Abstract: An apparatus for encoding an image and an apparatus for decoding an image are presented. An image contains one or more regions. For encoding the image, the image is decomposed into one or more regions and a region is evaluated to determine whether the region meets a predetermined compressions acceptability criteria. The region is then encoded in response to the transformed and quantized region meeting the predetermined compression acceptability criteria. For decoding the image, a region of the image is selected and the selected region is decoded using metadata associated with the selected region. The metadata includes transformation quantization settings and information describing an aspect ratio used to compress the region.

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 converting data to a tiling format when implementing convolutional neural networks are disclosed. A system includes at least a memory, a cache, a processor, and a plurality of compute units. The memory stores a first buffer and a second buffer in a linear format, where the first buffer stores convolutional filter data and the second buffer stores image data. The processor converts the first and second buffers from the linear format to third and fourth buffers, respectively, in a tiling format. The plurality of compute units load the tiling-formatted data from the third and fourth buffers in memory to the cache and then perform a convolutional filter operation on the tiling-formatted data. The system generates a classification of a first dataset based on a result of the convolutional filter operation.

Abstract: A processor reduces bus bandwidth consumption by employing a shared load scheme, whereby each shared load retrieves data for multiple compute units (CUs) of a processor. Each CU in a specified group monitors a bus for load accesses directed to a cache shared by the multiple CUs. In response to identifying a load access on the bus, a CU determines if the load access is a shared load access for its share group. In response to identifying a shared load access for its share group, the CU allocates an entry of a private cache associated with the CU for data responsive to the shared load access. The CU then monitors the bus for the data targeted by the shared load. In response to identifying the targeted data on the bus, the CU stores the data at the allocated entry of the private cache.

Abstract: A data processing system includes a host processor, a local memory coupled to the host processor, a plurality of remote memory media, and a scalable data fabric coupled to the host processor and to the plurality of remote memory media. The scalable data fabric includes a filter for storing information indicating a location of data that is stored by the data processing system. The host processor includes a hardware sequencer coupled to the filter for selectively moving data stored by the filter to the local memory.

Abstract: An indeterminate state representative of a metastable state is inserted into an output signal of a circuit representation responsive to the circuit representation receiving a metastable triggering event during a register transfer language (RTL) simulation. The simulation view of the RTL has been modified to ensure that the indeterminate state is propagated through the circuit representations regardless of the input on which the indeterminate state appears. The indeterminate state is maintained for a programmable amount of time and responsive to expiration of the amount of time, the output signal is set to a random binary value.

Abstract: A system and method for fabricating metal insulator metal capacitors while managing semiconductor processing yield and increasing capacitance per area are described. A semiconductor device fabrication process places an oxide layer on top of a metal layer. A photoresist layer is formed on top of the oxide layer and etched with repeating spacing. One of a variety of lithography techniques is used to alter the distance between the spacings. The process etches trenches into areas of the oxide layer unprotected by the photoresist layer and strips the photoresist layer. The top and bottom corners of the trenches are rounded. The process deposits a bottom metal, a dielectric, and a top metal on the oxide layer both on areas with the trenches and on areas without the trenches. The process completes the metal insulator metal capacitor with metal nodes contacting each of the top plate and the bottom plate.

Abstract: Systems, apparatuses, and methods for efficiently floor planning a semiconductor chip are disclosed. Within either the processor or the memory of a computing system, each of a first block and a neighboring second block has a same height. A first metal track plan for the first block is unaligned with respect to a second metal track plan for the second block. An offset for moving each track of the second metal plan to align with a track of the first metal track plan is determined where the offset is a fraction of the height. The placement of the second block is shifted by the offset with respect to the first block. The shifted placement of the second block allows the first metal track plan for the first block to use a unidirectional pattern across the first block and the second block.

Abstract: A data storage system performs partial compression and decompression of a set of memory items. The memory items each include a data block and a tag with a prefix making up at least part of the tag. The memory items are ordered based on the prefixes. A code word is created containing compressed information representing values of the prefixes for the set of memory items. The code word and block data for each of the memory items are stored in a memory. The code word is decompressed to recover the prefixes.

Abstract: Shader resources may be specified for input to a shader using a hierarchical data structure which may be referred to as a descriptor set. The descriptor set may be bound to a bind point of the shader and may contain slots with pointers to memory containing shader resources. The shader may reference a particular slot of the descriptor set using an offset, and may change shader resources by referencing a different slot of the descriptor set or by binding or rebinding a new descriptor set. A graphics pipeline may be specified by creating a pipeline object which specifies a shader and a rendering context object, and linking the pipeline object. Part or all of the pipeline may be validated, cross-validated, or optimized during linking.

Abstract: Systems, apparatuses, and methods for utilizing training sequences on a replica lane are described. A transmitter is coupled to a receiver via a communication channel with a plurality of lanes. One of the lanes is a replica lane used for tracking the drift in the optimal sampling point due to temperature variations, power supply variations, or other factors. While data is sent on the data lanes, test patterns are sent on the replica lane to determine if the optimal sampling point for the replica lane has drifted since a previous test. If the optimal sampling point has drifted for the replica lane, adjustments are made to the sampling point of the replica lane and to the sampling points of the data lanes.

