COMBINING READ REQUESTS HAVING SPATIAL LOCALITY

    公开(公告)号:US20240320167A1

    公开(公告)日:2024-09-26

    申请号:US18598722

    申请日:2024-03-07

    CPC classification number: G06F13/1668

    Abstract: Provided is a system comprising a communication interface between a host and a device, wherein the header of a first memory request transmitted on the forward link of the communication interface encodes, in a bit vector, addresses to be read for a plurality of second memory requests. Combining one or more read requests with another request such that a single request header is transmitted for a plurality of respective requests provides for more efficient use of the forward link bandwidth. Corresponding methods are also described.

    PARALLEL RAS CHANNELS IN CXL MEMORY DEVICE
    3.
    发明公开

    公开(公告)号:US20240345982A1

    公开(公告)日:2024-10-17

    申请号:US18444550

    申请日:2024-02-16

    CPC classification number: G06F13/4221 G06F13/1642

    Abstract: A memory device comprises a plurality of backend interfaces that are each configured to connect to a respective media device (e.g., DDR, LPDDR DRAM), a plurality of reliability, availability and serviceability (RAS) channel datapaths with each RAS channel datapath connected to one or more backend interfaces, one or more caches that are each connected to at least one RAS channel datapath, and control circuitry. The control circuitry is configured to: in response to receiving a memory access request for a memory location, search a cache of the one or more caches for the requested memory location; and when, in response to the search, the requested memory location is not found in the cache, obtain the requested memory location from a media device connected to the at least one RAS channel datapath. Corresponding methods are also described.

    ENCODING AND COMPRESSING BITS WITH WRITE-X FEATURE IN CXL

    公开(公告)号:US20240184477A1

    公开(公告)日:2024-06-06

    申请号:US18349053

    申请日:2023-07-07

    Inventor: Nikesh AGARWAL

    CPC classification number: G06F3/0655 G06F3/0604 G06F3/0673

    Abstract: In a computer host system, a system and method to compress the transmission between the central processing unit (CPU) and the dynamic random access memory (DRAM) of either of an extended consecutive series of ‘0’ bits or an extended consecutive series of ‘1’ bits. The CPU or a Compute Express Link (CXL) Initiator associated with the CPU identifies the consecutive strings of ‘0’ bits or ‘1’ bits. The CPU or the CXL Initiator sets data flags in a FLIT data structure, using just two bits or four bits to indicate the strings. The data structure is sent to a CXL memory, which interprets the flags and constructs the extended series of ‘0’ bits or extended series of ‘1’ bits.

    DIFFERENTIATED QOS IN PARALLEL CACHED RAS CHANNELS IN MEMORY DEVICES

    公开(公告)号:US20240330182A1

    公开(公告)日:2024-10-03

    申请号:US18444552

    申请日:2024-02-16

    CPC classification number: G06F12/0802

    Abstract: A memory device comprises a plurality of backend interfaces that are each configured to connect to a respective media device (e.g., DDR, LPDDR DRAM), a plurality of reliability, availability and serviceability (RAS) channel datapaths with each RAS channel datapath connected to one or more backend interfaces, one or more caches that are each connected to at least one RAS channel datapath, and control circuitry. The control circuitry is configured to: in response to receiving a memory access request for a memory location, search a cache of the one or more caches for the requested memory location; and when, in response to the search, the requested memory location is not found in the cache, obtain the requested memory location from a media device connected to the at least one RAS channel datapath. Corresponding methods are also described.

    FRAME PACKING USING STORED TEMPLATES
    6.
    发明公开

    公开(公告)号:US20240281399A1

    公开(公告)日:2024-08-22

    申请号:US18444545

    申请日:2024-02-16

    CPC classification number: G06F13/4221 G06F2213/0026

    Abstract: A method performed by a protocol controller for packing a frame includes selecting, based on current contents of at least one message buffer, a stored packing template, and packing the frame in accordance with the selected packing template. The packing comprises packing each slot of the frame with a respective request (e.g., read request, write request) from the message buffer in accordance with the selected packing template. The template is selected from a plurality of stored packing templates. Associated host devices on which the protocol controller is arranged are also described.

Patent Agency Ranking