blas

package module

v0.0.0-...-da4ca23 Latest Latest Go to latest Published: Feb 27, 2019 License: BSD-3-Clause Imports: 1 Imported by: 27

Details

Valid go.mod file

The Go module system was introduced in Go 1.11 and is the official dependency management solution for Go.
Redistributable license

Redistributable licenses place minimal restrictions on how software can be used, modified, and redistributed.
Tagged version

Modules with tagged versions give importers more predictable builds.
Stable version

When a project reaches major version v1 it is considered stable.
Learn more about best practices

Repository

github.com/ziutek/blas

Links

Open Source Insights

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

Function	Generic Go	Optimized for AMD64
Ddot	2825 ns/op	895 ns/op
Dnrm2	2787 ns/op	597 ns/op
Dasum	3145 ns/op	560 ns/op
Sdsdot	3133 ns/op	1733 ns/op
Sdot	2832 ns/op	508 ns/op

Documentation

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

Documentation ¶

Overview ¶

Go implementation of BLAS (Basic Linear Algebra Subprograms)

Index ¶

Constants
func Dasum(N int, X []float64, incX int) float64
func Daxpy(N int, alpha float64, X []float64, incX int, Y []float64, incY int)
func Dcopy(N int, X []float64, incX int, Y []float64, incY int)
func Ddot(N int, X []float64, incX int, Y []float64, incY int) float64
func Dnrm2(N int, X []float64, incX int) float64
func Drot(N int, X []float64, incX int, Y []float64, incY int, c, s float64)
func Drotg(a, b float64) (c, s, r, z float64)
func Dscal(N int, alpha float64, X []float64, incX int)
func Dswap(N int, X []float64, incX int, Y []float64, incY int)
func Idamax(N int, X []float64, incX int) int
func Isamax(N int, X []float32, incX int) int
func Sasum(N int, X []float32, incX int) float32
func Saxpy(N int, alpha float32, X []float32, incX int, Y []float32, incY int)
func Scopy(N int, X []float32, incX int, Y []float32, incY int)
func Sdot(N int, X []float32, incX int, Y []float32, incY int) float32
func Sdsdot(N int, alpha float32, X []float32, incX int, Y []float32, incY int) float32
func Snrm2(N int, X []float32, incX int) float32
func Srot(N int, X []float32, incX int, Y []float32, incY int, c, s float32)
func Srotg(a, b float32) (c, s, r, z float32)
func Sscal(N int, alpha float32, X []float32, incX int)
func Sswap(N int, X []float32, incX int, Y []float32, incY int)
type DrotmgParam
- func Drotmg(d1, d2, x1, y1 float64) (p DrotmgParam, rd1, rd2, rx1 float64)
type Order
type Transpose

Constants ¶

View Source

const (
	RowMajor = Order(101)
	ColMajor = Order(102)
)

View Source

const (
	NoTrans = Transpose(111)
	Trans   = Transpose(112)
)

Variables ¶

This section is empty.

Functions ¶

func Dasum ¶

func Dasum(N int, X []float64, incX int) float64

Absolute sum: \sum |X_i|

func Daxpy ¶

func Daxpy(N int, alpha float64, X []float64, incX int, Y []float64, incY int)

Compute the sum Y = \alpha X + Y for the vectors X and Y

func Dcopy ¶

func Dcopy(N int, X []float64, incX int, Y []float64, incY int)

Copy the elements of the vectors X and Y.

func Ddot ¶

func Ddot(N int, X []float64, incX int, Y []float64, incY int) float64

Scalar product: X^T Y

func Dnrm2 ¶

func Dnrm2(N int, X []float64, incX int) float64

Euclidean norm: ||X||_2 = \sqrt {\sum X_i^2}

func Drot ¶

func Drot(N int, X []float64, incX int, Y []float64, incY int, c, s float64)

Apply a Givens rotation (X', Y') = (c X + s Y, c Y - s X) to the vectors X, Y

func Drotg ¶

func Drotg(a, b float64) (c, s, r, z float64)

Compute a Givens rotation (c,s) which zeroes the vector (a,b)

func Dscal ¶

func Dscal(N int, alpha float64, X []float64, incX int)

Rescale the vector X by the multiplicative factor alpha

func Dswap ¶

func Dswap(N int, X []float64, incX int, Y []float64, incY int)

Exchange the elements of the vectors X and Y.

func Idamax ¶

func Idamax(N int, X []float64, incX int) int

Index of largest (absoulute) element of the vector X

func Isamax ¶

func Isamax(N int, X []float32, incX int) int

Index of largest (absoulute) element of the vector X

func Sasum ¶

func Sasum(N int, X []float32, incX int) float32

Absolute sum: \sum |X_i|

func Saxpy ¶

func Saxpy(N int, alpha float32, X []float32, incX int, Y []float32, incY int)

Compute the sum Y = \alpha X + Y for the vectors X and Y

func Scopy ¶

func Scopy(N int, X []float32, incX int, Y []float32, incY int)

Copy the elements of the vectors X and Y.

func Sdot ¶

func Sdot(N int, X []float32, incX int, Y []float32, incY int) float32

Scalar product: X^T Y

func Sdsdot ¶

func Sdsdot(N int, alpha float32, X []float32, incX int, Y []float32, incY int) float32

\alpha + X^T Y computed using float64

func Snrm2 ¶

func Snrm2(N int, X []float32, incX int) float32

Euclidean norm: ||X||_2 = \sqrt {\sum X_i^2}

func Srot ¶

func Srot(N int, X []float32, incX int, Y []float32, incY int, c, s float32)

Apply a Givens rotation (X', Y') = (c X + s Y, c Y - s X) to the vectors X, Y

func Srotg ¶

func Srotg(a, b float32) (c, s, r, z float32)

Compute a Givens rotation (c,s) which zeroes the vector (a,b)

func Sscal ¶

func Sscal(N int, alpha float32, X []float32, incX int)

Rescale the vector X by the multiplicative factor alpha

func Sswap ¶

func Sswap(N int, X []float32, incX int, Y []float32, incY int)

Exchange the elements of the vectors X and Y.

Types ¶

type DrotmgParam ¶

type DrotmgParam struct {
	// contains filtered or unexported fields
}

func Drotmg ¶

func Drotmg(d1, d2, x1, y1 float64) (p DrotmgParam, rd1, rd2, rx1 float64)

Compute a modified Givens transformation

type Order ¶

type Order int

type Transpose ¶

type Transpose int

Source Files ¶

View all Source files

?	: This menu
/	: Search site
f or F	: Jump to
y or Y	: Canonical URL