mirror of https://github.com/llvm/torch-mlir
Clean up stale examples.
They were confusing users, and most didn't even work anymore.pull/300/head
Sean Silva
parent
1dec561cfd
commit
7a3570e881
|
|
@ -1,32 +0,0 @@
|
|||
# -*- Python -*-
|
||||
# This file is licensed under a pytorch-style license
|
||||
# See frontends/pytorch/LICENSE for license information.
|
||||
|
||||
import torch
|
||||
import torch_mlir
|
||||
|
||||
import npcomp
|
||||
from npcomp.compiler.pytorch.backend import refjit, frontend_lowering
|
||||
from npcomp.compiler.utils import logging
|
||||
|
||||
import test_utils
|
||||
|
||||
logging.enable()
|
||||
|
||||
torch.manual_seed(0)
|
||||
input = torch.rand(2, 3)
|
||||
|
||||
mb = torch_mlir.ModuleBuilder()
|
||||
with mb.capture_function("cos", [input]) as f:
|
||||
result = torch.cos(input)
|
||||
f.returns([result])
|
||||
|
||||
backend = iree.IreeNpcompBackend()
|
||||
jit_module = backend.load(backend.compile(frontend_lowering.lower_module(mb.module)))
|
||||
|
||||
logging.debug(f"Executing jit_module.cos")
|
||||
test_utils.compare_outputs(torch.cos, jit_module.cos, input)
|
||||
|
||||
# This fails because ModuleBuilder represents torch.cos with a constant:
|
||||
# https://github.com/llvm/mlir-npcomp/issues/135
|
||||
test_utils.compare_outputs(torch.cos, jit_module.cos, input + 1)
|
||||
|
|
@ -1,32 +0,0 @@
|
|||
# -*- Python -*-
|
||||
# This file is licensed under a pytorch-style license
|
||||
# See frontends/pytorch/LICENSE for license information.
|
||||
|
||||
import torch
|
||||
import torch_mlir
|
||||
|
||||
import npcomp
|
||||
from npcomp.compiler.pytorch.backend import refjit, frontend_lowering
|
||||
from npcomp.compiler.utils import logging
|
||||
|
||||
import test_utils
|
||||
|
||||
logging.enable()
|
||||
|
||||
torch.manual_seed(0)
|
||||
|
||||
arg0 = torch.ones(2, 2)
|
||||
arg1 = torch.ones(2, 2)
|
||||
|
||||
def fun(a, b):
|
||||
return a.div_(b)
|
||||
|
||||
mb = torch_mlir.ModuleBuilder()
|
||||
with mb.capture_function("test", [arg0, arg1]) as f:
|
||||
f.returns([fun(arg0, arg1)])
|
||||
|
||||
backend = iree.IreeNpcompBackend()
|
||||
jit_module = backend.load(backend.compile(frontend_lowering.lower_module(mb.module)))
|
||||
|
||||
test_utils.compare_outputs(torch.mm, jit_module.test, arg0, arg1)
|
||||
test_utils.compare_outputs(torch.mm, jit_module.test, arg0 + 1, arg1 + 1)
|
||||
|
|
@ -1,29 +0,0 @@
|
|||
# -*- Python -*-
|
||||
# This file is licensed under a pytorch-style license
|
||||
# See frontends/pytorch/LICENSE for license information.
|
||||
|
||||
import torch
|
||||
import torch_mlir
|
||||
|
||||
import npcomp
|
||||
from npcomp.compiler.pytorch.backend import refjit, frontend_lowering
|
||||
from npcomp.compiler.utils import logging
|
||||
|
||||
import test_utils
|
||||
|
||||
logging.enable()
|
||||
|
||||
torch.manual_seed(0)
|
||||
lhs = torch.rand(2, 3)
|
||||
rhs = torch.rand(3, 4)
|
||||
|
||||
mb = torch_mlir.ModuleBuilder()
|
||||
with mb.capture_function("mm", [lhs, rhs]) as f:
|
||||
result = torch.mm(lhs, rhs)
|
||||
f.returns([result])
|
||||
|
||||
backend = iree.IreeNpcompBackend()
|
||||
jit_module = backend.load(backend.compile(frontend_lowering.lower_module(mb.module)))
|
||||
|
||||
test_utils.compare_outputs(torch.mm, jit_module.mm, lhs, rhs)
|
||||
test_utils.compare_outputs(torch.mm, jit_module.mm, lhs + 1, rhs - 1)
