Abstract: Sampling circuitry independently accesses channels of texture data that represent a set of pixels. One or more processing units separately compress the channels of the texture data and store compressed data representative of the channels of the texture data for the set of pixels. The channels can include a red channel, a blue channel, and a green channel that represent color values of the set of pixels and an alpha channel that represents degrees of transparency of the set of pixels. Storing the compressed data can include writing the compress data to portions of a cache. The processing units can identify a subset of the set of pixels that share a value of a first channel of the plurality of channels and represent the value of the first channel over the subset of the set of pixels using information representing the value, the first channel, and boundaries of the subset.

Abstract: Systems, apparatuses, and methods for using a multi-stream foveal display transport layer are disclosed. A virtual reality (VR) system includes a transmitter sending a plurality of streams over a display transport layer to a receiver coupled to a display. Each stream corresponds to a different image to be blended together by the receiver. The images include at least a foveal region image corresponding to a gaze direction of the eye and a background image which is a lower-resolution image with a wider field of view than the foveal region image. The phase timing of the foveal region stream being sent over the transport layer is adjusted with respect to the background stream to correspond to the location of the foveal region within the overall image. This helps to reduce the amount of buffering needed at the receiver for blending the images together to create a final image to be driven to the display.

Abstract: A technique for determining a quality value for a subject block of encoded video is provided. Contributing blocks, of the same frame and/or different frames of the subject block, are determined by identifying blocks likely to be a part of the same moving object or background as the subject block. A spatial and/or temporal filter is then applied to the quality values of the contributing blocks and an initial quality value of the subject block. With a spatial filter, quality values for contributing blocks from the same frame are combined and used to modify the quality value of the subject block. With a spatial filter, a temporal characteristic quality value for contributing blocks of one or more other frames (such as the immediately previous frame) is determined and then combined with a quality value representative of the subject block.

Abstract: A system-on-chip (SOC), includes a memory, a partition access module coupled to the memory, a partition requesting unit coupled to the partition access module, and a first input-output (IO) device coupled to the partition access module. The partition access module creates a first partition of the SOC. The first partition includes a first portion of a first processor, the first IO device, and a first portion of the memory. Based upon a partition request, the partition access module repartitions the SOC to create a dynamic partition. The dynamic partition includes the first portion of the first processor, the first input-output (IO) device, the first portion of the memory, and a second IO device not included in the first partition.

Abstract: For one or more stages of execution of a software application at a first processor, a remap vector of a second processor is reconfigured to represent a dynamic mapping of virtual address groups to physical address groups for that stage. Each bit position of the remap vector is configured to store a value indicating whether a corresponding virtual address group is actively mapped to a corresponding physical address group. Address translation operations issued during a stage of execution of the software application are selectively processed based on the configuration of the remap vector for that stage, with the particular value at the bit position of the remap vector associated with the corresponding virtual address group controlling whether processing of the address translation operation is continued to obtain a virtual-to-physical address translation sought by the address translation operation or processing of the address translation operation is ceased and a fault is issued.

Abstract: Disclosed herein is a region-based reference management system using in video frame encoding. Source content, such as video game streaming or remote desktop sharing, that includes scene changes or significant instantaneous changes in a region from one frame to the next can present encoding challenges. Techniques disclosed herein use hints about changes in regional frame content, dissect frame content into regions, and associate the dissected regions with stored reference frame data using the hints and information about the regions to more efficiently encode frames.

Abstract: A platform security processor is booted and reads a set of write-once memory bits to obtain a minimum security patch level (SPL). The security processor then verifies that a table SPL for a firmware security table is greater than or equal to the minimum SPL. The firmware security table includes a plurality of firmware identifiers for firmware code modules, and a plurality of check SPL values each associated with respective one of the firmware identifiers. The security processor verifies SPL values in a plurality of firmware code modules by, for each firmware code module, accessing the module to obtain its firmware SPL value and check if the respective firmware SPL value is equal to or greater than a respective check SPL value in the firmware security table.

Abstract: A graphics processing unit (GPU) instructs a display control module to capture content and display captured content in response to the refresh rate of a display exceeding a frame generation rate of the GPU. Rather than re-transmit the same frame multiple times, the GPU instructs the display control module to replay a previously-transmitted frame. During a refresh cycle in which the display control module is replaying captured content, the GPU omits accessing memory to retrieve and resend the frame that is being replayed, and instead sends only invalid data and GPU timing information so that the display control module remains synchronized with the GPU.

Abstract: A Management Component Transport Protocol platform management subsystem includes an internal bridge, a first segment group, and a second segment group. The first segment group is coupled to the internal bridge. The second segment group is coupled to the internal bridge and the first segment group. The first segment group has a first plurality of Peripheral Component Interconnect Express (PCIe)-based buses. The second segment group has a second plurality of PCIe-based buses, wherein based on an identification (ID)-routed packet from the first segment group to the second segment group, the internal bridge routes the ID-routed packet to the second segment group.

Abstract: A method and processing device are disclosed for allocating hardware bandwidth capability for a virtual environment. The processing device comprises memory and a processor. The processor is configured to determine current hardware bandwidth usages for a plurality of virtual functions (VFs) executing on corresponding virtual machines (VMs), determine utilizations of hardware bandwidth capabilities of the VFs, reallocate the hardware bandwidth capabilities based on the determined utilizations and store the reallocated hardware bandwidth usages in a portion of the memory which is accessible to the VMs. Utilizations are determined, for example, based on current hardware bandwidth usages. The hardware bandwidth capabilities are, for example, reallocated by storing metadata indicating the hardware bandwidth capability allocated to each of the VFs.

