commit fd472f05dc73005a89a5e6275940ab5c9a609485
author Viet-Hoa Do <viet-hoa.do@arm.com> Wed Mar 15 14:05:06 2023 +0000
committer Viet-Hoa Do <viet-hoa.do@arm.com> Wed Mar 29 14:03:30 2023 +0000
tree 4a00f42f64f4bea72c489961aaa376665d324c60
parent 5a7d1571a2de24eefc6f1d8d22deeef9f47521ee

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>

Android.bp

diff --git a/Android.bp b/Android.bp
index 848ae10..5617812 100644
--- a/Android.bp
+++ b/Android.bp
@@ -486,6 +486,7 @@
         "src/cpu/kernels/elementwise_unary/generic/neon/fp32.cpp",
         "src/cpu/kernels/elementwise_unary/generic/neon/impl.cpp",
         "src/cpu/kernels/elementwise_unary/generic/neon/integer.cpp",
+        "src/cpu/kernels/elementwise_unary/generic/neon/q8.cpp",
         "src/cpu/kernels/floor/neon/fp16.cpp",
         "src/cpu/kernels/floor/neon/fp32.cpp",
         "src/cpu/kernels/fuse_batch_normalization/generic/fp16.cpp",
@@ -513,6 +514,7 @@
         "src/cpu/kernels/l2normlayer/generic/neon/fp16.cpp",
         "src/cpu/kernels/l2normlayer/generic/neon/fp32.cpp",
         "src/cpu/kernels/l2normlayer/generic/neon/impl.cpp",
+        "src/cpu/kernels/lut/generic/neon/u8.cpp",
         "src/cpu/kernels/maxunpool/generic/neon/fp16.cpp",
         "src/cpu/kernels/maxunpool/generic/neon/fp32.cpp",
         "src/cpu/kernels/maxunpool/generic/neon/impl.cpp",