even faster on pimcomp models
Validate Operations / validate-operations (push) Has been cancelled

This commit is contained in:
NiccoloN
2026-07-31 21:15:28 +02:00
parent 9ca1a0ed9f
commit f4a3b012cc
49 changed files with 1923 additions and 583 deletions
+5 -3
View File
@@ -38,11 +38,12 @@ Run the complete suite with deadlock detection:
Use `--compile-only` for compiler and deadlock checks, then `--run-only` to
reuse those artifacts for reference execution, simulation, and comparison.
The validator prints the complete operation results table before its summary.
The validator prints the complete operation results table before its summary
and writes the same rows to `validation_results.csv`.
## Complete inventory
The suite contains 164 models. Tensor shapes, attributes, and constants are
The suite contains 165 models. Tensor shapes, attributes, and constants are
defined in `gen_tests.py` and in the checked-in ONNX models.
### Add (5)
@@ -63,7 +64,7 @@ defined in `gen_tests.py` and in the checked-in ONNX models.
| `negative_axis` | Concatenates tensors using a negative axis. |
| `three_inputs_channel_axis` | Concatenates three runtime NCHW tensors along the channel axis. |
### Conv (31)
### Conv (32)
| Case | Description |
|---|---|
@@ -98,6 +99,7 @@ defined in `gen_tests.py` and in the checked-in ONNX models.
| `with_bias_3x3` | Multi-channel 3x3 Conv with bias. |
| `with_constant` | Hand-authored SAME_UPPER Conv with constant weight and bias. |
| `without_kernel_shape_attr` | Conv whose kernel shape is inferred from its weight tensor. |
| `yolo11n_stem` | First two YOLO11n `Conv-SiLU` blocks at `640x640`, including the distributed activation boundary. |
### Div (6)
+25
View File
@@ -218,6 +218,30 @@ def conv_huge_pointwise_1024_dynamic():
save_model(model, "conv/huge_pointwise_1024_dynamic", "conv_huge_pointwise_1024_dynamic.onnx")
def conv_yolo11n_stem():
"""First two YOLO11n Conv-SiLU blocks, preserving the distributed intermediate."""
X = helper.make_tensor_value_info("X", TensorProto.FLOAT, [1, 3, 640, 640])
Y = helper.make_tensor_value_info("Y", TensorProto.FLOAT, [1, 32, 160, 160])
rng = np.random.default_rng(109)
W0 = numpy_helper.from_array(rng.uniform(-1, 1, (16, 3, 3, 3)).astype(np.float32), name="W0")
B0 = numpy_helper.from_array(rng.uniform(-1, 1, (16,)).astype(np.float32), name="B0")
W1 = numpy_helper.from_array(rng.uniform(-1, 1, (32, 16, 3, 3)).astype(np.float32), name="W1")
B1 = numpy_helper.from_array(rng.uniform(-1, 1, (32,)).astype(np.float32), name="B1")
nodes = [
helper.make_node("Conv", ["X", "W0", "B0"], ["C0"],
kernel_shape=[3, 3], strides=[2, 2], pads=[1, 1, 1, 1]),
helper.make_node("Sigmoid", ["C0"], ["S0"]),
helper.make_node("Mul", ["C0", "S0"], ["A0"]),
helper.make_node("Conv", ["A0", "W1", "B1"], ["C1"],
kernel_shape=[3, 3], strides=[2, 2], pads=[1, 1, 1, 1]),
helper.make_node("Sigmoid", ["C1"], ["S1"]),
helper.make_node("Mul", ["C1", "S1"], ["Y"]),
]
graph = helper.make_graph(nodes, "conv_yolo11n_stem", [X], [Y], initializer=[W0, B0, W1, B1])
model = helper.make_model(graph, opset_imports=[helper.make_opsetid("", 13)])
save_model(model, "conv/yolo11n_stem", "conv_yolo11n_stem.onnx")
def conv_pointwise_tiled_chain():
"""Chained pointwise Convs with a tiled intermediate."""
X = helper.make_tensor_value_info("X", TensorProto.FLOAT, [1, 1024, 1, 1])
@@ -2032,6 +2056,7 @@ if __name__ == "__main__":
conv_dynamic()
conv_huge_pointwise_1024()
conv_huge_pointwise_1024_dynamic()
conv_yolo11n_stem()
conv_pointwise_tiled_chain()
conv_large_output_channels_1x1()
conv_large_input_channels_1x1()
@@ -0,0 +1,166 @@
Operation,Result,Compile,Host mem,Cores mem,Cores,Xbars,Latency,Power,Energy
add/after_gemm,PASS,0.141 s,0.01 MiB,0.01 MiB,5,4,0.007784 ms,104.703618 mW,815012.960000 pJ
add/basic,PASS,0.114 s,0.00 MiB,0.00 MiB,1,0,0.000323 ms,78.222910 mW,25266.000000 pJ
add/broadcast_row,PASS,0.110 s,0.00 MiB,0.00 MiB,1,0,0.000323 ms,78.222910 mW,25266.000000 pJ
add/channel_broadcast_1024,PASS,0.105 s,0.02 MiB,0.01 MiB,1,0,0.006913 ms,78.118038 mW,540030.000000 pJ
add/leading_dimension_broadcast,PASS,0.137 s,0.00 MiB,0.00 MiB,1,0,0.000323 ms,78.222910 mW,25266.000000 pJ
concat/channel_axis,PASS,0.127 s,0.00 MiB,0.00 MiB,1,0,0.000457 ms,78.157549 mW,35718.000000 pJ
concat/negative_axis,PASS,0.102 s,0.00 MiB,0.00 MiB,1,0,0.001043 ms,78.092042 mW,81450.000000 pJ
concat/three_inputs_channel_axis,PASS,0.127 s,0.00 MiB,0.00 MiB,1,0,0.000644 ms,78.149068 mW,50328.000000 pJ
conv/batch_2,PASS,0.102 s,0.00 MiB,0.00 MiB,2,2,0.013694 ms,82.623885 mW,1131451.480000 pJ
conv/batch_4_pointwise,PASS,0.110 s,0.00 MiB,0.01 MiB,5,4,0.003932 ms,116.078576 mW,456420.960000 pJ
