# US 2016/0239344 A1 · Process Scheduling to Improve Victim Cache Mode

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

- Number: US 2016/0239344 A1
- Document ID: US20160239344A1
- Status: Published application
- Kind: A1
- Application number: 14/623,554
- Filed: 2015-02-17
- Published: 2016-08-18
- Earliest claimed: 2015-02-17
- Assignees: QUALCOMM Incorporated
- Applicants: QUALCOMM Incorporated
- Inventors: Feng Wang; George Patsilaras
- Web page: https://patentgrep.com/patent/US20160239344A1

## CPC

- G06F 9/5016: {the resource being the memory}
- G06F 12/0846: Cache with multiple tag or data arrays being simultaneously accessible
- G06F 9/5044: {considering hardware capabilities}
- G06F 9/5088: {involving task migration}
- G06F 12/084: with a shared cache
- G06F 12/0811: with multilevel cache hierarchies
- G06F 2209/502: Proximity
- G06F 2209/505: Clust
- G06F 2212/1024: Latency reduction
- G06F 2212/502: using adaptive policy
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Aspects include computing devices, systems, and methods for implementing scheduling an execution process to an execution processor cluster to take advantage of reduced latency with a victim cache. The computing device may determine a first processor cluster with a first remote shared cache memory having an available shared cache memory space. To properly schedule the execution process, the computing device may determine a second processor cluster with a lower latency to the first remote shared cache memory than an execution processor cluster scheduled with the execution process. The second processor cluster may be scheduled the execution process, thus becoming the execution processor cluster, based on a size of the available shared cache memory space and the latency of the second processor cluster to the first remote shared cache memory. The available shared cache memory space may be used as the victim cache for the execution process.

## Claims

### Claim 1

A method for scheduling an execution process to an execution processor cluster to take advantage of reduced latency with a victim cache, comprising:
determining a first processor cluster with a first remote shared cache memory having an available shared cache memory space;
determining a second processor cluster with a lower latency to the first remote shared cache memory than a first execution processor cluster scheduled with the execution process;
scheduling the execution process to the second processor cluster as a second execution processor cluster based on a size of the available shared cache memory space and the latency of the second processor cluster to the first remote shared cache memory; and
using the available shared cache memory space as the victim cache for the execution process.

### Claim 2 (depends on 1)

The method of claim 1, wherein:
determining a first processor cluster with a first remote shared cache memory having an available shared cache memory space comprises determining the first processor cluster with the first remote shared cache memory having a highest amount of available shared cache memory space;
determining a second processor cluster with a lower latency to the first remote shared cache memory than a first execution processor cluster scheduled with the execution process comprises determining the second processor cluster with a lowest latency to the first remote shared cache memory; and
scheduling the execution process to the second processor cluster as a second execution processor cluster based on a size of the available shared cache memory space and the latency of the second processor cluster to the first remote shared cache memory comprises scheduling the execution process to the second processor cluster as a second execution processor cluster based on the second processor cluster having the lowest latency to the first remote shared cache memory having the highest amount of available shared cache memory space.

### Claim 3 (depends on 1)

The method of claim 1, further comprising:
determining whether a process is scheduled for the second processor cluster; and
scheduling the process to the first execution processor cluster as a third processor cluster in response to determining that the process is scheduled for the second processor cluster.

### Claim 4 (depends on 1)

The method of claim 1, further comprising:
determining a third processor cluster with a second remote shared cache memory having a highest amount of available shared cache memory space wherein the second remote share cache memory includes any remote shared cache memory other than the first remote shared cache memory;
determining a fourth processor cluster having a lowest latency to the second execution processor cluster wherein the fourth processor cluster includes any processor cluster other than the first processor cluster;
scheduling a process scheduled for the third processor cluster to the fourth processor cluster; and
using the highest amount of available shared cache memory space as part of the victim cache for the execution process.

### Claim 5 (depends on 4)

The method of claim 4, further comprising:
determining whether a process is scheduled for the fourth processor cluster; and
scheduling the process to the third processor cluster in response to determining that the process is scheduled for the fourth processor cluster.

