpu == Cpu.ALTRA:
|
||||||
# i = i % 40
|
# i = i % 40
|
||||||
@ -97,12 +123,19 @@ for i, matrix in enumerate(glob.glob(f'{args.matrix_dir.rstrip("/")}/*.mtx')):
|
|||||||
#else:
|
#else:
|
||||||
srun_args_temp = srun_args[args.cpu]
|
srun_args_temp = srun_args[args.cpu]
|
||||||
|
|
||||||
output_filename = '_'.join([
|
synthetic_size = args.synthetic_size
|
||||||
|
synthetic_density = args.synthetic_density
|
||||||
|
output_filename_list = [
|
||||||
args.cpu.name.lower(),
|
args.cpu.name.lower(),
|
||||||
str(args.min_time_s),
|
str(args.min_time_s),
|
||||||
str(args.baseline_time_s),
|
str(args.baseline_time_s),
|
||||||
str(args.baseline_delay_s),
|
str(args.baseline_delay_s)]
|
||||||
os.path.splitext(os.path.basename(matrix))[0]])
|
if args.matrix_type == MatrixType.SUITESPARSE:
|
||||||
|
output_filename_list += [os.path.splitext(os.path.basename(parameter))[0]]
|
||||||
|
elif args.matrix_type == MatrixType.SYNTHETIC:
|
||||||
|
output_filename_list += [str(parameter[0]), str(parameter[1])]
|
||||||
|
|
||||||
|
output_filename = '_'.join(output_filename_list)
|
||||||
|
|
||||||
json_filepath = f'{args.output_dir.rstrip("/")}/{output_filename}.json'
|
json_filepath = f'{args.output_dir.rstrip("/")}/{output_filename}.json'
|
||||||
raw_filepath = f'{args.output_dir.rstrip("/")}/{output_filename}.output'
|
raw_filepath = f'{args.output_dir.rstrip("/")}/{output_filename}.output'
|
||||||
@ -111,13 +144,17 @@ for i, matrix in enumerate(glob.glob(f'{args.matrix_dir.rstrip("/")}/*.mtx')):
|
|||||||
print(raw_filepath)
|
print(raw_filepath)
|
||||||
|
|
||||||
if args.distribute:
|
if args.distribute:
|
||||||
processes.append(subprocess.Popen(
|
processes.append(subprocess.Popen(run(
|
||||||
run(args, matrix, srun_args_temp),
|
args,
|
||||||
|
parameter,
|
||||||
|
parameter[0],
|
||||||
|
parameter[1],
|
||||||
|
srun_args_temp),
|
||||||
stdout=json_file,
|
stdout=json_file,
|
||||||
stderr=raw_file))
|
stderr=raw_file))
|
||||||
else:
|
else:
|
||||||
subprocess.run(
|
subprocess.run(
|
||||||
run(args, matrix),
|
run(args, parameter, parameter[0], parameter[1]),
|
||||||
stdout=json_file,
|
stdout=json_file,
|
||||||
stderr=raw_file)
|
stderr=raw_file)
|
||||||
|
|
||||||
|
1
pytorch/output_test2/altra_10_2_10_100000_0.0001.json
Normal file
1
pytorch/output_test2/altra_10_2_10_100000_0.0001.json
Normal file
@ -0,0 +1 @@
|
|||||||
|
{"CPU": "Altra", "ITERATIONS": 82249, "MATRIX_TYPE": "synthetic", "MATRIX_FORMAT": "csr", "MATRIX_SHAPE": [100000, 100000], "MATRIX_SIZE": 10000000000, "MATRIX_NNZ": 999948, "MATRIX_DENSITY": 9.99948e-05, "TIME_S": 12.20802617073059, "TIME_S_1KI": 0.14842765469161437, "BASELINE_TIME_S": 2, "BASELINE_DELAY_S": 10, "J": 1033.954319496155, "W": 84.9319356344559, "J_1KI": 12.57102602458577, "W_1KI": 1.032619674822258, "W_D": 74.4169356344559, "J_D": 905.9455841684344, "W_D_1KI": 0.9047761752052413, "J_D_1KI": 0.011000451983674468}
|
17
pytorch/output_test2/altra_10_2_10_100000_0.0001.output
Normal file
17
pytorch/output_test2/altra_10_2_10_100000_0.0001.output
Normal file
@ -0,0 +1,17 @@
|
|||||||
|
/nfshomes/vut/ampere_research/pytorch/spmv.py:57: UserWarning: Sparse CSR tensor support is in beta state. If you miss a functionality in the sparse tensor support, please submit a feature request to https://github.com/pytorch/pytorch/issues. (Triggered internally at /space/jenkins/workspace/Releases/pytorch-dls/pytorch-dls/aten/src/ATen/SparseCsrTensorImpl.cpp:55.)