conv/depthwise_1024_channels,PASS,0.167 s,0.19 MiB,0.38 MiB,129,128,0.220751 ms,178.454307 mW,39393966.720000 pJ
conv/depthwise_grouped,PASS,0.109 s,0.01 MiB,0.00 MiB,5,4,0.006024 ms,108.326521 mW,652558.960000 pJ
conv/dilated_3x3,PASS,0.143 s,0.00 MiB,0.00 MiB,3,3,0.004045 ms,110.234541 mW,445898.720000 pJ
conv/dynamic,PASS,0.107 s,0.00 MiB,0.00 MiB,5,0,0.001835 ms,92.281199 mW,169336.000000 pJ
conv/explicit_padding,PASS,0.139 s,0.00 MiB,0.00 MiB,4,4,0.004327 ms,115.794768 mW,501043.960000 pJ
conv/grouped_many_groups,PASS,0.616 s,0.05 MiB,0.09 MiB,65,64,0.181845 ms,142.210104 mW,25860196.360000 pJ
conv/grouped_two_groups,PASS,0.145 s,0.00 MiB,0.00 MiB,3,2,0.005360 ms,101.459418 mW,543822.480000 pJ
conv/huge_pointwise_1024,PASS,0.749 s,0.01 MiB,0.01 MiB,1,64,0.028261 ms,133.488743 mW,3772525.360000 pJ
conv/huge_pointwise_1024_dynamic,PASS,0.097 s,8.04 MiB,12.61 MiB,168,0,2.627964 ms,169.518697 mW,445489032.000000 pJ
conv/kernel_3x3,PASS,0.155 s,0.00 MiB,0.00 MiB,3,3,0.003091 ms,115.862414 mW,358130.720000 pJ
conv/kernel_equals_input_spatial,PASS,0.156 s,0.00 MiB,0.00 MiB,1,2,0.008443 ms,83.863849 mW,708062.480000 pJ
conv/large_input_channels_1x1,PASS,0.160 s,0.01 MiB,0.01 MiB,1,8,0.017167 ms,89.416900 mW,1535019.920000 pJ
conv/large_output_channels_1x1,PASS,0.141 s,0.00 MiB,0.01 MiB,1,8,0.004964 ms,117.628106 mW,583905.920000 pJ
conv/large_spatial,PASS,0.141 s,0.00 MiB,0.01 MiB,6,6,0.004096 ms,129.015000 mW,528445.440000 pJ
conv/multi_channel,PASS,0.143 s,0.00 MiB,0.00 MiB,3,3,0.005148 ms,106.453520 mW,548022.720000 pJ
conv/non_square_kernel_1x3,PASS,0.127 s,0.00 MiB,0.00 MiB,5,5,0.004029 ms,123.600943 mW,497988.200000 pJ
conv/non_square_kernel_3x1,PASS,0.085 s,0.00 MiB,0.00 MiB,3,3,0.005526 ms,105.464843 mW,582798.720000 pJ
conv/non_uniform_stride,PASS,0.120 s,0.00 MiB,0.00 MiB,4,4,0.005808 ms,110.081433 mW,639352.960000 pJ
conv/pointwise_1x1,PASS,0.139 s,0.00 MiB,0.00 MiB,4,4,0.004539 ms,114.835858 mW,521239.960000 pJ
conv/pointwise_tiled_chain,PASS,0.943 s,0.01 MiB,0.02 MiB,2,80,0.084437 ms,102.289307 mW,8637002.200000 pJ
conv/real_asymmetric_padding,PASS,0.115 s,0.00 MiB,0.00 MiB,4,4,0.005232 ms,111.870214 mW,585304.960000 pJ
conv/relu_conv_store,PASS,0.107 s,0.05 MiB,0.08 MiB,32,32,0.062978 ms,246.649827 mW,15533512.800000 pJ
conv/same_lower_3x3,PASS,0.094 s,0.00 MiB,0.00 MiB,5,5,0.004700 ms,119.232170 mW,560391.200000 pJ
conv/same_padding_3x3,PASS,0.126 s,0.00 MiB,0.00 MiB,5,5,0.004700 ms,119.232170 mW,560391.200000 pJ
conv/simple,PASS,0.125 s,0.00 MiB,0.00 MiB,2,2,0.003148 ms,94.665972 mW,298008.480000 pJ
conv/stride_2,PASS,0.146 s,0.00 MiB,0.00 MiB,2,2,0.002827 ms,96.393873 mW,272505.480000 pJ
conv/with_bias_3x3,PASS,0.121 s,0.00 MiB,0.00 MiB,3,3,0.004898 ms,107.176546 mW,524950.720000 pJ
conv/with_constant,PASS,0.106 s,0.00 MiB,0.00 MiB,3,3,0.004273 ms,109.362677 mW,467306.720000 pJ
conv/without_kernel_shape_attr,PASS,0.105 s,0.00 MiB,0.00 MiB,3,3,0.003091 ms,115.862414 mW,358130.720000 pJ
conv/yolo11n_stem,PASS,3.091 s,29.20 MiB,31.38 MiB,168,488,9.799213 ms,361.075203 mW,3538252825.000010 pJ
div/after_gemm,PASS,0.130 s,0.01 MiB,0.01 MiB,5,4,0.007784 ms,104.703618 mW,815012.960000 pJ
div/basic,PASS,0.116 s,0.00 MiB,0.00 MiB,1,0,0.000323 ms,78.222910 mW,25266.000000 pJ
div/channel_broadcast_1024,PASS,0.121 s,0.02 MiB,0.01 MiB,1,0,0.006913 ms,78.118038 mW,540030.000000 pJ
div/leading_dimension_broadcast,PASS,0.095 s,0.00 MiB,0.00 MiB,1,0,0.000323 ms,78.222910 mW,25266.000000 pJ
div/runtime_scalar_rhs,PASS,0.126 s,0.02 MiB,0.01 MiB,1,0,0.006913 ms,78.118038 mW,540030.000000 pJ
div/scalar_constant,PASS,0.069 s,0.00 MiB,0.00 MiB,1,0,0.000323 ms,78.222910 mW,25266.000000 pJ
gather/3d_input_axis1,PASS,0.121 s,0.00 MiB,0.00 MiB,1,0,0.000589 ms,78.081494 mW,45990.000000 pJ
gather/axis0_matrix_indices,PASS,0.088 s,0.00 MiB,0.00 MiB,1,0,0.000697 ms,78.068867 mW,54414.000000 pJ
gather/axis1,PASS,0.123 s,0.00 MiB,0.00 MiB,1,0,0.000801 ms,78.059925 mW,62526.000000 pJ
gather/negative_axis,PASS,0.087 s,0.00 MiB,0.00 MiB,1,0,0.001437 ms,78.033403 mW,112134.000000 pJ
gather/negative_indices,PASS,0.115 s,0.00 MiB,0.00 MiB,1,0,0.000376 ms,78.127660 mW,29376.000000 pJ
gemm/alpha_beta,PASS,0.121 s,0.01 MiB,0.01 MiB,5,4,0.007456 ms,105.272125 mW,784908.960000 pJ
gemm/bias_rank2_broadcast,PASS,0.127 s,0.00 MiB,0.01 MiB,5,4,0.007072 ms,105.979208 mW,749484.960000 pJ
gemm/dynamic,PASS,0.084 s,0.00 MiB,0.00 MiB,5,0,0.002421 ms,91.480793 mW,221475.000000 pJ
gemm/dynamic_alpha,PASS,0.104 s,0.00 MiB,0.00 MiB,5,0,0.003262 ms,91.415696 mW,298198.000000 pJ
gemm/dynamic_beta,PASS,0.110 s,0.00 MiB,0.00 MiB,5,0,0.004365 ms,91.316151 mW,398595.000000 pJ
