You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
which provide a vectorised form of many common mathematical functions, however the package does provide access to several other vectorized operations and more are being added on a regular basis. In
8
-
general, the performance is significantly better than using standard libm
9
-
functions, though there does appear to be some reduced accuracy.
5
+
the moment, this package provides:
6
+
1. Access to Accelerate BLAS and LAPACK using the [libblastrampoline](https://github.com/JuliaLinearAlgebra/libblastrampoline) framework,
7
+
2. An interface to the [array-oriented functions](https://developer.apple.com/library/mac/documentation/Performance/Conceptual/vecLib/index.html#//apple_ref/doc/uid/TP30000414-357225),
8
+
which provide a vectorised form for many common mathematical functions
9
+
10
+
The performance is significantly better than using standard libm functions in some cases, though there does appear to be some reduced accuracy.
10
11
11
12
## OS Requirements
12
13
13
-
MacOS 13.3 is required in order to run AppleAccelerate.jl. On older MacOS versions, your mileage may vary.
14
+
MacOS 13.3 is required in order to run AppleAccelerate.jl, especially for the libblastrampoline forwarding. On older MacOS versions, your mileage may vary.
14
15
15
16
## Supported Functions
16
17
@@ -37,6 +38,17 @@ Some additional functions that are also available:
37
38
38
39
## Example
39
40
41
+
To use the Accelerate BLAS and LAPACK, simply load the library:
42
+
```julia
43
+
julia>peakflops(4096)
44
+
3.6024175318268243e11
45
+
46
+
julia>using AppleAccelerate
47
+
48
+
julia>peakflops(4096)
49
+
5.832806459434183e11
50
+
```
51
+
40
52
To avoid naming conflicts with Base, methods are not exported and so need to
0 commit comments