-
Notifications
You must be signed in to change notification settings - Fork 0
/
benchmark_hash.toml
executable file
·115 lines (93 loc) · 2.66 KB
/
benchmark_hash.toml
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
[test]
# test data
elements = [1000, 2000, 4000, 8000, 10_000, 20_000, 40_000, 80_000, 160_000, 500_000, 1_000_000]
#elements = [1000, 2000, 4000, 8000]
#elements = [1000]
element_max = 1000
rs_scale= [2.0]
rs_join_columns = [1]
# hash
hash_elements_sizes = [8, 16, 32, 64, 128, 256]
hash_algorithms = ["custom", "fnv"]
# algorithm setup
# probe
probe_build_table_loads = [0.5]
probe_build_n_per_threads = [1]
probe_build_threads = [256]
probe_prefix_n_per_threads = [1]
probe_prefix_threads = [128, 256]
probe_extract_n_per_threads = [1]
probe_extract_threads = [128]
probe_extract_x_threads = [16]
# launch
max_streams = 14
runs = 5
gpus = [ 1 ]
# results
output = "benchmark/run/local/hash/test"
[base_all]
# test data
elements = [1000, 2000, 4000, 8000, 10_000, 20_000, 40_000, 80_000, 160_000, 500_000, 1_000_000]
#elements = [1000, 2000, 4000, 8000]
#elements = [1000]
element_max = 1000
rs_scale= [2.0]
rs_join_columns = [1]
# hash
hash_elements_sizes = [8, 16, 32, 64, 128, 256]
hash_algorithms = ["custom_xor", "custom_xor_shift", "custom_mult_xor_shift", "custom_mult_xor_shift", "custom_n_mult_xor_shift", "custom_mult", "custom_mult_shift", "custom_add", "custom_add_shift", "fnv"]
# algorithm setup
# probe
probe_build_table_loads = [0.5]
probe_build_n_per_threads = [1]
probe_build_threads = [256]
probe_prefix_n_per_threads = [1]
probe_prefix_threads = [128, 256]
probe_extract_n_per_threads = [1]
probe_extract_threads = [128]
probe_extract_x_threads = [16]
# launch
max_streams = 14
runs = 5
gpus = [ 1 ]
# results
output = "benchmark/run/local/hash/vec4_4/base_all_vec4_4_1ep"
[gpus]
# test data
elements = [1000, 2000, 4000, 8000, 10_000, 20_000, 40_000, 80_000, 160_000, 500_000, 1_000_000, 10_000_000, 100_000_000]
max_values = [1000]
skews = [0.0]
rs_scale= [2.0]
rs_join_columns = [1]
verify = false
profile = false
# hash
hash_elements_sizes = [8, 16, 32, 64, 128, 256]
hash_algorithms = [
"custom_xor", "custom_xor_shift", "custom_xor_hw",
"custom_mult_xor_shift", "custom_mult_xor_hw", "custom_n_mult_xor_shift",
"custom_mult", "custom_mult_shift", "custom_mult_hw",
"custom_add", "custom_add_shift", "custom_add_hw",
"fnv"]
hash_threads = [256]
hashes_p_threads = [4]
# algorithm setup
# probe
probe_build_table_loads = [0.5]
probe_build_n_per_threads = [1]
probe_build_threads = [256]
probe_prefix_n_per_threads = [1]
probe_prefix_threads = [128, 256]
probe_extract_n_per_threads = [1]
probe_extract_threads = [128]
probe_extract_x_threads = [16]
probe_modes = [0]
# launch
max_streams = [14]
runs = [5]
gpus = [ 1, 2 ]
gpu_modes = [0, 1]
distribution = ["uniform"]
buckets = [2]
# results
output = "benchmark/run/remote/hash/gpus"