Abstract:
A neural network device includes a floating-point arithmetic circuit configured to perform a dot product operation and an accumulation operation; and a buffer configured to store first cumulative data generated by the floating-point arithmetic circuit, wherein the floating-point arithmetic circuit is further configured to perform the dot product operation and the accumulation operation by: identifying a maximum value from a plurality of exponent addition results, obtained by respectively adding exponents of a plurality of floating-point data pairs, and an exponent value of the first cumulative data; performing, based on the maximum value, an align shift of a plurality of fraction multiplication results, obtained by respectively multiplying fractions of the plurality of floating-point data pairs, and a fraction part of the first cumulative data; and performing a summation of the plurality of aligned fraction multiplication results and the aligned fraction part of the first cumulative data.
Abstract:
A method for unlocking a display panel and a display assembly are provided. The method includes: acquiring a plurality of preset pictures, wherein different preset pictures among the plurality of preset pictures correspond to different preset inputs; performing at least one unlocking process, wherein each of the at least one unlocking process includes: causing the display panel to display at least one preset picture of the plurality of preset pictures and receive a verification input from a user, when the display panel is in a locked state; determining whether the verification input is identical with the preset input corresponding to a displayed preset picture; and switching the display panel to an unlocked state, if the verification input is identical with the preset input corresponding to the displayed preset picture.
Abstract:
A method includes determining a set of k extreme values of a dataset of elements in a constant time irrespective of the size of the dataset. A method creates a set of k indicators, each indicator associated with one multi-bit binary number in a large dataset of multi-bit binary numbers. The method includes arranging the multi-bit binary numbers such that each bit n of each said multi-bit binary number is located in a different row n of an associative memory array, starting from a row storing a most significant bit (MSB), adding an indicator to the set for each multi-bit binary number having a bit with an extreme value in the row and continuing the adding until said set contains k indicators.
Abstract:
A method, system, and processor-readable storage medium are directed towards calculating approximate order statistics on a collection of real numbers. In one embodiment, the collection of real numbers is processed to create a digest comprising hierarchy of buckets. Each bucket is assigned a real number N having P digits of precision and ordinality O. The hierarchy is defined by grouping buckets into levels, where each level contains all buckets of a given ordinality. Each individual bucket in the hierarchy defines a range of numbers—all numbers that, after being truncated to that bucket's P digits of precision, are equal to that bucket's N. Each bucket additionally maintains a count of how many numbers have fallen within that bucket's range. Approximate order statistics may then be calculated by traversing the hierarchy and performing an operation on some or all of the ranges and counts associated with each bucket.
Abstract:
A list of digital elements to be sorted are converted to a group of analog signals. The group of analog signals are simultaneously compared to each other to determine the largest analog signal in the group. The largest analog signal is then compared to each of the analog signals in the group to determine which one or more of the analog signals in the group matches the largest analog signal. The matching one or more of the analog signals is removed from the group and the process is repeated until the group of analog signals have been sorted.
Abstract:
Instructions and logic provide vector horizontal majority voting functionality. Some embodiments, responsive to an instruction specifying: a destination operand, a size of the vector elements, a source operand, and a mask corresponding to a portion of the vector element data fields in the source operand; read a number of values from data fields of the specified size in the source operand, corresponding to the mask specified by the instruction and store a result value to that number of corresponding data fields in the destination operand, the result value computed from the majority of values read from the number of data fields of the source operand.
Abstract:
Techniques are disclosed for sorting an input data set. A sort tool determines a distribution of values of a data set that includes a plurality of data records. The sort tool partitions the data set into a plurality of subsets based on the distribution. Each of the data records is inserted into one of the subsets based on a corresponding sort value of the data record. The sort tool identifies one or more of the subsets that contain at least two distinct sort values. In each of the identified subsets, the data records are sorted by a corresponding sort value of the data record.
Abstract:
Techniques are disclosed for sorting an input data set. A sort tool determines a distribution of values of a data set that includes a plurality of data records. The sort tool partitions the data set into a plurality of subsets based on the distribution. Each of the data records is inserted into one of the subsets based on a corresponding sort value of the data record. The sort tool identifies one or more of the subsets that contain at least two distinct sort values. In each of the identified subsets, the data records are sorted by a corresponding sort value of the data record.
Abstract:
Systems and methods may determine a boundary value data unit in a large data set in parallel with determining an associated index of the determined boundary value data unit into the large data set using a single instruction multiple data (SIMD) instruction set architecture and a specialized data layout of array entries. In one example, the specialized data layout of array entries combines a data value and its associated index to an array into a single array entry.
Abstract:
Embodiments include methods, systems and computer program products for performing a composite sort on a tunable hardware sort engine includes determining desired sort performance parameters, configuring a composite sort engine based on the desired sort performance parameters, and receiving a plurality of keys having a payload associated with each of the plurality of keys. The method also includes reserving DRAM storage for each of the payloads, generating a tag for each of the plurality of keys, the tag identifying the DRAM storage reserved for each of the payloads, and storing the payloads in the portions of the DRAM storage. The method further includes generating a composite key for each of the plurality of keys, sorting the composite keys by the composite sort engine, and retrieving the payloads associated with the sorted composite keys from the DRAM storage. The method also includes outputting the payloads associated the sorted composite keys.