Precise longitudinal monitoring of memory operations

A system comprising:

• a memory from which to retrieve data to complete load operations;
• a core comprising:
• a memory subsystem coupled to the memory, wherein the memory subsystem comprises a plurality of memory subunits, each containing a status register;
• and
• an execution engine unit coupled to the memory subsystem and to the core, the execution engine unit to:
• randomly select a load operation to monitor from the load operations, the load operation associated with a thread currently executed by the core;
• determine a re-order buffer identifier of the load operation;
• and
• transmit the re-order buffer identifier to the memory subsystem;
• wherein, responsive to receipt of the re-order buffer identifier, each of the plurality of memory subunits is to store a piece of information, related to a status of the load operation, in the status register corresponding to respective memory subunit;
• and wherein the core is to:
• detect retirement of the load operation;
• and
• in response to detection of the retirement of the load operation, store the piece of information from each status register into a corresponding field of a record of a memory buffer, wherein the record is accessible by core-executed software as performance monitoring data.

A method comprising:

• randomly selecting, by an execution engine unit coupled to a memory subsystem, a load operation to monitor;
• determining, by the execution engine unit, a re-order buffer identifier of the load operation;
• transmitting, by the execution engine unit, the re-order buffer identifier to the memory subsystem;
• storing in a status register, by a first memory subunit of the memory subsystem responsive to receipt of the re-order buffer identifier, a piece of information related to a status of the load operation;
• detecting, by a processor that includes the execution engine unit, retirement of the load operation;
• and
• storing, by the processor in response to detecting the retirement of the load operation, the piece of information from the status register into a particular field of a record of a memory buffer, wherein the particular field is associated with the first memory subunit.