|
||||
|
|
@ -1,37 +0,0 @@
|
|||
# -*- Python -*-
|
||||
# This file is licensed under a pytorch-style license
|
||||
# See frontends/pytorch/LICENSE for license information.
|
||||
|
||||
import torch
|
||||
import torch_mlir
|
||||
|
||||
import npcomp
|
||||
from npcomp.compiler.pytorch.backend import refjit, frontend_lowering
|
||||
from npcomp.compiler.utils import logging
|
||||
|
||||
import test_utils
|
||||
|
||||
logging.enable()
|
||||
|
||||
lhs = torch.ones((4, 6, 1))
|
||||
rhs = torch.ones((1, 1, 3)) * 0.6
|
||||
bias = torch.ones((1, 1, 3)) * 0.2
|
||||
threshold = torch.tensor((0.75, 0.25, 0.10))
|
||||
|
||||
|
||||
def mul_maximum(lhs, rhs, threshold, bias):
|
||||
return torch.maximum(lhs * rhs, threshold) + bias
|
||||
|
||||
|
||||
mb = torch_mlir.ModuleBuilder()
|
||||
with mb.capture_function("mul_maximum", [lhs, rhs, threshold, bias]) as f:
|
||||
result = mul_maximum(lhs, rhs, threshold, bias)
|
||||
f.returns([result])
|
||||
|
||||
backend = iree.IreeNpcompBackend()
|
||||
jit_module = backend.load(backend.compile(frontend_lowering.lower_module(mb.module)))
|
||||
|
||||
test_utils.compare_outputs(mul_maximum, jit_module.mul_maximum, lhs, rhs,
|
||||
threshold, bias)
|
||||
test_utils.compare_outputs(mul_maximum, jit_module.mul_maximum, lhs + 1,
|
||||
rhs + 2, threshold, bias)
|
||||
|
|
@ -94,9 +94,7 @@
|
|||
"from mlir.passmanager import PassManager\n",
|
||||
"\n",
|
||||
"from torch_mlir_torchscript.annotations import annotate_args, export\n",
|
||||
"from torch_mlir.torchscript_annotations import extract_annotations\n",
|
||||
"\n",
|
||||
"from npcomp.compiler.pytorch.backend.iree import IreeNpcompBackend"
|
||||
"from torch_mlir.torchscript_annotations import extract_annotations"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
|
|||
|
|
@ -1,33 +0,0 @@
|
|||
# -*- Python -*-
|
||||
# This file is licensed under a pytorch-style license
|
||||
# See frontends/pytorch/LICENSE for license information.
|
||||
|
||||
import torch
|
||||
import torch_mlir
|
||||
|
||||
import npcomp
|
||||
from npcomp.compiler.pytorch.backend import refjit, frontend_lowering
|
||||
from npcomp.compiler.utils import logging
|
||||
|
||||
import test_utils
|
||||
|
||||
logging.enable()
|
||||
|
||||
torch.manual_seed(0)
|
||||
|
||||
arg0 = torch.ones(2, 2)
|
||||
|
||||
def fun(a):
|
||||
z = torch.zeros(2, 2)
|
||||
torch.tanh(a, out=z)
|
||||
return z
|
||||
|
||||
mb = torch_mlir.ModuleBuilder()
|
||||
with mb.capture_function("test", [arg0]) as f:
|
||||
f.returns([fun(arg0)])
|
||||
|
||||
backend = iree.IreeNpcompBackend()
|
||||
jit_module = backend.load(backend.compile(frontend_lowering.lower_module(mb.module)))
|
||||
|
||||
test_utils.compare_outputs(torch.mm, jit_module.test, arg0, arg1)
|
||||
test_utils.compare_outputs(torch.mm, jit_module.test, arg0 + 1, arg1 + 1)
