# US 2016/0259391 A1 · Dynamic clock rate control for power reduction

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

- Number: US 2016/0259391 A1
- Document ID: US20160259391A1
- Status: Published application
- Kind: A1
- Application number: 14/635,789
- Filed: 2015-03-02
- Published: 2016-09-08
- Earliest claimed: 2015-03-02
- Assignees: SanDisk Technologies LLC
- Applicants: SanDisk Technologies Inc.
- Inventors: Reed P. Tidwell
- Web page: https://patentgrep.com/patent/US20160259391A1

## CPC

- G06F 1/324: by lowering clock frequency
- G06F 1/08: Clock generators with changeable or programmable clock frequency
- G06F 9/3869: {Implementation aspects, e.g. pipeline latches; pipeline synchronisation and clocking}
- G06F 1/26: Power supply means, e.g. regulation thereof (for memories G11C)
- Y02D 10/00: Energy efficient computing, e.g. low power processors, power management or thermal management
- Y02D 30/50: in wire-line communication networks, e.g. low power modes or reduced link rate
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- Y02D: CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE

## Abstract

A pipeline system may adjust clock rates of variable-rate clock signals sent to different processing circuit blocks in a pipeline based on their respective, individual input and output buffer fill levels and processor busy statuses. Variable-rate clock generation circuitry may generate the variable-rate clock signals based on a common clock signal. Additionally, the variable-rate clock generation circuitry may set or adjust the rates of variable-rate clock signals linearly in evenly-spaced increments and decrements.

## Claims

### Claim 1

An electronic pipeline system comprising:
a pipeline comprising a plurality of processing circuit blocks configured to process data and communicate the processed data in a main data flow of the pipeline using buffers;
de-rating value generation circuitry configured to:
monitor fill levels of the buffers; and
generate de-rating values based on the fill levels, wherein each of the de-rating values corresponds to one of a plurality of fractions of a rate of a fixed-rate clock signal;
variable-rate clock generation circuitry configured to:
receive the de-rating values from the de-rating value generation circuitry and the fixed-rate clock signal;
generate a plurality of variable-rate clock signals based on the de-rating values; and
send the plurality of variable-rate clock signals to the plurality of processing circuit blocks.

### Claim 2 (depends on 1)

The electronic pipeline system of claim 1, wherein the de-rating value generation circuitry is further configured to:
monitor busy statuses of the plurality of processing circuit blocks; and
generate the de-rating values based on the busy statuses, wherein each of the busy statuses indicates that a respective one of the plurality of processing circuit blocks is in a busy state or an idle state.

### Claim 3 (depends on 2)

The electronic pipeline system of claim 2, wherein for each of the de-rating values, the de-rating value generation circuitry is configured to:
generate a de-rating value to correspond to an idle rate for the plurality of variable-rate clock signals when an associated one of the busy statuses indicates that an associated processing circuit block is in the idle state; and
generate a de-rating value to correspond to a maximum rate or one of a plurality of scaled-down rates for the plurality of variable-rate clock signals when an associated one of the busy statuses indicates that an associated processing circuit block is in the busy state.

### Claim 4 (depends on 3)

The electronic pipeline system of claim 3, wherein the de-rating value generation circuitry is configured to generate the de-rating values based on the fill levels relative to target levels of the buffers.

### Claim 5 (depends on 4)

The electronic pipeline system of claim 4, wherein for each of the de-rating values, when the de-rating value generation circuitry is configured to generate the de-rating value to correspond to a scaled-down rate of the plurality of the scaled-down rates, the de-rating value generation circuitry is configured to adjust the de-rating value until a fill level of an associated input buffer or a fill level of an associated output buffer reaches a respective target level.

### Claim 6 (depends on 5)

The electronic pipeline system of claim 5, wherein the de-rating value generation circuitry is configured to adjust the de-rating value in linearly-spaced increments and decrements.

### Claim 7 (depends on 4)

The electronic pipeline system of claim 4, wherein the de-rating value generation circuitry is configured to generate the de-rating values further based on an operation mode, wherein the operation mode comprises a performance mode or a reduced-power mode.

### Claim 8 (depends on 7)

The electronic pipeline system of claim 7, wherein for each of the de-rating values, when the associated one of the busy statuses indicates that the associated processing circuit block is in the busy state, a fill level of an associated input buffer is below an input buffer target level, and a fill level of an associated output buffer is below an output buffer target level, the de-rating value generation circuitry is configured to:
generate the de-rating value to correspond to the maximum rate when the operation mode comprises the performance mode; and
generate the de-rating value to correspond to a scaled-down rate of the plurality of scaled-down rates when the operation mode comprises the reduced-power mode.

### Claim 9 (depends on 7)

The electronic pipeline system of claim 7, wherein for each of the de-rating values, when the associated one of the busy statuses indicates that the associated processing circuit block is in the busy state, a fill level of an associated input buffer is below an input buffer target level, and a fill level of an associated output buffer is above an output buffer target level, the de-rating value generation circuitry is configured to generate the de-rating value to correspond to a scaled-down rate of the plurality of scaled-down rates when the operation mode comprises the performance mode or the reduced-power mode.