|
||||||
|
matrix = matrix.to_sparse_csr().type(torch.float32)
|
||||||
|
tensor(crow_indices=tensor([ 0, 12, 20, ..., 999931, 999940,
|
||||||
|
999948]),
|
||||||
|
col_indices=tensor([20217, 25552, 38877, ..., 63581, 75717, 96314]),
|
||||||
|
values=tensor([-1.5899, -0.7194, -0.7547, ..., 0.5402, -0.1912,
|
||||||
|
-0.1167]), size=(100000, 100000), nnz=999948,
|
||||||
|
layout=torch.sparse_csr)
|
||||||
|
tensor([0.7377, 0.7528, 0.7695, ..., 0.6702, 0.9924, 0.8686])
|
||||||
|
Matrix: synthetic
|
||||||
|
Matrix: csr
|
||||||
|
Shape: torch.Size([100000, 100000])
|
||||||
|
Size: 10000000000
|
||||||
|
NNZ: 999948
|
||||||
|
Density: 9.99948e-05
|
||||||
|
Time: 12.20802617073059 seconds
|
||||||
|
|
1
pytorch/output_test2/altra_10_2_10_100000_1e-05.json
Normal file
1
pytorch/output_test2/altra_10_2_10_100000_1e-05.json
Normal file
@ -0,0 +1 @@
|
|||||||
|
{"CPU": "Altra", "ITERATIONS": 104724, "MATRIX_TYPE": "synthetic", "MATRIX_FORMAT": "csr", "MATRIX_SHAPE": [100000, 100000], "MATRIX_SIZE": 10000000000, "MATRIX_NNZ": 99999, "MATRIX_DENSITY": 9.9999e-06, "TIME_S": 10.740116596221924, "TIME_S_1KI": 0.10255640155286203, "BASELINE_TIME_S": 2, "BASELINE_DELAY_S": 10, "J": 720.857314195633, "W": 76.49734010579499, "J_1KI": 6.883401266143702, "W_1KI": 0.7304661787727262, "W_D": 65.89234010579499, "J_D": 620.9232275140286, "W_D_1KI": 0.6291999933710991, "J_D_1KI": 0.0060081738032456665}
|
16
pytorch/output_test2/altra_10_2_10_100000_1e-05.output
Normal file
16
pytorch/output_test2/altra_10_2_10_100000_1e-05.output
Normal file
@ -0,0 +1,16 @@
|
|||||||
|
/nfshomes/vut/ampere_research/pytorch/spmv.py:57: UserWarning: Sparse CSR tensor support is in beta state. If you miss a functionality in the sparse tensor support, please submit a feature request to https://github.com/pytorch/pytorch/issues. (Triggered internally at /space/jenkins/workspace/Releases/pytorch-dls/pytorch-dls/aten/src/ATen/SparseCsrTensorImpl.cpp:55.)
|
||||||
|
matrix = matrix.to_sparse_csr().type(torch.float32)
|
||||||
|
tensor(crow_indices=tensor([ 0, 0, 1, ..., 99990, 99994, 99999]),
|
||||||
|
col_indices=tensor([77500, 30298, 91629, ..., 67143, 70964, 98118]),
|
||||||
|
values=tensor([ 0.0300, -1.0927, 1.5365, ..., -1.2655, 1.0213,
|
||||||
|
0.2378]), size=(100000, 100000), nnz=99999,
|
||||||
|
layout=torch.sparse_csr)
|
||||||
|
tensor([0.9139, 0.4903, 0.5737, ..., 0.7094, 0.3230, 0.9275])
|
||||||
|
Matrix: synthetic
|
||||||
|
Matrix: csr
|
||||||
|
Shape: torch.Size([100000, 100000])
|
||||||
|
Size: 10000000000
|
||||||
|
NNZ: 99999
|
||||||
|
Density: 9.9999e-06
|
||||||
|
Time: 10.740116596221924 seconds
|
||||||
|
|
@ -0,0 +1 @@
|
|||||||
|
{"CPU": "Epyc 7313P", "ITERATIONS": 101034, "MATRIX_TYPE": "synthetic", "MATRIX_FORMAT": "csr", "MATRIX_SHAPE": [100000, 100000], "MATRIX_SIZE": 10000000000, "MATRIX_NNZ": 999955, "MATRIX_DENSITY": 9.99955e-05, "TIME_S": 10.361092805862427, "TIME_S_1KI": 0.10255055531665011, "BASELINE_TIME_S": 2, "BASELINE_DELAY_S": 10, "J": 1568.5116010475158, "W": 147.64, "J_1KI": 15.524591731966623, "W_1KI": 1.4612902587247856, "W_D": 127.57249999999999, "J_D": 1355.316623033285, "W_D_1KI": 1.2626690025140053, "J_D_1KI": 0.012497466224379963}
|
17
pytorch/output_test2/epyc_7313p_10_2_10_100000_0.0001.output
Normal file
17
pytorch/output_test2/epyc_7313p_10_2_10_100000_0.0001.output
Normal file
@ -0,0 +1,17 @@
|
|||||||
|
/nfshomes/vut/ampere_research/pytorch/spmv.py:57: UserWarning: Sparse CSR tensor support is in beta state. If you miss a functionality in the sparse tensor support, please submit a feature request to https://github.com/pytorch/pytorch/issues. (Triggered internally at ../aten/src/ATen/SparseCsrTensorImpl.cpp:53.)
