Update on "[ET-VK][Ops] aten.avg_pool2d"

## The Operator
`nn.Module` invocations of [`torch.nn.AvgPool2d`](https://pytorch.org/docs/stable/generated/torch.nn.AvgPool2d.html) get compiled to `aten.avg_pool2d.default` in the Edge Dialect, which carries the following signature.
```
- func: avg_pool2d(Tensor self, int[2] kernel_size, int[2] stride=[], int[2] padding=0, bool ceil_mode=False, bool count_include_pad=True, int? divisor_override=None) -> Tensor
```

## Implementation
This is a full implementation. We start with [LiteInterpreter's `avg_pool2d.glsl` logic](https://github.com/pytorch/pytorch/blob/9257a0698b57acc5607ee6fe31a16fdd93af1731/aten/src/ATen/native/vulkan/glsl/avg_pool2d.glsl), which is incomplete, and cover `ceil_mode=True`,  `count_include_pad=True`, and `divisor_override` cases for full support. As a result, the divisor's computation is now a bit complex. If needed, we can simplify it into separate shaders in the future.

Differential Revision: [D57918523](https://our.internmc.facebook.com/intern/diff/D57918523/)

[ghstack-poisoned]

Author: jorgep31415

backends/vulkan/test/op_tests/cases.py

@@ -115,21 +115,54 @@ def get_linear_inputs():
 
 
 def get_avg_pool2d_inputs():
-    Test = namedtuple("VkAvgPoolTest", ["self", "kernel_size", "stride", "padding", "ceil_mode", "count_include_pad", "divisor_override"])
+    Test = namedtuple(
+        "VkAvgPoolTest",
+        [
+            "self",
+            "kernel_size",
+            "stride",
+            "padding",
+            "ceil_mode",
+            "count_include_pad",
+            "divisor_override",
+        ],
+    )
     Test.__new__.__defaults__ = (None, None)
 
-    test_cases = [
-        Test(self=(S, M1, M2), kernel_size=[2, 2], stride=[1, 1], padding=[0, 0], ceil_mode=False, count_include_pad=True, divisor_override=None),
-        Test(self=(S, M1, M2), kernel_size=[2, 2], stride=[1, 1], padding=[0, 0], ceil_mode=False, count_include_pad=True, divisor_override=5),
-        Test(self=(S, M1, M2), kernel_size=[5, 4], stride=[1, 1], padding=[2, 1], ceil_mode=False, count_include_pad=True, divisor_override=None),
-        Test(self=(S, M1, M2), kernel_size=[4, 5], stride=[1, 1], padding=[2, 1], ceil_mode=False, count_include_pad=True, divisor_override=None),
-        Test(self=(S, M1, M2), kernel_size=[5, 4], stride=[1, 1], padding=[2, 1], ceil_mode=True, count_include_pad=False, divisor_override=None),
-        Test(self=(S, M1, M2), kernel_size=[4, 5], stride=[2, 2], padding=[2, 1], ceil_mode=True, count_include_pad=False, divisor_override=None),
-        Test(self=(S, M1, M2), kernel_size=[5, 4], stride=[3, 1], padding=[2, 1], ceil_mode=False, count_include_pad=False, divisor_override=None),
-        Test(self=(S, M1, M2), kernel_size=[4, 5], stride=[1, 3], padding=[2, 1], ceil_mode=False, count_include_pad=False, divisor_override=None),
-        Test(self=(S, M1, M2), kernel_size=[5, 4], stride=[4, 4], padding=[2, 1], ceil_mode=True, count_include_pad=True, divisor_override=None),
-        Test(self=(S, M1, M2), kernel_size=[4, 5], stride=[1, 1], padding=[2, 1], ceil_mode=True, count_include_pad=True, divisor_override=None),
-    ]
+    test_cases = []
+
+    for ceil_mode in [True, False]:
+        for count_include_pad in [True, False]:
+            for divisor_override in [None, 5]:
+                test_cases += [
+                    Test(
+                        self=(S, M1, M2),
+                        kernel_size=[2, 2],
+                        stride=[1, 1],
+                        padding=[0, 0],
+                        ceil_mode=ceil_mode,
+                        count_include_pad=count_include_pad,
+                        divisor_override=divisor_override,
+                    ),
+                    Test(
+                        self=(S, M1, M2),
+                        kernel_size=[5, 4],
+                        stride=[3, 1],
+                        padding=[2, 1],
+                        ceil_mode=ceil_mode,
+                        count_include_pad=count_include_pad,
+                        divisor_override=divisor_override,
+                    ),
+                    Test(
+                        self=(S, M1, M2),
+                        kernel_size=[4, 5],
+                        stride=[1, 3],
+                        padding=[2, 1],
+                        ceil_mode=ceil_mode,
+                        count_include_pad=count_include_pad,
+                        divisor_override=divisor_override,
+                    ),
+                ]
 
     test_suite = VkTestSuite([tuple(tc) for tc in test_cases])
     return test_suite

backends/vulkan/test/op_tests/utils/codegen_base.py

@@ -5,7 +5,7 @@
 # LICENSE file in the root directory of this source tree.
 
 import re
-from typing import Any, List, Tuple
+from typing import Any, List
 
 from torchgen.api import cpp
 from torchgen.api.types import CppSignatureGroup