# US 2019/0171596 A1 · Semiconductor device and control method of semiconductor device

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

- Number: US 2019/0171596 A1
- Document ID: US20190171596A1
- Status: Published application
- Kind: A1
- Application number: 16/253,802
- Filed: 2019-01-22
- Published: 2019-06-06
- Earliest claimed: 2015-12-02
- Assignees: Renesas Electronics Corporation
- Applicants: Renesas Electronics Corporation
- Inventors: Masaru HASE; Tetsuji Tsuda; Naohiro Nishikawa; Yuki Inoue; Seiji Mochizuki; Katsushige Matsubara; Ren Imaoka
- Web page: https://patentgrep.com/patent/US20190171596A1

## CPC

- G06F 13/362: with centralised access control
- G06F 13/4022: {using switching circuits, e.g. switching matrix, connection or expansion network (G06F13/4009 takes precedence)}
- G06F 15/17312: {Routing techniques specific to parallel machines, e.g. wormhole, store and forward, shortest path problem congestion (routing on a LAN H04L45/00)}
- G06F 15/7807: {System on chip, i.e. computer system on a single chip; System in package, i.e. computer system on one or more chips in a single package}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

In a semiconductor device, a load of CPU required for arbitration when using a shared resource is reduced. The semiconductor device includes a CPU section and a hardware IP. In the CPU section, software modules are executed. The hardware IP includes a storage unit, an arbitration unit, and a calculation unit. The storage unit includes control receiving units that receive operation requests transmitted by the software modules, respectively. The calculation unit performs processing based on an operation request transmitted from the control receiving units. The arbitration unit controls information transmission between the control receiving units and the calculation unit so that the calculation unit receives only an operation request from any one of the control receiving units.

## Claims

### Claim 1

A semiconductor device comprising:
a CPU section configured to execute a plurality of software modules to transmit operation requests; and
a plurality of control receiving units configured to receive the operation requests transmitted by each respective ones of the software modules,
a calculation unit configured to perform processing based on the operation requests transmitted from the control receiving units to generate response information, and
an arbitration unit configured to control information transmission between the control receiving units and the calculation unit such that the calculation unit receives only one of the operation requests at a time from any one of the control receiving units, and
wherein, while forming a first information transmission path between the calculation unit and one of the control receiving units, the arbitration unit transmits the operation request output from the one of the control receiving units to the calculation unit and transmits the response information generated based on the transmitted operation request from the calculation unit to the one of the control receiving units.

### Claim 2 (depends on 1)

The semiconductor device according to claim 1, wherein the arbitration unit is further configured to select a control receiving unit to be a transmission source of an operation request to be received by the calculation unit according to a set arbitration method.

### Claim 3 (depends on 2)

The semiconductor device according to claim 2,
wherein the arbitration unit includes
a plurality of switching elements inserted between each of the control receiving units and the calculation unit in parallel, and
a control unit configured to control opening and closing of the switching elements, and
wherein the arbitration unit is further configured to close one of the switching elements coupled to the selected control receiving unit and to open other switching elements, of the switching elements, coupled to the control receiving units other than the selected control receiving unit.

### Claim 4 (depends on 3)

The semiconductor device according to claim 3, wherein the control unit controls a plurality of switching elements so that only one of the switching elements is closed.

### Claim 5 (depends on 1)

The semiconductor device according to claim 1,
wherein the control receiving units, the number of which is the same as that of the software modules, are provided, and
wherein the control receiving units are configured to receive operation requests from different software modules, respectively.

### Claim 6 (depends on 1)

The semiconductor device according to claim 1,
wherein the plurality of control receiving units are configured to be associated with the plurality of software modules, respectively, and
wherein one of the control receiving units receives an operation request from the software module associated with the one of the control receiving units and transmits information in the one of the control receiving units to the software module associated with the one of the control receiving units.

