Files
addr2line
adler
adler32
ahash
aho_corasick
angle
approx
backtrace
bitflags
blender
bytemuck
byteorder
case
cast_trait
cfg_if
chrono
color
color_quant
const_fn
crc32fast
crossbeam
crossbeam_channel
crossbeam_deque
crossbeam_epoch
crossbeam_queue
crossbeam_skiplist
crossbeam_utils
darling
darling_core
darling_macro
dds
deflate
densevec
derive_builder
derive_builder_core
dot
downcast_rs
dual_quat
either
erased_serde
failure
failure_derive
fixedbitset
float_cmp
fnv
freeimage
freeimage_sys
freetype
freetype_gl_sys
freetype_sys
freetypegl
futures
futures_channel
futures_core
futures_executor
futures_io
futures_macro
futures_sink
futures_task
futures_util
async_await
future
io
lock
sink
stream
task
fxhash
generational_arena
generic_array
getrandom
gif
gimli
glfw
glfw_sys
glin
glin_derive
glsl
half
harfbuzz
harfbuzz_ft_sys
harfbuzz_sys
hashbrown
human_sort
ident_case
image
indexmap
instant
itertools
itoa
jpeg_decoder
lazy_static
libc
libm
lock_api
log
lut_parser
matrixmultiply
memchr
memoffset
meshopt
miniz_oxide
monotonic_clock
mopa
mutiny_derive
na
nalgebra
base
geometry
linalg
ncollide3d
bounding_volume
interpolation
partitioning
pipeline
procedural
query
algorithms
closest_points
contact
distance
nonlinear_time_of_impact
point
proximity
ray
time_of_impact
visitors
shape
transformation
utils
nom
num_complex
num_cpus
num_integer
num_iter
num_rational
num_traits
numext_constructor
numext_fixed_uint
numext_fixed_uint_core
numext_fixed_uint_hack
object
once_cell
parking_lot
parking_lot_core
pathfinding
pennereq
petgraph
pin_project_lite
pin_utils
png
polygon2
ppv_lite86
proc_macro2
proc_macro_crate
proc_macro_hack
proc_macro_nested
quote
rand
rand_chacha
rand_core
rand_distr
raw_window_handle
rawpointer
rayon
rayon_core
rect_packer
regex
regex_syntax
retain_mut
rin
rin_app
rin_blender
rin_core
rin_gl
rin_graphics
rin_gui
rin_material
rin_math
rin_postpo
rin_scene
rin_util
rin_window
rinblender
rinecs
rinecs_derive
rinecs_derive_utils
ringui_derive
rustc_demangle
rusty_pool
ryu
scopeguard
seitan
seitan_derive
semver
semver_parser
serde
serde_derive
serde_json
shaderdata_derive
simba
slab
slice_of_array
slotmap
smallvec
std140_data
streaming_iterator
strsim
syn
synstructure
thiserror
thiserror_impl
thread_local
tiff
time
toml
typenum
unchecked_unwrap
unicode_xid
vec2
vec3
weezl
x11
zlib_sys
 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
#[cfg(target_arch="x86")]
use core::arch::x86::*;
#[cfg(target_arch="x86_64")]
use core::arch::x86_64::*;

#[macro_use]
mod macros;

pub(crate) struct FusedMulAdd;
pub(crate) struct AvxMulAdd;

pub(crate) trait SMultiplyAdd {
    const IS_FUSED: bool;
    unsafe fn multiply_add(__m256, __m256, __m256) -> __m256;
}

impl SMultiplyAdd for AvxMulAdd {
    const IS_FUSED: bool = false;
    #[inline(always)]
    unsafe fn multiply_add(a: __m256, b: __m256, c: __m256) -> __m256 {
        _mm256_add_ps(_mm256_mul_ps(a, b), c)
    }
}

impl SMultiplyAdd for FusedMulAdd {
    const IS_FUSED: bool = true;
    #[inline(always)]
    unsafe fn multiply_add(a: __m256, b: __m256, c: __m256) -> __m256 {
        _mm256_fmadd_ps(a, b, c)
    }
}

pub(crate) trait DMultiplyAdd {
    const IS_FUSED: bool;
    unsafe fn multiply_add(__m256d, __m256d, __m256d) -> __m256d;
}

impl DMultiplyAdd for AvxMulAdd {
    const IS_FUSED: bool = false;
    #[inline(always)]
    unsafe fn multiply_add(a: __m256d, b: __m256d, c: __m256d) -> __m256d {
        _mm256_add_pd(_mm256_mul_pd(a, b), c)
    }
}

impl DMultiplyAdd for FusedMulAdd {
    const IS_FUSED: bool = true;
    #[inline(always)]
    unsafe fn multiply_add(a: __m256d, b: __m256d, c: __m256d) -> __m256d {
        _mm256_fmadd_pd(a, b, c)
    }
}