This is a testharness.js-based test.
[FAIL] [gather] Test gather with default options and 0-D indices
promise_test: Unhandled rejection with value: object "TypeError: Failed to execute 'input' on 'MLGraphBuilder': Unsupported data type int64 for input operand named 'indices', must be one of [float32, float16, int32]."
[FAIL] [gather] Test gather with axis = 2
promise_test: Unhandled rejection with value: object "TypeError: Failed to execute 'input' on 'MLGraphBuilder': Unsupported data type int64 for input operand named 'indices', must be one of [float32, float16, int32]."
[FAIL] [gather] Test gather with indices's dataType = uint32
promise_test: Unhandled rejection with value: object "TypeError: Failed to execute 'input' on 'MLGraphBuilder': Unsupported data type uint32 for input operand named 'indices', must be one of [float32, float16, int32]."
[FAIL] [gather] TypeError is expected if the input is a scalar
promise_test: Unhandled rejection with value: object "TypeError: Failed to execute 'input' on 'MLGraphBuilder': Unsupported data type int64 for input operand named 'indices', must be one of [float32, float16, int32]."
[FAIL] [gather] TypeError is expected if the data type of indices is uint64 which is invalid
promise_test: Unhandled rejection with value: object "TypeError: Failed to execute 'input' on 'MLGraphBuilder': Unsupported data type uint64 for input operand named 'indices', must be one of [float32, float16, int32]."
[FAIL] [gather] throw if input is from another builder
promise_test: Unhandled rejection with value: object "TypeError: Failed to execute 'input' on 'MLGraphBuilder': Unsupported data type int64 for input operand named 'indices', must be one of [float32, float16, int32]."
[FAIL] [gather] throw if indices is from another builder
promise_test: Unhandled rejection with value: object "TypeError: Failed to execute 'input' on 'MLGraphBuilder': Unsupported data type int64 for input operand named 'indices', must be one of [float32, float16, int32]."
Harness: the test ran to completion.