|
||||
|
|
@ -1,30 +0,0 @@
|
|||
# -*- Python -*-
|
||||
# This file is licensed under a pytorch-style license
|
||||
# See frontends/pytorch/LICENSE for license information.
|
||||
|
||||
import sys
|
||||
import textwrap
|
||||
|
||||
import numpy as np
|
||||
|
||||
INDENT = " "
|
||||
|
||||
|
||||
def _indent(value):
|
||||
return textwrap.indent(str(value), INDENT)
|
||||
|
||||
|
||||
def compare_outputs(torch_func, jit_func, *args):
|
||||
print('-' * 80)
|
||||
|
||||
print(f"Input args:\n{_indent(args)}", file=sys.stderr)
|
||||
result = torch_func(*args)
|
||||
jit_result = jit_func(*args)
|
||||
|
||||
np.testing.assert_allclose(result.numpy(), jit_result, rtol=1e-05, atol=1e-08)
|
||||
|
||||
# Only print these if the test passes, as np.testing will print them if it
|
||||
# fails.
|
||||
print("SUCCESS", file=sys.stderr)
|
||||
print(f"PyTorch Result:\n{_indent(result.numpy())}", file=sys.stderr)
|
||||
print(f"JIT Result:\n{_indent(jit_result)}", file=sys.stderr)
|
||||
|
|
@ -1,58 +0,0 @@
|
|||
# -*- Python -*-
|
||||
# This file is licensed under a pytorch-style license
|
||||
# See frontends/pytorch/LICENSE for license information.
|
||||
|
||||
import typing
|
||||
|
||||
import torch
|
||||
import torch_mlir
|
||||
|
||||
import npcomp
|
||||
from npcomp.compiler.pytorch.backend import refjit, frontend_lowering
|
||||
from npcomp.compiler.utils import logging
|
||||
|
||||
import test_utils
|
||||
|
||||
logging.enable()
|
||||
|
||||
# RUN: %PYTHON %s | npcomp-opt | FileCheck %s
|
||||
|
||||
mb = torch_mlir.ModuleBuilder()
|
||||
|
||||
class Submodule(torch.nn.Module):
|
||||
def __init__(self):
|
||||
super().__init__()
|
||||
def forward(self, lhs, rhs):
|
||||
return torch.mm(lhs, rhs)
|
||||
|
||||
class TestModule(torch.nn.Module):
|
||||
def __init__(self):
|
||||
super().__init__()
|
||||
self.s = Submodule()
|
||||
def forward(self, lhs, rhs):
|
||||
return self.s.forward(lhs, rhs)
|
||||
|
||||
test_module = TestModule()
|
||||
class_annotator = torch_mlir.ClassAnnotator()
|
||||
recursivescriptmodule = torch.jit.script(test_module)
|
||||
torch.jit.save(recursivescriptmodule, '/tmp/foo.pt')
|
||||
|
||||
class_annotator.exportNone(recursivescriptmodule._c._type())
|
||||
class_annotator.exportPath(recursivescriptmodule._c._type(), ['forward'])
|
||||
class_annotator.annotateArgs(recursivescriptmodule._c._type(), ['forward'], [
|
||||
None,
|
||||
([-1, -1], torch.float32),
|
||||
([-1, -1], torch.float32),
|
||||
])
|
||||
# TODO: Automatically handle unpacking Python class RecursiveScriptModule into the underlying ScriptModule.
|
||||
mb.import_module(recursivescriptmodule._c, class_annotator)
|
||||
#mb.module.operation.print()
|
||||
|
||||
backend = iree.IreeNpcompBackend()
|
||||
compiled = backend.compile(frontend_lowering.lower_object_graph(mb.module))
|
||||
jit_module = backend.load(compiled)
|
||||
|
||||
torch.manual_seed(0)
|
||||
lhs = torch.rand(2, 3)
|
||||
rhs = torch.rand(3, 4)
|
||||
test_utils.compare_outputs(test_module.forward, jit_module.forward, lhs, rhs)
