IP Library Granted Patent US 10,162,642
Granted Patent B2
US 10,162,642 · App. 14/172,839 · Granted Dec 25, 2018

Shader with global and instruction caches

View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,162,642
App. No.
14/172,839
Granted
Dec 25, 2018
Kind
B2
Abstract

An instruction cache and data cache used to virtualize the storage of global data and instructions used by graphics shaders. Present day hardware design stores the global data and instructions used by the shaders in a fixed amount of registers or writable control store (WCS). However, this traditional approach limits the size and the complexity of the shaders that can be supported. By virtualizing the storage of the global data and instructions, the amount of global or state memory available to the shader and the length of the shading programs are no longer constrained by the physical on-chip memory.

Claims (12)

1. A 3D graphics processing system comprising:

a fragment shading unit configured to perform shading operations, the fragment shading unit being further configured to run multiple shaders, each shader being run as a separate thread for a shading operation;

a first on chip cache internal to the fragment shading unit and configured to store cached instruction used by the fragment shading unit; and

a second on chip cache internal to the fragment shading unit and configured to store global data used by the fragment shading unit, wherein the global data is used by multiple shaders;

wherein the fragment shading unit is further configured to switch operations between the multiple threads upon the occurrence of a cache miss.

2. The system of claim 1 , wherein the fragment shading unit is configured to read data from an external memory when a cache miss occurs.

3. The system of claim 1 , wherein said first and second caches may be accessed in parallel.

4. The system of claim 1 , wherein a shader is run once per active sub tile.

5. The system of claim 2 , further comprising a memory arbiter that manages virtual memory and performs data swapping if a miss occurs.

6. The system of claim 1 , further comprising a third cache configured to handle data other than the instructions and global data handled by the first and second caches.

7. The system of claim 1 , wherein the fragment shading unit is configured to suspend the current thread if the required data is unavailable from the on chip caches in a predetermined time period.

8. The system of claim 1 , wherein a sequencer checks for data in the first cache and second cache.

Assignments (8)
RELEASE OF SECURITY INTEREST IN SPECIFIED PATENTS Recorded May 10, 2022
From: BARINGS FINANCE LLC
To: RPX CLEARINGHOUSE LLC
Reel/Frame 059925/0652 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 18, 2021
From: MEDIATEK INC.
To: XUESHAN TECHNOLOGIES INC.
Reel/Frame 056593/0167 →
PATENT SECURITY AGREEMENT Recorded Oct 23, 2020
From: RPX CLEARINGHOUSE LLC; RPX CORPORATION
To: BARINGS FINANCE LLC, AS COLLATERAL AGENT
Reel/Frame 054244/0566 →
PATENT SECURITY AGREEMENT Recorded Oct 23, 2020
From: RPX CLEARINGHOUSE LLC; RPX CORPORATION
To: BARINGS FINANCE LLC, AS COLLATERAL AGENT
Reel/Frame 054198/0029 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 21, 2020
From: RPX CORPORATION
To: MEDIATEK INC.
Reel/Frame 054152/0888 →
RELEASE OF LIEN ON PATENTS Recorded Aug 14, 2020
From: JEFFERIES FINANCE LLC, AS COLLATERAL AGENT
To: RPX CORPORATION
Reel/Frame 053498/0067 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 5, 2020
From: RPX CORPORATION
To: MEDIATEK INC.
Reel/Frame 054107/0830 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 19, 2019
From: ZIILABS INC., LTD
To: RPX CORPORATION
Reel/Frame 048947/0592 →