-
公开(公告)号:US12079127B2
公开(公告)日:2024-09-03
申请号:US17208825
申请日:2021-03-22
Applicant: CoreSecure Technologies, LLC
Inventor: Ruby B. Lee , Fangfei Liu
IPC: G06F12/08 , G06F12/0802 , G06F12/0862 , G06F12/0868 , G06F12/14
CPC classification number: G06F12/0862 , G06F12/0802 , G06F12/0868 , G06F12/14 , G06F2212/1052 , G06F2212/602
Abstract: Systems and methods for random fill caching and prefetching for secure cache memories are provided. The system dynamically de-correlates fetching a cache line to the processor from filling the cache with this cache line, due to a demand memory access, in order to provide greater security from information leakage due to cache side-channel attacks on cache memories. The system includes a random fill engine which includes a random number generator and an adjustable random fill window. Also provided is an adaptive random fill caching system which dynamically adapts the random fill window to a wide variety of computational workloads. Systems and methods for cache prefetching to improve system performance using adaptive random fill prefetching and random fill prefetching are also provided.
-
公开(公告)号:US12061919B2
公开(公告)日:2024-08-13
申请号:US18460374
申请日:2023-09-01
Applicant: Dynavisor, Inc.
Inventor: Sreekumar R. Nair
IPC: G06F9/455 , C07K16/28 , G06F3/06 , G06F12/0868 , G06F12/1081 , G06F13/28 , A61K39/00 , G06F9/4401 , G06F12/084 , G06F12/0864
CPC classification number: G06F9/45533 , C07K16/2803 , C07K16/2887 , C07K16/2896 , G06F3/061 , G06F3/0664 , G06F3/0665 , G06F3/0685 , G06F3/0689 , G06F9/45558 , G06F12/0868 , G06F12/1081 , G06F13/28 , A61K2039/505 , A61K2039/507 , C07K2317/21 , C07K2317/24 , C07K2317/33 , C07K2317/52 , C07K2317/56 , C07K2317/565 , C07K2317/73 , C07K2317/76 , G06F3/0673 , G06F9/4411 , G06F2009/45579 , G06F12/084 , G06F12/0864 , G06F2212/152 , G06F2212/2532 , G06F2212/314 , G06F2212/463
Abstract: A system and method for providing dynamic I/O virtualization is herein disclosed. According to one embodiment, a device capable of performing hypervisor-agnostic and device-agnostic I/O virtualization includes a host computer interface, memory, I/O devices (GPU, disk, NIC), and efficient communication mechanisms for virtual machines to communicate their intention to perform I/O operations on the device. According to one embodiment, the communication mechanism may use shared memory. According to some embodiments, the device may be implemented purely in hardware, in software, or using a combination of hardware and software. According to some embodiments, the device may share its memory with guest processes to perform optimizations including but not limited to a shared page cache and a shared heap.
-
公开(公告)号:US12050537B2
公开(公告)日:2024-07-30
申请号:US17856918
申请日:2022-07-01
Applicant: Samsung Electronics Co., Ltd.
Inventor: Oscar P. Pinto
IPC: G06F12/0868 , G06F9/30 , G06F12/02 , G06F30/331
CPC classification number: G06F12/0868 , G06F9/30145 , G06F12/0246 , G06F30/331
Abstract: A method of streaming between a storage device and a secondary device includes receiving, by the storage device, from the secondary device, a memory read request command including a memory address of the storage device corresponding to a stream identity, the stream identity being unique between the storage device and the secondary device; streaming, by the storage device, data between the storage device and the secondary device by transferring the data corresponding to the memory address of the storage device to the secondary device; determining, by the storage device, that the data requested by the secondary device in the memory read request command is transferred to the secondary device; and ending, by the storage device, the streaming between the storage device and the secondary device.
-
公开(公告)号:US20240241830A1
公开(公告)日:2024-07-18
申请号:US18413211
申请日:2024-01-16
Applicant: Akeana, Inc.
Inventor: Sanjay Patel , Yogesh Shamkant Thombre
IPC: G06F12/0817 , G06F12/0868 , G06F12/0873
CPC classification number: G06F12/0828 , G06F12/0868 , G06F12/0873
Abstract: Techniques for cache management based on cache management using memory queues are disclosed. A plurality of processor cores is accessed. The plurality of processor cores comprises a coherency domain. Two or more processor cores within the plurality of processor cores generate read operations for a common memory structure coupled to the plurality of processor cores. Coherency for the coherency domain is managed using a compute coherency block (CCB). The CCB includes a memory queue for controlling transfer of cache lines determined by the CCB. The memory queue includes an evict queue and a miss queue. Snoop requests are generated by the CCB. The snoop requests correspond to entries in the memory queue. Cache lines are transferred between the CCB and a bus interface unit. The transferring is controlled by the memory queue. The bus interface unit controls memory accesses.
-
公开(公告)号:US20240160587A1
公开(公告)日:2024-05-16
申请号:US18513246
申请日:2023-11-17
Applicant: Rambus Inc.
Inventor: Frederick A. Ware , Kenneth L. Wright , John Eric Linstadt , Craig Hampel
IPC: G06F13/16 , G06F3/06 , G06F11/10 , G06F12/0868 , G06F12/0888 , G06F12/0895 , G06F13/28 , G11C7/10 , G11C29/52
CPC classification number: G06F13/1678 , G06F3/0604 , G06F3/0613 , G06F3/0619 , G06F3/0634 , G06F3/0656 , G06F3/0673 , G06F11/1004 , G06F11/1068 , G06F12/0868 , G06F12/0888 , G06F12/0895 , G06F13/28 , G11C7/10 , G11C29/52 , G06F2212/1016 , G06F2212/1032 , G06F2212/403
Abstract: Memory controllers, devices, modules, systems and associated methods are disclosed. In one embodiment, a memory module includes a pin interface for coupling to a bus. The bus has a first width. The module includes at least one storage class memory (SCM) component and at least one DRAM component. The memory module operates in a first mode that utilizes all of the first width, and in a second mode that utilizes less than all of the first width.
