add throughput mode to validation scripts

make raptor also emit input sizes
This commit is contained in:
NiccoloN
2026-08-11 10:34:50 +02:00
parent 910701dfaf
commit c55d9f3dad
15 changed files with 974 additions and 497 deletions
+2 -2
View File
@@ -38,8 +38,8 @@ 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
and writes the same rows to `validation_results.csv`.
The validator prints separate latency and throughput operation tables before
its summary and writes all of their rows to `validation_results.csv`.
## Complete inventory
+28 -28
View File
@@ -485,16 +485,16 @@ def conv_without_kernel_shape_attr():
# GEMM tests
# ---------------------------------------------------------------------------
def gemm_simple():
def gemm_square_weights():
"""Simple GEMM with square weights: [10, 132] @ [132, 132]."""
B, K, N = 10, 132, 132
W = numpy_helper.from_array(np.random.default_rng(41).uniform(-1, 1, (K, N)).astype(np.float32), name="W")
A = helper.make_tensor_value_info("A", TensorProto.FLOAT, [B, K])
Y = helper.make_tensor_value_info("Y", TensorProto.FLOAT, [B, N])
node = helper.make_node("Gemm", ["A", "W"], ["Y"])
graph = helper.make_graph([node], "gemm_simple", [A], [Y], initializer=[W])
graph = helper.make_graph([node], "gemm_square_weights", [A], [Y], initializer=[W])
model = helper.make_model(graph, opset_imports=[helper.make_opsetid("", 13)])
save_model(model, "gemm/simple", "gemm_simple.onnx")
save_model(model, "gemm/square_weights", "gemm_square_weights.onnx")
def gemm_non_square():
@@ -523,7 +523,7 @@ def gemm_with_bias():
save_model(model, "gemm/with_bias", "gemm_with_bias.onnx")
def gemm_transB():
def gemm_transpose_b():
"""GEMM with transB=1: Y = A @ W^T."""
B, K, N = 4, 128, 64
rng = np.random.default_rng(44)
@@ -532,9 +532,9 @@ def gemm_transB():
A = helper.make_tensor_value_info("A", TensorProto.FLOAT, [B, K])
Y = helper.make_tensor_value_info("Y", TensorProto.FLOAT, [B, N])
node = helper.make_node("Gemm", ["A", "W"], ["Y"], transB=1)
graph = helper.make_graph([node], "gemm_transB", [A], [Y], initializer=[W])
graph = helper.make_graph([node], "gemm_transpose_b", [A], [Y], initializer=[W])
model = helper.make_model(graph, opset_imports=[helper.make_opsetid("", 13)])
save_model(model, "gemm/transB", "gemm_transB.onnx")
save_model(model, "gemm/transpose_b", "gemm_transpose_b.onnx")
def gemm_alpha_beta():
@@ -577,7 +577,7 @@ def gemm_large():
save_model(model, "gemm/large", "gemm_large.onnx")
def gemm_transB_with_bias():
def gemm_transpose_b_with_bias():
"""GEMM with transB and bias: Y = A @ W^T + C."""
B, K, N = 4, 128, 64
rng = np.random.default_rng(48)
@@ -586,9 +586,9 @@ def gemm_transB_with_bias():
A = helper.make_tensor_value_info("A", TensorProto.FLOAT, [B, K])
Y = helper.make_tensor_value_info("Y", TensorProto.FLOAT, [B, N])
node = helper.make_node("Gemm", ["A", "W", "C"], ["Y"], transB=1)
graph = helper.make_graph([node], "gemm_transB_with_bias", [A], [Y], initializer=[W, C])
graph = helper.make_graph([node], "gemm_transpose_b_with_bias", [A], [Y], initializer=[W, C])
model = helper.make_model(graph, opset_imports=[helper.make_opsetid("", 13)])
save_model(model, "gemm/transB_with_bias", "gemm_transB_with_bias.onnx")
save_model(model, "gemm/transpose_b_with_bias", "gemm_transpose_b_with_bias.onnx")
def gemm_dynamic():
@@ -602,15 +602,15 @@ def gemm_dynamic():
save_model(model, "gemm/dynamic", "gemm_dynamic.onnx")
def gemm_dynamic_transB():
def gemm_dynamic_transpose_b():
"""GEMM with runtime matrix operands and transposed runtime B."""
A = helper.make_tensor_value_info("A", TensorProto.FLOAT, [2, 8])
B = helper.make_tensor_value_info("B", TensorProto.FLOAT, [4, 8])
Y = helper.make_tensor_value_info("Y", TensorProto.FLOAT, [2, 4])
node = helper.make_node("Gemm", ["A", "B"], ["Y"], transB=1)
graph = helper.make_graph([node], "gemm_dynamic_transB", [A, B], [Y])
graph = helper.make_graph([node], "gemm_dynamic_transpose_b", [A, B], [Y])
model = helper.make_model(graph, opset_imports=[helper.make_opsetid("", 13)])
save_model(model, "gemm/dynamic_transB", "gemm_dynamic_transB.onnx")
save_model(model, "gemm/dynamic_transpose_b", "gemm_dynamic_transpose_b.onnx")
def gemm_dynamic_bias():
@@ -696,26 +696,26 @@ def gemm_small_k_large_n():
save_model(model, "gemm/small_k_large_n", "gemm_small_k_large_n.onnx")
def gemm_transA():
def gemm_transpose_a():
"""GEMM with transA=1: A is stored as [K, M] and used as [M, K]."""
A = helper.make_tensor_value_info("A", TensorProto.FLOAT, [8, 4])
Y = helper.make_tensor_value_info("Y", TensorProto.FLOAT, [4, 6])
W = numpy_helper.from_array(np.random.default_rng(90).uniform(-1, 1, (8, 6)).astype(np.float32), name="W")
node = helper.make_node("Gemm", ["A", "W"], ["Y"], transA=1)
graph = helper.make_graph([node], "gemm_transA", [A], [Y], initializer=[W])
graph = helper.make_graph([node], "gemm_transpose_a", [A], [Y], initializer=[W])
model = helper.make_model(graph, opset_imports=[helper.make_opsetid("", 13)])
save_model(model, "gemm/transA", "gemm_transA.onnx")
save_model(model, "gemm/transpose_a", "gemm_transpose_a.onnx")
def gemm_transA_transB():
def gemm_transpose_a_and_b():
"""GEMM with transA=1 and transB=1."""
A = helper.make_tensor_value_info("A", TensorProto.FLOAT, [8, 4])
Y = helper.make_tensor_value_info("Y", TensorProto.FLOAT, [4, 6])
W = numpy_helper.from_array(np.random.default_rng(91).uniform(-1, 1, (6, 8)).astype(np.float32), name="W")
node = helper.make_node("Gemm", ["A", "W"], ["Y"], transA=1, transB=1)
graph = helper.make_graph([node], "gemm_transA_transB", [A], [Y], initializer=[W])
graph = helper.make_graph([node], "gemm_transpose_a_and_b", [A], [Y], initializer=[W])
model = helper.make_model(graph, opset_imports=[helper.make_opsetid("", 13)])
save_model(model, "gemm/transA_transB", "gemm_transA_transB.onnx")
save_model(model, "gemm/transpose_a_and_b", "gemm_transpose_a_and_b.onnx")
def gemm_bias_rank2_broadcast():
@@ -1415,7 +1415,7 @@ def resize_nearest_2x():
save_model(model, "resize/nearest_2x", "resize_nearest_2x.onnx")
def resize_nearest_non_uniform():
def resize_nearest_non_uniform_scales():
"""Resize an NCHW tensor with non-uniform nearest-neighbor scales."""
X = helper.make_tensor_value_info("X", TensorProto.FLOAT, [1, 1, 2, 3])
Y = helper.make_tensor_value_info("Y", TensorProto.FLOAT, [1, 1, 6, 6])
@@ -1424,9 +1424,9 @@ def resize_nearest_non_uniform():
node = helper.make_node(
"Resize", ["X", "roi", "scales"], ["Y"],
mode="nearest", coordinate_transformation_mode="asymmetric", nearest_mode="floor")
graph = helper.make_graph([node], "resize_nearest_non_uniform", [X], [Y], initializer=[roi, scales])
graph = helper.make_graph([node], "resize_nearest_non_uniform_scales", [X], [Y], initializer=[roi, scales])
model = helper.make_model(graph, opset_imports=[helper.make_opsetid("", 13)])
save_model(model, "resize/non_uniform", "resize_non_uniform.onnx")
save_model(model, "resize/non_uniform_scales", "resize_non_uniform_scales.onnx")
def resize_with_sizes():
@@ -2079,16 +2079,16 @@ def div_leading_dimension_broadcast():
if __name__ == "__main__":
print("Generating GEMM tests:")
gemm_simple()
gemm_square_weights()
gemm_non_square()
gemm_with_bias()
gemm_transB()
gemm_transpose_b()
gemm_alpha_beta()
gemm_small()
gemm_large()
gemm_transB_with_bias()
gemm_transpose_b_with_bias()
gemm_dynamic()
gemm_dynamic_transB()
gemm_dynamic_transpose_b()
gemm_dynamic_bias()
gemm_dynamic_alpha()
gemm_dynamic_beta()
@@ -2096,8 +2096,8 @@ if __name__ == "__main__":
gemm_huge_1024()
gemm_large_k_small_n()
gemm_small_k_large_n()
gemm_transA()
gemm_transA_transB()
gemm_transpose_a()
gemm_transpose_a_and_b()
gemm_bias_rank2_broadcast()
gemm_scalar_bias()
@@ -2220,7 +2220,7 @@ if __name__ == "__main__":
print("\nGenerating Resize tests:")
resize_nearest_2x()
resize_nearest_non_uniform()
resize_nearest_non_uniform_scales()
resize_with_sizes()
resize_nearest_downsample()
resize_height_only()
+178 -169
View File
@@ -1,169 +1,178 @@
Operation,Result,Compile,Host mem,Cores mem,Cores,Xbars,Latency,Power,Energy
add/after_gemm,PASS,0.063 s,0.01 MiB,0.01 MiB,5,4,SKIP,SKIP,SKIP
add/basic,PASS,0.057 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
add/broadcast_row,PASS,0.057 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
add/channel_broadcast_1024,PASS,0.061 s,0.02 MiB,0.01 MiB,1,0,SKIP,SKIP,SKIP
add/leading_dimension_broadcast,PASS,0.057 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
concat/channel_axis,PASS,0.069 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
concat/negative_axis,PASS,0.061 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
concat/three_inputs_channel_axis,PASS,0.058 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
conv/batch_2,PASS,0.066 s,0.00 MiB,0.00 MiB,2,2,SKIP,SKIP,SKIP
conv/batch_4_pointwise,PASS,0.065 s,0.00 MiB,0.01 MiB,5,4,SKIP,SKIP,SKIP
conv/depthwise_1024_channels,PASS,0.083 s,0.19 MiB,0.38 MiB,129,128,SKIP,SKIP,SKIP
conv/depthwise_grouped,PASS,0.071 s,0.01 MiB,0.00 MiB,5,4,SKIP,SKIP,SKIP
conv/dilated_3x3,PASS,0.068 s,0.01 MiB,0.01 MiB,10,9,SKIP,SKIP,SKIP
conv/dynamic,PASS,0.065 s,0.00 MiB,0.00 MiB,5,0,SKIP,SKIP,SKIP
conv/explicit_padding,PASS,0.062 s,0.01 MiB,0.02 MiB,17,16,SKIP,SKIP,SKIP
conv/grouped_many_groups,PASS,0.442 s,0.05 MiB,0.09 MiB,65,64,SKIP,SKIP,SKIP
conv/grouped_two_groups,PASS,0.060 s,0.00 MiB,0.00 MiB,3,2,SKIP,SKIP,SKIP
conv/huge_pointwise_1024,PASS,0.156 s,0.01 MiB,0.11 MiB,73,64,SKIP,SKIP,SKIP
conv/huge_pointwise_1024_dynamic,PASS,0.079 s,8.04 MiB,12.61 MiB,168,0,SKIP,SKIP,SKIP
conv/kernel_3x3,PASS,0.062 s,0.01 MiB,0.01 MiB,10,9,SKIP,SKIP,SKIP
conv/kernel_equals_input_spatial,PASS,0.064 s,0.00 MiB,0.00 MiB,2,2,SKIP,SKIP,SKIP
conv/large_input_channels_1x1,PASS,0.089 s,0.01 MiB,0.02 MiB,9,8,SKIP,SKIP,SKIP
conv/large_output_channels_1x1,PASS,0.098 s,0.01 MiB,0.02 MiB,17,8,SKIP,SKIP,SKIP
conv/large_spatial,PASS,0.069 s,0.01 MiB,0.04 MiB,37,36,SKIP,SKIP,SKIP
conv/multi_channel,PASS,0.066 s,0.00 MiB,0.00 MiB,4,3,SKIP,SKIP,SKIP
conv/non_square_kernel_1x3,PASS,0.061 s,0.00 MiB,0.00 MiB,3,2,SKIP,SKIP,SKIP
conv/non_square_kernel_3x1,PASS,0.064 s,0.00 MiB,0.00 MiB,3,2,SKIP,SKIP,SKIP
conv/non_uniform_stride,PASS,0.062 s,0.00 MiB,0.00 MiB,4,3,SKIP,SKIP,SKIP
conv/pointwise_1x1,PASS,0.059 s,0.00 MiB,0.00 MiB,1,1,SKIP,SKIP,SKIP
conv/pointwise_tiled_chain,PASS,0.604 s,0.01 MiB,0.04 MiB,20,80,SKIP,SKIP,SKIP
conv/real_asymmetric_padding,PASS,0.060 s,0.01 MiB,0.03 MiB,29,28,SKIP,SKIP,SKIP
conv/relu_conv_store,PASS,0.091 s,0.16 MiB,0.67 MiB,168,184,SKIP,SKIP,SKIP
conv/same_lower_3x3,PASS,0.078 s,0.01 MiB,0.02 MiB,26,25,SKIP,SKIP,SKIP
conv/same_padding_3x3,PASS,0.070 s,0.01 MiB,0.02 MiB,26,25,SKIP,SKIP,SKIP
conv/simple,PASS,0.064 s,0.00 MiB,0.00 MiB,1,1,SKIP,SKIP,SKIP
conv/stride_2,PASS,0.064 s,0.01 MiB,0.00 MiB,5,4,SKIP,SKIP,SKIP
conv/with_bias_3x3,PASS,0.067 s,0.00 MiB,0.01 MiB,4,3,SKIP,SKIP,SKIP
conv/with_constant,PASS,0.070 s,0.00 MiB,0.00 MiB,1,1,SKIP,SKIP,SKIP
conv/without_kernel_shape_attr,PASS,0.069 s,0.01 MiB,0.01 MiB,10,9,SKIP,SKIP,SKIP
conv/yolo11n_depthwise_head,PASS,1.482 s,8.66 MiB,34.24 MiB,168,255,SKIP,SKIP,SKIP
conv/yolo11n_heavy,PASS,0.431 s,4.82 MiB,19.10 MiB,161,800,SKIP,SKIP,SKIP
conv/yolo11n_stem,PASS,0.783 s,12.86 MiB,37.59 MiB,168,488,SKIP,SKIP,SKIP
div/after_gemm,PASS,0.072 s,0.01 MiB,0.01 MiB,5,4,SKIP,SKIP,SKIP
div/basic,PASS,0.061 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
div/channel_broadcast_1024,PASS,0.066 s,0.02 MiB,0.01 MiB,1,0,SKIP,SKIP,SKIP
div/leading_dimension_broadcast,PASS,0.059 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
div/runtime_scalar_rhs,PASS,0.056 s,0.02 MiB,0.01 MiB,1,0,SKIP,SKIP,SKIP
