Apache TVM 是一个端到端的深度学习编译框架，适用于 CPU、GPU 和各种机器学习加速芯片。更多 TVM 中文文档可访问 →https://tvm.hyper.ai/
本教程介绍如何为 NVIDIA GPU 编写高性能可调模板。通过在此模板上运行自动调优器，可在许多情况下胜过供应商提供的 cuDNN 库。
注意，本教程不会在 Windows 或最新版本的 macOS 上运行。如需运行，请将本教程的主体放在 if name == "__main__": 代码块中。
安装依赖
要在 TVM 中使用 autotvm 包，需要安装额外的依赖（如果用的是 Python2，请将「3」更改为「2」）：
pip3 install --user psutil xgboost tornado cloudpickle为了让 TVM 在调优中运行更快，推荐使用 Cython 作为 TVM 的 FFI。在 TVM 的根目录下，执行如下命令：
pip3 install --user cython
sudo make cython3在 Python 代码中导入包：
import logging
import sys
import numpy as np
import tvm
from tvm import te, topi, testing
from tvm.topi.testing import conv2d_nchw_python
import tvm.testing
from tvm import autotvm第 1 步：定义搜索空间
TVM 中有很多有用的调度原语，详细教程，例如（1）如何在 GPU 上优化卷积（2）在 NVIDIA GPU 上优化 DepthwiseConv。
但是，它们的实现是针对一些特殊的输入 shape 手动调整的。本节将构建足够大的空间，涵盖这些教程中使用的技术，然后依靠高效的自动调优器，对空间进行搜索并选择合适的配置。
熟悉 CUDA schedule 的开发者，对以下通用模板并不陌生。可以修改此模板以调整其他算子，例如深度卷积和 GEMM。要完全理解这个模板，需要熟悉调度原语和自动调优 API，可以参考上面的教程和 AutoTVM 教程。
需要注意 conv2d 算子的搜索空间可能非常大（某些输入 shape 为 10^9 级别）
@autotvm.template("tutorial/conv2d_no_batching")
def conv2d_no_batching(N, H, W, CO, CI, KH, KW, stride, padding):
assert N == 1, "Only consider batch_size = 1 in this template"
data = te.placeholder((N, CI, H, W), name="data")
kernel = te.placeholder((CO, CI, KH, KW), name="kernel")
conv = topi.nn.conv2d_nchw(data, kernel, stride, padding, dilation=1, out_dtype="float32")
s = te.create_schedule([conv.op])
#### 空间定义开始 ####
n, f, y, x = s[conv].op.axis
rc, ry, rx = s[conv].op.reduce_axis
cfg = autotvm.get_config()
cfg.define_split("tile_f", f, num_outputs=4)
cfg.define_split("tile_y", y, num_outputs=4)
cfg.define_split("tile_x", x, num_outputs=4)
cfg.define_split("tile_rc", rc, num_outputs=3)
cfg.define_split("tile_ry", ry, num_outputs=3)
cfg.define_split("tile_rx", rx, num_outputs=3)
cfg.define_knob("auto_unroll_max_step", [0, 512, 1500])
cfg.define_knob("unroll_explicit", [0, 1])
#### 空间定义结束 ####
# 内联填充
pad_data = s[conv].op.input_tensors[0]
s[pad_data].compute_inline()
data, raw_data = pad_data, data
output = conv
OL = s.cache_write(conv, "local")
# 创建 cache 阶段
AA = s.cache_read(data, "shared", [OL])
WW = s.cache_read(kernel, "shared", [OL])
AL = s.cache_read(AA, "local", [OL])
WL = s.cache_read(WW, "local", [OL])
# 平铺和绑定空间轴
n, f, y, x = s[output].op.axis
bf, vf, tf, fi = cfg["tile_f"].apply(s, output, f)
by, vy, ty, yi = cfg["tile_y"].apply(s, output, y)
bx, vx, tx, xi = cfg["tile_x"].apply(s, output, x)
kernel_scope = n # 这是在此内核中附加全局配置的范围
s[output].bind(bf, te.thread_axis("blockIdx.z"))
s[output].bind(by, te.thread_axis("blockIdx.y"))
s[output].bind(bx, te.thread_axis("blockIdx.x"))
s[output].bind(vf, te.thread_axis("vthread"))
s[output].bind(vy, te.thread_axis("vthread"))
s[output].bind(vx, te.thread_axis("vthread"))
s[output].bind(tf, te.thread_axis("threadIdx.z"))
s[output].bind(ty, te.thread_axis("threadIdx.y"))
