Abstract: Microelectronic assemblies, related devices and methods, are disclosed herein. In some embodiments, a microelectronic assembly may include a substrate having a glass core with a surface and a dielectric material on a portion of the surface of the core, the dielectric material including conductive pathways; a photonic integrated circuit (PIC) having an active surface, wherein the PIC is coupled to the surface of the core with the active surface facing away from the core; a processor integrated circuit (XPU) electrically coupled to the conductive pathways in the dielectric material and to the active surface of the PIC; a first optical component optically coupled to a lateral surface of the PIC and to the surface of the core; and a second optical component coupled to the core, wherein the second optical component is optically coupled to the PIC by an optical pathway through the first optical component and the core.

Abstract: Microelectronic assemblies, related devices and methods, are disclosed herein. In some embodiments, a microelectronic assembly may include a substrate having a glass core with a surface and a dielectric material on a portion of the surface of the core, the dielectric material including conductive pathways and an interconnect die; a processor integrated circuit (XPU) and a photonic integrated circuit (PIC), having an active surface facing towards the core, electrically coupled to the interconnect die and to the conductive pathways; a first optical component optically coupled to the active surface of the PIC and to the surface of the core; and a second optical component coupled to the core, wherein the second optical component is optically coupled to the PIC by an optical pathway through the first optical component and the core.

Abstract: Microelectronic assemblies, related devices and methods, are disclosed herein. In some embodiments, a photonic assembly may include a substrate having a core with a surface, wherein a material of the core includes glass; and a dielectric material on a portion of the surface of the core, the dielectric material including conductive pathways; a photonic integrated circuit (PIC) electrically coupled to the conductive pathways in the dielectric material; a first optical component between the PIC and the surface of the core, wherein the first optical component is coupled to the surface of the core by optical glue or by fusion bonding; and a second optical component coupled to the core, wherein the second optical component is optically coupled to the PIC by an optical pathway through the core and the first optical component.

Abstract: Signal lines in the pin field of a printed circuit board layout are modified to reduce line impedance and improve signal integrity. The widths of signal lines are extended in the pin field to take full advantage of the available routing space between pads and adjacent signal lines. The signal line extension can be considered a subtractive approach in that the signal lines are extended to occupy the available muting space, with signal line extensions that would otherwise cause design rule violations being subtracted out. The edge of a signal line is extended to a keep-out region associated with a centerline that extends through a plurality of pads arranged in a line and located adjacent to the signal line. The edge of the signal line is also extended to keep-out regions associated with pads in the pin fields.

Abstract: Microelectronic assemblies, related devices and methods, are disclosed herein. In some embodiments, a photonic assembly may include an interposer having a surface, wherein a material of the interposer includes glass and the interposer includes through-glass vias (TGVs); a photonic integrated circuit (PIC) optically coupled to the surface of the interposer by optical glue or fusion bonding and electrically coupled to the TGVs in the interposer by hybrid bond interconnects; and an optical component optically coupled to the interposer, wherein the optical component is optically coupled to the PIC by an optical pathway through the interposer.

Abstract: Various systems and methods for bus-off attack detection are described herein. An electronic device for bus-off attack detection and prevention includes bus-off prevention circuitry coupled to a protected node on a bus, the bus-off prevention circuitry to: detect a transmitted message from the protected node to the bus; detect a bit mismatch of the transmitted message on the bus; suspend further transmissions from the protected node while the bus is analyzed; determine whether the bit mismatch represents a bus fault or an active attack against the protected node; and signal the protected node indicating whether a fault has occurred.

Abstract: A processor may aggregate cache misses in a cache, the cache shared by a plurality of input/output (I/O) sources. The processor may aggregate cache occupancy in the cache by the plurality of VO sources. The processor may and identify, based on the aggregating, a first I/O source of the plurality of I/O sources as impacting the cache.

Abstract: An integrated circuit (IC) package substrate including a glass core having a cavity filter structure, and related devices and methods, are disclosed herein. In some embodiments, an IC package substrate may include a core made of glass, and the core including a first core portion having a first surface and a trench and a ridge in the first surface, the trench and the ridge lined with a conductive material; and a second core portion having a second surface, the second surface lined with the conductive material, wherein the first surface of the first core portion is physically coupled to the second surface of the second core portion forming a cavity filter structure.

