Micron Technology Incorporated

Patrick Alan Estep

Tony M Brewer

Skyler Arron Windh

Bryan D Hornung

Douglas John Vanesko

Emanuele Confalonieri

Stephen S Pawlowski

Nicola Del Gatto

David Andrew Roberts

Sean Stephen Eilert

Paolo Amato

Ameen D Akel

Allan Kennedy Porterfield

Aliasger Tayeb Zaidy

Bashar Romanous

Randall Paul Meyer

Devices and techniques for thread scheduling control and memory splitting in a processor are described herein. An apparatus includes a hardware interface configured to receive a first request to execute a first thread, the first request including an indication of a workload; and processing circuitry configured to: determine the workload to produce a metric based at least in part on the indication; compare the metric with a threshold to determine that the metric is beyond the threshold; divide, based at least in part on the comparison, the workload into a set of sub-workloads consisting of predefined number of equal parts from the workload; create a second request to execute a second thread, the second request including a first member of the set of sub-workloads; and process a second member of the set of sub-workloads in the first thread.

Dynamic decomposition and thread allocation

Systems, apparatuses, and methods related to data reconstruction based on queue depth comparison are described. To avoid accessing the 'congested' channel, a read command to access the “congested” channel can be executed by accessing the other relatively “idle” channels and utilize data read from the “idle” channels to reconstruct data corresponding to the read command.

Read replacement via data reconstruction based on access patterns

An apparatus can include a plurality of memory devices and a memory controller coupled to the plurality of memory devices via a plurality of memory channels. The plurality of memory channels are organized as a plurality of channel groups. The memory controller comprises a plurality of memory access request/response buffer sets, and each memory access request/response buffer set of the plurality of memory access request/response buffer sets corresponds to a different one of the plurality of channel groups.

Memory controller architecture

Systems, apparatuses, and methods related to a memory controller for cache bypass are described. An example memory controller can be coupled to a memory device. The example memory controller can include a cache including a cache sequence controller configured to determine a quantity of a given type of result of cache look-up operations, determine the quantity satisfies a bypass threshold, and cause performance of a bypass memory operation that bypasses the cache and accesses the memory device.

Cache bypass

Devices and techniques for CHAINED RESOURCE LOCKING are described herein. Threads form a last-in-first-out (LIFO) queue on a resource lock to create a chained lock on the resource. A data store representing the lock for the resource holds the previous thread's identifier, enabling a subsequent thread to wake the previous thread using the identifier when the subsequent thread releases the lock. Generally, the thread releasing the lock need not interact with the data store, reducing contention for the data store among many threads.

Chained resource locking

Linear interpolation is performed within a memory system. The memory system receives a floating-point point index into an integer-indexed memory array. The memory system accesses the two values of the two adjacent integer indices, performs the linear interpolation, and provides the resulting interpolated value. In many system architectures, the critical limitation on system performance is the data transfer rate between memory and processing elements. Accordingly, reducing the amount of data transferred improves overall system performance and reduces power consumption.

Interpolation acceleration in a processor memory interface

Disclosed in some examples, are methods, systems, devices, and machine-readable mediums which solve the above problems using a global shared region of memory that combines memory segments from multiple CXL devices. Each memory segment is a same size and naturally aligned in its own physical address space. The global shared region is contiguous and naturally aligned in the virtual address space. By organizing this global shared region in this manner, a series of three tables may be used to quickly translate a virtual address in the global shared region to a physical address. This prevents TLB thrashing and improves performance of the computing system.

Global virtual address space across operating system domains

Systems, devices, and methods related to a Deep Learning Accelerator and memory are described. For example, the accelerator can have processing units to perform at least matrix computations of an artificial neural network via execution of instructions. The processing units have a local memory store operands of the instructions. The accelerator can access a random access memory via a system buffer, or without going through the system buffer. A fetch instruction can request an item, available at a memory address in the random access memory, to be loaded into the local memory at a local address. The fetch instruction can include a hint for the caching of the item in the system buffer. During execution of the instruction, the hint can be used to determine whether to load the item through the system buffer or to bypass the system buffer in loading the item.

