CN111028128A - GPU (graphics processing Unit) -oriented vertex output control method and unit based on SystemC - Google Patents
GPU (graphics processing Unit) -oriented vertex output control method and unit based on SystemC Download PDFInfo
- Publication number
- CN111028128A CN111028128A CN201911125627.9A CN201911125627A CN111028128A CN 111028128 A CN111028128 A CN 111028128A CN 201911125627 A CN201911125627 A CN 201911125627A CN 111028128 A CN111028128 A CN 111028128A
- Authority
- CN
- China
- Prior art keywords
- vertex
- unit
- vertex output
- data
- output control
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T1/00—General purpose image data processing
- G06T1/20—Processor architectures; Processor configuration, e.g. pipelining
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2200/00—Indexing scheme for image data processing or generation, in general
- G06T2200/28—Indexing scheme for image data processing or generation, in general involving image processing hardware
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Generation (AREA)
Abstract
The invention relates to the technical field of computer hardware modeling, in particular to a GPU-oriented vertex output control method and unit based on SystemC. The method comprises the following steps: reading initial data; vertex output assembly in a simple mode; vertex output packing in complex mode. The invention realizes the design of the GPU-oriented vertex output control method and the GPU-oriented vertex output control unit, solves the problem of function verification of the GPU-oriented vertex output control unit, provides accurate data comparison for RTL simulation and accelerates the simulation speed.
Description
Technical Field
The invention relates to the technical field of computer hardware modeling, in particular to a GPU-oriented vertex output control method and unit based on SystemC.
Background
With the increasing of graphics applications, it is difficult for early solutions of graphics rendering by CPU alone to meet the graphics Processing requirements of performance and technology growth, and Graphics Processing Units (GPUs) have come into play. From 1999, the first GPU product released by Nvidia to date, the development of GPU technology mainly goes through the fixed function pipeline stage, the separation stainer architecture stage, and the unified stainer architecture stage, the graphics processing capability of the GPU technology is continuously improved, and the application field is gradually expanded from the initial graphics drawing to the general computing field. The GPU pipeline has high speed, parallel characteristics and flexible programmability, and provides a good running platform for graphic processing and general parallel computing.
The GPU chip has huge developed hardware logic scale and higher complexity, and the design needs to be described on a higher abstraction level so as to be capable of carrying out higher-speed simulation, software/hardware collaborative simulation and system architecture exploration. When the design is expressed as a system-level model, the design can be easily tried for many times by selecting different algorithms, and the test can be quickly completed by using different structures; if a design is expressed using a register transfer level or gate level model, the scale is usually quite large, and it is time consuming and laborious if different design structures are tried and some changes are made, if not too difficult.
The key factor of SystemC as a language for promoting the development and standardization is that system level design can be performed, and the hardware architecture and software algorithm can be described, so as to support verification and IP communication. Using SystemC as a partitioning tradeoff of software and hardware at the system level is much easier than other languages and the simulation is much faster than using multiple languages. Therefore, the microstructure of the unit is designed and described based on SystemC, so that a completely standard simulation environment can be established, and direct modeling can be realized at a high abstraction level.
The GPU vertex output control unit is used as an important node on a GPU graphic processing pipeline, maintains the output sequence of a plurality of vertex tasks, ensures that the output sequence of the dyeing tasks is consistent with the input sequence of the uniform dyeing unit, reads and assembles data into a primitive vertex command after the uniform dyeing unit finishes the dyeing tasks, and sends the primitive vertex command to the geometric engine unit.
Disclosure of Invention
Based on the problems in the background art, the GPU-oriented vertex output control method based on the SystemC solves the problem of function verification of the GPU vertex output control unit, provides accurate data comparison for RTL simulation, and accelerates the simulation speed.
The technical solution of the invention is as follows:
the invention aims to provide a GPU-oriented vertex output control method based on SystemC, which comprises the following steps:
s1: reading initial data;
s2: vertex output assembly in a simple mode;
s3: vertex output packing in complex mode.