div/scalar_constant,PASS,0.073 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
gather/3d_input_axis1,PASS,0.060 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
gather/axis0_matrix_indices,PASS,0.056 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
gather/axis1,PASS,0.058 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
gather/negative_axis,PASS,0.058 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
gather/negative_indices,PASS,0.063 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
gemm/alpha_beta,PASS,0.067 s,0.01 MiB,0.01 MiB,5,4,SKIP,SKIP,SKIP
gemm/bias_rank2_broadcast,PASS,0.060 s,0.00 MiB,0.01 MiB,5,4,SKIP,SKIP,SKIP
gemm/dynamic,PASS,0.064 s,0.00 MiB,0.00 MiB,5,0,SKIP,SKIP,SKIP
gemm/dynamic_alpha,PASS,0.062 s,0.00 MiB,0.00 MiB,5,0,SKIP,SKIP,SKIP
gemm/dynamic_beta,PASS,0.060 s,0.00 MiB,0.00 MiB,5,0,SKIP,SKIP,SKIP
gemm/dynamic_bias,PASS,0.058 s,0.00 MiB,0.00 MiB,5,0,SKIP,SKIP,SKIP
gemm/dynamic_bias_alpha_beta,PASS,0.067 s,0.00 MiB,0.00 MiB,5,0,SKIP,SKIP,SKIP
gemm/dynamic_transB,PASS,0.062 s,0.00 MiB,0.00 MiB,5,0,SKIP,SKIP,SKIP
gemm/huge_1024,PASS,0.147 s,0.01 MiB,0.10 MiB,73,64,SKIP,SKIP,SKIP
gemm/large,PASS,0.068 s,0.02 MiB,0.03 MiB,17,16,SKIP,SKIP,SKIP
gemm/large_k_small_n,PASS,0.095 s,0.01 MiB,0.01 MiB,9,8,SKIP,SKIP,SKIP
gemm/non_square,PASS,0.063 s,0.00 MiB,0.01 MiB,5,4,SKIP,SKIP,SKIP
gemm/scalar_bias,PASS,0.060 s,0.00 MiB,0.01 MiB,5,4,SKIP,SKIP,SKIP
gemm/simple,PASS,0.072 s,0.03 MiB,0.08 MiB,42,40,SKIP,SKIP,SKIP
gemm/small,PASS,0.065 s,0.00 MiB,0.00 MiB,2,2,SKIP,SKIP,SKIP
gemm/small_k_large_n,PASS,0.097 s,0.01 MiB,0.02 MiB,17,8,SKIP,SKIP,SKIP
gemm/transA,PASS,0.064 s,0.00 MiB,0.01 MiB,5,4,SKIP,SKIP,SKIP
gemm/transA_transB,PASS,0.069 s,0.00 MiB,0.01 MiB,5,4,SKIP,SKIP,SKIP
gemm/transB,PASS,0.062 s,0.00 MiB,0.01 MiB,5,4,SKIP,SKIP,SKIP
gemm/transB_with_bias,PASS,0.055 s,0.01 MiB,0.01 MiB,5,4,SKIP,SKIP,SKIP
gemm/with_bias,PASS,0.067 s,0.01 MiB,0.01 MiB,5,4,SKIP,SKIP,SKIP
gemv/constant,PASS,0.064 s,0.00 MiB,0.00 MiB,0,0,SKIP,SKIP,SKIP
gemv/simple,PASS,0.069 s,0.00 MiB,0.01 MiB,6,4,SKIP,SKIP,SKIP
gemv/with_heterogeneous_constant,PASS,0.066 s,0.00 MiB,0.01 MiB,6,4,SKIP,SKIP,SKIP
gemv/with_homogeneous_constant,PASS,0.070 s,0.00 MiB,0.01 MiB,6,4,SKIP,SKIP,SKIP
gemv/with_scalar_constant,PASS,0.070 s,0.00 MiB,0.01 MiB,6,4,SKIP,SKIP,SKIP
matmul/basic,PASS,0.062 s,0.00 MiB,0.00 MiB,2,2,SKIP,SKIP,SKIP
matmul/batched_3d,PASS,0.066 s,0.00 MiB,0.01 MiB,5,4,SKIP,SKIP,SKIP
matmul/batched_3d_dynamic,PASS,0.057 s,0.00 MiB,0.00 MiB,4,0,SKIP,SKIP,SKIP
matmul/batched_left_constant,PASS,0.070 s,0.00 MiB,0.02 MiB,9,8,SKIP,SKIP,SKIP
matmul/batched_lhs_broadcast,PASS,0.063 s,0.00 MiB,0.01 MiB,5,4,SKIP,SKIP,SKIP
matmul/batched_rhs_broadcast,PASS,0.062 s,0.00 MiB,0.01 MiB,5,4,SKIP,SKIP,SKIP
matmul/dynamic,PASS,0.060 s,0.00 MiB,0.00 MiB,5,0,SKIP,SKIP,SKIP
matmul/huge_1024,PASS,0.145 s,0.01 MiB,0.10 MiB,73,64,SKIP,SKIP,SKIP
matmul/left_constant,PASS,0.051 s,0.00 MiB,0.01 MiB,5,4,SKIP,SKIP,SKIP
matmul/matrix_vector,PASS,0.095 s,0.52 MiB,0.78 MiB,168,173,SKIP,SKIP,SKIP
matmul/vector_matrix,PASS,0.087 s,0.01 MiB,0.01 MiB,9,8,SKIP,SKIP,SKIP
matmul/yolo_attention,PASS,0.385 s,1.02 MiB,43.44 MiB,168,0,SKIP,SKIP,SKIP
mul/after_conv,PASS,0.055 s,0.00 MiB,0.00 MiB,4,3,SKIP,SKIP,SKIP
mul/basic,PASS,0.055 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
mul/channel_broadcast_1024,PASS,0.058 s,0.02 MiB,0.01 MiB,1,0,SKIP,SKIP,SKIP
mul/leading_dimension_broadcast,PASS,0.059 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
mul/scalar_constant,PASS,0.056 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
pool/avg_basic,PASS,0.063 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
pool/avg_ceil_mode,PASS,0.063 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
pool/avg_explicit_padding,PASS,0.061 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
pool/avg_include_pad,PASS,0.049 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
pool/avg_large_channels,PASS,0.059 s,0.04 MiB,0.02 MiB,1,0,SKIP,SKIP,SKIP
pool/avg_non_uniform_stride,PASS,0.066 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
pool/avg_real_asymmetric_padding,PASS,0.055 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
pool/max_after_conv,PASS,0.069 s,0.00 MiB,0.00 MiB,5,4,SKIP,SKIP,SKIP
pool/max_basic,PASS,0.064 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
pool/max_ceil_mode,PASS,0.058 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
pool/max_global_style_kernel_equals_input,PASS,0.063 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
pool/max_non_square_kernel,PASS,0.067 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
pool/max_real_asymmetric_padding,PASS,0.063 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
pool/max_same_upper,PASS,0.061 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
pool/max_stride2_multichannel,PASS,0.076 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
reduce_mean/4d_spatial,PASS,0.058 s,0.00 MiB,0.00 MiB,3,0,SKIP,SKIP,SKIP
reduce_mean/4d_spatial_keepdims_0,PASS,0.068 s,0.00 MiB,0.00 MiB,4,0,SKIP,SKIP,SKIP
reduce_mean/after_conv,PASS,0.067 s,0.00 MiB,0.00 MiB,5,3,SKIP,SKIP,SKIP
reduce_mean/all_axes_keepdims_0,PASS,0.057 s,0.00 MiB,0.00 MiB,2,0,SKIP,SKIP,SKIP
reduce_mean/all_axes_keepdims_1,PASS,0.053 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
reduce_mean/basic,PASS,0.058 s,0.00 MiB,0.00 MiB,4,0,SKIP,SKIP,SKIP
reduce_mean/channel_axis_nchw,PASS,0.063 s,0.03 MiB,0.02 MiB,4,0,SKIP,SKIP,SKIP
reduce_mean/keepdims_0,PASS,0.064 s,0.00 MiB,0.00 MiB,5,0,SKIP,SKIP,SKIP
reduce_mean/large_dimension_1024,PASS,0.066 s,0.01 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
reduce_mean/legacy_axes_1_2_keepdims_1,PASS,0.069 s,0.00 MiB,0.00 MiB,2,0,SKIP,SKIP,SKIP
reduce_mean/legacy_axis1_keepdims_0,PASS,0.067 s,0.00 MiB,0.00 MiB,9,0,SKIP,SKIP,SKIP
reduce_mean/legacy_axis1_keepdims_1,PASS,0.057 s,0.00 MiB,0.00 MiB,8,0,SKIP,SKIP,SKIP
reduce_mean/legacy_empty_axes_noop,PASS,0.058 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
reduce_mean/legacy_nchw_spatial,PASS,0.059 s,0.00 MiB,0.00 MiB,3,0,SKIP,SKIP,SKIP
reduce_mean/legacy_negative_axis,PASS,0.052 s,0.00 MiB,0.00 MiB,6,0,SKIP,SKIP,SKIP
reduce_mean/legacy_reduce_all_keepdims_1,PASS,0.057 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
reduce_mean/negative_axis,PASS,0.055 s,0.00 MiB,0.00 MiB,6,0,SKIP,SKIP,SKIP
relu/4d,PASS,0.059 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
relu/after_conv,PASS,0.062 s,0.00 MiB,0.00 MiB,4,3,SKIP,SKIP,SKIP
relu/after_gemm,PASS,0.062 s,0.01 MiB,0.01 MiB,5,4,SKIP,SKIP,SKIP
relu/basic,PASS,0.062 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
reshape/4d_to_2d_flatten,PASS,0.059 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
reshape/infer_dim_minus_one,PASS,0.059 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
reshape/same_rank,PASS,0.056 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
reshape/zero_copies_input_dim,PASS,0.077 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
resize/height_only,PASS,0.059 s,0.00 MiB,0.00 MiB,4,0,SKIP,SKIP,SKIP
resize/nearest_2x,PASS,0.066 s,0.00 MiB,0.00 MiB,4,0,SKIP,SKIP,SKIP
resize/nearest_downsample,PASS,0.062 s,0.00 MiB,0.00 MiB,2,0,SKIP,SKIP,SKIP
resize/non_uniform,PASS,0.069 s,0.00 MiB,0.00 MiB,6,0,SKIP,SKIP,SKIP
resize/width_only,PASS,0.055 s,0.00 MiB,0.00 MiB,2,0,SKIP,SKIP,SKIP
resize/with_sizes,PASS,0.060 s,0.00 MiB,0.00 MiB,3,0,SKIP,SKIP,SKIP
sigmoid/4d,PASS,0.060 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
sigmoid/after_gemm,PASS,0.059 s,0.01 MiB,0.01 MiB,5,4,SKIP,SKIP,SKIP
sigmoid/basic,PASS,0.053 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
slice/2d_basic,PASS,0.058 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
slice/after_conv,PASS,0.070 s,0.00 MiB,0.01 MiB,7,6,SKIP,SKIP,SKIP
slice/default_axes,PASS,0.066 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
slice/large_channel_1024,PASS,0.064 s,0.01 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
slice/nchw_spatial_crop,PASS,0.055 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
slice/negative_axis,PASS,0.060 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
slice/negative_indices,PASS,0.053 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
slice/step2,PASS,0.058 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
softmax/3d_last_axis,PASS,0.050 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
softmax/basic,PASS,0.061 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
softmax/channel_axis,PASS,0.058 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
softmax/large_dimension_1024,PASS,0.061 s,0.01 MiB,0.01 MiB,1,0,SKIP,SKIP,SKIP
softmax/negative_axis,PASS,0.058 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
split/basic,PASS,0.059 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
split/equal_three_way,PASS,0.063 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
split/negative_axis,PASS,0.059 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
split/uneven_channel_axis_4d,PASS,0.061 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
sub/after_gemm,PASS,0.064 s,0.01 MiB,0.01 MiB,5,4,SKIP,SKIP,SKIP
sub/basic,PASS,0.054 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
sub/broadcast_row,PASS,0.064 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
sub/channel_broadcast_1024,PASS,0.063 s,0.02 MiB,0.01 MiB,1,0,SKIP,SKIP,SKIP
sub/constant_lhs_broadcast,PASS,0.054 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
sub/leading_dimension_broadcast,PASS,0.054 s,0.00 MiB,0.00 MiB,1,0,SKIP,SKIP,SKIP
Operation,Arch,Result (l),Result (t),Compile (l),Host mem (l),Cores mem (l),Cores (l),Xbars (l),Latency (l),Power (l),Energy (l),Compile (t),Host mem (t),Cores mem (t),Cores (t),Xbars (t),Avg latency (t),Throughput (t),Avg power (t),Avg energy (t)
add/after_gemm,arch-a,PASS,FAIL,0.057 s,0.01 MiB,0.01 MiB,5,4,0.01 ms,104.70 mW,815012.96 pJ,0.055 s,0.01 MiB,0.01 MiB,6,4,277000.00 samples/s,0.00 ms,45.81 mW,190085.16 pJ/it
add/basic,arch-a,PASS,PASS,0.047 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,25266.00 pJ,0.048 s,0.00 MiB,0.00 MiB,1,0,3120000.00 samples/s,0.00 ms,2.23 mW,658.67 pJ/it
add/broadcast_row,arch-a,PASS,PASS,0.049 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,25266.00 pJ,0.049 s,0.00 MiB,0.00 MiB,1,0,3120000.00 samples/s,0.00 ms,2.23 mW,658.67 pJ/it
add/channel_broadcast_1024,arch-a,PASS,PASS,0.048 s,0.02 MiB,0.01 MiB,1,0,0.01 ms,78.12 mW,540030.00 pJ,0.048 s,0.02 MiB,0.01 MiB,1,0,145000.00 samples/s,0.01 ms,2.11 mW,13388.67 pJ/it
add/leading_dimension_broadcast,arch-a,PASS,PASS,0.052 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,25266.00 pJ,0.048 s,0.00 MiB,0.00 MiB,1,0,3120000.00 samples/s,0.00 ms,2.23 mW,658.67 pJ/it
concat/channel_axis,arch-a,PASS,PASS,0.053 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.16 mW,35718.00 pJ,0.047 s,0.00 MiB,0.00 MiB,1,0,2200000.00 samples/s,0.00 ms,2.16 mW,934.67 pJ/it
concat/negative_axis,arch-a,PASS,PASS,0.047 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.09 mW,81450.00 pJ,0.049 s,0.00 MiB,0.00 MiB,1,0,961000.00 samples/s,0.00 ms,2.09 mW,2108.00 pJ/it
concat/three_inputs_channel_axis,arch-a,PASS,PASS,0.049 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.15 mW,50328.00 pJ,0.045 s,0.00 MiB,0.00 MiB,1,0,1560000.00 samples/s,0.00 ms,2.15 mW,1332.67 pJ/it
conv/batch_2,arch-a,PASS,PASS,0.058 s,0.00 MiB,0.00 MiB,2,2,0.01 ms,82.62 mW,1131451.48 pJ,0.057 s,0.00 MiB,0.01 MiB,4,2,168000.00 samples/s,0.01 ms,53.33 mW,343254.69 pJ/it
conv/batch_4_pointwise,arch-a,PASS,FAIL,0.055 s,0.00 MiB,0.01 MiB,5,4,0.00 ms,116.08 mW,456420.96 pJ,0.060 s,0.00 MiB,0.01 MiB,5,4,486000.00 samples/s,0.00 ms,70.89 mW,160104.45 pJ/it
