| MobileNetV2 [fp32,imagenet] (TensorFlow) kernel-execution with IREE-Vulkan @ SM-G980F (GPU-Mali-G77) |
17 |
17 |
1 |
| MobileNetV2 [fp32,imagenet] (TensorFlow) 3-thread,little-core,full-inference with IREE-Dylib @ SM-G980F (CPU-ARMv8.2-A) |
873 |
872 |
8 |
| MobileNetV2 [fp32,imagenet] (TensorFlow) 1-thread,little-core,full-inference with IREE-Dylib @ SM-G980F (CPU-ARMv8.2-A) |
1225 |
1252 |
56 |
| MobileNetV2 [fp32,imagenet] (TensorFlow) full-inference with IREE-Vulkan @ SM-G980F (GPU-Mali-G77) |
85 |
86 |
4 |
| MobileNetV2 [fp32,imagenet] (TensorFlow) 3-thread,big-core,full-inference with IREE-Dylib @ SM-G980F (CPU-ARMv8.2-A) |
192 |
192 |
5 |
| MobileNetV2 [fp32,imagenet] (TensorFlow) 1-thread,big-core,full-inference with IREE-Dylib @ SM-G980F (CPU-ARMv8.2-A) |
139 |
140 |
1 |
| MobileNetV2 [fp32,imagenet] (TensorFlow) little-core,full-inference with IREE-Dylib-Sync @ SM-G980F (CPU-ARMv8.2-A) |
1252 |
1253 |
5 |
| MobileNetV2 [fp32,imagenet] (TensorFlow) big-core,full-inference with IREE-Dylib-Sync @ SM-G980F (CPU-ARMv8.2-A) |
140 |
140 |
2 |
| MobileNetV2 [fp32,imagenet] (TensorFlow) 3-thread,little-core,full-inference with IREE-VMVX @ SM-G980F (CPU-ARMv8.2-A) |
63426 |
63423 |
25 |
| MobileNetV3Small [fp32,imagenet] (TensorFlow) kernel-execution with IREE-Vulkan @ SM-G980F (GPU-Mali-G77) |
20 |
20 |
1 |
| MobileNetV3Small [fp32,imagenet] (TensorFlow) 3-thread,little-core,full-inference with IREE-Dylib @ SM-G980F (CPU-ARMv8.2-A) |
306 |
313 |
15 |
| MobileNetV3Small [fp32,imagenet] (TensorFlow) 1-thread,little-core,full-inference with IREE-Dylib @ SM-G980F (CPU-ARMv8.2-A) |
370 |
374 |
9 |
| MobileNetV3Small [fp32,imagenet] (TensorFlow) full-inference with IREE-Vulkan @ SM-G980F (GPU-Mali-G77) |
81 |
81 |
2 |
| MobileNetV3Small [fp32,imagenet] (TensorFlow) 3-thread,big-core,full-inference with IREE-Dylib @ SM-G980F (CPU-ARMv8.2-A) |
80 |
79 |
3 |
| MobileNetV3Small [fp32,imagenet] (TensorFlow) 1-thread,big-core,full-inference with IREE-Dylib @ SM-G980F (CPU-ARMv8.2-A) |
45 |
45 |
0 |
| MobileNetV3Small [fp32,imagenet] (TensorFlow) little-core,full-inference with IREE-Dylib-Sync @ SM-G980F (CPU-ARMv8.2-A) |
373 |
374 |
4 |
| MobileNetV3Small [fp32,imagenet] (TensorFlow) big-core,full-inference with IREE-Dylib-Sync @ SM-G980F (CPU-ARMv8.2-A) |
46 |
45 |
1 |
| MobileNetV3Small [fp32,imagenet] (TensorFlow) 3-thread,little-core,full-inference with IREE-VMVX @ SM-G980F (CPU-ARMv8.2-A) |
16923 |
16945 |