Caching techniques for deep learning accelerator

A memory controller can include a front end portion configured to interface with a host, a central controller portion configured to manage data, a back end portion configured to interface with memory devices. The memory controller can include interface management circuitry coupled to a cache and a memory device. The memory controller can receive, by the interface management controller, a first signal indicative of data associated with a memory access request from a host. The memory controller can transmit a second signal indicative of the data to cache the data in a first location in the cache. The memory controller can transmit a third signal indicative of the data to cache the data in a second location in the cache.

Memory controller for managing raid information

Various examples are directed to systems and methods for executing a loop in a reconfigurable compute fabric. A first flow controller may initiate a first thread at a first synchronous flow to execute a first portion of a first iteration of the loop. A second flow controller may receive a first asynchronous message instructing the second flow controller to initiate a first thread at a second synchronous flow to execute a second portion of the first iteration. The second flow controller may determine that the first iteration of the loop is the last iteration of the loop to be executed and initiate the first thread at the second synchronous flow with a last iteration flag set.

Loop execution in a reconfigurable compute fabric using flow controllers for respective synchronous flows

An assembly language program for a coarse grained reconfiguration array (CGRA), having dispatch interface information indicating operations to be performed via a dispatch interface of the CGRA to receive an input, memory interface information indicating operations to be performed via one or more memory interfaces of the CGRA, tile memory information indicating memory variables referring to memory locations to be implemented in tile memories of the CGRA, a flow description specifying one or more synchronous data flows, through the memory locations referenced via the memory variables in the tile memory information, to produce a result from the input using the CGRA.

Programming a coarse grained reconfigurable array through description of data flow graphs

A synthetic-aperture radar (SAR) antenna emits radar pulses and receives their reflections. SAR is typically used on a moving platform, such as an aircraft, drone, or spacecraft. Since the position of the antenna changes between the time of emitting a radar pulse and receiving the reflection of the pulse, the synthetic aperture of the radar is increased, giving greater accuracy for a same (physical) sized radar over conventional beam-scanning radar. The pulse data is processed, using a backprojection algorithm, to generate a two-dimensional image that can be used for navigation. The order in which the SAR data is processed can impact the likelihood of cache hits in accessing the data. Since accessing data from cache instead of memory storage reduces both access time and power consumption, devices that access more data from cache have greater battery life and range.

Increasing cache hits for synthetic aperture radar

Devices and techniques for triggering early termination of cooperating processes in a processor are described herein. A system includes multiple memory-compute nodes, wherein a memory-compute node comprises: event manager circuitry configured to establish a broadcast channel to receive event messages; and thread manager circuitry configured to organize a plurality of threads to perform portions of a cooperative task, wherein the plurality of threads each monitor the broadcast channel to receive event messages on the broadcast channel, and wherein upon achieving a threshold operation, the thread manager circuitry is to use the event manager circuitry to broadcast, on the broadcast channel, an event message indicating that the cooperative task is complete, causing other threads, in response to receiving the event message, to terminate execution of their respective portions of the cooperative task.

Mechanism to trigger early termination of cooperating processes

Disclosed in some examples are methods, systems, and machine-readable mediums that provide a memory allocation mechanism that evenly spreads the allocations for an application over all the MCs on the system, thus minimizing congestion and resulting in optimal application performance.

Alleviating memory hotspots on systems with multiple memory controllers

Disclosed in some examples are methods, systems, devices, and machine-readable mediums that use parallel hardware execution with software co-simulation to enable more advanced debugging operations on data flow architectures. Upon a halt to execution of a program thread, a state of the tiles that are executing the thread are saved and offloaded from the HTF to a host system. A developer may then examine this state on the host system to debug their program. Additionally, the state may be loaded into a software simulator that simulates the HTF hardware. This simulator allows for the developer to step through the code and to examine values to find bugs.

Growing community of inventors

Rowlett, TX, United States of America

Patrick Alan Estep