Abstract: Some implementations provide systems, devices, and methods for rendering a plurality of primitives of a frame, the plurality of primitives being divided into a plurality of batches of primitives and the frame being divided into a plurality of bins. For at least one batch of the plurality of batches the rendering includes, for each of the plurality of bins, rendering primitives of a first sub-batch rasterizing to that bin, and for each of the plurality of bins, rendering primitives of a second sub-batch rasterizing to that bin.

Abstract: Methods, devices, and systems for managing performance of a processor having multiple compute units. An effective number of the multiple compute units may be determined to designate as having priority. On a condition that the effective number is nonzero, the effective number of the multiple compute units may each be designated as a priority compute unit. Priority compute units may have access to a shared cache whereas non-priority compute units may not. Workgroups may be preferentially dispatched to priority compute units. Memory access requests from priority compute units may be served ahead of requests from non-priority compute units.

Abstract: A method for operating a memory device includes initiating an access operation to a corresponding row of an array of bit cells of the memory device. Responsive to an expansion mode signal having a first state, the method further includes dynamically operating each column of a plurality of columns of the array to access each bit cell of a corresponding row within the plurality of columns during the access operation. Alternatively, responsive to the expansion mode state signal having a second state different than the first state, the method includes dynamically operating each column of a first subset of columns of the plurality of columns to access each bit cell of a corresponding row within the first subset of columns during the access operation, and maintaining each column of a second subset of columns of the plurality of columns in a static state during the access operation.

Abstract: A memory controller includes a command queue and an arbiter for selecting entries from the command queue for transmission to a DRAM. The arbiter transacts streaks of consecutive read commands and streaks of consecutive write commands. The arbiter has a current mode indicating the type of commands currently being transacted, and a cross mode indicating the other type. The arbiter is operable to monitor commands in the command queue for the current mode and the cross mode, and in response to designated conditions, send at least one cross-mode command to the memory interface queue while continuing to operate in the current mode. In response to an end streak condition, the arbiter swaps the current mode and the cross mode, and transacts the cross-mode command.

Abstract: A texture processor based ray tracing accelerator method and system are described. The system includes a shader, texture processor (TP) and cache, which are interconnected. The TP includes a texture address unit (TA), a texture cache processor (TCP), a filter pipeline unit and a ray intersection engine. The shader sends a texture instruction which contains ray data and a pointer to a bounded volume hierarchy (BVH) node to the TA. The TCP uses an address provided by the TA to fetch BVH node data from the cache. The ray intersection engine performs ray-BVH node type intersection testing using the ray data and the BVH node data. The intersection testing results and indications for BVH traversal are returned to the shader via a texture data return path. The shader reviews the intersection results and the indications to decide how to traverse to the next BVH node.

Abstract: A data processing system includes a memory channel, a memory coupled to the memory channel, and a data processor. The data processor is coupled to the memory channel and accesses the memory over the memory channel using a packet structure defining a plurality of commands and having corresponding address bits, data bits, and user bits. The data processor communicates with the memory over the memory channel using a first type of error code. In response to a write access request, the data processor calculates a different, second type of error code and appends each bit of the second type of error code as a corresponding one of the user bits. The memory stores the user bits in the memory in response to a write command, and transfers the user bits to the data processor in a read response packet in response to a read command.

Abstract: An array processor includes processor element arrays (PEAs) distributed in rows and columns. The PEAs are configured to perform operations on parameter values. A first sequencer received a first direct memory access (DMA) instruction that includes a request to read data from at least one address in memory. A texture address (TA) engine requests the data from the memory based on the at least one address and a texture data (TD) engine provides the data to the PEAs. The PEAs provide first synchronization signals to the TD engine to indicate availability of registers for receiving the data. The TD engine provides second synchronization signals to the first sequencer in response to receiving acknowledgments that the PEAs have consumed the data.

Abstract: A thermal management system includes an integrated circuit having an active side including a control circuit and a backside including a first set of electrodes distributed across the backside. The thermal management system includes a heat exchanger having a surface including a second set of electrodes. The thermal management system includes a thermal interface material including thermally conductive particles suspended in a fluid. The thermal interface material is disposed between the backside of the integrated circuit and the surface of the heat exchanger. The control circuit is configured to apply an electric field to the thermal interface material using a first electrode of the first set of electrodes and a second electrode of the second set of electrodes to excite at least some of the thermally conductive particles between the first electrode and the second electrode.

Abstract: A technique for detecting a glitch in an image is provided. The technique includes providing an image to a plurality of individual classifiers to generate a plurality of individual classifier outputs and providing the plurality of individual classifier outputs to an ensemble classifier to generate a glitch classification.

