# US 2023/0274774 A1 · Effective DRAM Interleaving For Asymmetric Size Channels Or Ranks While Supporting Improved Partial Array Self-Refresh

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2023/0274774 A1
- Document ID: US20230274774A1
- Status: Published application
- Kind: A1
- Application number: 18/314,167
- Filed: 2023-05-09
- Published: 2023-08-31
- Earliest claimed: 2021-02-11
- Assignees: QUALCOMM Incorporated
- Applicants: QUALCOMM Incorporated
- Inventors: Kunal DESAI; Saurabh JAISWAL; Vikrant KUMAR; Swaraj SHA; Dharmesh PARIKH
- Web page: https://patentgrep.com/patent/US20230274774A1

## CPC

- G06F 12/0607: {Interleaved addressing}
- G11C 11/40618: {Refresh operations over multiple banks or interleaving}
- G06F 12/06: Addressing a physical block of locations, e.g. base addressing, module addressing, memory dedication (G06F12/08 takes precedence)
- G06F 2212/1028: Power efficiency
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G11C: STATIC STORES (semiconductor memory devices H10B)

## Abstract

Various embodiments include methods and devices for portion interleaving for asymmetric size memory portions. Embodiments may include determining an asymmetric memory portion assignment for an interleave unit, determining a consumed address space offset for consumed address space of a memory, modifying an address of the interleave unit using the consumed address space offset, and assigning the interleave unit to an interleave granule in the asymmetric memory portion using the modified address in a compact manner before assigning another interleave unit to another interleave granule. Embodiments may include receiving an address of memory access request in a memory, mapping the address to an interleave granule in an asymmetric memory portion, assigning consecutive interleave units to the interleave granule while the interleave granule has unused space before assigning another interleave unit to another interleave granule, and implementing the memory access request at the mapped address.

## Claims

### Claim 1

A method of portion interleaving for asymmetric size memory portions of a memory, comprising:
receiving an address of a memory access request in the memory;
mapping the address to a first interleave granule in a first asymmetric memory portion;
assigning consecutive interleave units to the first interleave granule while the first interleave granule has unused space before assigning another interleave unit to another interleave granule, wherein at least a first interleave unit of the consecutive interleave units corresponds to the address; and
implementing the memory access request at the mapped address within the first asymmetric memory portion.

### Claim 2 (depends on 1)

The method of claim 1, wherein mapping the address to the first interleave granule in the first asymmetric memory portion comprises:
determining a consumed address space offset for consumed address space of the memory in a second asymmetric memory portion; and
modifying the address using the consumed address space offset.

### Claim 3 (depends on 2)

The method of claim 2, wherein modifying the address using the consumed address space offset comprises subtracting the consumed address space offset from the address.

### Claim 4 (depends on 1)

The method of claim 1, wherein mapping the address to the first interleave granule comprises determining an asymmetric memory portion assignment of the address.

### Claim 5 (depends on 4)

The method of claim 4, wherein determining the asymmetric memory portion assignment of the address comprises:
determining an asymmetric memory portion capacity ratio of asymmetric size memory portions including the first asymmetric memory portion;
determining a combined asymmetric memory portion capacity of the asymmetric size memory portions;
determining a value of a function using the address and the combined asymmetric memory portion capacity; and
comparing the value of the function to a value of the asymmetric memory portion capacity ratio of asymmetric size memory portions representing an asymmetric size memory portion of the asymmetric size memory portions.

### Claim 6 (depends on 1)

The method of claim 1, wherein assigning consecutive interleave units to the first interleave granule comprises assigning a first consecutive interleave unit of the consecutive interleave units linearly to a second interleave unit of the consecutive interleave units.

### Claim 7 (depends on 1)

The method of claim 1, wherein assigning consecutive interleave units to the first interleave granule comprises assigning a first consecutive interleave unit of the consecutive interleave units nonlinearly to a second interleave unit of the consecutive interleave units.

### Claim 8 (depends on 1)

The method of claim 1, wherein assigning consecutive interleave units to the first interleave granule comprises assigning the consecutive interleave units to a first refresh segment for a dynamic random-access memory refresh control policy while the first refresh segment has unused space before assigning another interleave unit to another refresh segment.

