Abstract: A processing system selects entries for eviction at one cache based at least in part on the validity status of corresponding entries at a different cache. The processing system includes a memory hierarchy having at least two caches, a higher level cache and a lower level cache. The lower level cache monitors which locations of the higher level cache have been indicated as invalid and, when selecting an entry of the lower level cache for eviction to the higher level cache, selects the entry based at least in part on whether the selected cache entry will be stored at an invalid cache line of the higher level cache.

Abstract: Systems, apparatuses, and methods for utilizing a programmable memory command sequencer to generate multiple commands from a single memory request. A sequencer receives requests from a host processor and utilizes any of a plurality of programmable routines in response to determining that a given request meets specific criteria. A given programmable routine generates a plurality of memory commands which are then conveyed to a local memory controller and/or one or more remote memory controllers. The host processor programs the sequencer at boot time and updates the sequencer at runtime in response to changing application behavior. In various embodiments, the sequencer generates a variety of error correction routines in response to different requests received from the host processor.

Abstract: A processing system includes a processor that implements registers to define a state of a virtual machine (VM) running on the processor. The processor detects exit conditions of the VM. The processing system also includes a memory element to store contents of the registers in a first data structure that is isolated from a hypervisor of the VM in response to the processor detecting an exit condition. The VM is to selectively expose contents of a subset of the registers to the hypervisor.

Abstract: A system and method for efficient arbitration of memory access requests are described. One or more functional units generate memory access requests for a partitioned memory. An arbitration unit stores the generated requests and selects a given one of the stored requests. The arbitration unit identifies a given partition of the memory which stores a memory location targeted by the selected request. The arbitration unit determines whether one or more other stored requests access memory locations in the given partition. The arbitration unit sends each of the selected memory access request and the identified one or more other memory access requests to the memory to be serviced out of order.

Abstract: Techniques for managing message transmission in a large networked computer system that includes multiple individual networked computing systems are disclosed. Message passing among the computing systems include a sending computing device transmitting a message to a receiver computing device and a receiver computing device consuming that message. A build-up of data stored in a buffer at the receiver can reduce performance. In order to reduce the potential performance degradation associated with large amounts of “waiting” data in the buffer, a sending computer system first determines whether the receiver computer system is ready to receive a message and does not transmit the message if the receiver computer system is not ready. To determine whether the receiver computer system is ready to receive a message, the receiver computer system, at the request of the sending computer system, checks a counting filter that stores indications of whether particular messages are ready.

Abstract: Described herein is a method and system for directly accessing and transferring data between a first memory architecture and a second memory architecture associated with a graphics processing unit (GPU) by treating the first memory architecture, the second memory architecture and system memory as a single physical memory, where the first memory architecture is a non-volatile memory (NVM) and the second memory architecture is a local memory. Upon accessing a virtual address (VA) range by a processor, the requested content is paged in from the single physical memory and is then redirected by a virtual storage driver to the second memory architecture or the system memory, depending on which of the GPU or CPU triggered the access request. The memory transfer occurs without awareness of the application and the operating system.

Abstract: Systems, apparatuses, and methods for performing a division operation are disclosed. In one embodiment, a processor includes at least one arithmetic logic unit and a register file. In response to detecting a request to perform a division operation between a dividend and a divisor, the processor generates an initial approximation of the reciprocal of the divisor. Then, the processor converts the initial approximation of the reciprocal of the divisor into a fractional fixed point representation. The processor also introduces a small error into the initial approximation of the reciprocal of the divisor. Then, the processor implements one or more Newton-Raphson iterations for refining the approximation of the reciprocal and then multiplies the final reciprocal value by the dividend to generate the quotient.

Abstract: Various on-die-precision-resistor arrays, and methods of making and calibrating the same are disclosed. In one aspect, an apparatus is provided that includes a semiconductor chip and a precision resistor array on the semiconductor chip. A replica precision resistor array is on the semiconductor chip. The replica precision resistor array is configured to mimic the resistance behavior of the precision resistor array and has a characteristic resistance that is a function of temperature. The semiconductor chip is configured to calibrate the precision resistor array using the characterized resistance as a function of temperature, a resistance offset of the precision resistor array relative to the characterized resistance as a function of temperature, and a temperature of the precision resistor array.

Abstract: A method, system, and computer program product synchronize a group of workitems executing an instruction stream on a processor. The processor is yielded by a first workitem responsive to a synchronization instruction in the instruction stream. A first one of a plurality of program counters is updated to point to a next instruction following the synchronization instruction in the instruction stream to be executed by the first workitem. A second workitem is run on the processor after the yielding.