### Claim 6

A computing device, comprising:
a plurality of processor clusters communicatively connected to each other;
a first execution processor cluster of the plurality of processor clusters scheduled with an execution process;
a plurality of shared cache memories each communicatively connected to at least one of the plurality of processors; and
a processor communicatively connected to the plurality of processor clusters and configured with processor-executable instructions to perform operations comprising:
determining a first processor cluster with a first remote shared cache memory having an available shared cache memory space;
determining a second processor cluster with a lower latency to the first remote shared cache memory than the first execution processor cluster scheduled with the execution process;
scheduling the execution process to the second processor cluster as a second execution processor cluster based on a size of the available shared cache memory space and the latency of the second processor cluster to the first remote shared cache memory; and
using the available shared cache memory space as a victim cache for the execution process.

### Claim 7 (depends on 6)

The computing device of claim 6, wherein the processor is further configured with processor-executable instructions to perform operations such that:
determining a first processor cluster with a first remote shared cache memory having an available shared cache memory space comprises determining the first processor cluster with the first remote shared cache memory having a highest amount of available shared cache memory space;
determining a second processor cluster with a lower latency to the first remote shared cache memory than the first execution processor cluster scheduled with the execution process comprises determining the second processor cluster with a lowest latency to the first remote shared cache memory; and
scheduling the execution process to the second processor cluster as a second execution processor cluster based on a size of the available shared cache memory space and the latency of the second processor cluster to the first remote shared cache memory comprises scheduling the execution process to the second processor cluster as a second execution processor cluster based on the second processor cluster having the lowest latency to the first remote shared cache memory having the highest amount of available shared cache memory space.

### Claim 8 (depends on 6)

The computing device of claim 6, wherein the processor is further configured with processor-executable instructions to perform operations comprising:
determining whether a process is scheduled for the second processor cluster; and
scheduling the process to the first execution processor cluster as a third processor cluster in response to determining that the process is scheduled for the second processor cluster.

### Claim 9 (depends on 6)

The computing device of claim 6, wherein the processor is further configured with processor-executable instructions to perform operations comprising:
determining a third processor cluster with a second remote shared cache memory having a highest amount of available shared cache memory space wherein the second remote share cache memory includes any remote shared cache memory other than the first remote shared cache memory;
determining a fourth processor cluster having a lowest latency to the second execution processor cluster wherein the fourth processor cluster includes any processor cluster other than the first processor cluster;
scheduling a process scheduled for the third processor cluster to the fourth processor cluster; and
using the highest amount of available shared cache memory space as part of the victim cache for the execution process.

### Claim 10 (depends on 9)

The computing device of claim 9, wherein the processor is further configured with processor-executable instructions to perform operations comprising:
determining whether a process is scheduled for the fourth processor cluster; and
scheduling the process to the third processor cluster in response to determining that the process is scheduled for the fourth processor cluster.

### Claim 11

A computing device, comprising:
means for determining a first processor cluster with a first remote shared cache memory having an available shared cache memory space;
means for determining a second processor cluster with a lower latency to the first remote shared cache memory than a first execution processor cluster scheduled with an execution process;
means for scheduling the execution process to the second processor cluster as a second execution processor cluster based on a size of the available shared cache memory space and the latency of the second processor cluster to the first remote shared cache memory; and
means for using the available shared cache memory space as a victim cache for the execution process.

### Claim 12 (depends on 11)

The computing device of claim 11, wherein:
means for determining a first processor cluster with a first remote shared cache memory having an available shared cache memory space comprises means for determining the first processor cluster with the first remote shared cache memory having a highest amount of available shared cache memory space;
means for determining a second processor cluster with a lower latency to the first remote shared cache memory than a first execution processor cluster scheduled with the execution process comprises means for determining the second processor cluster with a lowest latency to the first remote shared cache memory; and
means for scheduling the execution process to the second processor cluster as a second execution processor cluster based on a size of the available shared cache memory space and the latency of the second processor cluster to the first remote shared cache memory comprises means scheduling the execution process to the second processor cluster as a second execution processor cluster based on the second processor cluster having the lowest latency to the first remote shared cache memory having the highest amount of available shared cache memory space.

