为x86 CPU自动调度神经网络
对特定设备和工作负载进行自动调试对于获得最佳性能至关重要。这是有关如何使用自动调度器为x86 CPU调试整个神经网络的文档。
为了自动调试神经网络，将网络划分为小的子图，并对其进行独立调试。每个子图被视为一个搜索任务。任务调度程序可以对时间进行分片，并为这些任务动态分配时间资源。任务调度程序可以预测每个任务对端到端执行时间的影响，并优先调度可以最大程度地减少执行时间的任务。
对于每个子图，使用compute声明tvm/python/topi获取张量表达式形式的计算DAG。然后，使用自动调度器来构造此DAG的搜索空间，并搜索良好的调度（低级优化）。
与依靠手动模板定义搜索空间的基于模板的autotvm不同，自动调度程序不需要任何调度模板。换句话说，自动调度程序仅在tvm/python/topi中使用计算声明，而不使用现有的调度模板。
注意，本文无法在Windows或最新版本的macOS上运行。要使其运行，需要将本文的内容包装在一个块中。if __name__ == "__main__":
import numpy as np
import tvm
from tvm import relay, auto_scheduler
import tvm.relay.testing
from tvm.contrib import graph_runtime
定义网络
首先，需要使用中继前端API定义网络。可以加载一些预定义的网络tvm.relay.testing。还可以从MXNet，ONNX，PyTorch和TensorFlow加载模型。
对于卷积神经网络，尽管自动调度程序可以在任何布局下正常工作，但使用NHWC布局通常可以实现最佳性能。还使用自动调度程序对NHWC布局实施了更多优化。因此，建议将模型转换为NHWC布局以使用自动调度程序。可以在TVM中使用ConvertLayout pass进行布局转换。
def get_network(name, batch_size, layout="NHWC", dtype="float32"):
"""Get the symbol definition and random weight of a network"""
# auto-scheduler prefers NHWC layout
if layout == "NHWC":
image_shape = (224, 224, 3)
elif layout == "NCHW":
image_shape = (3, 224, 224)
else:
raise ValueError("Invalid layout: " + layout)
input_shape = (batch_size,) + image_shape
output_shape = (batch_size, 1000)
if name.startswith("resnet-"):
n_layer = int(name.split("-")[1])
mod, params = relay.testing.resnet.get_workload(
num_layers=n_layer,
batch_size=batch_size,
layout=layout,
dtype=dtype,
image_shape=image_shape,
)
elif name.startswith("resnet3d-"):
n_layer = int(name.split("-")[1])
mod, params = relay.testing.resnet.get_workload(
num_layers=n_layer,
batch_size=batch_size,
layout=layout,
dtype=dtype,
image_shape=image_shape,
)
elif name == "mobilenet":
mod, params = relay.testing.mobilenet.get_workload(
batch_size=batch_size, layout=layout, dtype=dtype, image_shape=image_shape
)
elif name == "squeezenet_v1.1":
assert layout == "NCHW", "squeezenet_v1.1 only supports NCHW layout"
mod, params = relay.testing.squeezenet.get_workload(
version="1.1",
batch_size=batch_size,
dtype=dtype,
image_shape=image_shape,
)
elif name == "inception_v3":
input_shape = (batch_size, 3, 299, 299) if layout == "NCHW" else (batch_size, 299, 299, 3)
mod, params = relay.testing.inception_v3.get_workload(batch_size=batch_size, dtype=dtype)
elif name == "mxnet":
# an example for mxnet model
from mxnet.gluon.model_zoo.vision import get_model
assert layout == "NCHW"
block = get_model("resnet50_v1", pretrained=True)
mod, params = relay.frontend.from_mxnet(block, shape={"data": input_shape}, dtype=dtype)
net = mod["main"]
net = relay.Function(
net.params, relay.nn.softmax(net.body), None, net.type_params, net.attrs
)
mod = tvm.IRModule.from_expr(net)
return mod, params, input_shape, output_shape
# Define the neural network and compilation target.
# If the target machine supports avx512 instructions, replace the
# "llvm -mcpu=core-avx2" with "llvm -mcpu=skylake-avx512"
network = "resnet-50"
batch_size = 1
layout = "NHWC"
target = tvm.target.Target("llvm -mcpu=core-avx2")
dtype = "float32"
log_file = "%s-%s-B%d-%s.json" % (network, layout, batch_size, target.kind.name)
提取搜索任务
接下来，从网络中提取搜索任务及其权重。任务的权重是整个网络中任务子图的出现次数。通过使用权重，可以将网络的端到端延迟近似为sum(latency[t] * weight[t])，其中latency[t]是任务的延迟，weight[t]是任务的权重。任务调度程序只会优化此目标。
# Extract tasks from the network
print("Extract tasks...")