Abstract: A method and apparatus for reducing dynamic power consumption in a multi-thread content-addressable memory (CAM) is described. The disclosed apparatus includes a first input configured to receive a first virtual address corresponding to a first thread, a second input configured to receive a second virtual address corresponding to a second thread, a register bank including a plurality of registers each configured to store a binary word mapped to one of a plurality of physical addresses, a first comparator bank including a first plurality of comparators each coupled to one of the plurality of registers in a fully-associative configuration and configured to determine whether a first match is present, and a second comparator bank including a second plurality of comparators each coupled to one of the plurality of registers in a fully-associative configuration and configured to determine whether a second match is present.

Abstract: The present disclosure relates to a method and system for securing a performance state change of one or more processors. A disclosed method includes detecting a request to change a current performance state of a processor to a target performance state, and adjusting an operating level tolerance range of the current performance state to include operating levels associated with a transition from the current performance state to the target performance state. A disclosed system includes an operating system module operative to transmit a request for a performance state change of at least one processing core. The system includes performance state control logic operative to change the performance state of the at least one processing core based on the request.

Abstract: Methods, systems and computer-readable mediums for task scheduling on an accelerated processing device (APD) are provided. In an embodiment, a method comprises: enqueuing one or more tasks in a memory storage module based on the APD; using a software-based enqueuing module; and dequeuing the one or more tasks from the memory storage module using a hardware-based command processor, wherein the command processor forwards the one or more tasks to the shader cote.

Abstract: A method and apparatus of integrating memory stacks includes providing a first memory die of a first memory technology and a second memory die of a second memory technology. A first logic die is in communication with the first memory die of the first memory technology, and includes a first memory controller including a first memory control function for interpreting requests in accordance with a first protocol for the first memory technology. A second logic die is in communication with the second memory die of the second memory technology and includes a second memory controller including a second memory control function for interpreting requests in accordance with a second protocol for the second memory technology. A memory operation request is received at the first or second memory controller, and the memory operation request is performed in accordance with the associated first memory protocol or the second memory protocol.

Abstract: A method and apparatus of precomputing includes capturing a first image by a first image capturing device. An image space for the first image is defined and pixels in the image space are analyzed for validity. Valid pixels are stored as valid pixel groups and the valid pixel groups are processed.

Abstract: A method, a system, and a computer-readable storage medium directed to performing high-speed parallel tessellation of 3D surface patches are disclosed. The method includes generating a plurality of primitives in parallel. Each primitive in the plurality is generated by a sequence of functional blocks, in which each sequence acts independently of all the other sequences.

Abstract: Described herein is a method and apparatus for using cube mapping and mapping metadata with encoders. Video data, such as 360° video data, is sent by a capturing device to an application, such as video editing software, which generates cube mapped video data and mapping metadata from the 360° video data. An encoder then applies the mapping metadata to the cube mapped video data to minimize or eliminate search regions when performing motion estimation, minimize or eliminate neighbor regions when performing intra coding prediction and assign zero weights to edges having no relational meaning.

Abstract: Methods and apparatus of delegating instructions or data from a CU to an NOC node in a network on chip (NOC) is disclosed. The NOC node executes the delegated instructions or processes the delegated data. An NOC controller (NCC), which is operatively coupled to the CU and the NOC node, facilitates delegating the instructions or data from the CU to the NOC node.

Abstract: A graphics processing unit is disclosed, the graphics processing unit having a processor having one or more SIMD processing units, and a local data share corresponding to one of the one or more SIMD processing units, the local data share comprising one or more low latency accessible memory regions for each group of threads assigned to one or more execution wavefronts, and a global data share comprising one or more low latency memory regions for each group of threads.

Abstract: A GPU is configured to read and process data produced by a compute shader via the one or more ring buffers and pass the resulting processed data to a vertex shader as input. The GPU is further configured to allow the compute shader and vertex shader to write through a cache. Each ring buffer is configured to synchronize the compute shader and the vertex shader to prevent processed data generated by the compute shader that is written to a particular ring buffer from being overwritten before the data is accessed by the vertex shader. It is emphasized that this abstract is provided to comply with the rules requiring an abstract that will allow a searcher or other reader to quickly ascertain the subject matter of the technical disclosure. It is submitted with the understanding that it will not be used to interpret or limit the scope or meaning of the claims.

Abstract: In some embodiments, a method of managing cache memory includes identifying a group of cache lines in a cache memory, based on a correlation between the cache lines. The method also includes tracking evictions of cache lines in the group from the cache memory and, in response to a determination that a criterion regarding eviction of cache lines in the group from the cache memory is satisfied, selecting one or more (e.g., all) remaining cache lines in the group for eviction.