时间戳

首页 > 解决方案 > 尝试官方 TVM 教程时出现“找不到目标=opencl -device=intel_graphics -model=unknown,workload=”错误的配置

python - 尝试官方 TVM 教程时出现“找不到目标=opencl -device=intel_graphics -model=unknown,workload=”错误的配置

问题描述

我正在尝试在TVM中运行第一个示例，但一开始我就遇到了这些错误。我已经在LLVM ON和OpenCL On的情况下构建了 tvm （为 opencl 应用程序安装了 Intel sdk - opencl 2.1）。构建过程顺利进行，所以我想一切都准备就绪。

但是，当我尝试运行此示例中的此代码段时出现这些错误：编译深度学习模型的快速入门教程：

opt_level = 3
target = tvm.target.intel_graphics()
with relay.build_config(opt_level=opt_level):
    graph, lib, params = relay.build_module.build(
        mod, target, params=params)



Cannot find config for target=opencl -device=intel_graphics -model=unknown, workload=('conv2d', (1, 3, 224, 224, 'float32'), (64, 3, 7, 7, 'float32'), (2, 2), (3, 3), (1, 1), 'NCHW', 'float32'). A fallback configuration is used, which may bring great performance regression.
Cannot find config for target=opencl -device=intel_graphics -model=unknown, workload=('conv2d', (1, 64, 56, 56, 'float32'), (64, 64, 3, 3, 'float32'), (1, 1), (1, 1), (1, 1), 'NCHW', 'float32'). A fallback configuration is used, which may bring great performance regression.
Cannot find config for target=opencl -device=intel_graphics -model=unknown, workload=('conv2d', (1, 64, 56, 56, 'float32'), (64, 64, 1, 1, 'float32'), (1, 1), (0, 0), (1, 1), 'NCHW', 'float32'). A fallback configuration is used, which may bring great performance regression.
Cannot find config for target=opencl -device=intel_graphics -model=unknown, workload=('conv2d', (1, 64, 56, 56, 'float32'), (128, 64, 3, 3, 'float32'), (2, 2), (1, 1), (1, 1), 'NCHW', 'float32'). A fallback configuration is used, which may bring great performance regression.
Cannot find config for target=opencl -device=intel_graphics -model=unknown, workload=('conv2d', (1, 128, 28, 28, 'float32'), (128, 128, 3, 3, 'float32'), (1, 1), (1, 1), (1, 1), 'NCHW', 'float32'). A fallback configuration is used, which may bring great performance regression.
Cannot find config for target=opencl -device=intel_graphics -model=unknown, workload=('conv2d', (1, 64, 56, 56, 'float32'), (128, 64, 1, 1, 'float32'), (2, 2), (0, 0), (1, 1), 'NCHW', 'float32'). A fallback configuration is used, which may bring great performance regression.
Cannot find config for target=opencl -device=intel_graphics -model=unknown, workload=('conv2d', (1, 128, 28, 28, 'float32'), (256, 128, 3, 3, 'float32'), (2, 2), (1, 1), (1, 1), 'NCHW', 'float32'). A fallback configuration is used, which may bring great performance regression.
Cannot find config for target=opencl -device=intel_graphics -model=unknown, workload=('conv2d', (1, 256, 14, 14, 'float32'), (256, 256, 3, 3, 'float32'), (1, 1), (1, 1), (1, 1), 'NCHW', 'float32'). A fallback configuration is used, which may bring great performance regression.
Cannot find config for target=opencl -device=intel_graphics -model=unknown, workload=('conv2d', (1, 128, 28, 28, 'float32'), (256, 128, 1, 1, 'float32'), (2, 2), (0, 0), (1, 1), 'NCHW', 'float32'). A fallback configuration is used, which may bring great performance regression.
Cannot find config for target=opencl -device=intel_graphics -model=unknown, workload=('conv2d', (1, 256, 14, 14, 'float32'), (512, 256, 3, 3, 'float32'), (2, 2), (1, 1), (1, 1), 'NCHW', 'float32'). A fallback configuration is used, which may bring great performance regression.
Cannot find config for target=opencl -device=intel_graphics -model=unknown, workload=('conv2d', (1, 512, 7, 7, 'float32'), (512, 512, 3, 3, 'float32'), (1, 1), (1, 1), (1, 1), 'NCHW', 'float32'). A fallback configuration is used, which may bring great performance regression.
Cannot find config for target=opencl -device=intel_graphics -model=unknown, workload=('conv2d', (1, 256, 14, 14, 'float32'), (512, 256, 1, 1, 'float32'), (2, 2), (0, 0), (1, 1), 'NCHW', 'float32'). A fallback configuration is used, which may bring great performance regression.
Cannot find config for target=opencl -device=intel_graphics -model=unknown, workload=('dense', (1, 512, 'float32'), (1000, 512, 'float32'), 0, 'float32'). A fallback configuration is used, which may bring great performance regression.

我也试过发送图形模型看看是不是这个原因，但无济于事！我仍然收到相同的错误消息，这次是我提供的模型，即：

opt_level = 3
target = tvm.target.intel_graphics(model='Intel(R) Iris(R) Pro Graphics 580')
with relay.build_config(opt_level=opt_level):
    graph, lib, params = relay.build_module.build(
        mod, target, params=params)


Cannot find config for target=opencl -device=intel_graphics -model=Intel(R) Iris(R) Pro Graphics 580, workload=('conv2d', (1, 3, 224, 224, 'float32'), (64, 3, 7, 7, 'float32'), (2, 2), (3, 3), (1, 1), 'NCHW', 'float32'). A fallback configuration is used, which may bring great performance regression.
Cannot find config for target=opencl -device=intel_graphics -model=Intel(R) Iris(R) Pro Graphics 580, workload=('conv2d', (1, 64, 56, 56, 'float32'), (64, 64, 3, 3, 'float32'), (1, 1), (1, 1), (1, 1), 'NCHW', 'float32'). A fallback configuration is used, which may bring great performance regression.
Cannot find config for target=opencl -device=intel_graphics -model=Intel(R) Iris(R) Pro Graphics 580, workload=('conv2d', (1, 64, 56, 56, 'float32'), (64, 64, 1, 1, 'float32'), (1, 1), (0, 0), (1, 1), 'NCHW', 'float32'). A fallback configuration is used, which may bring great performance regression.
Cannot find config for target=opencl -device=intel_graphics -model=Intel(R) Iris(R) Pro Graphics 580, workload=('conv2d', (1, 64, 56, 56, 'float32'), (128, 64, 3, 3, 'float32'), (2, 2), (1, 1), (1, 1), 'NCHW', 'float32'). A fallback configuration is used, which may bring great performance regression.
Cannot find config for target=opencl -device=intel_graphics -model=Intel(R) Iris(R) Pro Graphics 580, workload=('conv2d', (1, 128, 28, 28, 'float32'), (128, 128, 3, 3, 'float32'), (1, 1), (1, 1), (1, 1), 'NCHW', 'float32'). A fallback configuration is used, which may bring great performance regression.
Cannot find config for target=opencl -device=intel_graphics -model=Intel(R) Iris(R) Pro Graphics 580, workload=('conv2d', (1, 64, 56, 56, 'float32'), (128, 64, 1, 1, 'float32'), (2, 2), (0, 0), (1, 1), 'NCHW', 'float32'). A fallback configuration is used, which may bring great performance regression.
Cannot find config for target=opencl -device=intel_graphics -model=Intel(R) Iris(R) Pro Graphics 580, workload=('conv2d', (1, 128, 28, 28, 'float32'), (256, 128, 3, 3, 'float32'), (2, 2), (1, 1), (1, 1), 'NCHW', 'float32'). A fallback configuration is used, which may bring great performance regression.
Cannot find config for target=opencl -device=intel_graphics -model=Intel(R) Iris(R) Pro Graphics 580, workload=('conv2d', (1, 256, 14, 14, 'float32'), (256, 256, 3, 3, 'float32'), (1, 1), (1, 1), (1, 1), 'NCHW', 'float32'). A fallback configuration is used, which may bring great performance regression.
Cannot find config for target=opencl -device=intel_graphics -model=Intel(R) Iris(R) Pro Graphics 580, workload=('conv2d', (1, 128, 28, 28, 'float32'), (256, 128, 1, 1, 'float32'), (2, 2), (0, 0), (1, 1), 'NCHW', 'float32'). A fallback configuration is used, which may bring great performance regression.
Cannot find config for target=opencl -device=intel_graphics -model=Intel(R) Iris(R) Pro Graphics 580, workload=('conv2d', (1, 256, 14, 14, 'float32'), (512, 256, 3, 3, 'float32'), (2, 2), (1, 1), (1, 1), 'NCHW', 'float32'). A fallback configuration is used, which may bring great performance regression.
Cannot find config for target=opencl -device=intel_graphics -model=Intel(R) Iris(R) Pro Graphics 580, workload=('conv2d', (1, 512, 7, 7, 'float32'), (512, 512, 3, 3, 'float32'), (1, 1), (1, 1), (1, 1), 'NCHW', 'float32'). A fallback configuration is used, which may bring great performance regression.
Cannot find config for target=opencl -device=intel_graphics -model=Intel(R) Iris(R) Pro Graphics 580, workload=('conv2d', (1, 256, 14, 14, 'float32'), (512, 256, 1, 1, 'float32'), (2, 2), (0, 0), (1, 1), 'NCHW', 'float32'). A fallback configuration is used, which may bring great performance regression.
Cannot find config for target=opencl -device=intel_graphics -model=Intel(R) Iris(R) Pro Graphics 580, workload=('dense', (1, 512, 'float32'), (1000, 512, 'float32'), 0, 'float32'). A fallback configuration is used, which may bring great performance regression.

我什至尝试更改 op_level，这没有任何影响。我应该怎么做才能摆脱这个问题？

标签： python

解决方案

您看到的不是错误，而是警告。因为 TVM 找不到包含优化计划的日志文件，它只会使用默认（回退）计划。

要消除警告，您需要使用 AutoTVM（如本例所示）来查找优化的时间表。之后，您可以继续编译。

推荐阅读