Added Float16 type definition from third-party
Refine float16 bias handlling in conv2d
Refine float16 case in conv2d
Caution: Headers of float16 only be included when build unit_test
Type: New Feature
Signed-off-by: Feiyue Chen <Feiyue.Chen@verisilicon.com>
If Executable object doesn't bind with a concrete DeviceID,
it will go first device by default.
When run multi executable with multi device, the behavior is not
expected. Fixed by attach device id with CompileOption.
Signed-off-by: xiang.zhang <xiang.zhang@verisilicon.com>
* Add support for different input dtype of MaxPoolGrad.
Type: Code improvement
* Integrate api trace into tim-vx source code, as part of experimeantal.
Type: New Feature
Support tensor cache while create tensor
Tensor can be shared between different operations, if tensor have
identical data and quantization parameter, they should share same
low-level tensor object to save memory.
In tim-vx, introduce a tensor cache which key is md5sum and value is
low-level tensor object. If up-coming tensor have same md5sum, the
cached tensor object reused for tensor creation.
Type: New feature
Signed-off-by: Chen Xin <jack.chen@verisilicon.com>
Co-authored-by: Chen Xin <jack.chen@verisilicon.com>
Added Clang build check with CMAKE
Added vx-delegate build and benchmark_model test for PR.
Added tim-vx/samples in ci
Save output from build for debugging purpose.
Parallel CI execution.
Signed-off-by: xiang.zhang <xiang.zhang@verisilicon.com>
* Remove unnecessary compiler flags
* Refactor CMakeLists.txt
* Tweak CMakeLists.txt for libtim_internal
* Tweak CMakeLists.txt for libtim-vx
* Make TIM_VX_ENABLE_TEST defaults to OFF
* Eliminate usage of include_directories
* Fix CI unit test
* Support auto-downloading toolchain and SDK from http
* Support one-click cross compilation
Usage:
mkdir build && cd build
cmake .. -DHARDWARE=A311D
make -j4
Signed-off-by: Zongwu.Yang <Zongwu.Yang@verisilicon.com>