Further, the S1 includes:
judging the states of vertexsamplettaskffo and vertexcomplexttaskffo, and if the states are both empty, circulating the step 1;
if vertexsamplettaskfiffo is not empty and vertexcomplexttaskffo is empty, then S2 is executed;
if vertexsampletatkfifo is empty and vertexcomplextatkfifo is not empty, then S3 is executed;
if vertexcempletaskfifo is not empty and vertexcomplex tasskfifo is not empty, the error exits;
wherein, vertexsampletatkffo represents an FIFO storing simple mode attribute data;
vertexcomplexttaskffo denotes a FIFO storing complex pattern attribute task information.
Further, the S2 includes:
s2.1: set vertexAssembleBusy 1;
s2.2: continuously reading the vertexsamplettaskffo data for 3 times, and executing S2.3;
if the data in the vertexsamplettaskffo is less than 3, blocking and the like until the glEndEnable is effective, executing S2.3;
s2.3: assembling the read vertexType/edgeFlag/cordinate/color data, and issuing the data to a geometry engine unit through a transaction-level interface;
s2.4: it is determined whether the glEndEnable is valid,
if the data is valid, sending a null packet to the geometry engine unit through the transaction-level interface, and ending;
if not, directly setting vertexAssembleBusy to 0, and ending.
Further, the S3 includes:
s3.1: reading data;
s3.2: preparing data assembly;
s3.3: assembling the vertex types of the glRasterPos;
s3.4: glVertex vertex type assembly.
Further, the step S3.1 includes the following steps:
s3.1.1: set vertexAssembleBusy 1;
s3.1.2: reading vertexcomplexttaskfifo data, and acquiring task information: slotId, vertexType, vertexMask;
wherein: vertexAssembleBusy indicates a vertex assembly state, 1 indicates busy, and 0 indicates idle;
the slot Id represents the slot task id;
the vertexType represents a vertex type and comprises two types of glRasterPos and glVertex;
vertexMask denotes a vertex mask.
Further, the step S3.2 includes the steps of:
s3.2.1: the completion state of a task corresponding to the current slotId of the unified coloring unit is inquired through transaction-level interface blocking until the state is valid;
s3.2.2: reading the data of the uniform dyeing unit through the transaction-level interface, reading the complete attribute of the data, and performing data format conversion;
s3.2.3: reading an attribute switch in a state parameter register unit through a transaction-level interface;
s3.2.4: it is determined whether the task type is glraterpos,
if so, executing S3.3,
otherwise, go to step S3.2.5;
s3.2.5: it is determined whether the task type is glVertex,
if so, go to step S3.4,
otherwise, ending.
Further, the S3.3 includes:
s3.3.1 ignoring the switch state of the attribute, and sending the assembled and read data to the geometry engine unit through the transaction-level interface;
s3.3.2, clearing the corresponding slotId bit of the unified dyeing unit, and submitting the slotId task through the transaction interface to complete the task;
s3.3.3, judging the vertexcomplexttaskffo state:
if not, returning to S3.1;
otherwise, executing the vertexassmblebusy busy being equal to 0, and ending.
Further, the S3.4 includes:
s3.4.1 if the switch corresponding to the attribute is on, the assembled read data is sent to the geometry engine unit through the transaction interface;
if the switch corresponding to the attribute is off, neglecting and assembling the next attribute;
s3.4.2, clearing the corresponding slotId bit of the unified dyeing unit, and submitting the slotId task through the transaction interface to complete the task;
s3.4.3, judging the vertexcomplexttaskffo state:
if not, returning to the step S3.1;
otherwise, S3.4.4 is executed;
s3.4.4 judges whether or not glEndEnable is valid:
if the command is valid, processing the glEnd command, sending a null packet to the geometry engine unit through the transaction-level interface, setting vertexAssembleBusy to be 0, and ending;
otherwise, go back to S3.4.3 after waiting for one beat;
wherein: the glEndEnable indicates an enable flag of the glEnd command, and a value of 1 indicates valid and a value of 0 indicates invalid.
Another objective of the present invention is to provide a system c-based GPU-oriented vertex output control unit, wherein the TLM micro-structure comprises an initialization module, a simple mode vertex output module, and a complex mode vertex output module;
the simple mode vertex output module and the complex mode vertex output module are physically and logically independent and are connected with the initialization module through a transaction-level interface;
the initialization module is used for reading initial data;
the simple mode vertex output module is used for performing vertex output in a simple mode;
and the complex mode vertex output module is used for outputting the vertex in the complex mode.
