Advanced Micro Devices Corporation

Ati Technologies Ulc

Anthony T Gutierrez

Vedula Venkata Srikant Bharadwaj

Yasuko Eckert

Sooraj Puthoor

Mark Henry Oskin

Karthik Ramu Sangaiah

Bradford Michael Beckmann

Salonik Resch

John Kalamatianos

Sergey Blagodurov

Shomit N Das

Vignesh Adhinarayanan

Matthew David Sinclair

Max Ruttenberg

Vendula Venkata Srikant Bharadwaj

Nuwan S Jayasena

Gabriel H Loh

Anthony Asaro

Brian D Emberling

David Allen Wood

Joseph Lee Greathouse

Johnathan R Alsop

Paul Blinzer

Ganesh Suryanarayan Dasika

Alexandru Dutu

Shrikanth Ganapathy

Jieming Yin

Muhammad Amber Hassaan

Xianwei Zhang

Sriseshan Srikanth

Millind Mittal

Nippon HarshadKumar Raval

Leopold Grinberg

Marcus Nathaniel Chow

Scott A Moe

Samuel Richard Bayliss

William Peter Ehrett

Prachi Shukla

A semiconductor device, referred to herein as a Globally Interconnected Operations (GIO) layer, provides global operations in the form of global data reduction for one or more PE arrays. The GIO layer includes processing elements that perform global data reduction on processing results from one or more PE arrays. The GIO layer includes connectors that allow it to be arranged in a 3D stack with one or more PE arrays, for example, on top of or beneath a PE array. This allows reduction operations to be implemented across PE arrays using an efficient topology with superior flexibility, scalability, latency and/or power characteristics that is customizable for particular use cases at assembly time, without requiring costly and time-consuming redesign of PE arrays, and without being constrained by particular PE array designs.

Semiconductor device for performing data reduction for processing arrays

An electronic device includes a quantum processor including a plurality of qubits. The quantum processor runs a plurality of instances of a quantum program using a separate set of qubits from among the qubits for each instance of the quantum program. The quantum processor then sets quantum states for ancilla qubits from among the qubits based on quantum states of respective groups of associated qubits from the separate sets of qubits. The quantum processor next provides an output of the instances of the quantum program based on the quantum states of the ancilla qubits.

Combining quantum states of qubits on a quantum processor

In accordance with the described techniques for extended attributes for shared page tables, a device includes an accelerator device and a memory management unit that maintains a first set of page tables and a second set of page tables. The second set of page tables includes extended attributes for accessing data that the accelerator device operates on. The memory management unit is configured to receive a virtual memory address, and translate the virtual memory address to a physical memory address using the first set of page tables. In addition, the memory management unit retrieves the extended attributes from the second set of page tables. In this way, data is accessed from the physical memory address based on the extended attributes.

Extended attributes for shared page tables

A processing system executes a specialized wavefront, referred to as a 'garbage collecting wavefront' or GCWF, to identify and deallocate resources such as, for example, scalar registers, vector registers, and local data share space, that are no longer being used by wavefronts of a workgroup executing at the processing system (i.e., dead resources). In some embodiments, the GCWF is programmed to have compiler information regarding the resource requirements of the other wavefronts of the workgroup and specifies the program counter after which there will be a permanent drop in resource requirements for the other wavefronts. In other embodiments, the standard compute wavefronts signal the GCWF when they have completed using resources. The GCWF sends a command to deallocate the dead resources so the dead resources can be made available for additional wavefronts.

Garbage collecting wavefront

Systems, methods, devices, and computer-implemented instructions for processor power management implemented in a compiler. In some implementations, a characteristic of code is determined. An instruction based on the determined characteristic is inserted into the code. The code and inserted instruction are compiled to generate compiled code. The compiled code is output.

Compiler directed fine grained power management

A technique for synchronizing workgroups is provided. Multiple workgroups execute a wait instruction that specifies a condition variable and a condition. A workgroup scheduler stops execution of a workgroup that executes a wait instruction and an advanced controller begins monitoring the condition variable. In response to the advanced controller detecting that the condition is met, the workgroup scheduler determines whether there is a high contention scenario, which occurs when the wait instruction is part of a mutual exclusion synchronization primitive and is detected by determining that there is a low number of updates to the condition variable prior to detecting that the condition has been met. In a high contention scenario, the workgroup scheduler wakes up one workgroup and schedules another workgroup to be woken up at a time in the future. In a non-contention scenario, more than one workgroup can be woken up at the same time.