-
公开(公告)号:US11977490B2
公开(公告)日:2024-05-07
申请号:US17755654
申请日:2020-10-27
Applicant: Idemia Identity & Security France
IPC: G06F12/0868 , G06F12/0804 , G06F12/0817
CPC classification number: G06F12/0868 , G06F12/0804 , G06F12/0822 , G06F2212/1016
Abstract: A method for executing a transaction for a processor associated with a persistent memory and with a cache memory, the cache memory comprising cache lines associated with respective states, including:
if a cache line is associated with a state allowing data to be copied directly:
copying data to the cache line;
associating the line with a state representative of an allocation to transaction data;
otherwise:
flushing lines associated with a state representative of an allocation to external data and associating them with a state indicating that content of the lines has not been modified;
copying data to the flushed lines;
associating these lines with a state representative of an allocation to transaction data.-
公开(公告)号:US20240126700A1
公开(公告)日:2024-04-18
申请号:US18391059
申请日:2023-12-20
Applicant: RELATIVITY ODA LLC
Inventor: Jeffrey Hibser , Mohammad Amer Ghazal , Steven Engelhardt , Michael R. Gayeski , Brandon Michelsen , Ankit Khandelwal , Ranga Sankar , Robert A. Skinner
IPC: G06F12/0868 , G06F3/06 , G06F12/0802 , G06F16/13 , G06F16/93
CPC classification number: G06F12/0868 , G06F3/0604 , G06F3/0659 , G06F3/067 , G06F12/0802 , G06F16/13 , G06F16/93 , G06F2212/60 , G06F2212/6042
Abstract: Systems and methods for object-based data storage are provided. There may be a read/write cache configured to cache objects to be written to an object-based data storage. A document in the read/write cache may have a lock state set to unlocked, thereby allowing the document to be deleted. Or, the document in the read/write cache may have a lock state set to locked, thereby preventing deletion of the document.
-
公开(公告)号:US11947463B2
公开(公告)日:2024-04-02
申请号:US18158953
申请日:2023-01-24
Inventor: Kwang-Won Koh , Chang-Dae Kim , Kang-Ho Kim
IPC: G06F12/08 , G06F12/0862 , G06F12/0868 , G06F12/0871 , G06F12/0882 , G06F12/0891
CPC classification number: G06F12/0882 , G06F12/0862 , G06F12/0868 , G06F12/0871 , G06F12/0891
Abstract: Disclosed herein is an apparatus for managing disaggregated memory, which is located in a virtual machine in a physical node. The apparatus is configured to select, depending on the proportion of valid pages, direct transfer between remote memory units or indirect transfer via local memory for each of the memory pages of the source remote memory to be migrated, among at least one remote memory unit used by the virtual machine, to transfer the memory pages of the source remote memory to target remote memory based on the direct transfer or the indirect transfer, and to release the source remote memory.
-
公开(公告)号:US11928246B2
公开(公告)日:2024-03-12
申请号:US17346908
申请日:2021-06-14
Applicant: Micron Technology, Inc.
Inventor: Alberto Troia , Antonino Mondello
IPC: H04L29/06 , G06F12/0868 , G06F12/0882 , G06F12/14 , G06F13/16 , G06F21/64 , G06F21/78
CPC classification number: G06F21/64 , G06F12/0868 , G06F12/0882 , G06F12/1408 , G06F12/1441 , G06F13/1673 , G06F21/78 , G06F2212/1052
Abstract: Content within a memory device (e.g., a DRAM) may be secured in a customizable manner. Data can be secured and the memory device performance by be dynamically defined. In some examples, setting a data security level for a group of memory cells of a memory device may be based, at least in part, on a security mode bit pattern (e.g., a flag, flags, or indicator) in metadata read from or written to the memory device. Some examples include comparing a first signature (e.g., a digital signature) in metadata to a second value (e.g., an expected digital signature) to validate the first value in the metadata. The first value and the second value can be based, at least in part, on the data security level. Some examples include performing a data transfer operation in response to validation of the first and/or second values.
-
公开(公告)号:US11921638B2
公开(公告)日:2024-03-05
申请号:US17833219
申请日:2022-06-06
Applicant: Samsung Electronics Co., Ltd.
Inventor: Krishna T. Malladi , Hongzhong Zheng
IPC: G06F12/08 , G06F12/0866 , G06F12/12 , G06F12/0868 , G06F12/0897
CPC classification number: G06F12/0866 , G06F12/0868 , G06F12/0897 , G06F12/12 , G06F2212/1041 , G06F2212/225 , G06F2212/283
Abstract: According to some embodiments of the present invention, there is provided a hybrid cache memory for a processing device having a host processor, the hybrid cache memory comprising: a high bandwidth memory (HBM) configured to store host data; a non-volatile memory (NVM) physically integrated with the HBM in a same package and configured to store a copy of the host data at the HBM; and a cache controller configured to be in bi-directional communication with the host processor, and to manage data transfer between the HBM and NVM and, in response to a command received from the host processor, to manage data transfer between the hybrid cache memory and the host processor.
-
-
-
-
-
-
-
-
-