Furthermore, the vertex output control unit is connected with the PCIE bus unit, the state parameter management unit, the vertex task assembly unit, the uniform dyeing unit, the geometric engine unit and the state parameter register unit through an object level interface;
under the simple mode, data are input into a simple mode vertex output module in a vertex output control unit from a vertex task assembling unit and are output to a geometric engine unit after being assembled;
in the complex mode, task information is input into a complex mode vertex output module in a vertex output control unit from a vertex task assembling unit, data information is input into the complex mode vertex output module in the vertex output control unit from a uniform dyeing unit, attribute control information is input into the vertex output control unit from a state parameter register unit, and the attribute control information is output to a geometric engine unit after being uniformly assembled.
The invention has the beneficial effects that:
the invention provides a GPU-oriented vertex output control method based on SystemC software/hardware collaborative design language, solves the problem of function verification of a GPU vertex output control unit, provides accurate data comparison for RTL simulation and accelerates the simulation speed.
Drawings
FIG. 1 is a flow diagram of an initialization module;
FIG. 2 is a flow diagram of a simple mode vertex output module;
FIG. 3 is a flow diagram of a complex mode vertex output module;
fig. 4 is a block diagram of a system c-based GPU-oriented vertex output control unit.
Detailed Description
The invention provides a GPU-oriented vertex output control method based on SystemC, which is characterized by comprising the following steps:
s1: reading initial data;
s2: vertex output assembly in a simple mode;
s3: vertex output packing in complex mode.
The method for controlling GPU-oriented vertex output based on SystemC is characterized in that S1 includes:
judging the states of vertexsamplettaskffo and vertexcomplexttaskffo, and if the states are both empty, circulating the step 1;
if vertexsamplettaskfiffo is not empty and vertexcomplexttaskffo is empty, then S2 is executed;
if vertexsampletatkfifo is empty and vertexcomplextatkfifo is not empty, then S3 is executed;
if vertexcempletaskfifo is not empty and vertexcomplex tasskfifo is not empty, the error exits;
wherein, vertexsampletatkffo represents an FIFO storing simple mode attribute data;
vertexcomplexttaskffo denotes a FIFO storing complex pattern attribute task information.
The method for controlling GPU-oriented vertex output based on SystemC is characterized in that S2 includes:
s2.1: set vertexAssembleBusy 1;
s2.2: continuously reading the vertexsamplettaskffo data for 3 times, and executing S2.3;
if the data in the vertexsamplettaskffo is less than 3, blocking and the like until the glEndEnable is effective, executing S2.3;
s2.3: assembling the read vertexType/edgeFlag/cordinate/color data, and issuing the data to a geometry engine unit through a transaction-level interface;
s2.4: it is determined whether the glEndEnable is valid,
if the data is valid, sending a null packet to the geometry engine unit through the transaction-level interface, and ending;
if not, directly setting vertexAssembleBusy to 0, and ending.
The method for controlling GPU-oriented vertex output based on SystemC is characterized in that S3 includes:
s3.1: reading data;
s3.2: preparing data assembly;
s3.3: assembling the vertex types of the glRasterPos;
s3.4: glVertex vertex type assembly.
The system C-based GPU-oriented vertex output control method is characterized in that the S3.1 comprises the following steps:
s3.1.1: set vertexAssembleBusy 1;
s3.1.2: reading vertexcomplexttaskfifo data, and acquiring task information: slotId, vertexType, vertexMask;
wherein: vertexAssembleBusy indicates a vertex assembly state, 1 indicates busy, and 0 indicates idle;
the slot Id represents the slot task id;
the vertexType represents a vertex type and comprises two types of glRasterPos and glVertex;
vertexMask denotes a vertex mask.
