Abstract: Various semiconductor chip devices with stacked chips are disclosed. In one aspect, a semiconductor chip device is provided. The semiconductor chip device includes a first semiconductor chip that has a floor plan with a high heat producing area and a low heat producing area. At least one second semiconductor chip is stacked on the low heat producing area. The semiconductor chip device also includes means for transferring heat from the high heat producing area.

Abstract: A high-performance on-module caching architecture for hybrid memory modules is provided. A hybrid memory module includes a cache controller, a first volatile memory coupled to the cache controller, a first multiplexing data buffer coupled to the first volatile memory and the cache controller, and a first non-volatile memory coupled to the first multiplexing data buffer and the cache controller, wherein the first multiplexing data buffer multiplexes data between the first volatile memory and the first non-volatile memory and wherein the cache controller enables a tag checking operation to occur in parallel with a data movement operation. The hybrid memory module includes a volatile memory tag unit coupled to the cache controller, wherein the volatile memory tag unit includes a line connection that allows the cache controller to store a plurality of tags in the volatile memory tag unit and retrieve the plurality of tags from the volatile memory tag unit.

Abstract: A processing system includes a cache that includes a cache lines that are partitioned into a first subset of the cache lines and a second subsets of the cache lines. The processing system also includes one or more counters that are associated with the second subsets of the cache lines. The processing system further includes a processor configured to modify the one or more counters in response to a cache hit or a cache miss associated with the second subsets. The one or more counters are modified by an amount determined by one or more characteristics of a memory access request that generated the cache hit or the cache miss.

Abstract: An integrated circuit device wafer includes a silicon wafer substrate and a back side metallization structure. The back side metallization structure includes a first adhesion layer on the back side of the substrate, a first metal later over the first adhesion layer, a second metal layer over the first metal layer, and a second adhesion layer over the second metal layer. The first includes at least one of: silicon nitride and silicon dioxide. The first metal layer includes titanium. The second metal layer includes nickel. The second adhesion layer includes at least one of: silver, gold, and tin.

Abstract: Virtual Reality (VR) systems, apparatuses and methods of processing data are provided which include predicting, at a server, a user viewpoint of a next frame of video data based on received user feedback information sensed at a client, rendering a portion of the next frame using the prediction, encoding the portion, formatting the encoded portion into packets and transmitting the video data. At a client, the encoded and packetized A/V data is received and depacketized. The portion of video data and corresponding audio data is decoded and controlled to be displayed and aurally provided in synchronization. Latency may be minimized by utilizing handshaking between hardware components and/or software components such as a 3D server engine, one or more client processors, one or more client processors, a video encoder, a server NIC, a video decoder, a client NIC; and a 3D client engine.

Abstract: A master/slave configuration of a frequency locked Loop (FLL) decouples the process, target voltage, temperature (PVT) tracking goals of locking the loop from adapting the clock frequency in response to voltage droops in the supply. A master oscillator circuit receives a regulated supply voltage and supplies a master oscillator signal. A control circuit supplies a master frequency control signal to control a frequency of the master oscillator signal to a target frequency. A slave oscillator circuit is coupled to a regulated supply voltage and a droopy supply voltage and supplies a slave oscillator signal having a frequency responsive to a slave frequency control signal that is based on the master frequency control signal. The frequency of the second oscillator signal is further responsive to a voltage change of the droopy supply voltage.

Abstract: A memory manager of a processor identifies a block of data for eviction from a first memory module to a second memory module. In response, the processor copies only those portions of the data block that have been identified as modified portions to the second memory module. The amount of data to be copied is thereby reduced, improving memory management efficiency and reducing processor power consumption.

Abstract: A management node of a server maintains a database of configuration parameters that stores the individual configuration parameters for each compute node. In response to a boot request at a compute node, a configuration parameter control module at the node intercepts locally targeted requests to load configuration parameters. The configuration parameter module sends the requests to the management node and in response the management node sends configuration parameters responsive to the requests. The configuration parameter module provides the configuration parameters to the compute node, thereby emulating a local boot memory for the compute node.

Abstract: A processing apparatus is provided that includes NVRAM and one or more processors configured to process a first set and a second set of instructions according to a hierarchical processing scope and process a scoped persistence barrier residing in the program after the first instruction set and before the second instruction set. The barrier includes an instruction to cause first data to persist in the NVRAM before second data persists in the NVRAM. The first data results from execution of each of the first set of instructions processed according to the one hierarchical processing scope. The second data results from execution of each of the second set of instructions processed according to the one hierarchical processing scope. The processing apparatus also includes a controller configured to cause the first data to persist in the NVRAM before the second data persists in the NVRAM based on the scoped persistence barrier.

Abstract: Techniques are provided herein for pre-emptively reinforcing one or more buses of a computing device against the effects of signal noise that could cause a reduction in signal integrity. The techniques generally include detecting an event (or “trigger”) that would tend to indicate that a reduction in signal integrity will occur, examining a reinforcement action policy and system status to determine what reinforcement action to take, and performing the reinforcement action.