67 |
| MobileNetV2 [fp32,imagenet] (TensorFlow) 3-thread,little-core,full-inference with IREE-Dylib @ Pixel-4 (CPU-ARMv8.2-A) |
993 |
973 |
71 |
| MobileNetV2 [fp32,imagenet] (TensorFlow) 1-thread,little-core,full-inference with IREE-Dylib @ Pixel-4 (CPU-ARMv8.2-A) |
1328 |
1331 |
8 |
| MobileNetV2 [fp32,imagenet] (TensorFlow) 3-thread,big-core,full-inference with IREE-Dylib @ Pixel-4 (CPU-ARMv8.2-A) |
231 |
232 |
13 |
| MobileNetV2 [fp32,imagenet] (TensorFlow) 1-thread,big-core,full-inference with IREE-Dylib @ Pixel-4 (CPU-ARMv8.2-A) |
170 |
170 |
0 |
| MobileNetV2 [fp32,imagenet] (TensorFlow) little-core,full-inference with IREE-Dylib-Sync @ Pixel-4 (CPU-ARMv8.2-A) |
1327 |
1325 |
5 |
| MobileNetV2 [fp32,imagenet] (TensorFlow) big-core,full-inference with IREE-Dylib-Sync @ Pixel-4 (CPU-ARMv8.2-A) |
211 |
210 |
2 |
| MobileNetV2 [fp32,imagenet] (TensorFlow) full-inference with IREE-Vulkan @ Pixel-4 (GPU-Adreno-640) |
74 |
74 |
0 |
| MobileNetV2 [fp32,imagenet] (TensorFlow) kernel-execution with IREE-Vulkan @ Pixel-4 (GPU-Adreno-640) |
70 |
70 |
1 |
| MobileNetV2 [fp32,imagenet] (TensorFlow) 3-thread,little-core,full-inference with IREE-VMVX @ Pixel-4 (CPU-ARMv8.2-A) |
71561 |
71575 |
37 |
| MobileNetV3Small [fp32,imagenet] (TensorFlow) 3-thread,little-core,full-inference with IREE-Dylib @ Pixel-4 (CPU-ARMv8.2-A) |
402 |
411 |
43 |
| MobileNetV3Small [fp32,imagenet] (TensorFlow) 1-thread,little-core,full-inference with IREE-Dylib @ Pixel-4 (CPU-ARMv8.2-A) |
388 |
388 |
2 |
| MobileNetV3Small [fp32,imagenet] (TensorFlow) 3-thread,big-core,full-inference with IREE-Dylib @ Pixel-4 (CPU-ARMv8.2-A) |
121 |
124 |
10 |
| MobileNetV3Small [fp32,imagenet] (TensorFlow) 1-thread,big-core,full-inference with IREE-Dylib @ Pixel-4 (CPU-ARMv8.2-A) |
51 |
51 |
0 |
| MobileNetV3Small [fp32,imagenet] (TensorFlow) little-core,full-inference with IREE-Dylib-Sync @ Pixel-4 (CPU-ARMv8.2-A) |
387 |
387 |
2 |
| MobileNetV3Small [fp32,imagenet] (TensorFlow) big-core,full-inference with IREE-Dylib-Sync @ Pixel-4 (CPU-ARMv8.2-A) |
60 |
60 |
0 |
| MobileNetV3Small [fp32,imagenet] (TensorFlow) full-inference with IREE-Vulkan @ Pixel-4 (GPU-Adreno-640) |
38 |
38 |
0 |
| MobileNetV3Small [fp32,imagenet] (TensorFlow) kernel-execution with IREE-Vulkan @ Pixel-4 (GPU-Adreno-640) |
35 |
34 |
1 |
| MobileNetV3Small [fp32,imagenet] (TensorFlow) 3-thread,little-core,full-inference with IREE-VMVX @ Pixel-4 (CPU-ARMv8.2-A) |
19122 |
19121 |
15 |