The system C-based GPU-oriented vertex output control method is characterized in that the S3.2 comprises the following steps:
s3.2.1: the completion state of a task corresponding to the current slotId of the unified coloring unit is inquired through transaction-level interface blocking until the state is valid;
s3.2.2: reading the data of the uniform dyeing unit through a transaction-level interface, and reading the complete attribute of the data, wherein the complete attribute of one vertex specifically comprises the following steps: coordinates, a front main color, a front second color, a back main color, a back second color, texture coordinates 0, texture coordinates 1, texture coordinates 2, texture coordinates 3, texture coordinates 4, texture coordinates 5, fog coordinates, and boundary marks; and carrying out data format conversion;
s3.2.3: reading an attribute switch in a state parameter register unit through a transaction-level interface; FOgEn, lightingEn, textureEn 0-textureEn 5, colorSum.
Wherein fogEn represents a fog enable switch;
lightingEn denotes a lighting enable switch;
textureEn 0-textureEn 5 represent a 6-fold texture enable switch;
colorSum denotes a second color enable switch;
s3.2.4: it is determined whether the task type is glraterpos,
if so, executing S3.3,
otherwise, go to step S3.2.5;
s3.2.5: it is determined whether the task type is glVertex,
if so, go to step S3.4,
otherwise, ending.
The system cc-based GPU-oriented vertex output control method is characterized in that S3.3 includes:
s3.3.1 ignoring the switch state of the attribute, and sending the assembled and read data to the geometry engine unit through the transaction-level interface;
s3.3.2, clearing the corresponding slotId bit of the unified dyeing unit, and submitting the slotId task through the transaction interface to complete the task;
s3.3.3, judging the vertexcomplexttaskffo state:
if not, returning to S3.1;
otherwise, executing the vertexassmblebusy busy being equal to 0, and ending.
The system c-based GPU-oriented vertex output control method is characterized in that S3.4 includes:
s3.4.1 if the switch corresponding to the attribute is on, the assembled read data is sent to the geometry engine unit through the transaction interface;
if the switch corresponding to the attribute is off, neglecting and assembling the next attribute;
s3.4.2, clearing the corresponding slotId bit of the unified dyeing unit, and submitting the slotId task through the transaction interface to complete the task;
s3.4.3, judging the vertexcomplexttaskffo state:
if not, returning to the step S3.1;
otherwise, S3.4.4 is executed;
s3.4.4 judges whether or not glEndEnable is valid:
if the command is valid, processing the glEnd command, sending a null packet to the geometry engine unit through the transaction-level interface, setting vertexAssembleBusy to be 0, and ending;
otherwise, go back to S3.4.3 after waiting for one beat;
wherein: the glEndEnable indicates an enable flag of the glEnd command, and a value of 1 indicates valid and a value of 0 indicates invalid.
The invention provides a GPU-oriented vertex output control unit based on SystemC, which is characterized in that a TLM microstructure comprises an initialization module, a simple mode vertex output module and a complex mode vertex output module;
the simple mode vertex output module and the complex mode vertex output module are physically and logically independent and are connected with the initialization module through a transaction-level interface;
the initialization module is used for reading initial data;
the simple mode vertex output module is used for performing vertex output in a simple mode;
and the complex mode vertex output module is used for outputting the vertex in the complex mode.
The system C-based GPU-oriented vertex output control unit is characterized in that the vertex output control unit is connected with a PCIE bus unit, a state parameter management unit, a vertex task assembly unit, a uniform dyeing unit, a geometric engine unit and a state parameter register unit through an object level interface;
under the simple mode, data are input into a simple mode vertex output module in a vertex output control unit from a vertex task assembling unit and are output to a geometric engine unit after being assembled;
in the complex mode, task information is input into a complex mode vertex output module in a vertex output control unit from a vertex task assembling unit, data information is input into the complex mode vertex output module in the vertex output control unit from a uniform dyeing unit, attribute control information is input into the vertex output control unit from a state parameter register unit, and the attribute control information is output to a geometric engine unit after being uniformly assembled.
Finally, it should be noted that the above embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those skilled in the art; the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A GPU-oriented vertex output control method based on SystemC is characterized by comprising the following steps:
s1: reading initial data;
s2: vertex output assembly in a simple mode;
s3: vertex output packing in complex mode.
