scientific computing Computational science, also known as scientific computing or scientific computation (SC), is a field in mathematics that uses advanced computing capabilities to understand and solve complex problems. It is an area of science that spans many disc ...

, GotoBLAS and GotoBLAS2 are

open source Open source is source code that is made freely available for possible modification and redistribution. Products include permission to use the source code, design documents, or content of the product. The open-source model is a decentralized sof ...

implementations of the

BLAS Basic Linear Algebra Subprograms (BLAS) is a specification that prescribes a set of low-level routines for performing common linear algebra operations such as vector addition, scalar multiplication, dot products, linear combinations, and matrix ...

(Basic Linear Algebra Subprograms)

API An application programming interface (API) is a way for two or more computer programs to communicate with each other. It is a type of software interface, offering a service to other pieces of software. A document or standard that describes how ...

with many hand-crafted optimizations for specific processor types. GotoBLAS was developed by

Kazushige Goto is a software engineer specializing in high performance, hand-written, machine code. Education Goto was a research associate at the Texas Advanced Computing Center at the University of Texas at Austin when he wrote his famously hand-optimized ...

at the

Texas Advanced Computing Center The Texas Advanced Computing Center (TACC) at the University of Texas at Austin, United States, is an advanced computing research center that provides comprehensive advanced computing resources and support services to researchers in Texas and acr ...

. , it was used in seven of the world's ten fastest supercomputers. GotoBLAS remains available, but development ceased with a final version touting optimal performance on Intel's Nehalem architecture (contemporary in 2008).

OpenBLAS In scientific computing, OpenBLAS is an open-source implementation of the BLAS (Basic Linear Algebra Subprograms) and LAPACK APIs with many hand-crafted optimizations for specific processor types. It is developed at the Lab of Parallel Softw ...

is an actively maintained fork of GotoBLAS, developed at the Lab of Parallel Software and Computational Science, ISCAS. GotoBLAS was written by Goto during his

sabbatical A sabbatical (from the Hebrew: (i.e., Sabbath); in Latin ; Greek: ) is a rest or break from work. The concept of the sabbatical is based on the Biblical practice of ''shmita'' (sabbatical year), which is related to agriculture. According to ...

leave from the

Japan Patent Office The is a Japanese governmental agency in charge of industrial property right affairs, under the Ministry of Economy, Trade and Industry. The Japan Patent Office is located in Kasumigaseki, Chiyoda, Tokyo and is one of the world's largest pa ...

in 2002. It was initially optimized for the

Pentium 4 Pentium 4 is a series of single-core CPUs for desktops, laptops and entry-level servers manufactured by Intel. The processors were shipped from November 20, 2000 until August 8, 2008. The production of Netburst processors was active from 2000 ...

processor and managed to immediately boost the performance of a supercomputer based on that CPU from 1.5

TFLOPS In computing, floating point operations per second (FLOPS, flops or flop/s) is a measure of computer performance, useful in fields of scientific computations that require floating-point calculations. For such cases, it is a more accurate meas ...

to 2 TFLOPS. , the library was available at no cost for noncommercial use. A later open source version was released under the terms of the

BSD license BSD licenses are a family of permissive free software licenses, imposing minimal restrictions on the use and distribution of covered software. This is in contrast to copyleft licenses, which have share-alike requirements. The original BSD li ...

. GotoBLAS's matrix-matrix multiplication routine, called GEMM in BLAS terms, is highly tuned for the x86 and

AMD64 x86-64 (also known as x64, x86_64, AMD64, and Intel 64) is a 64-bit version of the x86 instruction set, first released in 1999. It introduced two new modes of operation, 64-bit mode and compatibility mode, along with a new 4-level paging mo ...

processor architectures by means of handcrafted

assembly code In computer programming, assembly language (or assembler language, or symbolic machine code), often referred to simply as Assembly and commonly abbreviated as ASM or asm, is any low-level programming language with a very strong correspondence be ...

. It follows a similar decomposition into smaller "kernel" routines that other BLAS implementations use, but where earlier implementations streamed data from the L1 processor cache, GotoBLAS uses the

L2 cache A CPU cache is a hardware cache used by the central processing unit (CPU) of a computer to reduce the average cost (time or energy) to access data from the main memory. A cache is a smaller, faster memory, located closer to a processor core, whic ...

. The kernel used for GEMM is a routine called GEBP, for "General block-times-panel multiply", which was experimentally found to be "inherently superior" over several other kernels that were considered in the design. Several other BLAS routines are, as is customary in BLAS libraries, implemented in terms of GEMM.

References

{{Numerical linear algebra Numerical linear algebra Numerical software Software using the BSD license

See also

References