Abstract: Some implementations provide systems, devices, and methods for implementing a cache replacement policy. A memory request is issued for attribute information associated with a node in an acceleration data structure. The attribute information associated with the node is inserted into a cache entry of the cache and an age associated with the cache entry is set to a value based on the attribute information, in response to the memory request causing a cache miss.

Abstract: A processor maintains an access log indicating a stream of cache misses at a cache of the processor. In response to each of at least a subset of cache misses at the cache, the processor records a corresponding entry in the access log, indicating a physical memory address of the memory access request that resulted in the corresponding miss. In addition, the processor maintains an address translation log that indicates a mapping of physical memory addresses to virtual memory addresses. In response to an address translation (e.g., a page walk) that translates a virtual address to a physical address, the processor stores a mapping of the physical address to the corresponding virtual address at an entry of the address translation log. Software executing at the processor can use the two logs for memory management.

Abstract: A GPU is generally configured to detect changes in the rate of frame generation that can result from, for example, changes in the complexity of the frames being generated. In response to detecting the change in the rate of frame generation, the GPU identifies a corresponding change in the refresh rate that would be required to fully synchronize the refresh rate with the rate of frame generation. If the change in the refresh rate falls outside the boundaries of a specified or dynamically generated window, the GPU limits the change in refresh rate to the corresponding boundary.

Abstract: A method and apparatus for reducing latency in a virtual reality system including a plurality of devices comprises capturing and transmitting, by a first device, a first batch of data to a second device. The second device renders and encodes a second data based upon the first batch of data, and transmits the first encoded image to the first device. Based upon a determination of a likelihood of collision between a transmission of a second batch of data from the first device and the transmission of the second data, the first device adjusts a frequency of capturing and transmitting the second batch of data.

Abstract: A floating point unit includes a non-pickable scheduler queue (NSQ) that offers a load operation concurrently with a load store unit retrieving load data for an operand that is to be loaded by the load operation. The floating point unit also includes a renamer that renames architectural registers used by the load operation and allocates physical register numbers to the load operation in response to receiving the load operation from the NSQ. The floating point unit further includes a set of pickable scheduler queues that receive the load operation from the renamer and store the load operation prior to execution. A physical register file is implemented in the floating point unit and a free list is used to store physical register numbers of entries in the physical register file that are available for allocation.

Abstract: Systems, apparatuses, and methods for reducing chiplet interrupt latency are disclosed. A system includes one or more processing nodes, one or more memory devices, a communication fabric coupled to the processing unit(s) and memory device(s) via link interfaces, and a power management unit. The power management unit manages the power states of the various components and the link interfaces of the system. If the power management unit detects a request to wake up a given component, and the link interface to the given component is powered down, then the power management unit sends an out-of-band signal to wake up the given component in parallel with powering up the link interface. Also, when multiple link interfaces need to be powered up, the power management unit powers up the multiple link interfaces in an order which complies with voltage regulator load-step requirements while minimizing the latency of pending operations.

Abstract: Systems, apparatuses, and methods for implementing a deskewing method for a physical layer interface on a multi-chip module are disclosed. A circuit connected to a plurality of communication lanes trains each lane to synchronize a local clock of the lane with a corresponding global clock at a beginning of a timing window. Next, the circuit symbol rotates each lane by a single step responsive to determining that all of the plurality of lanes have an incorrect symbol alignment. Responsive to determining that some but not all of the plurality of lanes have a correct symbol alignment, the circuit symbol rotates lanes which have an incorrect symbol alignment by a single step. When the end of the timing window has been reached, the circuit symbol rotates lanes which have a correct symbol alignment and adjusts a phase of a corresponding global clock to compensate for missed symbol rotations.

Abstract: Systems, apparatuses, and methods for implementing a broadcast read response protocol are disclosed. A computing system includes a plurality of processing engines coupled to a memory subsystem. A first processing engine executes a read and broadcast response command, wherein the read and broadcast response command targets first data at a first address in the memory subsystem. One or more other processing engines execute a wait command to wait to receive the first data requested by the first processing engine. After receiving the first data from the memory subsystem, the plurality of processing engines process the first data as part of completing a first operation. In one implementation, the first operation is implementing a given layer of a machine learning model. In one implementation, the given layer is a convolutional layer of a neural network.

Abstract: Techniques for generating a task graph for workload scheduling based on a task graph specification program are provided. The techniques include executing control flow instructions of the task graph specification program to traverse the task graph specification program; generating pass nodes of the task graph based on pass instructions of the task graph specification program; generating resource nodes and directed edges based on resource declarations of the task graph specification program; and outputting the task graph specification program to a command scheduler for scheduling.

Abstract: Techniques for improving data transfer in a system having multiple accelerated processing devices (“APDs”) are described herein. In such a system, multiple APDs are coupled to a processor (e.g., a central processing unit (“CPU”)) via a general interconnect fabric and to each other via a high speed interconnect. The techniques herein increase the effective bandwidth for transfer of data between the CPU and the APD by transmitting data to both APDs through the portion of the interconnect fabric coupled to each respective APD. Then, one of the APDs transfers data to the other APD or to the processor via the high speed inter-APD interconnect. Although data transferred “indirectly” through the helper APD takes slightly more time to be transferred than a direct transfer, the total effective bandwidth to the target is increased due to the high-speed inter-APD interconnect.