* [GPU] Fix i8 representation error for clamp due to overflow
Signed-off-by: Andrew Park <andrew.park@intel.com>
* Fix to not include in ocl code
Signed-off-by: Andrew Park <andrew.park@intel.com>
---------
Signed-off-by: Andrew Park <andrew.park@intel.com>
* [GPU] Fix levit-128s accuracy issue
Wrong batch dims for fused eltwise of gemm.
-> The issue is getting incorrect batch size of fused eltwise used by gemm.
Its rank is different from src tensor. Eltwise tensor rank was reduced by mistake.
It is only reproduce in batch 1 and full tensor.
The batch size in here means all of non spatial dims, but previous implementation was default batch dim role.
Signed-off-by: hyunback <hyunback.kim@intel.com>
* [GPU] Resolve failed unit-tests on dGPU
+ Modified unit-tests of asymetric conv with per channel(WA for oneDNN issue)
+ Modified conv unit-tests with padded input or output
+ For testing oneDNN conv, it needs to query oneDNN about format. Applied this to conv tests.
+ Modified accuracy checking logic in unit-tests which have different format on dGPU.
+ reorder from fsv16 to bfyx should not be optimized out if not aligned by 16
Signed-off-by: Min, Byungil <byungil.min@intel.com>
* [GPU] Fix dump_graph failure issue in levit-128s model.
1. to_string() in strided_slice always access begin/end/stride param id from dependencies
regardless of max dependencies.
2. Add an exception in dump_full_node(). It helps below.
- Avoid a dump failure. Usually, graph dump are used during debugging,
which reduces unnecessary debugging time due to graph dump failure.
- You can immediately see which node has failed, making it easy to find it.
Signed-off-by: hyunback <hyunback.kim@intel.com>
* [Dynamic shape] Improve shape infer performance for igpu by preventing copy from usm_device to usm host from lock()
* Fixed is_shape_infer_dep to use pointer instead of unique_id becuase unique_id may not be set
* Remove constructors for ov Exceptions
* Fixed linux build
* Fixed ONNX Frontend
* Fixed paddle
* Fixed exceptions in tests
* Deprecate constructors for ov::Exception
* Suppress some warnings
* Merge several exceptions
* Some small changes
* Suppress more warnings
* More warnings
* mode warnings
* Suppress more warnings
* More warnings
+ Resolved issues related to deconv
+ Modified test-cases for conv, fc.
+ In fc unit-tests, tiny tensors showed unexpected behavior. Modified tensor size a little
+ Bugfix in get_test_stream
Signed-off-by: Min, Byungil <byungil.min@intel.com>
* updated to allocate memory in order of size while deserializing
* fix windows build error
* updated to check dependencies between not connected nodes
* [GPU] Fix to skip reorder optimization during post_optimize_graph phase
Signed-off-by: Andrew Park <andrew.park@intel.com>
* Apply comment
Signed-off-by: Andrew Park <andrew.park@intel.com>
* update condition to check empty padding
Signed-off-by: Andrew Park <andrew.park@intel.com>
* add condition to check batch size
Signed-off-by: Andrew Park <andrew.park@intel.com>
---------
Signed-off-by: Andrew Park <andrew.park@intel.com>
* Fix gather_nonzero not to be marked as constant.
Even though count nonzero is to be turned into a constant, gather nonzero still cannot infer shape at the moment of propagate constant.
* Apply the fix only for gather_non_zero