gemm/dynamic_bias,PASS,0.092 s,0.00 MiB,0.00 MiB,5,0,0.002665 ms,91.445779 mW,243703.000000 pJ
gemm/dynamic_bias_alpha_beta,PASS,0.089 s,0.00 MiB,0.00 MiB,5,0,0.005629 ms,91.279268 mW,513811.000000 pJ
gemm/dynamic_transB,PASS,0.077 s,0.00 MiB,0.00 MiB,5,0,0.001301 ms,91.378171 mW,118883.000000 pJ
gemm/huge_1024,PASS,0.219 s,0.01 MiB,0.10 MiB,73,64,0.017522 ms,215.037402 mW,3767885.360000 pJ
gemm/large,PASS,0.097 s,0.02 MiB,0.03 MiB,17,16,0.011229 ms,140.152181 mW,1573768.840000 pJ
gemm/large_k_small_n,PASS,0.106 s,0.01 MiB,0.01 MiB,9,8,0.004748 ms,133.481449 mW,633769.920000 pJ
gemm/non_square,PASS,0.102 s,0.00 MiB,0.01 MiB,5,4,0.003527 ms,118.958310 mW,419565.960000 pJ
gemm/scalar_bias,PASS,0.111 s,0.00 MiB,0.01 MiB,5,4,0.007072 ms,105.979208 mW,749484.960000 pJ
gemm/simple,PASS,0.135 s,0.03 MiB,0.08 MiB,42,40,0.021640 ms,151.774196 mW,3284393.600000 pJ
gemm/small,PASS,0.074 s,0.00 MiB,0.00 MiB,2,2,0.004420 ms,90.144000 mW,398436.480000 pJ
gemm/small_k_large_n,PASS,0.129 s,0.01 MiB,0.02 MiB,17,8,0.007962 ms,131.005014 mW,1043061.920000 pJ
gemm/transA,PASS,0.089 s,0.00 MiB,0.01 MiB,5,4,0.005762 ms,109.140743 mW,628868.960000 pJ
gemm/transA_transB,PASS,0.115 s,0.00 MiB,0.01 MiB,5,4,0.005762 ms,109.140743 mW,628868.960000 pJ
gemm/transB,PASS,0.068 s,0.00 MiB,0.01 MiB,5,4,0.003527 ms,118.958310 mW,419565.960000 pJ
gemm/transB_with_bias,PASS,0.069 s,0.01 MiB,0.01 MiB,5,4,0.005046 ms,110.546762 mW,557818.960000 pJ
gemm/with_bias,PASS,0.113 s,0.01 MiB,0.01 MiB,5,4,0.005562 ms,108.767882 mW,604966.960000 pJ
gemv/constant,PASS,0.112 s,0.00 MiB,0.00 MiB,0,0,0.000000 ms,2.000000 mW,0.000000 pJ
gemv/simple,PASS,0.136 s,0.00 MiB,0.01 MiB,6,4,0.005160 ms,111.150380 mW,573535.960000 pJ
gemv/with_heterogeneous_constant,PASS,0.138 s,0.00 MiB,0.01 MiB,6,4,0.005549 ms,109.816536 mW,609371.960000 pJ
gemv/with_homogeneous_constant,PASS,0.140 s,0.00 MiB,0.01 MiB,6,4,0.005549 ms,109.816536 mW,609371.960000 pJ
gemv/with_scalar_constant,PASS,0.124 s,0.00 MiB,0.01 MiB,6,4,0.005549 ms,109.816536 mW,609371.960000 pJ
matmul/basic,PASS,0.081 s,0.00 MiB,0.00 MiB,2,2,0.004420 ms,90.144000 mW,398436.480000 pJ
matmul/batched_3d,PASS,0.133 s,0.00 MiB,0.01 MiB,5,4,0.005958 ms,108.588949 mW,646972.960000 pJ
matmul/batched_3d_dynamic,PASS,0.105 s,0.00 MiB,0.00 MiB,9,0,0.003525 ms,92.330213 mW,325464.000000 pJ
matmul/batched_left_constant,PASS,0.136 s,0.00 MiB,0.02 MiB,9,8,0.008822 ms,114.385164 mW,1009105.920000 pJ
matmul/batched_lhs_broadcast,PASS,0.133 s,0.00 MiB,0.01 MiB,5,4,0.005681 ms,109.389361 mW,621440.960000 pJ
matmul/batched_rhs_broadcast,PASS,0.134 s,0.00 MiB,0.01 MiB,5,4,0.005958 ms,108.588949 mW,646972.960000 pJ
matmul/dynamic,PASS,0.093 s,0.00 MiB,0.00 MiB,5,0,0.001621 ms,91.421962 mW,148195.000000 pJ
matmul/huge_1024,PASS,0.277 s,0.01 MiB,0.10 MiB,73,64,0.017522 ms,215.037402 mW,3767885.360000 pJ
matmul/left_constant,PASS,0.123 s,0.00 MiB,0.01 MiB,5,4,0.005853 ms,108.861944 mW,637168.960000 pJ
matmul/matrix_vector,PASS,0.150 s,0.52 MiB,0.78 MiB,168,173,0.384660 ms,202.131271 mW,77751814.880000 pJ
matmul/vector_matrix,PASS,0.186 s,0.01 MiB,0.01 MiB,9,8,0.007409 ms,118.680243 mW,879301.920000 pJ
mul/after_conv,PASS,0.127 s,0.00 MiB,0.00 MiB,4,3,0.005453 ms,107.639046 mW,586955.720000 pJ
mul/basic,PASS,0.070 s,0.00 MiB,0.00 MiB,1,0,0.000323 ms,78.222910 mW,25266.000000 pJ
mul/channel_broadcast_1024,PASS,0.065 s,0.02 MiB,0.01 MiB,1,0,0.006913 ms,78.118038 mW,540030.000000 pJ
mul/leading_dimension_broadcast,PASS,0.108 s,0.00 MiB,0.00 MiB,1,0,0.000323 ms,78.222910 mW,25266.000000 pJ
mul/scalar_constant,PASS,0.082 s,0.00 MiB,0.00 MiB,1,0,0.000323 ms,78.222910 mW,25266.000000 pJ
pool/avg_basic,PASS,0.070 s,0.00 MiB,0.00 MiB,1,0,0.011939 ms,78.022112 mW,931506.000000 pJ
pool/avg_ceil_mode,PASS,0.107 s,0.00 MiB,0.00 MiB,1,0,0.004359 ms,78.033035 mW,340146.000000 pJ
pool/avg_explicit_padding,PASS,0.111 s,0.00 MiB,0.00 MiB,1,0,0.008822 ms,78.027205 mW,688356.000000 pJ
pool/avg_include_pad,PASS,0.075 s,0.00 MiB,0.00 MiB,1,0,0.008506 ms,78.016929 mW,663612.000000 pJ
pool/avg_large_channels,PASS,0.064 s,0.04 MiB,0.02 MiB,1,0,0.178249 ms,78.280327 mW,13953390.000000 pJ
pool/avg_non_uniform_stride,PASS,0.068 s,0.00 MiB,0.00 MiB,1,0,0.014513 ms,78.016537 mW,1132254.000000 pJ
pool/avg_real_asymmetric_padding,PASS,0.064 s,0.00 MiB,0.00 MiB,1,0,0.025206 ms,78.024756 mW,1966692.000000 pJ
pool/max_after_conv,PASS,0.070 s,0.00 MiB,0.00 MiB,6,4,0.006452 ms,96.374606 mW,621808.960000 pJ
pool/max_basic,PASS,0.063 s,0.00 MiB,0.00 MiB,3,0,0.001634 ms,92.132191 mW,150544.000000 pJ
pool/max_ceil_mode,PASS,0.065 s,0.00 MiB,0.00 MiB,2,0,0.001297 ms,79.111025 mW,102607.000000 pJ