|
||||||
|
matrix = matrix.to_sparse_csr().type(torch.float32)
|
||||||
|
tensor(crow_indices=tensor([ 0, 12, 24, ..., 999933, 999940,
|
||||||
|
999955]),
|
||||||
|
col_indices=tensor([ 5967, 15636, 19622, ..., 82825, 87847, 97213]),
|
||||||
|
values=tensor([-1.5657, 1.3165, 0.1051, ..., -0.5017, 0.1827,
|
||||||
|
-1.1977]), size=(100000, 100000), nnz=999955,
|
||||||
|
layout=torch.sparse_csr)
|
||||||
|
tensor([0.4289, 0.2254, 0.8435, ..., 0.1753, 0.8896, 0.3058])
|
||||||
|
Matrix: synthetic
|
||||||
|
Matrix: csr
|
||||||
|
Shape: torch.Size([100000, 100000])
|
||||||
|
Size: 10000000000
|
||||||
|
NNZ: 999955
|
||||||
|
Density: 9.99955e-05
|
||||||
|
Time: 10.361092805862427 seconds
|
||||||
|
|
@ -0,0 +1 @@
|
|||||||
|
{"CPU": "Epyc 7313P", "ITERATIONS": 150582, "MATRIX_TYPE": "synthetic", "MATRIX_FORMAT": "csr", "MATRIX_SHAPE": [100000, 100000], "MATRIX_SIZE": 10000000000, "MATRIX_NNZ": 100000, "MATRIX_DENSITY": 1e-05, "TIME_S": 10.027292013168335, "TIME_S_1KI": 0.06659024327720667, "BASELINE_TIME_S": 2, "BASELINE_DELAY_S": 10, "J": 1239.2374660491944, "W": 116.83, "J_1KI": 8.229652057013418, "W_1KI": 0.7758563440517459, "W_D": 97.04249999999999, "J_D": 1029.3477856636046, "W_D_1KI": 0.6444495358010917, "J_D_1KI": 0.0042797249060385146}
|
17
pytorch/output_test2/epyc_7313p_10_2_10_100000_1e-05.output
Normal file
17
pytorch/output_test2/epyc_7313p_10_2_10_100000_1e-05.output
Normal file
@ -0,0 +1,17 @@
|
|||||||
|
/nfshomes/vut/ampere_research/pytorch/spmv.py:57: UserWarning: Sparse CSR tensor support is in beta state. If you miss a functionality in the sparse tensor support, please submit a feature request to https://github.com/pytorch/pytorch/issues. (Triggered internally at ../aten/src/ATen/SparseCsrTensorImpl.cpp:53.)
|
||||||
|
matrix = matrix.to_sparse_csr().type(torch.float32)
|
||||||
|
tensor(crow_indices=tensor([ 0, 1, 2, ..., 99996, 99997,
|
||||||
|
100000]),
|
||||||
|
col_indices=tensor([98366, 86469, 784, ..., 24883, 35225, 74645]),
|
||||||
|
values=tensor([ 0.5652, 0.5870, -0.9667, ..., -0.8134, 0.3649,
|
||||||
|
-0.5054]), size=(100000, 100000), nnz=100000,
|
||||||
|
layout=torch.sparse_csr)
|
||||||
|
tensor([0.7832, 0.0968, 0.2513, ..., 0.3975, 0.2140, 0.9668])
|
||||||
|
Matrix: synthetic
|
||||||
|
Matrix: csr
|
||||||
|
Shape: torch.Size([100000, 100000])
|
||||||
|
Size: 10000000000
|
||||||
|
NNZ: 100000
|
||||||
|
Density: 1e-05
|
||||||
|
Time: 10.027292013168335 seconds
|
||||||
|
|
@ -0,0 +1 @@
|
|||||||
|
{"CPU": "Xeon 4216", "ITERATIONS": 41245, "MATRIX_TYPE": "synthetic", "MATRIX_FORMAT": "csr", "MATRIX_SHAPE": [100000, 100000], "MATRIX_SIZE": 10000000000, "MATRIX_NNZ": 999957, "MATRIX_DENSITY": 9.99957e-05, "TIME_S": 10.48258900642395, "TIME_S_1KI": 0.2541541764195406, "BASELINE_TIME_S": 2, "BASELINE_DELAY_S": 10, "J": 907.7721267700196, "W": 86.4, "J_1KI": 22.00926480227954, "W_1KI": 2.0947993696205605, "W_D": 77.29, "J_D": 812.0568018293382, "W_D_1KI": 1.8739241120135777, "J_D_1KI": 0.045433970469476975}
|
17
pytorch/output_test2/xeon_4216_10_2_10_100000_0.0001.output
Normal file
17
pytorch/output_test2/xeon_4216_10_2_10_100000_0.0001.output
Normal file
@ -0,0 +1,17 @@
|
|||||||
|
/nfshomes/vut/ampere_research/pytorch/spmv.py:57: UserWarning: Sparse CSR tensor support is in beta state. If you miss a functionality in the sparse tensor support, please submit a feature request to https://github.com/pytorch/pytorch/issues. (Triggered internally at ../aten/src/ATen/SparseCsrTensorImpl.cpp:53.)