mod, params, input_shape, output_shape = get_network(network, batch_size, layout, dtype=dtype)
tasks, task_weights = auto_scheduler.extract_tasks(mod["main"], params, target)
for idx, task in enumerate(tasks):
print("========== Task %d (workload key: %s) ==========" % (idx, task.workload_key))
print(task.compute_dag)
出：
Extract tasks...
========== Task 0 (workload key: ["b32ed43fb351136894c322ee49097a1a"]) ==========
placeholder = PLACEHOLDER [1, 1000]
T_softmax_maxelem(i0) max= placeholder[i0, k]
T_softmax_exp(i0, i1) = tir.exp((placeholder[i0, i1] - T_softmax_maxelem[i0]))
T_softmax_expsum(i0) += T_softmax_exp[i0, k]
T_softmax_norm(i0, i1) = (T_softmax_exp[i0, i1]/T_softmax_expsum[i0])
========== Task 1 (workload key: ["6129df1a3d5f6326c8393a8d17160199"]) ==========
placeholder = PLACEHOLDER [1, 2048]
placeholder = PLACEHOLDER [1000, 2048]
compute(z, y, x) += (placeholder[z, ((k*16) + x)]*placeholder[y, ((k*16) + x)])
compute(y, x) += compute[y, x, kk]
placeholder = PLACEHOLDER [1000]
T_add(ax0, ax1) = (compute[ax0, ax1] + placeholder[ax1])
========== Task 2 (workload key: ["36ee2798ed60bae3bcd1bb89a0285fe8"]) ==========
placeholder = PLACEHOLDER [1, 7, 7, 2048]
tensor(ax0, ax1, ax2, ax3) += placeholder[ax0, ((ax1*7) + rv0), ((ax2*7) + rv1), ax3]
tensor(ax0, ax1, ax2, ax3) = (tensor[ax0, ax1, ax2, ax3]/(float32((select((bool)1, ((ax1 + 1)*7), (((ax1 + 1)*7) + 1)) - (ax1*7)))*float32((select((bool)1, ((ax2 + 1)*7), (((ax2 + 1)*7) + 1)) - (ax2*7)))))
========== Task 3 (workload key: ["dcf6fcf5f56fa614bf9aef0c82382caf"]) ==========
placeholder = PLACEHOLDER [1, 7, 7, 512]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 512, 2048]
Conv2dOutput(nn, yy, xx, ff) += (PaddedInput[nn, (yy + ry), (xx + rx), rc]*placeholder[ry, rx, rc, ff])
placeholder = PLACEHOLDER [1, 7, 7, 2048]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, ax1, ax2, ax3])
placeholder = PLACEHOLDER [1, 1, 1, 2048]
T_multiply(ax0, ax1, ax2, ax3) = (T_add[ax0, ax1, ax2, ax3]*placeholder[ax0, 0, 0, ax3])
placeholder = PLACEHOLDER [1, 1, 1, 2048]
T_add(ax0, ax1, ax2, ax3) = (T_multiply[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
========== Task 4 (workload key: ["7e3f0cf5a6dd80d36dab1a3dad92674a"]) ==========
placeholder = PLACEHOLDER [1, 7, 7, 512]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 8)) && (i2 >= 1)) && (i2 < 8)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 512, 512]
Conv2dOutput(nn, yy, xx, ff) += (PaddedInput[nn, (yy + ry), (xx + rx), rc]*placeholder[ry, rx, rc, ff])
placeholder = PLACEHOLDER [1, 1, 1, 512]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
========== Task 5 (workload key: ["e0a9eb3795b531085e0ebb772e7e800c"]) ==========
placeholder = PLACEHOLDER [1, 7, 7, 2048]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 2048, 512]
Conv2dOutput(nn, yy, xx, ff) += (PaddedInput[nn, (yy + ry), (xx + rx), rc]*placeholder[ry, rx, rc, ff])
placeholder = PLACEHOLDER [1, 1, 1, 512]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
========== Task 6 (workload key: ["03614e726dc588d11887eb0953a77e53"]) ==========
placeholder = PLACEHOLDER [1, 7, 7, 512]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 512, 2048]
Conv2dOutput(nn, yy, xx, ff) += (PaddedInput[nn, (yy + ry), (xx + rx), rc]*placeholder[ry, rx, rc, ff])
placeholder = PLACEHOLDER [1, 7, 7, 2048]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, ax1, ax2, ax3])