conv/depthwise_1024_channels,arch-a,PASS,FAIL,0.081 s,0.19 MiB,0.38 MiB,129,128,0.22 ms,178.45 mW,39393966.72 pJ,-,-,-,-,-,-,-,-,-
conv/depthwise_grouped,arch-a,PASS,FAIL,0.055 s,0.01 MiB,0.00 MiB,5,4,0.01 ms,107.78 mW,671878.96 pJ,-,-,-,-,-,-,-,-,-
conv/dilated_3x3,arch-a,PASS,PASS,0.060 s,0.01 MiB,0.01 MiB,10,9,0.01 ms,118.77 mW,1034819.16 pJ,0.067 s,0.01 MiB,0.01 MiB,12,9,189000.00 samples/s,0.01 ms,75.03 mW,435165.28 pJ/it
conv/dynamic,arch-a,PASS,FAIL,0.056 s,0.00 MiB,0.00 MiB,5,0,0.00 ms,92.28 mW,169336.00 pJ,0.057 s,0.00 MiB,0.00 MiB,6,0,661000.00 samples/s,0.00 ms,18.68 mW,30964.00 pJ/it
conv/explicit_padding,arch-a,PASS,FAIL,0.062 s,0.01 MiB,0.02 MiB,17,16,0.01 ms,145.34 mW,1454397.84 pJ,-,-,-,-,-,-,-,-,-
conv/grouped_many_groups,arch-a,PASS,FAIL,0.486 s,0.05 MiB,0.09 MiB,65,64,0.18 ms,142.21 mW,25867112.36 pJ,0.500 s,0.11 MiB,0.79 MiB,127,64,569.00 samples/s,1.76 ms,141.19 mW,252570125.00 pJ/it
conv/grouped_two_groups,arch-a,PASS,FAIL,0.063 s,0.00 MiB,0.00 MiB,3,2,0.01 ms,101.46 mW,543914.48 pJ,0.061 s,0.00 MiB,0.01 MiB,9,2,327000.00 samples/s,0.00 ms,116.36 mW,453237.70 pJ/it
conv/huge_pointwise_1024,arch-a,PASS,FAIL,0.160 s,0.01 MiB,0.11 MiB,73,64,0.02 ms,249.55 mW,3896647.36 pJ,0.176 s,0.04 MiB,0.11 MiB,74,64,35300.00 samples/s,0.03 ms,136.81 mW,4031965.75 pJ/it
conv/huge_pointwise_1024_dynamic,arch-a,PASS,FAIL,0.101 s,8.04 MiB,12.61 MiB,168,0,2.63 ms,169.52 mW,445489032.00 pJ,-,-,-,-,-,-,-,-,-
conv/input_224_7x7_stride2,arch-a,PASS,FAIL,1.124 s,24.14 MiB,61.87 MiB,168,169,38.41 ms,185.26 mW,7116544212.12 pJ,-,-,-,-,-,-,-,-,-
conv/kernel_2x2,arch-a,PASS,FAIL,0.064 s,0.00 MiB,0.00 MiB,1,1,0.00 ms,83.83 mW,360568.24 pJ,0.099 s,0.00 MiB,0.00 MiB,3,1,380000.00 samples/s,0.00 ms,52.64 mW,151421.99 pJ/it
conv/kernel_3x3,arch-a,PASS,FAIL,0.057 s,0.01 MiB,0.01 MiB,10,9,0.01 ms,123.80 mW,889640.16 pJ,-,-,-,-,-,-,-,-,-
conv/kernel_equals_input_spatial,arch-a,PASS,PASS,0.056 s,0.00 MiB,0.00 MiB,2,2,0.00 ms,89.61 mW,415689.48 pJ,0.059 s,0.00 MiB,0.00 MiB,4,2,464000.00 samples/s,0.00 ms,68.91 mW,166273.89 pJ/it
conv/large_input_channels_1x1,arch-a,PASS,PASS,0.087 s,0.01 MiB,0.02 MiB,9,8,0.01 ms,117.82 mW,901121.92 pJ,0.087 s,0.01 MiB,0.02 MiB,10,8,306000.00 samples/s,0.00 ms,91.39 mW,360779.57 pJ/it
conv/large_output_channels_1x1,arch-a,PASS,PASS,0.088 s,0.01 MiB,0.02 MiB,17,8,0.01 ms,128.44 mW,1139415.92 pJ,0.089 s,0.01 MiB,0.02 MiB,18,8,207000.00 samples/s,0.00 ms,73.39 mW,358350.06 pJ/it
conv/large_spatial,arch-a,PASS,FAIL,0.060 s,0.01 MiB,0.04 MiB,37,36,0.02 ms,172.07 mW,2928344.64 pJ,-,-,-,-,-,-,-,-,-
conv/multi_channel,arch-a,PASS,FAIL,0.056 s,0.00 MiB,0.00 MiB,4,3,0.01 ms,105.68 mW,685040.72 pJ,0.057 s,0.00 MiB,0.00 MiB,4,3,178000.00 samples/s,0.01 ms,32.10 mW,185757.05 pJ/it
conv/non_square_kernel_1x3,arch-a,PASS,PASS,0.066 s,0.00 MiB,0.00 MiB,3,2,0.01 ms,99.35 mW,679752.48 pJ,0.054 s,0.00 MiB,0.00 MiB,3,2,163000.00 samples/s,0.01 ms,13.04 mW,81630.31 pJ/it
conv/non_square_kernel_3x1,arch-a,PASS,PASS,0.060 s,0.00 MiB,0.00 MiB,3,2,0.01 ms,95.89 mW,1292976.48 pJ,0.065 s,0.00 MiB,0.00 MiB,3,2,77500.00 samples/s,0.01 ms,9.04 mW,117499.65 pJ/it
conv/non_uniform_stride,arch-a,PASS,FAIL,0.056 s,0.00 MiB,0.00 MiB,4,3,0.01 ms,104.05 mW,790874.72 pJ,0.056 s,0.00 MiB,0.00 MiB,4,3,161000.00 samples/s,0.01 ms,30.89 mW,198689.55 pJ/it
conv/output_channel_grouping_minimal,arch-a,PASS,FAIL,0.083 s,0.10 MiB,0.34 MiB,131,128,0.26 ms,170.73 mW,44125916.72 pJ,-,-,-,-,-,-,-,-,-
conv/pointwise_1x1,arch-a,PASS,FAIL,0.052 s,0.00 MiB,0.00 MiB,1,1,0.01 ms,80.24 mW,987244.24 pJ,0.055 s,0.00 MiB,0.00 MiB,3,1,135000.00 samples/s,0.01 ms,47.15 mW,371973.57 pJ/it
conv/pointwise_tiled_chain,arch-a,PASS,PASS,0.699 s,0.01 MiB,0.04 MiB,20,80,0.04 ms,153.88 mW,6445455.20 pJ,0.634 s,0.05 MiB,0.08 MiB,22,80,14300.00 samples/s,0.07 ms,71.96 mW,5297594.20 pJ/it
conv/real_asymmetric_padding,arch-a,PASS,FAIL,0.063 s,0.01 MiB,0.03 MiB,29,28,0.01 ms,153.67 mW,2221606.72 pJ,-,-,-,-,-,-,-,-,-
conv/relu_conv_store,arch-a,PASS,FAIL,0.094 s,0.16 MiB,0.67 MiB,168,184,0.56 ms,183.08 mW,103057892.80 pJ,-,-,-,-,-,-,-,-,-
conv/same_lower_3x3,arch-a,PASS,FAIL,0.061 s,0.01 MiB,0.02 MiB,26,25,0.01 ms,166.15 mW,2215009.00 pJ,-,-,-,-,-,-,-,-,-
conv/same_padding_3x3,arch-a,PASS,FAIL,0.059 s,0.01 MiB,0.02 MiB,26,25,0.01 ms,166.15 mW,2215009.00 pJ,-,-,-,-,-,-,-,-,-
conv/strategy_depthwise_16,arch-a,PASS,FAIL,0.092 s,0.06 MiB,0.35 MiB,168,168,0.34 ms,197.94 mW,66331479.08 pJ,-,-,-,-,-,-,-,-,-
conv/strategy_input_k_tiled,arch-a,PASS,FAIL,0.084 s,0.08 MiB,0.27 MiB,109,108,0.35 ms,170.81 mW,60422605.92 pJ,-,-,-,-,-,-,-,-,-
conv/strategy_output_channel_tiled,arch-a,PASS,FAIL,0.071 s,0.03 MiB,0.16 MiB,74,72,0.09 ms,155.74 mW,14244739.28 pJ,-,-,-,-,-,-,-,-,-
conv/strategy_streamed_packed,arch-a,PASS,FAIL,0.184 s,3.34 MiB,7.89 MiB,168,168,9.35 ms,179.86 mW,1682364509.56 pJ,-,-,-,-,-,-,-,-,-
conv/strategy_streamed_patch,arch-a,PASS,FAIL,0.098 s,0.34 MiB,1.32 MiB,168,168,1.90 ms,181.91 mW,346476645.64 pJ,-,-,-,-,-,-,-,-,-
conv/strategy_tiled_2d,arch-a,PASS,FAIL,0.117 s,0.11 MiB,0.44 MiB,168,168,0.42 ms,182.13 mW,75690907.84 pJ,-,-,-,-,-,-,-,-,-
conv/stride_2,arch-a,PASS,FAIL,0.059 s,0.01 MiB,0.00 MiB,5,4,0.01 ms,110.78 mW,580154.96 pJ,-,-,-,-,-,-,-,-,-
conv/with_bias_3x3,arch-a,PASS,FAIL,0.057 s,0.00 MiB,0.01 MiB,4,3,0.01 ms,104.16 mW,776220.72 pJ,0.057 s,0.00 MiB,0.01 MiB,4,3,165000.00 samples/s,0.01 ms,30.99 mW,196092.89 pJ/it
conv/with_constant,arch-a,PASS,FAIL,0.057 s,0.00 MiB,0.00 MiB,1,1,0.01 ms,81.74 mW,541270.24 pJ,0.059 s,0.00 MiB,0.00 MiB,4,1,232000.00 samples/s,0.00 ms,92.34 mW,438607.24 pJ/it
conv/without_kernel_shape_attr,arch-a,PASS,FAIL,0.055 s,0.01 MiB,0.01 MiB,10,9,0.01 ms,123.80 mW,889640.16 pJ,-,-,-,-,-,-,-,-,-
conv/yolo11n_depthwise_head,arch-a,PASS,FAIL,2.274 s,8.66 MiB,34.24 MiB,168,255,42.70 ms,200.52 mW,8562449708.00 pJ,-,-,-,-,-,-,-,-,-
conv/yolo11n_heavy,arch-a,PASS,FAIL,0.478 s,4.82 MiB,19.10 MiB,161,800,8.54 ms,350.86 mW,2994764012.00 pJ,-,-,-,-,-,-,-,-,-
conv/yolo11n_stem,arch-a,PASS,FAIL,0.975 s,12.86 MiB,37.59 MiB,168,488,14.24 ms,301.23 mW,4289558753.00 pJ,-,-,-,-,-,-,-,-,-
div/after_gemm,arch-a,PASS,FAIL,0.056 s,0.01 MiB,0.01 MiB,5,4,0.01 ms,104.70 mW,815012.96 pJ,0.056 s,0.01 MiB,0.01 MiB,6,4,277000.00 samples/s,0.00 ms,45.81 mW,190085.16 pJ/it
div/basic,arch-a,PASS,PASS,0.049 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,25266.00 pJ,0.050 s,0.00 MiB,0.00 MiB,1,0,3120000.00 samples/s,0.00 ms,2.23 mW,658.67 pJ/it
div/channel_broadcast_1024,arch-a,PASS,PASS,0.051 s,0.02 MiB,0.01 MiB,1,0,0.01 ms,78.12 mW,540030.00 pJ,0.055 s,0.02 MiB,0.01 MiB,1,0,145000.00 samples/s,0.01 ms,2.11 mW,13388.67 pJ/it
div/leading_dimension_broadcast,arch-a,PASS,PASS,0.053 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,25266.00 pJ,0.052 s,0.00 MiB,0.00 MiB,1,0,3120000.00 samples/s,0.00 ms,2.23 mW,658.67 pJ/it
div/runtime_scalar_rhs,arch-a,PASS,PASS,0.048 s,0.02 MiB,0.01 MiB,1,0,0.01 ms,78.12 mW,540030.00 pJ,0.051 s,0.02 MiB,0.01 MiB,1,0,145000.00 samples/s,0.01 ms,2.11 mW,13388.67 pJ/it
div/scalar_constant,arch-a,PASS,PASS,0.057 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,25266.00 pJ,0.059 s,0.00 MiB,0.00 MiB,1,0,3120000.00 samples/s,0.00 ms,2.23 mW,658.67 pJ/it
gather/3d_input_axis1,arch-a,PASS,PASS,0.052 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.08 mW,45990.00 pJ,0.053 s,0.00 MiB,0.00 MiB,1,0,1700000.00 samples/s,0.00 ms,2.08 mW,1174.67 pJ/it
gather/axis0_matrix_indices,arch-a,PASS,PASS,0.055 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.07 mW,54414.00 pJ,0.052 s,0.00 MiB,0.00 MiB,1,0,1440000.00 samples/s,0.00 ms,2.07 mW,1390.67 pJ/it
gather/axis1,arch-a,PASS,PASS,0.051 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.06 mW,62526.00 pJ,0.053 s,0.00 MiB,0.00 MiB,1,0,1250000.00 samples/s,0.00 ms,2.06 mW,1598.67 pJ/it
gather/negative_axis,arch-a,PASS,PASS,0.049 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.03 mW,112134.00 pJ,0.051 s,0.00 MiB,0.00 MiB,1,0,697000.00 samples/s,0.00 ms,2.03 mW,2870.67 pJ/it
gather/negative_indices,arch-a,PASS,PASS,0.052 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.13 mW,29376.00 pJ,0.058 s,0.00 MiB,0.00 MiB,1,0,2670000.00 samples/s,0.00 ms,2.12 mW,748.67 pJ/it
gemm/alpha_beta,arch-a,PASS,FAIL,0.059 s,0.01 MiB,0.01 MiB,5,4,0.01 ms,105.27 mW,784908.96 pJ,0.061 s,0.01 MiB,0.01 MiB,6,4,304000.00 samples/s,0.00 ms,48.12 mW,184972.16 pJ/it
gemm/bias_rank2_broadcast,arch-a,PASS,FAIL,0.061 s,0.00 MiB,0.01 MiB,5,4,0.01 ms,105.98 mW,749484.96 pJ,0.058 s,0.01 MiB,0.01 MiB,6,4,351000.00 samples/s,0.00 ms,52.58 mW,176636.66 pJ/it
gemm/dynamic,arch-a,PASS,FAIL,0.053 s,0.00 MiB,0.00 MiB,5,0,0.00 ms,91.48 mW,221475.00 pJ,0.056 s,0.00 MiB,0.00 MiB,5,0,785000.00 samples/s,0.00 ms,20.31 mW,27813.50 pJ/it
gemm/dynamic_alpha,arch-a,PASS,FAIL,0.055 s,0.00 MiB,0.00 MiB,5,0,0.00 ms,91.42 mW,298198.00 pJ,0.056 s,0.00 MiB,0.00 MiB,5,0,612000.00 samples/s,0.00 ms,20.35 mW,37289.67 pJ/it
gemm/dynamic_beta,arch-a,PASS,FAIL,0.056 s,0.00 MiB,0.00 MiB,5,0,0.00 ms,91.32 mW,398595.00 pJ,0.056 s,0.00 MiB,0.00 MiB,5,0,359000.00 samples/s,0.00 ms,20.22 mW,60212.83 pJ/it
gemm/dynamic_bias,arch-a,PASS,FAIL,0.055 s,0.00 MiB,0.00 MiB,5,0,0.00 ms,91.45 mW,243703.00 pJ,0.055 s,0.00 MiB,0.00 MiB,5,0,785000.00 samples/s,0.00 ms,20.32 mW,28385.00 pJ/it
gemm/dynamic_bias_alpha_beta,arch-a,PASS,FAIL,0.055 s,0.00 MiB,0.00 MiB,5,0,0.01 ms,91.28 mW,513811.00 pJ,0.056 s,0.00 MiB,0.00 MiB,5,0,247000.00 samples/s,0.00 ms,20.20 mW,85611.50 pJ/it
gemm/dynamic_transpose_b,arch-a,PASS,FAIL,0.053 s,0.00 MiB,0.00 MiB,5,0,0.00 ms,91.38 mW,118883.00 pJ,0.055 s,0.00 MiB,0.00 MiB,5,0,1340000.00 samples/s,0.00 ms,20.55 mW,16541.00 pJ/it
gemm/huge_1024,arch-a,PASS,FAIL,0.144 s,0.01 MiB,0.10 MiB,73,64,0.02 ms,215.04 mW,3767885.36 pJ,0.167 s,0.03 MiB,0.10 MiB,73,64,14900.00 samples/s,0.07 ms,154.31 mW,10866697.65 pJ/it
gemm/large,arch-a,PASS,FAIL,0.058 s,0.02 MiB,0.03 MiB,17,16,0.01 ms,140.15 mW,1573768.84 pJ,0.063 s,0.02 MiB,0.03 MiB,17,16,142000.00 samples/s,0.01 ms,118.27 mW,830693.99 pJ/it
gemm/large_k_small_n,arch-a,PASS,FAIL,0.084 s,0.01 MiB,0.01 MiB,9,8,0.00 ms,133.48 mW,633769.92 pJ,0.089 s,0.01 MiB,0.01 MiB,9,8,439000.00 samples/s,0.00 ms,125.25 mW,329671.91 pJ/it
gemm/non_square,arch-a,PASS,FAIL,0.060 s,0.00 MiB,0.01 MiB,5,4,0.00 ms,118.96 mW,419565.96 pJ,0.060 s,0.00 MiB,0.01 MiB,5,4,486000.00 samples/s,0.00 ms,70.69 mW,160313.79 pJ/it
gemm/scalar_bias,arch-a,PASS,FAIL,0.059 s,0.00 MiB,0.01 MiB,5,4,0.01 ms,105.98 mW,749484.96 pJ,0.056 s,0.01 MiB,0.01 MiB,6,4,351000.00 samples/s,0.00 ms,52.58 mW,176636.66 pJ/it
gemm/small,arch-a,PASS,PASS,0.056 s,0.00 MiB,0.00 MiB,2,2,0.00 ms,90.14 mW,398436.48 pJ,0.055 s,0.00 MiB,0.00 MiB,4,2,464000.00 samples/s,0.00 ms,69.74 mW,162693.89 pJ/it
gemm/small_k_large_n,arch-a,PASS,PASS,0.092 s,0.01 MiB,0.02 MiB,17,8,0.01 ms,131.01 mW,1043061.92 pJ,0.089 s,0.01 MiB,0.02 MiB,18,8,248000.00 samples/s,0.00 ms,82.00 mW,345641.89 pJ/it
gemm/square_weights,arch-a,PASS,FAIL,0.076 s,0.03 MiB,0.08 MiB,42,40,0.02 ms,151.77 mW,3284393.60 pJ,-,-,-,-,-,-,-,-,-
gemm/transpose_a,arch-a,PASS,FAIL,0.056 s,0.00 MiB,0.01 MiB,5,4,0.01 ms,109.14 mW,628868.96 pJ,0.057 s,0.00 MiB,0.01 MiB,6,4,424000.00 samples/s,0.00 ms,58.98 mW,162091.12 pJ/it
gemm/transpose_a_and_b,arch-a,PASS,FAIL,0.055 s,0.00 MiB,0.01 MiB,5,4,0.01 ms,109.14 mW,628868.96 pJ,0.056 s,0.00 MiB,0.01 MiB,6,4,424000.00 samples/s,0.00 ms,58.98 mW,162091.12 pJ/it
gemm/transpose_b,arch-a,PASS,FAIL,0.061 s,0.00 MiB,0.01 MiB,5,4,0.00 ms,118.96 mW,419565.96 pJ,0.059 s,0.00 MiB,0.01 MiB,5,4,486000.00 samples/s,0.00 ms,70.69 mW,160313.79 pJ/it