### Claim 9

A computing device, comprising a processing device configured to perform operations comprising:
receiving an address of a memory access request in a memory;
mapping the address to a first interleave granule in a first asymmetric memory portion;
assigning consecutive interleave units to the first interleave granule while the first interleave granule has unused space before assigning another interleave unit to another interleave granule, wherein at least a first interleave unit of the consecutive interleave units corresponds to the address; and
implementing the memory access request at the mapped address within the first asymmetric memory portion.

### Claim 10 (depends on 9)

The computing device of claim 9, wherein the processing device is configured to perform operations such that mapping the address to the first interleave granule in the first asymmetric memory portion comprises:
determining a consumed address space offset for consumed address space of the memory in a second asymmetric memory portion; and
modifying the address using the consumed address space offset.

### Claim 11 (depends on 10)

The computing device of claim 10, wherein the processing device is configured to perform operations such that modifying the address using the consumed address space offset comprises subtracting the consumed address space offset from the address.

### Claim 12 (depends on 9)

The computing device of claim 9, wherein the processing device is configured to perform operations such that mapping the address to the first interleave granule comprises determining an asymmetric memory portion assignment of the address.

### Claim 13 (depends on 12)

The computing device of claim 12, wherein the processing device is configured to perform operations such that determining the asymmetric memory portion assignment of the address comprises:
determining an asymmetric memory portion capacity ratio of asymmetric size memory portions including the first asymmetric memory portion;
determining a combined asymmetric memory portion capacity of the asymmetric size memory portions;
determining a value of a function using the address and the combined asymmetric memory portion capacity; and
comparing the value of the function to a value of the asymmetric memory portion capacity ratio of asymmetric size memory portions representing an asymmetric size memory portion of the asymmetric size memory portions.

### Claim 14 (depends on 9)

The computing device of claim 9, wherein the processing device is configured to perform operations such that assigning consecutive interleave units to the first interleave granule comprises assigning a first consecutive interleave unit of the consecutive interleave units linearly to a second interleave unit of the consecutive interleave units.

### Claim 15 (depends on 9)

The computing device of claim 9, wherein the processing device is configured to perform operations such that assigning consecutive interleave units to the first interleave granule comprises assigning a first consecutive interleave unit of the consecutive interleave units nonlinearly to a second interleave unit of the consecutive interleave units.

### Claim 16 (depends on 9)

The computing device of claim 9, wherein the processing device is configured to perform operations such that assigning consecutive interleave units to the first interleave granule comprises assigning the consecutive interleave units to a first refresh segment for a dynamic random-access memory refresh control policy while the first refresh segment has unused space before assigning another interleave unit to another refresh segment.

### Claim 17

A computing device, comprising:
means for receiving an address of a memory access request in a memory;
means for mapping the address to a first interleave granule in a first asymmetric memory portion;
means for assigning consecutive interleave units to the first interleave granule while the first interleave granule has unused space before assigning another interleave unit to another interleave granule, wherein at least a first interleave unit of the consecutive interleave units corresponds to the address; and
means for implementing the memory access request at the mapped address within the first asymmetric memory portion.

### Claim 18 (depends on 17)

The computing device of claim 17, wherein means for mapping the address to the first interleave granule in the first asymmetric memory portion comprises:
means for determining a consumed address space offset for consumed address space of the memory in a second asymmetric memory portion; and
means for modifying the address using the consumed address space offset.

### Claim 19 (depends on 18)

The computing device of claim 18, wherein means for modifying the address using the consumed address space offset comprises means for subtracting the consumed address space offset from the address.

### Claim 20 (depends on 17)

The computing device of claim 17, wherein means for mapping the address to the first interleave granule comprises means for determining an asymmetric memory portion assignment of the address.

### Claim 21 (depends on 20)

The computing device of claim 20, wherein means for determining the asymmetric memory portion assignment of the address comprises:
means for determining an asymmetric memory portion capacity ratio of asymmetric size memory portions including the first asymmetric memory portion;
means for determining a combined asymmetric memory portion capacity of the asymmetric size memory portions;
means for determining a value of a function using the address and the combined asymmetric memory portion capacity; and
means for comparing the value of the function to a value of the asymmetric memory portion capacity ratio of asymmetric size memory portions representing an asymmetric size memory portion of the asymmetric size memory portions.