========== Task 7 (workload key: ["7657f886f5e9d8b5f19a5fd2c5b90d8d"]) ==========
placeholder = PLACEHOLDER [1, 14, 14, 1024]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 1024, 512]
Conv2dOutput(nn, yy, xx, ff) += (PaddedInput[nn, ((yy*2) + ry), ((xx*2) + rx), rc]*placeholder[ry, rx, rc, ff])
placeholder = PLACEHOLDER [1, 1, 1, 512]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
========== Task 8 (workload key: ["7e09b626cf077cd419190fee02091dd6"]) ==========
placeholder = PLACEHOLDER [1, 14, 14, 256]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 256, 1024]
Conv2dOutput(nn, yy, xx, ff) += (PaddedInput[nn, (yy + ry), (xx + rx), rc]*placeholder[ry, rx, rc, ff])
placeholder = PLACEHOLDER [1, 14, 14, 1024]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, ax1, ax2, ax3])
placeholder = PLACEHOLDER [1, 1, 1, 1024]
T_add(ax0, ax1, ax2, ax3) = (T_add[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
========== Task 9 (workload key: ["95bf49cc8cf7a351e974b2359702aac0"]) ==========
placeholder = PLACEHOLDER [1, 14, 14, 256]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 15)) && (i2 >= 1)) && (i2 < 15)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 256, 256]
Conv2dOutput(nn, yy, xx, ff) += (PaddedInput[nn, (yy + ry), (xx + rx), rc]*placeholder[ry, rx, rc, ff])
placeholder = PLACEHOLDER [1, 1, 1, 256]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
========== Task 10 (workload key: ["e043f834cc7f19597227e09dc7f59503"]) ==========
placeholder = PLACEHOLDER [1, 14, 14, 1024]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 1024, 256]
Conv2dOutput(nn, yy, xx, ff) += (PaddedInput[nn, (yy + ry), (xx + rx), rc]*placeholder[ry, rx, rc, ff])
placeholder = PLACEHOLDER [1, 1, 1, 256]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
========== Task 11 (workload key: ["cd7c4a374fb2bbc0d075c8cae638ad14"]) ==========
placeholder = PLACEHOLDER [1, 14, 14, 256]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 256, 1024]
Conv2dOutput(nn, yy, xx, ff) += (PaddedInput[nn, (yy + ry), (xx + rx), rc]*placeholder[ry, rx, rc, ff])
placeholder = PLACEHOLDER [1, 14, 14, 1024]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, ax1, ax2, ax3])
========== Task 12 (workload key: ["1dce2c5e4269b8a12dfc50cd4dd23ff1"]) ==========
placeholder = PLACEHOLDER [1, 28, 28, 512]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 512, 256]
Conv2dOutput(nn, yy, xx, ff) += (PaddedInput[nn, ((yy*2) + ry), ((xx*2) + rx), rc]*placeholder[ry, rx, rc, ff])
placeholder = PLACEHOLDER [1, 1, 1, 256]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
========== Task 13 (workload key: ["d3b36ce001dc24d693facfbdae1979b4"]) ==========
placeholder = PLACEHOLDER [1, 28, 28, 128]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 128, 512]
Conv2dOutput(nn, yy, xx, ff) += (PaddedInput[nn, (yy + ry), (xx + rx), rc]*placeholder[ry, rx, rc, ff])
placeholder = PLACEHOLDER [1, 28, 28, 512]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, ax1, ax2, ax3])
placeholder = PLACEHOLDER [1, 1, 1, 512]
T_add(ax0, ax1, ax2, ax3) = (T_add[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
========== Task 14 (workload key: ["0fb1dfcdb5b755e2dab290ed0129dcf2"]) ==========
placeholder = PLACEHOLDER [1, 28, 28, 128]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 29)) && (i2 >= 1)) && (i2 < 29)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 128, 128]
