提交 c4ea6761 authored 作者: Frederic's avatar Frederic

Add GpuCAReduce more cases and remove warning about shape of 0 in infer shape.

上级 907a465f
...@@ -90,6 +90,56 @@ class test_GpuCAReduce(test_GpuCAReduceCPY): ...@@ -90,6 +90,56 @@ class test_GpuCAReduce(test_GpuCAReduceCPY):
#((5, 0), ()), reduce on no axis isn't implemented #((5, 0), ()), reduce on no axis isn't implemented
#((), None), reduce on no axis isn't implemented #((), None), reduce on no axis isn't implemented
#((), ()) reduce on no axis isn't implemented #((), ()) reduce on no axis isn't implemented
#Test all GPU cases implemented
((1,0),(1,)),
((0,1),(1,)),
((0,0),(1,)),
((0,0,0),(1,2)),
((0,0,0,0),(1,2,3)),
((2,1),(1,)),
((1,2),(1,)),
((100,3,1300),[1]),
((0,),[0]),((5,),[0]),
((0,0),[0,1]),((1,0),[0,1]),((5,4),[0,1]),((33,31),[0,1]),((5,4),[1]),((5,4),[0]),#need something bigger then 32 for some opt test.
((5,4,3),[0]),((5,4,3),[1]),((5,4,3),[0,1]),((5,4,3),[2]),((5,4,3),[1,2]),((5,4,3),[0,1,2]),
((0,0,0,0),[0,1,2,3]),
((5,4,3,20),[2,3]), ((5,4,3,2),[0,1,2,3]), ((5,4,3,2),[0,2,3]),((5,4,3,2),[1,2,3]),
#test shape bigger then 4096 on each dimension to make sure that we work correctly when we don't have enough thread/block in each dimensions
((4100,3),[0]),((3,4101),[0]),#10
((1024,33),[0]),((33,1024),[0]),#10
((1025,33),[0]),((33,1025),[0]),#10
((4100,3),[1]),((3,4101),[1]),#01
((1024,33),[1]),((33,1024),[1]),#01
((1025,33),[1]),((33,1025),[1]),#01
((4100,3),[0,1]),((3,4101),[0,1]),#11
((1024,33),[0,1]),((33,1024),[0,1]),#01
((1025,33),[0,1]),((33,1025),[0,1]),#01
((4100,4,3),[0]),((5,4100,3),[0]),((5,4,4100),[0]), ((3,65536,1), [0]),#100
((4100,4,3),[1]),((5,4100,3),[1]),((5,4,4100),[1]),#010
((4100,4,3),[2]),((5,4100,3),[2]),((5,4,4100),[2]),#001
((4100,4,3),[0,1]),((5,4100,3),[0,1]),((5,4,4100),[0,1]),#110
((4100,4,3),[1,2]),((5,4100,3),[1,2]),((5,4,4100),[1,2]),#011
#((4100,4,3),[0,2]),((5,4100,3),[0,2]),((5,4,4100),[0,2]),#101 ##not implemented
((4100,4,3),[0,1,2]),((5,4100,3),[0,1,2]),((5,4,4100),[0,1,2]),#111
((4100,4,3,2),[2,3]),((4,4100,3,2),[2,3]),((4,3,4100,2),[2,3]),((4,3,2,4100),[2,3]),#0011
((4100,4,3,2),[1,3]),((4,4100,3,2),[1,3]),((4,3,4100,2),[1,3]),((4,3,2,4100),[1,3]),#0101
((4100,4,3,2),[0,2,3]),((4,4100,3,2),[0,2,3]),((4,3,4100,2),[0,2,3]),#((4,3,2,4100),[0,2,3]),#1011
((4100,4,3,2),[1,2,3]),((4,4100,3,2),[1,2,3]),((4,3,4100,2),[1,2,3]),((4,3,2,4100),[1,2,3]),#0111
((4100,2,3,4),[0,1,2,3]),((2,4100,3,4),[0,1,2,3]),((2,3,4100,4),[0,1,2,3]),((2,3,4,4100),[0,1,2,3]),((128,1,3,3), [0,1,2,3]),#1111
#test pattern implemented by reshape
# ((4100,4,3,2),[0]),((4,4100,3,2),[0]),((4,3,4100,2),[0]),((4,3,2,4100),[0]),#1000
# ((4100,4,3,2),[1]),((4,4100,3,2),[1]),((4,3,4100,2),[1]),((4,3,2,4100),[1]),#0100
# ((4100,4,3,2),[2]),((4,4100,3,2),[2]),((4,3,4100,2),[2]),((4,3,2,4100),[2]),#0010
# ((4100,4,3,2),[3]),((4,4100,3,2),[3]),((4,3,4100,2),[3]),((4,3,2,4100),[3]),#0001
# ((1100,2,3,4,5),[0,1,2,3,4]),((2,1100,3,4,5),[0,1,2,3,4]),((2,3,1100,4,5),[0,1,2,3,4]),((2,3,4,1100,5),[0,1,2,3,4]),((2,3,4,5,1100),[0,1,2,3,4]),#11111
# ((5,4,3,10,11),[1,2]),
] ]
op = GpuCAReduce op = GpuCAReduce
reds = [scalar.add, scalar.mul] reds = [scalar.add, scalar.mul]
......
...@@ -507,8 +507,10 @@ class test_CAReduce(unittest_tools.InferShapeTester): ...@@ -507,8 +507,10 @@ class test_CAReduce(unittest_tools.InferShapeTester):
tosum = range(len(xsh)) tosum = range(len(xsh))
xv = numpy.asarray(numpy.random.rand(*xsh), dtype=dtype) xv = numpy.asarray(numpy.random.rand(*xsh), dtype=dtype)
self._compile_and_check([x], self._compile_and_check([x],
[self.op(scalar.add, axis=tosum)(x)], [self.op(scalar.add, axis=tosum)(x)],
[xv], self.op, ["local_cut_useless_reduce"]) [xv], self.op,
["local_cut_useless_reduce"],
warn=0 not in xsh)
class test_Prod(unittest.TestCase): class test_Prod(unittest.TestCase):
......
Markdown 格式
0%
您添加了 0 到此讨论。请谨慎行事。
请先完成此评论的编辑!
注册 或者 后发表评论