-
Notifications
You must be signed in to change notification settings - Fork 0
/
vta_v0.05.log
63 lines (63 loc) · 35.6 KB
/
vta_v0.05.log
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
# ultra96 cpu
{"i": ["llvm -device=arm_cpu -model=ultra96", "topi_nn_conv2d", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 7, 7], "float32"], [2, 2], [3, 3], [1, 1], "NCHW", "float32"], {}, ["conv2d", [1, 3, 224, 224, "float32"], [64, 3, 7, 7, "float32"], [2, 2], [3, 3], [1, 1], "NCHW", "float32"], {"i": 58242, "c": null, "e": [["tile_co", "sp", [16, 4]], ["tile_oh", "sp", [112, 1]], ["tile_ow", "sp", [28, 4]], ["reorder_0", "re", [0, 1, 2, 3, 4, 5, 6, 9, 7, 8]], ["ann_reduce", "an", ["none", "unroll"]], ["ann_spatial", "an", ["unroll", "none", "vec"]]], "t": "direct"}], "r": [[0.0202839052], 0, 1.0239202976226807, 1535933156.928128], "v": 0.1}
{"i": ["llvm -device=arm_cpu -model=ultra96", "topi_nn_conv2d", [["TENSOR", [1, 512, 7, 7], "int8"], ["TENSOR", [512, 512, 3, 3], "int8"], [1, 1], [1, 1], [1, 1], "NCHW", "int32"], {}, ["conv2d", [1, 512, 7, 7, "int8"], [512, 512, 3, 3, "int8"], [1, 1], [1, 1], [1, 1], "NCHW", "int32"], {"i": 4423, "t": "direct", "c": null, "e": [["tile_co", "sp", [64, 8]], ["tile_oh", "sp", [7, 1]], ["tile_ow", "sp", [1, 7]], ["reorder_0", "re", [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]], ["ann_reduce", "an", ["unroll", "unroll"]], ["ann_spatial", "an", ["unroll", "unroll", "vec"]]]}], "r": [[0.0100865416], 0, 5.641042947769165, 1535551214.651092], "v": 0.1}
{"i": ["llvm -device=arm_cpu -model=ultra96", "topi_nn_conv2d", [["TENSOR", [1, 256, 14, 14], "int8"], ["TENSOR", [512, 256, 1, 1], "int8"], [2, 2], [0, 0], [1, 1], "NCHW", "int32"], {}, ["conv2d", [1, 256, 14, 14, "int8"], [512, 256, 1, 1, "int8"], [2, 2], [0, 0], [1, 1], "NCHW", "int32"], {"i": 1904, "t": "direct", "c": null, "e": [["tile_co", "sp", [32, 16]], ["tile_oh", "sp", [7, 1]], ["tile_ow", "sp", [1, 7]], ["reorder_0", "re", [0, 1, 2, 3, 4, 5, 6, 9, 7, 8]], ["ann_reduce", "an", ["unroll", "unroll"]], ["ann_spatial", "an", ["none", "unroll", "vec"]]]}], "r": [[0.0007296307999999999], 0, 2.3051419258117676, 1535551739.2673764], "v": 0.1}
{"i": ["llvm -device=arm_cpu -model=ultra96", "topi_nn_conv2d", [["TENSOR", [1, 256, 14, 14], "int8"], ["TENSOR", [512, 256, 3, 3], "int8"], [2, 2], [1, 1], [1, 1], "NCHW", "int32"], {}, ["conv2d", [1, 256, 14, 14, "int8"], [512, 256, 3, 3, "int8"], [2, 2], [1, 1], [1, 1], "NCHW", "int32"], {"i": 3463, "t": "direct", "c": null, "e": [["tile_co", "sp", [64, 8]], ["tile_oh", "sp", [7, 1]], ["tile_ow", "sp", [1, 7]], ["reorder_0", "re", [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]], ["ann_reduce", "an", ["unroll", "unroll"]], ["ann_spatial", "an", ["unroll", "none", "vec"]]]}], "r": [[0.0059753762], 0, 3.171846866607666, 1535551981.8172796], "v": 0.1}
{"i": ["llvm -device=arm_cpu -model=ultra96", "topi_nn_conv2d", [["TENSOR", [1, 256, 14, 14], "int8"], ["TENSOR", [256, 256, 3, 3], "int8"], [1, 1], [1, 1], [1, 1], "NCHW", "int32"], {}, ["conv2d", [1, 256, 14, 14, "int8"], [256, 256, 3, 3, "int8"], [1, 1], [1, 1], [1, 1], "NCHW", "int32"], {"i": 16059, "t": "direct", "c": null, "e": [["tile_co", "sp", [32, 8]], ["tile_oh", "sp", [14, 1]], ["tile_ow", "sp", [2, 7]], ["reorder_0", "re", [0, 1, 2, 3, 4, 5, 6, 9, 7, 8]], ["ann_reduce", "an", ["unroll", "unroll"]], ["ann_spatial", "an", ["unroll", "unroll", "vec"]]]}], "r": [[0.0099357546], 0, 1.8019628524780273, 1535552294.3617342], "v": 0.1}
{"i": ["llvm -device=arm_cpu -model=ultra96", "topi_nn_conv2d", [["TENSOR", [1, 128, 28, 28], "int8"], ["TENSOR", [256, 128, 1, 1], "int8"], [2, 2], [0, 0], [1, 1], "NCHW", "int32"], {}, ["conv2d", [1, 128, 28, 28, "int8"], [256, 128, 1, 1, "int8"], [2, 2], [0, 0], [1, 1], "NCHW", "int32"], {"i": 6556, "t": "direct", "c": null, "e": [["tile_co", "sp", [16, 16]], ["tile_oh", "sp", [14, 1]], ["tile_ow", "sp", [2, 7]], ["reorder_0", "re", [0, 1, 2, 3, 4, 5, 6, 9, 7, 8]], ["ann_reduce", "an", ["unroll", "none"]], ["ann_spatial", "an", ["none", "unroll", "vec"]]]}], "r": [[0.0007622722], 0, 0.5538501739501953, 1535552684.6286695], "v": 0.1}
{"i": ["llvm -device=arm_cpu -model=ultra96", "topi_nn_conv2d", [["TENSOR", [1, 128, 28, 28], "int8"], ["TENSOR", [256, 128, 3, 3], "int8"], [2, 2], [1, 1], [1, 1], "NCHW", "int32"], {}, ["conv2d", [1, 128, 28, 28, "int8"], [256, 128, 3, 3, "int8"], [2, 2], [1, 1], [1, 1], "NCHW", "int32"], {"i": 6817, "t": "direct", "c": null, "e": [["tile_co", "sp", [16, 16]], ["tile_oh", "sp", [7, 2]], ["tile_ow", "sp", [7, 2]], ["reorder_0", "re", [0, 1, 2, 3, 4, 5, 6, 9, 7, 8]], ["ann_reduce", "an", ["unroll", "unroll"]], ["ann_spatial", "an", ["none", "unroll", "vec"]]]}], "r": [[0.005641302], 0, 0.6911592483520508, 1535553000.5167894], "v": 0.1}
