A system, method and apparatus to facilitate data exchange via pointers. For example, in a computing system having a first processor and a second processor that is separate and independent from the first processor, the first processor can run a program configured to use a pointer identifying a virtual memory address having an ID of an object and an offset within the object. The first processor can use the virtual memory address to store data at a memory location in the computing system and/or identify a routine at the memory location for execution by the second processor. After the pointer is communicated from the first processor to the second processor, the second processor can access the same memory location identified by the virtual memory address. The second processor may operate on the data stored at the memory location or load the routine from the memory location for execution.

A processing apparatus includes a processing resource including a general-purpose parallel processing engine and a matrix accelerator. The matrix accelerator includes first circuitry to receive a command to perform operations associated with an instruction, second circuitry to configure the matrix accelerator according to a physical depth of a systolic array within the matrix accelerator and a logical depth associated with the instruction, third circuitry to read operands for the instruction from a register file associated with the systolic array, fourth circuitry to perform operations for the instruction via one or more passes through one or more physical pipeline stages of the systolic array based on a configuration performed by the second circuitry, and fifth circuitry to write output of the operations to the register file associated with the systolic array.

A method of activating scheduling instructions within a parallel processing unit is described. The method comprises decoding, in an instruction decoder, an instruction in a scheduled task in an active state and checking, by an instruction controller, if a swap flag is set in the decoded instruction. If the swap flag in the decoded instruction is set, a scheduler is triggered to de-activate the scheduled task by changing the scheduled task from the active state to a non-active state.

An apparatus comprises first instruction execution circuitry, second instruction execution circuitry, and a decoupled access buffer. Instructions of an ordered sequence of instructions are issued to one of the first and second instruction execution circuitry for execution in dependence on whether the instruction has a first type label or a second type label. An instruction with the first type label is an access-related instruction which determines at least one characteristic of a load operation to retrieve a data value from a memory address. Instruction execution by the first instruction execution circuitry of instructions having the first type label is prioritised over instruction execution by the second instruction execution circuitry of instructions having the second type label. Data values retrieved from memory as a result of execution of the first type instructions are stored in the decoupled access buffer.

Disclosed embodiments relate to instructions for fast element unpacking. In one example, a processor includes fetch circuitry to fetch an instruction whose format includes fields to specify an opcode and locations of an Array-of-Structures (AOS) source matrix and one or more Structure of Arrays (SOA) destination matrices, wherein: the specified opcode calls for unpacking elements of the specified AOS source matrix into the specified Structure of Arrays (SOA) destination matrices, the AOS source matrix is to contain N structures each containing K elements of different types, with same-typed elements in consecutive structures separated by a stride, the SOA destination matrices together contain K segregated groups, each containing N same-typed elements, decode circuitry to decode the fetched instruction, and execution circuitry, responsive to the decoded instruction, to unpack each element of the specified AOS matrix into one of the K element types of the one or more SOA matrices.

A method of synchronizing a group of scheduled tasks within a parallel processing unit into a known state is described. The method uses a synchronization instruction in a scheduled task which triggers, in response to decoding of the instruction, an instruction decoder to place the scheduled task into a non-active state and forward the decoded synchronization instruction to an atomic ALU for execution. When the atomic ALU executes the decoded synchronization instruction, the atomic ALU performs an operation and check on data assigned to the group ID of the scheduled task and if the check is passed, all scheduled tasks having the particular group ID are removed from the non-active state.

An embodiment of the invention is a processor including execution circuitry to, in response to a decoded instruction, convert a half-precision floating-point value to a single-precision floating-point value and store the single-precision floating-point value in each of the plurality of element locations of a destination register. The processor also includes a decoder and the destination register. The decoder is to decode an instruction to generate the decoded instruction.

A method of activating scheduling instructions within a parallel processing unit is described. The method comprises decoding, in an instruction decoder, an instruction in a scheduled task in an active state and checking, by an instruction controller, if a swap flag is set in the decoded instruction. If the swap flag in the decoded instruction is set, a scheduler is triggered to de-activate the scheduled task by changing the scheduled task from the active state to a non-active state.

An apparatus and method for performing dual concurrent multiplications of packed data elements. For example one embodiment of a processor comprises: a decoder to decode a first instruction to generate a decoded instruction; a first source register to store a first plurality of packed doubleword data elements; a second source register to store a second plurality of packed doubleword data elements; and execution circuitry to execute the decoded instruction, the execution circuitry comprising: multiplier circuitry to multiply a first doubleword data element from the first source register with a second doubleword data element from the second source register to generate a first quadword product and to concurrently multiply a third doubleword data element from the first source register with a fourth doubleword data element from the second source register to generate a second quadword product; and a destination register to store the first quadword product and the second quadword product as first and second packed quadword data elements.

Systems, methods, and apparatuses relating sparsity based FMA. In some examples, an instance of a single FMA instruction has one or more fields for an opcode, one or more fields to identify a source/destination matrix operand, one or more fields to identify a first plurality of source matrix operands, one or more fields to identify a second plurality of matrix operands, wherein the opcode is to indicate that execution circuitry is to select a proper subset of data elements from the first plurality of source matrix operands based on sparsity controls from a first matrix operand of the second plurality of matrix operands and perform a FMA.