[GitHub] [incubator-mxnet] Laurawly commented on a change in pull request #16151: [numpy] [tvm] operator floor_divide

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

Laurawly commented on a change in pull request #16151: [numpy] [tvm] operator floor_divide
URL: https://github.com/apache/incubator-mxnet/pull/16151#discussion_r331255293
 
 

 ##########
 File path: contrib/tvmop/core/umath.py
 ##########
 @@ -0,0 +1,113 @@
+ # Licensed to the Apache Software Foundation (ASF) under one
+ # or more contributor license agreements.  See the NOTICE file
+ # distributed with this work for additional information
+ # regarding copyright ownership.  The ASF licenses this file
+ # to you under the Apache License, Version 2.0 (the
+ # "License"); you may not use this file except in compliance
+ # with the License.  You may obtain a copy of the License at
+ #
+ #   http://www.apache.org/licenses/LICENSE-2.0
+ #
+ # Unless required by applicable law or agreed to in writing,
+ # software distributed under the License is distributed on an
+ # "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ # KIND, either express or implied.  See the License for the
+ # specific language governing permissions and limitations
+ # under the License.
+import tvm
+from .. import defop, AllTypes
+
+def compute_floor_divide(dtype, ndim):
+    A = tvm.placeholder([tvm.var() for _ in range(ndim)], name='A', dtype=dtype)
+    B = tvm.placeholder([tvm.var() for _ in range(ndim)], name='B', dtype=dtype)
+    if dtype in ['float16', 'float32', 'float64']:
+        C = tvm.compute([tvm.var() for _ in range(ndim)],
+                    lambda *index: tvm.floor(A[index] / B[index]), name='C')
+    else:
+        C = tvm.compute([tvm.var() for _ in range(ndim)],
+                        lambda *index: tvm.if_then_else(B[index] == 0, tvm.const(0, dtype),
+                                                        tvm.floor(A[index].astype('float64') /
+                                                                  B[index].astype('float64')).astype(dtype)), name='C')
+    s = tvm.create_schedule(C.op)
+    return s, A, B, C
+
+@defop(name="floor_divide", target="cpu", auto_broadcast=True,
+       dtype=AllTypes, ndim=list(range(6)))
+def floor_divide(dtype, ndim):
+    s, A, B, C = compute_floor_divide(dtype, ndim)
+    axes = [axis for axis in C.op.axis]
+    fused = s[C].fuse(*axes)
+    s[C].parallel(fused)
+    return s, [A, B, C]
+
+@defop(name="cuda_floor_divide", target="cuda", auto_broadcast=True,
+       dtype=AllTypes, ndim=list(range(6)))
+def floor_divide_gpu(dtype, ndim):
+    s, A, B, C = compute_floor_divide(dtype, ndim)
+    axes = [axis for axis in C.op.axis]
+    fused = s[C].fuse(*axes)
+    bx, tx = s[C].split(fused, factor=64)
+    s[C].bind(bx, tvm.thread_axis("blockIdx.x"))
+    s[C].bind(tx, tvm.thread_axis("threadIdx.x"))
+    return s, [A, B, C]
+
+#  r represents the position of tensor
 
 Review comment:
   You can replace `r` with other name like `pos` or `tensor_pos` to remove this comment.

----------------------------------------------------------------
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