{"i": ["llvm -device=arm_cpu -model=ultra96", "topi_nn_conv2d", [["TENSOR", [1, 128, 28, 28], "int8"], ["TENSOR", [128, 128, 3, 3], "int8"], [1, 1], [1, 1], [1, 1], "NCHW", "int32"], {}, ["conv2d", [1, 128, 28, 28, "int8"], [128, 128, 3, 3, "int8"], [1, 1], [1, 1], [1, 1], "NCHW", "int32"], {"i": 24875, "t": "direct", "c": null, "e": [["tile_co", "sp", [16, 8]], ["tile_oh", "sp", [14, 2]], ["tile_ow", "sp", [7, 4]], ["reorder_0", "re", [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]], ["ann_reduce", "an", ["unroll", "unroll"]], ["ann_spatial", "an", ["unroll", "none", "vec"]]]}], "r": [[0.0098091426], 0, 1.2815163135528564, 1535553347.3520076], "v": 0.1}
{"i": ["llvm -device=arm_cpu -model=ultra96", "topi_nn_conv2d", [["TENSOR", [1, 64, 56, 56], "int8"], ["TENSOR", [128, 64, 1, 1], "int8"], [2, 2], [0, 0], [1, 1], "NCHW", "int32"], {}, ["conv2d", [1, 64, 56, 56, "int8"], [128, 64, 1, 1, "int8"], [2, 2], [0, 0], [1, 1], "NCHW", "int32"], {"i": 6772, "t": "direct", "c": null, "e": [["tile_co", "sp", [8, 16]], ["tile_oh", "sp", [28, 1]], ["tile_ow", "sp", [4, 7]], ["reorder_0", "re", [0, 1, 2, 3, 4, 5, 6, 9, 7, 8]], ["ann_reduce", "an", ["unroll", "unroll"]], ["ann_spatial", "an", ["none", "none", "vec"]]]}], "r": [[0.0008892208000000001], 0, 3.323061227798462, 1535553730.5811121], "v": 0.1}
{"i": ["llvm -device=arm_cpu -model=ultra96", "topi_nn_conv2d", [["TENSOR", [1, 64, 56, 56], "int8"], ["TENSOR", [128, 64, 3, 3], "int8"], [2, 2], [1, 1], [1, 1], "NCHW", "int32"], {}, ["conv2d", [1, 64, 56, 56, "int8"], [128, 64, 3, 3, "int8"], [2, 2], [1, 1], [1, 1], "NCHW", "int32"], {"i": 31164, "t": "direct", "c": null, "e": [["tile_co", "sp", [8, 16]], ["tile_oh", "sp", [14, 2]], ["tile_ow", "sp", [14, 2]], ["reorder_0", "re", [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]], ["ann_reduce", "an", ["unroll", "none"]], ["ann_spatial", "an", ["unroll", "unroll", "vec"]]]}], "r": [[0.0060430568], 0, 1.1739919185638428, 1535554281.3413563], "v": 0.1}
{"i": ["llvm -device=arm_cpu -model=ultra96", "topi_nn_conv2d", [["TENSOR", [1, 64, 56, 56], "int8"], ["TENSOR", [64, 64, 1, 1], "int8"], [1, 1], [0, 0], [1, 1], "NCHW", "int32"], {}, ["conv2d", [1, 64, 56, 56, "int8"], [64, 64, 1, 1, "int8"], [1, 1], [0, 0], [1, 1], "NCHW", "int32"], {"i": 17945, "t": "direct", "c": null, "e": [["tile_co", "sp", [4, 16]], ["tile_oh", "sp", [8, 7]], ["tile_ow", "sp", [56, 1]], ["reorder_0", "re", [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]], ["ann_reduce", "an", ["none", "none"]], ["ann_spatial", "an", ["none", "unroll", "vec"]]]}], "r": [[0.0018701498], 0, 3.8785617351531982, 1535555032.8744369], "v": 0.1}
{"i": ["llvm -device=arm_cpu -model=ultra96", "topi_nn_conv2d", [["TENSOR", [1, 64, 56, 56], "int8"], ["TENSOR", [64, 64, 3, 3], "int8"], [1, 1], [1, 1], [1, 1], "NCHW", "int32"], {}, ["conv2d", [1, 64, 56, 56, "int8"], [64, 64, 3, 3, "int8"], [1, 1], [1, 1], [1, 1], "NCHW", "int32"], {"i": 38650, "t": "direct", "c": null, "e": [["tile_co", "sp", [8, 8]], ["tile_oh", "sp", [28, 2]], ["tile_ow", "sp", [14, 4]], ["reorder_0", "re", [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]], ["ann_reduce", "an", ["unroll", "unroll"]], ["ann_spatial", "an", ["unroll", "none", "vec"]]]}], "r": [[0.010470156999999999], 0, 3.982750177383423, 1535555338.4477994], "v": 0.1}
{"i": ["llvm -device=arm_cpu -model=ultra96", "topi_nn_conv2d", [["TENSOR", [1, 3, 224, 224], "int8"], ["TENSOR", [64, 3, 7, 7], "int8"], [2, 2], [3, 3], [1, 1], "NCHW", "int32"], {}, ["conv2d", [1, 3, 224, 224, "int8"], [64, 3, 7, 7, "int8"], [2, 2], [3, 3], [1, 1], "NCHW", "int32"], {"i": 29487, "t": "direct", "c": null, "e": [["tile_co", "sp", [8, 8]], ["tile_oh", "sp", [28, 4]], ["tile_ow", "sp", [56, 2]], ["reorder_0", "re", [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]], ["ann_reduce", "an", ["none", "unroll"]], ["ann_spatial", "an", ["none", "unroll", "vec"]]]}], "r": [[0.012954154200000002], 0, 7.431337833404541, 1535556557.9278886], "v": 0.1}
# pynq cpu
{"v": 0.1, "i": ["llvm -device=arm_cpu -model=pynq", "topi_nn_conv2d", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 7, 7], "float32"], [2, 2], [3, 3], [1, 1], "NCHW", "float32"], {}, ["conv2d", [1, 3, 224, 224, "float32"], [64, 3, 7, 7, "float32"], [2, 2], [3, 3], [1, 1], "NCHW", "float32"], {"t": "direct", "i": 72880, "c": null, "e": [["tile_co", "sp", [8, 8]], ["tile_oh", "sp", [56, 2]], ["tile_ow", "sp", [56, 2]], ["reorder_0", "re", [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]], ["ann_reduce", "an", ["none", "none"]], ["ann_spatial", "an", ["unroll", "unroll", "vec"]]]}], "r": [[0.106961243], 0, 1.368462085723877, 1536393445.5359874]}