gemm/transpose_b_with_bias,arch-a,PASS,FAIL,0.064 s,0.01 MiB,0.01 MiB,5,4,0.01 ms,110.55 mW,557818.96 pJ,0.057 s,0.01 MiB,0.01 MiB,5,4,339000.00 samples/s,0.00 ms,55.18 mW,180359.12 pJ/it
gemm/with_bias,arch-a,PASS,FAIL,0.050 s,0.01 MiB,0.01 MiB,5,4,0.01 ms,108.77 mW,604966.96 pJ,0.055 s,0.01 MiB,0.01 MiB,5,4,288000.00 samples/s,0.00 ms,52.44 mW,186098.45 pJ/it
gemv/all_constant,arch-a,PASS,PASS,0.050 s,0.00 MiB,0.00 MiB,0,0,0.00 ms,2.00 mW,0.00 pJ,0.052 s,0.00 MiB,0.00 MiB,0,0,0.00 samples/s,0.00 ms,2.00 mW,0.00 pJ/it
gemv/constant_weight,arch-a,PASS,FAIL,0.062 s,0.00 MiB,0.01 MiB,6,4,0.01 ms,111.15 mW,573535.96 pJ,0.063 s,0.00 MiB,0.01 MiB,8,4,412000.00 samples/s,0.00 ms,86.05 mW,242243.79 pJ/it
gemv/non_uniform_bias,arch-a,PASS,FAIL,0.063 s,0.00 MiB,0.01 MiB,6,4,0.01 ms,109.82 mW,609371.96 pJ,0.063 s,0.00 MiB,0.01 MiB,8,4,376000.00 samples/s,0.00 ms,82.45 mW,254539.29 pJ/it
gemv/scalar_bias,arch-a,PASS,FAIL,0.063 s,0.00 MiB,0.01 MiB,6,4,0.01 ms,109.82 mW,609371.96 pJ,0.064 s,0.00 MiB,0.01 MiB,8,4,376000.00 samples/s,0.00 ms,82.45 mW,254539.29 pJ/it
gemv/uniform_bias,arch-a,PASS,FAIL,0.064 s,0.00 MiB,0.01 MiB,6,4,0.01 ms,109.82 mW,609371.96 pJ,0.063 s,0.00 MiB,0.01 MiB,8,4,376000.00 samples/s,0.00 ms,82.45 mW,254539.29 pJ/it
matmul/basic,arch-a,PASS,PASS,0.057 s,0.00 MiB,0.00 MiB,2,2,0.00 ms,90.14 mW,398436.48 pJ,0.056 s,0.00 MiB,0.00 MiB,4,2,464000.00 samples/s,0.00 ms,69.74 mW,162693.89 pJ/it
matmul/batched_3d,arch-a,PASS,FAIL,0.058 s,0.00 MiB,0.01 MiB,5,4,0.01 ms,108.59 mW,646972.96 pJ,0.059 s,0.00 MiB,0.01 MiB,6,4,438000.00 samples/s,0.00 ms,59.21 mW,161865.62 pJ/it
matmul/batched_3d_dynamic,arch-a,PASS,PASS,0.054 s,0.00 MiB,0.00 MiB,4,0,0.00 ms,92.19 mW,167975.00 pJ,0.054 s,0.00 MiB,0.00 MiB,5,0,1140000.00 samples/s,0.00 ms,17.43 mW,16336.83 pJ/it
matmul/batched_left_constant,arch-a,PASS,FAIL,0.061 s,0.00 MiB,0.02 MiB,9,8,0.01 ms,114.39 mW,1009105.92 pJ,-,-,-,-,-,-,-,-,-
matmul/batched_lhs_broadcast,arch-a,PASS,FAIL,0.057 s,0.00 MiB,0.01 MiB,5,4,0.01 ms,109.39 mW,621440.96 pJ,0.071 s,0.00 MiB,0.01 MiB,6,4,441000.00 samples/s,0.00 ms,60.34 mW,160658.62 pJ/it
matmul/batched_rhs_broadcast,arch-a,PASS,FAIL,0.056 s,0.00 MiB,0.01 MiB,5,4,0.01 ms,108.59 mW,646972.96 pJ,0.056 s,0.00 MiB,0.01 MiB,6,4,438000.00 samples/s,0.00 ms,59.21 mW,161865.62 pJ/it
matmul/dynamic,arch-a,PASS,FAIL,0.055 s,0.00 MiB,0.00 MiB,5,0,0.00 ms,91.42 mW,148195.00 pJ,0.058 s,0.00 MiB,0.00 MiB,5,0,1310000.00 samples/s,0.00 ms,20.49 mW,18009.67 pJ/it
matmul/huge_1024,arch-a,PASS,FAIL,0.151 s,0.01 MiB,0.10 MiB,73,64,0.02 ms,215.04 mW,3767885.36 pJ,0.172 s,0.03 MiB,0.10 MiB,73,64,14900.00 samples/s,0.07 ms,154.31 mW,10866697.65 pJ/it
matmul/left_constant,arch-a,PASS,FAIL,0.058 s,0.00 MiB,0.01 MiB,5,4,0.01 ms,108.86 mW,637168.96 pJ,0.064 s,0.00 MiB,0.01 MiB,6,4,424000.00 samples/s,0.00 ms,58.67 mW,162346.12 pJ/it
matmul/matrix_vector,arch-a,PASS,FAIL,0.102 s,0.52 MiB,0.78 MiB,168,173,0.38 ms,202.13 mW,77751814.88 pJ,-,-,-,-,-,-,-,-,-
matmul/vector_matrix,arch-a,PASS,FAIL,0.085 s,0.01 MiB,0.01 MiB,9,8,0.01 ms,118.68 mW,879301.92 pJ,-,-,-,-,-,-,-,-,-
matmul/yolo_attention,arch-a,PASS,FAIL,0.483 s,1.02 MiB,43.44 MiB,168,0,8.15 ms,170.00 mW,1385775865.00 pJ,-,-,-,-,-,-,-,-,-
mul/after_conv,arch-a,PASS,FAIL,0.074 s,0.00 MiB,0.00 MiB,4,3,0.01 ms,107.64 mW,586955.72 pJ,0.062 s,0.00 MiB,0.00 MiB,4,3,220000.00 samples/s,0.00 ms,34.96 mW,162998.05 pJ/it
mul/after_conv_scalar_constant,arch-a,PASS,FAIL,0.063 s,0.00 MiB,0.00 MiB,4,3,0.01 ms,107.64 mW,586955.72 pJ,0.061 s,0.00 MiB,0.00 MiB,4,3,220000.00 samples/s,0.00 ms,34.96 mW,162998.05 pJ/it
mul/basic,arch-a,PASS,PASS,0.055 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,25266.00 pJ,0.052 s,0.00 MiB,0.00 MiB,1,0,3120000.00 samples/s,0.00 ms,2.23 mW,658.67 pJ/it
mul/channel_broadcast_1024,arch-a,PASS,PASS,0.049 s,0.02 MiB,0.01 MiB,1,0,0.01 ms,78.12 mW,540030.00 pJ,0.049 s,0.02 MiB,0.01 MiB,1,0,145000.00 samples/s,0.01 ms,2.11 mW,13388.67 pJ/it
mul/leading_dimension_broadcast,arch-a,PASS,PASS,0.052 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,25266.00 pJ,0.053 s,0.00 MiB,0.00 MiB,1,0,3120000.00 samples/s,0.00 ms,2.23 mW,658.67 pJ/it
mul/scalar_constant,arch-a,PASS,PASS,0.055 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,25266.00 pJ,0.051 s,0.00 MiB,0.00 MiB,1,0,3120000.00 samples/s,0.00 ms,2.23 mW,658.67 pJ/it
pool/avg_basic,arch-a,PASS,PASS,0.057 s,0.00 MiB,0.00 MiB,1,0,0.01 ms,78.02 mW,931506.00 pJ,0.052 s,0.00 MiB,0.00 MiB,1,0,84000.00 samples/s,0.01 ms,2.02 mW,24067.00 pJ/it
pool/avg_ceil_mode,arch-a,PASS,PASS,0.055 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.03 mW,340146.00 pJ,0.055 s,0.00 MiB,0.00 MiB,1,0,230000.00 samples/s,0.00 ms,2.03 mW,8810.67 pJ/it
pool/avg_explicit_padding,arch-a,PASS,PASS,0.056 s,0.00 MiB,0.00 MiB,1,0,0.01 ms,78.03 mW,688356.00 pJ,0.058 s,0.00 MiB,0.00 MiB,1,0,114000.00 samples/s,0.01 ms,2.03 mW,17809.00 pJ/it
pool/avg_include_pad,arch-a,PASS,PASS,0.056 s,0.00 MiB,0.00 MiB,1,0,0.01 ms,78.02 mW,663612.00 pJ,0.058 s,0.00 MiB,0.00 MiB,1,0,118000.00 samples/s,0.01 ms,2.02 mW,17081.00 pJ/it
pool/avg_large_channels,arch-a,PASS,PASS,0.064 s,0.04 MiB,0.02 MiB,1,0,0.24 ms,78.00 mW,18399156.00 pJ,0.060 s,0.04 MiB,0.02 MiB,1,0,4250.00 samples/s,0.24 ms,2.00 mW,471428.00 pJ/it
pool/avg_non_uniform_stride,arch-a,PASS,PASS,0.055 s,0.00 MiB,0.00 MiB,1,0,0.01 ms,78.02 mW,1132254.00 pJ,0.052 s,0.00 MiB,0.00 MiB,1,0,69100.00 samples/s,0.01 ms,2.02 mW,29191.00 pJ/it
pool/avg_real_asymmetric_padding,arch-a,PASS,PASS,0.055 s,0.00 MiB,0.00 MiB,1,0,0.03 ms,78.02 mW,1966692.00 pJ,0.057 s,0.00 MiB,0.00 MiB,1,0,39700.00 samples/s,0.03 ms,2.02 mW,50961.00 pJ/it
pool/max_after_conv,arch-a,PASS,FAIL,0.059 s,0.00 MiB,0.00 MiB,5,4,0.01 ms,99.12 mW,1210689.96 pJ,0.061 s,0.00 MiB,0.00 MiB,5,4,142000.00 samples/s,0.01 ms,34.60 mW,273954.62 pJ/it
pool/max_basic,arch-a,PASS,PASS,0.053 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.06 mW,324744.00 pJ,0.052 s,0.00 MiB,0.00 MiB,1,0,241000.00 samples/s,0.00 ms,2.06 mW,8532.67 pJ/it
pool/max_ceil_mode,arch-a,PASS,PASS,0.051 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.07 mW,151464.00 pJ,0.049 s,0.00 MiB,0.00 MiB,1,0,516000.00 samples/s,0.00 ms,2.07 mW,3972.67 pJ/it
pool/max_global_style_kernel_equals_input,arch-a,PASS,PASS,0.054 s,0.00 MiB,0.00 MiB,1,0,0.01 ms,78.01 mW,658626.00 pJ,0.056 s,0.00 MiB,0.00 MiB,1,0,119000.00 samples/s,0.01 ms,2.01 mW,16871.00 pJ/it
pool/max_non_square_kernel,arch-a,PASS,PASS,0.052 s,0.00 MiB,0.00 MiB,1,0,0.01 ms,78.02 mW,1063068.00 pJ,0.051 s,0.00 MiB,0.00 MiB,1,0,73600.00 samples/s,0.01 ms,2.02 mW,27417.00 pJ/it
pool/max_real_asymmetric_padding,arch-a,PASS,PASS,0.054 s,0.00 MiB,0.00 MiB,1,0,0.01 ms,78.03 mW,814992.00 pJ,0.058 s,0.00 MiB,0.00 MiB,1,0,96100.00 samples/s,0.01 ms,2.03 mW,21173.00 pJ/it
pool/max_same_upper,arch-a,PASS,PASS,0.057 s,0.00 MiB,0.00 MiB,1,0,0.01 ms,78.04 mW,625068.00 pJ,0.052 s,0.00 MiB,0.00 MiB,1,0,125000.00 samples/s,0.01 ms,2.04 mW,16233.00 pJ/it
pool/max_stride2_multichannel,arch-a,PASS,PASS,0.051 s,0.00 MiB,0.00 MiB,1,0,0.02 ms,78.02 mW,1247274.00 pJ,0.051 s,0.00 MiB,0.00 MiB,1,0,62700.00 samples/s,0.02 ms,2.02 mW,32153.00 pJ/it
reduce_mean/4d_spatial,arch-a,PASS,FAIL,0.053 s,0.00 MiB,0.00 MiB,3,0,0.00 ms,92.45 mW,29676.00 pJ,0.055 s,0.00 MiB,0.00 MiB,3,0,2560000.00 samples/s,0.00 ms,4.38 mW,1667.33 pJ/it
reduce_mean/4d_spatial_keepdims_0,arch-a,PASS,FAIL,0.052 s,0.00 MiB,0.00 MiB,4,0,0.00 ms,94.35 mW,61801.00 pJ,0.053 s,0.00 MiB,0.00 MiB,4,0,2390000.00 samples/s,0.00 ms,19.52 mW,9025.83 pJ/it
reduce_mean/after_conv,arch-a,PASS,FAIL,0.059 s,0.00 MiB,0.00 MiB,5,3,0.01 ms,106.95 mW,571332.72 pJ,0.063 s,0.00 MiB,0.00 MiB,5,3,220000.00 samples/s,0.00 ms,21.90 mW,102726.72 pJ/it
reduce_mean/all_axes_keepdims_0,arch-a,PASS,PASS,0.050 s,0.00 MiB,0.00 MiB,2,0,0.00 ms,79.24 mW,30982.00 pJ,0.052 s,0.00 MiB,0.00 MiB,2,0,4520000.00 samples/s,0.00 ms,3.41 mW,775.00 pJ/it
reduce_mean/all_axes_keepdims_1,arch-a,PASS,PASS,0.052 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,17286.00 pJ,0.048 s,0.00 MiB,0.00 MiB,1,0,4570000.00 samples/s,0.00 ms,2.22 mW,437.33 pJ/it
reduce_mean/basic,arch-a,PASS,FAIL,0.052 s,0.00 MiB,0.00 MiB,4,0,0.00 ms,93.51 mW,34881.00 pJ,0.053 s,0.00 MiB,0.00 MiB,4,0,2780000.00 samples/s,0.00 ms,5.56 mW,1904.50 pJ/it
reduce_mean/channel_axis_nchw,arch-a,PASS,FAIL,0.052 s,0.03 MiB,0.02 MiB,4,0,0.16 ms,93.60 mW,15436518.00 pJ,0.055 s,0.03 MiB,0.08 MiB,4,0,16000.00 samples/s,0.06 ms,5.00 mW,323993.33 pJ/it
reduce_mean/keepdims_0,arch-a,PASS,FAIL,0.055 s,0.00 MiB,0.00 MiB,5,0,0.00 ms,91.40 mW,68368.00 pJ,0.054 s,0.00 MiB,0.00 MiB,5,0,1880000.00 samples/s,0.00 ms,20.60 mW,11458.17 pJ/it
reduce_mean/large_dimension_1024,arch-a,PASS,PASS,0.053 s,0.01 MiB,0.00 MiB,1,0,0.00 ms,78.02 mW,217278.00 pJ,0.052 s,0.01 MiB,0.00 MiB,1,0,359000.00 samples/s,0.00 ms,2.02 mW,5274.00 pJ/it
reduce_mean/legacy_axes_1_2_keepdims_1,arch-a,PASS,FAIL,0.052 s,0.00 MiB,0.00 MiB,2,0,0.00 ms,79.35 mW,21505.00 pJ,0.052 s,0.00 MiB,0.00 MiB,2,0,3860000.00 samples/s,0.00 ms,3.37 mW,798.00 pJ/it
reduce_mean/legacy_axis1_keepdims_0,arch-a,PASS,FAIL,0.071 s,0.00 MiB,0.00 MiB,9,0,0.00 ms,92.50 mW,183708.00 pJ,0.061 s,0.00 MiB,0.00 MiB,9,0,1010000.00 samples/s,0.00 ms,38.63 mW,41198.50 pJ/it
reduce_mean/legacy_axis1_keepdims_1,arch-a,PASS,FAIL,0.053 s,0.00 MiB,0.00 MiB,8,0,0.00 ms,94.56 mW,129830.00 pJ,0.054 s,0.00 MiB,0.00 MiB,8,0,1390000.00 samples/s,0.00 ms,9.56 mW,6733.50 pJ/it
reduce_mean/legacy_empty_axes_noop,arch-a,PASS,PASS,0.050 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,17286.00 pJ,0.048 s,0.00 MiB,0.00 MiB,1,0,4570000.00 samples/s,0.00 ms,2.22 mW,437.33 pJ/it
reduce_mean/legacy_nchw_spatial,arch-a,PASS,FAIL,0.054 s,0.00 MiB,0.00 MiB,3,0,0.00 ms,92.45 mW,29676.00 pJ,0.056 s,0.00 MiB,0.00 MiB,3,0,1960000.00 samples/s,0.00 ms,4.28 mW,2167.33 pJ/it
reduce_mean/legacy_negative_axis,arch-a,PASS,FAIL,0.051 s,0.00 MiB,0.00 MiB,6,0,0.00 ms,93.52 mW,51717.00 pJ,0.057 s,0.00 MiB,0.00 MiB,6,0,1850000.00 samples/s,0.00 ms,7.57 mW,3828.83 pJ/it
reduce_mean/legacy_reduce_all_keepdims_1,arch-a,PASS,PASS,0.051 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,17286.00 pJ,0.048 s,0.00 MiB,0.00 MiB,1,0,4570000.00 samples/s,0.00 ms,2.22 mW,437.33 pJ/it
reduce_mean/negative_axis,arch-a,PASS,FAIL,0.058 s,0.00 MiB,0.00 MiB,6,0,0.00 ms,93.52 mW,51717.00 pJ,0.054 s,0.00 MiB,0.00 MiB,6,0,1850000.00 samples/s,0.00 ms,7.57 mW,3828.83 pJ/it
relu/4d,arch-a,PASS,PASS,0.052 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.18 mW,40734.00 pJ,0.049 s,0.00 MiB,0.00 MiB,1,0,1930000.00 samples/s,0.00 ms,2.18 mW,1014.00 pJ/it
relu/after_conv,arch-a,PASS,FAIL,0.058 s,0.00 MiB,0.00 MiB,4,3,0.01 ms,107.89 mW,577437.72 pJ,0.060 s,0.00 MiB,0.00 MiB,4,3,220000.00 samples/s,0.00 ms,34.98 mW,162801.39 pJ/it
relu/after_gemm,arch-a,PASS,FAIL,0.061 s,0.01 MiB,0.01 MiB,5,4,0.01 ms,105.16 mW,790056.96 pJ,0.059 s,0.01 MiB,0.01 MiB,6,4,291000.00 samples/s,0.00 ms,47.08 mW,187063.49 pJ/it
relu/basic,arch-a,PASS,PASS,0.052 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,17286.00 pJ,0.050 s,0.00 MiB,0.00 MiB,1,0,4570000.00 samples/s,0.00 ms,2.22 mW,437.33 pJ/it
reshape/4d_to_2d_flatten,arch-a,PASS,PASS,0.047 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.28 mW,20196.00 pJ,0.050 s,0.00 MiB,0.00 MiB,1,0,3910000.00 samples/s,0.00 ms,2.28 mW,488.00 pJ/it
reshape/infer_dim_minus_one,arch-a,PASS,PASS,0.054 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.30 mW,12684.00 pJ,0.048 s,0.00 MiB,0.00 MiB,1,0,6250000.00 samples/s,0.00 ms,2.30 mW,308.00 pJ/it
reshape/same_rank,arch-a,PASS,PASS,0.056 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.30 mW,12684.00 pJ,0.048 s,0.00 MiB,0.00 MiB,1,0,6250000.00 samples/s,0.00 ms,2.30 mW,308.00 pJ/it