|
||||||
|
matrix = matrix.to_sparse_csr().type(torch.float32)
|
||||||
|
tensor(crow_indices=tensor([ 0, 10, 20, ..., 999933, 999947,
|
||||||
|
999957]),
|
||||||
|
col_indices=tensor([10614, 12000, 12630, ..., 76477, 82289, 92989]),
|
||||||
|
values=tensor([ 0.5650, 0.5553, -0.5300, ..., 0.3637, -1.1395,
|
||||||
|
0.7341]), size=(100000, 100000), nnz=999957,
|
||||||
|
layout=torch.sparse_csr)
|
||||||
|
tensor([0.5083, 0.7251, 0.1206, ..., 0.9177, 0.3147, 0.5521])
|
||||||
|
Matrix: synthetic
|
||||||
|
Matrix: csr
|
||||||
|
Shape: torch.Size([100000, 100000])
|
||||||
|
Size: 10000000000
|
||||||
|
NNZ: 999957
|
||||||
|
Density: 9.99957e-05
|
||||||
|
Time: 10.48258900642395 seconds
|
||||||
|
|
1
pytorch/output_test2/xeon_4216_10_2_10_100000_1e-05.json
Normal file
1
pytorch/output_test2/xeon_4216_10_2_10_100000_1e-05.json
Normal file
@ -0,0 +1 @@
|
|||||||
|
{"CPU": "Xeon 4216", "ITERATIONS": 118541, "MATRIX_TYPE": "synthetic", "MATRIX_FORMAT": "csr", "MATRIX_SHAPE": [100000, 100000], "MATRIX_SIZE": 10000000000, "MATRIX_NNZ": 99998, "MATRIX_DENSITY": 9.9998e-06, "TIME_S": 10.91425085067749, "TIME_S_1KI": 0.09207152673486381, "BASELINE_TIME_S": 2, "BASELINE_DELAY_S": 10, "J": 868.9650503587723, "W": 82.07, "J_1KI": 7.3305021077835715, "W_1KI": 0.6923342978378788, "W_D": 72.5, "J_D": 767.636970281601, "W_D_1KI": 0.6116027366059, "J_D_1KI": 0.005159419412742426}
|
16
pytorch/output_test2/xeon_4216_10_2_10_100000_1e-05.output
Normal file
16
pytorch/output_test2/xeon_4216_10_2_10_100000_1e-05.output
Normal file
@ -0,0 +1,16 @@
|
|||||||
|
/nfshomes/vut/ampere_research/pytorch/spmv.py:57: UserWarning: Sparse CSR tensor support is in beta state. If you miss a functionality in the sparse tensor support, please submit a feature request to https://github.com/pytorch/pytorch/issues. (Triggered internally at ../aten/src/ATen/SparseCsrTensorImpl.cpp:53.)
|
||||||
|
matrix = matrix.to_sparse_csr().type(torch.float32)
|
||||||
|
tensor(crow_indices=tensor([ 0, 2, 3, ..., 99997, 99997, 99998]),
|
||||||
|
col_indices=tensor([90305, 96230, 86891, ..., 66888, 39495, 21203]),
|
||||||
|
values=tensor([-0.5290, 1.7137, 0.7615, ..., 1.2465, -0.3855,
|
||||||
|
-0.4542]), size=(100000, 100000), nnz=99998,
|
||||||
|
layout=torch.sparse_csr)
|
||||||
|
tensor([0.2048, 0.5046, 0.8421, ..., 0.4453, 0.3792, 0.7036])
|
||||||
|
Matrix: synthetic
|
||||||
|
Matrix: csr
|
||||||
|
Shape: torch.Size([100000, 100000])
|
||||||
|
Size: 10000000000
|
||||||
|
NNZ: 99998
|
||||||
|
Density: 9.9998e-06
|
||||||
|
Time: 10.91425085067749 seconds
|
||||||
|
|
@ -1,5 +1,5 @@
|
|||||||
import data_stat
|
import data_stat
|
||||||
from data_stat import Stat, Cpu, Format
|
from data_stat import Stat, Cpu, Format, MatrixType
|
||||||
|
|
||||||
import argparse
|
import argparse
|
||||||
import os, sys
|
import os, sys
|
||||||
@ -9,7 +9,8 @@ import time
|
|||||||
|
|
||||||
parser = argparse.ArgumentParser()
|
parser = argparse.ArgumentParser()
|
||||||
parser.add_argument('cpu', choices=[x.name.lower() for x in Cpu])
|
parser.add_argument('cpu', choices=[x.name.lower() for x in Cpu])
|
||||||
parser.add_argument('matrix_file')
|
parser.add_argument('matrix_type', type=str,
|
||||||
|
choices=[t.name.lower() for t in MatrixType])
|
||||||
parser.add_argument('format', type=str,
|
parser.add_argument('format', type=str,
|
||||||
choices=[fmt.name.lower() for fmt in Format])
|
choices=[fmt.name.lower() for fmt in Format])
|
||||||
parser.add_argument('base_iterations', type=int)
|
parser.add_argument('base_iterations', type=int)
|
||||||
@ -17,11 +18,16 @@ parser.add_argument('min_time_s', type=int)
|
|||||||
parser.add_argument('baseline_time_s', type=int)
|
parser.add_argument('baseline_time_s', type=int)
|
||||||
parser.add_argument('baseline_delay_s', type=int)
|
parser.add_argument('baseline_delay_s', type=int)
|
||||||
#parser.add_argument('--perf', action='store_true')
|
#parser.add_argument('--perf', action='store_true')
