[GitHub] [incubator-tvm] alexgl-github commented on a change in pull request #4737: Add CUDA conv2d for NHWC layout

[GitBox <gi...@apache.org>]

alexgl-github commented on a change in pull request #4737: Add CUDA conv2d for NHWC layout
URL: https://github.com/apache/incubator-tvm/pull/4737#discussion_r368340774
 
 

 ##########
 File path: topi/python/topi/cuda/conv2d.py
 ##########
 @@ -162,3 +164,37 @@ def _callback(op):
 
     traverse_inline(s, outs[0].op, _callback)
     return s
+
+
+@autotvm.register_topi_schedule(generic.schedule_conv2d_nhwc, ["cuda", "gpu"],
+                                ["direct"])
+def schedule_conv2d_nhwc_cuda(cfg, outs):
+    """TOPI schedule for CUDA conv2d_nhwc
+
+    Parameters
+    ----------
+    cfg: ConfigEntity
+        The config for this template
+
+    outs: Array of Tensor
+        The computation graph description of conv2d
+        in the format of an array of tensors.
+
+    Returns
+    -------
+    s: Schedule
+        The computation schedule for conv2d.
+    """
+    target = tvm.target.current_target()
+    if 'cudnn' in target.libs:
+        return generic.schedule_extern(outs)
+
+    outs = [outs] if isinstance(outs, tvm.tensor.Tensor) else outs
+    s = tvm.create_schedule([x.op for x in outs])
+
+    def _callback(op):
+        if op.tag == 'conv2d_nhwc':
+            schedule_direct_cuda(cfg, s, op.output(0))
 
 Review comment:
   Yes it does. The tests are also passing.

----------------------------------------------------------------
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.
 
For queries about this service, please contact Infrastructure at:
users@infra.apache.org


With regards,
Apache Git Services