|
||||
|
|
@ -1,49 +0,0 @@
|
|||
# -*- Python -*-
|
||||
# This file is licensed under a pytorch-style license
|
||||
# See frontends/pytorch/LICENSE for license information.
|
||||
|
||||
import typing
|
||||
|
||||
import torch
|
||||
import torch_mlir
|
||||
|
||||
import npcomp
|
||||
from npcomp.compiler.pytorch.backend import refjit, frontend_lowering
|
||||
from npcomp.compiler.utils import logging
|
||||
|
||||
import test_utils
|
||||
|
||||
#logging.enable()
|
||||
|
||||
# RUN: %PYTHON %s | npcomp-opt | FileCheck %s
|
||||
|
||||
mb = torch_mlir.ModuleBuilder()
|
||||
|
||||
class TestModule(torch.nn.Module):
|
||||
def __init__(self):
|
||||
super().__init__()
|
||||
def forward(self, x):
|
||||
return torch.tanh(x)
|
||||
|
||||
test_module = TestModule()
|
||||
class_annotator = torch_mlir.ClassAnnotator()
|
||||
recursivescriptmodule = torch.jit.script(test_module)
|
||||
torch.jit.save(recursivescriptmodule, '/tmp/foo.pt')
|
||||
|
||||
class_annotator.exportNone(recursivescriptmodule._c._type())
|
||||
class_annotator.exportPath(recursivescriptmodule._c._type(), ['forward'])
|
||||
class_annotator.annotateArgs(recursivescriptmodule._c._type(), ['forward'], [
|
||||
None,
|
||||
([2, 3, -1], torch.float32)
|
||||
])
|
||||
# TODO: Automatically handle unpacking Python class RecursiveScriptModule into the underlying ScriptModule.
|
||||
mb.import_module(recursivescriptmodule._c, class_annotator)
|
||||
#mb.module.operation.print()
|
||||
|
||||
backend = iree.IreeNpcompBackend()
|
||||
compiled = backend.compile(frontend_lowering.lower_object_graph(mb.module))
|
||||
jit_module = backend.load(compiled)
|
||||
|
||||
torch.manual_seed(0)
|
||||
input = torch.rand(2, 3, 1)
|
||||
test_utils.compare_outputs(test_module.forward, jit_module.forward, input)
|
||||
|
|
@ -1,49 +0,0 @@
|
|||
# -*- Python -*-
|
||||
# This file is licensed under a pytorch-style license
|
||||
# See frontends/pytorch/LICENSE for license information.
|
||||
|
||||
import typing
|
||||
|
||||
import torch
|
||||
import torch_mlir
|
||||
|
||||
import npcomp
|
||||
from npcomp.compiler.pytorch.backend import iree, frontend_lowering
|
||||
from npcomp.compiler.utils import logging
|
||||
|
||||
import test_utils
|
||||
|
||||
logging.enable()
|
||||
|
||||
# RUN: %PYTHON %s | npcomp-opt | FileCheck %s
|
||||
|
||||
mb = torch_mlir.ModuleBuilder()
|
||||
|
||||
class TestModule(torch.nn.Module):
|
||||
def __init__(self):
|
||||
super().__init__()
|
||||
def forward(self, x):
|
||||
return torch.tanh(x)
|
||||
|
||||
test_module = TestModule()
|
||||
class_annotator = torch_mlir.ClassAnnotator()
|
||||
recursivescriptmodule = torch.jit.script(test_module)
|
||||
torch.jit.save(recursivescriptmodule, '/tmp/foo.pt')
|
||||
|
||||
class_annotator.exportNone(recursivescriptmodule._c._type())
|
||||
class_annotator.exportPath(recursivescriptmodule._c._type(), ['forward'])
|
||||
class_annotator.annotateArgs(recursivescriptmodule._c._type(), ['forward'], [
|
||||
None,
|
||||
([2, 3, -1], torch.float32, True)
|
||||
])
|
||||
# TODO: Automatically handle unpacking Python class RecursiveScriptModule into the underlying ScriptModule.
|
||||
mb.import_module(recursivescriptmodule._c, class_annotator)
|
||||
#mb.module.operation.print()
|
||||
|
||||
backend = iree.IreeNpcompBackend()
|
||||
compiled = backend.compile(frontend_lowering.lower_object_graph(mb.module))
|
||||
jit_module = backend.load(compiled)
|
||||
|
||||
torch.manual_seed(0)
|
||||
input = torch.rand(2, 3, 1)
|
||||
test_utils.compare_outputs(test_module.forward, jit_module.forward, input)
|
||||
Loading…
Reference in New Issue