Abstract: Systems, apparatuses, and methods for intentionally delaying servicing of interrupts in a computing system are disclosed. A computing system includes a processor that services interrupts generated by components of the computing system. An interrupt controller detects a received interrupt and intentionally delays servicing of the interrupt depending on various conditions. If the interrupt is a first type of interrupt and the processor is in a first power state, servicing of the interrupt is delayed by a first period of time. If the interrupt corresponds to the first type of interrupt and the processor is in a second power state, servicing of the interrupt is delayed for a period of time that is longer than the first period of time. If a non-maskable interrupt is received before expiration of either the first or second period of time, then servicing of any previously delayed interrupts is allowed to proceed.

Abstract: Systems, apparatuses, and methods for performing efficient data transfer in a computing system are disclosed. A computing system includes multiple transmitters sending singled-ended data signals to multiple receivers. A termination voltage is generated and sent to the multiple receivers. The termination voltage is coupled to each of signal termination circuitry and signal sampling circuitry within each of the multiple receivers. Any change in the termination voltage affects the termination circuitry and affects comparisons performed by the sampling circuitry. Received signals are reconstructed at the receivers using the received signals, the signal termination circuitry and the signal sampling circuitry.

Abstract: Systems, apparatuses, and methods for performing network packet templating for graphics processing unit (GPU)-initiated communication are disclosed. A central processing unit (CPU) creates a network packet according to a template and populates a first subset of fields of the network packet with static data. Next, the CPU stores the network packet in a memory. A GPU initiates execution of a kernel and detects a network communication request within the kernel and prior to the kernel completing execution. Responsive to this determination, the GPU populates a second subset of fields of the network packet with runtime data. Then, the GPU generates a notification that the network packet is ready to be processed. A network interface controller (NIC) processes the network packet using data retrieved from the first subset of fields and from the second subset of fields responsive to detecting the notification.

Abstract: A method and system for compiler optimization includes analyzing a representation of source code to identify an original conditional construct having both a high-latency instruction and one or more instructions dependent on the high-latency instruction in a branch of the conditional construct. A set of one or more instructions following the conditional construct in the representation of source code and independent of the high-latency instruction is selected. An optimized representation of the source code is generated, whereby the optimized representation replaces the original conditional construct with a first split conditional construct positioned prior to the selected set of one or more instructions and a second split conditional construct positioned following the selected set of one or more instructions, The method further includes generating an executable representation of the source code based on the optimized representation of the source code.

Abstract: A processing system employs an expandable memory buffer that supports enlarging the memory buffer when the processing system generates a large number of long latency memory transactions. The hybrid structure of the memory buffer allows a memory controller of the processing system to store a larger number of memory transactions while still maintaining adequate transaction throughput and also ensuring a relatively small buffer footprint and power consumption. Further, the hybrid structure allows different portions of the buffer to be placed on separate integrated circuit dies, which in turn allows the memory controller to be used in a wide variety of integrated circuit configurations, including configurations that use only one portion of the memory buffer.

Abstract: A computer vision processing device is provided which comprises memory configured to store data and a processor. The processor is configured to store captured image data in a first buffer and acquire access to the captured image data in the first buffer when the captured image data is available for processing. The processor is also configured to execute a first group of operations in a processing pipeline, each of which processes the captured image data accessed from the first buffer and return the first buffer for storing next captured image data when a last operation of the first group of operations executes.

Abstract: Methods are provided for creating objects in a way that permits an API client to explicitly participate in memory management for an object created using the API. Methods for managing data object memory include requesting memory requirements for an object using an API and expressly allocating a memory location for the object based on the memory requirements. Methods are also provided for cloning objects such that a state of the object remains unchanged from the original object to the cloned object or can be explicitly specified.

Abstract: A set of entries in a branch prediction structure for a set of second blocks are accessed based on a first address of a first block. The set of second blocks correspond to outcomes of one or more first branch instructions in the first block. Speculative prediction of outcomes of second branch instructions in the second blocks is initiated based on the entries in the branch prediction structure. State associated with the speculative prediction is selectively flushed based on types of the branch instructions. In some cases, the branch predictor can be accessed using an address of a previous block or a current block. State associated with the speculative prediction is selectively flushed from the ahead branch prediction, and prediction of outcomes of branch instructions in one of the second blocks is selectively initiated using non-ahead accessing, based on the types of the one or more branch instructions.

Abstract: A method and apparatus of performing processing in an image capturing device includes receiving an image by the image capturing device. The image is filtered to generate a first visible light component and a second infrared component. A decontamination is performed on the infrared component to generate a decontaminated infrared component, and an interpolation is performed on the visible component to generate an interpolated visible component, both of which are provided to an image signal processor (ISP) for further processing.