reshape/zero_copies_input_dim,arch-a,PASS,PASS,0.056 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.30 mW,12684.00 pJ,0.056 s,0.00 MiB,0.00 MiB,1,0,6250000.00 samples/s,0.00 ms,2.30 mW,308.00 pJ/it
resize/height_only,arch-a,PASS,FAIL,0.054 s,0.00 MiB,0.00 MiB,4,0,0.00 ms,93.55 mW,64833.00 pJ,0.055 s,0.00 MiB,0.00 MiB,4,0,2430000.00 samples/s,0.00 ms,5.46 mW,2298.25 pJ/it
resize/nearest_2x,arch-a,PASS,FAIL,0.055 s,0.00 MiB,0.00 MiB,4,0,0.00 ms,93.57 mW,109761.00 pJ,0.051 s,0.00 MiB,0.00 MiB,4,0,1760000.00 samples/s,0.00 ms,5.33 mW,3085.12 pJ/it
resize/nearest_downsample,arch-a,PASS,FAIL,0.054 s,0.00 MiB,0.00 MiB,2,0,0.00 ms,79.45 mW,33925.00 pJ,0.052 s,0.00 MiB,0.00 MiB,2,0,2420000.00 samples/s,0.00 ms,3.22 mW,1262.50 pJ/it
resize/non_uniform_scales,arch-a,PASS,FAIL,0.054 s,0.00 MiB,0.00 MiB,6,0,0.00 ms,93.58 mW,164037.00 pJ,0.055 s,0.00 MiB,0.00 MiB,6,0,1750000.00 samples/s,0.00 ms,7.49 mW,4551.90 pJ/it
resize/width_only,arch-a,PASS,FAIL,0.051 s,0.00 MiB,0.00 MiB,2,0,0.00 ms,79.50 mW,53029.00 pJ,0.052 s,0.00 MiB,0.00 MiB,2,0,1750000.00 samples/s,0.00 ms,3.16 mW,1735.50 pJ/it
resize/with_sizes,arch-a,PASS,FAIL,0.054 s,0.00 MiB,0.00 MiB,3,0,0.00 ms,92.54 mW,73756.00 pJ,0.056 s,0.00 MiB,0.00 MiB,3,0,1930000.00 samples/s,0.00 ms,4.27 mW,2196.00 pJ/it
sigmoid/4d,arch-a,PASS,PASS,0.050 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.18 mW,40734.00 pJ,0.055 s,0.00 MiB,0.00 MiB,1,0,1930000.00 samples/s,0.00 ms,2.18 mW,1014.00 pJ/it
sigmoid/after_gemm,arch-a,PASS,FAIL,0.056 s,0.01 MiB,0.01 MiB,5,4,0.01 ms,105.16 mW,790056.96 pJ,0.058 s,0.01 MiB,0.01 MiB,6,4,291000.00 samples/s,0.00 ms,47.08 mW,187063.49 pJ/it
sigmoid/basic,arch-a,PASS,PASS,0.053 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,17286.00 pJ,0.049 s,0.00 MiB,0.00 MiB,1,0,4570000.00 samples/s,0.00 ms,2.22 mW,437.33 pJ/it
slice/2d_basic,arch-a,PASS,PASS,0.051 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.30 mW,18948.00 pJ,0.048 s,0.00 MiB,0.00 MiB,1,0,4170000.00 samples/s,0.00 ms,2.30 mW,491.67 pJ/it
slice/after_conv,arch-a,PASS,FAIL,0.062 s,0.00 MiB,0.01 MiB,7,6,0.01 ms,118.19 mW,1335082.88 pJ,0.069 s,0.00 MiB,0.01 MiB,7,6,130000.00 samples/s,0.01 ms,58.48 mW,484364.44 pJ/it
slice/default_axes,arch-a,PASS,PASS,0.051 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.30 mW,18948.00 pJ,0.052 s,0.00 MiB,0.00 MiB,1,0,4170000.00 samples/s,0.00 ms,2.30 mW,491.67 pJ/it
slice/large_channel_1024,arch-a,PASS,PASS,0.051 s,0.01 MiB,0.00 MiB,1,0,0.00 ms,78.14 mW,221304.00 pJ,0.050 s,0.01 MiB,0.00 MiB,1,0,353000.00 samples/s,0.00 ms,2.14 mW,5058.00 pJ/it
slice/nchw_spatial_crop,arch-a,PASS,PASS,0.053 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.24 mW,101868.00 pJ,0.047 s,0.00 MiB,0.00 MiB,1,0,769000.00 samples/s,0.00 ms,2.24 mW,2851.67 pJ/it
slice/negative_axis,arch-a,PASS,PASS,0.050 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.30 mW,44004.00 pJ,0.049 s,0.00 MiB,0.00 MiB,1,0,1790000.00 samples/s,0.00 ms,2.30 mW,1227.67 pJ/it
slice/negative_indices,arch-a,PASS,PASS,0.048 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.30 mW,25212.00 pJ,0.051 s,0.00 MiB,0.00 MiB,1,0,3120000.00 samples/s,0.00 ms,2.30 mW,675.67 pJ/it
slice/step2,arch-a,PASS,PASS,0.053 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.29 mW,159876.00 pJ,0.052 s,0.00 MiB,0.00 MiB,1,0,490000.00 samples/s,0.00 ms,2.29 mW,4619.67 pJ/it
softmax/3d_last_axis,arch-a,PASS,PASS,0.052 s,0.00 MiB,0.00 MiB,1,0,UNSUPPORTED,UNSUPPORTED,UNSUPPORTED,0.053 s,0.00 MiB,0.00 MiB,1,0,UNSUPPORTED,UNSUPPORTED,UNSUPPORTED,UNSUPPORTED
softmax/basic,arch-a,PASS,PASS,0.050 s,0.00 MiB,0.00 MiB,1,0,UNSUPPORTED,UNSUPPORTED,UNSUPPORTED,0.053 s,0.00 MiB,0.00 MiB,1,0,UNSUPPORTED,UNSUPPORTED,UNSUPPORTED,UNSUPPORTED
softmax/channel_axis,arch-a,PASS,FAIL,0.051 s,0.00 MiB,0.00 MiB,1,0,UNSUPPORTED,UNSUPPORTED,UNSUPPORTED,0.052 s,0.00 MiB,0.00 MiB,3,0,UNSUPPORTED,UNSUPPORTED,UNSUPPORTED,UNSUPPORTED
softmax/large_dimension_1024,arch-a,PASS,PASS,0.049 s,0.01 MiB,0.01 MiB,1,0,UNSUPPORTED,UNSUPPORTED,UNSUPPORTED,0.052 s,0.01 MiB,0.01 MiB,1,0,UNSUPPORTED,UNSUPPORTED,UNSUPPORTED,UNSUPPORTED
softmax/negative_axis,arch-a,PASS,PASS,0.050 s,0.00 MiB,0.00 MiB,1,0,UNSUPPORTED,UNSUPPORTED,UNSUPPORTED,0.049 s,0.00 MiB,0.00 MiB,1,0,UNSUPPORTED,UNSUPPORTED,UNSUPPORTED,UNSUPPORTED
split/basic,arch-a,PASS,PASS,0.048 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.30 mW,31554.00 pJ,0.052 s,0.00 MiB,0.00 MiB,1,0,2490000.00 samples/s,0.00 ms,2.30 mW,861.67 pJ/it
split/equal_three_way,arch-a,PASS,PASS,0.049 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.30 mW,44160.00 pJ,0.052 s,0.00 MiB,0.00 MiB,1,0,1780000.00 samples/s,0.00 ms,2.30 mW,1231.67 pJ/it
split/negative_axis,arch-a,PASS,PASS,0.051 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.29 mW,84786.00 pJ,0.050 s,0.00 MiB,0.00 MiB,1,0,925000.00 samples/s,0.00 ms,2.29 mW,2413.67 pJ/it
split/uneven_channel_axis_4d,arch-a,PASS,PASS,0.051 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.30 mW,18948.00 pJ,0.049 s,0.00 MiB,0.00 MiB,1,0,4170000.00 samples/s,0.00 ms,2.30 mW,491.67 pJ/it
sub/after_gemm,arch-a,PASS,FAIL,0.058 s,0.01 MiB,0.01 MiB,5,4,0.01 ms,104.70 mW,815012.96 pJ,0.057 s,0.01 MiB,0.01 MiB,6,4,277000.00 samples/s,0.00 ms,45.81 mW,190085.16 pJ/it
sub/basic,arch-a,PASS,PASS,0.049 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,25266.00 pJ,0.048 s,0.00 MiB,0.00 MiB,1,0,3120000.00 samples/s,0.00 ms,2.23 mW,658.67 pJ/it
sub/broadcast_row,arch-a,PASS,PASS,0.049 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,25266.00 pJ,0.051 s,0.00 MiB,0.00 MiB,1,0,3120000.00 samples/s,0.00 ms,2.23 mW,658.67 pJ/it
sub/channel_broadcast_1024,arch-a,PASS,PASS,0.058 s,0.02 MiB,0.01 MiB,1,0,0.01 ms,78.12 mW,540030.00 pJ,0.053 s,0.02 MiB,0.01 MiB,1,0,145000.00 samples/s,0.01 ms,2.11 mW,13388.67 pJ/it
sub/constant_lhs_broadcast,arch-a,PASS,PASS,0.049 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,25188.00 pJ,0.051 s,0.00 MiB,0.00 MiB,1,0,3120000.00 samples/s,0.00 ms,2.23 mW,656.67 pJ/it
sub/leading_dimension_broadcast,arch-a,PASS,PASS,0.050 s,0.00 MiB,0.00 MiB,1,0,0.00 ms,78.22 mW,25266.00 pJ,0.050 s,0.00 MiB,0.00 MiB,1,0,3120000.00 samples/s,0.00 ms,2.23 mW,658.67 pJ/it
1 Operation Arch Compile Result Result (l) Result (t) Compile (l) Host mem Host mem (l) Cores mem Cores mem (l) Latency Cores Cores (l) Power Xbars Xbars (l) Energy Latency (l) Power (l) Energy (l) Compile (t) Host mem (t) Cores mem (t) Cores (t) Xbars (t) Avg latency (t) Throughput (t) Avg power (t) Avg energy (t)
2 add/after_gemm arch-a 0.063 s PASS FAIL 0.057 s 0.01 MiB 0.01 MiB SKIP 5 SKIP 4 SKIP 0.01 ms 104.70 mW 815012.96 pJ 0.055 s 0.01 MiB 0.01 MiB 6 4 277000.00 samples/s 0.00 ms 45.81 mW 190085.16 pJ/it
3 add/basic arch-a 0.057 s PASS PASS 0.047 s 0.00 MiB 0.00 MiB SKIP 1 SKIP 0 SKIP 0.00 ms 78.22 mW 25266.00 pJ 0.048 s 0.00 MiB 0.00 MiB 1 0 3120000.00 samples/s 0.00 ms 2.23 mW 658.67 pJ/it
4 add/broadcast_row arch-a 0.057 s PASS PASS 0.049 s 0.00 MiB 0.00 MiB SKIP 1 SKIP 0 SKIP 0.00 ms 78.22 mW 25266.00 pJ 0.049 s 0.00 MiB 0.00 MiB 1 0 3120000.00 samples/s 0.00 ms 2.23 mW 658.67 pJ/it
5 add/channel_broadcast_1024 arch-a 0.061 s PASS PASS 0.048 s 0.02 MiB 0.01 MiB SKIP 1 SKIP 0 SKIP 0.01 ms 78.12 mW 540030.00 pJ 0.048 s 0.02 MiB 0.01 MiB 1 0 145000.00 samples/s 0.01 ms 2.11 mW 13388.67 pJ/it
6 add/leading_dimension_broadcast arch-a 0.057 s PASS PASS 0.052 s 0.00 MiB 0.00 MiB SKIP 1 SKIP 0 SKIP 0.00 ms 78.22 mW 25266.00 pJ 0.048 s 0.00 MiB 0.00 MiB 1 0 3120000.00 samples/s 0.00 ms 2.23 mW 658.67 pJ/it
7 concat/channel_axis arch-a 0.069 s PASS PASS 0.053 s 0.00 MiB 0.00 MiB SKIP 1 SKIP 0 SKIP 0.00 ms 78.16 mW 35718.00 pJ 0.047 s 0.00 MiB 0.00 MiB 1 0 2200000.00 samples/s 0.00 ms 2.16 mW 934.67 pJ/it
8 concat/negative_axis arch-a 0.061 s PASS PASS 0.047 s 0.00 MiB 0.00 MiB SKIP 1 SKIP 0 SKIP 0.00 ms 78.09 mW 81450.00 pJ 0.049 s 0.00 MiB 0.00 MiB 1 0 961000.00 samples/s 0.00 ms 2.09 mW 2108.00 pJ/it
9 concat/three_inputs_channel_axis arch-a 0.058 s PASS PASS 0.049 s 0.00 MiB 0.00 MiB SKIP 1 SKIP 0 SKIP 0.00 ms 78.15 mW 50328.00 pJ 0.045 s 0.00 MiB 0.00 MiB 1 0 1560000.00 samples/s 0.00 ms 2.15 mW 1332.67 pJ/it
10 conv/batch_2 arch-a 0.066 s PASS PASS 0.058 s 0.00 MiB 0.00 MiB SKIP 2 SKIP 2 SKIP 0.01 ms 82.62 mW 1131451.48 pJ 0.057 s 0.00 MiB 0.01 MiB 4 2 168000.00 samples/s 0.01 ms 53.33 mW 343254.69 pJ/it
11 conv/batch_4_pointwise arch-a 0.065 s PASS FAIL 0.055 s 0.00 MiB 0.01 MiB SKIP 5 SKIP 4 SKIP 0.00 ms 116.08 mW 456420.96 pJ 0.060 s 0.00 MiB 0.01 MiB 5 4 486000.00 samples/s 0.00 ms 70.89 mW 160104.45 pJ/it
12 conv/depthwise_1024_channels arch-a 0.083 s PASS FAIL 0.081 s 0.19 MiB 0.38 MiB SKIP 129 SKIP 128 SKIP 0.22 ms 178.45 mW 39393966.72 pJ - - - - - - - - -
13 conv/depthwise_grouped arch-a 0.071 s PASS FAIL 0.055 s 0.01 MiB 0.00 MiB SKIP 5 SKIP 4 SKIP 0.01 ms 107.78 mW 671878.96 pJ - - - - - - - - -
14 conv/dilated_3x3 arch-a 0.068 s PASS PASS 0.060 s 0.01 MiB 0.01 MiB SKIP 10 SKIP 9 SKIP 0.01 ms 118.77 mW 1034819.16 pJ 0.067 s 0.01 MiB 0.01 MiB 12 9 189000.00 samples/s 0.01 ms 75.03 mW 435165.28 pJ/it
15 conv/dynamic arch-a 0.065 s PASS FAIL 0.056 s 0.00 MiB 0.00 MiB SKIP 5 SKIP 0 SKIP 0.00 ms 92.28 mW 169336.00 pJ 0.057 s 0.00 MiB 0.00 MiB 6 0 661000.00 samples/s 0.00 ms 18.68 mW 30964.00 pJ/it
16 conv/explicit_padding arch-a 0.062 s PASS FAIL 0.062 s 0.01 MiB 0.02 MiB SKIP 17 SKIP 16 SKIP 0.01 ms 145.34 mW 1454397.84 pJ - - - - - - - - -
17 conv/grouped_many_groups arch-a 0.442 s PASS FAIL 0.486 s 0.05 MiB 0.09 MiB SKIP 65 SKIP 64 SKIP 0.18 ms 142.21 mW 25867112.36 pJ 0.500 s 0.11 MiB 0.79 MiB 127 64 569.00 samples/s 1.76 ms 141.19 mW 252570125.00 pJ/it
18 conv/grouped_two_groups arch-a 0.060 s PASS FAIL 0.063 s 0.00 MiB 0.00 MiB SKIP 3 SKIP 2 SKIP 0.01 ms 101.46 mW 543914.48 pJ 0.061 s 0.00 MiB 0.01 MiB 9 2 327000.00 samples/s 0.00 ms 116.36 mW 453237.70 pJ/it
19 conv/huge_pointwise_1024 arch-a 0.156 s PASS FAIL 0.160 s 0.01 MiB 0.11 MiB SKIP 73 SKIP 64 SKIP 0.02 ms 249.55 mW 3896647.36 pJ 0.176 s 0.04 MiB 0.11 MiB 74 64 35300.00 samples/s 0.03 ms 136.81 mW 4031965.75 pJ/it
20 conv/huge_pointwise_1024_dynamic arch-a 0.079 s PASS FAIL 0.101 s 8.04 MiB 12.61 MiB SKIP 168 SKIP 0 SKIP 2.63 ms 169.52 mW 445489032.00 pJ - - - - - - - - -
21 conv/kernel_3x3 conv/input_224_7x7_stride2 arch-a 0.062 s PASS FAIL 1.124 s 0.01 MiB 24.14 MiB 0.01 MiB 61.87 MiB SKIP 10 168 SKIP 9 169 SKIP 38.41 ms 185.26 mW 7116544212.12 pJ - - - - - - - - -
22 conv/kernel_equals_input_spatial conv/kernel_2x2 arch-a 0.064 s PASS FAIL 0.064 s 0.00 MiB 0.00 MiB SKIP 2 1 SKIP 2 1 SKIP 0.00 ms 83.83 mW 360568.24 pJ 0.099 s 0.00 MiB 0.00 MiB 3 1 380000.00 samples/s 0.00 ms 52.64 mW 151421.99 pJ/it
23 conv/large_input_channels_1x1 conv/kernel_3x3 arch-a 0.089 s PASS FAIL 0.057 s 0.01 MiB 0.02 MiB 0.01 MiB SKIP 9 10 SKIP 8 9 SKIP 0.01 ms 123.80 mW 889640.16 pJ - - - - - - - - -
24 conv/large_output_channels_1x1 conv/kernel_equals_input_spatial arch-a 0.098 s PASS PASS 0.056 s 0.01 MiB 0.00 MiB 0.02 MiB 0.00 MiB SKIP 17 2 SKIP 8 2 SKIP 0.00 ms 89.61 mW 415689.48 pJ 0.059 s 0.00 MiB 0.00 MiB 4 2 464000.00 samples/s 0.00 ms 68.91 mW 166273.89 pJ/it
25 conv/large_spatial conv/large_input_channels_1x1 arch-a 0.069 s PASS PASS 0.087 s 0.01 MiB 0.04 MiB 0.02 MiB SKIP 37 9 SKIP 36 8 SKIP 0.01 ms 117.82 mW 901121.92 pJ 0.087 s 0.01 MiB 0.02 MiB 10 8 306000.00 samples/s 0.00 ms 91.39 mW 360779.57 pJ/it
26 conv/multi_channel conv/large_output_channels_1x1 arch-a 0.066 s PASS PASS 0.088 s 0.00 MiB 0.01 MiB 0.00 MiB 0.02 MiB SKIP 4 17 SKIP 3 8 SKIP 0.01 ms 128.44 mW 1139415.92 pJ 0.089 s 0.01 MiB 0.02 MiB 18 8 207000.00 samples/s 0.00 ms 73.39 mW 358350.06 pJ/it
