A method of verifying processing logic of a graphics processing unit receives a test task including a predefined set of instructions for execution on the graphics processing unit, the predefined set of instructions being configured to perform a predetermined set of operations on the graphics processing unit when executed for predefined input data. In a test phase, the test task is processed by executing the predefined set of instructions for the predefined input data first and second times at the graphics processing unit so as to, respectively, generate first and second outputs. A fault signal is raised if the first and second outputs do not match.

In various examples, a VPU and associated components may be optimized to improve VPU performance and throughput. For example, the VPU may include a min/max collector, automatic store predication functionality, a SIMD data path organization that allows for inter-lane sharing, a transposed load/store with stride parameter functionality, a load with permute and zero insertion functionality, hardware, logic, and memory layout functionality to allow for two point and two by two point lookups, and per memory bank load caching capabilities. In addition, decoupled accelerators may be used to offload VPU processing tasks to increase throughput and performance, and a hardware sequencer may be included in a DMA system to reduce programming complexity of the VPU and the DMA system. The DMA and VPU may execute a VPU configuration mode that allows the VPU and DMA to operate without a processing controller for performing dynamic region based data movement operations.

An apparatus to facilitate scalable runtime validation for on-device design rule checks is disclosed. The apparatus includes a memory to store a contention set, one or more multiplexors, and a validator communicably coupled to the memory. In one implementation, the validator is to: receive design rule information for the one or more multiplexers, the design rule information referencing the contention set; analyze, using the design rule information, a user bitstream against the contention set at a programming time of the apparatus, the user bitstream for programming the one or more multiplexors; and provide an error indication responsive to identifying a match between the user bitstream and the contention set.

A microprocessor system comprises a matrix computational unit and a control unit. The matrix computational unit includes a plurality of processing elements. The control unit is configured to provide a matrix processor instruction to the matrix computational unit. The matrix processor instruction specifies a floating-point operand formatted using a first floating-point representation format. The matrix computational unit accumulates an intermediate result value calculated using the floating-point operand. The intermediate result value is in a second floating-point representation format.

At a first compute instance run on a virtualization host, a local instance scaling manager is launched. The scaling manager determines, based on metrics collected at the host, that a triggering condition for redistributing one or more types of resources of the first compute instance has been met. The scaling manager causes virtualization management components to allocate a subset of the first compute instance's resources to a second compute instance at the host.

A method of processing in-memory commands in a high-bandwidth memory (HBM) system includes sending a function-in-HBM instruction to the HBM by a HBM memory controller of a GPU. A logic component of the HBM receives the FIM instruction and coordinates the instructions execution using the controller, an ALU, and a SRAM located on the logic component.

A processor core is configured to execute a parent task that is described by a data structure stored in a memory. A coprocessor is configured to dispatch a child task to the at least one processor core in response to the coprocessor receiving a request from the parent task concurrently with the parent task executing on the at least one processor core. In some cases, the parent task registers the child task in a task pool and the child task is a future task that is configured to monitor a completion object and enqueue another task associated with the future task in response to detecting the completion object. The future task is configured to self-enqueue by adding a continuation future task to a continuation queue for subsequent execution in response to the future task failing to detect the completion object.

Apparatuses, systems, and techniques to receive, by a processor of a computer system, one or more operations for a kernel; automatically generate, by the processor, one or more operators that perform the one or more operations on elements of one or more input data structures; and automatically generate, by the processor, the kernel that comprises the one or more operators.

A data processing apparatus comprises receiver circuitry for receiving instructions from each of a plurality of requester devices. Processing circuitry executes the instructions associated with each of a subset of the requester devices at a time and arbitration circuitry determines the subset of the requester devices and causes the instructions associated with each of the subset of the requester devices to be executed next. In response to the receiver circuitry receiving an instruction of a predetermined type from one of the requester devices outside the subset of requester devices, the arbitration circuitry causes the instruction of the predetermined type to be executed next.

A cellular modem processor can include dedicated processing engines that implement specific, complex data processing operations. To implement PDCCH decoding, a cellular modem can include a pipeline having multiple processing engines, with the processing engines including functional units that execute instructions corresponding to different stages in the PDCCH decoding process. Flow control and data synchronization between instructions can be provided using a hybrid of firmware-based flow control and hardware-based data dependency management.