diff options
| author | David Gross <dgross@google.com> | 2019-03-15 17:26:32 -0700 |
|---|---|---|
| committer | Xusong Wang <xusongw@google.com> | 2019-03-21 19:37:36 -0700 |
| commit | 632b4bd9b0ba0b26a40c3f81fad724f8c07179fe (patch) | |
| tree | e114120211498ececf746c4710ae8adbbee04e13 /identity/support/src/cppbor_parse.cpp | |
| parent | ad439a04249944fa017ed13f833a5c500f794084 (diff) | |
Add @V1_2::Capabilities to support all non extension operand types.
Performance information in Capabilities is used by the runtime when
it selects the appropriate processor to distribute work to. Prior to
this CL, Capabilities can only distinguish between float and non-float
data types -- so, for example, float16 and float32 performance is
considered to be the same, and performance for all non-float data types is
considered to be the same.
Bug: 124041010
Test: NeuralNetworksTest_static
Test: VtsHalNeuralnetworksV1_2TargetTest --hal_service_instance=android.hardware.neuralnetworks@1.2::IDevice/sample-all
Change-Id: I83fb5920c1c75afbd7750d793a0b8f3e72a0552c
Diffstat (limited to 'identity/support/src/cppbor_parse.cpp')
0 files changed, 0 insertions, 0 deletions