Conv2dOutput(nn, yy, xx, ff) += (PaddedInput[nn, (yy + ry), (xx + rx), rc]*placeholder[ry, rx, rc, ff])
placeholder = PLACEHOLDER [1, 1, 1, 128]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
========== Task 15 (workload key: ["45acfc473c772458684f36a34549d8aa"]) ==========
placeholder = PLACEHOLDER [1, 28, 28, 512]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 512, 128]
Conv2dOutput(nn, yy, xx, ff) += (PaddedInput[nn, (yy + ry), (xx + rx), rc]*placeholder[ry, rx, rc, ff])
placeholder = PLACEHOLDER [1, 1, 1, 128]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
========== Task 16 (workload key: ["5e3ceb6e23ae8c351d5a1770d5fc6c7c"]) ==========
placeholder = PLACEHOLDER [1, 28, 28, 128]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 128, 512]
Conv2dOutput(nn, yy, xx, ff) += (PaddedInput[nn, (yy + ry), (xx + rx), rc]*placeholder[ry, rx, rc, ff])
placeholder = PLACEHOLDER [1, 28, 28, 512]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, ax1, ax2, ax3])
========== Task 17 (workload key: ["a085717fb3dcb046e5c4c2c04d3dc541"]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 256]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 256, 128]
Conv2dOutput(nn, yy, xx, ff) += (PaddedInput[nn, ((yy*2) + ry), ((xx*2) + rx), rc]*placeholder[ry, rx, rc, ff])
placeholder = PLACEHOLDER [1, 1, 1, 128]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
========== Task 18 (workload key: ["691feef049c8693bbe91bd5e7c9cdf34"]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 64]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 64, 256]
Conv2dOutput(nn, yy, xx, ff) += (PaddedInput[nn, (yy + ry), (xx + rx), rc]*placeholder[ry, rx, rc, ff])
placeholder = PLACEHOLDER [1, 56, 56, 256]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, ax1, ax2, ax3])
placeholder = PLACEHOLDER [1, 1, 1, 256]
T_add(ax0, ax1, ax2, ax3) = (T_add[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
========== Task 19 (workload key: ["a9e632e5167afb60fbe29e7aeef1d152"]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 64]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 1) && (i1 < 57)) && (i2 >= 1)) && (i2 < 57)), placeholder[i0, (i1 - 1), (i2 - 1), i3], 0f)
placeholder = PLACEHOLDER [3, 3, 64, 64]
Conv2dOutput(nn, yy, xx, ff) += (PaddedInput[nn, (yy + ry), (xx + rx), rc]*placeholder[ry, rx, rc, ff])
placeholder = PLACEHOLDER [1, 1, 1, 64]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
========== Task 20 (workload key: ["b51e06c1131d4cded40d1b215f722a4e"]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 256]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 256, 64]
Conv2dOutput(nn, yy, xx, ff) += (PaddedInput[nn, (yy + ry), (xx + rx), rc]*placeholder[ry, rx, rc, ff])
placeholder = PLACEHOLDER [1, 1, 1, 64]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
========== Task 21 (workload key: ["8fcee68a4342c38248a827f1c6c69177"]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 64]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 64, 256]
Conv2dOutput(nn, yy, xx, ff) += (PaddedInput[nn, (yy + ry), (xx + rx), rc]*placeholder[ry, rx, rc, ff])
placeholder = PLACEHOLDER [1, 56, 56, 256]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, ax1, ax2, ax3])
