lhutton1 commented on a change in pull request #9209:
URL: https://github.com/apache/tvm/pull/9209#discussion_r723689306
##########
File path: python/tvm/relay/backend/contrib/ethosu/legalize.py
##########
@@ -208,6 +208,96 @@ def __call__(self, *args, **kwargs):
pass
+class EthosuDepthwise2DRewriter(DFPatternCallback):
+ """Convert ethosu.qnn_depthwise2d composite functions to
ethosu_depthwise2d operators"""
+
+ def __init__(self):
+ super().__init__(require_type=True)
+ self.pattern = (
+ wildcard().has_attr({"Composite":
ethosu_patterns.QnnDepthwise2DParams.composite_name})
+ )(wildcard())
+
+ def callback(
+ self, pre: tvm.relay.Expr, post: tvm.relay.Expr, node_map:
tvm.ir.container.Map
+ ) -> tvm.relay.Expr:
+ params = ethosu_patterns.QnnDepthwise2DParams(post.op.body)
+ params.ifm.tensor = post.args[0]
+ channels_map = {
+ "NHWC": 3,
+ }
+ if str(params.ofm.layout) not in channels_map.keys():
+ raise UnsupportedLayout(str(params.ofm.layout))
+ kernel_shape_map = {
+ "HWOI": params.weights.shape[0:2],
Review comment:
Is it worth supporting OHWI weights here?
##########
File path: python/tvm/relay/op/contrib/ethosu.py
##########
@@ -223,12 +223,13 @@ def __init__(self, func_body: tvm.relay.Function):
self.strides = qnn_conv2d.attrs.strides
self.dilation = qnn_conv2d.attrs.dilation
self.activation = activation
+ self.channels = qnn_conv2d.attrs.channels
Review comment:
Better to access attrs once here i.e,
```
attrs = qnn_conv2d.attrs
self.padding = attrs.padding
...
self.channels = attrs.channels
```
##########
File path: python/tvm/relay/op/contrib/ethosu.py
##########
@@ -272,14 +315,34 @@ def qnn_conv2d_pattern() ->
tvm.relay.dataflow_pattern.DFPattern:
return clip_or_req
+def qnn_depthwise2d_pattern() -> tvm.relay.dataflow_pattern.DFPattern:
+ """
+ This function creates the pattern for depthwise qnn.conv2D with optional
fused RELU activation.
+ """
+ qnn_conv2d = is_op("qnn.conv2d")(
+ wildcard(), is_constant(), is_constant(), is_constant(),
is_constant(), is_constant()
+ ).has_attr({"kernel_layout": "HWOI"})
+ bias_add = is_op("nn.bias_add")(qnn_conv2d, is_constant())
+ req = is_op("qnn.requantize")(
+ qnn_conv2d | bias_add, is_constant(), is_constant(), is_constant(),
is_constant()
Review comment:
Remove optional bias here? Then we can follow up with separate PR for
conv2d
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
