Clarify 'device type' is a normative type

webmachinelearning · Jun 16, 2022 · 5185b9f · 5185b9f
1 parent 7d85c93
commit 5185b9f
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/index.bs b/index.bs
@@ -438,7 +438,7 @@ Unlike APIs like WebGL, and WebGPU; this API does not intrinsically support cust
 
 The WebGPU API identifies <a href="https://gpuweb.github.io/gpuweb/#privacy-machine-artifacts">machine-specific artifacts</a> as a privacy consideration. Given the WebNN API defines means to record an ML worload onto a WebGPU-compatible {{GPUCommandBuffer}}, compute unit scheduling may under certain circumstances introduce a fingerprint. However, similarly to WebGPU, such fingerprints are identical across most or all of the devices of each vendor, mitigating the concern. Furthermore, software implementations can be used to further eliminate such artifacts.
 
-The WebNN API defines two developer-settable preferences to help inform [[#programming-model-device-selection]] and allow the implementation better select the most appropriate underlying execution device for the workload. [=Device type=] preference indicates the kind of device and is either "cpu" or "gpu". If this preference cannot be satisfied, an {{OperationError}} exception is thrown, thus this preference can in some cases add two bits of entropy to the fingerprint. [=Power preference=] indicates preference as related to the power consumption and is considered a hint only and as such does not increase entropy of the fingerprint.
+The WebNN API defines two developer-settable preferences to help inform [[#programming-model-device-selection]] and allow the implementation better select the most appropriate underlying execution device for the workload. [=Device type=] normatively indicates the kind of device and is either "cpu" or "gpu". If this type cannot be satisfied, an {{OperationError}} exception is thrown, thus this type can in some cases add two bits of entropy to the fingerprint. [=Power preference=] indicates preference as related to the power consumption and is considered a hint only and as such does not increase entropy of the fingerprint.
 
 If a future version of this specification introduces support for new a  [=device type=] that can only support a subset of {{MLOperandType}}s, that may introduce a new fingerprint.