s[output].bind(tx, te.thread_axis("threadIdx.x"))
s[output].reorder(n, bf, by, bx, vf, vy, vx, tf, ty, tx, fi, yi, xi)
s[OL].compute_at(s[output], tx)
# tile reduction 轴
n, f, y, x = s[OL].op.axis
rc, ry, rx = s[OL].op.reduce_axis
rco, rcm, rci = cfg["tile_rc"].apply(s, OL, rc)
ryo, rym, ryi = cfg["tile_rx"].apply(s, OL, ry)
rxo, rxm, rxi = cfg["tile_ry"].apply(s, OL, rx)
s[OL].reorder(rco, ryo, rxo, rcm, rym, rxm, rci, ryi, rxi, n, f, y, x)
s[AA].compute_at(s[OL], rxo)
s[WW].compute_at(s[OL], rxo)
s[AL].compute_at(s[OL], rxm)
s[WL].compute_at(s[OL], rxm)
# 协作获取
for load in [AA, WW]:
n, f, y, x = s[load].op.axis
fused = s[load].fuse(n, f, y, x)
tz, fused = s[load].split(fused, nparts=cfg["tile_f"].size[2])
ty, fused = s[load].split(fused, nparts=cfg["tile_y"].size[2])
tx, fused = s[load].split(fused, nparts=cfg["tile_x"].size[2])
s[load].bind(tz, te.thread_axis("threadIdx.z"))
s[load].bind(ty, te.thread_axis("threadIdx.y"))
s[load].bind(tx, te.thread_axis("threadIdx.x"))
# 调优 unroll
s[output].pragma(kernel_scope, "auto_unroll_max_step", cfg["auto_unroll_max_step"].val)
s[output].pragma(kernel_scope, "unroll_explicit", cfg["unroll_explicit"].val)
return s, [raw_data, kernel, conv]第 2 步：在空间中搜索
选择 resnet 上的最后一层作为测试用例。由于空间足够大，所以 XGBoostTuner 最适合。这里只做 20 次试验来演示。实际上试验 1000 次可以为这个模板找到更合适的内核。
# logging 配置（用于将调优日志打印到屏幕）
logging.getLogger("autotvm").setLevel(logging.DEBUG)
logging.getLogger("autotvm").addHandler(logging.StreamHandler(sys.stdout))
# resnet 中的最后一层
N, H, W, CO, CI, KH, KW, strides, padding = 1, 7, 7, 512, 512, 3, 3, (1, 1), (1, 1)
task = autotvm.task.create(
"tutorial/conv2d_no_batching", args=(N, H, W, CO, CI, KH, KW, strides, padding), target="cuda"
)
print(task.config_space)
# 使用本地 gpu，为每个配置测量 10 次以减少方差
# 编译程序超时 10 秒，运行超时 4 秒
measure_option = autotvm.measure_option(
builder=autotvm.LocalBuilder(),
runner=autotvm.LocalRunner(repeat=3, min_repeat_ms=100, timeout=4),
)
record_file = None
# 开始调优，将 log 记录到 `conv2d.log`
# 在调优过程中，会尝试很多无效的配置，所以你应该
# 查看许多错误报告。只要能看到非零的 GFLOPS 就可以。
# 我们不再在服务器上运行调优，因为太耗时间了
# 去掉下面的注释，自己运行
# tuner = autotvm.tuner.XGBTuner(task)
# record_file = "conv2d.log"
# tuner.tune(
# n_trial=5,
# measure_option=measure_option,
# callbacks=[autotvm.callback.log_to_file(record_file)],
# )输出结果：
ConfigSpace (len=10454400, space_map=
0 tile_f: Split(policy=factors, product=512, num_outputs=4) len=220
1 tile_y: Split(policy=factors, product=7, num_outputs=4) len=4
2 tile_x: Split(policy=factors, product=7, num_outputs=4) len=4
3 tile_rc: Split(policy=factors, product=512, num_outputs=3) len=55
4 tile_ry: Split(policy=factors, product=3, num_outputs=3) len=3
5 tile_rx: Split(policy=factors, product=3, num_outputs=3) len=3
6 auto_unroll_max_step: OtherOption([0, 512, 1500]) len=3
7 unroll_explicit: OtherOption([0, 1]) len=2
)
waiting for device...