### Claim 10 (depends on 9)

The electronic pipeline system of claim 9, wherein for each of the de-rating values, when the associated one of the busy statuses indicates that the associated processing circuit block is in the busy state, the fill level of the associated input buffer is below the input buffer target level, and the fill level of the associated output buffer is above the output buffer target level:
when the operation mode comprises the performance mode, the scaled-down rate is scaled down in proportion to an amount that the fill level of the associated output buffer is above the output buffer target level, and
when the operation mode comprises the reduced-power mode, the scaled-down rate corresponds to whichever of the fill level of the associated input buffer and the fill level of the associated output buffer indicates a lower rate for an associated one of the plurality of variable-rate clock signals.

### Claim 11 (depends on 7)

The electronic pipeline system of claim 7, wherein for each of the de-rating values, when the associated one of the busy statuses indicates that the associated processing circuit block is in the busy state, a fill level of an associated input buffer is above an input buffer target level, and a fill level of an associated output buffer is below an output buffer target level, the de-rating value generation circuitry is configured to generate the de-rating value to correspond to the maximum rate when the operation mode comprises the performance mode or the reduced-power mode.

### Claim 12 (depends on 7)

The electronic pipeline system of claim 7, wherein for each of the de-rating values, when the associated one of the busy statues indicates that the associated processing circuit block is in the busy state, a fill level of an associated input buffer is above an input buffer target level, and a fill level of an associated output buffer is above an output buffer target level, the de-rating value generation circuitry is configured to generate the de-rating value to correspond to a scaled-down rate of the plurality of scaled-down rates when the operation mode comprises the performance mode or the reduced power mode.

### Claim 13 (depends on 3)

The electronic pipeline system of claim 3, wherein the plurality of fractions comprises a range of linearly-decreasing fractions that linearly decrease from a maximum fraction to a minimum fraction, and wherein for each of the de-rating values:
when the de-rating value generation circuitry determines to generate the de-rating value to correspond to the maximum rate, the de-rating value generation circuitry is configured to generate the de-rating value to correspond to the maximum fraction of the range; and
when the de-rating value generation circuitry determines to generate the de-rating value to correspond to a scaled-down rate of the plurality of scaled-down rates, the de-rating value generation circuitry is configured to generate the de-rating value to correspond to one of the linearly-decreasing fractions other than the maximum fraction.

### Claim 14 (depends on 13)

The electronic pipeline system of claim 13, wherein the plurality of fractions further comprises an idle fraction, and wherein for each of the de-rating values:
when the de-rating value generation circuitry determines to generate the de-rating value to correspond to the idle rate, the de-rating value generation circuitry is configured to generate the de-rating value to correspond to the idle fraction,
wherein the idle fraction is less than or equal to half of the rate of the fixed-rate clock signal.

### Claim 15 (depends on 3)

The electronic pipeline system of claim 3, wherein the maximum rate is equal to the rate of the fixed-rate clock signal, or the rate of the fixed-rate clock signal is a multiple of the maximum rate.

### Claim 16

A method of generating a clock signal for a pipeline, the method comprising:
receiving, with a de-rating value generator, fill level information from at least one of an input buffer or an output buffer associated with a processing circuit block of the pipeline;
determining, with the de-rating value generator, a fraction of a first rate of a first clock signal based on the fill level information, wherein the fraction comprises one among a plurality of fractions;
sending, with the de-rating value generator, a de-rating value corresponding to the fraction to clock generation circuitry;
generating, with the clock generation circuitry, a second clock signal at a second rate, wherein the second rate comprises the fraction of the first rate; and
sending, with the clock generation circuitry, the second clock signal to the processing circuit block.

### Claim 17 (depends on 16)

The method of claim 16, further comprising:
receiving, with de-rating value generator, busy status information from the processing circuit blocks; and
wherein determining the fraction of the first rate of the first clock signal comprises determining, with the de-rating value generator, the fraction of the first rate based on the fill level information and the busy status information.

### Claim 18 (depends on 17)

The method of claim 17, wherein determining the fraction of the first rate of the first clock signal comprises determining, with the de-rating value generator, whether the fraction of the first rate corresponds to one of: an idle rate, a maximum rate, and a scaled-down rate of a plurality of scaled-down rates.

### Claim 19 (depends on 18)

The method of claim 18, wherein the fill level information identifies at least one of an input buffer fill level of the input buffer or an output buffer fill level of the output buffer, and
wherein determining whether the fraction of the first rate corresponds to one of the idle rate, the maximum rate and the scaled-down rate is based on the at least one of the input buffer fill level relative to an input buffer target level or the output buffer fill level relative to an output buffer target level.

### Claim 20 (depends on 19)

The method of claim 19, further comprising:
when determining that the fraction of the first rate corresponds to the scaled-down rate, adjusting, with the de-rating value generator, the de-rating value until the input buffer fill level reaches the input buffer target level or the output buffer fill level reaches the output buffer target level.

