commit 068df81ab68f787e6d910595590c6353efc7e7e1
author Ian Hua <ianhua@google.com> Wed Sep 15 15:10:06 2021 +0100
committer Ian Hua <ianhua@google.com> Mon Oct 18 11:38:55 2021 +0100
tree 77af4c672400c8bc839441a7b4b0eaecefb8269f
parent 996054b24fc8d5bd70328aabacd4cbd27da0db20

AIDL interface changes for NNAPI feature level 6.

- Add BATCH_MATMUL operation
- Support TENSOR_INT32 for RESHAPE operation.

Also update "current" version snapshot and use
android.hardware.neuralnetworks-V2-ndk since AIDL v1 has been frozen.

Bug: 193012662
Bug: 200281183
Test: mm
Change-Id: Iabe45c57e2306d61055f711eda03b80b9cbe906d
Merged-In: Iabe45c57e2306d61055f711eda03b80b9cbe906d

neuralnetworks/utils/service/Android.bp

diff --git a/neuralnetworks/utils/service/Android.bp b/neuralnetworks/utils/service/Android.bp
index 653e51a..fbb8679 100644
--- a/neuralnetworks/utils/service/Android.bp
+++ b/neuralnetworks/utils/service/Android.bp
@@ -39,7 +39,7 @@
         "neuralnetworks_utils_hal_common",
     ],
     shared_libs: [
-        "android.hardware.neuralnetworks-V1-ndk",
+        "android.hardware.neuralnetworks-V2-ndk",
         "android.hardware.neuralnetworks@1.0",
         "android.hardware.neuralnetworks@1.1",
         "android.hardware.neuralnetworks@1.2",