{"i": ["llvm -device=arm_cpu -model=pynq", "topi_nn_conv2d", [["TENSOR", [1, 512, 7, 7], "int8"], ["TENSOR", [512, 512, 3, 3], "int8"], [1, 1], [1, 1], [1, 1], "NCHW", "int32"], {}, ["conv2d", [1, 512, 7, 7, "int8"], [512, 512, 3, 3, "int8"], [1, 1], [1, 1], [1, 1], "NCHW", "int32"], {"i": 1742, "t": "direct", "c": null, "e": [["tile_co", "sp", [128, 4]], ["tile_oh", "sp", [7, 1]], ["tile_ow", "sp", [1, 7]], ["reorder_0", "re", [0, 1, 2, 3, 4, 5, 6, 9, 7, 8]], ["ann_reduce", "an", ["none", "unroll"]], ["ann_spatial", "an", ["none", "unroll", "vec"]]]}], "r": [[0.11922881433333334], 0, 13.844602346420288, 1535551459.0461988], "v": 0.1}
{"i": ["llvm -device=arm_cpu -model=pynq", "topi_nn_conv2d", [["TENSOR", [1, 256, 14, 14], "int8"], ["TENSOR", [512, 256, 1, 1], "int8"], [2, 2], [0, 0], [1, 1], "NCHW", "int32"], {}, ["conv2d", [1, 256, 14, 14, "int8"], [512, 256, 1, 1, "int8"], [2, 2], [0, 0], [1, 1], "NCHW", "int32"], {"i": 3492, "t": "direct", "c": null, "e": [["tile_co", "sp", [128, 4]], ["tile_oh", "sp", [1, 7]], ["tile_ow", "sp", [7, 1]], ["reorder_0", "re", [0, 1, 2, 3, 4, 5, 6, 9, 7, 8]], ["ann_reduce", "an", ["unroll", "unroll"]], ["ann_spatial", "an", ["unroll", "none", "vec"]]]}], "r": [[0.007602235], 0, 3.289456367492676, 1535552198.6877465], "v": 0.1}
{"i": ["llvm -device=arm_cpu -model=pynq", "topi_nn_conv2d", [["TENSOR", [1, 256, 14, 14], "int8"], ["TENSOR", [512, 256, 3, 3], "int8"], [2, 2], [1, 1], [1, 1], "NCHW", "int32"], {}, ["conv2d", [1, 256, 14, 14, "int8"], [512, 256, 3, 3, "int8"], [2, 2], [1, 1], [1, 1], "NCHW", "int32"], {"i": 702, "t": "direct", "c": null, "e": [["tile_co", "sp", [128, 4]], ["tile_oh", "sp", [7, 1]], ["tile_ow", "sp", [1, 7]], ["reorder_0", "re", [0, 1, 2, 3, 4, 5, 6, 9, 7, 8]], ["ann_reduce", "an", ["none", "none"]], ["ann_spatial", "an", ["none", "none", "vec"]]]}], "r": [[0.064834877], 0, 9.512434720993042, 1535552633.3174489], "v": 0.1}
{"i": ["llvm -device=arm_cpu -model=pynq", "topi_nn_conv2d", [["TENSOR", [1, 256, 14, 14], "int8"], ["TENSOR", [256, 256, 3, 3], "int8"], [1, 1], [1, 1], [1, 1], "NCHW", "int32"], {}, ["conv2d", [1, 256, 14, 14, "int8"], [256, 256, 3, 3, "int8"], [1, 1], [1, 1], [1, 1], "NCHW", "int32"], {"i": 5978, "t": "direct", "c": null, "e": [["tile_co", "sp", [64, 4]], ["tile_oh", "sp", [14, 1]], ["tile_ow", "sp", [2, 7]], ["reorder_0", "re", [0, 1, 2, 3, 4, 5, 6, 9, 7, 8]], ["ann_reduce", "an", ["none", "none"]], ["ann_spatial", "an", ["none", "unroll", "vec"]]]}], "r": [[0.12019337633333334], 0, 13.085431098937988, 1535553319.1595852], "v": 0.1}
{"i": ["llvm -device=arm_cpu -model=pynq", "topi_nn_conv2d", [["TENSOR", [1, 128, 28, 28], "int8"], ["TENSOR", [256, 128, 1, 1], "int8"], [2, 2], [0, 0], [1, 1], "NCHW", "int32"], {}, ["conv2d", [1, 128, 28, 28, "int8"], [256, 128, 1, 1, "int8"], [2, 2], [0, 0], [1, 1], "NCHW", "int32"], {"i": 6520, "t": "direct", "c": null, "e": [["tile_co", "sp", [16, 16]], ["tile_oh", "sp", [14, 1]], ["tile_ow", "sp", [7, 2]], ["reorder_0", "re", [0, 1, 2, 3, 4, 5, 6, 9, 7, 8]], ["ann_reduce", "an", ["unroll", "none"]], ["ann_spatial", "an", ["none", "unroll", "vec"]]]}], "r": [[0.006816275], 0, 5.8638012409210205, 1535554041.0982096], "v": 0.1}
{"i": ["llvm -device=arm_cpu -model=pynq", "topi_nn_conv2d", [["TENSOR", [1, 128, 28, 28], "int8"], ["TENSOR", [256, 128, 3, 3], "int8"], [2, 2], [1, 1], [1, 1], "NCHW", "int32"], {}, ["conv2d", [1, 128, 28, 28, "int8"], [256, 128, 3, 3, "int8"], [2, 2], [1, 1], [1, 1], "NCHW", "int32"], {"i": 2343, "t": "direct", "c": null, "e": [["tile_co", "sp", [32, 8]], ["tile_oh", "sp", [14, 1]], ["tile_ow", "sp", [7, 2]], ["reorder_0", "re", [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]], ["ann_reduce", "an", ["none", "none"]], ["ann_spatial", "an", ["none", "none", "vec"]]]}], "r": [[0.06175303966666667], 0, 3.050752639770508, 1535554364.6778674], "v": 0.1}
{"i": ["llvm -device=arm_cpu -model=pynq", "topi_nn_conv2d", [["TENSOR", [1, 128, 28, 28], "int8"], ["TENSOR", [128, 128, 3, 3], "int8"], [1, 1], [1, 1], [1, 1], "NCHW", "int32"], {}, ["conv2d", [1, 128, 28, 28, "int8"], [128, 128, 3, 3, "int8"], [1, 1], [1, 1], [1, 1], "NCHW", "int32"], {"i": 5042, "t": "direct", "c": null, "e": [["tile_co", "sp", [32, 4]], ["tile_oh", "sp", [28, 1]], ["tile_ow", "sp", [4, 7]], ["reorder_0", "re", [0, 1, 2, 3, 4, 5, 6, 9, 7, 8]], ["ann_reduce", "an", ["none", "none"]], ["ann_spatial", "an", ["none", "none", "vec"]]]}], "r": [[0.12095182866666666], 0, 11.543709993362427, 1535554860.9579132], "v": 0.1}
