# US 2017/0255464 A1 · Merged floating point operation using a modebit

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

- Number: US 2017/0255464 A1
- Document ID: US20170255464A1
- Status: Published application
- Kind: A1
- Application number: 15/604,263
- Filed: 2017-05-24
- Published: 2017-09-07
- Earliest claimed: 2012-01-25
- Assignees: ARM Finance Overseas Limited
- Applicants: ARM Finance Overseas Limited
- Inventors: David Yiu-Man Lau
- Web page: https://patentgrep.com/patent/US20170255464A1

## CPC

- G06F 9/30014: {with variable precision}
- G06F 7/483: Computations with numbers represented by a non-linear combination of denominational numbers, e.g. rational numbers, logarithmic number system or floating-point numbers {(G06F7/4806, G06F7/4824, G06F7/49, G06F7/491, G06F7/544 take precedence)}
- G06F 7/49947: {Rounding}
- G06F 7/5443: {Sum of products (for applications thereof, see the relevant places, e.g. G06F17/10, H03H17/00)}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A first floating-point operation unit receives first and second variables and performs a first operation generating a first output. A first rounding unit receives and rounds the first output to generate a second output if a control bit is in a first state. A second floating-point operation unit receives a third variable and either the first output or the second output and performs a second operation on the third variable and either the first output or the second output, to generate a third output. The second floating-point operation unit receives and operates on the first output if the control bit is in the first state, or the second output if the control bit is in the second state. A second rounding unit receives and rounds the third output.

## Claims

### Claim at position 1

1-9. (canceled)

### Claim 10

A floating-point processing system comprising:
a storage unit to store a control bit having a first and a second state;
a floating-point operation unit to perform a first floating-point operation on first and second floating-point variables to generate a first output; and
a second floating-point operation unit to, when the control bit is in the first state, perform a second floating-point operation on the first output and a third floating-point variable to generate a second output.

### Claim 11 (depends on 10)

The system of claim 10, further comprising a first rounding unit to receive and round the first output to generate a third output when the control bit is in the second state.

### Claim 12 (depends on 11)

The system of claim 11, wherein the second floating-point operation unit is configured to, when the control bit is in the second state, perform the second floating-point operation on the third output and the third floating-point variable to generate the second output.

### Claim 13 (depends on 10)

The system of claim 10, wherein the state of the control bit is set during an initialization of the system.

### Claim 14 (depends on 10)

The system of claim 10, wherein the state of the control bit is set responsive to an instruction issued by an execution unit coupled to the system. (New) The system of claim 10, further configured to determine the state of the control bit before the first floating-point operation.

### Claim 16 (depends on 10)

The system of claim 10, further configured to determine the state of the control bit concurrently with the first floating-point operation.

### Claim 17 (depends on 10)

The system of claim 10, wherein the first output has a first precision, and wherein the second output has a second precision.

### Claim 18 (depends on 17)

The system of claim 17, wherein the first precision is equal to the second precision.

### Claim 19 (depends on 11)

The system of claim 11, wherein the third output has a third precision.

### Claim 20 (depends on 19)

The system of claim 19, wherein the third precision is less than the first precision.

### Claim 21 (depends on 10)

The system of claim 10, further comprising a second rounding unit to receive and round the second output.

### Claim 22 (depends on 10)

The system of claim 10, wherein the first floating-point operation is a floating-point multiplication or floating-point negate-multiplication.

### Claim 23 (depends on 10)

The system of claim 10, wherein the second floating-point operation is a floating-point addition or floating-point subtraction.

### Claim 24 (depends on 10)

The system of claim 10, wherein the first floating-point operation unit is configured to perform a third floating-point operation on fourth and fifth floating-point variables in the same machine cycle as the second floating point operation.

### Claim 25

A method of processing a floating-point operation comprising:
storing a control bit having a first and a second state;
performing a first floating-point operation on first and second floating-point variables to generate a first output;
determining the state of the control bit;
performing, responsive to a determination that the control bit is in the first state, a second floating-point operation on the first output and a third floating-point variable to generate a second output.

### Claim 26 (depends on 25)

The method of claim 25, further comprising:
performing, responsive to a determination that the control bit is in the second state, a rounding operation on the first output to generate a third output;
performing the second floating-point operation on the third output and the third floating point variable to generate the second output.

### Claim 27 (depends on 25)

The method of claim 25, further comprising:
determining the state of the control bit before the first floating-point operation.

### Claim 28 (depends on 25)

The method of claim 25, further comprising:
determining the state of the control bit concurrently with the first floating-point operation.

### Claim 29

A non-transitory computer readable storage medium including instructions defining logic blocks of a floating-point processing system, the computer readable storage medium adapted for use by an electronic design automation application executed by a computer, wherein the logic blocks are configured to perform an operation comprising:
storing a control bit having a first and a second state;
performing a first floating-point operation on first and second floating-point variables to generate a first output;
determining the state of the control bit;
performing, responsive to a determination that the control bit is in the first state, a second floating-point operation on the first output and a third floating-point variable to generate a second output.
