SDRAM data allocation system and method utilizing dual bank storage and retrieval
AssigneeHewlett-Packard Company
InventorsJohn Dykstal, Byron A. Alcorn, Darel N. Emmot
Life of this patent
Estimating the term…
Abstract
A system and method for allocating data among first and second banks of at least one SDRAM, the data including first, second and third words to be accessed during consecutive read operations. The method includes the following steps: storing the first and third words within the first bank, and storing the second word within the second bank. The texture mapping computer graphics system includes a host computer with a main memory that stores texture data including a plurality of texels, and a local memory that stores at least a portion of the texture data. The local memory includes at least one SDRAM.
Claims15
A method for allocating data among first and second banks of at least one SDRAM, the data including first, second, and third word sequences to be accessed during consecutive read operations, the method comprising the steps of:
- storing the first and third word sequences in a common page within the first bank, the first and third word sequences belonging to a first set of data;
- and
- storing the second word sequence within the second bank, the second word sequence belonging to a second set of data, wherein the first set has a predefined correlation to the second set such that the first, second and third word sequences always will be accessed in that order.
A method for accessing first, second and third word sequences from a data storage system respectively during first, second and third consecutive read operations, the method comprising the steps of:
- accessing the first word sequence from a page of a first bank of at least one SDRAM during the first read operation;
- accessing the second word sequence from a second bank of the at least one SDRAM during the second read operation;
- and
- accessing the third word sequence from the page of the first bank of the at least one SDRAM during the third read operation, wherein the first and third word sequences belong to a first set of data, the second word sequence belongs to a second set of data, and the first set has a predefined correlation to the second set such that the first, second and third word sequences always will be accessed in that order.
A system for storing data including first, second and third word sequences to be accessed during consecutive read operations, the system comprising:
- at least one SDRAM, each SDRAM having first and second banks;
- wherein the first bank stores the first and third word sequences in a common page and the second bank stores the second word sequence, and wherein the first and third word sequences belong to a first set of data, the second word sequence belongs to a second set of data, and the first set has a predefined correlation to the second set such that the first, second and third word sequences always will be accessed in that order.
A method for allocating the first and second sets of data among first and second banks of at least one SDRAM comprising the steps of:
- dividing each of the first and second sets of data into at least first and second sub-sets of data;
- storing the first sub-set of the first set of data and the second sub-set of the second set of data within the first bank;
- and
- storing the second sub-set of the first set of data and the first sub-set of the second set of data within the second bank;
- wherein the first sub-set of the first set of data has a predefined correlation to the first sub-set of the second set of data such that the data always will be accessed sequentially from the first bank, then from the second bank, then again from the first bank without incurring a re-paging penalty of the SDRAM.
Dependencies are inferred from the claim text.