Memory managementMemory management is a form of resource management applied to computer memory. The essential requirement of memory management is to provide ways to dynamically allocate portions of memory to programs at their request, and free it for reuse when no longer needed. This is critical to any advanced computer system where more than a single process might be underway at any time. Several methods have been devised that increase the effectiveness of memory management.
Shared memoryIn computer science, shared memory is memory that may be simultaneously accessed by multiple programs with an intent to provide communication among them or avoid redundant copies. Shared memory is an efficient means of passing data between programs. Depending on context, programs may run on a single processor or on multiple separate processors. Using memory for communication inside a single program, e.g. among its multiple threads, is also referred to as shared memory.
Memory pagingIn computer operating systems, memory paging (or swapping on some Unix-like systems) is a memory management scheme by which a computer stores and retrieves data from secondary storage for use in main memory. In this scheme, the operating system retrieves data from secondary storage in same-size blocks called pages. Paging is an important part of virtual memory implementations in modern operating systems, using secondary storage to let programs exceed the size of available physical memory.
Distributed shared memoryIn computer science, distributed shared memory (DSM) is a form of memory architecture where physically separated memories can be addressed as a single shared address space. The term "shared" does not mean that there is a single centralized memory, but that the address space is shared—i.e., the same physical address on two processors refers to the same location in memory. Distributed global address space (DGAS), is a similar term for a wide class of software and hardware implementations, in which each node of a cluster has access to shared memory in addition to each node's private (i.
General-purpose computing on graphics processing unitsGeneral-purpose computing on graphics processing units (GPGPU, or less often GPGP) is the use of a graphics processing unit (GPU), which typically handles computation only for computer graphics, to perform computation in applications traditionally handled by the central processing unit (CPU). The use of multiple video cards in one computer, or large numbers of graphics chips, further parallelizes the already parallel nature of graphics processing.
Graphics processing unitA graphics processing unit (GPU) is a specialized electronic circuit initially designed to accelerate computer graphics and (either on a video card or embedded on the motherboards, mobile phones, personal computers, workstations, and game consoles). After their initial design, GPUs were found to be useful for non-graphic calculations involving embarrassingly parallel problems due to their parallel structure. Other non-graphical uses include the training of neural networks and cryptocurrency mining.
Memory management unitA memory management unit (MMU), sometimes called paged memory management unit (PMMU), is a computer hardware unit that examines all memory references on the memory bus, translating these requests, known as virtual memory addresses, into physical addresses in main memory. In modern systems, programs generally have addresses that access the theoretical maximum memory of the computer architecture, 32 or 64 bits. The MMU maps the addresses from each program into separate areas in physical memory, which is generally much smaller than the theoretical maximum.
Uniform memory accessUniform memory access (UMA) is a shared memory architecture used in parallel computers. All the processors in the UMA model share the physical memory uniformly. In an UMA architecture, access time to a memory location is independent of which processor makes the request or which memory chip contains the transferred data. Uniform memory access computer architectures are often contrasted with non-uniform memory access (NUMA) architectures. In the NUMA architecture, each processor may use a private cache.
TransposeIn linear algebra, the transpose of a matrix is an operator which flips a matrix over its diagonal; that is, it switches the row and column indices of the matrix A by producing another matrix, often denoted by AT (among other notations). The transpose of a matrix was introduced in 1858 by the British mathematician Arthur Cayley. In the case of a logical matrix representing a binary relation R, the transpose corresponds to the converse relation RT.
Parallel computingParallel computing is a type of computation in which many calculations or processes are carried out simultaneously. Large problems can often be divided into smaller ones, which can then be solved at the same time. There are several different forms of parallel computing: bit-level, instruction-level, data, and task parallelism. Parallelism has long been employed in high-performance computing, but has gained broader interest due to the physical constraints preventing frequency scaling.
