Abstract: Techniques for shared data prefetch are described. An exemplary instruction for shared data prefetch includes at least one field for an opcode, at least one field for a source operand to provide a memory address at least a byte of data, wherein the opcode is to indicate that circuitry is to fetch of a line of data from memory at the provided address that contains the byte specified with the source operand and store that byte in at least a cache local to a requester, wherein the byte of data is to be stored in a shared state.

Abstract: A microelectronic assembly is provided comprising: a first plurality of integrated circuit (IC) dies arranged in an array of rows and columns in a first layer; and a second plurality of IC dies in a second layer not coplanar with the first layer. A first IC die in the first plurality is differently sized than surrounding IC dies in the first plurality, and a second IC die in the second plurality coupled to the first IC die comprises at least one of: a repeater circuitry and a fanout structure in an electrical pathway coupling the first IC die with an adjacent IC die in the first plurality.

Abstract: Embodiments of apparatuses, methods, and systems for flexible provisioning of coherent memory address decoders in hardware are disclosed. In an embodiment, an apparatus includes a plurality of address decoders and a plurality of configuration storage locations. Each of the configuration storage locations corresponds to one of the plurality of address decoders to configure the corresponding one of the plurality of address decoders to decode based on a corresponding one of a plurality of decode rules. Each of the plurality of configuration storage locations is allocated to one of a plurality of memory tiers.

Abstract: Techniques and mechanisms to facilitate access to a cache based on a dual basis partition scheme. In an embodiment, a first one or more registers of a processor provide information which describes multiple set-wise partitions of a cache. A second one or more registers of the processor provides additional information which describes multiple way-wise partitions of the cache. A virtual cache is defined as that region of the cache which is both in a particular set-wise partition, and in a particular way-wise partition. In another embodiment, a cache agent of the processor performs operations, based on the set-wise partitioning and the way-wise partitioning, to determine a mapping of one address—which is provided in a memory access request, and which indicates a location in one virtual cache—to another address which indicates another location in a different virtual cache.

Abstract: A server system for installation in a data center is provided, including: a server sled; a backplane disposed in the server sled, said backplane having a plurality of PCIe slots; a plurality of console compute cards mated to the PCIe slots of the backplane, wherein each of the console compute cards includes compute resources substantially similar to compute resources of a game console; wherein the backplane includes a PCIe switch to enable communication with the console compute cards over a PCIe fabric of a server rack in which the server sled is configured to be disposed.

Abstract: A console compute card for installation in a host system is provided, including: an accelerated processing unit (APU); a Southbridge having a PCIe connection to the APU; an endpoint management bridge (EMB) having a PCIe connection to the Southbridge, the EMB exposing one or more mirrored PCIe endpoints, including one or more local endpoints for enumeration by the APU, and one or more host-facing endpoints for enumeration by the host system; a PCIe edge connector for insertion into a PCIe slot of the host system to form a PCIe connection between the console compute card and the host system; wherein the console compute card includes compute resources substantially similar to compute resources of a retail game console.

Abstract: A method includes: initiating boot-up of a host system, wherein initiating boot-up causes powering of a console compute card connected via a PCIe connection to the host system, wherein the console compute card includes an accelerated processing unit (APU) and an endpoint management bridge (EMB); wherein the EMB exposes a plurality of PCIe endpoints, including one or more local endpoints, and one or more host-facing endpoints; wherein the boot-up of the host system includes enumerating the host-facing endpoints by the host system through a PCIe fabric of the host system; wherein the EMB delays enumeration of the local endpoints until the enumeration of the host-facing endpoints is completed; after completion of the enumeration of the host-facing endpoints by the host system, then enumerating the local endpoints by the APU of the console compute card through a PCIe fabric of the console compute card.

Abstract: A console compute card for installation in a host system is provided, including: an accelerated processing unit (APU); a Southbridge; a PCIe edge connector for insertion into a PCIe slot of the host system to form a PCIe connection between the console compute card and the host system; wherein a PCIe connection between the APU and the Southbridge is defined as part of a PCIe fabric of the console compute card; wherein the Southbridge exposes one or more mirrored PCIe endpoints, including one or more local endpoints for enumeration by the APU through the PCIe fabric of the console compute card, and one or more host-facing endpoints for enumeration by the host system through a PCIe fabric of the host system; wherein the console compute card includes compute resources substantially similar to compute resources of a retail game console.

Abstract: A processor package comprises a caching agent that is operable to respond to a first sequence of direct-to-cache (DTC) write misses to a partition in a set in a cache by writing data from those write misses to the partition. When the partition comprises W ways, the caching agent is operable to write data from those write misses to all W ways in the partition. After writing data from those write misses to the partition, and before any data from the partition in the set has been read, the caching agent is operable to receive a second sequence of DTC write misses to the partition, and in response, complete those write misses while retaining the data from the first sequence in at least W-1 of the ways in the partition. Other embodiments are described and claimed.

