Advanced Micro Devices Corporation

Ati Technologies Ulc

Ati International Srl

Intel Corporation

Ati Technologies Inc.

Real 3-d

Advanced Micro Devices (shanghai) Co., Ltd.

Sony Interactive Entertainment Inc.

Michael Mantor

Mark M Leather

Rex Eldon McCrary

Mark Fowler

Robert Scott Hartog

Bin He

Michael Andrew Mang

Brian D Emberling

Ralph Clay Taylor

Jiasheng Chen

Laurent Lefebvre

Philip J Rogers

Nuwan S Jayasena

Ralph Clayton Taylor

Sebastien Nussbaum

Jeffrey T Brady

Thomas R Woller

Kevin John McGrath

Mika Tuomi

Angel E Socarras

Anthony Asaro

Mangesh P Nijasure

Allen H Rush

Kiia Kaappoo Kallio

YunXiao Zou

Mikko Alho

Todd Martin

Anirudh Rajendra Acharya

Sateesh Lagudu

Thomas A Piazza

Timour T Paltashev

Randy Wayne Ramsey

Arun Vaidyanathan Ananthanarayan

Patrick Klas Rudolf Buss

Jari Antero Komppa

Kaj Tuomi

Val Gene Cook

Alexander Fuad Ashkar

Timothy Kelley

John Kalamatianos

Vineet Goel

James Michael O'Connor

Christopher Jude Brennan

Benjamin T Sander

Sudhanva Gurumurthi

Maxim V Kazakov

Benedict R Gaster

Michael C Houston

Jeffrey Gongxian Cheng

Lee W Howes

Gongxian Jeffrey Cheng

Harry J Wise

Norman Rubin

Qingcheng Wang

Prasad Nagabhushanamgari

Marcos Zini

Carl Kittredge Wakeland

Alexander Lyashevsky

Swapnil Pradipkumar Sakharshete

Wei Yuan

Christopher L Spencer

John A Carey

Jian Huang

Tushar K Shah

Jeffrey D Potter

Daniel Clifton

Karl Mann

R Scott Hartog

Samuel D Naffziger

Andrew Evan Gruber

Gabriel H Loh

Mark Evan Cerny

Rahul Kumar Agarwal

Aditya Sreenivas

David Simpson

Raja Koduri

Alan Dodson Smith

Anthony P DeLaurier

Radhakrishna Giduthuri

John T Pedicone

Kostantinos Danny Christidis

Daniel Wong

Jason Scanlin

Nishank Pathak

Raja Swaminathan

Tad Robert Litwiller

Gabriel Wong

Kam Leung

Brian D Rauchfuss

Kiia Kallio

Michael S Alfano

Robert W Martin

Matthaeus G Chajdas

Rostyslav Kyrychynskyi

Ashkan Hosseinzadeh Namin

Konstantin Igorevich Shkurko

Syed Zohaib M Gilani

Sajjad A Zaidi

Chao Liu

Nicolai Haehnle

A method, computer system, and a non-transitory computer-readable storage medium for performing primitive batch binning are disclosed. The method, computer system, and non-transitory computer-readable storage medium include techniques for generating a primitive batch from a plurality of primitives, computing respective bin intercepts for each of the plurality of primitives in the primitive batch, and shading the primitive batch by iteratively processing each of the respective bin intercepts computed until all of the respective bin intercepts are processed.

Hybrid render with deferred primitive batch binning

A graphics processing unit (GPU) of a processing system is partitioned into multiple dies (referred to as GPU chiplets) that are configurable to collectively function and interface with an application as a single GPU in a first mode and as multiple GPUs in a second mode. By dividing the GPU into multiple GPU chiplets, the processing system flexibly and cost-effectively configures an amount of active GPU physical resources based on an operating mode. In addition, a configurable number of GPU chiplets are assembled into a single GPU, such that multiple different GPUs having different numbers of GPU chiplets can be assembled using a small number of tape-outs and a multiple-die GPU can be constructed out of GPU chiplets that implement varying generations of technology.