|
||||||
|
parser.add_argument('-m', '--matrix_file', type=str)
|
||||||
|
parser.add_argument('-ss', '--synthetic_size', type=int)
|
||||||
|
parser.add_argument('-sd', '--synthetic_density', type=float)
|
||||||
parser.add_argument('--power', action='store_true')
|
parser.add_argument('--power', action='store_true')
|
||||||
parser.add_argument('-d', '--debug', action='store_true')
|
parser.add_argument('-d', '--debug', action='store_true')
|
||||||
args = parser.parse_args()
|
args = parser.parse_args()
|
||||||
args.cpu = Cpu[args.cpu.upper()]
|
args.cpu = Cpu[args.cpu.upper()]
|
||||||
|
args.matrix_type = MatrixType[args.matrix_type.upper()]
|
||||||
args.format = Format[args.format.upper()]
|
args.format = Format[args.format.upper()]
|
||||||
|
assert args.baseline_time_s >= 2
|
||||||
|
|
||||||
python = {
|
python = {
|
||||||
Cpu.ALTRA: 'python3',
|
Cpu.ALTRA: 'python3',
|
||||||
@ -38,21 +44,39 @@ perf_args = {
|
|||||||
['-M', 'l2_cache_miss_ratio,l2_tlb_miss_ratio,ll_cache_read_miss_ratio']]
|
['-M', 'l2_cache_miss_ratio,l2_tlb_miss_ratio,ll_cache_read_miss_ratio']]
|
||||||
}
|
}
|
||||||
|
|
||||||
def program(cpu: Cpu, matrix_file: str, iterations: int) -> list:
|
def program(
|
||||||
|
cpu: Cpu,
|
||||||
|
matrix_type: MatrixType,
|
||||||
|
fmt: Format,
|
||||||
|
iterations: int,
|
||||||
|
matrix_file: str,
|
||||||
|
synthetic_size: int,
|
||||||
|
synthetic_density: float
|
||||||
|
) -> list:
|
||||||
|
spmv = f'python3 spmv.py {matrix_type.name.lower()} {fmt.name.lower()} '
|
||||||
|
spmv += f'{iterations} '
|
||||||
|
if matrix_type == MatrixType.SUITESPARSE:
|
||||||
|
spmv += f'-m {matrix_file}'
|
||||||
|
elif matrix_type == MatrixType.SYNTHETIC:
|
||||||
|
spmv += f'-ss {synthetic_size} -sd {synthetic_density}'
|
||||||
|
else:
|
||||||
|
exit("Unrecognized matrix type!")
|
||||||
|
|
||||||
if cpu == Cpu.ALTRA:
|
if cpu == Cpu.ALTRA:
|
||||||
return [
|
return [
|
||||||
'apptainer', 'run', 'pytorch-altra.sif', '-c',
|
'apptainer', 'run', 'pytorch-altra.sif', '-c',
|
||||||
'numactl --cpunodebind=0 --membind=0 '
|
'numactl --cpunodebind=0 --membind=0 ' + spmv]
|
||||||
+ f'python3 spmv.py {iterations} csr -m {matrix_file}']
|
#+ f'python3 spmv.py {matrix_type.name.lower()} '
|
||||||
|
#+ f'csr {iterations} -m {matrix_file}']
|
||||||
elif cpu == Cpu.EPYC_7313P:
|
elif cpu == Cpu.EPYC_7313P:
|
||||||
return [
|
return ['apptainer', 'run', 'pytorch-epyc_7313p.sif'] + spmv.split(' ')
|
||||||
'apptainer', 'run', 'pytorch-epyc_7313p.sif',
|
#'python3', 'spmv.py', f'{iterations}', 'csr', '-m', f'{matrix_file}']
|
||||||
'python3', 'spmv.py', f'{iterations}', 'csr', '-m', f'{matrix_file}']
|
|
||||||
elif cpu == Cpu.XEON_4216:
|
elif cpu == Cpu.XEON_4216:
|
||||||
return [
|
return [
|
||||||
'apptainer', 'run', 'pytorch-xeon_4216.sif',
|
'apptainer', 'run', 'pytorch-xeon_4216.sif',
|
||||||
'numactl', '--cpunodebind=0', '--membind=0',
|
'numactl', '--cpunodebind=0', '--membind=0'
|
||||||
'python3', 'spmv.py', f'{iterations}', 'csr', '-m', f'{matrix_file}']
|
] + spmv.split(' ')
|
||||||
|
#'python3', 'spmv.py', f'{iterations}', 'csr', '-m', f'{matrix_file}']
|
||||||
|
|
||||||
def baseline_power(cpu: Cpu, baseline_time_s: int) -> list:
|
def baseline_power(cpu: Cpu, baseline_time_s: int) -> list:
|
||||||
power_process = subprocess.Popen(['./power.sh', str(baseline_time_s)],
|
power_process = subprocess.Popen(['./power.sh', str(baseline_time_s)],
|
||||||
@ -61,14 +85,14 @@ def baseline_power(cpu: Cpu, baseline_time_s: int) -> list:
|
|||||||
|
|
||||||
def run_program(program: list[str]) -> tuple[dict, str]:
|
def run_program(program: list[str]) -> tuple[dict, str]:
|
||||||
if args.debug:
|
if args.debug:
|
||||||
print(program)
|
print(program, file=sys.stderr)
|
||||||
process = subprocess.run(program,
|
process = subprocess.run(program,
|
||||||
stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True)
|
stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True)