{"i": ["llvm -device=arm_cpu -model=pynq", "topi_nn_conv2d", [["TENSOR", [1, 64, 56, 56], "int8"], ["TENSOR", [128, 64, 1, 1], "int8"], [2, 2], [0, 0], [1, 1], "NCHW", "int32"], {}, ["conv2d", [1, 64, 56, 56, "int8"], [128, 64, 1, 1, "int8"], [2, 2], [0, 0], [1, 1], "NCHW", "int32"], {"i": 31732, "t": "direct", "c": null, "e": [["tile_co", "sp", [8, 16]], ["tile_oh", "sp", [28, 1]], ["tile_ow", "sp", [14, 2]], ["reorder_0", "re", [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]], ["ann_reduce", "an", ["unroll", "unroll"]], ["ann_spatial", "an", ["unroll", "unroll", "vec"]]]}], "r": [[0.0073260719999999994], 0, 2.993452787399292, 1535555590.831976], "v": 0.1}
{"i": ["llvm -device=arm_cpu -model=pynq", "topi_nn_conv2d", [["TENSOR", [1, 64, 56, 56], "int8"], ["TENSOR", [128, 64, 3, 3], "int8"], [2, 2], [1, 1], [1, 1], "NCHW", "int32"], {}, ["conv2d", [1, 64, 56, 56, "int8"], [128, 64, 3, 3, "int8"], [2, 2], [1, 1], [1, 1], "NCHW", "int32"], {"i": 5811, "t": "direct", "c": null, "e": [["tile_co", "sp", [16, 8]], ["tile_oh", "sp", [28, 1]], ["tile_ow", "sp", [14, 2]], ["reorder_0", "re", [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]], ["ann_reduce", "an", ["unroll", "none"]], ["ann_spatial", "an", ["none", "none", "vec"]]]}], "r": [[0.062554371], 0, 3.906409978866577, 1535555957.328984], "v": 0.1}
{"i": ["llvm -device=arm_cpu -model=pynq", "topi_nn_conv2d", [["TENSOR", [1, 64, 56, 56], "int8"], ["TENSOR", [64, 64, 1, 1], "int8"], [1, 1], [0, 0], [1, 1], "NCHW", "int32"], {}, ["conv2d", [1, 64, 56, 56, "int8"], [64, 64, 1, 1, "int8"], [1, 1], [0, 0], [1, 1], "NCHW", "int32"], {"i": 48499, "t": "direct", "c": null, "e": [["tile_co", "sp", [8, 8]], ["tile_oh", "sp", [56, 1]], ["tile_ow", "sp", [14, 4]], ["reorder_0", "re", [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]], ["ann_reduce", "an", ["unroll", "none"]], ["ann_spatial", "an", ["unroll", "unroll", "vec"]]]}], "r": [[0.014775187666666667], 0, 5.335652112960815, 1535556501.3760905], "v": 0.1}
{"i": ["llvm -device=arm_cpu -model=pynq", "topi_nn_conv2d", [["TENSOR", [1, 64, 56, 56], "int8"], ["TENSOR", [64, 64, 3, 3], "int8"], [1, 1], [1, 1], [1, 1], "NCHW", "int32"], {}, ["conv2d", [1, 64, 56, 56, "int8"], [64, 64, 3, 3, "int8"], [1, 1], [1, 1], [1, 1], "NCHW", "int32"], {"i": 7227, "t": "direct", "c": null, "e": [["tile_co", "sp", [8, 8]], ["tile_oh", "sp", [56, 1]], ["tile_ow", "sp", [28, 2]], ["reorder_0", "re", [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]], ["ann_reduce", "an", ["none", "none"]], ["ann_spatial", "an", ["none", "none", "vec"]]]}], "r": [[0.12438399366666668], 0, 9.061516523361206, 1535556874.9369888], "v": 0.1}
{"i": ["llvm -device=arm_cpu -model=pynq", "topi_nn_conv2d", [["TENSOR", [1, 3, 224, 224], "int8"], ["TENSOR", [64, 3, 7, 7], "int8"], [2, 2], [3, 3], [1, 1], "NCHW", "int32"], {}, ["conv2d", [1, 3, 224, 224, "int8"], [64, 3, 7, 7, "int8"], [2, 2], [3, 3], [1, 1], "NCHW", "int32"], {"i": 59580, "t": "direct", "c": null, "e": [["tile_co", "sp", [8, 8]], ["tile_oh", "sp", [56, 2]], ["tile_ow", "sp", [56, 2]], ["reorder_0", "re", [0, 1, 2, 3, 4, 5, 6, 9, 7, 8]], ["ann_reduce", "an", ["unroll", "none"]], ["ann_spatial", "an", ["unroll", "none", "vec"]]]}], "r": [[0.127179968], 0, 10.66846251487732, 1535558518.751117], "v": 0.1}
# ultra96 fpga
{"v": 0.1, "r": [[0.0006344365], 0, 6.047821760177612, 1536796371.6109414], "i": ["ext_dev -device=vta -keys=cpu -model=ultra96", "topi_nn_conv2d", [["TENSOR", [1, 16, 14, 14, 1, 16], "int8"], ["TENSOR", [32, 16, 1, 1, 16, 16], "int8"], [2, 2], [0, 0], [1, 1], "NCHW1n16c", "int32"], {}, ["conv2d", [1, 16, 14, 14, 1, 16, "int8"], [32, 16, 1, 1, 16, 16, "int8"], [2, 2], [0, 0], [1, 1], "NCHW1n16c", "int32"], {"e": [["tile_b", "sp", [1, 1]], ["tile_h", "sp", [1, 7]], ["tile_w", "sp", [1, 7]], ["tile_ci", "sp", [16, 1]], ["tile_co", "sp", [2, 16]], ["oc_nthread", "ot", 2], ["h_nthread", "ot", 1]], "c": null, "i": 203, "t": "direct"}]}
{"v": 0.1, "r": [[0.00172219525], 0, 4.90694785118103, 1536796564.39578], "i": ["ext_dev -device=vta -keys=cpu -model=ultra96", "topi_nn_conv2d", [["TENSOR", [1, 32, 7, 7, 1, 16], "int8"], ["TENSOR", [32, 32, 3, 3, 16, 16], "int8"], [1, 1], [1, 1], [1, 1], "NCHW1n16c", "int32"], {}, ["conv2d", [1, 32, 7, 7, 1, 16, "int8"], [32, 32, 3, 3, 16, 16, "int8"], [1, 1], [1, 1], [1, 1], "NCHW1n16c", "int32"], {"e": [["tile_b", "sp", [1, 1]], ["tile_h", "sp", [1, 7]], ["tile_w", "sp", [1, 7]], ["tile_ci", "sp", [32, 1]], ["tile_co", "sp", [2, 16]], ["oc_nthread", "ot", 2], ["h_nthread", "ot", 1]], "c": null, "i": 243, "t": "direct"}]}