### Claim 7 (depends on 1)

The semiconductor device according to claim 1, further comprising a hardware IP,
wherein the hardware IP includes:
the plurality of control receiving units;
the calculation unit; and
the arbitration unit.

### Claim 8 (depends on 1)

The semiconductor device according to claim 1, wherein when two or more control receiving units hold the received operation requests, the arbitration unit controls information transmission between the control receiving units and the calculation unit so that the calculation unit receives only one of the operation requests held by the control receiving units

### Claim 9 (depends on 1)

The semiconductor device according to claim 1, wherein when the response information is not transmitted via the first information transmission path within a predetermined period of time, the calculation unit stops generating the response information based on the transmitted operation request via the first information transmission path.

### Claim 10 (depends on 9)

The semiconductor device according to claim 9, wherein, after the calculation unit stops generating the response information, the arbitration unit switches an information transmission path from the first information transmission path to a second information transmission path that is formed between the calculation unit and one of the other control receiving units.

### Claim 11 (depends on 1)

The semiconductor device according to claim 1, wherein when one of the other control receiving units receives the operation request from a specific software module, the calculation unit stops generating the response information based on the transmitted operation request via the first information transmission path.

### Claim 12 (depends on 11)

The semiconductor device according to claim 11, wherein when stopping generating the response information, the calculation unit performs reset and notifies a completion of the reset to the one of the control receiving unit via the first information transmission path.

### Claim 13 (depends on 11)

The semiconductor device according to claim 11, wherein the control receiving unit sets a period of time from when the processing being executed by the calculation unit is stopped to when the operation request from the specific software module is started.

### Claim 14 (depends on 1)

The semiconductor device according to claim 1,
wherein the arbitration unit includes an arbitration method setting unit in which a plurality of arbitration methods are stored,
wherein the CPU section is further configured to specify an arbitration method to be used by the arbitration unit based on the response information, and
wherein the arbitration unit is further configured to acquire an arbitration method corresponding to the specification from the arbitration method setting unit.

### Claim 15 (depends on 14)

The semiconductor device according to claim 14,
wherein the calculation unit sets a period of time from when the processing being executed by the calculation unit is stopped to when the next operation becomes able to be started in the control receiving unit and
wherein the control receiving unit transmits the set information to the CPU section to change a processing order of an operation request and an arbitration method that is set in the arbitration method setting unit.

### Claim 16 (depends on 1)

The semiconductor device according to claim 1,
wherein the response information comprises information indicating a load factor of the calculation unit,
wherein the CPU section compares the load factor with a predetermined value to decide an arbitration method, and specifies the decided arbitration method to be used by the arbitration unit, and
wherein the arbitration unit performs a switch of information transmission paths between the calculation unit and anyone of the control receiving units according to the specified arbitration method.

### Claim 17 (depends on 16)

The semiconductor device according to claim 16, wherein the arbitration method includes round robin.

### Claim 18 (depends on 16)

The semiconductor device according to claim 16, wherein the arbitration method includes LRU (Least Recently Used).

### Claim 19

A method for controlling a semiconductor devise, the method comprising:
transmitting a first operation request from a first software module to a first control receiving unit;
transmitting a second operation request from a second software module to a second control receiving unit;
holding the first operation request in the first control receiving unit;
holding the second operation request in the second control receiving unit; and
forming a first information transmission path between the calculation unit and the control receiving unit holding the first operation request,
wherein the forming includes:
transmitting the first operation request to the calculation unit;
performing processing based on the first operation requests to generate first response information; and
transmitting the first response information to the control receiving units which transmitted the first operation request.

### Claim 20 (depends on 19)

The method for controlling the semiconductor devise according to claim 19, the method further comprising:
after transmitting first response information, forming a second information transmission path between the calculation unit and the control receiving unit holding the second operation request,
wherein the forming of the second information transmission path includes:
transmitting the second operation request to the calculation unit;
performing processing based on the second operation requests to generate second response information; and
transmitting the second response information to the control receiving units which transmitted the second operation request.
