Back to results
US 12,277,491 B2Granted
Encoded host to DLA traffic
AssigneeMicron Technology, Inc.
InventorsPoorna Kale, Saideep Tiku
Life of this patent
Estimating the term…
Abstract
Apparatuses and methods can be related to encoding traffic between a host and a deep learning accelerator (DLA). Traffic between a host can be encoded utilizing an autoencoder. Encoding traffic between a host and a DLA changes the bandwidth of the traffic. Changing the bandwidth of the traffic prevents the correlation between the bandwidth and the input from which the traffic is generated.
Claims23
An apparatus, comprising:
- an array of memory cells;
- a deep learning accelerator (DLA) coupled to the array;
- and
- a controller coupled to the array and to the DLA, wherein the controller is configured to:
- receive encoded data from a host;
- store the encoded data in the array;
- and
- wherein the DLA is configured to:
- responsive to receiving signals from the controller, access the encoded data from the array;
- decode the encoded data utilizing an autoencoder wherein the encoded data is decoded by a decoder of the autoencoder implemented by the DLA to generate decoded data and wherein the decoder of the autoencoder is implemented as an artificial neural network (ANN);
- and
- perform a plurality of operations on the decoded data.
9 more elements
A method, comprising:
- receiving, from a host at a deep learning accelerator (DLA) of a memory device, signaling indicative of first data that comprises hyperparameters to configure an artificial neural network (ANN), wherein the ANN is implemented by the DLA;
- receiving encoded second data from the host at the DLA of the memory device, wherein the second data is generated by a plurality of sensors and is encoded by an encoder of an autoencoder implemented by the host;
- decoding the encoded second data to generate decoded second data, wherein the decoding comprises utilizing a decoder of the autoencoder and wherein the decoder is implemented by the DLA;
- processing the decoded second data utilizing the ANN;
- and
- transmitting, to the host, an encoded output of the ANN.
3 more elements
A system, comprising:
- a host;
- a memory device comprising a deep learning accelerator (DLA) and an array of memory cells and wherein the DLA comprises a decoder of an autoencoder and an artificial neural network (ANN);
- wherein the host is configured to:
- encode a first set of data to generate encoded data, wherein the first set of data is encoded by an encoder of the autoencoder, wherein the encoder is implemented by the host;
- and
- provide the encoded data from the host to the DLA of the memory device to cause the DLA to process a second set of data, corresponding to the first set of data, utilizing the ANN;
- wherein the DLA is configured to:
- decode the encoded data, utilizing the decoder of the autoencoder, to generate a second set of data that corresponds to the first set of data;
- and
- process the second set of data utilizing the ANN.
7 more elements
Dependencies are inferred from the claim text.