Abstract: Apparatus and method for leveraging simultaneous multithreading for bulk compute operations. For example, one embodiment of a processor comprises: a plurality of cores including a first core to simultaneously process instructions of a plurality of threads; a cache hierarchy coupled to the first core and the memory, the cache hierarchy comprising a Level 1 (L1) cache, a Level 2 (L2) cache, and a Level 3 (L3) cache; and a plurality of compute units coupled to the first core including a first compute unit associated with the L1 cache, a second compute unit associated with the L2 cache, and a third compute unit associated with the L3 cache, wherein the first core is to offload instructions for execution by the compute units, the first core to offload instructions from a first thread to the first compute unit, instructions from a second thread to the second compute unit, and instructions from a third thread to the third compute unit.

Abstract: A disclosed apparatus to multiply matrices includes a compute engine. The compute engine includes multipliers in a two dimensional array that has a plurality of array locations defined by columns and rows. The apparatus also includes a plurality of adders in columns. A broadcast interconnect between a cache and the multipliers broadcasts a first set of operand data elements to multipliers in the rows of the array. A unicast interconnect unicasts a second set of operands between a data buffer and the multipliers. The multipliers multiply the operands to generate a plurality of outputs, and the adders add the outputs generated by the multipliers.

Abstract: Techniques for processing loops are described. An exemplary apparatus at least includes decoder circuitry to decode a single instruction, the single instruction to include a field for an opcode, the opcode to indicate execution circuitry is to perform an operation to configure execution of one or more loops, wherein the one or more loops are to include a plurality of configuration instructions and instructions that are to use metadata generated by ones of the plurality of configuration instructions; and execution circuitry to perform the operation as indicated by the opcode.

Abstract: A disclosed apparatus to multiply matrices includes a compute engine. The compute engine includes multipliers in a two dimensional array that has a plurality of array locations defined by columns and rows. The apparatus also includes a plurality of adders in columns. A broadcast interconnect between a cache and the multipliers broadcasts a first set of operand data elements to multipliers in the rows of the array. A unicast interconnect unicasts a second set of operands between a data buffer and the multipliers. The multipliers multiply the operands to generate a plurality of outputs, and the adders add the outputs generated by the multipliers.

Abstract: A technique to share execution resources. In one embodiment, a CPU and a GPU share resources according to workload, power considerations, or available resources by scheduling or transferring instructions and information between the CPU and GPU.

Abstract: An interconnect bandwidth throttler is disclosed. The interconnect bandwidth throttler turns off the interconnect, based on whether a maximum number of transactions has taken place within a predetermined throttle window. Both the maximum number of transactions and the throttle window are adjustable. Characteristics such as performance, thermal considerations, and average power are adjustable using the interconnect bandwidth throttler.

Abstract: A technique to share execution resources. In one embodiment, a CPU and a GPU share resources according to workload, power considerations, or available resources by scheduling or transferring instructions and information between the CPU and GPU.

Abstract: A technique to share execution resources. In one embodiment, a CPU and a GPU share resources according to workload, power considerations, or available resources by scheduling or transferring instructions and information between the CPU and GPU.

Abstract: A method to reduce idle leakage power in I/O pins of an integrated circuit using external circuitry. Initially, I/O pins on a package are subdivided into those that will also remain powered up and those that will power down during idle state. When a system enters a low power mode, a signal is sent to the external circuitry. The signal notifies the I/O pins that always remain powered up to notify the external circuitry to power down the other set of I/O pins.

Abstract: An interconnect bandwidth throttler is disclosed. The interconnect bandwidth throttler turns off the interconnect, based on whether a maximum number of transactions has taken place within a predetermined throttle window. Both the maximum number of transactions and the throttle window are adjustable. Characteristics such as performance, thermal considerations, and average power are adjustable using the interconnect bandwidth throttler.

Abstract: An interconnect bandwidth throttler is disclosed. The interconnect bandwidth throttler turns off the interconnect, based on whether a maximum number of transactions has taken place within a predetermined throttle window. Both the maximum number of transactions and the throttle window are adjustable. Characteristics such as performance, thermal considerations, and average power are adjustable using the interconnect bandwidth throttler.

Abstract: An interconnect bandwidth throttler is disclosed. The interconnect bandwidth throttler turns off the interconnect, based on whether a maximum number of transactions has take place within a predetermined throttle window. Both the maximum number of transactions and the throttle window are adjustable.

Abstract: A technique to share execution resources. In one embodiment, a CPU and a GPU share resources according to workload, power considerations, or available resources by scheduling or transferring instructions and information between the CPU and GPU.

Abstract: An interconnect bandwidth throttler is disclosed. The interconnect bandwidth throttler turns off the interconnect, based on whether a maximum number of transactions has take place within a predetermined throttle window. Both the maximum number of transactions and the throttle window are adjustable.

Abstract: One embodiment of a method is disclosed. The method generates requests waiting for data to be loaded into a data cache including a first level cache (FLC). The method further receives the requests from instruction sources, schedules the requests, and then passes the requests on to an execution unit having the data cache. Further, the method checks contents of the data cache, replays to the requests if the data is not located in the data cache, and stores the requests that are replay safe. The method further detects the readiness of the data of bus clocks prior to the data being ready to be transmitted to a processor, and transmits an early data ready indication to the processor to drain the requests from a resource scheduler.

Abstract: One embodiment of a method is disclosed. The method generates requests waiting for data to be loaded into a data cache including a first level cache (FLC). The method further receives the requests from instruction sources, schedules the requests, and then passes the requests on to an execution unit having the data cache. Further, the method checks contents of the data cache, replays to the requests if the data is not located in the data cache, and stores the requests that are replay safe. The method further detects the readiness of the data of bus clocks prior to the data being ready to be transmitted to a processor, and transmits an early data ready indication to the processor to drain the requests from a resource scheduler.

Abstract: Methods and apparatus to generate addresses in processors are disclosed. An example address generator disclosed herein includes an adder to add a first address component and a second address component to generate an address, a correction indicator to indicate if the address is correct, and a control input to modify an operation of the adder.

Abstract: One embodiment of a method is disclosed. The method generates requests waiting for data to be loaded into a data cache including a first level cache (FLC). The method further receives the requests from instruction sources, schedules the requests, and then passes the requests on to an execution unit having the data cache. Further, the method checks contents of the data cache, replays to the requests if the data is not located in the data cache, and stores the requests that are replay safe. The method further detects the readiness of the data of bus clocks prior to the data being ready to be transmitted to a processor, and transmits an early data ready indication to the processor to drain the requests from a resource scheduler.

Abstract: A method, apparatus, and system are provided for early data return indication mechanism. According to one embodiment, data cache is accessed for data in response to a request for the data, the request received from an instruction source, and the request waits for the data to be retrieved from memory if the data is not located in the data cache, and an early data ready indication is received at a resource scheduler, the early data ready indication being received prior to receiving a data ready indication referring to the data being ready to be retrieved from the memory.

Abstract: A buffer virtualization mechanism to allow for a large number of allocate-able buffering resources. In particular, embodiments of the invention involve a tracking technique for implementing the use of virtual buffers within a microprocessor architecture.