Advanced Micro Devices Corporation

Mitesh Ramesh Meswani

David Andrew Roberts

Gabriel H Loh

Arkaprava Basu

Sergey Blagodurov

Mark Richard Nutter

Michael Ignatowski

Sooraj Puthoor

Dmitri Yudanov

John Robert Slice

Dibakar Gope

Manish Satyapal Gupta

Nuwan S Jayasena

Yasuko Eckert

James Michael O'Connor

Mauricio Breternitz, Jr

Indrani Paul

Vilas K Sridharan

Joseph Lee Greathouse

Steven E Raasch

Mark Henry Oskin

Daniel I Lowell

Jee Ho Ryoo

David James Roberts

Prashant Jayaprakash Nair

Andreas Prodromou

Ahsen Jamshed Uppal

A processing apparatus is provided that includes NVRAM and one or more processors configured to process a first set and a second set of instructions according to a hierarchical processing scope and process a scoped persistence barrier residing in the program after the first instruction set and before the second instruction set. The barrier includes an instruction to cause first data to persist in the NVRAM before second data persists in the NVRAM. The first data results from execution of each of the first set of instructions processed according to the one hierarchical processing scope. The second data results from execution of each of the second set of instructions processed according to the one hierarchical processing scope. The processing apparatus also includes a controller configured to cause the first data to persist in the NVRAM before the second data persists in the NVRAM based on the scoped persistence barrier.

Scoped persistence barriers for non-volatile memories

A compute unit configured to execute multiple threads in parallel is presented. The compute unit includes one or more single instruction multiple data (SIMD) units and a fetch and decode logic. The SIMD units have differing numbers of arithmetic logic units (ALUs), such that each SIMD unit can execute a different number of threads. The fetch and decode logic is in communication with each of the SIMD units, and is configured to assign the threads to the SIMD units for execution based on such differing numbers of ALUs.

Heterogeneous graphics processing unit for scheduling thread groups for execution on variable width SIMD units

A method and processing apparatus for accelerating program processing is provided that includes a plurality of processors configured to process a plurality of tasks of a program and a controller. The controller is configured to determine, from the plurality of tasks being processed by the plurality of processors, a task being processed on a first processor to be a lagging task causing a delay in execution of one or more other tasks of the plurality of tasks. The controller is further configured to provide the determined lagging task to a second processor to be executed by the second processor to accelerate execution of the lagging task.

Multi-processor apparatus and method of detection and acceleration of lagging tasks

The described embodiments include a computing device that caches data acquired from a main memory in a high-bandwidth memory (HBM), the computing device including channels for accessing data stored in corresponding portions of the HBM. During operation, the computing device sets each of the channels so that data blocks stored in the corresponding portions of the HBM include corresponding numbers of cache lines. Based on records of accesses of cache lines in the HBM that were acquired from pages in the main memory, the computing device sets a data block size for each of the pages, the data block size being a number of cache lines. The computing device stores, in the HBM, data blocks acquired from each of the pages in the main memory using a channel having a data block size corresponding to the data block size for each of the pages.

Data block sizing for channels in a multi-channel high-bandwidth memory

Techniques for selecting one of a plurality of heterogeneous memory units for placement of blocks of data (e.g., memory pages), based on both reliability and performance, are disclosed. A 'cost' for each data block/memory unit combination is determined, based on the frequency of access of the data block, the latency of the memory unit, and, optionally, an architectural vulnerability factor (which represents the level of exposure of a particular memory data value to memory faults such as bit flips). A memory unit is selected for the data block for which the determined cost is the lowest, out of all memory units considered, and the data block is placed into that memory unit.

Performance-aware and reliability-aware data placement for n-level heterogeneous memory systems

The described embodiments include a computing device that has two or more levels of memory, each level of memory having different performance characteristics. During operation, the computing device receives a request to lease an available block of memory in a specified level of memory for storing an object. When a block of memory is available for leasing in the specified level of memory, the computing device stores the object in the block of memory in the specified level of memory. The computing device also commences the lease for the block of memory by setting an indicator for the block of memory to indicate that the block of memory is leased. During the lease (i.e., until the lease is terminated), the object is kept in the block of memory.