Configurable multiple-die graphics processing unit

An array processor includes processor element arrays distributed in rows and columns. The processor element arrays perform operations on parameter values. The array processor also includes memory interfaces that broadcast sets of the parameter values to mutually exclusive subsets of the rows and columns of the processor element arrays. In some cases, the array processor includes single-instruction-multiple-data (SIMD) units including subsets of the processor element arrays in corresponding rows, workgroup processors (WGPs) including subsets of the SIMD units, and a memory fabric configured to interconnect with an external memory that stores the parameter values. The memory interfaces broadcast the parameter values to the SIMD units that include the processor element arrays in rows associated with the memory interfaces and columns of processor element arrays that are implemented across the SIMD units in the WGPs. The memory interfaces access the parameter values from the external memory via the memory fabric.

Vertical and horizontal broadcast of shared operands

A processing system executes wavefronts at multiple arithmetic logic unit (ALU) pipelines of a single instruction multiple data (SIMD) unit in a single execution cycle. The ALU pipelines each include a number of ALUs that execute instructions on wavefront operands that are collected from vector general process register (VGPR) banks at a cache and output results of the instructions executed on the wavefronts at a buffer. By storing wavefronts supplied by the VGPR banks at the cache, a greater number of wavefronts can be made available to the SIMD unit without increasing the VGPR bandwidth, enabling multiple ALU pipelines to execute instructions during a single execution cycle.

Dual vector arithmetic logic unit

A graphics processing unit (GPU) includes a plurality of programmable processing cores configured to process graphics primitives and corresponding data and a plurality of fixed-function hardware units. The plurality of processing cores and the plurality of fixed-function hardware units are configured to implement a configurable number of virtual pipelines to concurrently process different command flows. Each virtual pipeline includes a configurable number of fragments and an operational state of each virtual pipeline is specified by a different context. The configurable number of virtual pipelines can be modified from a first number to a second number that is different than the first number. An emulation of a fixed-function hardware unit can be instantiated on one or more of the graphics processing cores in response to detection of a bottleneck in a fixed-function hardware unit. One or more of the virtual pipelines can then be reconfigured to utilize the emulation instead of the fixed-function hardware unit.

Reconfigurable virtual graphics and compute processor pipeline

Block data load with transpose techniques are described. In one example, an input is received, at a control unit, specifying an instruction to load a block of data to at least one memory module using a transpose operation. Responsive to the receiving the input by the control unit, the block of data is caused to be loaded to the at least one memory module by transposing the block of data to form a transposed block of data and storing the transposed block of data in the at least one memory.

Block data load with transpose into memory

A parallel processing unit employs an arithmetic logic unit (ALU) having a relatively small footprint, thereby reducing the overall power consumption and circuit area of the processing unit. To support the smaller footprint, the ALU includes multiple stages to execute operations corresponding to a received instruction. The ALU executes at least one operation at a precision indicated by the received instruction, and then reduces the resulting data of the at least one operation to a smaller size before providing the results to another stage of the ALU to continue execution of the instruction.

Processing unit with small footprint arithmetic logic unit

A graphics processing unit (GPU) or other apparatus includes a plurality of shader engines. The apparatus also includes a first front end (FE) circuit and one or more second FE circuits. The first FE circuit is configured to schedule geometry workloads for the plurality of shader engines in a first mode. The first FE circuit is configured to schedule geometry workloads for a first subset of the plurality of shader engines and the one or more second FE circuits are configured to schedule geometry workloads for a second subset of the plurality of shader engines in a second mode. In some cases, a partition switch is configured to selectively connect the first FE circuit or the one or more second FE circuits to the second subset of the plurality of shader engines depending on whether the apparatus is in the first mode or the second mode.

Spatial partitioning in a multi-tenancy graphics processing unit

Systems, apparatuses, and methods for preemptively reserving buffer space for primitives and positions in a graphics pipeline are disclosed. A system includes a graphics pipeline frontend with any number of geometry engines coupled to corresponding shader engines. Each geometry engine launches shader wavefronts to execute on a corresponding shader engine. The geometry engine preemptively reserves buffer space for each wavefront prior to the wavefront being launched on the shader engine. When the shader engine executes a wavefront, the shader engine exports primitive and position data to the reserved buffer space. Multiple scan converters will consume the primitive and position data, with each scan converter consuming primitive and position data based on the screen coverage of the scan converter. After consuming the primitive and position data, the scan converters mark the buffer space as freed so that the geometry engine can then allocate the freed buffer space to subsequent shader wavefronts.

Graphics primitives and positions through memory buffers

A method for hierarchical work scheduling includes consuming a work item at a first scheduling domain having a local scheduler circuit and one or more workgroup processing elements. Consuming the work item produces a set of new work items. Subsequently, the local scheduler circuit distributes at least one new work item of the set of new work items to be executed locally at the first scheduling domain. If the local scheduler circuit of the first scheduling domain determines that the set of new work items includes one or more work items that would overload the first scheduling domain with work if scheduled for local execution, those work items are distributed to the next higher-level scheduler circuit in a scheduling domain hierarchy for redistribution to one or more other scheduling domains.

Hierarchical work scheduling

Systems, apparatuses, and methods for abstracting tasks in virtual memory identifier (VMID) containers are disclosed. A processor coupled to a memory executes a plurality of concurrent tasks including a first task. Responsive to detecting one or more instructions of the first task which correspond to a first operation, the processor retrieves a first identifier (ID) which is used to uniquely identify the first task, wherein the first ID is transparent to the first task. Then, the processor maps the first ID to a second ID and/or a third ID. The processor completes the first operation by using the second ID and/or the third ID to identify the first task to at least a first data structure. In one implementation, the first operation is a memory access operation and the first data structure is a set of page tables. Also, in one implementation, the second ID identifies a first application of the first task and the third ID identifies a first operating system (OS) of the first task.

VMID as a GPU task container for virtualization

Systems, apparatuses, and methods for implementing a low power parallel matrix multiply pipeline are disclosed. In one embodiment, a system includes at least first and second vector register files coupled to a matrix multiply pipeline. The matrix multiply pipeline comprises a plurality of dot product units. The dot product units are configured to calculate dot or outer products for first and second sets of operands retrieved from the first vector register file. The results of the dot or outer product operations are written back to the second vector register file. The second vector register file provides the results from the previous dot or outer product operations as inputs to subsequent dot or outer product operations. The dot product units receive the results from previous phases of the matrix multiply operation and accumulate these previous dot or outer product results with the current dot or outer product results.

Stream processor with low power parallel matrix multiply pipeline

A processor maintains an access log indicating a stream of cache misses at a cache of the processor. In response to each of at least a subset of cache misses at the cache, the processor records a corresponding entry in the access log, indicating a physical memory address of the memory access request that resulted in the corresponding miss. In addition, the processor maintains an address translation log that indicates a mapping of physical memory addresses to virtual memory addresses. In response to an address translation (e.g., a page walk) that translates a virtual address to a physical address, the processor stores a mapping of the physical address to the corresponding virtual address at an entry of the address translation log. Software executing at the processor can use the two logs for memory management.

Access log and address translation log for a processor

A processing system includes a first set and a second set of general-purpose registers (GPRs) and memory access circuitry that fetches nonzero values of a sparse matrix into consecutive slots in the first set. The memory access circuitry also fetches values of an expanded matrix into consecutive slots in the second set of GPRs. The expanded matrix is formed based on values of a vector and locations of the nonzero values in the sparse matrix. The processing system also includes a set of multipliers that concurrently perform multiplication of the nonzero values in slots of the first set of GPRs with the values of the vector in corresponding slots of the second set. Reduced sum circuitry accumulates results from the set of multipliers for rows of the sparse matrix.

Sparse matrix-vector multiplication

A method, system, and non-transitory computer readable storage medium for rasterizing primitives are disclosed. The method, system, and non-transitory computer readable storage medium includes: generating a primitive batch from a sequence of one or more primitives, wherein the primitive batch includes primitives sorted into one or more row groups based on which row of a plurality of rows each primitive intersects; and processing each row group, the processing for each row group including: identifying one or more primitive column intercepts for each of the one or more primitives in the row group, wherein each combination of primitive column intercept and row identifies a bin; and rasterizing the one or more primitives that intersect the bin.

Hybrid render with preferred primitive batch binning and sorting

Growing community of inventors

Orlando, FL, United States of America

Michael Mantor