device available
Get devices for measurement successfully!
No: 1 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
func = build(s, args, target_host=task.target_host, runtime=runtime)
File "/workspace/python/tvm/driver/build_module.py", line 228, in build
input_mod = lower(inputs, args, name=name, binds=binds)
File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
tvm._ffi.base.TVMError: Traceback (most recent call last):
24: TVMFuncCall
at ../src/runtime/c_runtime_api.cc:477
23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
at ../include/tvm/runtime/packed_func.h:1217
22: Call
at ../include/tvm/runtime/packed_func.h:1213
21: operator()
at ../include/tvm/runtime/packed_func.h:1731
20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
at ../include/tvm/runtime/packed_func.h:1671
19: run<>
at ../include/tvm/runtime/packed_func.h:1631
18: run<tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1631
17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1631
16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1631
15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1631
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
at ../src/driver/driver_api.cc:365
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
at ../src/driver/driver_api.cc:352
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
at ../src/driver/driver_api.cc:252
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
at ../src/ir/transform.cc:274
8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
at ../src/ir/transform.cc:453
7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
at ../src/ir/transform.cc:274
6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
at ../src/tir/ir/transform.cc:100
5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
at ../include/tvm/runtime/packed_func.h:1750
4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
at ../include/tvm/runtime/packed_func.h:1694
3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
at ../include/tvm/runtime/packed_func.h:1618
2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
at ../include/tvm/runtime/packed_func.h:1217
1: Call
at ../include/tvm/runtime/packed_func.h:1213
0: operator()
at ../src/runtime/c_runtime_api.cc:534
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
Traceback (most recent call last):
24: TVMFuncCall
at ../src/runtime/c_runtime_api.cc:477
23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
at ../include/tvm/runtime/packed_func.h:1217
22: Call
at ../include/tvm/runtime/packed_func.h:1213
21: operator()
at ../include/tvm/runtime/packed_func.h:1731
20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
at ../include/tvm/runtime/packed_func.h:1671
19: run<>
at ../include/tvm/runtime/packed_func.h:1631
18: run<tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1631
17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1631
16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1631
15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1631
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
at ../src/driver/driver_api.cc:365
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
at ../src/driver/driver_api.cc:352
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
at ../src/driver/driver_api.cc:252
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
at ../src/ir/transform.cc:274
8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
at ../src/ir/transform.cc:453
7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
at ../src/ir/transform.cc:274
6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
at ../src/tir/ir/transform.cc:100
5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
at ../include/tvm/runtime/packed_func.h:1750
4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
at ../include/tvm/runtime/packed_func.h:1694
3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
at ../include/tvm/runtime/packed_func.h:1618
2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
at ../include/tvm/runtime/packed_func.h:1217
1: Call
at ../include/tvm/runtime/packed_func.h:1213
0: operator()
at ../src/runtime/c_runtime_api.cc:534
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6171524
No: 2 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
func = build(s, args, target_host=task.target_host, runtime=runtime)
File "/workspace/python/tvm/driver/build_module.py", line 228, in build
input_mod = lower(inputs, args, name=name, binds=binds)
File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
tvm._ffi.base.TVMError: Traceback (most recent call last):
24: TVMFuncCall
at ../src/runtime/c_runtime_api.cc:477
23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
at ../include/tvm/runtime/packed_func.h:1217
22: Call
at ../include/tvm/runtime/packed_func.h:1213
21: operator()
at ../include/tvm/runtime/packed_func.h:1731
20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
at ../include/tvm/runtime/packed_func.h:1671
19: run<>
at ../include/tvm/runtime/packed_func.h:1631
18: run<tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1631
17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1631
16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1631