Abstract: Disclosed herein are microelectronic assemblies including strengthened glass cores, as well as related devices and methods. In some embodiments, a microelectronic assembly may include a glass core having a surface, a first region having a first concentration of ions extending from the surface of the core to a first depth; a second region having a second concentration of ions greater than the first concentration of ions, the second region between the first region and the surface of the core; a dielectric with a conductive pathway at the surface of the glass core; and a die electrically coupled to the conductive pathway in the dielectric at the surface of the core by an interconnect.

Abstract: A circuit system includes a memory block and first and second processing circuits. The first and second processing circuits store a matrix in the memory block by concurrently writing first and second rows or columns of the matrix to first and second regions of storage in the memory block, respectively. The first and second processing circuits transpose the matrix to generate a transposed matrix by concurrently reading first and second rows or columns of the transposed matrix from third and fourth regions of storage in the memory block, respectively.

Abstract: For example, a Bluetooth (BT) device may be capable of configuring a BT link for communication between the BT device and a keyboard device. For example, the BT device may be configured to identify a keypress attribute of keypresses on the keyboard device. For example, the BT device may be configured to identify the keypress attribute based on transmissions from the keyboard device to the BT device over the BT link between the BT device and the keyboard device. For example, the BT device may configure a bandwidth (BW) allocation for the BT link, for example, based on the keypress attribute.

Abstract: Embodiments may be generally directed to techniques to cause communication of a registration request between a first end-point and a second end-point of an end-to-end path, the registration request to establish resource load monitoring for one or more resources of the end-to-end path, receive one or more acknowledgements indicating resource loads for each of the one or more resources of the end-to-end path, at least one of the acknowledgements to indicate a resource of the one or more resources is not meeting a threshold requirement for the end-to-end path, and perform an action for communication traffic utilizing the one or more resources based on the acknowledgement.

Abstract: Embodiments disclosed herein include semiconductor devices and methods of forming such devices. In an embodiment, a semiconductor device comprises a semiconductor substrate and a source. The source has a first conductivity type and a first insulator separates the source from the semiconductor substrate. The semiconductor device further comprises a drain. The drain has a second conductivity type that is opposite from the first conductivity type, and a second insulator separates the drain from the semiconductor substrate. In an embodiment, the semiconductor further comprises a semiconductor body between the source and the drain, where the semiconductor body is spaced away from the semiconductor substrate.

Abstract: An apparatus and system to enable URLLC PUSCH repetitions in the unlicensed spectrum are described. The number of consecutive PUSCH repetitions indicated in the RRC parameter is reinterpreted as the number of transmission occasions over which the UE is able to attempt CCA. An orphan symbol is used to provide a DMRS transmission or cyclic prefix of the PUSCH transmission causing the orphan symbol. Whether a CG-UCI is piggybacked in a PUSCH transmission, and whether DCI-DFI is used, is dependent on whether cg-RetransmissionTimer is configured.

Abstract: Various systems and methods for providing opportunistic placement of compute in an edge network are described herein. A node in an edge network may be configured to access a service level agreement related to a workload, the workload to be orchestrated for a user equipment by the node; modify a machine learning model based on the service level agreement; implement the machine learning model to identify resource requirements to execute the workload in a manner to satisfy the service level agreement; initiate resource assignments from a resource provider, the resource assignments to satisfy the resource requirements; construct a resource hierarchy from the resource assignments; initiate execution of the workload using resources from the resource hierarchy; and monitor and adapt execution of the workload based on the resource hierarchy in response to the execution of the workload.

Abstract: An active filter and an analog-to-digital converter (ADC) configured to suppress out-of-band peaking. An active filter may include an active device configured to provide a power gain to an input signal, a feedback network configured to connect an output of the active device to an input of the active device, and an input impedance network configured to couple the input signal to the input of the active device. A combination of the feedback network and the input impedance network is configured to provide frequency response properties of the active filter such that a frequency domain signal transfer function of the active filter has a constant in numerator.

Abstract: Techniques for transferring virtual machines and resource management in a virtualized computing environment are described. In one embodiment, for example, an apparatus may include at least one memory, at least one processor, and logic for transferring a virtual machine (VM), at least a portion of the logic comprised in hardware coupled to the at least one memory and the at least one processor, the logic to generate a plurality of virtualized capability registers for a virtual device (VDEV) by virtualizing a plurality of device-specific capability registers of a physical device to be virtualized by the VM, the plurality of virtualized capability registers comprising a plurality of device-specific capabilities of the physical device, determine a version of the physical device to support via a virtual machine monitor (VMM), and expose a subset of the virtualized capability registers associated with the version to the VM. Other embodiments are described and claimed.