========== Task 22 (workload key: ["8dd7d81db440763f622f03fdc99e6d46"]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 64]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 64, 64]
Conv2dOutput(nn, yy, xx, ff) += (PaddedInput[nn, (yy + ry), (xx + rx), rc]*placeholder[ry, rx, rc, ff])
placeholder = PLACEHOLDER [1, 1, 1, 64]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
========== Task 23 (workload key: ["ba2026d923536b75e9b4faed89287d5f"]) ==========
placeholder = PLACEHOLDER [1, 112, 112, 64]
pad_temp(ax0, ax1, ax2, ax3) = tir.if_then_else(((((ax1 >= 1) && (ax1 < 113)) && (ax2 >= 1)) && (ax2 < 113)), placeholder[ax0, (ax1 - 1), (ax2 - 1), ax3], -3.40282e+38f)
tensor(ax0, ax1, ax2, ax3) max= pad_temp[ax0, ((ax1*2) + dh), ((ax2*2) + dw), ax3]
placeholder = PLACEHOLDER [1, 1, 1, 64]
T_add(ax0, ax1, ax2, ax3) = (tensor[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
========== Task 24 (workload key: ["a0eb8d6048282a4a0986cc2ccf14eaa2"]) ==========
placeholder = PLACEHOLDER [1, 224, 224, 3]
PaddedInput(i0, i1, i2, i3) = tir.if_then_else(((((i1 >= 3) && (i1 < 227)) && (i2 >= 3)) && (i2 < 227)), placeholder[i0, (i1 - 3), (i2 - 3), i3], 0f)
placeholder = PLACEHOLDER [7, 7, 3, 64]
Conv2dOutput(nn, yy, xx, ff) += (PaddedInput[nn, ((yy*2) + ry), ((xx*2) + rx), rc]*placeholder[ry, rx, rc, ff])
placeholder = PLACEHOLDER [1, 1, 1, 64]
T_add(ax0, ax1, ax2, ax3) = (Conv2dOutput[ax0, ax1, ax2, ax3] + placeholder[ax0, 0, 0, ax3])
T_relu(ax0, ax1, ax2, ax3) = max(T_add[ax0, ax1, ax2, ax3], 0f)
========== Task 25 (workload key: ["45b4de07687dee43ee1cbde9f516b2bf"]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 64]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 64, 256]
Conv2dOutput(nn, yy, xx, ff) += (PaddedInput[nn, (yy + ry), (xx + rx), rc]*placeholder[ry, rx, rc, ff])
========== Task 26 (workload key: ["b2010aa63c95dedf1f58f3fe8bc78634"]) ==========
placeholder = PLACEHOLDER [1, 56, 56, 256]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 256, 512]
Conv2dOutput(nn, yy, xx, ff) += (PaddedInput[nn, ((yy*2) + ry), ((xx*2) + rx), rc]*placeholder[ry, rx, rc, ff])
========== Task 27 (workload key: ["4d7e646d99bfa3cea8245bd7100369cb"]) ==========
placeholder = PLACEHOLDER [1, 28, 28, 512]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 512, 1024]
Conv2dOutput(nn, yy, xx, ff) += (PaddedInput[nn, ((yy*2) + ry), ((xx*2) + rx), rc]*placeholder[ry, rx, rc, ff])
========== Task 28 (workload key: ["537c8642716948c33a6eaaabc86b159d"]) ==========
placeholder = PLACEHOLDER [1, 14, 14, 1024]
PaddedInput(i0, i1, i2, i3) = placeholder[i0, i1, i2, i3]
placeholder = PLACEHOLDER [1, 1, 1024, 2048]
Conv2dOutput(nn, yy, xx, ff) += (PaddedInput[nn, ((yy*2) + ry), ((xx*2) + rx), rc]*placeholder[ry, rx, rc, ff])
开始Tuning调试
现在，设置一些选项来优化和启动搜索任务
- num_measure_trials是在调试期间可以使用的测量试验次数。可以将其设置为较小的数字（例如200）以进行快速演示。实际上，建议将其设置为800
- 此外，还用RecordToFile将测量记录转储到日志文件中，这些测量记录可用于最好地查询历史记录，恢复搜索以及以后进行更多分析。
- 有关更多参数， 请参见auto_scheduler.TuningOptions, auto_scheduler.LocalRunner。
def run_tuning():
print("Begin tuning...")
tuner = auto_scheduler.TaskScheduler(tasks, task_weights)
tune_option = auto_scheduler.TuningOptions(
num_measure_trials=200, # change this to 20000 to achieve the best performance
runner=auto_scheduler.LocalRunner(repeat=10, enable_cpu_cache_flush=True),
measure_callbacks=[auto_scheduler.RecordToFile(log_file)],
)
tuner.tune(tune_option)