27 conv/non_square_kernel_1x3 conv/large_spatial arch-a 0.061 s PASS FAIL 0.060 s 0.00 MiB 0.01 MiB 0.00 MiB 0.04 MiB SKIP 3 37 SKIP 2 36 SKIP 0.02 ms 172.07 mW 2928344.64 pJ - - - - - - - - -
28 conv/non_square_kernel_3x1 conv/multi_channel arch-a 0.064 s PASS FAIL 0.056 s 0.00 MiB 0.00 MiB SKIP 3 4 SKIP 2 3 SKIP 0.01 ms 105.68 mW 685040.72 pJ 0.057 s 0.00 MiB 0.00 MiB 4 3 178000.00 samples/s 0.01 ms 32.10 mW 185757.05 pJ/it
29 conv/non_uniform_stride conv/non_square_kernel_1x3 arch-a 0.062 s PASS PASS 0.066 s 0.00 MiB 0.00 MiB SKIP 4 3 SKIP 3 2 SKIP 0.01 ms 99.35 mW 679752.48 pJ 0.054 s 0.00 MiB 0.00 MiB 3 2 163000.00 samples/s 0.01 ms 13.04 mW 81630.31 pJ/it
30 conv/pointwise_1x1 conv/non_square_kernel_3x1 arch-a 0.059 s PASS PASS 0.060 s 0.00 MiB 0.00 MiB SKIP 1 3 SKIP 1 2 SKIP 0.01 ms 95.89 mW 1292976.48 pJ 0.065 s 0.00 MiB 0.00 MiB 3 2 77500.00 samples/s 0.01 ms 9.04 mW 117499.65 pJ/it
31 conv/pointwise_tiled_chain conv/non_uniform_stride arch-a 0.604 s PASS FAIL 0.056 s 0.01 MiB 0.00 MiB 0.04 MiB 0.00 MiB SKIP 20 4 SKIP 80 3 SKIP 0.01 ms 104.05 mW 790874.72 pJ 0.056 s 0.00 MiB 0.00 MiB 4 3 161000.00 samples/s 0.01 ms 30.89 mW 198689.55 pJ/it
32 conv/real_asymmetric_padding conv/output_channel_grouping_minimal arch-a 0.060 s PASS FAIL 0.083 s 0.01 MiB 0.10 MiB 0.03 MiB 0.34 MiB SKIP 29 131 SKIP 28 128 SKIP 0.26 ms 170.73 mW 44125916.72 pJ - - - - - - - - -
33 conv/relu_conv_store conv/pointwise_1x1 arch-a 0.091 s PASS FAIL 0.052 s 0.16 MiB 0.00 MiB 0.67 MiB 0.00 MiB SKIP 168 1 SKIP 184 1 SKIP 0.01 ms 80.24 mW 987244.24 pJ 0.055 s 0.00 MiB 0.00 MiB 3 1 135000.00 samples/s 0.01 ms 47.15 mW 371973.57 pJ/it
34 conv/same_lower_3x3 conv/pointwise_tiled_chain arch-a 0.078 s PASS PASS 0.699 s 0.01 MiB 0.02 MiB 0.04 MiB SKIP 26 20 SKIP 25 80 SKIP 0.04 ms 153.88 mW 6445455.20 pJ 0.634 s 0.05 MiB 0.08 MiB 22 80 14300.00 samples/s 0.07 ms 71.96 mW 5297594.20 pJ/it
35 conv/same_padding_3x3 conv/real_asymmetric_padding arch-a 0.070 s PASS FAIL 0.063 s 0.01 MiB 0.02 MiB 0.03 MiB SKIP 26 29 SKIP 25 28 SKIP 0.01 ms 153.67 mW 2221606.72 pJ - - - - - - - - -
36 conv/simple conv/relu_conv_store arch-a 0.064 s PASS FAIL 0.094 s 0.00 MiB 0.16 MiB 0.00 MiB 0.67 MiB SKIP 1 168 SKIP 1 184 SKIP 0.56 ms 183.08 mW 103057892.80 pJ - - - - - - - - -
37 conv/stride_2 conv/same_lower_3x3 arch-a 0.064 s PASS FAIL 0.061 s 0.01 MiB 0.00 MiB 0.02 MiB SKIP 5 26 SKIP 4 25 SKIP 0.01 ms 166.15 mW 2215009.00 pJ - - - - - - - - -
38 conv/with_bias_3x3 conv/same_padding_3x3 arch-a 0.067 s PASS FAIL 0.059 s 0.00 MiB 0.01 MiB 0.01 MiB 0.02 MiB SKIP 4 26 SKIP 3 25 SKIP 0.01 ms 166.15 mW 2215009.00 pJ - - - - - - - - -
39 conv/with_constant conv/strategy_depthwise_16 arch-a 0.070 s PASS FAIL 0.092 s 0.00 MiB 0.06 MiB 0.00 MiB 0.35 MiB SKIP 1 168 SKIP 1 168 SKIP 0.34 ms 197.94 mW 66331479.08 pJ - - - - - - - - -
40 conv/without_kernel_shape_attr conv/strategy_input_k_tiled arch-a 0.069 s PASS FAIL 0.084 s 0.01 MiB 0.08 MiB 0.01 MiB 0.27 MiB SKIP 10 109 SKIP 9 108 SKIP 0.35 ms 170.81 mW 60422605.92 pJ - - - - - - - - -
41 conv/yolo11n_depthwise_head conv/strategy_output_channel_tiled arch-a 1.482 s PASS FAIL 0.071 s 8.66 MiB 0.03 MiB 34.24 MiB 0.16 MiB SKIP 168 74 SKIP 255 72 SKIP 0.09 ms 155.74 mW 14244739.28 pJ - - - - - - - - -
42 conv/yolo11n_heavy conv/strategy_streamed_packed arch-a 0.431 s PASS FAIL 0.184 s 4.82 MiB 3.34 MiB 19.10 MiB 7.89 MiB SKIP 161 168 SKIP 800 168 SKIP 9.35 ms 179.86 mW 1682364509.56 pJ - - - - - - - - -
43 conv/yolo11n_stem conv/strategy_streamed_patch arch-a 0.783 s PASS FAIL 0.098 s 12.86 MiB 0.34 MiB 37.59 MiB 1.32 MiB SKIP 168 SKIP 488 168 SKIP 1.90 ms 181.91 mW 346476645.64 pJ - - - - - - - - -
44 div/after_gemm conv/strategy_tiled_2d arch-a 0.072 s PASS FAIL 0.117 s 0.01 MiB 0.11 MiB 0.01 MiB 0.44 MiB SKIP 5 168 SKIP 4 168 SKIP 0.42 ms 182.13 mW 75690907.84 pJ - - - - - - - - -
45 div/basic conv/stride_2 arch-a 0.061 s PASS FAIL 0.059 s 0.00 MiB 0.01 MiB 0.00 MiB SKIP 1 5 SKIP 0 4 SKIP 0.01 ms 110.78 mW 580154.96 pJ - - - - - - - - -
46 div/channel_broadcast_1024 conv/with_bias_3x3 arch-a 0.066 s PASS FAIL 0.057 s 0.02 MiB 0.00 MiB 0.01 MiB SKIP 1 4 SKIP 0 3 SKIP 0.01 ms 104.16 mW 776220.72 pJ 0.057 s 0.00 MiB 0.01 MiB 4 3 165000.00 samples/s 0.01 ms 30.99 mW 196092.89 pJ/it
47 div/leading_dimension_broadcast conv/with_constant arch-a 0.059 s PASS FAIL 0.057 s 0.00 MiB 0.00 MiB SKIP 1 SKIP 0 1 SKIP 0.01 ms 81.74 mW 541270.24 pJ 0.059 s 0.00 MiB 0.00 MiB 4 1 232000.00 samples/s 0.00 ms 92.34 mW 438607.24 pJ/it
48 div/runtime_scalar_rhs conv/without_kernel_shape_attr arch-a 0.056 s PASS FAIL 0.055 s 0.02 MiB 0.01 MiB 0.01 MiB SKIP 1 10 SKIP 0 9 SKIP 0.01 ms 123.80 mW 889640.16 pJ - - - - - - - - -
49 div/scalar_constant conv/yolo11n_depthwise_head arch-a 0.073 s PASS FAIL 2.274 s 0.00 MiB 8.66 MiB 0.00 MiB 34.24 MiB SKIP 1 168 SKIP 0 255 SKIP 42.70 ms 200.52 mW 8562449708.00 pJ - - - - - - - - -
50 gather/3d_input_axis1 conv/yolo11n_heavy arch-a 0.060 s PASS FAIL 0.478 s 0.00 MiB 4.82 MiB 0.00 MiB 19.10 MiB SKIP 1 161 SKIP 0 800 SKIP 8.54 ms 350.86 mW 2994764012.00 pJ - - - - - - - - -
51 gather/axis0_matrix_indices conv/yolo11n_stem arch-a 0.056 s PASS FAIL 0.975 s 0.00 MiB 12.86 MiB 0.00 MiB 37.59 MiB SKIP 1 168 SKIP 0 488 SKIP 14.24 ms 301.23 mW 4289558753.00 pJ - - - - - - - - -
52 gather/axis1 div/after_gemm arch-a 0.058 s PASS FAIL 0.056 s 0.00 MiB 0.01 MiB 0.00 MiB 0.01 MiB SKIP 1 5 SKIP 0 4 SKIP 0.01 ms 104.70 mW 815012.96 pJ 0.056 s 0.01 MiB 0.01 MiB 6 4 277000.00 samples/s 0.00 ms 45.81 mW 190085.16 pJ/it
53 gather/negative_axis div/basic arch-a 0.058 s PASS PASS 0.049 s 0.00 MiB 0.00 MiB SKIP 1 SKIP 0 SKIP 0.00 ms 78.22 mW 25266.00 pJ 0.050 s 0.00 MiB 0.00 MiB 1 0 3120000.00 samples/s 0.00 ms 2.23 mW 658.67 pJ/it
54 gather/negative_indices div/channel_broadcast_1024 arch-a 0.063 s PASS PASS 0.051 s 0.00 MiB 0.02 MiB 0.00 MiB 0.01 MiB SKIP 1 SKIP 0 SKIP 0.01 ms 78.12 mW 540030.00 pJ 0.055 s 0.02 MiB 0.01 MiB 1 0 145000.00 samples/s 0.01 ms 2.11 mW 13388.67 pJ/it
55 gemm/alpha_beta div/leading_dimension_broadcast arch-a 0.067 s PASS PASS 0.053 s 0.01 MiB 0.00 MiB 0.01 MiB 0.00 MiB SKIP 5 1 SKIP 4 0 SKIP 0.00 ms 78.22 mW 25266.00 pJ 0.052 s 0.00 MiB 0.00 MiB 1 0 3120000.00 samples/s 0.00 ms 2.23 mW 658.67 pJ/it
56 gemm/bias_rank2_broadcast div/runtime_scalar_rhs arch-a 0.060 s PASS PASS 0.048 s 0.00 MiB 0.02 MiB 0.01 MiB SKIP 5 1 SKIP 4 0 SKIP 0.01 ms 78.12 mW 540030.00 pJ 0.051 s 0.02 MiB 0.01 MiB 1 0 145000.00 samples/s 0.01 ms 2.11 mW 13388.67 pJ/it
57 gemm/dynamic div/scalar_constant arch-a 0.064 s PASS PASS 0.057 s 0.00 MiB 0.00 MiB SKIP 5 1 SKIP 0 SKIP 0.00 ms 78.22 mW 25266.00 pJ 0.059 s 0.00 MiB 0.00 MiB 1 0 3120000.00 samples/s 0.00 ms 2.23 mW 658.67 pJ/it
58 gemm/dynamic_alpha gather/3d_input_axis1 arch-a 0.062 s PASS PASS 0.052 s 0.00 MiB 0.00 MiB SKIP 5 1 SKIP 0 SKIP 0.00 ms 78.08 mW 45990.00 pJ 0.053 s 0.00 MiB 0.00 MiB 1 0 1700000.00 samples/s 0.00 ms 2.08 mW 1174.67 pJ/it
59 gemm/dynamic_beta gather/axis0_matrix_indices arch-a 0.060 s PASS PASS 0.055 s 0.00 MiB 0.00 MiB SKIP 5 1 SKIP 0 SKIP 0.00 ms 78.07 mW 54414.00 pJ 0.052 s 0.00 MiB 0.00 MiB 1 0 1440000.00 samples/s 0.00 ms 2.07 mW 1390.67 pJ/it
60 gemm/dynamic_bias gather/axis1 arch-a 0.058 s PASS PASS 0.051 s 0.00 MiB 0.00 MiB SKIP 5 1 SKIP 0 SKIP 0.00 ms 78.06 mW 62526.00 pJ 0.053 s 0.00 MiB 0.00 MiB 1 0 1250000.00 samples/s 0.00 ms 2.06 mW 1598.67 pJ/it
61 gemm/dynamic_bias_alpha_beta gather/negative_axis arch-a 0.067 s PASS PASS 0.049 s 0.00 MiB 0.00 MiB SKIP 5 1 SKIP 0 SKIP 0.00 ms 78.03 mW 112134.00 pJ 0.051 s 0.00 MiB 0.00 MiB 1 0 697000.00 samples/s 0.00 ms 2.03 mW 2870.67 pJ/it
62 gemm/dynamic_transB gather/negative_indices arch-a 0.062 s PASS PASS 0.052 s 0.00 MiB 0.00 MiB SKIP 5 1 SKIP 0 SKIP 0.00 ms 78.13 mW 29376.00 pJ 0.058 s 0.00 MiB 0.00 MiB 1 0 2670000.00 samples/s 0.00 ms 2.12 mW 748.67 pJ/it
63 gemm/huge_1024 gemm/alpha_beta arch-a 0.147 s PASS FAIL 0.059 s 0.01 MiB 0.10 MiB 0.01 MiB SKIP 73 5 SKIP 64 4 SKIP 0.01 ms 105.27 mW 784908.96 pJ 0.061 s 0.01 MiB 0.01 MiB 6 4 304000.00 samples/s 0.00 ms 48.12 mW 184972.16 pJ/it
64 gemm/large gemm/bias_rank2_broadcast arch-a 0.068 s PASS FAIL 0.061 s 0.02 MiB 0.00 MiB 0.03 MiB 0.01 MiB SKIP 17 5 SKIP 16 4 SKIP 0.01 ms 105.98 mW 749484.96 pJ 0.058 s 0.01 MiB 0.01 MiB 6 4 351000.00 samples/s 0.00 ms 52.58 mW 176636.66 pJ/it
65 gemm/large_k_small_n gemm/dynamic arch-a 0.095 s PASS FAIL 0.053 s 0.01 MiB 0.00 MiB 0.01 MiB 0.00 MiB SKIP 9 5 SKIP 8 0 SKIP 0.00 ms 91.48 mW 221475.00 pJ 0.056 s 0.00 MiB 0.00 MiB 5 0 785000.00 samples/s 0.00 ms 20.31 mW 27813.50 pJ/it
66 gemm/non_square gemm/dynamic_alpha arch-a 0.063 s PASS FAIL 0.055 s 0.00 MiB 0.01 MiB 0.00 MiB SKIP 5 SKIP 4 0 SKIP 0.00 ms 91.42 mW 298198.00 pJ 0.056 s 0.00 MiB 0.00 MiB 5 0 612000.00 samples/s 0.00 ms 20.35 mW 37289.67 pJ/it
67 gemm/scalar_bias gemm/dynamic_beta arch-a 0.060 s PASS FAIL 0.056 s 0.00 MiB 0.01 MiB 0.00 MiB SKIP 5 SKIP 4 0 SKIP 0.00 ms 91.32 mW 398595.00 pJ 0.056 s 0.00 MiB 0.00 MiB 5 0 359000.00 samples/s 0.00 ms 20.22 mW 60212.83 pJ/it
68 gemm/simple gemm/dynamic_bias arch-a 0.072 s PASS FAIL 0.055 s 0.03 MiB 0.00 MiB 0.08 MiB 0.00 MiB SKIP 42 5 SKIP 40 0 SKIP 0.00 ms 91.45 mW 243703.00 pJ 0.055 s 0.00 MiB 0.00 MiB 5 0 785000.00 samples/s 0.00 ms 20.32 mW 28385.00 pJ/it
69 gemm/small gemm/dynamic_bias_alpha_beta arch-a 0.065 s PASS FAIL 0.055 s 0.00 MiB 0.00 MiB SKIP 2 5 SKIP 2 0 SKIP 0.01 ms 91.28 mW 513811.00 pJ 0.056 s 0.00 MiB 0.00 MiB 5 0 247000.00 samples/s 0.00 ms 20.20 mW 85611.50 pJ/it
70 gemm/small_k_large_n gemm/dynamic_transpose_b arch-a 0.097 s PASS FAIL 0.053 s 0.01 MiB 0.00 MiB 0.02 MiB 0.00 MiB SKIP 17 5 SKIP 8 0 SKIP 0.00 ms 91.38 mW 118883.00 pJ 0.055 s 0.00 MiB 0.00 MiB 5 0 1340000.00 samples/s 0.00 ms 20.55 mW 16541.00 pJ/it
71 gemm/transA gemm/huge_1024 arch-a 0.064 s PASS FAIL 0.144 s 0.00 MiB 0.01 MiB 0.01 MiB 0.10 MiB SKIP 5 73 SKIP 4 64 SKIP 0.02 ms 215.04 mW 3767885.36 pJ 0.167 s 0.03 MiB 0.10 MiB 73 64 14900.00 samples/s 0.07 ms 154.31 mW 10866697.65 pJ/it
72 gemm/transA_transB gemm/large arch-a 0.069 s PASS FAIL 0.058 s 0.00 MiB 0.02 MiB 0.01 MiB 0.03 MiB SKIP 5 17 SKIP 4 16 SKIP 0.01 ms 140.15 mW 1573768.84 pJ 0.063 s 0.02 MiB 0.03 MiB 17 16 142000.00 samples/s 0.01 ms 118.27 mW 830693.99 pJ/it
73 gemm/transB gemm/large_k_small_n arch-a 0.062 s PASS FAIL 0.084 s 0.00 MiB 0.01 MiB 0.01 MiB SKIP 5 9 SKIP 4 8 SKIP 0.00 ms 133.48 mW 633769.92 pJ 0.089 s 0.01 MiB 0.01 MiB 9 8 439000.00 samples/s 0.00 ms 125.25 mW 329671.91 pJ/it
74 gemm/transB_with_bias gemm/non_square arch-a 0.055 s PASS FAIL 0.060 s 0.01 MiB 0.00 MiB 0.01 MiB SKIP 5 SKIP 4 SKIP 0.00 ms 118.96 mW 419565.96 pJ 0.060 s 0.00 MiB 0.01 MiB 5 4 486000.00 samples/s 0.00 ms 70.69 mW 160313.79 pJ/it
75 gemm/with_bias gemm/scalar_bias arch-a 0.067 s PASS FAIL 0.059 s 0.01 MiB 0.00 MiB 0.01 MiB SKIP 5 SKIP 4 SKIP 0.01 ms 105.98 mW 749484.96 pJ 0.056 s 0.01 MiB 0.01 MiB 6 4 351000.00 samples/s 0.00 ms 52.58 mW 176636.66 pJ/it
76 gemv/constant gemm/small arch-a 0.064 s PASS PASS 0.056 s 0.00 MiB 0.00 MiB SKIP 0 2 SKIP 0 2 SKIP 0.00 ms 90.14 mW 398436.48 pJ 0.055 s 0.00 MiB 0.00 MiB 4 2 464000.00 samples/s 0.00 ms 69.74 mW 162693.89 pJ/it
77 gemv/simple gemm/small_k_large_n arch-a 0.069 s PASS PASS 0.092 s 0.00 MiB 0.01 MiB 0.01 MiB 0.02 MiB SKIP 6 17 SKIP 4 8 SKIP 0.01 ms 131.01 mW 1043061.92 pJ 0.089 s 0.01 MiB 0.02 MiB 18 8 248000.00 samples/s 0.00 ms 82.00 mW 345641.89 pJ/it
78 gemv/with_heterogeneous_constant gemm/square_weights arch-a 0.066 s PASS FAIL 0.076 s 0.00 MiB 0.03 MiB 0.01 MiB 0.08 MiB SKIP 6 42 SKIP 4 40 SKIP 0.02 ms 151.77 mW 3284393.60 pJ - - - - - - - - -
