Unified stateless compression system for universally consumable compression

US12469099B2 · US · B2

Patent metadata
FieldValue
Publication numberUS-12469099-B2
Application numberUS-202117561666-A
CountryUS
Kind codeB2
Filing dateDec 23, 2021
Priority dateDec 23, 2021
Publication dateNov 11, 2025
Grant dateNov 11, 2025

How to read this patent

A practical reading order for non-experts. Skip the full description unless you need deep technical detail.

  1. Title

    What the patent document calls the invention.

  2. Abstract

    A short plain-language summary of the technical disclosure.

  3. Assignees and inventors

    Who owns or filed the patent and who is credited as inventor.

  4. Key dates

    Filing, priority, publication, and grant dates set the timeline.

  5. First independent claim

    The legal scope of protection — read this for what is actually claimed.

  6. CPC / IPC classifications

    Technology tags used to group this patent with similar filings.

  7. Citations and related patents

    Prior art links and similar publications in this corpus.

Abstract

Official abstract text for this publication.

A system includes a compression engine that stores the compression format information embedded in the compressed data. The compression format information can be included in a header that includes compression control surface (CCS) information. The system includes a shared memory to store compressed data for multiple hardware pipelines, where blocks of the compressed data have a common memory footprint and the compression header. The compression engine can compress data to store in the shared memory including generation of the header. The compression engine can decompress data read from the shared memory, including identification of the compression format from the header.

First claim

Opening claim text (preview).

What is claimed is: 1 . A graphics processor, comprising: a memory controller to couple to a shared memory to store compressed data for multiple graphics components, wherein blocks of the compressed data have a common memory footprint where a starting location of the blocks in the shared memory is based on a full block size regardless of compression ratio, and wherein the blocks include a header with compression format information and compression control surface (CCS) information; and a compression engine to compress data to store in the shared memory and decompress data read from the shared memory, wherein to compress the data to store includes generation of the header and wherein to decompress the data read includes identification of the compression format from the header, wherein the compression engine is to compress the data prior to transmission of the data to the shared memory, where transmission includes a fixed-size packet with a variable amount of data based on compression levels of the data. 2 . The graphics processor of claim 1 , wherein the compression format information comprises a value for a lookup table to indicate a compression type. 3 . The graphics processor of claim 1 , wherein the compression engine comprises a compressor/decompressor core and a control plane cache to store CCS information. 4 . The graphics processor of claim 3 , wherein the compression engine is to receive data to be compressed from one of the multiple graphics components, including an indicator that the received data is to be compressed in a stateless format, and in response to the indicator, the compression engine is to generate the header with the compression format information. 5 . The graphics processor of claim 1 , wherein the blocks of the compressed data have a unified memory layout. 6 . The graphics processor of claim 5 , wherein the unified memory layout comprises a row major format layout. 7 . The graphics processor of claim 1 , further comprising: a communication fabric between the graphics components, wherein the communication fabric is to support multiple data transfer sizes based on block compression ratio. 8 . The graphics processor of claim 7 , wherein the communication fabric supports transfer of compressed data and transfer of uncompressed data. 9 . The graphics processor of claim 1 , wherein the compression engine comprises a first compression engine, and further comprising: a second compression engine, wherein the first compression engine and the second compression engine are at different layers of the graphics processor. 10 . A computer system comprising: a central processing unit (CPU) to execute general computations; a graphics unit coupled to the CPU, the graphics unit including: a memory controller to couple to a shared memory to store compressed data for multiple graphics components, wherein blocks of the compressed data have a common memory footprint where a starting location of the blocks in the shared memory is based on a full block size regardless of compression ratio, and wherein the blocks include a header with compression format information and compression control surface (CCS) information; and a compression engine to compress data to store in the shared memory and decompress data read from the shared memory, wherein to compress the data to store includes generation of the header and wherein to decompress the data read includes identification of the compression format from the header, wherein the compression engine is to compress the data prior to transmission of the data to the shared memory, where transmission includes a fixed-size packet with a variable amount of data based on compression levels of the data. 11 . The computer system of claim 10 , wherein the compression format information comprises a value for a lookup table to indicate a compression type. 12 . The computer system of claim 10 , wherein the compression engine is to receive data to be compressed from one of the multiple graphics components, including an indicator that the received data is to be compressed in a stateless format, and in response to the indicator, the compression engine is to generate the header with the compression format information and the CCS information. 13 . The computer system of claim 10 , wherein the blocks of the compressed data have a unified memory layout, wherein the unified memory layout comprises a row major format layout. 14 . The computer system of claim 10 , further comprising: a communication fabric between the multiple graphics components, wherein the communication fabric is to support multiple data transfer sizes based on block compression ratio. 15 . The computer system of claim 14 , wherein the communication fabric supports transfer of compressed data and transfer of uncompressed data. 16 . The computer system of claim 10 , wherein the multiple graphics components comprise one or more of: a media pipeline; a color pipeline; a display pipeline; a video capture pipeline; or an artificial intelligence (AI) accelerator pipeline. 17 . The computer system of claim 10 , wherein the compression engine comprises a first compression engine, and further comprising: a second compression engine, wherein the first compression engine and the second compression engine are at different layers of the graphics unit. 18 . The computer system of claim 10 , further comprising: main system memory separate from the shared memory of the graphics unit; wherein the compression engine is to provide compression and decompression of data in the main system memory for access by the CPU. 19 . A method for compression, comprising: storing compressed data in a shared memory for multiple graphics components as blocks of compressed data have a common memory footprint where a starting location of the blocks in the shared memory is based on a full block size regardless of compression ratio, and the blocks include a header with compression format information and compression control surface (CCS) information; compressing data to store in the shared memory, including generating the header; and decompressing data read from the shared memory, including identifying the compression format from the header; wherein compressing the data comprises compressing the data prior to transmission of the data to the shared memory, where transmission includes a fixed-size packet with a variable amount of data based on compression levels of the data. 20 . The method of claim 19 , further comprising: transmitting blocks of compressed data between the graphics components with a communication fabric that supports multiple data transfer sizes based on block compression ratio. 21 . The method of claim 20 , wherein the communication fabric supports transfer of compressed data and transfer of uncompressed data.

Assignees

Inventors

Classifications

  • with a shared cache · CPC title

  • Processor architectures; Processor configuration, e.g. pipelining · CPC title

  • Compressed data · CPC title

  • G06T1/60Primary

    Memory management · CPC title

  • using memory downsizing methods · CPC title

Patent family

Related publications grouped by family.

External sources

Frequently asked questions

Answers are generated from the same data shown on this page.

What does patent US12469099B2 cover?
A system includes a compression engine that stores the compression format information embedded in the compressed data. The compression format information can be included in a header that includes compression control surface (CCS) information. The system includes a shared memory to store compressed data for multiple hardware pipelines, where blocks of the compressed data have a common memory foo…
Who is the assignee on this patent?
Intel Corp
What technology area does this patent fall under?
Primary CPC classification G06T1/60. Mapped technology areas include Physics.
When was this patent published?
Publication date Tue Nov 11 2025 00:00:00 GMT+0000 (Coordinated Universal Time) (B2). Legal status and post-grant events are not shown on this page.
What related patents are in patentsdb?
We list 12 related publications on this page (citations in our corpus or others sharing the same primary CPC).