Abstract: Systems, methods, and devices for determining a derived counter value based on a hardware performance counter. Example devices include input circuitry configured to input a hardware performance counter value; counter engine circuitry configured to determine the derived counter value by applying a model to the hardware performance counter value; and output circuitry configured to communicate the derived counter value to a consumer. In some examples, the consumer includes an operating system scheduler, a memory controller, a power manager, or a data prefetcher, or a cache controller. In some examples, the processor includes circuitry configured to dynamically change the model during operation of the processor. In some examples, the model includes or is generated by an artificial neural network (ANN).

Abstract: Improvements in graphics processing pipelines are disclosed. The graphics processing pipeline processes graphics objects in a particular order (application programming interface order—“API order”) as requested by an application or other entity. However, certain components within the graphics processing pipeline, such as the pixel shader stage, may process those objects out of order. A technique is provided herein to allow the pixel shader stage to complete and export processed fragments out of order. The technique includes using a scoreboard to determine whether fragments ready to be exported from a pixel shader stage are the newest fragments in API order. If the fragments are the newest in API order, then the fragments are exported. If the fragments are not the newest in API order, then the fragments are discarded.

Abstract: Techniques are provided for using a translation lookaside buffer to provide low latency memory address translations for data streams. Clients of a memory system first prepare the address translation cache hierarchy by requesting that a translation pre-fetch stream is initialized. After the translation pre-fetch stream is initialized, the cache hierarchy returns an acknowledgment of completion to the client, which then begins to access memory. Pre-fetch streams are specified in terms of address ranges and are performed for large contiguous portions of the virtual memory address space.

Abstract: Described is a method and system to efficiently compress and stream texture-space rendered content that enables low latency wireless virtual reality applications. In particular, camera motion, object motion/deformation, and shading information are decoupled and each type of information is then compressed as needed and streamed separately, while taking into account its tolerance to delays.

Abstract: Briefly, methods and apparatus to migrate a software thread from one wavefront executing on one execution unit to another wavefront executing on another execution unit whereby both execution units are associated with a compute unit of a processing device such as, for example, a GPU. The methods and apparatus may execute compiled dynamic thread migration swizzle buffer instructions that when executed allow access to a dynamic thread migration swizzle buffer that allows for the migration of register context information when migrating software threads. The register context information may be located in one or more locations of a register file prior to storing the register context information into the dynamic thread migration swizzle buffer. The method and apparatus may also return the register context information from the dynamic thread migration swizzle buffer to one or more different register file locations of the register file.

Abstract: Systems, apparatuses, and methods for dynamically optimizing memory traffic in multi-client systems are disclosed. A system includes a plurality of client devices, a memory subsystem, and a communication fabric coupled to the client devices and the memory subsystem. The system includes a first client which generates memory access requests targeting the memory subsystem. Prior to sending a given memory access request to the fabric, the first client analyzes metadata associated with data targeted by the given memory access request. If the metadata indicates the targeted data is the same as or is able to be derived from previously retrieved data, the first client prevents the request from being sent out on the fabric on the data path to memory subsystem. This helps to reduce memory bandwidth consumption and allows the fabric and the memory subsystem to stay in a low-power state for longer periods of time.

Abstract: A cooling system is provided for a 3D integrated circuit (IC) to deliver fluid in x, y, and z dimensions to interior regions of the IC as a means to regulate heat. An IC includes a microfluidic network of channels, at least one sensor and at least one microelectromechanical system (MEMS)-based device that is disposed within the network of channels and that is configured to regulate a flow of fluid within the network of channels. Each sensor monitors a state of the IC. Each MEMS-based device receives control signals based on a state of the IC and regulates a flow of fluid within the network of channels based on control signals that area received on a real-time basis based on changes detected in a state of the IC.

Abstract: A processing device is provided which includes a plurality of encoders each configured to compress a portion of data using a different compression algorithm. The processing device also includes one or more processors configured to cause an encoder, of the plurality of encoders, to compress the portion of data when it is determined that the portion of data, which is compressed by another encoder configured to compress the portion of data prior to the encoder in an encoder hierarchy, is not successfully compressed according to a compression metric by the other encoder in the encoder hierarchy. The one or more processors are also configured to prevent the encoder from compressing the portion of data when it is determined that the portion of data is successfully compressed according to the compression metric by the other encoder in the encoder hierarchy.

Abstract: In one form, an apparatus includes a memory controller. The memory controller includes a command queue and an arbiter. The command queue receives and stores memory access requests. The arbiter picks the memory access requests from the command queue based on a plurality of criteria, and provides picked memory access requests to a memory channel. The arbiter includes a streak counter for counting a number of consecutive memory access requests of a first type that the arbiter picks from the command queue. When the streak counter reaches a threshold, the arbiter suspends picking requests of the first type and picks at least one memory access request of a second type. The arbiter provides the at least one memory access request of the second type to the memory channel.

Abstract: A memory controller includes a host interface for receiving memory access requests including access addresses, a memory interface for providing memory accesses to a memory system, and an address decoder coupled to the host interface for programmably mapping the access addresses to selected ones of a plurality of regions. The address decoder is programmable to map the access addresses to a first region having a non-power-of-two size using a primary decoder and a secondary decoder each having power-of-two sizes, and providing a first region mapping signal in response. A command queue stores the memory access requests and region mapping signals. An arbiter picks the memory access requests from the command queue based on a plurality of criteria, which are evaluated based in part on the region mapping signals, and provides corresponding memory accesses to the memory interface in response.