Selective workgroup wake-up based on synchronization mechanism identification with high contention scenario

An electronic device includes a quantum processor having a plurality of qubits and a processor. The processor runs a plurality of instances of a quantum program substantially in parallel on the quantum processor using a separate set of qubits from among the plurality of qubits for each instance of the quantum program. The processor then acquires an output for each instance of the quantum program from the quantum processor. The processor next uses the outputs for generating an output of the quantum program.

Running instances of a quantum program concurrently on a quantum processor

A processor core is configured to execute a parent task that is described by a data structure stored in a memory. A coprocessor is configured to dispatch a child task to the at least one processor core in response to the coprocessor receiving a request from the parent task concurrently with the parent task executing on the at least one processor core. In some cases, the parent task registers the child task in a task pool and the child task is a future task that is configured to monitor a completion object and enqueue another task associated with the future task in response to detecting the completion object. The future task is configured to self-enqueue by adding a continuation future task to a continuation queue for subsequent execution in response to the future task failing to detect the completion object.

Hardware accelerated dynamic work creation on a graphics processing unit

A memory controller includes an arbiter, a vector arithmetic logic unit (VALU), a read buffer and a write buffer both coupled to the VALU, and an atomic memory operation scheduler. The VALU performs scattered atomic memory operations on arrays of data elements responsive to selected memory access commands. The atomic memory operation scheduler is for scheduling atomic memory operations at the VALU; identifying a plurality of scattered atomic memory operations with commutative and associative properties, the plurality of scattered atomic memory operations on at least one element of an array of data elements associated with an address; and commanding the VALU to perform the plurality of scattered atomic memory operations.

Accelerating relaxed remote atomics on multiple writer operations

A processor distributes memory timing parameters and data among different memory modules based upon memory access patterns. The memory access patterns indicate different types, or classes, of data for an executing workload, with each class associated with different memory access characteristics, such as different row buffer hit rate levels, different frequencies of access, different criticalities, and the like. The processor assigns each memory module to a data class and sets the memory timing parameters for each memory module according to the module's assigned data class, thereby tailoring the memory timing parameters for efficient access of the corresponding data.

Distribution of data and memory timing parameters across memory modules based on memory access patterns

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

A dynamically configurable overprovisioned microprocessor optimally supports a variety of different compute application workloads and with the capability to tradeoff among compute performance, energy consumption, and clock frequency on a per-compute application basis, using general-purpose microprocessor designs. In some embodiments, the overprovisioned microprocessor comprises a physical compute resource and a dynamic configuration logic configured to: detect an activation-warranting operating condition; undarken the physical compute resource responsive to detecting the activation-warranting operating condition; detect a configuration-warranting operating condition; and configure the overprovisioned microprocessor to use the undarkened physical compute resource responsive to detecting the configuration-warranting operating condition.

Dynamically configurable overprovisioned microprocessor

Methods and systems are disclosed for performing dataflow execution by an accelerated processing unit (APU). Techniques disclosed include decoding information from one or more dataflow instructions. The decoded information is associated with dataflow execution of a computational task. Techniques disclosed further include configuring, based on the decoded information, dataflow circuitry, and, then, executing the dataflow execution of the computational task using the dataflow circuitry.

Enabling accelerated processing units to perform dataflow execution

Systems and methods are disclosed that map quantum circuits to physical qubits of a quantum computer. Techniques are disclosed to generate a graph that characterizes the physical qubits of the quantum computer and to compute the resource requirements of each circuit of the quantum circuits. For each circuit, the graph is searched for a subgraph that matches the resource requirements of the circuit, based on a density matrix. Physical qubits, defined by the matching subgraph, are then allocated to the logical qubits of the circuit.

Quantum circuit mapping for multi-programmed quantum computers

Implementing heterogeneous wavefronts on a graphics processing unit (GPU) is disclosed. A scheduler assigns heterogeneous wavefronts for execution on a compute unit of a processing device. The heterogeneous wavefronts include different types of wavefronts such as vector compute wavefronts and service-level wavefronts that vary in resource requirements and instruction sets. As one example, heterogeneous wavefronts may include scalar wavefronts and vector compute wavefronts that execute on scalar units and vector units, respectively. Distinct sets of instructions are executed for the heterogeneous wavefronts on the compute unit. Heterogeneous wavefronts are processed in the same pipeline of the processing device.

Growing community of inventors

Bellevue, WA, United States of America

Anthony T Gutierrez