2. The SystemC-based GPU-oriented vertex output control method according to claim 1, wherein the S1 includes:
judging the states of vertexsamplettaskffo and vertexcomplexttaskffo, and if the states are both empty, circulating the step 1;
if vertexsamplettaskfiffo is not empty and vertexcomplexttaskffo is empty, then S2 is executed;
if vertexsampletatkfifo is empty and vertexcomplextatkfifo is not empty, then S3 is executed;
if vertexcempletaskfifo is not empty and vertexcomplex tasskfifo is not empty, the error exits;
wherein, vertexsampletatkffo represents an FIFO storing simple mode attribute data;
vertexcomplexttaskffo denotes a FIFO storing complex pattern attribute task information.
3. The SystemC-based GPU-oriented vertex output control method according to claim 1, wherein the S2 includes:
s2.1: set vertexAssembleBusy 1;
s2.2: continuously reading the vertexsamplettaskffo data for 3 times, and executing S2.3;
if the data in the vertexsamplettaskffo is less than 3, blocking and the like until the glEndEnable is effective, executing S2.3;
s2.3: assembling the read edgeFlag/coordinate/color/vertexType data, and issuing the data to a geometry engine unit through a transaction-level interface;
wherein edgeFlag represents a vertex boundary flag attribute;
coordinate represents a vertex coordinate attribute;
color represents the vertex color attribute;
the vertexType represents a vertex type and comprises two types of glRasterPos and glVertex;
s2.4: it is determined whether the glEndEnable is valid,
if the data is valid, sending a null packet to the geometry engine unit through the transaction-level interface, and ending;
if not, directly setting vertexAssembleBusy to 0, and ending.
4. The SystemC-based GPU-oriented vertex output control method according to claim 1, wherein the S3 includes:
s3.1: reading data;
s3.2: preparing data assembly;
s3.3: assembling the vertex types of the glRasterPos;
s3.4: glVertex vertex type assembly.
5. The SystemC-based GPU-oriented vertex output control method of claim 4, wherein the S3.1 comprises the following steps:
s3.1.1: set vertexAssembleBusy 1;
s3.1.2: reading vertexcomplexttaskfifo data, and acquiring task information: slotId, vertexType, vertexMask;
wherein: vertexAssembleBusy indicates a vertex assembly state, 1 indicates busy, and 0 indicates idle;
the slot Id represents the slot task id;
vertexMask denotes a vertex mask.
6. The SystemC-based GPU-oriented vertex output control method of claim 4, wherein the S3.2 comprises the steps of:
s3.2.1: the completion state of a task corresponding to the current slotId of the unified coloring unit is inquired through transaction-level interface blocking until the state is valid;
s3.2.2: reading the data of the uniform dyeing unit through the transaction-level interface, reading the complete attribute of the data, and performing data format conversion;
s3.2.3: reading an attribute switch in a state parameter register unit through a transaction-level interface;
s3.2.4: it is determined whether the task type is glraterpos,
if so, executing S3.3,
otherwise, go to step S3.2.5;
s3.2.5: it is determined whether the task type is glVertex,
if so, go to step S3.4,
otherwise, ending.
7. The SystemC-based GPU-oriented vertex output control method of claim 4, wherein the S3.3 comprises:
s3.3.1 ignoring the switch state of the attribute, and sending the assembled and read data to the geometry engine unit through the transaction-level interface;
s3.3.2, clearing the corresponding slotId bit of the unified dyeing unit, and submitting the slotId task through the transaction interface to complete the task;
s3.3.3, judging the vertexcomplexttaskffo state:
if not, returning to S3.1;
otherwise, executing the vertexassmblebusy busy being equal to 0, and ending.
8. The SystemC-based GPU-oriented vertex output control method of claim 4, wherein the S3.4 comprises:
s3.4.1 if the switch corresponding to the attribute is on, the assembled read data is sent to the geometry engine unit through the transaction interface;
if the switch corresponding to the attribute is off, neglecting and assembling the next attribute;
s3.4.2, clearing the corresponding slotId bit of the unified dyeing unit, and submitting the slotId task through the transaction interface to complete the task;
s3.4.3, judging the vertexcomplexttaskffo state:
if not, returning to the step S3.1;
otherwise, S3.4.4 is executed;
s3.4.4 judges whether or not glEndEnable is valid:
if the command is valid, processing the glEnd command, sending a null packet to the geometry engine unit through the transaction-level interface, setting vertexAssembleBusy to be 0, and ending;
otherwise, go back to S3.4.3 after waiting for one beat;
wherein: the glEndEnable indicates an enable flag of the glEnd command, and a value of 1 indicates valid and a value of 0 indicates invalid.
