# US 2019/0317744 A1 · Control speculation in dataflow graphs

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

- Number: US 2019/0317744 A1
- Document ID: US20190317744A1
- Status: Published application
- Kind: A1
- Application number: 16/456,953
- Filed: 2019-06-28
- Published: 2019-10-17
- Earliest claimed: 2019-06-28
- Assignees: Intel Corporation
- Applicants: Intel Corporation
- Inventors: Kermin ChoFleming
- Web page: https://patentgrep.com/patent/US20190317744A1

## CPC

- G06F 8/433: {Dependency analysis; Data or control flow analysis}
- G06F 8/4441: {Reducing the execution time required by the program code}
- G06F 12/0813: with a network or matrix configuration
- G06F 12/0888: using selective caching, e.g. bypass
- G06F 12/10: Address translation
- G06F 12/1027: using associative or pseudo-associative address translation means, e.g. translation look-aside buffer [TLB]
- G06F 2212/1016: Performance improvement
- G06F 2212/65: Details of virtual memory and virtual address translation
- G06F 2212/681: Multi-level TLB, e.g. microTLB and main TLB
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Systems, apparatuses and methods may provide for technology that determines that a control loop is to be executed for an unspecified number of iterations and automatically forces the control loop to be executed for a fixed number of iterations in addition to the unspecified number of iterations, where execution of the control loop for the fixed number of iterations is conducted in parallel. In one example, the technology also removes one or more dataflow tokens associated with the execution of the control loop for the fixed number of iterations.

## Claims

### Claim 1

A computing system comprising:
a network controller; and
a processor coupled to the network controller, the processor including logic coupled to one or more substrates, wherein the logic is to:
determine that a control loop is to be executed for an unspecified number of iterations, and
force the control loop to be executed for a fixed number of iterations in addition to the unspecified number of iterations, wherein execution of the control loop for the fixed number of iterations is to be conducted in parallel.

### Claim 2 (depends on 1)

The system of claim 1, wherein the logic coupled to the one or more substrates is to remove one or more dataflow tokens associated with the execution of the control loop for the fixed number of iterations.

### Claim 3 (depends on 1)

The system of claim 1, wherein the control loop is to involve a load from a memory address, and wherein the logic coupled to the one or more substrates is to generate a signal indicating whether the load was successful.

### Claim 4 (depends on 3)

The system of claim 3, wherein the load is to be from an input/output (IO) memory address.

### Claim 5 (depends on 3)

The system of claim 3, wherein the load is to be from a virtual memory address.

### Claim 6 (depends on 5)

The system of claim 5, wherein the logic coupled to the one or more substrates is to:
detect that the load was unsuccessful due to a non-cacheable memory mode anomaly; and
annotate one or more virtual pages as being non-translatable in response to the anomaly.

### Claim 7

A semiconductor apparatus comprising:
one or more substrates; and
logic coupled to the one or more substrates, wherein the logic is implemented at least partly in one or more of configurable logic or fixed-functionality hardware logic, the logic coupled to the one or more substrates to:
determine that a control loop is to be executed for an unspecified number of iterations; and
force the control loop to be executed for a fixed number of iterations in addition to the unspecified number of iterations, wherein execution of the control loop for the fixed number of iterations is to be conducted in parallel.

### Claim 8 (depends on 7)

The semiconductor apparatus of claim 7, wherein the logic coupled to the one or more substrates is to remove one or more dataflow tokens associated with the execution of the control loop for the fixed number of iterations.

### Claim 9 (depends on 7)

The semiconductor apparatus of claim 7, wherein the control loop is to involve a load from a memory address, and wherein the logic coupled to the one or more substrates is to generate a signal indicating whether the load was successful.

### Claim 10 (depends on 9)

The semiconductor apparatus of claim 9, wherein the load is to be from an input/output (IO) memory address.

### Claim 11 (depends on 9)

The semiconductor apparatus of claim 9, wherein the load is to be from a virtual memory address.

### Claim 12 (depends on 11)

The semiconductor apparatus of claim 11, wherein the logic coupled to the one or more substrates is to:
detect that the load was unsuccessful due to a non-cacheable memory mode anomaly; and
annotate one or more virtual pages as being non-translatable in response to the anomaly.

### Claim 13

At least one computer readable storage medium comprising a set of executable program instructions, which when executed by a computing system, cause the computing system to:
determine that a control loop is to be executed for an unspecified number of iterations; and
force the control loop to be executed for a fixed number of iterations in addition to the unspecified number of iterations, wherein execution of the control loop for the fixed number of iterations is to be conducted in parallel.

### Claim 14 (depends on 13)

The at least one computer readable storage medium of claim 13, wherein the program instructions, when executed, cause the computing system to remove one or more dataflow tokens associated with the execution of the control loop for the fixed number of iterations.

### Claim 15 (depends on 13)

The at least one computer readable storage medium of claim 13, wherein the control loop is to involve a load from a memory address, and wherein the program instructions, when executed, cause the computing system to generate a signal indicating whether the load was successful.

### Claim 16 (depends on 15)

The at least one computer readable storage medium of claim 15, wherein the load is to be from an input/output (IO) memory address.

### Claim 17 (depends on 15)

The at least one computer readable storage medium of claim 15, wherein the load is to be from a virtual memory address.

### Claim 18 (depends on 17)

The at least one computer readable storage medium of claim 17, wherein the program instructions, when executed, cause the computing system to:
detect that the load was unsuccessful due to a non-cacheable memory mode anomaly; and
annotate one or more virtual pages as being non-translatable in response to the anomaly.

### Claim 19

A method comprising:
determining that a control loop is to be executed for an unspecified number of iterations; and
forcing the control loop to be executed for a fixed number of iterations in addition to the unspecified number of iterations, wherein execution of the control loop for the fixed number of iterations is conducted in parallel.

### Claim 20 (depends on 19)

The method of claim 19, further including removing one or more dataflow tokens associated with the execution of the control loop for the fixed number of iterations.

### Claim 21 (depends on 19)

The method of claim 19, wherein the control loop involves a load from a memory address, and wherein the method further includes generating a signal indicating whether the load was successful.

### Claim 22 (depends on 21)

The method of claim 21, wherein the load is from an input/output (IO) memory address.

### Claim 23 (depends on 21)

The method of claim 21, wherein the load is from a virtual memory address.

### Claim 24 (depends on 23)

The method of claim 23, further including:
detecting that the load was unsuccessful due to a non-cacheable memory mode anomaly; and
annotating one or more virtual pages as being non-translatable in response to the anomaly.