Abstract: Examples include techniques associated with data movement to a cache in a disaggregated die system. Examples include circuitry at a first die receiving and granting requests to move data to a first cache resident on the first die or to a second cache resident on a second die that also includes a core of a processor. The granting of the request based, at least in part, on a traffic source type associated with a source of the request.

Abstract: Embodiments of apparatuses, methods, and systems for flexible provisioning of coherent memory address decoders in hardware are disclosed. In an embodiment, an apparatus includes a plurality of address decoders and a plurality of configuration storage locations. Each of the configuration storage locations corresponds to one of the plurality of address decoders to configure the corresponding one of the plurality of address decoders to decode based on a corresponding one of a plurality of decode rules. Each of the plurality of configuration storage locations is allocated to one of a plurality of memory tiers.

Abstract: Techniques and mechanisms to facilitate access to a cache based on a dual basis partition scheme. In an embodiment, a first one or more registers of a processor provide information which describes multiple set-wise partitions of a cache. A second one or more registers of the processor provides additional information which describes multiple way-wise partitions of the cache. A virtual cache is defined as that region of the cache which is both in a particular set-wise partition, and in a particular way-wise partition. In another embodiment, a cache agent of the processor performs operations, based on the set-wise partitioning and the way-wise partitioning, to determine a mapping of one address—which is provided in a memory access request, and which indicates a location in one virtual cache—to another address which indicates another location in a different virtual cache.

Abstract: A microelectronic assembly is provided comprising: a first plurality of integrated circuit (IC) dies arranged in an array of rows and columns in a first layer; and a second plurality of IC dies in a second layer not coplanar with the first layer. A first IC die in the first plurality is differently sized than surrounding IC dies in the first plurality, and a second IC die in the second plurality coupled to the first IC die comprises at least one of: a repeater circuitry and a fanout structure in an electrical pathway coupling the first IC die with an adjacent IC die in the first plurality.

Abstract: A fabric controller to provide a coherent accelerator fabric, including: a host interconnect to communicatively couple to a host device; a memory interconnect to communicatively couple to an accelerator memory; an accelerator interconnect to communicatively couple to an accelerator having a last-level cache (LLC); and an LLC controller configured to provide a bias check for memory access operations.

Abstract: Techniques for shared data prefetch are described. An exemplary instruction for shared data prefetch includes at least one field for an opcode, at least one field for a source operand to provide a memory address at least a byte of data, wherein the opcode is to indicate that circuitry is to fetch of a line of data from memory at the provided address that contains the byte specified with the source operand and store that byte in at least a cache local to a requester, wherein the byte of data is to be stored in a shared state.

Abstract: Examples include techniques associated with mapping system memory physical addresses to proximity domains. Examples include mapping system memory physical addresses for a memory coupled with a multi-die system to proximity domains that include cores of a multi-core processor and the associated level 3 (L3) cache for use by each core included in a respective proximity domain. The mapping is to facilitate cache line ownership of a cache line in an L3 cache by an input/output device or agent located on a separate die from the multi-core processor.

Abstract: Methods and apparatus relating to a scalable address decoding scheme for Compute Express Link™ or CXL™ Type-2 devices with programmable interleave granularity are described. In an embodiment, configurator logic circuitry determines an interleave granularity and an address range size for a plurality of devices coupled to a socket of a processor. A single System Address Decoder (SAD) rule for two or more of the plurality of the devices coupled to the socket of the processor is stored in memory. A memory access transaction directed at a first device from the plurality of devices is routed to the first device in accordance with the SAD rule. Other embodiments are also disclosed and claimed.

Abstract: In one embodiment, a system includes an (input/output) I/O domain and a compute domain. The I/O domain includes an I/O agent and a I/O domain caching agent. The compute domain includes a compute domain caching agent and a compute domain cache hierarchy. The I/O agent issues an ownership request to the compute domain caching agent to obtain ownership of a cache line in the compute domain cache hierarchy. In response to the ownership request, the compute domain caching agent places the cache line in the compute domain cache hierarchy in a placeholder state. The placeholder state reserves the cache line for performance of a write operation by the I/O agent. The compute domain caching agent writes data received from the I/O agent to the cache line in the compute domain cache hierarchy and transitions the state of the cache line out of the placeholder state.

Abstract: A fabric controller to provide a coherent accelerator fabric, including: a host interconnect to communicatively couple to a host device; a memory interconnect to communicatively couple to an accelerator memory; an accelerator interconnect to communicatively couple to an accelerator having a last-level cache (LLC); and an LLC controller configured to provide a bias check for memory access operations.

Abstract: A fabric controller is provided for a coherent accelerator fabric. The coherent accelerator fabric includes a host interconnect, a memory interconnect, and an accelerator interconnect. The host interconnect communicatively couples to a host device. The memory interconnect communicatively couples to an accelerator memory. The accelerator interconnect communicatively couples to an accelerator having a last-level cache (LLC). An LLC controller is provided that is configured to provide a bias check for memory access operations on the fabric.