Abstract: Reconfigurable dataflow architecture is an emerging design for deep learning training accelerator. This architecture maps model operators to an accelerator in a spatial way, enabling pipeline parallelization for high throughput. An essential ingredient to exploit this throughput advantage is compiler Performance Optimization (PO) which searches for optimal model mappings. The convention in industry-leading dataflow compilation uses hand-tuned rules to guide PO, requiring immense engineering cost to develop. This paper challenges this convention and asks if data-driven learned performance optimization can reduce the engineering cost while improving training throughput over hand-tuned rules. We present a workflow which guides PO using simple machine learning models trained from throughput observations of randomly generated mappings.

Abstract: A cost estimation tool in a system for implementing an operation unit graph on a reconfigurable processor is presented as well as a method of operating a cost estimation tool for estimating a cost of implementing an operation unit graph. The operation unit graph may include first and second logical units that perform first and second data operations and have first and second ports, respectively, coupled by a logical edge, on a reconfigurable processor. The method includes receiving the operation unit graph, determining first and second upper bandwidth limits of the first and second ports, respectively, determining a logical edge bandwidth of the logical edge based on the first and second upper bandwidth limits, determining a timing group for the logical edge, and providing the logical edge bandwidth and the timing group as a cost estimation of implementing the operation unit graph on the reconfigurable processor.

Abstract: A system with a cost estimation tool for estimating a realized bandwidth consumption of a logical edge between a logical producer unit and a logical consumer unit of an operation unit graph during placement and routing of the logical producer unit, the logical consumer unit, and the logical edge onto a reconfigurable processor is presented as well as a method of operating such a cost estimation tool and a non-transitory computer-readable storage medium including instructions that, when executed by a processing unit, cause the processing unit to operate such a cost estimation tool The cost estimation tool may be configured to determine the realized bandwidth consumption of the tentative assignment based on an upper bandwidth limit of the logical edge, an end-to-end bandwidth, a scaling factor of a realized bandwidth, and a congestion estimation of the physical link.

Abstract: A cost estimation tool in a system for implementing an operation unit graph on a reconfigurable processor is presented as well as a method of operating a cost estimation tool for determining scaled logical edge bandwidths in an operation unit graph in preparation of placing and routing the operation unit graph onto a reconfigurable processor. The cost estimation tool may be configured to receive the operation unit graph, divide the operation unit graph in first and second subgraphs, determine maximum latencies of the first and second subgraphs, and determine a scaled logical edge bandwidth of a logical edge that couples a first logical unit of M logical units in the first subgraph with a second logical unit of N logical units in the first subgraph based on M, N, and scaled bandwidth limits of the M and N logical units.

Abstract: A biometric input system for an electronic device is provided. The biometric input system may be a fingerprint sensing system. The biometric input system includes a biometric sensing component, which may be a capacitive sensing component. The biometric input system also includes a composite cover element, which may be a dielectric cap or coating, and the biometric sensing component is capable of receiving a biometric input from a user through the composite cover element. Electronic devices including the biometric input system are also provided.

Abstract: A method comprises a compiler generating a MI (mixed integer) model to determine mapping decisions to map a dataflow application to hardware of a computing system to execute the application. The MI model comprises MI equations to solve by an MI solver. The MI equations include equations of an objective function corresponding to an optimization objective. The MI equations can comprise decision variables and equations and constraint variables and equations. The compiler outputs the MI model to the MI solver and invokes the MI solver to compute an MI solution comprising solutions to equations among the equations included in the MI model. The compiler receives the MI solution and generates a globally optimized mapping decision based on the MI solution. The MI solver can comprise a commercial program to solve MI linear equations. A computer program product and a computing system can implement the method.

Abstract: A method for providing data blocking to facilitate distributed entity resolution is disclosed. The method includes receiving data sets from a source, the data sets including records that correspond to an entity; grouping each of the records into a block based on a shared characteristic, the block including a blocking key; converting the block into a data file, the data file corresponding to a predetermined file format; partitioning the data file based on the corresponding blocking key; determining, via a worker node, a potential record pair by using the partitioned data file; and persisting the potential record pair.

Abstract: A force input sensor includes a load cell to adapt a compressive force applied to the force input sensor into a strain experienced by a strain sensor in the load cell. In particular, the load cell includes two compression plates separated from one another by a gap so as to define a volume between them. A flexible substrate (a “diaphragm”)—includes a strain sensor and is disposed and supported within the volume. One of the two compression plates includes a feature (a “loading feature”) that extends toward a central region of the flexible substrate. As a result of this construction, when the compression plates receive a compressive force, the loading feature induces a bending moment in the flexible substrate, thereby straining the strain sensor.

Abstract: A portable electronic device can include a housing defining an aperture and a display positioned in the aperture. The display and the housing can define an internal volume and a speaker assembly can be positioned in the internal volume. The speaker assembly can include a speaker enclosure sealed to the housing within the internal volume, the speaker enclosure and the housing defining a speaker volume, and a speaker module in fluid communication with the speaker volume, the speaker module including a diaphragm positioned at an aperture defined by the speaker volume, the diaphragm defining multiple ridges.

Abstract: A portable electronic device can include a housing defining an aperture and a display positioned in the aperture. The display and the housing can define an internal volume and a speaker assembly can be positioned in the internal volume. The speaker assembly can include a speaker enclosure sealed to the housing within the internal volume, the speaker enclosure and the housing defining a speaker volume, and a speaker module in fluid communication with the speaker volume, the speaker module including a diaphragm positioned at an aperture defined by the speaker volume, the diaphragm defining multiple ridges.

Abstract: A force input sensor includes a load cell to adapt a compressive force applied to the force input sensor into a strain experienced by a strain sensor in the load cell. In particular, the load cell includes two compression plates separated from one another by a gap so as to define a volume between them. A flexible substrate (a “diaphragm”)—includes a strain sensor and is disposed and supported within the volume. One of the two compression plates includes a feature (a “loading feature”) that extends toward a central region of the flexible substrate. As a result of this construction, when the compression plates receive a compressive force, the loading feature induces a bending moment in the flexible substrate, thereby straining the strain sensor.

Abstract: A force input sensor includes a load cell to adapt a compressive force applied to the force input sensor into a strain experienced by a strain sensor in the load cell. In particular, the load cell includes two compression plates separated from one another by a gap so as to define a volume between them. A flexible substrate (a “diaphragm”)—includes a strain sensor and is disposed and supported within the volume. One of the two compression plates includes a feature (a “loading feature”) that extends toward a central region of the flexible substrate. As a result of this construction, when the compression plates receive a compressive force, the loading feature induces a bending moment in the flexible substrate, thereby straining the strain sensor.

Abstract: A force input sensor includes a load cell to adapt a compressive force applied to the force input sensor into a strain experienced by a strain sensor in the load cell. In particular, the load cell includes two compression plates separated from one another by a gap so as to define a volume between them. A flexible substrate (a “diaphragm”)—includes a strain sensor and is disposed and supported within the volume. One of the two compression plates includes a feature (a “loading feature”) that extends toward a central region of the flexible substrate. As a result of this construction, when the compression plates receive a compressive force, the loading feature induces a bending moment in the flexible substrate, thereby straining the strain sensor.