15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1631
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
at ../src/driver/driver_api.cc:365
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
at ../src/driver/driver_api.cc:352
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
at ../src/driver/driver_api.cc:252
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
at ../src/ir/transform.cc:274
8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
at ../src/ir/transform.cc:453
7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
at ../src/ir/transform.cc:274
6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
at ../src/tir/ir/transform.cc:100
5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
at ../include/tvm/runtime/packed_func.h:1750
4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
at ../include/tvm/runtime/packed_func.h:1694
3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
at ../include/tvm/runtime/packed_func.h:1618
2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
at ../include/tvm/runtime/packed_func.h:1217
1: Call
at ../include/tvm/runtime/packed_func.h:1213
0: operator()
at ../src/runtime/c_runtime_api.cc:534
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
Traceback (most recent call last):
24: TVMFuncCall
at ../src/runtime/c_runtime_api.cc:477
23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
at ../include/tvm/runtime/packed_func.h:1217
22: Call
at ../include/tvm/runtime/packed_func.h:1213
21: operator()
at ../include/tvm/runtime/packed_func.h:1731
20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
at ../include/tvm/runtime/packed_func.h:1671
19: run<>
at ../include/tvm/runtime/packed_func.h:1631
18: run<tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1631
17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1631
16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1631
15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1631
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
at ../src/driver/driver_api.cc:365
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
at ../src/driver/driver_api.cc:352
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
at ../src/driver/driver_api.cc:252
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
at ../src/ir/transform.cc:274
8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
at ../src/ir/transform.cc:453
7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
at ../src/ir/transform.cc:274
6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
at ../src/tir/ir/transform.cc:100
5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
at ../include/tvm/runtime/packed_func.h:1750
4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
at ../include/tvm/runtime/packed_func.h:1694
3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
at ../include/tvm/runtime/packed_func.h:1618
2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
at ../include/tvm/runtime/packed_func.h:1217
1: Call
at ../include/tvm/runtime/packed_func.h:1213
0: operator()
at ../src/runtime/c_runtime_api.cc:534
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 1, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2502827
No: 3 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
func = build(s, args, target_host=task.target_host, runtime=runtime)
File "/workspace/python/tvm/driver/build_module.py", line 228, in build
input_mod = lower(inputs, args, name=name, binds=binds)
File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
tvm._ffi.base.TVMError: Traceback (most recent call last):
24: TVMFuncCall
at ../src/runtime/c_runtime_api.cc:477
23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
at ../include/tvm/runtime/packed_func.h:1217
22: Call
at ../include/tvm/runtime/packed_func.h:1213
21: operator()
at ../include/tvm/runtime/packed_func.h:1731
20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
at ../include/tvm/runtime/packed_func.h:1671
19: run<>
at ../include/tvm/runtime/packed_func.h:1631
18: run<tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1631
17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1631
16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1631
15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1631
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
at ../src/driver/driver_api.cc:365
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
at ../src/driver/driver_api.cc:352
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
at ../src/driver/driver_api.cc:252
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
at ../src/ir/transform.cc:274
8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
at ../src/ir/transform.cc:453
7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
at ../src/ir/transform.cc:274
6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
at ../src/tir/ir/transform.cc:100
5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
at ../include/tvm/runtime/packed_func.h:1750
4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
at ../include/tvm/runtime/packed_func.h:1694
3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
at ../include/tvm/runtime/packed_func.h:1618