Conjugate transposeIn mathematics, the conjugate transpose, also known as the Hermitian transpose, of an complex matrix is an matrix obtained by transposing and applying complex conjugate on each entry (the complex conjugate of being , for real numbers and ). It is often denoted as or or and very commonly in physics as . For real matrices, the conjugate transpose is just the transpose, . The conjugate transpose of an matrix is formally defined by where the subscript denotes the -th entry, for and , and the overbar denotes a scalar complex conjugate.
Data parallelismData parallelism is parallelization across multiple processors in parallel computing environments. It focuses on distributing the data across different nodes, which operate on the data in parallel. It can be applied on regular data structures like arrays and matrices by working on each element in parallel. It contrasts to task parallelism as another form of parallelism. A data parallel job on an array of n elements can be divided equally among all the processors.
Computer memoryComputer memory stores information, such as data and programs for immediate use in the computer. The term memory is often synonymous with the term primary storage or main memory. An archaic synonym for memory is store. Computer memory operates at a high speed compared to storage which is slower but less expensive and higher in capacity. Besides storing opened programs, computer memory serves as disk cache and write buffer to improve both reading and writing performance.
Compute kernelIn computing, a compute kernel is a routine compiled for high throughput accelerators (such as graphics processing units (GPUs), digital signal processors (DSPs) or field-programmable gate arrays (FPGAs)), separate from but used by a main program (typically running on a central processing unit). They are sometimes called compute shaders, sharing execution units with vertex shaders and pixel shaders on GPUs, but are not limited to execution on one class of device, or graphics APIs.
Matrix multiplicationIn mathematics, particularly in linear algebra, matrix multiplication is a binary operation that produces a matrix from two matrices. For matrix multiplication, the number of columns in the first matrix must be equal to the number of rows in the second matrix. The resulting matrix, known as the matrix product, has the number of rows of the first and the number of columns of the second matrix. The product of matrices A and B is denoted as AB.
Heterogeneous computingHeterogeneous computing refers to systems that use more than one kind of processor or core. These systems gain performance or energy efficiency not just by adding the same type of processors, but by adding dissimilar coprocessors, usually incorporating specialized processing capabilities to handle particular tasks. Usually heterogeneity in the context of computing referred to different instruction-set architectures (ISA), where the main processor has one and other processors have another - usually a very different - architecture (maybe more than one), not just a different microarchitecture (floating point number processing is a special case of this - not usually referred to as heterogeneous).
Memory access patternIn computing, a memory access pattern or IO access pattern is the pattern with which a system or program reads and writes memory on secondary storage. These patterns differ in the level of locality of reference and drastically affect cache performance, and also have implications for the approach to parallelism and distribution of workload in shared memory systems. Further, cache coherency issues can affect multiprocessor performance, which means that certain memory access patterns place a ceiling on parallelism (which manycore approaches seek to break).
Block matrixIn mathematics, a block matrix or a partitioned matrix is a matrix that is interpreted as having been broken into sections called blocks or submatrices. Intuitively, a matrix interpreted as a block matrix can be visualized as the original matrix with a collection of horizontal and vertical lines, which break it up, or partition it, into a collection of smaller matrices. Any matrix may be interpreted as a block matrix in one or more ways, with each interpretation defined by how its rows and columns are partitioned.
Matrix decompositionIn the mathematical discipline of linear algebra, a matrix decomposition or matrix factorization is a factorization of a matrix into a product of matrices. There are many different matrix decompositions; each finds use among a particular class of problems. In numerical analysis, different decompositions are used to implement efficient matrix algorithms. For instance, when solving a system of linear equations , the matrix A can be decomposed via the LU decomposition.
Massively parallelMassively parallel is the term for using a large number of computer processors (or separate computers) to simultaneously perform a set of coordinated computations in parallel. GPUs are massively parallel architecture with tens of thousands of threads. One approach is grid computing, where the processing power of many computers in distributed, diverse administrative domains is opportunistically used whenever a computer is available. An example is BOINC, a volunteer-based, opportunistic grid system, whereby the grid provides power only on a best effort basis.
