fv = f(gv)
assert numpy.all(fv == av)
def gpu_alloc_expected(x, *shp):
g = gpuarray.empty(shp, dtype=x.dtype, context=get_context(test_ctx_name))
g[:] = x
return g
GpuAllocTester = makeTester(
name="GpuAllocTester",
op=alloc,
gpu_op=GpuAlloc(test_ctx_name),
cases=dict(
correct01=(rand(), numpy.int32(7)),
# just gives a DeepCopyOp with possibly wrong results on the CPU
# correct01_bcast=(rand(1), numpy.int32(7)),
correct02=(rand(), numpy.int32(4), numpy.int32(7)),
correct12=(rand(7), numpy.int32(4), numpy.int32(7)),
correct13=(rand(7), numpy.int32(2), numpy.int32(4), numpy.int32(7)),
correct23=(rand(4, 7), numpy.int32(2), numpy.int32(4), numpy.int32(7)),
bad_shape12=(rand(7), numpy.int32(7), numpy.int32(5)),
))
class TestAlloc(test_basic.TestAlloc):
dtype = "float32"
mode = mode_with_gpu
shared = staticmethod(gpuarray_shared_constructor)
allocs = [GpuAlloc(test_ctx_name), GpuAlloc(test_ctx_name), T.Alloc()]
fvs = f(gvs)
assert cuda_ndarray.CudaNdarrayType.values_eq_approx(fvs, cvs)
def gpu_alloc_expected(x, *shp):
g = gpuarray.empty(shp, dtype=x.dtype)
g[:] = x
return g
GpuAllocTester = makeTester(
name="GpuAllocTester",
op=alloc,
gpu_op=gpu_alloc,
cases=dict(
correct01=(rand(), numpy.int32(7)),
# just gives a DeepCopyOp with possibly wrong results on the CPU
# correct01_bcast=(rand(1), numpy.int32(7)),
correct02=(rand(), numpy.int32(4), numpy.int32(7)),
correct12=(rand(7), numpy.int32(4), numpy.int32(7)),
correct13=(rand(7), numpy.int32(2), numpy.int32(4),
numpy.int32(7)),
correct23=(rand(4, 7), numpy.int32(2), numpy.int32(4),
numpy.int32(7)),
bad_shape12=(rand(7), numpy.int32(7), numpy.int32(5)),
)
)
class TestAlloc(test_basic.TestAlloc):
dtype = "float32"