pool/max_global_style_kernel_equals_input,PASS,0.089 s,0.00 MiB,0.00 MiB,1,0,0.004366 ms,78.010994 mW,340596.000000 pJ
pool/max_non_square_kernel,PASS,0.103 s,0.00 MiB,0.00 MiB,4,0,0.003409 ms,93.253447 mW,317901.000000 pJ
pool/max_real_asymmetric_padding,PASS,0.088 s,0.00 MiB,0.00 MiB,4,0,0.003078 ms,93.124756 mW,286638.000000 pJ
pool/max_same_upper,PASS,0.065 s,0.00 MiB,0.00 MiB,3,0,0.003024 ms,92.095238 mW,278496.000000 pJ
pool/max_stride2_multichannel,PASS,0.086 s,0.00 MiB,0.00 MiB,3,0,0.004012 ms,92.269192 mW,370184.000000 pJ
reduce_mean/4d_spatial,PASS,0.061 s,0.00 MiB,0.00 MiB,3,0,0.000321 ms,92.448598 mW,29676.000000 pJ
reduce_mean/4d_spatial_keepdims_0,PASS,0.067 s,0.00 MiB,0.00 MiB,4,0,0.000655 ms,94.352672 mW,61801.000000 pJ
reduce_mean/after_conv,PASS,0.115 s,0.00 MiB,0.00 MiB,5,3,0.005342 ms,106.951089 mW,571332.720000 pJ
reduce_mean/all_axes_keepdims_0,PASS,0.103 s,0.00 MiB,0.00 MiB,2,0,0.000391 ms,79.237852 mW,30982.000000 pJ
reduce_mean/all_axes_keepdims_1,PASS,0.086 s,0.00 MiB,0.00 MiB,1,0,0.000221 ms,78.217195 mW,17286.000000 pJ
reduce_mean/basic,PASS,0.099 s,0.00 MiB,0.00 MiB,4,0,0.000373 ms,93.514745 mW,34881.000000 pJ
reduce_mean/channel_axis_nchw,PASS,0.078 s,0.03 MiB,0.02 MiB,4,0,0.164926 ms,93.596631 mW,15436518.000000 pJ
reduce_mean/keepdims_0,PASS,0.073 s,0.00 MiB,0.00 MiB,5,0,0.000748 ms,91.401070 mW,68368.000000 pJ
reduce_mean/large_dimension_1024,PASS,0.115 s,0.01 MiB,0.00 MiB,1,0,0.002785 ms,78.017235 mW,217278.000000 pJ
reduce_mean/legacy_axes_1_2_keepdims_1,PASS,0.074 s,0.00 MiB,0.00 MiB,2,0,0.000271 ms,79.354244 mW,21505.000000 pJ
reduce_mean/legacy_axis1_keepdims_0,PASS,0.111 s,0.00 MiB,0.00 MiB,9,0,0.001986 ms,92.501511 mW,183708.000000 pJ
reduce_mean/legacy_axis1_keepdims_1,PASS,0.086 s,0.00 MiB,0.00 MiB,8,0,0.001373 ms,94.559359 mW,129830.000000 pJ
reduce_mean/legacy_empty_axes_noop,PASS,0.115 s,0.00 MiB,0.00 MiB,1,0,0.000221 ms,78.217195 mW,17286.000000 pJ
reduce_mean/legacy_nchw_spatial,PASS,0.090 s,0.00 MiB,0.00 MiB,3,0,0.000321 ms,92.448598 mW,29676.000000 pJ
reduce_mean/legacy_negative_axis,PASS,0.110 s,0.00 MiB,0.00 MiB,6,0,0.000553 ms,93.520796 mW,51717.000000 pJ
reduce_mean/legacy_reduce_all_keepdims_1,PASS,0.107 s,0.00 MiB,0.00 MiB,1,0,0.000221 ms,78.217195 mW,17286.000000 pJ
reduce_mean/negative_axis,PASS,0.120 s,0.00 MiB,0.00 MiB,6,0,0.000553 ms,93.520796 mW,51717.000000 pJ
relu/4d,PASS,0.116 s,0.00 MiB,0.00 MiB,1,0,0.000521 ms,78.184261 mW,40734.000000 pJ
relu/after_conv,PASS,0.078 s,0.00 MiB,0.00 MiB,3,3,0.004956 ms,106.998935 mW,530286.720000 pJ
relu/after_gemm,PASS,0.077 s,0.01 MiB,0.01 MiB,5,4,0.007513 ms,105.158653 mW,790056.960000 pJ
relu/basic,PASS,0.066 s,0.00 MiB,0.00 MiB,1,0,0.000221 ms,78.217195 mW,17286.000000 pJ
reshape/4d_to_2d_flatten,PASS,0.098 s,0.00 MiB,0.00 MiB,1,0,0.000258 ms,78.279070 mW,20196.000000 pJ
reshape/infer_dim_minus_one,PASS,0.105 s,0.00 MiB,0.00 MiB,1,0,0.000162 ms,78.296296 mW,12684.000000 pJ
reshape/same_rank,PASS,0.057 s,0.00 MiB,0.00 MiB,1,0,0.000162 ms,78.296296 mW,12684.000000 pJ
reshape/zero_copies_input_dim,PASS,0.090 s,0.00 MiB,0.00 MiB,1,0,0.000162 ms,78.296296 mW,12684.000000 pJ
resize/height_only,PASS,0.104 s,0.00 MiB,0.00 MiB,1,0,0.000795 ms,78.060377 mW,62058.000000 pJ
resize/nearest_2x,PASS,0.104 s,0.00 MiB,0.00 MiB,1,0,0.001422 ms,78.033755 mW,110964.000000 pJ
resize/nearest_downsample,PASS,0.059 s,0.00 MiB,0.00 MiB,1,0,0.000481 ms,78.099792 mW,37566.000000 pJ
resize/non_uniform,PASS,0.063 s,0.00 MiB,0.00 MiB,1,0,0.002108 ms,78.034156 mW,164496.000000 pJ
resize/width_only,PASS,0.068 s,0.00 MiB,0.00 MiB,1,0,0.000792 ms,78.060606 mW,61824.000000 pJ
resize/with_sizes,PASS,0.056 s,0.00 MiB,0.00 MiB,1,0,0.000951 ms,78.050473 mW,74226.000000 pJ
sigmoid/4d,PASS,0.104 s,0.00 MiB,0.00 MiB,1,0,0.000521 ms,78.184261 mW,40734.000000 pJ
sigmoid/after_gemm,PASS,0.118 s,0.01 MiB,0.01 MiB,5,4,0.007513 ms,105.158653 mW,790056.960000 pJ
sigmoid/basic,PASS,0.083 s,0.00 MiB,0.00 MiB,1,0,0.000221 ms,78.217195 mW,17286.000000 pJ
slice/2d_basic,PASS,0.067 s,0.00 MiB,0.00 MiB,1,0,0.000242 ms,78.297521 mW,18948.000000 pJ
slice/after_conv,PASS,0.111 s,0.00 MiB,0.01 MiB,7,6,0.011296 ms,118.190765 mW,1335082.880000 pJ
slice/default_axes,PASS,0.065 s,0.00 MiB,0.00 MiB,1,0,0.000242 ms,78.297521 mW,18948.000000 pJ
slice/large_channel_1024,PASS,0.060 s,0.01 MiB,0.00 MiB,1,0,0.002832 ms,78.144068 mW,221304.000000 pJ
slice/nchw_spatial_crop,PASS,0.067 s,0.00 MiB,0.00 MiB,1,0,0.001302 ms,78.239631 mW,101868.000000 pJ
slice/negative_axis,PASS,0.098 s,0.00 MiB,0.00 MiB,1,0,0.000562 ms,78.298932 mW,44004.000000 pJ
slice/negative_indices,PASS,0.106 s,0.00 MiB,0.00 MiB,1,0,0.000322 ms,78.298137 mW,25212.000000 pJ