# We do not run the tuning in our webpage server since it takes too long.
# Uncomment the following line to run it by yourself.
# run_tuning()
注意
tuning调试期间说明打印的信息
在tuning调试期间，控制台上会打印很多信息。它们用于调试目的。最重要的信息是任务调度程序的输出。下表是示例输出。
----------------------------------------------------------------------
------------------------------ [ Task Scheduler ]
----------------------------------------------------------------------
| ID | Latency (ms) | Speed (GFLOPS) | Trials |
-------------------------------------------------
| 0 | 0.010 | 0.40 | 64 |
| 1 | 0.087 | 47.19 | 64 |
| 2 | 0.008 | -0.00 | 64 |
| 3 | 0.177 | 582.07 | 64 |
| 4 | 0.268 | 862.37 | 256 |
| 5 | 0.166 | 621.13 | 128 |
| 6 | 0.170 | 605.10 | 128 |
| 7 | 0.128 | 403.20 | 64 |
| 8 | 0.189 | 545.71 | 64 |
| 9 | 0.231 | 1001.01 | 448 |
| 10 | 0.155 | 664.80 | 256 |
| 11 | 0.155 | 662.86 | 256 |
| 12 | 0.119 | 434.08 | 64 |
| 13 | 0.199 | 522.13 | 64 |
| 14 | 0.235 | 986.56 | 320 |
| 15 | 0.149 | 689.13 | 128 |
| 16 | 0.155 | 664.80 | 192 |
| 17 | 0.151 | 340.64 | 64 |
| 18 | 0.176 | 597.55 | 128 |
| 19 | 0.220 | 1054.37 | 192 |
| 20 | 0.150 | 686.01 | 128 |
| 21 | 0.159 | 650.88 | 128 |
| 22 | 0.073 | 358.19 | 64 |
| 23 | 0.031 | 70.63 | 64 |
| 24 | 0.251 | 947.73 | 128 |
| 25 | 0.157 | 652.47 | 128 |
| 26 | 0.215 | 954.84 | 128 |
| 27 | 0.237 | 868.92 | 128 |
| 28 | 0.266 | 774.06 | 128 |
-------------------------------------------------
Estimated total latency: 10.016 ms Trials: 3992 Used time : 1131 s Next ID: 15
下表列出了所有任务的延迟和（估计）速度。它还列出了所有任务的测量试验分配。最后一行显示这些任务的总加权延迟，这可以粗略估计网络的端到端执行时间。最后一行还显示测量试验的总数，自动调试所花费的总时间以及要调试的下一个任务的ID。
也将出现一些“ dmlc :: Error”错误，因为自动调度程序将尝试某些无效的调度。如果可以继续进行调试，则可以放心地忽略它们，因为这些错误与主要过程是隔离的。
注意
提前终止调试
可以通过强制终止此过程来提前终止调试。只要为日志文件中的每个任务获得至少一个有效的调度，就应该能够进行编译（下面的部分）。
编译和评估
自动调试后，可以使用发现的最佳时间表来编译网络。在自动调试过程中，所有测量记录都将转储到日志文件中，因此可以读取日志文件并加载最佳调度。
# Compile with the history best
print("Compile...")
with auto_scheduler.ApplyHistoryBest(log_file):
with tvm.transform.PassContext(opt_level=3, config={"relay.backend.use_auto_scheduler": True}):
lib = relay.build(mod, target=target, params=params)
# Create graph runtime
ctx = tvm.context(str(target), 0)
module = graph_runtime.GraphModule(lib["default"](ctx))
data_tvm = tvm.nd.array((np.random.uniform(size=input_shape)).astype(dtype))
module.set_input("data", data_tvm)
# Evaluate
print("Evaluate inference time cost...")
ftimer = module.module.time_evaluator("run", ctx, repeat=3, min_repeat_ms=500)
prof_res = np.array(ftimer().results) * 1e3 # convert to millisecond
print("Mean inference time (std dev): %.2f ms (%.2f ms)" % (np.mean(prof_res), np.std(prof_res)))
出：
Compile...
Evaluate inference time cost...
Mean inference time (std dev): 30.72 ms (0.09 ms)
其他技巧
- 在调试期间，自动调度器需要编译许多程序并从中提取功能。此部分占用大量CPU，因此建议使用具有多个内核的高性能CPU以加快搜索速度。
- 可以 用python3
- 可以从上一个日志文件继续搜索。load_log_file在function中创建任务调度程序时，只需添加一个新参数run_tuning。也就是， tuner
- 如果有多个目标CPU，则可以将它们全部用于测量以并行化测量。检查本节 以了解如何使用RPC跟踪器和RPC服务器。要在自动调度使用RPC跟踪，在TuningOptions中用auto_scheduler.RPCRunner更换runner 。