Abstract: One embodiment provides a graphics processor comprising a graphics processor comprising a base die including a plurality of chiplet sockets and a plurality of chiplets coupled with the plurality of chiplet sockets. At least one of the plurality of chiplets include a matrix accelerator having circuitry to perform a floating-point operation including a plurality of floating-point multiplications. The circuitry includes input circuitry to store floating-point input values, a first adder to generate an intermediate exponent sum, a multiplier to generate an intermediate mantissa product, and an intermediate accumulator configured to accumulate a plurality of intermediate mantissa products as integer values within a plurality of rows of bitwise storage, the plurality of rows respectively associated with different exponent sums.

Abstract: Techniques for performing horizontal reductions are described. In some examples, an instance of a horizontal instruction is to include at least one field for an opcode, one or more fields to reference a first source operand, and one or more fields to reference a destination operand, wherein the opcode is to indicate that execution circuitry is, in response to a decoded instance of the single instruction, to at least perform a horizontal reduction using at least one data element of a non-masked data element position of at least the first source operand and store a result of the horizontal reduction in the destination operand.

Abstract: In one embodiment, a method of computing comprises executing a software application, wherein the software application comprises at least first and second versions of a subroutine for performing a specific function, wherein the first version exhibits a first behavior and the second version exhibits a second behavior; and selecting for execution one of the first version or the second version based on whether one or more licensing criteria are satisfied. Optionally, the behavior of second version can be redefined on a user basis. The method can be implemented and distributed within software libraries.