https://github.com/ziutek/blas

Go implementation of BLAS (Basic Linear Algebra Subprograms)
https://github.com/ziutek/blas

Last synced: about 1 month ago
JSON representation

Go implementation of BLAS (Basic Linear Algebra Subprograms)

• Host: GitHub
• URL: https://github.com/ziutek/blas
• Owner: ziutek
• License: other
• Created: 2011-10-21T20:47:08.000Z (about 13 years ago)
• Default Branch: master
• Last Pushed: 2019-02-27T12:29:24.000Z (almost 6 years ago)
• Last Synced: 2024-02-15T09:38:21.855Z (10 months ago)
• Language: Assembly
• Homepage:
• Size: 64.5 KB
• Stars: 151
• Watchers: 9
• Forks: 19
• Open Issues: 3
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-cobol - blas - Implementation of BLAS (Basic Linear Algebra Subprograms) (Science and Data Analysis / Middlewares)
• awesome-go - blas - Go implementation of BLAS (Basic Linear Algebra Subprograms) - ★ 124 (Science and Data Analysis)
• awesome-go-zh - blas

README

        
### Go implementation of BLAS (Basic Linear Algebra Subprograms)

Any function is implemented in generic Go and if it is justified, it is

optimized for AMD64 (using SSE2 instructions).

AMD64 implementation uses MOVUPS/MOVUPD instructions if all strides equal to 1

so it run fast on Nehalem, Sandy Bridge and newer processors but relatively

slow on older processors.

Any implemented function has its own unity test and benchmark.

#### Implemented functions

*Level 1*

Sdsdot, Sdot, Ddot, Snrm2, Dnrm2, Sasum, Dasum, Isamax, Idamax, Sswap, Dswap,

Scopy, Dcopy, Saxpy, Daxpy, Sscal, Dscal, Srotg, Drotg, Srot, Drot

*Level 2*

not implemented

*Level 3*

not implemented

####Example benchmarks

    FunctionGeneric GoOptimized for AMD64

    Ddot2825 ns/op895 ns/op

    Dnrm22787 ns/op597 ns/op

    Dasum3145 ns/op560 ns/op

    Sdsdot3133 ns/op1733 ns/op

    Sdot2832 ns/op508 ns/op

#### Documentation

http://godoc.org/github.com/ziutek/blas