Abstract: Embodiments detailed herein relate to matrix operations. In particular, matrix (tile) multiply accumulate and negated matrix (tile) multiply accumulate are discussed. For example, in some embodiments decode circuitry to decode an instruction having fields for an opcode, an identifier for a first source matrix operand, an identifier of a second source matrix operand, and an identifier for a source/destination matrix operand; and execution circuitry to execute the decoded instruction to multiply the identified first source matrix operand by the identified second source matrix operand, add a result of the multiplication to the identified source/destination matrix operand, and store a result of the addition in the identified source/destination matrix operand and zero unconfigured columns of identified source/destination matrix operand are detailed.

Abstract: A method for handling load faults in an out-of-order processor is described. The method includes detecting, by a memory ordering buffer of the out-of-order processor, a load fault corresponding to a load instruction that was executed out-of-order by the out-of-order processor; determining, by the memory ordering buffer, whether instant reclamation is available for resolving the load fault of the load instruction; and performing, in response to determining that instant reclamation is available for resolving the load fault of the load instruction, instant reclamation to re-fetch the load instruction for execution prior to attempting to retire the load instruction.

Abstract: Embodiments detailed herein relate to matrix operations. In particular, matrix (tile) multiply accumulate and negated matrix (tile) multiply accumulate are discussed. For example, in some embodiments decode circuitry to decode an instruction having fields for an opcode, an identifier for a first source matrix operand, an identifier of a second source matrix operand, and an identifier for a source/destination matrix operand; and execution circuitry to execute the decoded instruction to multiply the identified first source matrix operand by the identified second source matrix operand, add a result of the multiplication to the identified source/destination matrix operand, and store a result of the addition in the identified source/destination matrix operand and zero unconfigured columns of identified source/destination matrix operand are detailed.

Abstract: System and method for prefetching pointer-referenced data. A method embodiment includes: tracking a plurality of load instructions which includes a first load instruction to access a first data that identifies a first memory location; detecting a second load instruction which accesses a second memory location for a second data, the second memory location matching the first memory location identified by the first data; responsive to the detecting, updating a list of pointer load instructions to include information identifying the first load instruction as a pointer load instruction; prefetching a third data for a third load instruction prior to executing the third load instruction; identifying the third load instruction as a pointer load instruction based on information from the list of pointer load instructions and responsively prefetching a fourth data from a fourth memory location, wherein the fourth memory location is identified by the third data.

Abstract: An apparatus and method for pairing store operations. For example, one embodiment of a processor comprises: a grouping eligibility checker to evaluate a plurality of store instructions based on a set of grouping rules to determine whether two or more of the plurality of store instructions are eligible for grouping; and a dispatcher to simultaneously dispatch a first group of store instructions of the plurality of store instructions determined to be eligible for grouping by the grouping eligibility checker.

Abstract: Systems, methods, and apparatuses relating to hardware for split data translation lookaside buffers. In one embodiment, a processor includes a decode circuit to decode instructions into decoded instructions, an execution circuit to execute the decoded instructions, and a memory circuit comprising a load data translation lookaside buffer circuit and a store data translation lookaside buffer circuit separate and distinct from the load data translation lookaside buffer circuit, wherein the memory circuit sends a memory access request of the instructions to the load data translation lookaside buffer circuit when the memory access request is a load data request and to the store data translation lookaside buffer circuit when the memory access request is a store data request to determine a physical address for a virtual address of the memory access request.

Abstract: Disclosed embodiments relate to predicting load data. In one example, a processor a pipeline having stages ordered as fetch, decode, allocate, write back, and commit, a training table to store an address, predicted data, a state, and a count of instances of unchanged return data, and tracking circuitry to determine, during one or more of the allocate and decode stages, whether a training table entry has a first state and matches a fetched first load instruction, and, if so, using the data predicted by the entry during the execute stage, the tracking circuitry further to update the training table during or after the write back stage to set the state of the first load instruction in the training table to the first state when the count reaches a first threshold.

Abstract: A processing device includes a branch IP table and branch predication circuitry coupled to the branch IP table. The branch predication circuitry to: determine a dynamic convergence point in a conditional branch of set of instructions; store the dynamic convergence point in the branch IP table; fetch a first and second speculative path of the conditional branch; while determining which of the first speculative path and the second speculative path is a taken path of the conditional branch and determining whether a dynamic convergence point is fetched corresponding to the stored dynamic convergence point, stall scheduling of instructions of the first speculative path and the second speculative path; and in response to determining that one of the first speculative path and the second speculative path is the taken path and the fetched dynamic convergence point corresponds to the stored convergence point, resume scheduling of the instructions of the taken path.

Abstract: Embodiments detailed herein relate to matrix operations. In particular, the loading of a matrix (tile) from memory. For example, support for a loading instruction is described in the form of decode circuitry to decode an instruction having fields for an opcode, a destination matrix operand identifier, and source memory information, and execution circuitry to execute the decoded instruction to load groups of strided data elements from memory into configured rows of the identified destination matrix operand to memory.