2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
at ../include/tvm/runtime/packed_func.h:1217
1: Call
at ../include/tvm/runtime/packed_func.h:1213
0: operator()
at ../src/runtime/c_runtime_api.cc:534
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
Traceback (most recent call last):
24: TVMFuncCall
at ../src/runtime/c_runtime_api.cc:477
23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
at ../include/tvm/runtime/packed_func.h:1217
22: Call
at ../include/tvm/runtime/packed_func.h:1213
21: operator()
at ../include/tvm/runtime/packed_func.h:1731
20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
at ../include/tvm/runtime/packed_func.h:1671
19: run<>
at ../include/tvm/runtime/packed_func.h:1631
18: run<tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1631
17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1631
16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1631
15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1631
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
at ../src/driver/driver_api.cc:365
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
at ../src/driver/driver_api.cc:352
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
at ../src/driver/driver_api.cc:252
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
at ../src/ir/transform.cc:274
8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
at ../src/ir/transform.cc:453
7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
at ../src/ir/transform.cc:274
6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
at ../src/tir/ir/transform.cc:100
5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
at ../include/tvm/runtime/packed_func.h:1750
4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
at ../include/tvm/runtime/packed_func.h:1694
3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
at ../include/tvm/runtime/packed_func.h:1618
2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
at ../include/tvm/runtime/packed_func.h:1217
1: Call
at ../include/tvm/runtime/packed_func.h:1213
0: operator()
at ../src/runtime/c_runtime_api.cc:534
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 1, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 512, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,3325707
No: 4 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
func = build(s, args, target_host=task.target_host, runtime=runtime)
File "/workspace/python/tvm/driver/build_module.py", line 228, in build
input_mod = lower(inputs, args, name=name, binds=binds)
File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
tvm._ffi.base.TVMError: Traceback (most recent call last):
24: TVMFuncCall
at ../src/runtime/c_runtime_api.cc:477
23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
at ../include/tvm/runtime/packed_func.h:1217
22: Call
at ../include/tvm/runtime/packed_func.h:1213
21: operator()
at ../include/tvm/runtime/packed_func.h:1731
20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
at ../include/tvm/runtime/packed_func.h:1671
19: run<>
at ../include/tvm/runtime/packed_func.h:1631
18: run<tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1631
17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1631
16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1631
15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1631
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
at ../src/driver/driver_api.cc:365
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
at ../src/driver/driver_api.cc:352
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
at ../src/driver/driver_api.cc:252
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
at ../src/ir/transform.cc:274
8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
at ../src/ir/transform.cc:453
7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
at ../src/ir/transform.cc:274
6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
at ../src/tir/ir/transform.cc:100
5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
at ../include/tvm/runtime/packed_func.h:1750
4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
at ../include/tvm/runtime/packed_func.h:1694
3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
at ../include/tvm/runtime/packed_func.h:1618
2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
at ../include/tvm/runtime/packed_func.h:1217
1: Call
at ../include/tvm/runtime/packed_func.h:1213
0: operator()
at ../src/runtime/c_runtime_api.cc:534
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
Traceback (most recent call last):
24: TVMFuncCall
at ../src/runtime/c_runtime_api.cc:477
23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
at ../include/tvm/runtime/packed_func.h:1217
22: Call
at ../include/tvm/runtime/packed_func.h:1213
21: operator()
at ../include/tvm/runtime/packed_func.h:1731
20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
at ../include/tvm/runtime/packed_func.h:1671
19: run<>
at ../include/tvm/runtime/packed_func.h:1631
18: run<tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1631
17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1631
16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1631