{"v": 0.1, "r": [[0.00107295075], 0, 2.922736644744873, 1536796661.6000884], "i": ["ext_dev -device=vta -keys=cpu -model=ultra96", "topi_nn_conv2d", [["TENSOR", [1, 16, 14, 14, 1, 16], "int8"], ["TENSOR", [32, 16, 3, 3, 16, 16], "int8"], [2, 2], [1, 1], [1, 1], "NCHW1n16c", "int32"], {}, ["conv2d", [1, 16, 14, 14, 1, 16, "int8"], [32, 16, 3, 3, 16, 16, "int8"], [2, 2], [1, 1], [1, 1], "NCHW1n16c", "int32"], {"e": [["tile_b", "sp", [1, 1]], ["tile_h", "sp", [1, 7]], ["tile_w", "sp", [1, 7]], ["tile_ci", "sp", [16, 1]], ["tile_co", "sp", [2, 16]], ["oc_nthread", "ot", 2], ["h_nthread", "ot", 1]], "c": null, "i": 203, "t": "direct"}]}
{"v": 0.1, "r": [[0.0007468395], 0, 0.643439769744873, 1536796748.679697], "i": ["ext_dev -device=vta -keys=cpu -model=ultra96", "topi_nn_conv2d", [["TENSOR", [1, 8, 28, 28, 1, 16], "int8"], ["TENSOR", [16, 8, 1, 1, 16, 16], "int8"], [2, 2], [0, 0], [1, 1], "NCHW1n16c", "int32"], {}, ["conv2d", [1, 8, 28, 28, 1, 16, "int8"], [16, 8, 1, 1, 16, 16, "int8"], [2, 2], [0, 0], [1, 1], "NCHW1n16c", "int32"], {"e": [["tile_b", "sp", [1, 1]], ["tile_h", "sp", [2, 7]], ["tile_w", "sp", [1, 14]], ["tile_ci", "sp", [8, 1]], ["tile_co", "sp", [2, 8]], ["oc_nthread", "ot", 1], ["h_nthread", "ot", 2]], "c": null, "i": 846, "t": "direct"}]}
{"v": 0.1, "r": [[0.00194319875], 0, 3.9710025787353516, 1536796971.2791762], "i": ["ext_dev -device=vta -keys=cpu -model=ultra96", "topi_nn_conv2d", [["TENSOR", [1, 16, 14, 14, 1, 16], "int8"], ["TENSOR", [16, 16, 3, 3, 16, 16], "int8"], [1, 1], [1, 1], [1, 1], "NCHW1n16c", "int32"], {}, ["conv2d", [1, 16, 14, 14, 1, 16, "int8"], [16, 16, 3, 3, 16, 16, "int8"], [1, 1], [1, 1], [1, 1], "NCHW1n16c", "int32"], {"e": [["tile_b", "sp", [1, 1]], ["tile_h", "sp", [1, 14]], ["tile_w", "sp", [2, 7]], ["tile_ci", "sp", [16, 1]], ["tile_co", "sp", [2, 8]], ["oc_nthread", "ot", 2], ["h_nthread", "ot", 1]], "c": null, "i": 651, "t": "direct"}]}
{"v": 0.1, "r": [[0.0012129645], 0, 2.8182592391967773, 1536797151.7134035], "i": ["ext_dev -device=vta -keys=cpu -model=ultra96", "topi_nn_conv2d", [["TENSOR", [1, 8, 28, 28, 1, 16], "int8"], ["TENSOR", [16, 8, 3, 3, 16, 16], "int8"], [2, 2], [1, 1], [1, 1], "NCHW1n16c", "int32"], {}, ["conv2d", [1, 8, 28, 28, 1, 16, "int8"], [16, 8, 3, 3, 16, 16, "int8"], [2, 2], [1, 1], [1, 1], "NCHW1n16c", "int32"], {"e": [["tile_b", "sp", [1, 1]], ["tile_h", "sp", [1, 14]], ["tile_w", "sp", [2, 7]], ["tile_ci", "sp", [8, 1]], ["tile_co", "sp", [2, 8]], ["oc_nthread", "ot", 2], ["h_nthread", "ot", 1]], "c": null, "i": 523, "t": "direct"}]}
{"v": 0.1, "r": [[0.0011736], 0, 2.3224570751190186, 1536797477.2869701], "i": ["ext_dev -device=vta -keys=cpu -model=ultra96", "topi_nn_conv2d", [["TENSOR", [1, 4, 56, 56, 1, 16], "int8"], ["TENSOR", [8, 4, 1, 1, 16, 16], "int8"], [2, 2], [0, 0], [1, 1], "NCHW1n16c", "int32"], {}, ["conv2d", [1, 4, 56, 56, 1, 16, "int8"], [8, 4, 1, 1, 16, 16, "int8"], [2, 2], [0, 0], [1, 1], "NCHW1n16c", "int32"], {"e": [["tile_b", "sp", [1, 1]], ["tile_h", "sp", [4, 7]], ["tile_w", "sp", [1, 28]], ["tile_ci", "sp", [4, 1]], ["tile_co", "sp", [2, 4]], ["oc_nthread", "ot", 2], ["h_nthread", "ot", 1]], "c": null, "i": 681, "t": "direct"}]}
{"v": 0.1, "r": [[0.002396551], 0, 1.7836413383483887, 1536797617.4679008], "i": ["ext_dev -device=vta -keys=cpu -model=ultra96", "topi_nn_conv2d", [["TENSOR", [1, 8, 28, 28, 1, 16], "int8"], ["TENSOR", [8, 8, 3, 3, 16, 16], "int8"], [1, 1], [1, 1], [1, 1], "NCHW1n16c", "int32"], {}, ["conv2d", [1, 8, 28, 28, 1, 16, "int8"], [8, 8, 3, 3, 16, 16, "int8"], [1, 1], [1, 1], [1, 1], "NCHW1n16c", "int32"], {"e": [["tile_b", "sp", [1, 1]], ["tile_h", "sp", [1, 28]], ["tile_w", "sp", [4, 7]], ["tile_ci", "sp", [8, 1]], ["tile_co", "sp", [2, 4]], ["oc_nthread", "ot", 2], ["h_nthread", "ot", 1]], "c": null, "i": 887, "t": "direct"}]}
{"v": 0.1, "r": [[0.00170585525], 0, 4.208229064941406, 1536797797.2484655], "i": ["ext_dev -device=vta -keys=cpu -model=ultra96", "topi_nn_conv2d", [["TENSOR", [1, 4, 56, 56, 1, 16], "int8"], ["TENSOR", [8, 4, 3, 3, 16, 16], "int8"], [2, 2], [1, 1], [1, 1], "NCHW1n16c", "int32"], {}, ["conv2d", [1, 4, 56, 56, 1, 16, "int8"], [8, 4, 3, 3, 16, 16, "int8"], [2, 2], [1, 1], [1, 1], "NCHW1n16c", "int32"], {"e": [["tile_b", "sp", [1, 1]], ["tile_h", "sp", [4, 7]], ["tile_w", "sp", [1, 28]], ["tile_ci", "sp", [4, 1]], ["tile_co", "sp", [2, 4]], ["oc_nthread", "ot", 2], ["h_nthread", "ot", 1]], "c": null, "i": 681, "t": "direct"}]}