### Claim 22 (depends on 17)

The computing device of claim 17, wherein means for assigning consecutive interleave units to the first interleave granule comprises means for assigning a first consecutive interleave unit of the consecutive interleave units linearly to a second interleave unit of the consecutive interleave units.

### Claim 23 (depends on 17)

The computing device of claim 17, wherein means for assigning consecutive interleave units to the first interleave granule comprises means for assigning a first consecutive interleave unit of the consecutive interleave units nonlinearly to a second interleave unit of the consecutive interleave units.

### Claim 24 (depends on 17)

The computing device of claim 17, wherein means for assigning consecutive interleave units to the first interleave granule comprises means for assigning the consecutive interleave units to a first refresh segment for a dynamic random-access memory refresh control policy while the first refresh segment has unused space before assigning another interleave unit to another refresh segment.

### Claim 25

A non-transitory processor-readable medium having stored thereon processor-executable instructions configured to cause a processing device to perform operations comprising:
receiving an address of a memory access request in a memory;
mapping the address to a first interleave granule in a first asymmetric memory portion;
assigning consecutive interleave units to the first interleave granule while the first interleave granule has unused space before assigning another interleave unit to another interleave granule, wherein at least a first interleave unit of the consecutive interleave units corresponds to the address; and
implementing the memory access request at the mapped address within the first asymmetric memory portion.

### Claim 26 (depends on 25)

The non-transitory processor-readable medium of claim 25, wherein the stored processor-executable instructions are configured to cause the processing device to perform operations such that mapping the address to the first interleave granule in the first asymmetric memory portion comprises:
determining a consumed address space offset for consumed address space of the memory in a second asymmetric memory portion; and
modifying the address using the consumed address space offset.

### Claim 27 (depends on 26)

The non-transitory processor-readable medium of claim 26, wherein the stored processor-executable instructions are configured to cause the processing device to perform operations such that modifying the address using the consumed address space offset comprises subtracting the consumed address space offset from the address.

### Claim 28 (depends on 25)

The non-transitory processor-readable medium of claim 25, wherein the stored processor-executable instructions are configured to cause the processing device to perform operations such that mapping the address to the first interleave granule comprises determining an asymmetric memory portion assignment of the address.

### Claim 29 (depends on 28)

The non-transitory processor-readable medium of claim 28, wherein the stored processor-executable instructions are configured to cause the processing device to perform operations such that determining the asymmetric memory portion assignment of the address comprises:
determining an asymmetric memory portion capacity ratio of asymmetric size memory portions including the first asymmetric memory portion;
determining a combined asymmetric memory portion capacity of the asymmetric size memory portions;
determining a value of a function using the address and the combined asymmetric memory portion capacity; and
comparing the value of the function to a value of the asymmetric memory portion capacity ratio of asymmetric size memory portions representing an asymmetric size memory portion of the asymmetric size memory portions.

### Claim 30 (depends on 25)

The non-transitory processor-readable medium of claim 25, wherein the stored processor-executable instructions are configured to cause the processing device to perform operations such that assigning consecutive interleave units to the first interleave granule comprises assigning a first consecutive interleave unit of the consecutive interleave units linearly to a second interleave unit of the consecutive interleave units.

### Claim 31 (depends on 25)

The non-transitory processor-readable medium of claim 25, wherein the stored processor-executable instructions are configured to cause the processing device to perform operations such that assigning consecutive interleave units to the first interleave granule comprises assigning a first consecutive interleave unit of the consecutive interleave units nonlinearly to a second interleave unit of the consecutive interleave units.

### Claim 32 (depends on 25)

The non-transitory processor-readable medium of claim 25, wherein the stored processor-executable instructions are configured to cause the processing device to perform operations such that assigning consecutive interleave units to the first interleave granule comprises assigning the consecutive interleave units to a first refresh segment for a dynamic random-access memory refresh control policy while the first refresh segment has unused space before assigning another interleave unit to another refresh segment.