15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1631
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
at ../src/driver/driver_api.cc:365
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
at ../src/driver/driver_api.cc:352
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
at ../src/driver/driver_api.cc:252
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
at ../src/ir/transform.cc:274
8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
at ../src/ir/transform.cc:453
7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
at ../src/ir/transform.cc:274
6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
at ../src/tir/ir/transform.cc:100
5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
at ../include/tvm/runtime/packed_func.h:1750
4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
at ../include/tvm/runtime/packed_func.h:1694
3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
at ../include/tvm/runtime/packed_func.h:1618
2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
at ../include/tvm/runtime/packed_func.h:1217
1: Call
at ../include/tvm/runtime/packed_func.h:1213
0: operator()
at ../src/runtime/c_runtime_api.cc:534
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 4, 2]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4942815
No: 5 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
func = build(s, args, target_host=task.target_host, runtime=runtime)
File "/workspace/python/tvm/driver/build_module.py", line 228, in build
input_mod = lower(inputs, args, name=name, binds=binds)
File "/workspace/python/tvm/driver/build_module.py", line 134, in lower
return ffi.lower_schedule(inp, args, name, binds, simple_mode)
File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
File "tvm/_ffi/_cython/./packed_func.pxi", line 276, in tvm._ffi._cy3.core.FuncCall
File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
tvm._ffi.base.TVMError: Traceback (most recent call last):
24: TVMFuncCall
at ../src/runtime/c_runtime_api.cc:477
23: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
at ../include/tvm/runtime/packed_func.h:1217
22: Call
at ../include/tvm/runtime/packed_func.h:1213
21: operator()
at ../include/tvm/runtime/packed_func.h:1731
20: unpack_call<tvm::IRModule, 5, tvm::<lambda(tvm::te::Schedule, const tvm::runtime::Array<tvm::runtime::ObjectRef>&, const tvm::runtime::String&, const tvm::runtime::Map<tvm::te::Tensor, tvm::tir::Buffer>&, bool)> >
at ../include/tvm/runtime/packed_func.h:1671
19: run<>
at ../include/tvm/runtime/packed_func.h:1631
18: run<tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1631
17: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1631
16: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1631
15: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1631
14: run<tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_, tvm::runtime::TVMMovableArgValueWithContext_>
at ../include/tvm/runtime/packed_func.h:1646
13: operator()
at ../src/driver/driver_api.cc:365
12: tvm::LowerSchedule(tvm::te::Schedule, tvm::runtime::Array<tvm::runtime::ObjectRef, void> const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::unordered_map<tvm::te::Tensor, tvm::tir::Buffer, std::hash<tvm::te::Tensor>, std::equal_to<tvm::te::Tensor>, std::allocator<std::pair<tvm::te::Tensor const, tvm::tir::Buffer> > > const&, bool)
at ../src/driver/driver_api.cc:352
11: tvm::LowerWithPassList(tvm::IRModule, tvm::runtime::Array<tvm::transform::Pass, void>)
at ../src/driver/driver_api.cc:252
10: tvm::transform::Pass::operator()(tvm::IRModule) const
at ../src/ir/transform.cc:258
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
at ../src/ir/transform.cc:274
8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
at ../src/ir/transform.cc:453
7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
at ../src/ir/transform.cc:274
6: tvm::tir::transform::PrimFuncPassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
at ../src/tir/ir/transform.cc:100
5: tvm::runtime::TypedPackedFunc<tvm::tir::PrimFunc (tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext)>::operator()(tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext) const
at ../include/tvm/runtime/packed_func.h:1750
4: tvm::tir::PrimFunc tvm::runtime::detail::typed_packed_call_dispatcher<tvm::tir::PrimFunc>::run<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::runtime::PackedFunc const&, tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&)
at ../include/tvm/runtime/packed_func.h:1694
3: tvm::runtime::TVMRetValue tvm::runtime::PackedFunc::operator()<tvm::tir::PrimFunc, tvm::IRModule, tvm::transform::PassContext>(tvm::tir::PrimFunc&&, tvm::IRModule&&, tvm::transform::PassContext&&) const
at ../include/tvm/runtime/packed_func.h:1618
2: tvm::runtime::PackedFuncObj::CallPacked(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
at ../include/tvm/runtime/packed_func.h:1217
1: Call
at ../include/tvm/runtime/packed_func.h:1213
0: operator()
at ../src/runtime/c_runtime_api.cc:534
File "tvm/_ffi/_cython/./packed_func.pxi", line 56, in tvm._ffi._cy3.core.tvm_callback
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel
