fast_image_resize 6.0.0

Library for fast image resizing with using of SIMD instructions
Documentation 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92

use super::{Coefficients, Convolution};
use crate::convolution::vertical_f32::vert_convolution_f32;
use crate::cpu_extensions::CpuExtensions;
use crate::pixels::F32x2;
use crate::{ImageView, ImageViewMut};

#[cfg(target_arch = "x86_64")]
mod avx2;
mod native;
// #[cfg(target_arch = "aarch64")]
// mod neon;
#[cfg(target_arch = "x86_64")]
mod sse4;
// #[cfg(target_arch = "wasm32")]
// mod wasm32;

type P = F32x2;

impl Convolution for P {
    fn horiz_convolution(
        src_view: &impl ImageView<Pixel = Self>,
        dst_view: &mut impl ImageViewMut<Pixel = Self>,
        offset: u32,
        coeffs: Coefficients,
        cpu_extensions: CpuExtensions,
    ) {
        debug_assert!(src_view.height() - offset >= dst_view.height());
        let coeffs_ref = &coeffs;

        try_process_in_threads_h! {
            horiz_convolution(
                src_view,
                dst_view,
                offset,
                coeffs_ref,
                cpu_extensions,
            );
        }
    }

    fn vert_convolution(
        src_view: &impl ImageView<Pixel = Self>,
        dst_view: &mut impl ImageViewMut<Pixel = Self>,
        offset: u32,
        coeffs: Coefficients,
        cpu_extensions: CpuExtensions,
    ) {
        debug_assert!(src_view.width() - offset >= dst_view.width());

        let coeffs_ref = &coeffs;

        try_process_in_threads_v! {
            vert_convolution(
                src_view,
                dst_view,
                offset,
                coeffs_ref,
                cpu_extensions,
            );
        }
    }
}

fn horiz_convolution(
    src_view: &impl ImageView<Pixel = P>,
    dst_view: &mut impl ImageViewMut<Pixel = P>,
    offset: u32,
    coeffs: &Coefficients,
    cpu_extensions: CpuExtensions,
) {
    match cpu_extensions {
        #[cfg(target_arch = "x86_64")]
        CpuExtensions::Avx2 => avx2::horiz_convolution(src_view, dst_view, offset, coeffs),
        #[cfg(target_arch = "x86_64")]
        CpuExtensions::Sse4_1 => sse4::horiz_convolution(src_view, dst_view, offset, coeffs),
        // #[cfg(target_arch = "aarch64")]
        // CpuExtensions::Neon => neon::horiz_convolution(src_view, dst_view, offset, coeffs),
        // #[cfg(target_arch = "wasm32")]
        // CpuExtensions::Simd128 => wasm32::horiz_convolution(src_view, dst_view, offset, coeffs),
        _ => native::horiz_convolution(src_view, dst_view, offset, coeffs),
    }
}

fn vert_convolution(
    src_view: &impl ImageView<Pixel = P>,
    dst_view: &mut impl ImageViewMut<Pixel = P>,
    offset: u32,
    coeffs: &Coefficients,
    cpu_extensions: CpuExtensions,
) {
    vert_convolution_f32(src_view, dst_view, offset, coeffs, cpu_extensions);
}