79 gemv/with_homogeneous_constant gemm/transpose_a arch-a 0.070 s PASS FAIL 0.056 s 0.00 MiB 0.01 MiB SKIP 6 5 SKIP 4 SKIP 0.01 ms 109.14 mW 628868.96 pJ 0.057 s 0.00 MiB 0.01 MiB 6 4 424000.00 samples/s 0.00 ms 58.98 mW 162091.12 pJ/it
80 gemv/with_scalar_constant gemm/transpose_a_and_b arch-a 0.070 s PASS FAIL 0.055 s 0.00 MiB 0.01 MiB SKIP 6 5 SKIP 4 SKIP 0.01 ms 109.14 mW 628868.96 pJ 0.056 s 0.00 MiB 0.01 MiB 6 4 424000.00 samples/s 0.00 ms 58.98 mW 162091.12 pJ/it
81 matmul/basic gemm/transpose_b arch-a 0.062 s PASS FAIL 0.061 s 0.00 MiB 0.00 MiB 0.01 MiB SKIP 2 5 SKIP 2 4 SKIP 0.00 ms 118.96 mW 419565.96 pJ 0.059 s 0.00 MiB 0.01 MiB 5 4 486000.00 samples/s 0.00 ms 70.69 mW 160313.79 pJ/it
82 matmul/batched_3d gemm/transpose_b_with_bias arch-a 0.066 s PASS FAIL 0.064 s 0.00 MiB 0.01 MiB 0.01 MiB SKIP 5 SKIP 4 SKIP 0.01 ms 110.55 mW 557818.96 pJ 0.057 s 0.01 MiB 0.01 MiB 5 4 339000.00 samples/s 0.00 ms 55.18 mW 180359.12 pJ/it
83 matmul/batched_3d_dynamic gemm/with_bias arch-a 0.057 s PASS FAIL 0.050 s 0.00 MiB 0.01 MiB 0.00 MiB 0.01 MiB SKIP 4 5 SKIP 0 4 SKIP 0.01 ms 108.77 mW 604966.96 pJ 0.055 s 0.01 MiB 0.01 MiB 5 4 288000.00 samples/s 0.00 ms 52.44 mW 186098.45 pJ/it
84 matmul/batched_left_constant gemv/all_constant arch-a 0.070 s PASS PASS 0.050 s 0.00 MiB 0.02 MiB 0.00 MiB SKIP 9 0 SKIP 8 0 SKIP 0.00 ms 2.00 mW 0.00 pJ 0.052 s 0.00 MiB 0.00 MiB 0 0 0.00 samples/s 0.00 ms 2.00 mW 0.00 pJ/it
85 matmul/batched_lhs_broadcast gemv/constant_weight arch-a 0.063 s PASS FAIL 0.062 s 0.00 MiB 0.01 MiB SKIP 5 6 SKIP 4 SKIP 0.01 ms 111.15 mW 573535.96 pJ 0.063 s 0.00 MiB 0.01 MiB 8 4 412000.00 samples/s 0.00 ms 86.05 mW 242243.79 pJ/it
86 matmul/batched_rhs_broadcast gemv/non_uniform_bias arch-a 0.062 s PASS FAIL 0.063 s 0.00 MiB 0.01 MiB SKIP 5 6 SKIP 4 SKIP 0.01 ms 109.82 mW 609371.96 pJ 0.063 s 0.00 MiB 0.01 MiB 8 4 376000.00 samples/s 0.00 ms 82.45 mW 254539.29 pJ/it
87 matmul/dynamic gemv/scalar_bias arch-a 0.060 s PASS FAIL 0.063 s 0.00 MiB 0.00 MiB 0.01 MiB SKIP 5 6 SKIP 0 4 SKIP 0.01 ms 109.82 mW 609371.96 pJ 0.064 s 0.00 MiB 0.01 MiB 8 4 376000.00 samples/s 0.00 ms 82.45 mW 254539.29 pJ/it
88 matmul/huge_1024 gemv/uniform_bias arch-a 0.145 s PASS FAIL 0.064 s 0.01 MiB 0.00 MiB 0.10 MiB 0.01 MiB SKIP 73 6 SKIP 64 4 SKIP 0.01 ms 109.82 mW 609371.96 pJ 0.063 s 0.00 MiB 0.01 MiB 8 4 376000.00 samples/s 0.00 ms 82.45 mW 254539.29 pJ/it
89 matmul/left_constant matmul/basic arch-a 0.051 s PASS PASS 0.057 s 0.00 MiB 0.01 MiB 0.00 MiB SKIP 5 2 SKIP 4 2 SKIP 0.00 ms 90.14 mW 398436.48 pJ 0.056 s 0.00 MiB 0.00 MiB 4 2 464000.00 samples/s 0.00 ms 69.74 mW 162693.89 pJ/it
90 matmul/matrix_vector matmul/batched_3d arch-a 0.095 s PASS FAIL 0.058 s 0.52 MiB 0.00 MiB 0.78 MiB 0.01 MiB SKIP 168 5 SKIP 173 4 SKIP 0.01 ms 108.59 mW 646972.96 pJ 0.059 s 0.00 MiB 0.01 MiB 6 4 438000.00 samples/s 0.00 ms 59.21 mW 161865.62 pJ/it
91 matmul/vector_matrix matmul/batched_3d_dynamic arch-a 0.087 s PASS PASS 0.054 s 0.01 MiB 0.00 MiB 0.01 MiB 0.00 MiB SKIP 9 4 SKIP 8 0 SKIP 0.00 ms 92.19 mW 167975.00 pJ 0.054 s 0.00 MiB 0.00 MiB 5 0 1140000.00 samples/s 0.00 ms 17.43 mW 16336.83 pJ/it
92 matmul/yolo_attention matmul/batched_left_constant arch-a 0.385 s PASS FAIL 0.061 s 1.02 MiB 0.00 MiB 43.44 MiB 0.02 MiB SKIP 168 9 SKIP 0 8 SKIP 0.01 ms 114.39 mW 1009105.92 pJ - - - - - - - - -
93 mul/after_conv matmul/batched_lhs_broadcast arch-a 0.055 s PASS FAIL 0.057 s 0.00 MiB 0.00 MiB 0.01 MiB SKIP 4 5 SKIP 3 4 SKIP 0.01 ms 109.39 mW 621440.96 pJ 0.071 s 0.00 MiB 0.01 MiB 6 4 441000.00 samples/s 0.00 ms 60.34 mW 160658.62 pJ/it
94 mul/basic matmul/batched_rhs_broadcast arch-a 0.055 s PASS FAIL 0.056 s 0.00 MiB 0.00 MiB 0.01 MiB SKIP 1 5 SKIP 0 4 SKIP 0.01 ms 108.59 mW 646972.96 pJ 0.056 s 0.00 MiB 0.01 MiB 6 4 438000.00 samples/s 0.00 ms 59.21 mW 161865.62 pJ/it
95 mul/channel_broadcast_1024 matmul/dynamic arch-a 0.058 s PASS FAIL 0.055 s 0.02 MiB 0.00 MiB 0.01 MiB 0.00 MiB SKIP 1 5 SKIP 0 SKIP 0.00 ms 91.42 mW 148195.00 pJ 0.058 s 0.00 MiB 0.00 MiB 5 0 1310000.00 samples/s 0.00 ms 20.49 mW 18009.67 pJ/it
96 mul/leading_dimension_broadcast matmul/huge_1024 arch-a 0.059 s PASS FAIL 0.151 s 0.00 MiB 0.01 MiB 0.00 MiB 0.10 MiB SKIP 1 73 SKIP 0 64 SKIP 0.02 ms 215.04 mW 3767885.36 pJ 0.172 s 0.03 MiB 0.10 MiB 73 64 14900.00 samples/s 0.07 ms 154.31 mW 10866697.65 pJ/it
97 mul/scalar_constant matmul/left_constant arch-a 0.056 s PASS FAIL 0.058 s 0.00 MiB 0.00 MiB 0.01 MiB SKIP 1 5 SKIP 0 4 SKIP 0.01 ms 108.86 mW 637168.96 pJ 0.064 s 0.00 MiB 0.01 MiB 6 4 424000.00 samples/s 0.00 ms 58.67 mW 162346.12 pJ/it
98 pool/avg_basic matmul/matrix_vector arch-a 0.063 s PASS FAIL 0.102 s 0.00 MiB 0.52 MiB 0.00 MiB 0.78 MiB SKIP 1 168 SKIP 0 173 SKIP 0.38 ms 202.13 mW 77751814.88 pJ - - - - - - - - -
99 pool/avg_ceil_mode matmul/vector_matrix arch-a 0.063 s PASS FAIL 0.085 s 0.00 MiB 0.01 MiB 0.00 MiB 0.01 MiB SKIP 1 9 SKIP 0 8 SKIP 0.01 ms 118.68 mW 879301.92 pJ - - - - - - - - -
100 pool/avg_explicit_padding matmul/yolo_attention arch-a 0.061 s PASS FAIL 0.483 s 0.00 MiB 1.02 MiB 0.00 MiB 43.44 MiB SKIP 1 168 SKIP 0 SKIP 8.15 ms 170.00 mW 1385775865.00 pJ - - - - - - - - -
101 pool/avg_include_pad mul/after_conv arch-a 0.049 s PASS FAIL 0.074 s 0.00 MiB 0.00 MiB SKIP 1 4 SKIP 0 3 SKIP 0.01 ms 107.64 mW 586955.72 pJ 0.062 s 0.00 MiB 0.00 MiB 4 3 220000.00 samples/s 0.00 ms 34.96 mW 162998.05 pJ/it
102 pool/avg_large_channels mul/after_conv_scalar_constant arch-a 0.059 s PASS FAIL 0.063 s 0.04 MiB 0.00 MiB 0.02 MiB 0.00 MiB SKIP 1 4 SKIP 0 3 SKIP 0.01 ms 107.64 mW 586955.72 pJ 0.061 s 0.00 MiB 0.00 MiB 4 3 220000.00 samples/s 0.00 ms 34.96 mW 162998.05 pJ/it
103 pool/avg_non_uniform_stride mul/basic arch-a 0.066 s PASS PASS 0.055 s 0.00 MiB 0.00 MiB SKIP 1 SKIP 0 SKIP 0.00 ms 78.22 mW 25266.00 pJ 0.052 s 0.00 MiB 0.00 MiB 1 0 3120000.00 samples/s 0.00 ms 2.23 mW 658.67 pJ/it
104 pool/avg_real_asymmetric_padding mul/channel_broadcast_1024 arch-a 0.055 s PASS PASS 0.049 s 0.00 MiB 0.02 MiB 0.00 MiB 0.01 MiB SKIP 1 SKIP 0 SKIP 0.01 ms 78.12 mW 540030.00 pJ 0.049 s 0.02 MiB 0.01 MiB 1 0 145000.00 samples/s 0.01 ms 2.11 mW 13388.67 pJ/it
105 pool/max_after_conv mul/leading_dimension_broadcast arch-a 0.069 s PASS PASS 0.052 s 0.00 MiB 0.00 MiB SKIP 5 1 SKIP 4 0 SKIP 0.00 ms 78.22 mW 25266.00 pJ 0.053 s 0.00 MiB 0.00 MiB 1 0 3120000.00 samples/s 0.00 ms 2.23 mW 658.67 pJ/it
106 pool/max_basic mul/scalar_constant arch-a 0.064 s PASS PASS 0.055 s 0.00 MiB 0.00 MiB SKIP 1 SKIP 0 SKIP 0.00 ms 78.22 mW 25266.00 pJ 0.051 s 0.00 MiB 0.00 MiB 1 0 3120000.00 samples/s 0.00 ms 2.23 mW 658.67 pJ/it
107 pool/max_ceil_mode pool/avg_basic arch-a 0.058 s PASS PASS 0.057 s 0.00 MiB 0.00 MiB SKIP 1 SKIP 0 SKIP 0.01 ms 78.02 mW 931506.00 pJ 0.052 s 0.00 MiB 0.00 MiB 1 0 84000.00 samples/s 0.01 ms 2.02 mW 24067.00 pJ/it
108 pool/max_global_style_kernel_equals_input pool/avg_ceil_mode arch-a 0.063 s PASS PASS 0.055 s 0.00 MiB 0.00 MiB SKIP 1 SKIP 0 SKIP 0.00 ms 78.03 mW 340146.00 pJ 0.055 s 0.00 MiB 0.00 MiB 1 0 230000.00 samples/s 0.00 ms 2.03 mW 8810.67 pJ/it
109 pool/max_non_square_kernel pool/avg_explicit_padding arch-a 0.067 s PASS PASS 0.056 s 0.00 MiB 0.00 MiB SKIP 1 SKIP 0 SKIP 0.01 ms 78.03 mW 688356.00 pJ 0.058 s 0.00 MiB 0.00 MiB 1 0 114000.00 samples/s 0.01 ms 2.03 mW 17809.00 pJ/it
110 pool/max_real_asymmetric_padding pool/avg_include_pad arch-a 0.063 s PASS PASS 0.056 s 0.00 MiB 0.00 MiB SKIP 1 SKIP 0 SKIP 0.01 ms 78.02 mW 663612.00 pJ 0.058 s 0.00 MiB 0.00 MiB 1 0 118000.00 samples/s 0.01 ms 2.02 mW 17081.00 pJ/it
111 pool/max_same_upper pool/avg_large_channels arch-a 0.061 s PASS PASS 0.064 s 0.00 MiB 0.04 MiB 0.00 MiB 0.02 MiB SKIP 1 SKIP 0 SKIP 0.24 ms 78.00 mW 18399156.00 pJ 0.060 s 0.04 MiB 0.02 MiB 1 0 4250.00 samples/s 0.24 ms 2.00 mW 471428.00 pJ/it
112 pool/max_stride2_multichannel pool/avg_non_uniform_stride arch-a 0.076 s PASS PASS 0.055 s 0.00 MiB 0.00 MiB SKIP 1 SKIP 0 SKIP 0.01 ms 78.02 mW 1132254.00 pJ 0.052 s 0.00 MiB 0.00 MiB 1 0 69100.00 samples/s 0.01 ms 2.02 mW 29191.00 pJ/it
113 reduce_mean/4d_spatial pool/avg_real_asymmetric_padding arch-a 0.058 s PASS PASS 0.055 s 0.00 MiB 0.00 MiB SKIP 3 1 SKIP 0 SKIP 0.03 ms 78.02 mW 1966692.00 pJ 0.057 s 0.00 MiB 0.00 MiB 1 0 39700.00 samples/s 0.03 ms 2.02 mW 50961.00 pJ/it
114 reduce_mean/4d_spatial_keepdims_0 pool/max_after_conv arch-a 0.068 s PASS FAIL 0.059 s 0.00 MiB 0.00 MiB SKIP 4 5 SKIP 0 4 SKIP 0.01 ms 99.12 mW 1210689.96 pJ 0.061 s 0.00 MiB 0.00 MiB 5 4 142000.00 samples/s 0.01 ms 34.60 mW 273954.62 pJ/it
115 reduce_mean/after_conv pool/max_basic arch-a 0.067 s PASS PASS 0.053 s 0.00 MiB 0.00 MiB SKIP 5 1 SKIP 3 0 SKIP 0.00 ms 78.06 mW 324744.00 pJ 0.052 s 0.00 MiB 0.00 MiB 1 0 241000.00 samples/s 0.00 ms 2.06 mW 8532.67 pJ/it
116 reduce_mean/all_axes_keepdims_0 pool/max_ceil_mode arch-a 0.057 s PASS PASS 0.051 s 0.00 MiB 0.00 MiB SKIP 2 1 SKIP 0 SKIP 0.00 ms 78.07 mW 151464.00 pJ 0.049 s 0.00 MiB 0.00 MiB 1 0 516000.00 samples/s 0.00 ms 2.07 mW 3972.67 pJ/it
117 reduce_mean/all_axes_keepdims_1 pool/max_global_style_kernel_equals_input arch-a 0.053 s PASS PASS 0.054 s 0.00 MiB 0.00 MiB SKIP 1 SKIP 0 SKIP 0.01 ms 78.01 mW 658626.00 pJ 0.056 s 0.00 MiB 0.00 MiB 1 0 119000.00 samples/s 0.01 ms 2.01 mW 16871.00 pJ/it
118 reduce_mean/basic pool/max_non_square_kernel arch-a 0.058 s PASS PASS 0.052 s 0.00 MiB 0.00 MiB SKIP 4 1 SKIP 0 SKIP 0.01 ms 78.02 mW 1063068.00 pJ 0.051 s 0.00 MiB 0.00 MiB 1 0 73600.00 samples/s 0.01 ms 2.02 mW 27417.00 pJ/it
119 reduce_mean/channel_axis_nchw pool/max_real_asymmetric_padding arch-a 0.063 s PASS PASS 0.054 s 0.03 MiB 0.00 MiB 0.02 MiB 0.00 MiB SKIP 4 1 SKIP 0 SKIP 0.01 ms 78.03 mW 814992.00 pJ 0.058 s 0.00 MiB 0.00 MiB 1 0 96100.00 samples/s 0.01 ms 2.03 mW 21173.00 pJ/it
120 reduce_mean/keepdims_0 pool/max_same_upper arch-a 0.064 s PASS PASS 0.057 s 0.00 MiB 0.00 MiB SKIP 5 1 SKIP 0 SKIP 0.01 ms 78.04 mW 625068.00 pJ 0.052 s 0.00 MiB 0.00 MiB 1 0 125000.00 samples/s 0.01 ms 2.04 mW 16233.00 pJ/it
121 reduce_mean/large_dimension_1024 pool/max_stride2_multichannel arch-a 0.066 s PASS PASS 0.051 s 0.01 MiB 0.00 MiB 0.00 MiB SKIP 1 SKIP 0 SKIP 0.02 ms 78.02 mW 1247274.00 pJ 0.051 s 0.00 MiB 0.00 MiB 1 0 62700.00 samples/s 0.02 ms 2.02 mW 32153.00 pJ/it
122 reduce_mean/legacy_axes_1_2_keepdims_1 reduce_mean/4d_spatial arch-a 0.069 s PASS FAIL 0.053 s 0.00 MiB 0.00 MiB SKIP 2 3 SKIP 0 SKIP 0.00 ms 92.45 mW 29676.00 pJ 0.055 s 0.00 MiB 0.00 MiB 3 0 2560000.00 samples/s 0.00 ms 4.38 mW 1667.33 pJ/it
123 reduce_mean/legacy_axis1_keepdims_0 reduce_mean/4d_spatial_keepdims_0 arch-a 0.067 s PASS FAIL 0.052 s 0.00 MiB 0.00 MiB SKIP 9 4 SKIP 0 SKIP 0.00 ms 94.35 mW 61801.00 pJ 0.053 s 0.00 MiB 0.00 MiB 4 0 2390000.00 samples/s 0.00 ms 19.52 mW 9025.83 pJ/it
124 reduce_mean/legacy_axis1_keepdims_1 reduce_mean/after_conv arch-a 0.057 s PASS FAIL 0.059 s 0.00 MiB 0.00 MiB SKIP 8 5 SKIP 0 3 SKIP 0.01 ms 106.95 mW 571332.72 pJ 0.063 s 0.00 MiB 0.00 MiB 5 3 220000.00 samples/s 0.00 ms 21.90 mW 102726.72 pJ/it
125 reduce_mean/legacy_empty_axes_noop reduce_mean/all_axes_keepdims_0 arch-a 0.058 s PASS PASS 0.050 s 0.00 MiB 0.00 MiB SKIP 1 2 SKIP 0 SKIP 0.00 ms 79.24 mW 30982.00 pJ 0.052 s 0.00 MiB 0.00 MiB 2 0 4520000.00 samples/s 0.00 ms 3.41 mW 775.00 pJ/it
126 reduce_mean/legacy_nchw_spatial reduce_mean/all_axes_keepdims_1 arch-a 0.059 s PASS PASS 0.052 s 0.00 MiB 0.00 MiB SKIP 3 1 SKIP 0 SKIP 0.00 ms 78.22 mW 17286.00 pJ 0.048 s 0.00 MiB 0.00 MiB 1 0 4570000.00 samples/s 0.00 ms 2.22 mW 437.33 pJ/it