Abstract: Embodiments detailed herein relate to matrix operations. In particular, embodiment of broadcasting elements are described. For example, some embodiments describe broadcasting a scalar to all configured data element positons of a destination matrix (tile). For example, some embodiments describe broadcasting a row to all configured data element positons of a destination matrix (tile). For example, some embodiments describe broadcasting a column to all configured data element positons of a destination matrix (tile).

Abstract: Embodiments detailed herein relate to matrix operations. In particular, performing a matrix operation of zeroing a matrix in response to a single instruction. For example, a processor detailed which includes decode circuitry to decode an instruction having fields for an opcode and a source/destination matrix operand identifier; and execution circuitry to execute the decoded instruction to zero each data element of the identified source/destination matrix.

Abstract: Embodiments detailed herein relate to matrix operations. In particular, the loading of a matrix (tile) from memory.

Abstract: Embodiments detailed herein relate to matrix operations. In particular, matrix (tile) multiply accumulate and negated matrix (tile) multiply accumulate are discussed. For example, in some embodiments decode circuitry to decode an instruction having fields for an opcode, an identifier for a first source matrix operand, an identifier of a second source matrix operand, and an identifier for a source/destination matrix operand; and execution circuitry to execute the decoded instruction to multiply the identified first source matrix operand by the identified second source matrix operand, add a result of the multiplication to the identified source/destination matrix operand, and store a result of the addition in the identified source/destination matrix operand and zero unconfigured columns of identified source/destination matrix operand are detailed.

Abstract: A processor including an execution unit, an instruction scheduler circuit to identify a first instruction of an instruction stream, identify a second instruction on which execution of the first instruction depends, and assign a first dispatch priority value to the first instruction and the second instruction, and a dispatch circuit to dispatch, based on the first dispatch priority value, the first instruction and the second instruction to an instruction execution circuit.

Abstract: System and method for prefetching pointer-referenced data. A method embodiment includes: tracking a plurality of load instructions which includes a first load instruction to access a first data that identifies a first memory location; detecting a second load instruction which accesses a second memory location for a second data, the second memory location matching the first memory location identified by the first data; responsive to the detecting, updating a list of pointer load instructions to include information identifying the first load instruction as a pointer load instruction; prefetching a third data for a third load instruction prior to executing the third load instruction; identifying the third load instruction as a pointer load instruction based on information from the list of pointer load instructions and responsively prefetching a fourth data from a fourth memory location, wherein the fourth memory location is identified by the third data.

Abstract: In one embodiment, a processor of a cryptographic computing system includes data cache units storing encrypted data and circuitry coupled to the data cache units. The circuitry accesses a sequence of cryptographic-based instructions to execute based on the encrypted data, decrypts the encrypted data based on a first pointer value, executes the cryptographic-based instruction using the decrypted data, encrypts a result of the execution of the cryptographic-based instruction based on a second pointer value, and stores the encrypted result in the data cache units. In some embodiments, the circuitry generates, for each cryptographic-based instruction, at least one encryption-based microoperation and at least one non-encryption-based microoperation. The circuitry also schedules the at least one encryption-based microoperation and the at least one non-encryption-based microoperation for execution based on timings of the encryption-based microoperation.

Abstract: In an embodiment, a processor includes a plurality of cores, with at least one core including prefetch logic. The prefetch logic comprises circuitry to: receive a prefetch request; compare the received prefetch request to a plurality of entries of a prefetch filter cache; and in response to a determination that the received prefetch request matches one of the plurality of entries of the prefetch filter cache, drop the received prefetch request. Other embodiments are described and claimed.

Abstract: Embodiments detailed herein relate to matrix (tile) operations. For example, decode circuitry to decode an instruction having fields for an opcode and a memory address; and execution circuitry to execute the decoded instruction to set a tile configuration for the processor to utilize tiles in matrix operations based on a description retrieved from the memory address, wherein a tile a set of 2-dimensional registers are discussed.

Abstract: Disclosed embodiments relate to predicting load data. In one example, a processor a pipeline having stages ordered as fetch, decode, allocate, write back, and commit, a training table to store an address, predicted data, a state, and a count of instances of unchanged return data, and tracking circuitry to determine, during one or more of the allocate and decode stages, whether a training table entry has a first state and matches a fetched first load instruction, and, if so, using the data predicted by the entry during the execute stage, the tracking circuitry further to update the training table during or after the write back stage to set the state of the first load instruction in the training table to the first state when the count reaches a first threshold.

Abstract: A processing device includes a branch IP table and branch predication circuitry coupled to the branch IP table. The branch predication circuitry to: determine a dynamic convergence point in a conditional branch of set of instructions; store the dynamic convergence point in the branch IP table; fetch a first and second speculative path of the conditional branch; while determining which of the first speculative path and the second speculative path is a taken path of the conditional branch and determining whether a dynamic convergence point is fetched corresponding to the stored dynamic convergence point, stall scheduling of instructions of the first speculative path and the second speculative path; and in response to determining that one of the first speculative path and the second speculative path is the taken path and the fetched dynamic convergence point corresponds to the stored convergence point, resume scheduling of the instructions of the taken path.