Abstract: There is disclosed example techniques to include obtaining a filtering rule via a control plane message that includes information to identify a source of a general packet radio service (GPRS) tunneling protocol (GTP) user-plane (GTP-U) packet. The example techniques also include configuring, based on the information to identify the source, a virtual switch to identify the source of the GTP-U packet to use in the filtering rule to cause a received GTP-U packet to be sent to a local edge server or a mobile core network for processing based on at least a portion of a first extension header included in the GTP-U packet.

Abstract: Stacked transistor structures having a conductive interconnect between upper and lower transistors. In an embodiment, the interconnect is formed by first provisioning a protective layer over an area to be protected (gate dielectric or other sensitive material) of upper transistor, and then etching material adjacent and below the protected area to expose an underlying contact point of lower transistor. A metal is deposited into the void created by the etch to provide the interconnect. The protective layer is resistant to the etch process and is preserved in the structure, and in some cases may be utilized as a work-function metal. In an embodiment, the protective layer is formed by deposition of reactive semiconductor and metal material layers which are subsequently transformed into a work function metal or work function metal-containing compound. A remnant of unreacted reactive semiconductor material may be left in structure and collinear with protective layer.

Abstract: Representative implementations of devices and techniques provide communication between networked nodes operating on a communication network medium. In an implementation, a node generates a broadcast frame that includes at least a preamble and a payload. The preamble of the broadcast frame may include auxiliary information. The auxiliary information may be associated with one or more symbols of the preamble. The auxiliary information may contain power boost information.

Abstract: Embodiments disclosed herein include stacked forksheet transistor devices, and methods of fabricating stacked forksheet transistor devices. In an example, an integrated circuit structure includes a backbone. A first transistor device includes a first vertical stack of semiconductor channels adjacent to an edge of the backbone. A second transistor device includes a second vertical stack of semiconductor channels adjacent to the edge of the backbone. The second transistor device is stacked on the first transistor device.

Abstract: Embodiments of the present disclosure may relate to the existence of a unique value associated with each PCIe function or device that is readable from two or more PCIe functions, or from a CPU running system software. Embodiments enable system software to identify which PCIe functions have private or hidden connections. In addition, embodiments may allow system software to differentiate among multiple identical instances of PCIe add-in components that have associations. Other embodiments may be described and/or claimed.

Abstract: A universal serial bus (USB) router can include a display port input device to receive a display port signal. The display port input device can include display port link layer parser circuitry to identify display port control or data information from the received display port signal, USB packet construction circuitry to construct a USB packet comprising the display port control or data information identified by the display port link layer parser circuitry, and a USB switch to transmit the USB packet comprising the display control or data information over a USB link. A display port output device can include display port packetizer circuitry to construct a display port packet from the display port control or data information from the USB packet, and display port output circuitry to output the display port packet across a display port link.

Abstract: Described herein are memory controllers for integrated circuits that implement network-on-chip (NoC) to provide access to memory to couple processing cores of the integrated circuit to a memory device. The NoC may be dedicated to service the memory controller and may include one or more routers to facilitate management of the access to the memory controller.

Abstract: Multi-tile Memory Management for Detecting Cross Tile Access, Providing Multi-Tile Inference Scaling with multicasting of data via copy operation, and Providing Page Migration are disclosed herein. In one embodiment, a graphics processor for a multi-tile architecture includes a first graphics processing unit (GPU) having a memory and a memory controller, a second graphics processing unit (GPU) having a memory and a cross-GPU fabric to communicatively couple the first and second GPUs. The memory controller is configured to determine whether frequent cross tile memory accesses occur from the first GPU to the memory of the second GPU in the multi-GPU configuration and to send a message to initiate a data transfer mechanism when frequent cross tile memory accesses occur from the first GPU to the memory of the second GPU.