127 reduce_mean/legacy_negative_axis reduce_mean/basic arch-a 0.052 s PASS FAIL 0.052 s 0.00 MiB 0.00 MiB SKIP 6 4 SKIP 0 SKIP 0.00 ms 93.51 mW 34881.00 pJ 0.053 s 0.00 MiB 0.00 MiB 4 0 2780000.00 samples/s 0.00 ms 5.56 mW 1904.50 pJ/it
128 reduce_mean/legacy_reduce_all_keepdims_1 reduce_mean/channel_axis_nchw arch-a 0.057 s PASS FAIL 0.052 s 0.00 MiB 0.03 MiB 0.00 MiB 0.02 MiB SKIP 1 4 SKIP 0 SKIP 0.16 ms 93.60 mW 15436518.00 pJ 0.055 s 0.03 MiB 0.08 MiB 4 0 16000.00 samples/s 0.06 ms 5.00 mW 323993.33 pJ/it
129 reduce_mean/negative_axis reduce_mean/keepdims_0 arch-a 0.055 s PASS FAIL 0.055 s 0.00 MiB 0.00 MiB SKIP 6 5 SKIP 0 SKIP 0.00 ms 91.40 mW 68368.00 pJ 0.054 s 0.00 MiB 0.00 MiB 5 0 1880000.00 samples/s 0.00 ms 20.60 mW 11458.17 pJ/it
130 relu/4d reduce_mean/large_dimension_1024 arch-a 0.059 s PASS PASS 0.053 s 0.00 MiB 0.01 MiB 0.00 MiB SKIP 1 SKIP 0 SKIP 0.00 ms 78.02 mW 217278.00 pJ 0.052 s 0.01 MiB 0.00 MiB 1 0 359000.00 samples/s 0.00 ms 2.02 mW 5274.00 pJ/it
131 relu/after_conv reduce_mean/legacy_axes_1_2_keepdims_1 arch-a 0.062 s PASS FAIL 0.052 s 0.00 MiB 0.00 MiB SKIP 4 2 SKIP 3 0 SKIP 0.00 ms 79.35 mW 21505.00 pJ 0.052 s 0.00 MiB 0.00 MiB 2 0 3860000.00 samples/s 0.00 ms 3.37 mW 798.00 pJ/it
132 relu/after_gemm reduce_mean/legacy_axis1_keepdims_0 arch-a 0.062 s PASS FAIL 0.071 s 0.01 MiB 0.00 MiB 0.01 MiB 0.00 MiB SKIP 5 9 SKIP 4 0 SKIP 0.00 ms 92.50 mW 183708.00 pJ 0.061 s 0.00 MiB 0.00 MiB 9 0 1010000.00 samples/s 0.00 ms 38.63 mW 41198.50 pJ/it
133 relu/basic reduce_mean/legacy_axis1_keepdims_1 arch-a 0.062 s PASS FAIL 0.053 s 0.00 MiB 0.00 MiB SKIP 1 8 SKIP 0 SKIP 0.00 ms 94.56 mW 129830.00 pJ 0.054 s 0.00 MiB 0.00 MiB 8 0 1390000.00 samples/s 0.00 ms 9.56 mW 6733.50 pJ/it
134 reshape/4d_to_2d_flatten reduce_mean/legacy_empty_axes_noop arch-a 0.059 s PASS PASS 0.050 s 0.00 MiB 0.00 MiB SKIP 1 SKIP 0 SKIP 0.00 ms 78.22 mW 17286.00 pJ 0.048 s 0.00 MiB 0.00 MiB 1 0 4570000.00 samples/s 0.00 ms 2.22 mW 437.33 pJ/it
135 reshape/infer_dim_minus_one reduce_mean/legacy_nchw_spatial arch-a 0.059 s PASS FAIL 0.054 s 0.00 MiB 0.00 MiB SKIP 1 3 SKIP 0 SKIP 0.00 ms 92.45 mW 29676.00 pJ 0.056 s 0.00 MiB 0.00 MiB 3 0 1960000.00 samples/s 0.00 ms 4.28 mW 2167.33 pJ/it
136 reshape/same_rank reduce_mean/legacy_negative_axis arch-a 0.056 s PASS FAIL 0.051 s 0.00 MiB 0.00 MiB SKIP 1 6 SKIP 0 SKIP 0.00 ms 93.52 mW 51717.00 pJ 0.057 s 0.00 MiB 0.00 MiB 6 0 1850000.00 samples/s 0.00 ms 7.57 mW 3828.83 pJ/it
137 reshape/zero_copies_input_dim reduce_mean/legacy_reduce_all_keepdims_1 arch-a 0.077 s PASS PASS 0.051 s 0.00 MiB 0.00 MiB SKIP 1 SKIP 0 SKIP 0.00 ms 78.22 mW 17286.00 pJ 0.048 s 0.00 MiB 0.00 MiB 1 0 4570000.00 samples/s 0.00 ms 2.22 mW 437.33 pJ/it
138 resize/height_only reduce_mean/negative_axis arch-a 0.059 s PASS FAIL 0.058 s 0.00 MiB 0.00 MiB SKIP 4 6 SKIP 0 SKIP 0.00 ms 93.52 mW 51717.00 pJ 0.054 s 0.00 MiB 0.00 MiB 6 0 1850000.00 samples/s 0.00 ms 7.57 mW 3828.83 pJ/it
139 resize/nearest_2x relu/4d arch-a 0.066 s PASS PASS 0.052 s 0.00 MiB 0.00 MiB SKIP 4 1 SKIP 0 SKIP 0.00 ms 78.18 mW 40734.00 pJ 0.049 s 0.00 MiB 0.00 MiB 1 0 1930000.00 samples/s 0.00 ms 2.18 mW 1014.00 pJ/it
140 resize/nearest_downsample relu/after_conv arch-a 0.062 s PASS FAIL 0.058 s 0.00 MiB 0.00 MiB SKIP 2 4 SKIP 0 3 SKIP 0.01 ms 107.89 mW 577437.72 pJ 0.060 s 0.00 MiB 0.00 MiB 4 3 220000.00 samples/s 0.00 ms 34.98 mW 162801.39 pJ/it
141 resize/non_uniform relu/after_gemm arch-a 0.069 s PASS FAIL 0.061 s 0.00 MiB 0.01 MiB 0.00 MiB 0.01 MiB SKIP 6 5 SKIP 0 4 SKIP 0.01 ms 105.16 mW 790056.96 pJ 0.059 s 0.01 MiB 0.01 MiB 6 4 291000.00 samples/s 0.00 ms 47.08 mW 187063.49 pJ/it
142 resize/width_only relu/basic arch-a 0.055 s PASS PASS 0.052 s 0.00 MiB 0.00 MiB SKIP 2 1 SKIP 0 SKIP 0.00 ms 78.22 mW 17286.00 pJ 0.050 s 0.00 MiB 0.00 MiB 1 0 4570000.00 samples/s 0.00 ms 2.22 mW 437.33 pJ/it
143 resize/with_sizes reshape/4d_to_2d_flatten arch-a 0.060 s PASS PASS 0.047 s 0.00 MiB 0.00 MiB SKIP 3 1 SKIP 0 SKIP 0.00 ms 78.28 mW 20196.00 pJ 0.050 s 0.00 MiB 0.00 MiB 1 0 3910000.00 samples/s 0.00 ms 2.28 mW 488.00 pJ/it
144 sigmoid/4d reshape/infer_dim_minus_one arch-a 0.060 s PASS PASS 0.054 s 0.00 MiB 0.00 MiB SKIP 1 SKIP 0 SKIP 0.00 ms 78.30 mW 12684.00 pJ 0.048 s 0.00 MiB 0.00 MiB 1 0 6250000.00 samples/s 0.00 ms 2.30 mW 308.00 pJ/it
145 sigmoid/after_gemm reshape/same_rank arch-a 0.059 s PASS PASS 0.056 s 0.01 MiB 0.00 MiB 0.01 MiB 0.00 MiB SKIP 5 1 SKIP 4 0 SKIP 0.00 ms 78.30 mW 12684.00 pJ 0.048 s 0.00 MiB 0.00 MiB 1 0 6250000.00 samples/s 0.00 ms 2.30 mW 308.00 pJ/it
146 sigmoid/basic reshape/zero_copies_input_dim arch-a 0.053 s PASS PASS 0.056 s 0.00 MiB 0.00 MiB SKIP 1 SKIP 0 SKIP 0.00 ms 78.30 mW 12684.00 pJ 0.056 s 0.00 MiB 0.00 MiB 1 0 6250000.00 samples/s 0.00 ms 2.30 mW 308.00 pJ/it
147 slice/2d_basic resize/height_only arch-a 0.058 s PASS FAIL 0.054 s 0.00 MiB 0.00 MiB SKIP 1 4 SKIP 0 SKIP 0.00 ms 93.55 mW 64833.00 pJ 0.055 s 0.00 MiB 0.00 MiB 4 0 2430000.00 samples/s 0.00 ms 5.46 mW 2298.25 pJ/it
148 slice/after_conv resize/nearest_2x arch-a 0.070 s PASS FAIL 0.055 s 0.00 MiB 0.01 MiB 0.00 MiB SKIP 7 4 SKIP 6 0 SKIP 0.00 ms 93.57 mW 109761.00 pJ 0.051 s 0.00 MiB 0.00 MiB 4 0 1760000.00 samples/s 0.00 ms 5.33 mW 3085.12 pJ/it
149 slice/default_axes resize/nearest_downsample arch-a 0.066 s PASS FAIL 0.054 s 0.00 MiB 0.00 MiB SKIP 1 2 SKIP 0 SKIP 0.00 ms 79.45 mW 33925.00 pJ 0.052 s 0.00 MiB 0.00 MiB 2 0 2420000.00 samples/s 0.00 ms 3.22 mW 1262.50 pJ/it
150 slice/large_channel_1024 resize/non_uniform_scales arch-a 0.064 s PASS FAIL 0.054 s 0.01 MiB 0.00 MiB 0.00 MiB SKIP 1 6 SKIP 0 SKIP 0.00 ms 93.58 mW 164037.00 pJ 0.055 s 0.00 MiB 0.00 MiB 6 0 1750000.00 samples/s 0.00 ms 7.49 mW 4551.90 pJ/it
151 slice/nchw_spatial_crop resize/width_only arch-a 0.055 s PASS FAIL 0.051 s 0.00 MiB 0.00 MiB SKIP 1 2 SKIP 0 SKIP 0.00 ms 79.50 mW 53029.00 pJ 0.052 s 0.00 MiB 0.00 MiB 2 0 1750000.00 samples/s 0.00 ms 3.16 mW 1735.50 pJ/it
152 slice/negative_axis resize/with_sizes arch-a 0.060 s PASS FAIL 0.054 s 0.00 MiB 0.00 MiB SKIP 1 3 SKIP 0 SKIP 0.00 ms 92.54 mW 73756.00 pJ 0.056 s 0.00 MiB 0.00 MiB 3 0 1930000.00 samples/s 0.00 ms 4.27 mW 2196.00 pJ/it
153 slice/negative_indices sigmoid/4d arch-a 0.053 s PASS PASS 0.050 s 0.00 MiB 0.00 MiB SKIP 1 SKIP 0 SKIP 0.00 ms 78.18 mW 40734.00 pJ 0.055 s 0.00 MiB 0.00 MiB 1 0 1930000.00 samples/s 0.00 ms 2.18 mW 1014.00 pJ/it
154 slice/step2 sigmoid/after_gemm arch-a 0.058 s PASS FAIL 0.056 s 0.00 MiB 0.01 MiB 0.00 MiB 0.01 MiB SKIP 1 5 SKIP 0 4 SKIP 0.01 ms 105.16 mW 790056.96 pJ 0.058 s 0.01 MiB 0.01 MiB 6 4 291000.00 samples/s 0.00 ms 47.08 mW 187063.49 pJ/it
155 softmax/3d_last_axis sigmoid/basic arch-a 0.050 s PASS PASS 0.053 s 0.00 MiB 0.00 MiB SKIP 1 SKIP 0 SKIP 0.00 ms 78.22 mW 17286.00 pJ 0.049 s 0.00 MiB 0.00 MiB 1 0 4570000.00 samples/s 0.00 ms 2.22 mW 437.33 pJ/it
156 softmax/basic slice/2d_basic arch-a 0.061 s PASS PASS 0.051 s 0.00 MiB 0.00 MiB SKIP 1 SKIP 0 SKIP 0.00 ms 78.30 mW 18948.00 pJ 0.048 s 0.00 MiB 0.00 MiB 1 0 4170000.00 samples/s 0.00 ms 2.30 mW 491.67 pJ/it
157 softmax/channel_axis slice/after_conv arch-a 0.058 s PASS FAIL 0.062 s 0.00 MiB 0.00 MiB 0.01 MiB SKIP 1 7 SKIP 0 6 SKIP 0.01 ms 118.19 mW 1335082.88 pJ 0.069 s 0.00 MiB 0.01 MiB 7 6 130000.00 samples/s 0.01 ms 58.48 mW 484364.44 pJ/it
158 softmax/large_dimension_1024 slice/default_axes arch-a 0.061 s PASS PASS 0.051 s 0.01 MiB 0.00 MiB 0.01 MiB 0.00 MiB SKIP 1 SKIP 0 SKIP 0.00 ms 78.30 mW 18948.00 pJ 0.052 s 0.00 MiB 0.00 MiB 1 0 4170000.00 samples/s 0.00 ms 2.30 mW 491.67 pJ/it
159 softmax/negative_axis slice/large_channel_1024 arch-a 0.058 s PASS PASS 0.051 s 0.00 MiB 0.01 MiB 0.00 MiB SKIP 1 SKIP 0 SKIP 0.00 ms 78.14 mW 221304.00 pJ 0.050 s 0.01 MiB 0.00 MiB 1 0 353000.00 samples/s 0.00 ms 2.14 mW 5058.00 pJ/it
160 split/basic slice/nchw_spatial_crop arch-a 0.059 s PASS PASS 0.053 s 0.00 MiB 0.00 MiB SKIP 1 SKIP 0 SKIP 0.00 ms 78.24 mW 101868.00 pJ 0.047 s 0.00 MiB 0.00 MiB 1 0 769000.00 samples/s 0.00 ms 2.24 mW 2851.67 pJ/it
161 split/equal_three_way slice/negative_axis arch-a 0.063 s PASS PASS 0.050 s 0.00 MiB 0.00 MiB SKIP 1 SKIP 0 SKIP 0.00 ms 78.30 mW 44004.00 pJ 0.049 s 0.00 MiB 0.00 MiB 1 0 1790000.00 samples/s 0.00 ms 2.30 mW 1227.67 pJ/it
162 split/negative_axis slice/negative_indices arch-a 0.059 s PASS PASS 0.048 s 0.00 MiB 0.00 MiB SKIP 1 SKIP 0 SKIP 0.00 ms 78.30 mW 25212.00 pJ 0.051 s 0.00 MiB 0.00 MiB 1 0 3120000.00 samples/s 0.00 ms 2.30 mW 675.67 pJ/it
163 split/uneven_channel_axis_4d slice/step2 arch-a 0.061 s PASS PASS 0.053 s 0.00 MiB 0.00 MiB SKIP 1 SKIP 0 SKIP 0.00 ms 78.29 mW 159876.00 pJ 0.052 s 0.00 MiB 0.00 MiB 1 0 490000.00 samples/s 0.00 ms 2.29 mW 4619.67 pJ/it
164 sub/after_gemm softmax/3d_last_axis arch-a 0.064 s PASS PASS 0.052 s 0.01 MiB 0.00 MiB 0.01 MiB 0.00 MiB SKIP 5 1 SKIP 4 0 SKIP UNSUPPORTED UNSUPPORTED UNSUPPORTED 0.053 s 0.00 MiB 0.00 MiB 1 0 UNSUPPORTED UNSUPPORTED UNSUPPORTED UNSUPPORTED
165 sub/basic softmax/basic arch-a 0.054 s PASS PASS 0.050 s 0.00 MiB 0.00 MiB SKIP 1 SKIP 0 SKIP UNSUPPORTED UNSUPPORTED UNSUPPORTED 0.053 s 0.00 MiB 0.00 MiB 1 0 UNSUPPORTED UNSUPPORTED UNSUPPORTED UNSUPPORTED
166 sub/broadcast_row softmax/channel_axis arch-a 0.064 s PASS FAIL 0.051 s 0.00 MiB 0.00 MiB SKIP 1 SKIP 0 SKIP UNSUPPORTED UNSUPPORTED UNSUPPORTED 0.052 s 0.00 MiB 0.00 MiB 3 0 UNSUPPORTED UNSUPPORTED UNSUPPORTED UNSUPPORTED
167 sub/channel_broadcast_1024 softmax/large_dimension_1024 arch-a 0.063 s PASS PASS 0.049 s 0.02 MiB 0.01 MiB 0.01 MiB SKIP 1 SKIP 0 SKIP UNSUPPORTED UNSUPPORTED UNSUPPORTED 0.052 s 0.01 MiB 0.01 MiB 1 0 UNSUPPORTED UNSUPPORTED UNSUPPORTED UNSUPPORTED
168 sub/constant_lhs_broadcast softmax/negative_axis arch-a 0.054 s PASS PASS 0.050 s 0.00 MiB 0.00 MiB SKIP 1 SKIP 0 SKIP UNSUPPORTED UNSUPPORTED UNSUPPORTED 0.049 s 0.00 MiB 0.00 MiB 1 0 UNSUPPORTED UNSUPPORTED UNSUPPORTED UNSUPPORTED
169 sub/leading_dimension_broadcast split/basic arch-a 0.054 s PASS PASS 0.048 s 0.00 MiB 0.00 MiB SKIP 1 SKIP 0 SKIP 0.00 ms 78.30 mW 31554.00 pJ 0.052 s 0.00 MiB 0.00 MiB 1 0 2490000.00 samples/s 0.00 ms 2.30 mW 861.67 pJ/it
170 split/equal_three_way arch-a PASS PASS 0.049 s 0.00 MiB 0.00 MiB 1 0 0.00 ms 78.30 mW 44160.00 pJ 0.052 s 0.00 MiB 0.00 MiB 1 0 1780000.00 samples/s 0.00 ms 2.30 mW 1231.67 pJ/it
171 split/negative_axis arch-a PASS PASS 0.051 s 0.00 MiB 0.00 MiB 1 0 0.00 ms 78.29 mW 84786.00 pJ 0.050 s 0.00 MiB 0.00 MiB 1 0 925000.00 samples/s 0.00 ms 2.29 mW 2413.67 pJ/it
172 split/uneven_channel_axis_4d arch-a PASS PASS 0.051 s 0.00 MiB 0.00 MiB 1 0 0.00 ms 78.30 mW 18948.00 pJ 0.049 s 0.00 MiB 0.00 MiB 1 0 4170000.00 samples/s 0.00 ms 2.30 mW 491.67 pJ/it
173 sub/after_gemm arch-a PASS FAIL 0.058 s 0.01 MiB 0.01 MiB 5 4 0.01 ms 104.70 mW 815012.96 pJ 0.057 s 0.01 MiB 0.01 MiB 6 4 277000.00 samples/s 0.00 ms 45.81 mW 190085.16 pJ/it
174 sub/basic arch-a PASS PASS 0.049 s 0.00 MiB 0.00 MiB 1 0 0.00 ms 78.22 mW 25266.00 pJ 0.048 s 0.00 MiB 0.00 MiB 1 0 3120000.00 samples/s 0.00 ms 2.23 mW 658.67 pJ/it
175 sub/broadcast_row arch-a PASS PASS 0.049 s 0.00 MiB 0.00 MiB 1 0 0.00 ms 78.22 mW 25266.00 pJ 0.051 s 0.00 MiB 0.00 MiB 1 0 3120000.00 samples/s 0.00 ms 2.23 mW 658.67 pJ/it
176 sub/channel_broadcast_1024 arch-a PASS PASS 0.058 s 0.02 MiB 0.01 MiB 1 0 0.01 ms 78.12 mW 540030.00 pJ 0.053 s 0.02 MiB 0.01 MiB 1 0 145000.00 samples/s 0.01 ms 2.11 mW 13388.67 pJ/it
177 sub/constant_lhs_broadcast arch-a PASS PASS 0.049 s 0.00 MiB 0.00 MiB 1 0 0.00 ms 78.22 mW 25188.00 pJ 0.051 s 0.00 MiB 0.00 MiB 1 0 3120000.00 samples/s 0.00 ms 2.23 mW 656.67 pJ/it
178 sub/leading_dimension_broadcast arch-a PASS PASS 0.050 s 0.00 MiB 0.00 MiB 1 0 0.00 ms 78.22 mW 25266.00 pJ 0.050 s 0.00 MiB 0.00 MiB 1 0 3120000.00 samples/s 0.00 ms 2.23 mW 658.67 pJ/it