slice/step2,PASS,0.068 s,0.00 MiB,0.00 MiB,1,0,0.002042 ms,78.293830 mW,159876.000000 pJ
softmax/3d_last_axis,PASS,0.072 s,0.00 MiB,0.00 MiB,1,0,UNSUPPORTED,UNSUPPORTED,UNSUPPORTED
softmax/basic,PASS,0.088 s,0.00 MiB,0.00 MiB,1,0,UNSUPPORTED,UNSUPPORTED,UNSUPPORTED
softmax/channel_axis,PASS,0.110 s,0.00 MiB,0.00 MiB,1,0,UNSUPPORTED,UNSUPPORTED,UNSUPPORTED
softmax/large_dimension_1024,PASS,0.104 s,0.01 MiB,0.01 MiB,1,0,UNSUPPORTED,UNSUPPORTED,UNSUPPORTED
softmax/negative_axis,PASS,0.118 s,0.00 MiB,0.00 MiB,1,0,UNSUPPORTED,UNSUPPORTED,UNSUPPORTED
split/basic,PASS,0.077 s,0.00 MiB,0.00 MiB,1,0,0.000403 ms,78.297767 mW,31554.000000 pJ
split/equal_three_way,PASS,0.107 s,0.00 MiB,0.00 MiB,1,0,0.000564 ms,78.297872 mW,44160.000000 pJ
split/negative_axis,PASS,0.111 s,0.00 MiB,0.00 MiB,1,0,0.001083 ms,78.288089 mW,84786.000000 pJ
split/uneven_channel_axis_4d,PASS,0.061 s,0.00 MiB,0.00 MiB,1,0,0.000242 ms,78.297521 mW,18948.000000 pJ
sub/after_gemm,PASS,0.068 s,0.01 MiB,0.01 MiB,5,4,0.007784 ms,104.703618 mW,815012.960000 pJ
sub/basic,PASS,0.063 s,0.00 MiB,0.00 MiB,1,0,0.000323 ms,78.222910 mW,25266.000000 pJ
sub/broadcast_row,PASS,0.075 s,0.00 MiB,0.00 MiB,1,0,0.000323 ms,78.222910 mW,25266.000000 pJ
sub/channel_broadcast_1024,PASS,0.052 s,0.02 MiB,0.01 MiB,1,0,0.006913 ms,78.118038 mW,540030.000000 pJ
sub/constant_lhs_broadcast,PASS,0.057 s,0.00 MiB,0.00 MiB,1,0,0.000322 ms,78.223602 mW,25188.000000 pJ
sub/leading_dimension_broadcast,PASS,0.053 s,0.00 MiB,0.00 MiB,1,0,0.000323 ms,78.222910 mW,25266.000000 pJ
1 Operation Result Compile Host mem Cores mem Cores Xbars Latency Power Energy
2 add/after_gemm PASS 0.141 s 0.01 MiB 0.01 MiB 5 4 0.007784 ms 104.703618 mW 815012.960000 pJ
3 add/basic PASS 0.114 s 0.00 MiB 0.00 MiB 1 0 0.000323 ms 78.222910 mW 25266.000000 pJ
4 add/broadcast_row PASS 0.110 s 0.00 MiB 0.00 MiB 1 0 0.000323 ms 78.222910 mW 25266.000000 pJ
5 add/channel_broadcast_1024 PASS 0.105 s 0.02 MiB 0.01 MiB 1 0 0.006913 ms 78.118038 mW 540030.000000 pJ
6 add/leading_dimension_broadcast PASS 0.137 s 0.00 MiB 0.00 MiB 1 0 0.000323 ms 78.222910 mW 25266.000000 pJ
7 concat/channel_axis PASS 0.127 s 0.00 MiB 0.00 MiB 1 0 0.000457 ms 78.157549 mW 35718.000000 pJ
8 concat/negative_axis PASS 0.102 s 0.00 MiB 0.00 MiB 1 0 0.001043 ms 78.092042 mW 81450.000000 pJ
9 concat/three_inputs_channel_axis PASS 0.127 s 0.00 MiB 0.00 MiB 1 0 0.000644 ms 78.149068 mW 50328.000000 pJ
10 conv/batch_2 PASS 0.102 s 0.00 MiB 0.00 MiB 2 2 0.013694 ms 82.623885 mW 1131451.480000 pJ
11 conv/batch_4_pointwise PASS 0.110 s 0.00 MiB 0.01 MiB 5 4 0.003932 ms 116.078576 mW 456420.960000 pJ
12 conv/depthwise_1024_channels PASS 0.167 s 0.19 MiB 0.38 MiB 129 128 0.220751 ms 178.454307 mW 39393966.720000 pJ
13 conv/depthwise_grouped PASS 0.109 s 0.01 MiB 0.00 MiB 5 4 0.006024 ms 108.326521 mW 652558.960000 pJ
14 conv/dilated_3x3 PASS 0.143 s 0.00 MiB 0.00 MiB 3 3 0.004045 ms 110.234541 mW 445898.720000 pJ
15 conv/dynamic PASS 0.107 s 0.00 MiB 0.00 MiB 5 0 0.001835 ms 92.281199 mW 169336.000000 pJ
16 conv/explicit_padding PASS 0.139 s 0.00 MiB 0.00 MiB 4 4 0.004327 ms 115.794768 mW 501043.960000 pJ
17 conv/grouped_many_groups PASS 0.616 s 0.05 MiB 0.09 MiB 65 64 0.181845 ms 142.210104 mW 25860196.360000 pJ
18 conv/grouped_two_groups PASS 0.145 s 0.00 MiB 0.00 MiB 3 2 0.005360 ms 101.459418 mW 543822.480000 pJ
19 conv/huge_pointwise_1024 PASS 0.749 s 0.01 MiB 0.01 MiB 1 64 0.028261 ms 133.488743 mW 3772525.360000 pJ
20 conv/huge_pointwise_1024_dynamic PASS 0.097 s 8.04 MiB 12.61 MiB 168 0 2.627964 ms 169.518697 mW 445489032.000000 pJ
21 conv/kernel_3x3 PASS 0.155 s 0.00 MiB 0.00 MiB 3 3 0.003091 ms 115.862414 mW 358130.720000 pJ
22 conv/kernel_equals_input_spatial PASS 0.156 s 0.00 MiB 0.00 MiB 1 2 0.008443 ms 83.863849 mW 708062.480000 pJ
23 conv/large_input_channels_1x1 PASS 0.160 s 0.01 MiB 0.01 MiB 1 8 0.017167 ms 89.416900 mW 1535019.920000 pJ
24 conv/large_output_channels_1x1 PASS 0.141 s 0.00 MiB 0.01 MiB 1 8 0.004964 ms 117.628106 mW 583905.920000 pJ
25 conv/large_spatial PASS 0.141 s 0.00 MiB 0.01 MiB 6 6 0.004096 ms 129.015000 mW 528445.440000 pJ
26 conv/multi_channel PASS 0.143 s 0.00 MiB 0.00 MiB 3 3 0.005148 ms 106.453520 mW 548022.720000 pJ
27 conv/non_square_kernel_1x3 PASS 0.127 s 0.00 MiB 0.00 MiB 5 5 0.004029 ms 123.600943 mW 497988.200000 pJ
28 conv/non_square_kernel_3x1 PASS 0.085 s 0.00 MiB 0.00 MiB 3 3 0.005526 ms 105.464843 mW 582798.720000 pJ
29 conv/non_uniform_stride PASS 0.120 s 0.00 MiB 0.00 MiB 4 4 0.005808 ms 110.081433 mW 639352.960000 pJ
30 conv/pointwise_1x1 PASS 0.139 s 0.00 MiB 0.00 MiB 4 4 0.004539 ms 114.835858 mW 521239.960000 pJ