Abstract: Systems, apparatuses and methods may provide for a memory controller to manage quality of service enforcement and migration between local and pooled memory. A memory controller may include logic to communicate with a local memory and with a pooled memory controller to track memory page usage on a per application basis, instruct the pooled memory controller to perform a quality of service enforcement in response to a determination that an application is latency bound or bandwidth bound, wherein the determination that the application is latency bound or bandwidth bound is based on a cycles per instruction determination, and instruct a Direct Memory Access engine to perform a migration from a remote memory to the local memory in response to a determination that the quality of service cannot be enforced.

Abstract: Systems, apparatuses, and methods to response to detected attacks in an autonomous system based on context of the autonomous system are described. In particular, the disclosure provides an intrusion detection system receiving contexts and contracts dictating particular response guide rails from a higher level components or stack on the autonomous system. The intrusion detection system is arranged to respond to attacks according to the contract without intervention by the higher level components or stack.

Abstract: A processor for supporting secure memory intent is disclosed. The processor of the disclosure includes a memory execution unit to access memory and a processor core coupled to the memory execution unit. The processor core is to receive a request to access a convertible page of the memory. In response to the request, the processor core to determine an intent for the convertible page in view of a page table entry (PTE) corresponding to the convertible page. The intent indicates whether the convertible page is to be accessed as at least one of a secure page or a non-secure page.

Abstract: A low-latency digital-signature with side-channel security is described. An example of an apparatus includes a coefficient multiplier circuit to perform polynomial multiplication, the coefficient multiplier circuit providing Number Theoretic Transform (NTT) and INTT (Inverse NTT) processing; and one or more accessory operation circuits coupled with the coefficient multiplier circuit, each of the one or more accessory operation circuits to perform a computation based at least in part on a result of an operation of the NTT/INTT coefficient multiplier circuit, wherein the one or more accessory operation circuits are to receive results of operations of the NTT/INTT coefficient multiplier circuit prior to the results being stored in a memory.

Abstract: Technologies for providing accelerated functions as a service in a disaggregated architecture include a compute device that is to receive a request for an accelerated task. The task is associated with a kernel usable by an accelerator sled communicatively coupled to the compute device to execute the task. The compute device is further to determine, in response to the request and with a database indicative of kernels and associated accelerator sleds, an accelerator sled that includes an accelerator device configured with the kernel associated with the request. Additionally, the compute device is to assign the task to the determined accelerator sled for execution. Other embodiments are also described and claimed.

Abstract: Thread dispatch circuitry is configured to dispatch threads of a two-dimensional (2D) thread group based on data access locality associated with the threads. The thread dispatch circuitry can dispatch a first 2D sub-group of the 2D thread group to a compute block of the multiple compute blocks, the first 2D sub-group associated with a first 2D tile of memory and dispatch a second 2D sub-group of the 2D thread group to the compute block of the multiple compute blocks, the second 2D sub-group associated with a second 2D tile of memory.

Abstract: Resonator control techniques for wireless power transmitting units are described. One or more novel parameters may be defined for use in conjunction with dominant PRU selection on the part of a PTU. In various embodiments, each of a plurality of PRUs may determine values for one or more such parameters, and may report those values to the PTU. In some embodiments, the PTU may identify a parameter to be used as a selection criterion, and may identify the dominant PRU based on the respective values reported for that parameter by the plurality of PRUs. Other embodiments are described and claimed.

Abstract: Integrated circuit (IC) cell architectures including a crenellated interconnect trace layout. A crenellated trace layout may be employed where an IC cell includes transistor having a source/drain terminal interconnected through a back-side (3D) routing scheme that reduces front-side routing density for a given transistor footprint. In the crenellated layout, adjacent interconnect traces or tracks may have their ends staggered according to a crenellation phase for the cell. Crenellated tracks may intersect one cell boundary with adjacent tracks intersecting an opposite cell boundary. Track ends may be offset by at least the width of an underlying orthogonal interconnect trace. Crenellated track ends may be offset by the width of an underlying orthogonal interconnect trace and half a spacing between adjacent orthogonal interconnect traces.

Abstract: Methods and apparatus for platform ambient data management schemes for tiered architectures. A platform including one or more CPUs coupled to multiple tiers of memory comprising various types of DIMMs (e.g., DRAM, hybrid, DCPMM) is powered by a battery subsystem receiving input energy harvested from one or more green energy sources. Energy threshold conditions are detected, and associated memory reconfiguration is performed. The memory reconfiguration may include but is not limited to copying data between DIMMs (or memory ranks on the DIMMS in the same tier, copying data between a first type of memory to a second type of memory on a hybrid DIMM, and flushing dirty lines in a DIMM in a first memory tier being used as a cache for a second memory tier. Following data copy and flushing operations, the DIMMs and/or their memory devices are powered down and/or deactivated.