|
||||||
process.check_returncode()
|
process.check_returncode()
|
||||||
|
|
||||||
if args.debug:
|
if args.debug:
|
||||||
print(process.stdout)
|
print(process.stdout, file=sys.stderr)
|
||||||
print(process.stderr)
|
print(process.stderr, file=sys.stderr)
|
||||||
return (json.loads(process.stdout), process.stderr)
|
return (json.loads(process.stdout), process.stderr)
|
||||||
|
|
||||||
def trapezoidal_rule(power: list[float], time_s: float) -> float:
|
def trapezoidal_rule(power: list[float], time_s: float) -> float:
|
||||||
@ -85,17 +109,21 @@ def trapezoidal_rule(power: list[float], time_s: float) -> float:
|
|||||||
return result
|
return result
|
||||||
|
|
||||||
result = dict()
|
result = dict()
|
||||||
result[Stat.CPU.name] = args.cpu.name
|
result[Stat.CPU.name] = args.cpu.value
|
||||||
|
|
||||||
iterations = args.base_iterations
|
iterations = args.base_iterations
|
||||||
program_result = run_program(program(args.cpu, args.matrix_file, iterations))
|
program_result = run_program(program(
|
||||||
|
args.cpu, args.matrix_type, args.format, iterations,
|
||||||
|
args.matrix_file, args.synthetic_size, args.synthetic_density))
|
||||||
while program_result[0][Stat.TIME_S.name] < args.min_time_s:
|
while program_result[0][Stat.TIME_S.name] < args.min_time_s:
|
||||||
# Increase the number of iterations by difference between the current time taken and the desired time.
|
# Increase the number of iterations by difference between the current time taken and the desired time.
|
||||||
iterations *= 1 / (program_result[0][Stat.TIME_S.name] / args.min_time_s)
|
iterations *= 1 / (program_result[0][Stat.TIME_S.name] / args.min_time_s)
|
||||||
# Add another 5% for safety.
|
# Add another 5% for safety.
|
||||||
iterations += iterations * 0.05
|
iterations += iterations * 0.05
|
||||||
iterations = int(iterations)
|
iterations = int(iterations)
|
||||||
program_result = run_program(program(args.cpu, args.matrix_file, iterations))
|
program_result = run_program(program(
|
||||||
|
args.cpu, args.matrix_type, args.format, iterations,
|
||||||
|
args.matrix_file, args.synthetic_size, args.synthetic_density))
|
||||||
|
|
||||||
result[Stat.ITERATIONS.name] = iterations
|
result[Stat.ITERATIONS.name] = iterations
|
||||||
|
|
||||||
@ -114,12 +142,15 @@ if args.power:
|
|||||||
time.sleep(args.baseline_delay_s)
|
time.sleep(args.baseline_delay_s)
|
||||||
baseline_list = baseline_power(args.cpu, args.baseline_time_s)
|
baseline_list = baseline_power(args.cpu, args.baseline_time_s)
|
||||||
if args.debug:
|
if args.debug:
|
||||||
print(baseline_list)
|
print(baseline_list, file=sys.stderr)
|
||||||
assert(len(baseline_list) == args.baseline_time_s)
|
assert(len(baseline_list) == args.baseline_time_s)
|
||||||
|
|
||||||
# Power Collection
|
# Power Collection
|
||||||
power_process = subprocess.run(
|
power_process = subprocess.run(
|
||||||
['./power.sh', '-1'] + program(args.cpu, args.matrix_file, result[Stat.ITERATIONS.name]),
|
['./power.sh', '-1'] + program(
|
||||||
|
args.cpu, args.matrix_type, args.format,
|
||||||
|
result[Stat.ITERATIONS.name],
|
||||||
|
args.matrix_file, args.synthetic_size, args.synthetic_density),
|
||||||
stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True)
|
stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True)
|
||||||
power_process.check_returncode()
|
power_process.check_returncode()
|
||||||
|
|
||||||
@ -127,8 +158,8 @@ if args.power:
|
|||||||
for x in power_process.stdout.strip().split('\n')]
|
for x in power_process.stdout.strip().split('\n')]
|
||||||
power_time_s = json.loads(power_process.stderr)[Stat.TIME_S.name]
|
power_time_s = json.loads(power_process.stderr)[Stat.TIME_S.name]
|
||||||
if args.debug:
|
if args.debug:
|
||||||
print(power_list)
|
print(power_list, file=sys.stderr)
|
||||||
print(power_time_s)
|
print(power_time_s, file=sys.stderr)
|
||||||
|
|
||||||
if args.cpu == Cpu.ALTRA:
|
if args.cpu == Cpu.ALTRA:
|
||||||
# Trapezoidal Rule across the last (s) power recordings.
|
# Trapezoidal Rule across the last (s) power recordings.
|
||||||
@ -140,7 +171,7 @@ if args.power:
|
|||||||
result[Stat.W.name] = result[Stat.J.name] / power_time_s
|
result[Stat.W.name] = result[Stat.J.name] / power_time_s
|
||||||
|
|
||||||
if args.debug:
|
if args.debug:
|
||||||
print(result)
|
print(result, file=sys.stderr)
|
||||||
#print(len(result['power']))
|
#print(len(result['power']))
|
||||||
#print(sum(result['power']) / len(result['power']))
|
#print(sum(result['power']) / len(result['power']))
|
||||||
|
|
||||||
@ -148,7 +179,7 @@ if args.power:
|
|||||||
time.sleep(args.baseline_delay_s)
|
time.sleep(args.baseline_delay_s)
|
||||||
baseline_list += baseline_power(args.cpu, args.baseline_time_s)
|
baseline_list += baseline_power(args.cpu, args.baseline_time_s)
|
||||||
if args.debug:
|
if args.debug:
|
||||||
print(baseline_list)
|
print(baseline_list, file=sys.stderr)
|
||||||
assert(len(baseline_list) / 2 == args.baseline_time_s)
|
assert(len(baseline_list) / 2 == args.baseline_time_s)
|
||||||
|
|
||||||
baseline_joules = (
|
baseline_joules = (
|
||||||
@ -161,8 +192,8 @@ if args.power:
|
|||||||
)
|
)
|
||||||
baseline_wattage = baseline_joules / (args.baseline_time_s * 2)
|
baseline_wattage = baseline_joules / (args.baseline_time_s * 2)
|
||||||
if args.debug:
|
if args.debug:
|
||||||
print(baseline_joules)
|
print(baseline_joules, file=sys.stderr)
|
||||||
print(baseline_wattage)
|
print(baseline_wattage, file=sys.stderr)
|
||||||
|
|
||||||
result[Stat.J_1KI.name] = (
|
result[Stat.J_1KI.name] = (
|
||||||
(result[Stat.J.name] / result[Stat.ITERATIONS.name]) * 1000
|
(result[Stat.J.name] / result[Stat.ITERATIONS.name]) * 1000
|
||||||
@ -180,7 +211,7 @@ if args.power:
|
|||||||
)
|
)
|
||||||
|
|
||||||
if args.debug:
|
if args.debug:
|
||||||
print(result)
|
print(result, file=sys.stderr)
|
||||||
|
|
||||||
print(json.dumps(result))
|
print(json.dumps(result))
|
||||||
#if args.perf:
|
#if args.perf:
|
||||||
|
@ -1,4 +1,4 @@
|
|||||||
from data_stat import Stat, Format
|
from data_stat import Stat, Format, MatrixType
|
||||||
|
|
||||||
import torch, scipy
|
import torch, scipy
|
||||||
import numpy as np
|
import numpy as np
|
||||||
@ -8,28 +8,39 @@ import json
|
|||||||
import sys, os
|
import sys, os
|
||||||
|
|
||||||
parser = argparse.ArgumentParser()
|
parser = argparse.ArgumentParser()
|
||||||
parser.add_argument('iterations', type=int, help='the number of iterations of multiplication to perform')
|
parser.add_argument('matrix_type', type=str,
|
||||||
|
choices=[t.name.lower() for t in MatrixType],
|
||||||
|
help='the type of matrix')
|
||||||
parser.add_argument('format', type=str,
|
parser.add_argument('format', type=str,
|
||||||
choices=[fmt.name.lower() for fmt in Format],
|
choices=[fmt.name.lower() for fmt in Format],
|
||||||
help='the sparse format to use')
|
help='the sparse format to use')
|
||||||
parser.add_argument('-m', '--matrix_file', help='the input matrix (.mtx) file')
|
parser.add_argument('iterations', type=int, help='the number of iterations of multiplication to perform')
|
||||||
|
parser.add_argument('-m', '--matrix_file', type=str,
|
||||||
|
help='the input matrix (.mtx) file')
|
||||||
parser.add_argument('-ss', '--synthetic_size', type=int,
|
parser.add_argument('-ss', '--synthetic_size', type=int,
|
||||||
help='the synthetic matrix parameters size (rows)')
|
help='the synthetic matrix parameters size (rows)')
|
||||||
parser.add_argument('-sd', '--synthetic_density', type=float,
|
parser.add_argument('-sd', '--synthetic_density', type=float,
|
||||||
help='the synthetic matrix density (%)')
|
help='the synthetic matrix density')
|
||||||
args = parser.parse_args()
|
args = parser.parse_args()
|
||||||
|
args.matrix_type = MatrixType[args.matrix_type.upper()]
|
||||||
args.format = Format[args.format.upper()]
|
args.format = Format[args.format.upper()]
|
||||||
|
|
||||||
device = 'cpu'
|
device = 'cpu'
|
||||||
|
|
||||||
if args.matrix_file is not None:
|
if args.matrix_type == MatrixType.SUITESPARSE:
|
||||||
|
if args.matrix_file is None:
|
||||||
|
exit("Matrix file not specified!")