Leases for blocks of memory in a multi-level memory

A processor modifies memory management mode for a range of memory locations of a multilevel memory hierarchy based on changes in an application phase of an application executing at a processor. The processor monitors the application phase (e.g., computation-bound phase, input/output phase, or memory access phase) of the executing application and in response to a change in phase consults a management policy to identify a memory management mode. The processor automatically reconfigures a memory controller and other modules so that a range of memory locations of the multilevel memory hierarchy are managed according to the identified memory management mode. By changing the memory management mode for the range of memory locations according to the application phase, the processor improves processing efficiency and flexibility.

Techniques for changing management modes of multilevel memory hierarchy

Cluster manager functional blocks perform operations for migrating pages in portions in corresponding migration clusters. During operation, each cluster manager keeps an access record that includes information indicating accesses of pages in the portions in the corresponding migration cluster. Based on the access record and one or more migration policies, each cluster manager migrates pages between the portions in the corresponding migration cluster.

Cluster-based migration in a multi-level memory hierarchy

Systems, apparatuses, and methods for sorting memory pages in a multi-level heterogeneous memory architecture. The system may classify pages into a first 'hot' category or a second 'cold' category. The system may attempt to place the &#x201c;hot&#x201d; pages into the memory level(s) closest to the systems' processor cores. The system may track parameters associated with each page, with the parameters including number of accesses, types of accesses, power consumed per access, temperature, wearability, and/or other parameters. Based on these parameters, the system may generate a score for each page. Then, the system may compare the score of each page to a threshold. If the score of a given page is greater than the threshold, the given page may be designated as &#x201c;hot&#x201d;. If the score of the given page is less than the threshold, the given page may be designated as &#x201c;cold&#x201d;.

Hot page selection in multi-level memory hierarchies

Systems, apparatuses, and methods for implementing a memory sampling based migrating page cache are disclosed. In one embodiment, a system includes one or more processors and a multi-level memory hierarchy. The system is configured to record metadata associated with a portion of memory access instructions executed by one or more processors in one or more sampling intervals. The system generates predictions on which memory pages will be accessed in a subsequent sampling interval based on the recorded metadata. The system migrates one or more memory pages to a first memory level from a second memory level responsive to predicting that the one or more memory pages will be accessed in the subsequent sampling interval. The system also adjusts a duration of the sampling interval based on the number of memory accesses or a number of page faults per interval.

Memory-sampling based migrating page cache

A method and apparatus for performing inter-lane power management includes de-energizing one or more execution lanes upon a determination that the one or more execution lanes are to be predicated. Energy from the predicated execution lanes is redistributed to one or more active execution lanes.

Method and apparatus for performing inter-lane power management

A processor maintains a count of accesses to each memory page. When the accesses to a memory page exceed a threshold amount for that memory page, the processor sets an indicator for the page. Based on the indicators for the memory pages, the processor manages data at one or more levels of the processor's memory hierarchy.

Memory page access detection

Embodiments are described for a communications interconnect scheme for 3D stacked memory devices. A ring network design is used for networks of memory chips organized as individual devices with multiple dies or wafers. The design comprises a three-tier ring network where each ring serves a different set of memory blocks. One ring or set of rings interconnects memory within a die (inter-bank), a second ring or set of rings interconnects memory across die in a stack (inter-die), and the third ring or set of rings interconnects memory across stacks or chip packages (inter-stack).

Ring networks for intra- and inter-memory I/O including 3D-stacked memories

A system for memory allocation in a multiclass memory system includes a processor coupleable to a plurality of memories sharing a unified memory address space, and a library store to store a library of software functions. The processor identifies a type of a data structure in response to a memory allocation function call to the library for allocating memory to the data structure. Using the library, the processor allocates portions of the data structure among multiple memories of the multiclass memory system based on the type of the data structure.

Growing community of inventors

Austin, TX, United States of America

Mitesh Ramesh Meswani