Abstract:
An apparatus and method for tile binning are provided. The tile binning apparatus may include a determination unit to determine whether a triangle obtained as a result of geometric processing includes an abnormal edge, an overlap test unit to perform an overlap test with respect to each edge of the triangle when the abnormal edge is absent from the triangle, and to sort three vertices of the triangle according to Y-axis values and perform the overlap test with respect to each edge of the triangle based on a sorting result when the triangle includes the abnormal edge, and a bin array update unit to update a bin array based on an overlap test result.
Abstract:
An operating method of a computational storage device includes: setting a first computing namespace, including a first queue and a first accelerator and having a first value as its first ID, per instructions from a first host; setting a second computing namespace, including a second queue and a second accelerator and having a second value as its first ID, per instructions from a second host; loading a first program from the first host in the first computing namespace; loading a second program from the second host in the second computing namespace; setting a second ID of the first computing namespace to a third value based on an ID of the first program per instructions to activate the first program; and setting the second ID of the second computing namespace to a fourth value based on an ID of the second program per instructions to activate the second program.
Abstract:
Fragment merging is performed on a draw call basis. One application is for quad merging. Primitives of the same draw call have many common attributes, such as a graphics state, which facilitates merging of quad fragments. Partially covered quad fragments of the same draw call are considered for possible merging and at least one merge test performed. The merge test may include error tests such as a level of detail error test, interpolated depth, and an interpolation error test.
Abstract:
An apparatus and method for processing a primitive in a three-dimensional (3D) graphics rendering system is provided. The primitive processing apparatus may discard a primitive or store the primitive in a memory, depending on whether a sampling point overlapping the primitive is present among sampling points in a pixel area.
Abstract:
A rendering system and method. The rendering system may perform rendering using a rendering context stored in an internal memory. When a rendering context to be used is not available in the internal memory, the rendering system may load the rendering context to be used from an external memory into the internal memory. When an insufficient amount of storage space is available in the internal memory, storage space may be secured by selectively deleting a rendering context from the internal memory, and a requested rendering context stored in the external memory may be loaded into the internal memory.
Abstract:
A method and apparatus for controlling a fragment that controls processing of a fragment during a graphic rendering process. The method of controlling the fragment includes determining whether to process a second fragment, based on flag data representing a processing state of a first fragment, and updating the flag data based on a processing state of at least one of the first fragment and the second fragment, wherein the first fragment and the second fragment refer to fragments representing an identical spatial location among fragments included in differing primitives in a frame.
Abstract:
An apparatus and method for non-blocking execution of a static scheduled processor, the apparatus including a processor to process at least one operation using transferred input data, and an input buffer used to transfer the input data to the processor, and store a result of processing the at least one operation, wherein the processor may include at least one functional unit (FU) to execute the at least one operation, and the at least one FU may process the transferred input data using at least one of a regular latency operation and an irregular latency operation.
Abstract:
A method and apparatus for configuring dynamic data are provided. A compilation apparatus may select a data format showing an optimum performance when a binary code is executed, from among a plurality of data formats supported by an execution apparatus used to execute a binary code, and may generate a binary code that uses the selected data format. The execution apparatus may execute a binary code provided by the compilation apparatus.