XNNPACK
XNNPACK is a Google library for high efficiency floating-point neural network inference operators across mobile / server / web use. XNNPACK is used by machine learning frameworks like TensorFlow, PyTorch, ONNX Runtime, MediaPipe, and others. This test profile uses XNNPACK with its bench-models benchmark and testing all available CPU threads.
XNNPACK b7b048
Model: QS8MobileNetV2
OpenBenchmarking.org metrics for this test profile configuration based on 194 public results since 15 October 2024 with the latest data as of 22 December 2024.
Below is an overview of the generalized performance for components where there is sufficient statistically significant data based upon user-uploaded results. It is important to keep in mind particularly in the Linux/open-source space there can be vastly different OS configurations, with this overview intended to offer just general guidance as to the performance expectations.
Component
Details
Percentile Rank
# Compatible Public Results
us (Average)
Zen 5 [8 Cores / 16 Threads]
99th
5
309 +/- 6
Zen 4 [8 Cores / 16 Threads]
96th
3
547 +/- 30
Zen 4 [4 Cores / 8 Threads]
95th
4
623
Arrow Lake [24 Cores / 24 Threads]
91st
7
649 +/- 25
Arrow Lake [14 Cores / 14 Threads]
88th
5
696 +/- 8
Zen 4 [12 Cores / 24 Threads]
88th
4
703
Zen 4 [12 Cores / 24 Threads]
83rd
6
720 +/- 3
Zen 5 [16 Cores / 32 Threads]
80th
4
762 +/- 20
Raptor Lake [24 Cores / 32 Threads]
79th
4
781 +/- 6
Zen 4 [16 Cores / 32 Threads]
76th
8
808 +/- 5
Zen 4 [16 Cores / 32 Threads]
72nd
6
847 +/- 5
Alder Lake [10 Cores / 16 Threads]
69th
3
932 +/- 131
Zen 4 [8 Cores / 16 Threads]
66th
4
984 +/- 53
Zen 5 [10 Cores / 20 Threads]
63rd
3
1097 +/- 12
Zen 5 [12 Cores / 24 Threads]
61st
4
1145 +/- 18
Tiger Lake [4 Cores / 8 Threads]
58th
3
1239 +/- 7
Zen 2 [12 Cores / 24 Threads]
56th
3
1373 +/- 3
Zen 3 [8 Cores / 16 Threads]
54th
4
1409 +/- 5
Lunar Lake [8 Cores / 8 Threads]
52nd
4
1425 +/- 9
Cascade Lake [18 Cores / 36 Threads]
51st
3
1451 +/- 37
Zen 3 [8 Cores / 16 Threads]
49th
4
1781
Alder Lake [14 Cores / 20 Threads]
46th
4
1866 +/- 26
Zen 3 [8 Cores / 16 Threads]
44th
3
1939 +/- 3
Ice Lake [4 Cores / 8 Threads]
38th
3
2071 +/- 285
Zen 2 [32 Cores / 64 Threads]
38th
4
2075 +/- 19
Meteor Lake [16 Cores / 22 Threads]
37th
4
2092 +/- 39
Cascade Lake [16 Cores / 32 Threads]
31st
3
2480 +/- 23
Zen 4 [64 Cores / 128 Threads]
28th
5
4015 +/- 27
Zen 2 [64 Cores / 128 Threads]
22nd
3
5808 +/- 199
Zen 5 [96 Cores / 192 Threads]
13th
21
10163 +/- 686
Granite Rapids [128 Cores / 256 Threads]
10th
3
16276 +/- 298