{"v": 0.1, "r": [[0.0032872445], 0, 1.0076298713684082, 1536797855.1884694], "i": ["ext_dev -device=vta -keys=cpu -model=ultra96", "topi_nn_conv2d", [["TENSOR", [1, 4, 56, 56, 1, 16], "int8"], ["TENSOR", [4, 4, 3, 3, 16, 16], "int8"], [1, 1], [1, 1], [1, 1], "NCHW1n16c", "int32"], {}, ["conv2d", [1, 4, 56, 56, 1, 16, "int8"], [4, 4, 3, 3, 16, 16, "int8"], [1, 1], [1, 1], [1, 1], "NCHW1n16c", "int32"], {"e": [["tile_b", "sp", [1, 1]], ["tile_h", "sp", [1, 56]], ["tile_w", "sp", [7, 8]], ["tile_ci", "sp", [4, 1]], ["tile_co", "sp", [2, 2]], ["oc_nthread", "ot", 2], ["h_nthread", "ot", 1]], "c": null, "i": 807, "t": "direct"}]}
# my tune optons
{"v": 0.1, "r": [[0.0006344365], 0, 6.047821760177612, 1536796371.6109414], "i": ["ext_dev -device=vta -keys=cpu -model=ultra96", "topi_nn_conv2d", [["TENSOR", [1, 8, 14, 14, 1, 16], "int8"], ["TENSOR", [16, 8, 1, 1, 16, 16], "int8"], [2, 2], [0, 0], [1, 1], "NCHW1n16c", "int32"], {}, ["conv2d", [1, 8, 14, 14, 1, 16, "int8"], [16, 8, 1, 1, 16, 16, "int8"], [2, 2], [0, 0], [1, 1], "NCHW1n16c", "int32"], {"e": [["tile_b", "sp", [1, 1]], ["tile_h", "sp", [1, 7]], ["tile_w", "sp", [1, 7]], ["tile_ci", "sp", [8, 1]], ["tile_co", "sp", [2, 8]], ["oc_nthread", "ot", 2], ["h_nthread", "ot", 1]], "c": null, "i": 203, "t": "direct"}]}
{"v": 0.1, "r": [[0.00172219525], 0, 4.90694785118103, 1536796564.39578], "i": ["ext_dev -device=vta -keys=cpu -model=pynq", "topi_nn_conv2d", [["TENSOR", [1, 16, 7, 7, 1, 16], "int8"], ["TENSOR", [16, 16, 3, 3, 16, 16], "int8"], [1, 1], [1, 1], [1, 1], "NCHW1n16c", "int32"], {}, ["conv2d", [1, 16, 7, 7, 1, 16, "int8"], [16, 16, 3, 3, 16, 16, "int8"], [1, 1], [1, 1], [1, 1], "NCHW1n16c", "int32"], {"e": [["tile_b", "sp", [1, 1]], ["tile_h", "sp", [1, 7]], ["tile_w", "sp", [1, 7]], ["tile_ci", "sp", [16, 1]], ["tile_co", "sp", [2, 8]], ["oc_nthread", "ot", 2], ["h_nthread", "ot", 1]], "c": null, "i": 243, "t": "direct"}]}
{"v": 0.1, "r": [[0.00107295075], 0, 2.922736644744873, 1536796661.6000884], "i": ["ext_dev -device=vta -keys=cpu -model=pynq", "topi_nn_conv2d", [["TENSOR", [1, 8, 14, 14, 1, 16], "int8"], ["TENSOR", [16, 8, 3, 3, 16, 16], "int8"], [2, 2], [1, 1], [1, 1], "NCHW1n16c", "int32"], {}, ["conv2d", [1, 8, 14, 14, 1, 16, "int8"], [16, 8, 3, 3, 16, 16, "int8"], [2, 2], [1, 1], [1, 1], "NCHW1n16c", "int32"], {"e": [["tile_b", "sp", [1, 1]], ["tile_h", "sp", [1, 7]], ["tile_w", "sp", [1, 7]], ["tile_ci", "sp", [8, 1]], ["tile_co", "sp", [2, 8]], ["oc_nthread", "ot", 2], ["h_nthread", "ot", 1]], "c": null, "i": 203, "t": "direct"}]}
{"v": 0.1, "r": [[0.0007468395], 0, 0.643439769744873, 1536796748.679697], "i": ["ext_dev -device=vta -keys=cpu -model=pynq", "topi_nn_conv2d", [["TENSOR", [1, 4, 28, 28, 1, 16], "int8"], ["TENSOR", [8, 4, 1, 1, 16, 16], "int8"], [2, 2], [0, 0], [1, 1], "NCHW1n16c", "int32"], {}, ["conv2d", [1, 4, 28, 28, 1, 16, "int8"], [8, 4, 1, 1, 16, 16, "int8"], [2, 2], [0, 0], [1, 1], "NCHW1n16c", "int32"], {"e": [["tile_b", "sp", [1, 1]], ["tile_h", "sp", [2, 7]], ["tile_w", "sp", [1, 14]], ["tile_ci", "sp", [4, 1]], ["tile_co", "sp", [2, 4]], ["oc_nthread", "ot", 1], ["h_nthread", "ot", 2]], "c": null, "i": 846, "t": "direct"}]}
{"v": 0.1, "r": [[0.00194319875], 0, 3.9710025787353516, 1536796971.2791762], "i": ["ext_dev -device=vta -keys=cpu -model=pynq", "topi_nn_conv2d", [["TENSOR", [1, 8, 14, 14, 1, 16], "int8"], ["TENSOR", [8, 8, 3, 3, 16, 16], "int8"], [1, 1], [1, 1], [1, 1], "NCHW1n16c", "int32"], {}, ["conv2d", [1, 8, 14, 14, 1, 16, "int8"], [8, 8, 3, 3, 16, 16, "int8"], [1, 1], [1, 1], [1, 1], "NCHW1n16c", "int32"], {"e": [["tile_b", "sp", [1, 1]], ["tile_h", "sp", [1, 14]], ["tile_w", "sp", [2, 7]], ["tile_ci", "sp", [8, 1]], ["tile_co", "sp", [2, 4]], ["oc_nthread", "ot", 2], ["h_nthread", "ot", 1]], "c": null, "i": 651, "t": "direct"}]}
{"v": 0.1, "r": [[0.0012129645], 0, 2.8182592391967773, 1536797151.7134035], "i": ["ext_dev -device=vta -keys=cpu -model=pynq", "topi_nn_conv2d", [["TENSOR", [1, 4, 28, 28, 1, 16], "int8"], ["TENSOR", [8, 4, 3, 3, 16, 16], "int8"], [2, 2], [1, 1], [1, 1], "NCHW1n16c", "int32"], {}, ["conv2d", [1, 4, 28, 28, 1, 16, "int8"], [8, 4, 3, 3, 16, 16, "int8"], [2, 2], [1, 1], [1, 1], "NCHW1n16c", "int32"], {"e": [["tile_b", "sp", [1, 1]], ["tile_h", "sp", [1, 14]], ["tile_w", "sp", [2, 7]], ["tile_ci", "sp", [4, 1]], ["tile_co", "sp", [2, 4]], ["oc_nthread", "ot", 2], ["h_nthread", "ot", 1]], "c": null, "i": 523, "t": "direct"}]}
