公开(公告)号：US20210358072A1

公开(公告)日：2021-11-18

申请号：US16931435

申请日：2020-07-16

Applicant: Samsung Electronics Co., Ltd.

Inventor： Veynu NARASIMAN ,  David TANNENBAUM ,  Keshavan VARADARAJAN

IPC: G06T1/20 ,  G06T15/80 ,  G06T15/00

Abstract: A method of executing an early-Z draw call in a graphics processing pipeline may include detecting a late-Z draw call in the pipeline, determining a compatibility of a depth comparison function of the early-Z draw call with a depth comparison function of the late-Z draw call, and speculatively executing a fragment of the early-Z draw call with a shader. The method may further include determining that the fragment of the early-Z draw call passes the depth comparison function of the early-Z draw call, and updating a depth buffer with a depth value for the fragment of the early-Z draw call. The method may further include determining that the fragment of the early-Z draw call provides a correct result, and forwarding the speculative shader result for the fragment to a next stage of the pipeline.

公开(公告)号：US20220301095A1

公开(公告)日：2022-09-22

申请号：US17357964

申请日：2021-06-24

Applicant: Samsung Electronics Co., Ltd.

Inventor： Gabriel T. DAGANI ,  Christopher P. FRASCATI ,  FNU GURUPAD ,  David TANNENBAUM ,  Rama S.B. HARIHARA ,  Keshavan VARADARAJAN

IPC: G06T1/20 ,  G06F9/48

Abstract: A system and a method are disclosed improving forward progress of preempted workloads. A graphics pipeline processes tiles of a first low-priority job. A controller stops the first job by resetting the GPU and preempting the first job with a second job having a higher priority, determine whether the first job has been previously preempted one or more times, and adjust a batch-binning parameter reducing a likelihood that the first job will again be preempted in the current frame. In one embodiment, the controller is configured to stop the first job at a preemption boundary during a draw call or by resetting the GPU. A batch-binning parameter may include postponing sorting primitives into tiles during a binning process, increasing a number of tiles for backend rendering, reducing a quality of anti-aliasing, decreasing a shading rate quality, and/or decreasing input resolution and increasing upscaling of the first job.

公开(公告)号：US20250022090A1

公开(公告)日：2025-01-16

申请号：US18751186

申请日：2024-06-21

Applicant: Samsung Electronics Co., Ltd.

Inventor： Gabriel T. DAGANI ,  Christopher P. FRASCATI ,  FNU GURUPAD ,  David TANNENBAUM ,  Rama S.B. HARIHARA ,  Keshavan VARADARAJAN

IPC: G06T1/20 ,  G06F9/48

Abstract: A system and a method are disclosed improving forward progress of preempted workloads. A graphics pipeline processes tiles of a first low-priority job. A controller stops the first job by resetting the GPU and preempting the first job with a second job having a higher priority, determine whether the first job has been previously preempted one or more times, and adjust a batch-binning parameter reducing a likelihood that the first job will again be preempted in the current frame. In one embodiment, the controller is configured to stop the first job at a preemption boundary during a draw call or by resetting the GPU. A batch-binning parameter may include postponing sorting primitives into tiles during a binning process, increasing a number of tiles for backend rendering, reducing a quality of anti-aliasing, decreasing a shading rate quality, and/or decreasing input resolution and increasing upscaling of the first job.

公开(公告)号：US20210343052A1

公开(公告)日：2021-11-04

申请号：US17029016

申请日：2020-09-22

Applicant: Samsung Electronics Co., Ltd.

Inventor： Derek J. LENTZ ,  David TANNENBAUM

IPC: G06T11/00 ,  G06F9/48 ,  G06F7/523 ,  G06T1/20

Abstract: A method for performing a blending operation in a graphics processing unit may include multiplying a first value and a first blend factor for a component of a render target with a first multiply operation of a multiplier, multiplying a second value and a second blend factor for the component of the render target with a second multiply operation of the multiplier, and adding a first result of the first multiply operation and a second result of the second multiply operation. The method may further include bypassing the multiplier for a first blend factor of substantially zero. The method may further include, for a blend factor of substantially one: bypassing the multiplier, and providing the first value of the component of the render target as a result of the first multiply operation.

公开(公告)号：US20210327118A1

公开(公告)日：2021-10-21

申请号：US16930310

申请日：2020-07-15

Applicant: Samsung Electronics Co., Ltd.

Inventor： Keshavan VARADARAJAN ,  David TANNENBAUM ,  Srinidhi PADMANABHAN

IPC: G06T15/06 ,  G06T15/00 ,  G06T1/20

Abstract: A system and a method are disclosed for ray tracing in a pipeline of a graphic processing unit (GPU). It is determined whether a ray bounce of a first ray intersects a first primitive that is the closest primitive intersected by the ray bounce. The first ray is part of a first group of rays being processed by a first single-instruction-multiple-data (SIMD) process. The first ray is assigned by a sorting or binning unit to a second group of rays based on the intersection of the first primitive. The second group of rays is processed by a second SIMD process. The first ray is assigned to the second group of rays based on a material identification of the first primitive, an identification of the first primitive intersected by the ray bound of the first ray, a pixel location, and a bounce number of the ray bounce intersecting the first primitive.