You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by GitBox <gi...@apache.org> on 2021/07/21 17:39:45 UTC

[GitHub] [tvm] comaniac commented on a change in pull request #8523: [Bugfix] check type failed when partitioning tensorarray ops

comaniac commented on a change in pull request #8523:
URL: https://github.com/apache/tvm/pull/8523#discussion_r674196197



##########
File path: tests/python/relay/test_tensor_array.py
##########
@@ -780,5 +780,32 @@ def run(dtype, shape):
     run("int32", [2, 3])
 
 
+@tvm.testing.uses_gpu
+def test_static_tensor_array_gather_partition():
+    def run(dtype, shape):
+        mod = tvm.IRModule()
+        p = Prelude(mod)
+        static_tensor_array_ops = StaticTensorArrayOps(p, dtype, shape)
+        static_tensor_array_ops.register()
+
+        tensor_array = p.get_global_var_static("tensor_array", dtype, shape)
+        tensor = p.get_tensor_ctor_static("tensor_constructor", dtype, shape)
+        write = p.get_global_var_static("tensor_array_write", dtype, shape)
+        gather = p.get_global_var_static("tensor_array_gather", dtype, shape)
+        v = relay.var("v")
+        indice = relay.var("indice")
+        init_tensor_array = tensor_array(relay.const(3))
+        tensor_array1 = write(init_tensor_array, relay.const(0), tensor(v))
+        tensor_array2 = write(tensor_array1, relay.const(1), tensor(v))
+        tensor_array3 = write(tensor_array2, relay.const(2), tensor(v))
+        out = gather(tensor_array3, indice)
+        mod["main"] = relay.Function([v, indice], out)
+        from tvm.relay.op.contrib.tensorrt import partition_for_tensorrt

Review comment:
       1. Move to the beginning to this function.
   2. Add a guard to make sure TRT is enabled.
   3. Add a comment saying what to test. For example, you can say this is to make sure type definition and imports are preserved during the BYOC pipeline. 




-- 
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-unsubscribe@tvm.apache.org

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