{"v": 0.1, "r": [[0.0011736], 0, 2.3224570751190186, 1536797477.2869701], "i": ["ext_dev -device=vta -keys=cpu -model=pynq", "topi_nn_conv2d", [["TENSOR", [1, 2, 56, 56, 1, 16], "int8"], ["TENSOR", [4, 2, 1, 1, 16, 16], "int8"], [2, 2], [0, 0], [1, 1], "NCHW1n16c", "int32"], {}, ["conv2d", [1, 2, 56, 56, 1, 16, "int8"], [4, 2, 1, 1, 16, 16, "int8"], [2, 2], [0, 0], [1, 1], "NCHW1n16c", "int32"], {"e": [["tile_b", "sp", [1, 1]], ["tile_h", "sp", [4, 7]], ["tile_w", "sp", [1, 28]], ["tile_ci", "sp", [2, 1]], ["tile_co", "sp", [2, 2]], ["oc_nthread", "ot", 2], ["h_nthread", "ot", 1]], "c": null, "i": 681, "t": "direct"}]}
{"v": 0.1, "r": [[0.002396551], 0, 1.7836413383483887, 1536797617.4679008], "i": ["ext_dev -device=vta -keys=cpu -model=pynq", "topi_nn_conv2d", [["TENSOR", [1, 4, 28, 28, 1, 16], "int8"], ["TENSOR", [4, 4, 3, 3, 16, 16], "int8"], [1, 1], [1, 1], [1, 1], "NCHW1n16c", "int32"], {}, ["conv2d", [1, 4, 28, 28, 1, 16, "int8"], [4, 4, 3, 3, 16, 16, "int8"], [1, 1], [1, 1], [1, 1], "NCHW1n16c", "int32"], {"e": [["tile_b", "sp", [1, 1]], ["tile_h", "sp", [1, 28]], ["tile_w", "sp", [4, 7]], ["tile_ci", "sp", [4, 1]], ["tile_co", "sp", [2, 2]], ["oc_nthread", "ot", 2], ["h_nthread", "ot", 1]], "c": null, "i": 887, "t": "direct"}]}
{"v": 0.1, "r": [[0.00170585525], 0, 4.208229064941406, 1536797797.2484655], "i": ["ext_dev -device=vta -keys=cpu -model=pynq", "topi_nn_conv2d", [["TENSOR", [1, 2, 56, 56, 1, 16], "int8"], ["TENSOR", [4, 2, 3, 3, 16, 16], "int8"], [2, 2], [1, 1], [1, 1], "NCHW1n16c", "int32"], {}, ["conv2d", [1, 2, 56, 56, 1, 16, "int8"], [4, 2, 3, 3, 16, 16, "int8"], [2, 2], [1, 1], [1, 1], "NCHW1n16c", "int32"], {"e": [["tile_b", "sp", [1, 1]], ["tile_h", "sp", [4, 7]], ["tile_w", "sp", [1, 28]], ["tile_ci", "sp", [2, 1]], ["tile_co", "sp", [2, 2]], ["oc_nthread", "ot", 2], ["h_nthread", "ot", 1]], "c": null, "i": 681, "t": "direct"}]}
{"v": 0.1, "r": [[0.0032872445], 0, 1.0076298713684082, 1536797855.1884694], "i": ["ext_dev -device=vta -keys=cpu -model=pynq", "topi_nn_conv2d", [["TENSOR", [1, 2, 56, 56, 1, 16], "int8"], ["TENSOR", [2, 2, 3, 3, 16, 16], "int8"], [1, 1], [1, 1], [1, 1], "NCHW1n16c", "int32"], {}, ["conv2d", [1, 2, 56, 56, 1, 16, "int8"], [2, 2, 3, 3, 16, 16, "int8"], [1, 1], [1, 1], [1, 1], "NCHW1n16c", "int32"], {"e": [["tile_b", "sp", [1, 1]], ["tile_h", "sp", [1, 56]], ["tile_w", "sp", [7, 8]], ["tile_ci", "sp", [2, 1]], ["tile_co", "sp", [2, 1]], ["oc_nthread", "ot", 2], ["h_nthread", "ot", 1]], "c": null, "i": 807, "t": "direct"}]}
# sim
{"v": 0.1, "r": [[0.0006344365], 0, 6.047821760177612, 1536796371.6109414], "i": ["ext_dev -device=vta -keys=cpu -model=sim", "topi_nn_conv2d", [["TENSOR", [1, 16, 14, 14, 1, 16], "int8"], ["TENSOR", [32, 16, 1, 1, 16, 16], "int8"], [2, 2], [0, 0], [1, 1], "NCHW1n16c", "int32"], {}, ["conv2d", [1, 16, 14, 14, 1, 16, "int8"], [32, 16, 1, 1, 16, 16, "int8"], [2, 2], [0, 0], [1, 1], "NCHW1n16c", "int32"], {"e": [["tile_b", "sp", [1, 1]], ["tile_h", "sp", [1, 7]], ["tile_w", "sp", [1, 7]], ["tile_ci", "sp", [16, 1]], ["tile_co", "sp", [2, 16]], ["oc_nthread", "ot", 2], ["h_nthread", "ot", 1]], "c": null, "i": 203, "t": "direct"}]}
{"v": 0.1, "r": [[0.00172219525], 0, 4.90694785118103, 1536796564.39578], "i": ["ext_dev -device=vta -keys=cpu -model=sim", "topi_nn_conv2d", [["TENSOR", [1, 32, 7, 7, 1, 16], "int8"], ["TENSOR", [32, 32, 3, 3, 16, 16], "int8"], [1, 1], [1, 1], [1, 1], "NCHW1n16c", "int32"], {}, ["conv2d", [1, 32, 7, 7, 1, 16, "int8"], [32, 32, 3, 3, 16, 16, "int8"], [1, 1], [1, 1], [1, 1], "NCHW1n16c", "int32"], {"e": [["tile_b", "sp", [1, 1]], ["tile_h", "sp", [1, 7]], ["tile_w", "sp", [1, 7]], ["tile_ci", "sp", [32, 1]], ["tile_co", "sp", [2, 16]], ["oc_nthread", "ot", 2], ["h_nthread", "ot", 1]], "c": null, "i": 243, "t": "direct"}]}
{"v": 0.1, "r": [[0.00107295075], 0, 2.922736644744873, 1536796661.6000884], "i": ["ext_dev -device=vta -keys=cpu -model=sim", "topi_nn_conv2d", [["TENSOR", [1, 16, 14, 14, 1, 16], "int8"], ["TENSOR", [32, 16, 3, 3, 16, 16], "int8"], [2, 2], [1, 1], [1, 1], "NCHW1n16c", "int32"], {}, ["conv2d", [1, 16, 14, 14, 1, 16, "int8"], [32, 16, 3, 3, 16, 16, "int8"], [2, 2], [1, 1], [1, 1], "NCHW1n16c", "int32"], {"e": [["tile_b", "sp", [1, 1]], ["tile_h", "sp", [1, 7]], ["tile_w", "sp", [1, 7]], ["tile_ci", "sp", [16, 1]], ["tile_co", "sp", [2, 16]], ["oc_nthread", "ot", 2], ["h_nthread", "ot", 1]], "c": null, "i": 203, "t": "direct"}]}
{"v": 0.1, "r": [[0.0007468395], 0, 0.643439769744873, 1536796748.679697], "i": ["ext_dev -device=vta -keys=cpu -model=sim", "topi_nn_conv2d", [["TENSOR", [1, 8, 28, 28, 1, 16], "int8"], ["TENSOR", [16, 8, 1, 1, 16, 16], "int8"], [2, 2], [0, 0], [1, 1], "NCHW1n16c", "int32"], {}, ["conv2d", [1, 8, 28, 28, 1, 16, "int8"], [16, 8, 1, 1, 16, 16, "int8"], [2, 2], [0, 0], [1, 1], "NCHW1n16c", "int32"], {"e": [["tile_b", "sp", [1, 1]], ["tile_h", "sp", [2, 7]], ["tile_w", "sp", [1, 14]], ["tile_ci", "sp", [8, 1]], ["tile_co", "sp", [2, 8]], ["oc_nthread", "ot", 1], ["h_nthread", "ot", 2]], "c": null, "i": 846, "t": "direct"}]}
