SEMICONDUCTOR ASSEMBLIES WITH UNDERFILL SQUEEZE-UP, AND METHODS FOR MAKING THE SAME

    公开(公告)号:US20250157828A1

    公开(公告)日:2025-05-15

    申请号:US18896782

    申请日:2024-09-25

    Abstract: A semiconductor device assembly is provided. The assembly includes a substrate and a stack of semiconductor devices. The stack of semiconductor devices includes core semiconductor devices and a top semiconductor device disposed at the top of the stack. Each core device has a first thickness. The top device has a second thickness that is greater than the first thickness. Every device in the stack has a gap beneath it, with underfill material filling every gap and covering the sides of the core semiconductor devices. The underfill material has a squeeze-out region protruding away from the stack a first distance, and a squeeze-up region extending up the top semiconductor device a second distance. The second distance measures at least the same as the height of the gap beneath the devices in the stack.

    APPARATUSES AND METHODS FOR GENERATING DYNAMIC UNIQUE IDENTIFIER ADDRESSES IN A MEMORY FOR I3C PROTOCOL

    公开(公告)号:US20250156351A1

    公开(公告)日:2025-05-15

    申请号:US18908554

    申请日:2024-10-07

    Abstract: A memory module control hub includes a first priority logic circuit configured to receive an in-band interrupt (IBI) message from a memory device having a unique identifier and configured to set a first priority flag based on a category of the IBI message, and a second priority logic circuit configured to receive the IBI message from the memory device and configured to set a second priority flag based on the category of the IBI message. The memory module control hub further includes a dynamic identifier assignment circuit configured to adjust priority bits of the unique identifier based on whether the first or second priority flags are set.

    MEMORY ALLOCATION FOR A BENCHMARK TEST

    公开(公告)号:US20250156296A1

    公开(公告)日:2025-05-15

    申请号:US18929369

    申请日:2024-10-28

    Abstract: Methods, systems, and devices for memory allocation for a benchmark test are described. A memory system may be configured to allocate and deallocate portions of a volatile memory for specific uses based on detecting the occurrence of a benchmark testing operation. For example, the memory system may be configured to detect the occurrence of a benchmark testing operation based on the occurrence of one or more conditions. After detecting the benchmark testing operation, the memory system may deallocate a portion of the volatile memory associated with multiple-level cell accesses and may allocate (e.g., reallocate) the portion for storing additional logical-to-physical mappings.

    READ COUNTER FOR QUALITY OF SERVICE DESIGN

    公开(公告)号:US20250156123A1

    公开(公告)日:2025-05-15

    申请号:US19020825

    申请日:2025-01-14

    Abstract: Methods, systems, and devices for a read counter for quality of service design are described. First commands may be assigned to a first queue of a memory die of a memory sub-system, wherein the first queue is associated with a first priority level. The memory die may include a second queue associated with a second priority level different from the first priority level, the second queue comprising one or more second commands assigned. Based at least in part on a counter associated with the first queue and the first and second priority levels, it may be determined that a threshold number of the first commands of the first queue have issued without a command from the one or more second commands having issued. A command from the second commands may issue before issuing a next command of the first commands based at least in part on the counter.

    METHOD OF ORGANIZING A PROGRAMMABLE ATOMIC UNIT INSTRUCTION MEMORY

    公开(公告)号:US20250156098A1

    公开(公告)日:2025-05-15

    申请号:US19022852

    申请日:2025-01-15

    Inventor: Tony M. Brewer

    Abstract: Disclosed in some examples, are methods, systems, devices, and machine readable mediums that store instructions for programmable atomic transactions in a memory of the programmable atomic unit prior to execution of the programmable atomic transaction. The memory in some examples may be an instruction RAM. The memory in some examples may be partitioned into partitions of a fixed size that stores a same number of instructions. Each programmable atomic transaction may use one or more contiguously located instruction partitions. By loading the instructions ahead of time, the instructions are ready for execution when the transaction is requested.

    ADAPTIVE CONTROL FOR IN-MEMORY VERSIONING

    公开(公告)号:US20250156092A1

    公开(公告)日:2025-05-15

    申请号:US19022888

    申请日:2025-01-15

    Abstract: Disclosed in some examples are systems, devices, machine-readable mediums, and methods for customizing an in-memory versioning mode for each memory location according to a predicted access behavior to optimize memory device performance. Usage data in a previous time period may be utilized along with policy rules to determine whether to configure a particular memory address as a zero copy or direct copy mode. For example, memory addresses that are read frequently may be configured as direct copy mode to reduce the read latency penalty. This improves the functioning of the memory system by reducing read latency for memory addresses that are frequently read but written to less frequently, and reduces write latency for memory locations that are frequently written to, but not read as frequently.

    PERFORMANCE ALLOCATION AMONG USERS FOR ACCESSING NON-VOLATILE MEMORY DEVICES

    公开(公告)号:US20250156079A1

    公开(公告)日:2025-05-15

    申请号:US19025733

    申请日:2025-01-16

    Inventor: Alex Frolikov

    Abstract: A computer having a plurality of accounts and a storage device having a host interface, a controller, non-volatile storage media, and firmware. An account is configured with at least a predetermined speed in accessing the non-volatile storage media by allocating a number of input/output submission queues in the buffer area of the host. The number can be determined from a ratio between the predetermined speed configured for the account and a saturated speed of the storage device with sufficient submission queues. Data access requests from the account are evenly distributed to the submission queues allocated for the exclusive use by the account; and the controller, configured via the firmware, processes with equal priority the submission queues configured for the storage device. Thus, the account can have at least the predetermined speed in accessing the non-volatile storage media, regardless of how other accounts access the storage device.

Patent Agency Ranking