公开(公告)号：US20220122646A1

公开(公告)日：2022-04-21

申请号：US17071924

申请日：2020-10-15

Applicant: HEWLETT PACKARD ENTERPRISE DEVELOPMENT LP

Inventor： Catherine Graves ,  Can Li ,  Kivanc Ozonat ,  John Paul Strachan

IPC: G11C11/00 ,  G11C11/412 ,  G11C11/06 ,  G06F9/38

Abstract: Examples described herein relate to a decision tree computation system in which a hardware accelerator for a decision tree is implemented in the form of an analog Content Addressable Memory (a-CAM) array. The hardware accelerator accesses a decision tree. The decision tree comprises of multiple paths and each path of the multiple paths includes a set of nodes. Each node of the decision tree is associated with a feature variable of multiple feature variables of the decision tree. The hardware accelerator combines multiple nodes among the set of nodes with a same feature variable into a combined single node. Wildcard values are replaced for feature variables not being evaluated in each path. Each combined single node associated with each feature variable is mapped to a corresponding column in the a-CAM array and the multiple paths of the decision tree to rows of the a-CAM array.

公开(公告)号：US11615827B2

公开(公告)日：2023-03-28

申请号：US17071924

申请日：2020-10-15

Applicant: HEWLETT PACKARD ENTERPRISE DEVELOPMENT LP

Inventor： Catherine Graves ,  Can Li ,  Kivanc Ozonat ,  John Paul Strachan

IPC: G11C15/04 ,  G11C11/00 ,  G06F9/38 ,  G11C11/06 ,  G11C11/412

Abstract: Examples described herein relate to a decision tree computation system in which a hardware accelerator for a decision tree is implemented in the form of an analog Content Addressable Memory (a-CAM) array. The hardware accelerator accesses a decision tree. The decision tree comprises of multiple paths and each path of the multiple paths includes a set of nodes. Each node of the decision tree is associated with a feature variable of multiple feature variables of the decision tree. The hardware accelerator combines multiple nodes among the set of nodes with a same feature variable into a combined single node. Wildcard values are replaced for feature variables not being evaluated in each path. Each combined single node associated with each feature variable is mapped to a corresponding column in the a-CAM array and the multiple paths of the decision tree to rows of the a-CAM array.