Abstract: A technique for generating a trained discriminator is provided. The technique includes applying one or more of a glitched image or an unglitched image to a discriminator; receiving classification output from the discriminator; adjusting weights of the discriminator to improve classification accuracy of the discriminator; applying noise to a generator; receiving an output image from the generator; applying the output image to the discriminator to obtain a classification; and adjusting weights of one of the discriminator or the generator to improve ability of the generator to reduce classification accuracy of the discriminator, based on the classification.

Abstract: A memory controller selects from among a plurality of memory access commands including volatile memory reads, volatile memory writes, non-volatile memory reads, and non-volatile memory writes. The selected memory access commands are transmitted to a heterogenous memory channel coupled to a non-volatile memory and a volatile memory. The non-volatile read commands that are transmitted are stored in a non-volatile command queue (NV queue). A ready response is received from the non-volatile memory indicating that responsive data is available for an associated one of the non-volatile read commands. In response to receiving the ready response, a send command is transmitted for commanding the non-volatile memory to send the responsive data.

Abstract: Described herein are techniques for improving the effectiveness of depth culling. In a first technique, a binner is used to sort primitives into depth bins. Each depth bin covers a range of depths. The binner transmits the depth bins to the screen space pipeline for processing in near-to-far order. Processing the near bins first results in the depth buffer being updated, allowing fragments for the primitives in the farther bins to be culled more aggressively than if the depth binning did not occur. In a second technique, a buffer is used to initiate two-pass processing through the screen space pipeline. In the first pass, primitives are sent down to update the depth block and are then culled. The fragments are processed normally in the second pass, with the benefit of the updated depth values.

Abstract: A processing system includes a memory controller that preemptively exits a dynamic random access (DRAM) integrated circuit rank from a low power mode such as power down mode based on a predicted time when the memory controller will receive a request to access the DRAM rank. The memory controller tracks how long after a DRAM rank enters the low power mode before a request to access the DRAM rank is received by the memory controller. Based on a history of the timing of access requests, the memory controller predicts for each DRAM rank a predicted time reflecting how long after entering low power mode a request to access each DRAM rank is expected to be received. The memory controller speculatively exits the DRAM rank from the low power mode based on the predicted time and prior to receiving a request to access the DRAM IC rank.

Abstract: A system for automatically discovering fabric topology includes at least one or more processing units, one or more memory devices, a security processor, and a communication fabric with an unknown topology coupled to the processing unit(s), memory device(s), and security processor. The security processor queries each component of the fabric to retrieve various attributes associated with the component. The security processor utilizes the retrieved attributes to create a network graph of the topology of the components within the fabric. The security processor generates routing tables from the network graph and programs the routing tables into the fabric components. Then, the fabric components utilize the routing tables to determine how to route incoming packets.

Abstract: Described is a method and apparatus for application migration between a dockable device and a docking station in a seamless manner. The dockable device includes a processor and the docking station includes a high-performance processor. The method includes determining a docking state of a dockable device while at least an application is running. Application migration from the dockable device to a docking station is initiated when the dockable device is moving to a docked state. Application migration from the docking station to the dockable device is initiated when the dockable device is moving to an undocked state. The application continues to run during the application migration from the dockable device to the docking station or during the application migration from the docking station to the dockable device.

Abstract: In some examples, thermal aware optimization logic determines a characteristic (e.g., a workload or type) of a wavefront (e.g., multiple threads). For example, the characteristic indicates whether the wavefront is compute intensive, memory intensive, mixed, and/or another type of wavefront. The thermal aware optimization logic determines temperature information for one or more compute units (CUs) in one or more processing cores. The temperature information includes predictive thermal information indicating expected temperatures corresponding to the one or more CUs and historical thermal information indicating current or past thermal temperatures of at least a portion of a graphics processing unit (GPU). The logic selects the one or more compute units to process the plurality of threads based on the determined characteristic and the temperature information. The logic provides instructions to the selected subset of the plurality of CUs to execute the wavefront.

Abstract: Speculative execution using a page-level tracked load order queue includes: determining that a first load instruction targets a determined memory region; and in response to the first load instruction targeting the determined memory region, adding an entry to a page-level tracked load order queue instead of a load order queue, where the entry indicates a page address of a target of the first load instruction.

Abstract: A system configured to perform scalable video encoding is provided. The system includes a memory; and a processing unit, wherein the processing unit is configured to: receive inter-layer data and a current picture, wherein the current picture has a base layer; upsample the inter-layer data to generate residual data and reconstruction data, wherein the inter-layer data includes a base mode flag; and encode the current picture to an enhanced layer using the upsampled inter-layer data based on a block type of the base layer and the base mode flag.

Abstract: A device is disclosed. The device includes a machine learning die including a memory and one or more machine learning accelerators; and a processing core die stacked with the machine learning die, the processing core die being configured to execute shader programs for controlling operations on the machine learning die, wherein the memory is configurable as either or both of a cache and a directly accessible memory.

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.