Sun Microsystems, Inc.

Advanced Micro Devices Corporation

Oracle America, Inc.

Ati Technologies Ulc

Brian D Emberling

Michael Mantor

Michael G Lavelle

Ewa M Kubalska

Mark M Leather

Michael Wasserman

Bin He

David C Kehlet

Anthony S Ramirez

Mark Fowler

Michael C Houston

Mark E Pascual

Norman Rubin

Wayne Eric Burk

Joseph Lee Greathouse

Nathaniel David Naegle

Anthony T Gutierrez

Mangesh P Nijasure

Benedict R Gaster

Randy Wayne Ramsey

Jiasheng Chen

Alexander Fuad Ashkar

Lee W Howes

Stanislaw K Skowronek

Nandini Ramani

Radhakrishna Giduthuri

YunXiao Zou

Assana Fard

Deron D Johnson

Thomas W Bowman

Roger Swanson

Stephen David Presant

Rashad Oreifej

Wayne A Morse

Ranjit S Oberoi

Ali Ibrahim

Andre J Gaytan

Michael Y Chow

Paul R Ramsey

Andrew V Brown

Krishna Sitaraman

Marcos Zini

Tushar K Shah

Chao Liu

Eric J Finger

Elaine Poon

Jeff Herman

John McCardle

Rangit S Oberoi

Steve Kurihara

Liang Huang

Seth Hendrickson

Michael J Mantor

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

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

Systems, apparatuses, and methods for implementing register compaction with early release are disclosed. A processor includes at least a command processor, a plurality of compute units, a plurality of registers, and a control unit. Registers are statically allocated to wavefronts by the control unit when wavefronts are launched by the command processor on the compute units. In response to determining that a first set of registers, previously allocated to a first wavefront, are no longer needed, the first wavefront executes an instruction to release the first set of registers. The control unit detects the executed instruction and releases the first set of registers to the available pool of registers to potentially be used by other wavefronts. Then, the control unit can allocate the first set of registers to a second wavefront for use by threads of the second wavefront while the first wavefront is still active.

Register compaction with early release

Methods and systems are disclosed for executing a collaborative task in a shader system. Techniques disclosed include receiving, by the system, input data and computing instructions associated with the collaborative task, as well as a configuration setting, causing the system to operate in a takeover mode. The system then launches, exclusively in one workgroup processor, a workgroup including wavefronts configured to execute the collaborative task.

System and methods for efficient execution of a collaborative task in a shader system

Systems, apparatuses, and methods for efficiently processing arithmetic operations are disclosed. A computing system includes a processor capable of executing single precision mathematical instructions on data sizes of M bits and half precision mathematical instructions on data sizes of N bits, which is less than M bits. At least two source operands with M bits indicated by a received instruction are read from a register file. If the instruction is a packed math instruction, at least a first source operand with a size of N bits less than M bits is selected from either a high portion or a low portion of one of the at least two source operands read from the register file. The instruction includes fields storing bits, each bit indicating the high portion or the low portion of a given source operand associated with a register identifier specified elsewhere in the instruction.

Packed 16 bits instruction pipeline

A software-based instruction scoreboard indicates dependencies between closely-issued instructions issued to an arithmetic logic unit (ALU) pipeline. The software-based instruction scoreboard inserts one or more control words into the command stream between the dependent instructions, which is then executed by the ALU pipeline. The control words identify the instruction(s) upon which the dependent instructions depend (parent instructions) so that the GPU hardware can ensure that the ALU pipeline does not stall while the dependent instruction waits for results from the parent instruction.

Software-based instruction scoreboard for arithmetic logic units

The address of the draw or dispatch packet responsible for creating an exception is tied to a shader/wavefront back to the draw command from which it originated. In various embodiments, a method of operating a graphics pipeline and exception handling includes receiving, at a command processor of a graphics processing unit (GPU), an exception signal indicating an occurrence of a pipeline exception at a shader stage of a graphics pipeline. The shader stage generates an exception signal in response to a pipeline exception and transmits the exception signal to the command processor. The command processor determines, based on the exception signal, an address of a command packet responsible for the occurrence of the pipeline exception.