### Claim 21 (depends on 20)

The method of claim 20, wherein adjusting the de-rating value comprises adjusting, with the de-rating value generator, the de-rating value in linearly-spaced increments and decrements.

### Claim 22 (depends on 19)

The method of claim 19, wherein determining whether the fraction of the first rate corresponds to one of the idle rate, the maximum rate, and the scaled-down rate is further based on an operation mode, wherein the operation mode comprises a performance mode or a reduced-power mode.

### Claim 23 (depends on 18)

The method of claim 18, wherein the plurality of fractions comprises a range of linearly-decreasing fractions that linearly decrease from a maximum fraction to a minimum fraction and an idle fraction, wherein:
when determining that the fraction of the first rate corresponds to the maximum rate, generating, with the de-rating value generator, the de-rating value to correspond to the maximum fraction of the range;
when determining that the fraction of the first rate corresponds to the scaled-down rate of the plurality of scaled-down rates, generating, with the de-rating value generator, the de-rating value to correspond to one of the linearly-decreasing fractions other than the maximum fraction; and
when determining that the fraction of the first rate corresponds to the idle rate, generating with the de-rating value generator, the de-rating value to correspond to the idle fraction,
wherein the idle fraction is less than or equal to half of the rate of the fixed-rate clock signal.

### Claim 24 (depends on 18)

The electronic pipeline system of claim 18, wherein the maximum rate is equal to the rate of the fixed-rate clock signal, or the rate of the fixed-rate clock signal is a multiple of the maximum rate.

### Claim 25

Clock generation circuitry for a pipeline, the clock generation circuitry comprising:
first circuitry configured to:
receive feedback information from the pipeline, wherein the feedback information comprises fill level information of input and output buffers associated with processing circuit blocks of the pipeline; and
determine a plurality of fractions of a rate of a fixed-rate clock signal for a plurality of variable-rate clock signals based on the feedback information; and
second circuitry configured to:
generate the plurality of variable-rate clock signals, each at one of the plurality of fractions of the rate of the fixed-rate clock signal determined by the first circuitry; and
send the plurality of variable-rate clock signals to the processing circuit blocks of the pipeline.

### Claim 26 (depends on 25)

The clock generation circuitry of claim 25, wherein the feedback information further comprises busy status information identifying whether each of the processing circuit blocks is in a busy state or an idle state,
wherein the first circuitry is configured to determine the plurality of fractions of the rate of the fixed-rate clock signal further based on the busy state information.

### Claim 27 (depends on 26)

The clock generation circuitry of claim 26, wherein the first circuitry is further configured to generate de-rating values corresponding to the plurality of fractions, wherein for each of the de-rating values, the first circuitry is configured to:
generate a de-rating value to correspond to an idle rate for the plurality of variable-rate clock signals when the busy status information indicates that an associated one of the processing circuit blocks is in the idle state; and
generate a de-rating value to correspond to a maximum rate or one of a plurality of scaled-down rates when the busy status information indicates that an associated one of the processing circuit blocks is in the busy state.

### Claim 28 (depends on 27)

The clock generation circuitry of claim 27, wherein the first circuitry is configured to generate the de-rating values based on the fill levels identified in the fill level information relative to target levels of the input and output buffers.

### Claim 29 (depends on 28)

The clock generation circuitry of claim 28, wherein for each of the de-rating values, when the first circuitry is configured to generate the de-rating value to correspond to a scaled-down rate of the plurality of the scaled-down rates, the first circuitry is configured to adjust the de-rating value until a fill level of an associated input buffer or a fill level of an associated output buffer reaches a respective target level.

### Claim 30 (depends on 29)

The clock generation circuitry of claim 29, wherein the first circuitry is configured to adjust the de-rating value in linearly-spaced increments and decrements.

### Claim 31 (depends on 28)

The clock generation circuitry of claim 28, wherein the first circuitry is configured to generate the de-rating values further based on an operation mode, wherein the operation mode comprises a performance mode or a reduced-power mode.

### Claim 32 (depends on 27)

The clock generation circuitry of claim 27, wherein the plurality of fractions comprises a range of linearly-decreasing fractions that linearly decrease from a maximum fraction to a minimum fraction and an idle fraction, and wherein for each of the de-rating values:
when the first circuitry determines to generate the de-rating value to correspond to the maximum rate, the first circuitry is configured to generate the de-rating value to correspond to the maximum fraction of the range;
when the first circuitry determines to generate the de-rating value to correspond to a scaled-down rate of the plurality of scaled-down rates, the first circuitry is configured to generate the de-rating value to correspond to one of the linearly-decreasing fractions other than the maximum fraction; and
when the de-rating value generation circuitry determines to generate the de-rating value to correspond to the idle rate, the de-rating value generation circuitry is configured to generate the de-rating value to correspond to the idle fraction,
wherein the idle fraction is less than or equal to half of the rate of the fixed-rate clock signal.

### Claim 33 (depends on 27)

The clock generation circuitry of claim 27, wherein the maximum rate is equal to the rate of the fixed-rate clock signal, or the rate of the fixed-rate clock signal is a multiple of the maximum rate.