9. A GPU-oriented vertex output control unit based on SystemC is characterized in that the TLM microstructure comprises an initialization module, a simple mode vertex output module and a complex mode vertex output module;
the simple mode vertex output module and the complex mode vertex output module are physically and logically independent and are connected with the initialization module through a transaction-level interface;
the initialization module is used for reading initial data;
the simple mode vertex output module is used for performing vertex output in a simple mode;
and the complex mode vertex output module is used for outputting the vertex in the complex mode.
10. The SystemC-based GPU-oriented vertex output control unit of claim 9, wherein the vertex output control unit is connected to a PCIE bus unit, a state parameter management unit, a vertex task assembly unit, a uniform dyeing unit, a geometry engine unit, and a state parameter register unit through a transaction interface;
under the simple mode, data are input into a simple mode vertex output module in a vertex output control unit from a vertex task assembling unit and are output to a geometric engine unit after being assembled;
in the complex mode, task information is input into a complex mode vertex output module in a vertex output control unit from a vertex task assembling unit, data information is input into the complex mode vertex output module in the vertex output control unit from a uniform dyeing unit, attribute control information is input into the vertex output control unit from a state parameter register unit, and the attribute control information is output to a geometric engine unit after being uniformly assembled.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911125627.9A CN111028128B (en) | 2019-11-18 | 2019-11-18 | GPU-oriented vertex output control method and unit based on SystemC |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911125627.9A CN111028128B (en) | 2019-11-18 | 2019-11-18 | GPU-oriented vertex output control method and unit based on SystemC |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111028128A true CN111028128A (en) | 2020-04-17 |
| CN111028128B CN111028128B (en) | 2023-10-17 |
Family
ID=70200318
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911125627.9A Active CN111028128B (en) | 2019-11-18 | 2019-11-18 | GPU-oriented vertex output control method and unit based on SystemC |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111028128B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112581577A (en) * | 2020-12-05 | 2021-03-30 | 西安翔腾微电子科技有限公司 | GPU (graphics processing Unit) chip element output control TLM (transport layer Module) device based on SystemC (System chip) and operation method |
| CN112634422A (en) * | 2020-12-24 | 2021-04-09 | 西安翔腾微电子科技有限公司 | TLM device of GPU output control module based on SysML view and operation method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6717577B1 (en) * | 1999-10-28 | 2004-04-06 | Nintendo Co., Ltd. | Vertex cache for 3D computer graphics |
| CN108109103A (en) * | 2017-12-06 | 2018-06-01 | 中国航空工业集团公司西安航空计算技术研究所 | A kind of high-performance GPU dyeing tasks and unified dyeing array task scene mapping structure |
| CN108154461A (en) * | 2017-12-06 | 2018-06-12 | 中国航空工业集团公司西安航空计算技术研究所 | A kind of low-power consumption GPU dyeing tasks and unified dyeing array task scene mapping structure |
| CN109669769A (en) * | 2018-12-12 | 2019-04-23 | 中国航空工业集团公司西安航空计算技术研究所 | One kind is based on SystemC towards GPU vertex coloring method for scheduling task |
| CN109710398A (en) * | 2018-12-12 | 2019-05-03 | 中国航空工业集团公司西安航空计算技术研究所 | It is a kind of based on UML towards GPU vertex coloring method for scheduling task |
| CN109727186A (en) * | 2018-12-12 | 2019-05-07 | 中国航空工业集团公司西安航空计算技术研究所 | One kind is based on SystemC towards GPU piece member colouring task dispatching method |
-
2019
- 2019-11-18 CN CN201911125627.9A patent/CN111028128B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6717577B1 (en) * | 1999-10-28 | 2004-04-06 | Nintendo Co., Ltd. | Vertex cache for 3D computer graphics |