Exception handler for sampling draw dispatch identifiers

A processing unit includes a plurality of processing elements and one or more caches. A first thread executes a program that includes one or more prefetch instructions to prefetch information into a first cache. Prefetching is selectively enabled when executing the first thread on a first processing element dependent upon whether one or more second threads previously executed the program on the first processing element. The first thread is then dispatched to execute the program on the first processing element. In some cases, a dispatcher receives the first thread four dispatching to the first processing element. The dispatcher modifies the prefetch instruction to disable prefetching into the first cache in response to the one or more second threads having previously executed the program on the first processing element.

Selective prefetching in multithreaded processing units

Systems, apparatuses, and methods for maintaining separate pending load and store counters are disclosed herein. In one embodiment, a system includes at least one execution unit, a memory subsystem, and a pair of counters for each thread of execution. In one embodiment, the system implements a software based approach for managing dependencies between instructions. In one embodiment, the execution unit(s) maintains counters to support the software-based approach for managing dependencies between instructions. The execution unit(s) are configured to execute instructions that are used to manage the dependencies during run-time. In one embodiment, the execution unit(s) execute wait instructions to wait until a given counter is equal to a specified value before continuing to execute the instruction sequence.

Wait instruction for preventing execution of one or more instructions until a load counter or store counter reaches a specified value

Systems, apparatuses, and methods for processing variable wavefront sizes on a processor are disclosed. In one embodiment, a processor includes at least a scheduler, cache, and multiple execution units. When operating in a first mode, the processor executes the same instruction on multiple portions of a wavefront before proceeding to the next instruction of the shader program. When operating in a second mode, the processor executes a set of instructions on a first portion of a wavefront. In the second mode, when the processor finishes executing the set of instructions on the first portion of the wavefront, the processor executes the set of instructions on a second portion of the wavefront, and so on until all portions of the wavefront have been processed. The processor determines the operating mode based on one or more conditions.

Indicating instruction scheduling mode for processing wavefront portions

A graphics processing unit is disclosed, the graphics processing unit having a processor having one or more SIMD processing units, and a local data share corresponding to one of the one or more SIMD processing units, the local data share comprising one or more low latency accessible memory regions for each group of threads assigned to one or more execution wavefronts, and a global data share comprising one or more low latency memory regions for each group of threads.

SIMD processing lanes storing input pixel operand data in local register file for thread execution of image processing operations

SIMD processing unit with local data share and access to a global data share of a GPU

A method of allocating a memory to a plurality of concurrent threads is presented. The method includes dynamically determining writer threads each having at least one pending write to the memory; and dynamically allocating respective contiguous blocks in the memory for each of the writer threads. Another method of allocating a memory to a plurality of concurrent threads includes launching the plurality of threads as a plurality of wavefronts, dynamically determining a group of wavefronts each having at least one thread requiring a write to the memory, and dynamically allocating respective contiguous blocks in the memory for each wavefront from the group of wavefronts. A corresponding method of assigning a memory to a plurality of reader threads includes determining a first number corresponding to a number of writer threads having a block allocated in said memory, launching a first number of reader threads, entering a first wavefront of said reader threads from said group of wavefronts to an atomic operation, and assigning a first block in the memory to the first wavefront during the corresponding atomic operation, where the first block is contiguous to a previously allocated block dynamically allocated to another wavefront from said group of wavefronts. Corresponding system embodiments and computer program product embodiments are also presented.

Interlocked increment memory allocation and access

Systems and methods to improve performance in a graphics processing unit are described herein. Embodiments achieve power saving in a graphics processing unit by dynamically activating/deactivating individual SIMDs in a shader complex that comprises multiple SIMD units. On-the-fly dynamic disabling and enabling of individual SIMDs provides flexibility in achieving a required performance and power level for a given processing application. Embodiments of the invention also achieve dynamic medium grain clock gating of SIMDs in a shader complex. Embodiments reduce switching power by shutting down clock trees to unused logic by providing a clock on demand mechanism. In this way, embodiments enhance clock gating to save more switching power for the duration of time when SIMDs are idle (or assigned no work). Embodiments can also save leakage power by power gating SIMDs for a duration when SIMDs are idle for an extended period of time.

Dynamic control of SIMDs

Growing community of inventors

Palo Alto, CA, United States of America

Brian D Emberling