elvin-n commented on code in PR #11878:
URL: https://github.com/apache/tvm/pull/11878#discussion_r931917655
##########
tests/python/relay/test_conv2d_nchw_texture.py:
##########
@@ -435,3 +435,558 @@ def test_conv2d_vgg16_winograd_4d():
graph = build_run_compare(mod, params1, {"data": input_shape}, dtype,
target)
matches = re.findall("winograd", graph)
assert len(matches) > 0
+
+
+@tvm.testing.requires_opencl
+def test_residual_block():
+ target = "opencl --device=adreno"
+ dtype = "float16"
+
+ input_shape = (1, 32, 40, 40)
+ filter_shape1 = (32, 32, 2, 2)
+ filter_shape2 = (32, 32, 1, 1)
+ filter_shape3 = (32, 32, 2, 2)
+ bias_shape1 = (1, 32, 1, 1)
+ A = relay.var("data", shape=input_shape, dtype=dtype)
+ W1 = relay.var("weight1", shape=filter_shape1, dtype=dtype)
+ B1 = relay.var("bias1", shape=bias_shape1, dtype=dtype)
+ W2 = relay.var("weight2", shape=filter_shape2, dtype=dtype)
+ W3 = relay.var("weight3", shape=filter_shape3, dtype=dtype)
+
+ conv1 = relay.nn.conv2d(
+ A,
+ W1,
+ data_layout="NCHW",
+ kernel_layout="OIHW",
+ padding=[0, 0, 0, 0],
+ strides=[2, 2],
+ out_dtype=dtype,
+ channels=32,
+ kernel_size=(2, 2),
+ )
+ D = relay.op.add(conv1, B1)
+ D = relay.op.nn.relu(D)
+
+ conv2 = relay.nn.conv2d(
+ D,
+ W2,
+ data_layout="NCHW",
+ kernel_layout="OIHW",
+ padding=[0, 0, 0, 0],
+ strides=[1, 1],
+ out_dtype=dtype,
+ channels=32,
+ kernel_size=(1, 1),
+ )
+ D = relay.op.add(conv2, D)
+ D = D * relay.const(0.15, "float16")
+ D = relay.op.nn.relu(D)
+
+ conv3 = relay.nn.conv2d(
+ D,
+ W3,
+ data_layout="NCHW",
+ kernel_layout="OIHW",
+ padding=[0, 0, 0, 0],
+ strides=[2, 2],
+ out_dtype=dtype,
+ channels=32,
+ kernel_size=(2, 2),
+ )
+ D = relay.op.nn.relu(conv3)
+
+ mod = relay.Function([A, W1, B1, W2, W3], D)
+ np.random.seed(0)
+ initializer = relay.testing.init.Xavier()
+ filter_data1 = np.zeros(filter_shape1).astype(dtype)
+ bias_data1 = np.zeros(bias_shape1).astype(dtype)
+ initializer("weight", filter_data1)
+ initializer("bias", bias_data1)
+ filter_data2 = np.zeros(filter_shape2).astype(dtype)
+ initializer("weight", filter_data2)
+ filter_data3 = np.zeros(filter_shape3).astype(dtype)
+ initializer("weight", filter_data3)
+ params1 = {
+ "weight1": tvm.nd.array(filter_data1),
+ "bias1": tvm.nd.array(bias_data1),
+ "weight2": tvm.nd.array(filter_data2),
+ "weight3": tvm.nd.array(filter_data3),
+ }
+
+ static_memory_scope = [
+ "",
+ "global",
+ "global.texture-weight",
+ "global.texture-weight",
+ "global.texture",
+ "global.texture-weight",
+ "global",
+ "global.texture",
+ "global.texture-weight",
+ "",
Review Comment:
BTW, please don't be confused by the name of the memory scopes. It is
historical naming. Now the layout of texture is defined by some algorithm
defined in annotate_texture_storage.cc `Scope()` functions. and it is rather
refer to
```texture -> 123|4|5
texture-weight -> 1|234|5
texture-nchw ->12|34|5```
these scopes are applied to any type of the tensor - data/weights/bias.
dividing by buckets are defined only based by values in shape
--
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: commits-unsubscr...@tvm.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