{"v": 0.1, "r": [[0.00194319875], 0, 3.9710025787353516, 1536796971.2791762], "i": ["ext_dev -device=vta -keys=cpu -model=sim", "topi_nn_conv2d", [["TENSOR", [1, 16, 14, 14, 1, 16], "int8"], ["TENSOR", [16, 16, 3, 3, 16, 16], "int8"], [1, 1], [1, 1], [1, 1], "NCHW1n16c", "int32"], {}, ["conv2d", [1, 16, 14, 14, 1, 16, "int8"], [16, 16, 3, 3, 16, 16, "int8"], [1, 1], [1, 1], [1, 1], "NCHW1n16c", "int32"], {"e": [["tile_b", "sp", [1, 1]], ["tile_h", "sp", [1, 14]], ["tile_w", "sp", [2, 7]], ["tile_ci", "sp", [16, 1]], ["tile_co", "sp", [2, 8]], ["oc_nthread", "ot", 2], ["h_nthread", "ot", 1]], "c": null, "i": 651, "t": "direct"}]}
{"v": 0.1, "r": [[0.0012129645], 0, 2.8182592391967773, 1536797151.7134035], "i": ["ext_dev -device=vta -keys=cpu -model=sim", "topi_nn_conv2d", [["TENSOR", [1, 8, 28, 28, 1, 16], "int8"], ["TENSOR", [16, 8, 3, 3, 16, 16], "int8"], [2, 2], [1, 1], [1, 1], "NCHW1n16c", "int32"], {}, ["conv2d", [1, 8, 28, 28, 1, 16, "int8"], [16, 8, 3, 3, 16, 16, "int8"], [2, 2], [1, 1], [1, 1], "NCHW1n16c", "int32"], {"e": [["tile_b", "sp", [1, 1]], ["tile_h", "sp", [1, 14]], ["tile_w", "sp", [2, 7]], ["tile_ci", "sp", [8, 1]], ["tile_co", "sp", [2, 8]], ["oc_nthread", "ot", 2], ["h_nthread", "ot", 1]], "c": null, "i": 523, "t": "direct"}]}
{"v": 0.1, "r": [[0.0011736], 0, 2.3224570751190186, 1536797477.2869701], "i": ["ext_dev -device=vta -keys=cpu -model=sim", "topi_nn_conv2d", [["TENSOR", [1, 4, 56, 56, 1, 16], "int8"], ["TENSOR", [8, 4, 1, 1, 16, 16], "int8"], [2, 2], [0, 0], [1, 1], "NCHW1n16c", "int32"], {}, ["conv2d", [1, 4, 56, 56, 1, 16, "int8"], [8, 4, 1, 1, 16, 16, "int8"], [2, 2], [0, 0], [1, 1], "NCHW1n16c", "int32"], {"e": [["tile_b", "sp", [1, 1]], ["tile_h", "sp", [4, 7]], ["tile_w", "sp", [1, 28]], ["tile_ci", "sp", [4, 1]], ["tile_co", "sp", [2, 4]], ["oc_nthread", "ot", 2], ["h_nthread", "ot", 1]], "c": null, "i": 681, "t": "direct"}]}
{"v": 0.1, "r": [[0.002396551], 0, 1.7836413383483887, 1536797617.4679008], "i": ["ext_dev -device=vta -keys=cpu -model=sim", "topi_nn_conv2d", [["TENSOR", [1, 8, 28, 28, 1, 16], "int8"], ["TENSOR", [8, 8, 3, 3, 16, 16], "int8"], [1, 1], [1, 1], [1, 1], "NCHW1n16c", "int32"], {}, ["conv2d", [1, 8, 28, 28, 1, 16, "int8"], [8, 8, 3, 3, 16, 16, "int8"], [1, 1], [1, 1], [1, 1], "NCHW1n16c", "int32"], {"e": [["tile_b", "sp", [1, 1]], ["tile_h", "sp", [1, 28]], ["tile_w", "sp", [4, 7]], ["tile_ci", "sp", [8, 1]], ["tile_co", "sp", [2, 4]], ["oc_nthread", "ot", 2], ["h_nthread", "ot", 1]], "c": null, "i": 887, "t": "direct"}]}
{"v": 0.1, "r": [[0.00170585525], 0, 4.208229064941406, 1536797797.2484655], "i": ["ext_dev -device=vta -keys=cpu -model=sim", "topi_nn_conv2d", [["TENSOR", [1, 4, 56, 56, 1, 16], "int8"], ["TENSOR", [8, 4, 3, 3, 16, 16], "int8"], [2, 2], [1, 1], [1, 1], "NCHW1n16c", "int32"], {}, ["conv2d", [1, 4, 56, 56, 1, 16, "int8"], [8, 4, 3, 3, 16, 16, "int8"], [2, 2], [1, 1], [1, 1], "NCHW1n16c", "int32"], {"e": [["tile_b", "sp", [1, 1]], ["tile_h", "sp", [4, 7]], ["tile_w", "sp", [1, 28]], ["tile_ci", "sp", [4, 1]], ["tile_co", "sp", [2, 4]], ["oc_nthread", "ot", 2], ["h_nthread", "ot", 1]], "c": null, "i": 681, "t": "direct"}]}
{"v": 0.1, "r": [[0.0032872445], 0, 1.0076298713684082, 1536797855.1884694], "i": ["ext_dev -device=vta -keys=cpu -model=sim", "topi_nn_conv2d", [["TENSOR", [1, 4, 56, 56, 1, 16], "int8"], ["TENSOR", [4, 4, 3, 3, 16, 16], "int8"], [1, 1], [1, 1], [1, 1], "NCHW1n16c", "int32"], {}, ["conv2d", [1, 4, 56, 56, 1, 16, "int8"], [4, 4, 3, 3, 16, 16, "int8"], [1, 1], [1, 1], [1, 1], "NCHW1n16c", "int32"], {"e": [["tile_b", "sp", [1, 1]], ["tile_h", "sp", [1, 56]], ["tile_w", "sp", [7, 8]], ["tile_ci", "sp", [4, 1]], ["tile_co", "sp", [2, 2]], ["oc_nthread", "ot", 2], ["h_nthread", "ot", 1]], "c": null, "i": 807, "t": "direct"}]}
# dcgan
{"v": 0.1, "i": ["llvm -device=arm_cpu -model=ultra96 -target=aarch64-linux-gnu -mattr=+neon", "topi_nn_conv2d_transpose_nchw", [["TENSOR", [1, 128, 32, 32], "int8"], ["TENSOR", [128, 3, 4, 4], "int8"], [2, 2], [1, 1], "int32"], {}, ["conv2d_transpose_nchw", [1, 128, 32, 32, "int8"], [128, 3, 4, 4, "int8"], [2, 2], [1, 1], "int32"], {"c": null, "e": [["tile_co", "sp", [3, 1]], ["tile_oh", "sp", [16, 4]], ["tile_ow", "sp", [16, 4]], ["reorder_0", "re", [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]], ["ann_reduce", "an", ["unroll", "unroll"]], ["ann_spatial", "an", ["unroll", "vec", "none"]]], "i": 11596, "t": "direct"}], "r": [[0.007714500923076923], 0, 6.476067066192627, 1542336257.7748442]}