31 conv/pointwise_tiled_chain PASS 0.943 s 0.01 MiB 0.02 MiB 2 80 0.084437 ms 102.289307 mW 8637002.200000 pJ
32 conv/real_asymmetric_padding PASS 0.115 s 0.00 MiB 0.00 MiB 4 4 0.005232 ms 111.870214 mW 585304.960000 pJ
33 conv/relu_conv_store PASS 0.107 s 0.05 MiB 0.08 MiB 32 32 0.062978 ms 246.649827 mW 15533512.800000 pJ
34 conv/same_lower_3x3 PASS 0.094 s 0.00 MiB 0.00 MiB 5 5 0.004700 ms 119.232170 mW 560391.200000 pJ
35 conv/same_padding_3x3 PASS 0.126 s 0.00 MiB 0.00 MiB 5 5 0.004700 ms 119.232170 mW 560391.200000 pJ
36 conv/simple PASS 0.125 s 0.00 MiB 0.00 MiB 2 2 0.003148 ms 94.665972 mW 298008.480000 pJ
37 conv/stride_2 PASS 0.146 s 0.00 MiB 0.00 MiB 2 2 0.002827 ms 96.393873 mW 272505.480000 pJ
38 conv/with_bias_3x3 PASS 0.121 s 0.00 MiB 0.00 MiB 3 3 0.004898 ms 107.176546 mW 524950.720000 pJ
39 conv/with_constant PASS 0.106 s 0.00 MiB 0.00 MiB 3 3 0.004273 ms 109.362677 mW 467306.720000 pJ
40 conv/without_kernel_shape_attr PASS 0.105 s 0.00 MiB 0.00 MiB 3 3 0.003091 ms 115.862414 mW 358130.720000 pJ
41 conv/yolo11n_stem PASS 3.091 s 29.20 MiB 31.38 MiB 168 488 9.799213 ms 361.075203 mW 3538252825.000010 pJ
42 div/after_gemm PASS 0.130 s 0.01 MiB 0.01 MiB 5 4 0.007784 ms 104.703618 mW 815012.960000 pJ
43 div/basic PASS 0.116 s 0.00 MiB 0.00 MiB 1 0 0.000323 ms 78.222910 mW 25266.000000 pJ
44 div/channel_broadcast_1024 PASS 0.121 s 0.02 MiB 0.01 MiB 1 0 0.006913 ms 78.118038 mW 540030.000000 pJ
45 div/leading_dimension_broadcast PASS 0.095 s 0.00 MiB 0.00 MiB 1 0 0.000323 ms 78.222910 mW 25266.000000 pJ
46 div/runtime_scalar_rhs PASS 0.126 s 0.02 MiB 0.01 MiB 1 0 0.006913 ms 78.118038 mW 540030.000000 pJ
47 div/scalar_constant PASS 0.069 s 0.00 MiB 0.00 MiB 1 0 0.000323 ms 78.222910 mW 25266.000000 pJ
48 gather/3d_input_axis1 PASS 0.121 s 0.00 MiB 0.00 MiB 1 0 0.000589 ms 78.081494 mW 45990.000000 pJ
49 gather/axis0_matrix_indices PASS 0.088 s 0.00 MiB 0.00 MiB 1 0 0.000697 ms 78.068867 mW 54414.000000 pJ
50 gather/axis1 PASS 0.123 s 0.00 MiB 0.00 MiB 1 0 0.000801 ms 78.059925 mW 62526.000000 pJ
51 gather/negative_axis PASS 0.087 s 0.00 MiB 0.00 MiB 1 0 0.001437 ms 78.033403 mW 112134.000000 pJ
52 gather/negative_indices PASS 0.115 s 0.00 MiB 0.00 MiB 1 0 0.000376 ms 78.127660 mW 29376.000000 pJ
53 gemm/alpha_beta PASS 0.121 s 0.01 MiB 0.01 MiB 5 4 0.007456 ms 105.272125 mW 784908.960000 pJ
54 gemm/bias_rank2_broadcast PASS 0.127 s 0.00 MiB 0.01 MiB 5 4 0.007072 ms 105.979208 mW 749484.960000 pJ
55 gemm/dynamic PASS 0.084 s 0.00 MiB 0.00 MiB 5 0 0.002421 ms 91.480793 mW 221475.000000 pJ
56 gemm/dynamic_alpha PASS 0.104 s 0.00 MiB 0.00 MiB 5 0 0.003262 ms 91.415696 mW 298198.000000 pJ
57 gemm/dynamic_beta PASS 0.110 s 0.00 MiB 0.00 MiB 5 0 0.004365 ms 91.316151 mW 398595.000000 pJ
58 gemm/dynamic_bias PASS 0.092 s 0.00 MiB 0.00 MiB 5 0 0.002665 ms 91.445779 mW 243703.000000 pJ
59 gemm/dynamic_bias_alpha_beta PASS 0.089 s 0.00 MiB 0.00 MiB 5 0 0.005629 ms 91.279268 mW 513811.000000 pJ
60 gemm/dynamic_transB PASS 0.077 s 0.00 MiB 0.00 MiB 5 0 0.001301 ms 91.378171 mW 118883.000000 pJ
61 gemm/huge_1024 PASS 0.219 s 0.01 MiB 0.10 MiB 73 64 0.017522 ms 215.037402 mW 3767885.360000 pJ
62 gemm/large PASS 0.097 s 0.02 MiB 0.03 MiB 17 16 0.011229 ms 140.152181 mW 1573768.840000 pJ
63 gemm/large_k_small_n PASS 0.106 s 0.01 MiB 0.01 MiB 9 8 0.004748 ms 133.481449 mW 633769.920000 pJ
64 gemm/non_square PASS 0.102 s 0.00 MiB 0.01 MiB 5 4 0.003527 ms 118.958310 mW 419565.960000 pJ
65 gemm/scalar_bias PASS 0.111 s 0.00 MiB 0.01 MiB 5 4 0.007072 ms 105.979208 mW 749484.960000 pJ
66 gemm/simple PASS 0.135 s 0.03 MiB 0.08 MiB 42 40 0.021640 ms 151.774196 mW 3284393.600000 pJ
67 gemm/small PASS 0.074 s 0.00 MiB 0.00 MiB 2 2 0.004420 ms 90.144000 mW 398436.480000 pJ
68 gemm/small_k_large_n PASS 0.129 s 0.01 MiB 0.02 MiB 17 8 0.007962 ms 131.005014 mW 1043061.920000 pJ
69 gemm/transA PASS 0.089 s 0.00 MiB 0.01 MiB 5 4 0.005762 ms 109.140743 mW 628868.960000 pJ
70 gemm/transA_transB PASS 0.115 s 0.00 MiB 0.01 MiB 5 4 0.005762 ms 109.140743 mW 628868.960000 pJ
71 gemm/transB PASS 0.068 s 0.00 MiB 0.01 MiB 5 4 0.003527 ms 118.958310 mW 419565.960000 pJ
72 gemm/transB_with_bias PASS 0.069 s 0.01 MiB 0.01 MiB 5 4 0.005046 ms 110.546762 mW 557818.960000 pJ
73 gemm/with_bias PASS 0.113 s 0.01 MiB 0.01 MiB 5 4 0.005562 ms 108.767882 mW 604966.960000 pJ
74 gemv/constant PASS 0.112 s 0.00 MiB 0.00 MiB 0 0 0.000000 ms 2.000000 mW 0.000000 pJ
75 gemv/simple PASS 0.136 s 0.00 MiB 0.01 MiB 6 4 0.005160 ms 111.150380 mW 573535.960000 pJ
76 gemv/with_heterogeneous_constant PASS 0.138 s 0.00 MiB 0.01 MiB 6 4 0.005549 ms 109.816536 mW 609371.960000 pJ