Abstract: A method comprises generating, for a cacheline, a first tag and a second tag, the first tag and the second tag generated as a function of user data stored and metadata in the cacheline stored in a first memory device, and a multiplication parameter derived from a secret key, storing the user data, the metadata, the first tag and the second tag in the first cacheline of the first memory device; generating, for the cacheline, a third tag and a fourth tag, the third tag and the fourth tag generated as a function of the user data stored and metadata in the cacheline stored in a second memory device, and the multiplication parameter; storing the user data, the metadata, the third tag and the fourth tag in the corresponding cache line of the second memory device; receiving, from a requesting device, a read operation directed to the cacheline; and using the first tag, the second tag, the third tag, and the fourth tag to determine whether a read error occurred during the read operation.

Abstract: Apparatus and method for compression of acceleration structure build data in a ray tracing implementation. For example, one embodiment of an apparatus comprises: traversal hardware logic to traverse rays through a graphics scene comprising a plurality of primitives; and an acceleration data structure processing unit comprising: a bounding box compressor to compress a set of bounding boxes to generate a plurality of bounding box compression blocks, and an index compressor to compress a set of indices to generate a plurality of index compression blocks, and an acceleration data structure builder for constructing acceleration structures based on bounding box compression blocks and index compression blocks.

Abstract: Described is an apparatus which comprises: a first clocking source having a first divider; a second clocking source having a second divider, wherein the first and second clocking sources are inductively coupled; and calibration logic to monitor clock signals associated with the first and second clocking sources and to generate at least one calibration code for adjusting at least one divider ratio of the first or second dividers according to the monitored clock signals.

Abstract: Monolithic FETs including a fin of a first semiconductor composition disposed on a sub-fin of a second composition. In some examples, an InGaAs fin is grown over GaAs sub-fin. The sub-fin may be epitaxially grown from a seeding surface disposed within a trench defined in an isolation dielectric. The sub-fin may be planarized with the isolation dielectric. The fin may then be epitaxially grown from the planarized surface of the sub-fin. A gate stack may be disposed over the fin with the gate stack contacting the planarized surface of the isolation dielectric so as to be self-aligned with the interface between the fin and sub-fin. Other embodiments may be described and/or claimed.

Abstract: Technologies for establishing device locality are disclosed. A processor in a computing device generates an identifier distinct to the computing device. The processor transmits the identifier to a management controller via a hardware bus in the computing device. The processor generates a key and encrypts the key with the identifier to generate a wrapped key. The processor transmits the wrapped key to the management controller. In turn, the management controller unwraps the key using the identifier. Other embodiments are described and claimed.

Abstract: Embodiments herein describe techniques for a semiconductor device including a TFT having a gate electrode with a gate length determined by a spacer. Embodiments may include a gate electrode above a substrate, a channel layer above the gate electrode, and a source electrode, a drain electrode, and a spacer above the channel layer. The drain electrode may be separated from the source electrode by the spacer. The drain electrode and the source electrode may have different widths or include different materials. Furthermore, the spacer may overlap with the gate electrode, hence the gate length of the gate electrode may be determined by the spacer width. Other embodiments may be described and/or claimed.

Abstract: Various embodiments herein provide techniques for reference signal (RS) configuration for high frequency bands (e.g., frequency above 52.6 GHz). For example, embodiments may include techniques for configuration of a demodulation reference signal (DM-RS), a channel state information reference signal (CSI-RS), and/or a sounding reference signal (SRS). The RS configuration may provide a low peak-to-average power ratio (PAPR) compared to prior techniques. Other embodiments may be described and claimed.

Abstract: A monolithic three-dimensional integrated circuit may include multiple transistor levels separated by one or more levels of metallization. An upper level transistor structure may include a monocrystalline channel material over a bottom gate stack. The channel material and the gate stack materials may be formed on a donor substrate at any suitable temperature, and subsequently transferred from the donor substrate to a host substrate that includes lower-level circuitry. The upper-level transistor may be patterned from the transferred layers so that the gate electrode includes one or more bonding layers. Source and drain material may be patterned from a source and drain material layer that was transferred from the donor substrate along with the channel material, or source and drain material may be grown at low temperatures from the transferred channel material.