### Claim 13 (depends on 11)

The computing device of claim 11, further comprising:
means for determining whether a process is scheduled for the second processor cluster; and
means for scheduling the process to the first execution processor cluster as a third processor cluster in response to determining that the process is scheduled for the second processor cluster.

### Claim 14 (depends on 11)

The computing device of claim 11, further comprising:
means for determining a third processor cluster with a second remote shared cache memory having a highest amount of available shared cache memory space wherein the second remote share cache memory includes any remote shared cache memory other than the first remote shared cache memory;
means for determining a fourth processor cluster having a lowest latency to the second execution processor cluster wherein the fourth processor cluster includes any processor cluster other than the first processor cluster;
means for scheduling a process scheduled for the third processor cluster to the fourth processor cluster; and
means for using the highest amount of available shared cache memory space as part of the victim cache for the execution process.

### Claim 15 (depends on 14)

The computing device of claim 14, further comprising:
means for determining whether a process is scheduled for the fourth processor cluster; and
means for scheduling the process to the third processor cluster in response to determining that the process is scheduled for the fourth processor cluster.

### Claim 16

A non-transitory processor-readable medium having stored thereon processor-executable instructions configured to cause a processor to perform operations comprising:
determining a first processor cluster with a first remote shared cache memory having an available shared cache memory space;
determining a second processor cluster with a lower latency to the first remote shared cache memory than a first execution processor cluster scheduled with an execution process;
scheduling the execution process to the second processor cluster as a second execution processor cluster based on a size of the available shared cache memory space and the latency of the second processor cluster to the first remote shared cache memory; and
using the available shared cache memory space as a victim cache for the execution process.

### Claim 17 (depends on 16)

The non-transitory processor-readable medium of claim 16, wherein the stored processor-executable instructions are configured to cause the processor to perform operations such that:
determining a first processor cluster with a first remote shared cache memory having an available shared cache memory space comprises determining the first processor cluster with the first remote shared cache memory having a highest amount of available shared cache memory space;
determining a second processor cluster with a lower latency to the first remote shared cache memory than a first execution processor cluster scheduled with the execution process comprises determining the second processor cluster with a lowest latency to the first remote shared cache memory; and
scheduling the execution process to the second processor cluster as a second execution processor cluster based on a size of the available shared cache memory space and the latency of the second processor cluster to the first remote shared cache memory comprises scheduling the execution process to the second processor cluster as a second execution processor cluster based on the second processor cluster having the lowest latency to the first remote shared cache memory having the highest amount of available shared cache memory space.

### Claim 18 (depends on 16)

The non-transitory processor-readable medium of claim 16, wherein the stored processor-executable instructions are configured to cause the processor to perform operations further comprising:
determining whether a process is scheduled for the second processor cluster; and
scheduling the process to the first execution processor cluster as a third processor cluster in response to determining that the process is scheduled for the second processor cluster.

### Claim 19 (depends on 16)

The non-transitory processor-readable medium of claim 16, wherein the stored processor-executable instructions are configured to cause the processor to perform operations further comprising:
determining a third processor cluster with a second remote shared cache memory having a highest amount of available shared cache memory space wherein the second remote share cache memory includes any remote shared cache memory other than the first remote shared cache memory;
determining a fourth processor cluster having a lowest latency to the second execution processor cluster wherein the fourth processor cluster includes any processor cluster other than the first processor cluster;
scheduling a process scheduled for the third processor cluster to the fourth processor cluster; and
using the highest amount of available shared cache memory space as part of the victim cache for the execution process.

### Claim 20 (depends on 19)

The non-transitory processor-readable medium of claim 19, wherein the stored processor-executable instructions are configured to cause the processor to perform operations further comprising:
determining whether a process is scheduled for the fourth processor cluster; and
scheduling the process to the third processor cluster in response to determining that the process is scheduled for the fourth processor cluster.