77 gemv/with_homogeneous_constant PASS 0.140 s 0.00 MiB 0.01 MiB 6 4 0.005549 ms 109.816536 mW 609371.960000 pJ
78 gemv/with_scalar_constant PASS 0.124 s 0.00 MiB 0.01 MiB 6 4 0.005549 ms 109.816536 mW 609371.960000 pJ
79 matmul/basic PASS 0.081 s 0.00 MiB 0.00 MiB 2 2 0.004420 ms 90.144000 mW 398436.480000 pJ
80 matmul/batched_3d PASS 0.133 s 0.00 MiB 0.01 MiB 5 4 0.005958 ms 108.588949 mW 646972.960000 pJ
81 matmul/batched_3d_dynamic PASS 0.105 s 0.00 MiB 0.00 MiB 9 0 0.003525 ms 92.330213 mW 325464.000000 pJ
82 matmul/batched_left_constant PASS 0.136 s 0.00 MiB 0.02 MiB 9 8 0.008822 ms 114.385164 mW 1009105.920000 pJ
83 matmul/batched_lhs_broadcast PASS 0.133 s 0.00 MiB 0.01 MiB 5 4 0.005681 ms 109.389361 mW 621440.960000 pJ
84 matmul/batched_rhs_broadcast PASS 0.134 s 0.00 MiB 0.01 MiB 5 4 0.005958 ms 108.588949 mW 646972.960000 pJ
85 matmul/dynamic PASS 0.093 s 0.00 MiB 0.00 MiB 5 0 0.001621 ms 91.421962 mW 148195.000000 pJ
86 matmul/huge_1024 PASS 0.277 s 0.01 MiB 0.10 MiB 73 64 0.017522 ms 215.037402 mW 3767885.360000 pJ
87 matmul/left_constant PASS 0.123 s 0.00 MiB 0.01 MiB 5 4 0.005853 ms 108.861944 mW 637168.960000 pJ
88 matmul/matrix_vector PASS 0.150 s 0.52 MiB 0.78 MiB 168 173 0.384660 ms 202.131271 mW 77751814.880000 pJ
89 matmul/vector_matrix PASS 0.186 s 0.01 MiB 0.01 MiB 9 8 0.007409 ms 118.680243 mW 879301.920000 pJ
90 mul/after_conv PASS 0.127 s 0.00 MiB 0.00 MiB 4 3 0.005453 ms 107.639046 mW 586955.720000 pJ
91 mul/basic PASS 0.070 s 0.00 MiB 0.00 MiB 1 0 0.000323 ms 78.222910 mW 25266.000000 pJ
92 mul/channel_broadcast_1024 PASS 0.065 s 0.02 MiB 0.01 MiB 1 0 0.006913 ms 78.118038 mW 540030.000000 pJ
93 mul/leading_dimension_broadcast PASS 0.108 s 0.00 MiB 0.00 MiB 1 0 0.000323 ms 78.222910 mW 25266.000000 pJ
94 mul/scalar_constant PASS 0.082 s 0.00 MiB 0.00 MiB 1 0 0.000323 ms 78.222910 mW 25266.000000 pJ
95 pool/avg_basic PASS 0.070 s 0.00 MiB 0.00 MiB 1 0 0.011939 ms 78.022112 mW 931506.000000 pJ
96 pool/avg_ceil_mode PASS 0.107 s 0.00 MiB 0.00 MiB 1 0 0.004359 ms 78.033035 mW 340146.000000 pJ
97 pool/avg_explicit_padding PASS 0.111 s 0.00 MiB 0.00 MiB 1 0 0.008822 ms 78.027205 mW 688356.000000 pJ
98 pool/avg_include_pad PASS 0.075 s 0.00 MiB 0.00 MiB 1 0 0.008506 ms 78.016929 mW 663612.000000 pJ
99 pool/avg_large_channels PASS 0.064 s 0.04 MiB 0.02 MiB 1 0 0.178249 ms 78.280327 mW 13953390.000000 pJ
100 pool/avg_non_uniform_stride PASS 0.068 s 0.00 MiB 0.00 MiB 1 0 0.014513 ms 78.016537 mW 1132254.000000 pJ
101 pool/avg_real_asymmetric_padding PASS 0.064 s 0.00 MiB 0.00 MiB 1 0 0.025206 ms 78.024756 mW 1966692.000000 pJ
102 pool/max_after_conv PASS 0.070 s 0.00 MiB 0.00 MiB 6 4 0.006452 ms 96.374606 mW 621808.960000 pJ
103 pool/max_basic PASS 0.063 s 0.00 MiB 0.00 MiB 3 0 0.001634 ms 92.132191 mW 150544.000000 pJ
104 pool/max_ceil_mode PASS 0.065 s 0.00 MiB 0.00 MiB 2 0 0.001297 ms 79.111025 mW 102607.000000 pJ
105 pool/max_global_style_kernel_equals_input PASS 0.089 s 0.00 MiB 0.00 MiB 1 0 0.004366 ms 78.010994 mW 340596.000000 pJ
106 pool/max_non_square_kernel PASS 0.103 s 0.00 MiB 0.00 MiB 4 0 0.003409 ms 93.253447 mW 317901.000000 pJ
107 pool/max_real_asymmetric_padding PASS 0.088 s 0.00 MiB 0.00 MiB 4 0 0.003078 ms 93.124756 mW 286638.000000 pJ
108 pool/max_same_upper PASS 0.065 s 0.00 MiB 0.00 MiB 3 0 0.003024 ms 92.095238 mW 278496.000000 pJ
109 pool/max_stride2_multichannel PASS 0.086 s 0.00 MiB 0.00 MiB 3 0 0.004012 ms 92.269192 mW 370184.000000 pJ
110 reduce_mean/4d_spatial PASS 0.061 s 0.00 MiB 0.00 MiB 3 0 0.000321 ms 92.448598 mW 29676.000000 pJ
111 reduce_mean/4d_spatial_keepdims_0 PASS 0.067 s 0.00 MiB 0.00 MiB 4 0 0.000655 ms 94.352672 mW 61801.000000 pJ
112 reduce_mean/after_conv PASS 0.115 s 0.00 MiB 0.00 MiB 5 3 0.005342 ms 106.951089 mW 571332.720000 pJ
113 reduce_mean/all_axes_keepdims_0 PASS 0.103 s 0.00 MiB 0.00 MiB 2 0 0.000391 ms 79.237852 mW 30982.000000 pJ
114 reduce_mean/all_axes_keepdims_1 PASS 0.086 s 0.00 MiB 0.00 MiB 1 0 0.000221 ms 78.217195 mW 17286.000000 pJ
115 reduce_mean/basic PASS 0.099 s 0.00 MiB 0.00 MiB 4 0 0.000373 ms 93.514745 mW 34881.000000 pJ
116 reduce_mean/channel_axis_nchw PASS 0.078 s 0.03 MiB 0.02 MiB 4 0 0.164926 ms 93.596631 mW 15436518.000000 pJ
117 reduce_mean/keepdims_0 PASS 0.073 s 0.00 MiB 0.00 MiB 5 0 0.000748 ms 91.401070 mW 68368.000000 pJ
118 reduce_mean/large_dimension_1024 PASS 0.115 s 0.01 MiB 0.00 MiB 1 0 0.002785 ms 78.017235 mW 217278.000000 pJ
119 reduce_mean/legacy_axes_1_2_keepdims_1 PASS 0.074 s 0.00 MiB 0.00 MiB 2 0 0.000271 ms 79.354244 mW 21505.000000 pJ
120 reduce_mean/legacy_axis1_keepdims_0 PASS 0.111 s 0.00 MiB 0.00 MiB 9 0 0.001986 ms 92.501511 mW 183708.000000 pJ
