def verify_gather_nd(src_shape, indices_src, indices_dtype): src_dtype = "float32" indices_src = np.array(indices_src, dtype=indices_dtype) A = tvm.placeholder(shape=src_shape, dtype=src_dtype, name="A") indices = tvm.placeholder(shape=indices_src.shape, dtype=indices_dtype, name="indices") out_tensor = topi.gather_nd(a=A, indices=indices) def check_device(device): ctx = tvm.context(device, 0) if not ctx.exist: print("Skip because %s is not enabled" % device) return print("Running on target: %s" % device) with tvm.target.create(device): s = topi.generic.schedule_injective(out_tensor) func = tvm.build(s, [A, indices, out_tensor], device, name="take") shape_size = 1 for i in range(len(src_shape)): shape_size = shape_size * src_shape[i] data_npy = np.arange(shape_size, dtype=src_dtype).reshape((src_shape)) out_npys = topi.testing.gather_nd_python(data_npy, indices_src) data_nd = tvm.nd.array(data_npy, ctx) indices_nd = tvm.nd.array(indices_src, ctx) out_nd = tvm.nd.empty(out_npys.shape, ctx=ctx, dtype=src_dtype) func(data_nd, indices_nd, out_nd) tvm.testing.assert_allclose(out_nd.asnumpy(), out_npys) for device in get_all_backend(): check_device(device)
def verify_gather_nd(src_shape, indices_src, indices_dtype): src_dtype = "float32" indices_src = np.array(indices_src, dtype=indices_dtype) A = tvm.placeholder(shape=src_shape, dtype=src_dtype, name="A") indices = tvm.placeholder(shape=indices_src.shape, dtype=indices_dtype, name="indices") out_tensor = topi.gather_nd(a=A, indices=indices) def check_device(device): ctx = tvm.context(device, 0) if not ctx.exist: print("Skip because %s is not enabled" % device) return print("Running on target: %s" % device) with tvm.target.create(device): s = topi.generic.schedule_injective(out_tensor) func = tvm.build(s, [A, indices, out_tensor] , device, name="take") shape_size = 1 for i in range(len(src_shape)): shape_size = shape_size * src_shape[i] data_npy = np.arange(shape_size, dtype=src_dtype).reshape((src_shape)) out_npys = topi.testing.gather_nd_python(data_npy, indices_src) data_nd = tvm.nd.array(data_npy, ctx) indices_nd = tvm.nd.array(indices_src, ctx) out_nd = tvm.nd.empty(out_npys.shape, ctx=ctx, dtype=src_dtype) func(data_nd, indices_nd, out_nd) tvm.testing.assert_allclose(out_nd.asnumpy(), out_npys) for device in get_all_backend(): check_device(device)