|
||||||
|
|
||||||
matrix = scipy.io.mmread(args.matrix_file)
|
matrix = scipy.io.mmread(args.matrix_file)
|
||||||
matrix = torch.sparse_coo_tensor(
|
matrix = torch.sparse_coo_tensor(
|
||||||
np.vstack((matrix.row, matrix.col)),
|
np.vstack((matrix.row, matrix.col)),
|
||||||
matrix.data, matrix.shape,
|
matrix.data, matrix.shape,
|
||||||
device=device, dtype=torch.float32)
|
device=device, dtype=torch.float32)
|
||||||
elif args.synthetic_size is not None and args.synthetic_density is not None:
|
elif args.matrix_type == MatrixType.SYNTHETIC:
|
||||||
nnz = int((args.synthetic_size ** 2) * (args.synthetic_density / 100))
|
if args.synthetic_size is None and args.synthetic_density is None:
|
||||||
|
exit("Synthetic matrix parameters not specified!")
|
||||||
|
|
||||||
|
nnz = int((args.synthetic_size ** 2) * args.synthetic_density)
|
||||||
row_indices = torch.randint(0, args.synthetic_size, (nnz,))
|
row_indices = torch.randint(0, args.synthetic_size, (nnz,))
|
||||||
col_indices = torch.randint(0, args.synthetic_size, (nnz,))
|
col_indices = torch.randint(0, args.synthetic_size, (nnz,))
|
||||||
indices = torch.stack([row_indices, col_indices])
|
indices = torch.stack([row_indices, col_indices])
|
||||||
@ -40,16 +51,14 @@ elif args.synthetic_size is not None and args.synthetic_density is not None:
|
|||||||
size=(args.synthetic_size, args.synthetic_size),
|
size=(args.synthetic_size, args.synthetic_size),
|
||||||
device=device, dtype=torch.float32)
|
device=device, dtype=torch.float32)
|
||||||
else:
|
else:
|
||||||
print("No matrix specified!")
|
exit("Unrecognized matrix type!")
|
||||||
exit(1)
|
|
||||||
|
|
||||||
if args.format == Format.CSR:
|
if args.format == Format.CSR:
|
||||||
matrix = matrix.to_sparse_csr().type(torch.float32)
|
matrix = matrix.to_sparse_csr().type(torch.float32)
|
||||||
elif args.format == Format.COO:
|
elif args.format == Format.COO:
|
||||||
pass
|
pass
|
||||||
else:
|
else:
|
||||||
print("Unrecognized format!")
|
exit("Unrecognized format!")
|
||||||
exit(1)
|
|
||||||
|
|
||||||
vector = torch.rand(matrix.shape[1], device=device)
|
vector = torch.rand(matrix.shape[1], device=device)
|
||||||
|
|
||||||
@ -65,12 +74,16 @@ end = time.time()
|
|||||||
|
|
||||||
result = dict()
|
result = dict()
|
||||||
|
|
||||||
if args.matrix_file is not None:
|
result[Stat.MATRIX_TYPE.name] = args.matrix_type.value
|
||||||
|
print(f"Matrix: {result[Stat.MATRIX_TYPE.name]}", file=sys.stderr)
|
||||||
|
|
||||||
|
if args.matrix_type == MatrixType.SUITESPARSE:
|
||||||
result[Stat.MATRIX_FILE.name] = os.path.splitext(os.path.basename(args.matrix_file))[0]
|
result[Stat.MATRIX_FILE.name] = os.path.splitext(os.path.basename(args.matrix_file))[0]
|
||||||
else:
|
|
||||||
result[Stat.MATRIX_FILE.name] = "synthetic"
|
|
||||||
print(f"Matrix: {result[Stat.MATRIX_FILE.name]}", file=sys.stderr)
|
print(f"Matrix: {result[Stat.MATRIX_FILE.name]}", file=sys.stderr)
|
||||||
|
|
||||||
|
result[Stat.MATRIX_FORMAT.name] = args.format.value
|
||||||
|
print(f"Matrix: {result[Stat.MATRIX_FORMAT.name]}", file=sys.stderr)
|
||||||
|
|
||||||
result[Stat.MATRIX_SHAPE.name] = matrix.shape
|
result[Stat.MATRIX_SHAPE.name] = matrix.shape
|
||||||
print(f"Shape: {result[Stat.MATRIX_SHAPE.name]}", file=sys.stderr)
|
print(f"Shape: {result[Stat.MATRIX_SHAPE.name]}", file=sys.stderr)
|
||||||
|
|
||||||
|
Loading…
Reference in New Issue
Block a user