121 reduce_mean/legacy_axis1_keepdims_1 PASS 0.086 s 0.00 MiB 0.00 MiB 8 0 0.001373 ms 94.559359 mW 129830.000000 pJ
122 reduce_mean/legacy_empty_axes_noop PASS 0.115 s 0.00 MiB 0.00 MiB 1 0 0.000221 ms 78.217195 mW 17286.000000 pJ
123 reduce_mean/legacy_nchw_spatial PASS 0.090 s 0.00 MiB 0.00 MiB 3 0 0.000321 ms 92.448598 mW 29676.000000 pJ
124 reduce_mean/legacy_negative_axis PASS 0.110 s 0.00 MiB 0.00 MiB 6 0 0.000553 ms 93.520796 mW 51717.000000 pJ
125 reduce_mean/legacy_reduce_all_keepdims_1 PASS 0.107 s 0.00 MiB 0.00 MiB 1 0 0.000221 ms 78.217195 mW 17286.000000 pJ
126 reduce_mean/negative_axis PASS 0.120 s 0.00 MiB 0.00 MiB 6 0 0.000553 ms 93.520796 mW 51717.000000 pJ
127 relu/4d PASS 0.116 s 0.00 MiB 0.00 MiB 1 0 0.000521 ms 78.184261 mW 40734.000000 pJ
128 relu/after_conv PASS 0.078 s 0.00 MiB 0.00 MiB 3 3 0.004956 ms 106.998935 mW 530286.720000 pJ
129 relu/after_gemm PASS 0.077 s 0.01 MiB 0.01 MiB 5 4 0.007513 ms 105.158653 mW 790056.960000 pJ
130 relu/basic PASS 0.066 s 0.00 MiB 0.00 MiB 1 0 0.000221 ms 78.217195 mW 17286.000000 pJ
131 reshape/4d_to_2d_flatten PASS 0.098 s 0.00 MiB 0.00 MiB 1 0 0.000258 ms 78.279070 mW 20196.000000 pJ
132 reshape/infer_dim_minus_one PASS 0.105 s 0.00 MiB 0.00 MiB 1 0 0.000162 ms 78.296296 mW 12684.000000 pJ
133 reshape/same_rank PASS 0.057 s 0.00 MiB 0.00 MiB 1 0 0.000162 ms 78.296296 mW 12684.000000 pJ
134 reshape/zero_copies_input_dim PASS 0.090 s 0.00 MiB 0.00 MiB 1 0 0.000162 ms 78.296296 mW 12684.000000 pJ
135 resize/height_only PASS 0.104 s 0.00 MiB 0.00 MiB 1 0 0.000795 ms 78.060377 mW 62058.000000 pJ
136 resize/nearest_2x PASS 0.104 s 0.00 MiB 0.00 MiB 1 0 0.001422 ms 78.033755 mW 110964.000000 pJ
137 resize/nearest_downsample PASS 0.059 s 0.00 MiB 0.00 MiB 1 0 0.000481 ms 78.099792 mW 37566.000000 pJ
138 resize/non_uniform PASS 0.063 s 0.00 MiB 0.00 MiB 1 0 0.002108 ms 78.034156 mW 164496.000000 pJ
139 resize/width_only PASS 0.068 s 0.00 MiB 0.00 MiB 1 0 0.000792 ms 78.060606 mW 61824.000000 pJ
140 resize/with_sizes PASS 0.056 s 0.00 MiB 0.00 MiB 1 0 0.000951 ms 78.050473 mW 74226.000000 pJ
141 sigmoid/4d PASS 0.104 s 0.00 MiB 0.00 MiB 1 0 0.000521 ms 78.184261 mW 40734.000000 pJ
142 sigmoid/after_gemm PASS 0.118 s 0.01 MiB 0.01 MiB 5 4 0.007513 ms 105.158653 mW 790056.960000 pJ
143 sigmoid/basic PASS 0.083 s 0.00 MiB 0.00 MiB 1 0 0.000221 ms 78.217195 mW 17286.000000 pJ
144 slice/2d_basic PASS 0.067 s 0.00 MiB 0.00 MiB 1 0 0.000242 ms 78.297521 mW 18948.000000 pJ
145 slice/after_conv PASS 0.111 s 0.00 MiB 0.01 MiB 7 6 0.011296 ms 118.190765 mW 1335082.880000 pJ
146 slice/default_axes PASS 0.065 s 0.00 MiB 0.00 MiB 1 0 0.000242 ms 78.297521 mW 18948.000000 pJ
147 slice/large_channel_1024 PASS 0.060 s 0.01 MiB 0.00 MiB 1 0 0.002832 ms 78.144068 mW 221304.000000 pJ
148 slice/nchw_spatial_crop PASS 0.067 s 0.00 MiB 0.00 MiB 1 0 0.001302 ms 78.239631 mW 101868.000000 pJ
149 slice/negative_axis PASS 0.098 s 0.00 MiB 0.00 MiB 1 0 0.000562 ms 78.298932 mW 44004.000000 pJ
150 slice/negative_indices PASS 0.106 s 0.00 MiB 0.00 MiB 1 0 0.000322 ms 78.298137 mW 25212.000000 pJ
151 slice/step2 PASS 0.068 s 0.00 MiB 0.00 MiB 1 0 0.002042 ms 78.293830 mW 159876.000000 pJ
152 softmax/3d_last_axis PASS 0.072 s 0.00 MiB 0.00 MiB 1 0 UNSUPPORTED UNSUPPORTED UNSUPPORTED
153 softmax/basic PASS 0.088 s 0.00 MiB 0.00 MiB 1 0 UNSUPPORTED UNSUPPORTED UNSUPPORTED
154 softmax/channel_axis PASS 0.110 s 0.00 MiB 0.00 MiB 1 0 UNSUPPORTED UNSUPPORTED UNSUPPORTED
155 softmax/large_dimension_1024 PASS 0.104 s 0.01 MiB 0.01 MiB 1 0 UNSUPPORTED UNSUPPORTED UNSUPPORTED
156 softmax/negative_axis PASS 0.118 s 0.00 MiB 0.00 MiB 1 0 UNSUPPORTED UNSUPPORTED UNSUPPORTED
157 split/basic PASS 0.077 s 0.00 MiB 0.00 MiB 1 0 0.000403 ms 78.297767 mW 31554.000000 pJ
158 split/equal_three_way PASS 0.107 s 0.00 MiB 0.00 MiB 1 0 0.000564 ms 78.297872 mW 44160.000000 pJ
159 split/negative_axis PASS 0.111 s 0.00 MiB 0.00 MiB 1 0 0.001083 ms 78.288089 mW 84786.000000 pJ
160 split/uneven_channel_axis_4d PASS 0.061 s 0.00 MiB 0.00 MiB 1 0 0.000242 ms 78.297521 mW 18948.000000 pJ
161 sub/after_gemm PASS 0.068 s 0.01 MiB 0.01 MiB 5 4 0.007784 ms 104.703618 mW 815012.960000 pJ
162 sub/basic PASS 0.063 s 0.00 MiB 0.00 MiB 1 0 0.000323 ms 78.222910 mW 25266.000000 pJ
163 sub/broadcast_row PASS 0.075 s 0.00 MiB 0.00 MiB 1 0 0.000323 ms 78.222910 mW 25266.000000 pJ
164 sub/channel_broadcast_1024 PASS 0.052 s 0.02 MiB 0.01 MiB 1 0 0.006913 ms 78.118038 mW 540030.000000 pJ
165 sub/constant_lhs_broadcast PASS 0.057 s 0.00 MiB 0.00 MiB 1 0 0.000322 ms 78.223602 mW 25188.000000 pJ
166 sub/leading_dimension_broadcast PASS 0.053 s 0.00 MiB 0.00 MiB 1 0 0.000323 ms 78.222910 mW 25266.000000 pJ