diff options
| author | Viet-Hoa Do <viet-hoa.do@arm.com> | 2023-03-15 14:05:06 +0000 |
|---|---|---|
| committer | Viet-Hoa Do <viet-hoa.do@arm.com> | 2023-03-29 14:03:30 +0000 |
| commit | fd472f05dc73005a89a5e6275940ab5c9a609485 (patch) | |
| tree | 4a00f42f64f4bea72c489961aaa376665d324c60 /src/CMakeLists.txt | |
| parent | 5a7d1571a2de24eefc6f1d8d22deeef9f47521ee (diff) | |
| download | ComputeLibrary-fd472f05dc73005a89a5e6275940ab5c9a609485.tar.gz | |
Add quantized support for unary elementwise in CPU
* Add quantized unary elementwise in CPU using LUT.
* Widen the input data range of the test suite.
- Fix CPU exponential function overflow/underflow range.
- Fix saturation issue of CL round operator.
Resolves: COMPMID-5763
Signed-off-by: Viet-Hoa Do <viet-hoa.do@arm.com>
Change-Id: I41445de2b4a33ec6b01e0ab701516c240c852d0b
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9367
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Jakub Sujak <jakub.sujak@arm.com>
Reviewed-by: Pablo Marquez Tello <pablo.tello@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'src/CMakeLists.txt')
| -rw-r--r-- | src/CMakeLists.txt | 5 |
1 files changed, 4 insertions, 1 deletions
diff --git a/src/CMakeLists.txt b/src/CMakeLists.txt index ca07ebf029..92c888056e 100644 --- a/src/CMakeLists.txt +++ b/src/CMakeLists.txt @@ -305,6 +305,8 @@ target_sources( cpu/kernels/elementwise_unary/generic/sve/fp32.cpp cpu/kernels/elementwise_unary/generic/sve/impl.cpp cpu/kernels/elementwise_unary/generic/sve/integer.cpp + cpu/kernels/elementwise_unary/generic/sve/q8.cpp + cpu/kernels/lut/generic/sve/u8.cpp cpu/kernels/scale/sve/fp16.cpp cpu/kernels/scale/sve/fp32.cpp cpu/kernels/scale/sve/integer.cpp @@ -730,6 +732,7 @@ target_sources( cpu/kernels/elementwise_unary/generic/neon/fp32.cpp cpu/kernels/elementwise_unary/generic/neon/impl.cpp cpu/kernels/elementwise_unary/generic/neon/integer.cpp + cpu/kernels/elementwise_unary/generic/neon/q8.cpp cpu/kernels/floor/neon/fp16.cpp cpu/kernels/floor/neon/fp32.cpp cpu/kernels/fuse_batch_normalization/generic/fp16.cpp @@ -754,6 +757,7 @@ target_sources( cpu/kernels/instancenorm/generic/neon/impl.cpp cpu/kernels/internal/CpuDepthwiseConv2dAssemblyWrapperKernel.cpp cpu/kernels/internal/CpuPool2dAssemblyWrapperKernel.cpp + cpu/kernels/lut/generic/neon/u8.cpp cpu/kernels/l2normlayer/generic/neon/fp16.cpp cpu/kernels/l2normlayer/generic/neon/fp32.cpp cpu/kernels/l2normlayer/generic/neon/impl.cpp @@ -957,4 +961,3 @@ target_sources( runtime/TensorAllocator.cpp runtime/Utils.cpp ) -
\ No newline at end of file |