Abstract: Various embodiments herein provide physical uplink control channel (PUCCH) designs for discrete Fourier transform-spread-orthogonal frequency-division multiplexing (DFT-s-OFDM) waveforms for systems operating above the 52.6 GHz carrier frequency. Some embodiments of the present disclosure may be directed to phase tracking reference signal (PT-RS) design for PUCCH with carrier frequencies above 52.6 GHz. Other embodiments may be disclosed and/or claimed.

Abstract: Apparatuses, methods and storage medium associated with compensating for a sensor deficiency in a heterogeneous sensor array are disclosed herein. In embodiments, an apparatus may include a compute device to aggregate perception data from individual perception pipelines, each of which is associated with respective one of different types of sensors of a heterogeneous sensor set, to identify a characteristic associated with a space to be monitored by the heterogeneous sensor set; detect a sensor deficiency associated with a first sensor of the sensors; and in response to a detection of the sensor deficiency, derive next perception data for more than one of the individual perception pipelines from sensor data originating from at least one second sensor of the sensors. Other embodiments may be disclosed or claimed.

Abstract: Homomorphic encryption (HE) acceleration circuitry includes encode circuitry to encode cleartext data into plaintext data, encrypt circuitry to encrypt the plaintext data into HE ciphertext data according to an HE process, decrypt circuitry to decrypt the HE ciphertext data into the plaintext data according to the HE process, and decode circuitry to decode the plaintext data into the cleartext data.

Abstract: The technology disclosed herein includes broadcasting, to a plurality of destination computing systems, a request to live migrate at least one trusted execution environment virtual machine (TVM) to at least one of the plurality of destination computing systems, receiving one or more bids from at least one of the plurality of destination computing systems, allocating the at least one TVM to at least one of the plurality of destination computing systems based at least on a bidding price in the one or more bids, automatically live migrating the at least one TVM to the at least one of the plurality of destination computing systems based on the allocating, and storing live migration allocation information of the at least one TVM on a first blockchain.

Abstract: An apparatus to facilitate supporting and load balancing multiple double precision pipelines in a graphics environment is disclosed. The apparatus includes a processing core having at least one processing resource comprising: a first double precision (DP) pipeline to support double float operations, the first DP pipeline comprising a first set of floating point units (FPUs) configured in a pipelined configuration to enable new instructions to be issued to the first DP pipeline before previous instructions are complete; and a second DP pipeline to support the double float operations, wherein the second DP pipeline comprising a second set of FPUs configured in a pipelined configuration to enable new instructions to be issued to the first DP pipeline before previous instructions are complete.

Abstract: A system and method of implementing digitally signed secure quick response (SQR) codes include storing captured content as a hash map, calculating a hash of the captured content, where the hash is a unique key that is stored in the hash map, creating a digital signature for the captured content using a private key such that the captured content is digitally signed, generating a SQR code of the digitally signed captured content, and storing the SQR code including the digitally signed captured content in a secure digital (SD) card.

Abstract: Techniques include an apparatus to retrieve a first parameter for the IDS to monitor a device for a time-synchronized network. The first parameter may represent a number of messages the IDS needs to analyze in order to detect a security attack. The messages may comprise time information to synchronize a clock for a device to a network time for a time-synchronized network. The processor circuitry may retrieve a second parameter for a time sensitive application. The second parameter may represent a defined amount of time error tolerated by the time sensitive application, and determine a third parameter for the IDS based on the first and second parameters. The third parameter may represent a defined frequency to receive a number of messages with time information in order to detect the security attack on the device within a defined time interval. Other embodiments are described and claimed.

Abstract: An apparatus to facilitate cross-thread register sharing for matrix multiplication compute is disclosed. The apparatus includes matrix acceleration hardware comprising a plurality of data processing units, wherein the respective plurality of data processing units are to: receive a decoded instruction for a first thread having a first register space, wherein the decoded instruction is for a matrix multiplication operation and comprises an indication to utilize a second register space of a second thread for an operand of the decoded instruction for the first thread; access the second register space of the second thread to obtain data for the operand of the decoded instruction; and perform the matrix multiplication operation for the first thread using the data for the operand from the second register space of the second thread.