| CN108109103A (en) * | 2017-12-06 | 2018-06-01 | 中国航空工业集团公司西安航空计算技术研究所 | A kind of high-performance GPU dyeing tasks and unified dyeing array task scene mapping structure |
| CN108154461A (en) * | 2017-12-06 | 2018-06-12 | 中国航空工业集团公司西安航空计算技术研究所 | A kind of low-power consumption GPU dyeing tasks and unified dyeing array task scene mapping structure |
| CN109669769A (en) * | 2018-12-12 | 2019-04-23 | 中国航空工业集团公司西安航空计算技术研究所 | One kind is based on SystemC towards GPU vertex coloring method for scheduling task |
| CN109710398A (en) * | 2018-12-12 | 2019-05-03 | 中国航空工业集团公司西安航空计算技术研究所 | It is a kind of based on UML towards GPU vertex coloring method for scheduling task |
| CN109727186A (en) * | 2018-12-12 | 2019-05-07 | 中国航空工业集团公司西安航空计算技术研究所 | One kind is based on SystemC towards GPU piece member colouring task dispatching method |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112581577A (en) * | 2020-12-05 | 2021-03-30 | 西安翔腾微电子科技有限公司 | GPU (graphics processing Unit) chip element output control TLM (transport layer Module) device based on SystemC (System chip) and operation method |
| CN112634422A (en) * | 2020-12-24 | 2021-04-09 | 西安翔腾微电子科技有限公司 | TLM device of GPU output control module based on SysML view and operation method |
| CN112634422B (en) * | 2020-12-24 | 2024-02-23 | 西安翔腾微电子科技有限公司 | TLM device of GPU output control module based on SysML view and operation method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111028128B (en) | 2023-10-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109669769B (en) | GPU vertex coloring task scheduling method based on SystemC | |
| US7523023B1 (en) | Automatic generation of component interfaces for computational hardware implementations generated from a block diagram model | |
| CN109727186B (en) | SystemC-based GPU (graphics processing Unit) fragment coloring task scheduling method | |
| CN109840878B (en) | GPU parameter management method based on SystemC | |
| CN113656227B (en) | Chip verification method and device, electronic equipment and storage medium | |
| CN109669832A (en) | One kind is towards GPU graphics chip pipeline unit performance verification method and platform | |
| CN109598077A (en) | A kind of graphics pipeline device and modeling method based on GPU chip | |
| JPH11513512A (en) | Method of manufacturing digital signal processor | |
| CN103886538A (en) | Technique For Storing Shared Vertices | |
| CN111028128A (en) | GPU (graphics processing Unit) -oriented vertex output control method and unit based on SystemC | |
| CN109711003A (en) | One kind is towards GPU graphics chip pipeline unit functional simulation method and platform | |
| CN110765715B (en) | GPU chip rendering output unit performance simulation method and platform | |
| CN111062173A (en) | GPU chip-oriented rendering output unit function simulation method and platform | |
| CN112581585B (en) | TLM device of GPU command processing module based on SysML view and operation method | |
| WO2018080735A2 (en) | Method, apparatus and system for automatically performing end-to-end channel mapping for an interconnect | |
| CN111028132B (en) | System C-based GPU command processor unit hardware TLM microstructure | |
| CN117933328A (en) | Hardware accelerator, chip and computer equipment suitable for machine learning | |
| CN109346028B (en) | TLM-based triangular raster scanning structure | |
| CN109710398B (en) | GPU (graphics processing Unit) -oriented vertex coloring task scheduling method based on UML (unified modeling language) | |
| CN101918982B (en) | Efficient state management for a graphics pipeline | |
| CN112581576B (en) | GPU shielding query TLM device based on SystemC and operation method | |
| CN111242832B (en) | System C-based GPU texture mapping period accurate joint simulation device and method | |
| CN110942478B (en) | Texture integrity calculation method and calculation unit based on SystemC | |
| Juurlink et al. | GRAAL: A framework for low-power 3D graphics accelerators | |
| CN112581577A (en) | GPU (graphics processing Unit) chip element output control TLM (transport layer Module) device based on SystemC (System chip) and operation method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |