/rust/registry/src/index.crates.io-1949cf8c6b5b557f/chacha20-0.10.2/src/backends/sse2.rs

Source
//! SSE2 backend.

#![allow(unsafe_op_in_unsafe_fn, reason = "needs triage")]
#![allow(clippy::cast_possible_truncation, reason = "needs triage")]
#![allow(clippy::cast_possible_wrap, reason = "needs triage")]
#![allow(clippy::cast_sign_loss, reason = "needs triage")]
#![allow(clippy::undocumented_unsafe_blocks, reason = "TODO")]

use crate::{Rounds, STATE_WORDS, Variant};

#[cfg(feature = "rng")]
use crate::ChaChaCore;

#[cfg(feature = "cipher")]
use crate::chacha::Block;
#[cfg(feature = "cipher")]
use cipher::{
    BlockSizeUser, ParBlocksSizeUser, StreamCipherBackend, StreamCipherClosure,
    consts::{U4, U64},
};
use core::marker::PhantomData;

#[cfg(target_arch = "x86")]
use core::arch::x86::*;
#[cfg(target_arch = "x86_64")]
use core::arch::x86_64::*;

const PAR_BLOCKS: usize = 4;

#[inline]
#[target_feature(enable = "sse2")]
#[cfg(feature = "cipher")]
pub(crate) unsafe fn inner<R, F, V>(state: &mut [u32; STATE_WORDS], f: F)
where
    R: Rounds,
    F: StreamCipherClosure<BlockSize = U64>,
    V: Variant,
{
    let mut backend = Backend::<R, V>::new(state);
    f.call(&mut backend);
    backend.save_ctr(state);
}

#[inline]
#[target_feature(enable = "sse2")]
#[cfg(feature = "rng")]
pub(crate) unsafe fn rng_inner<R, V>(core: &mut ChaChaCore<R, V>, buffer: &mut [u32; 64])
where
    R: Rounds,
    V: Variant,
{
    let mut backend = Backend::<R, V>::new(&core.state);
    backend.gen_ks_blocks(buffer);
    backend.save_ctr(&mut core.state);
}

struct Backend<R: Rounds, V: Variant> {
    v: [__m128i; 4],
    _pd: PhantomData<(R, V)>,
}

impl<R: Rounds, V: Variant> Backend<R, V> {
    unsafe fn new(state: &[u32; STATE_WORDS]) -> Self {
        let state_ptr = state.as_ptr().cast::<__m128i>();
        Self {
            v: core::array::from_fn(|i| _mm_loadu_si128(state_ptr.add(i))),
            _pd: PhantomData,
        }
    }

    unsafe fn save_ctr(self, state: &mut [u32; STATE_WORDS]) {
        let state_ptr = state.as_mut_ptr().cast::<__m128i>();
        _mm_storeu_si128(state_ptr.add(3), self.v[3]);
    }
}

#[cfg(feature = "cipher")]
impl<R: Rounds, V: Variant> BlockSizeUser for Backend<R, V> {
    type BlockSize = U64;
}

#[cfg(feature = "cipher")]
impl<R: Rounds, V: Variant> ParBlocksSizeUser for Backend<R, V> {
    type ParBlocksSize = U4;
}

#[cfg(feature = "cipher")]
impl<R: Rounds, V: Variant> StreamCipherBackend for Backend<R, V> {
    #[inline(always)]
    fn gen_ks_block(&mut self, block: &mut Block) {
        unsafe {
            let res = rounds::<R, V>(&self.v);
            self.v[3] = match size_of::<V::Counter>() {
                4 => _mm_add_epi32(self.v[3], _mm_set_epi32(0, 0, 0, 1)),
                8 => _mm_add_epi64(self.v[3], _mm_set_epi64x(0, 1)),
                _ => unreachable!(),
            };

            let block_ptr = block.as_mut_ptr().cast::<__m128i>();
            for i in 0..4 {
                _mm_storeu_si128(block_ptr.add(i), res[0][i]);
            }
        }
    }

    #[inline(always)]
    fn gen_par_ks_blocks(&mut self, blocks: &mut cipher::ParBlocks<Self>) {
        unsafe {
            let res = rounds::<R, V>(&self.v);
            self.v[3] = match size_of::<V::Counter>() {
                4 => _mm_add_epi32(self.v[3], _mm_set_epi32(0, 0, 0, PAR_BLOCKS as i32)),
                8 => _mm_add_epi64(self.v[3], _mm_set_epi64x(0, PAR_BLOCKS as i64)),
                _ => unreachable!(),
            };

            let blocks_ptr = blocks.as_mut_ptr().cast::<__m128i>();
            for block in 0..PAR_BLOCKS {
                for i in 0..4 {
                    _mm_storeu_si128(blocks_ptr.add(i + block * PAR_BLOCKS), res[block][i]);
                }
            }
        }
    }
}

#[cfg(feature = "rng")]
impl<R: Rounds, V: Variant> Backend<R, V> {
    #[inline(always)]
    fn gen_ks_blocks(&mut self, block: &mut [u32; 64]) {
        const _: () = assert!(4 * PAR_BLOCKS * size_of::<__m128i>() == size_of::<[u32; 64]>());
        unsafe {
            let res = rounds::<R, V>(&self.v);
            self.v[3] = _mm_add_epi64(self.v[3], _mm_set_epi64x(0, PAR_BLOCKS as i64));

            let blocks_ptr = block.as_mut_ptr().cast::<__m128i>();
            for block in 0..PAR_BLOCKS {
                for i in 0..4 {
                    _mm_storeu_si128(blocks_ptr.add(i + block * PAR_BLOCKS), res[block][i]);
                }
            }
        }
    }
}

#[inline]
#[target_feature(enable = "sse2")]
unsafe fn rounds<R: Rounds, V: Variant>(v: &[__m128i; 4]) -> [[__m128i; 4]; PAR_BLOCKS] {
    let mut res = [*v; 4];
    for block in 1..PAR_BLOCKS {
        res[block][3] = match size_of::<V::Counter>() {
            4 => _mm_add_epi32(res[block][3], _mm_set_epi32(0, 0, 0, block as i32)),
            8 => _mm_add_epi64(res[block][3], _mm_set_epi64x(0, block as i64)),
            _ => unreachable!(),
        }
    }

    for _ in 0..R::COUNT {
        double_quarter_round(&mut res);
    }

    for block in 0..PAR_BLOCKS {
        for i in 0..3 {
            res[block][i] = _mm_add_epi32(res[block][i], v[i]);
        }
        let ctr = match size_of::<V::Counter>() {
            4 => _mm_add_epi32(v[3], _mm_set_epi32(0, 0, 0, block as i32)),
            8 => _mm_add_epi64(v[3], _mm_set_epi64x(0, block as i64)),
            _ => unreachable!(),
        };
        res[block][3] = _mm_add_epi32(res[block][3], ctr);
    }

    res
}

#[inline]
#[target_feature(enable = "sse2")]
unsafe fn double_quarter_round(v: &mut [[__m128i; 4]; PAR_BLOCKS]) {
    add_xor_rot(v);
    rows_to_cols(v);
    add_xor_rot(v);
    cols_to_rows(v);
}

/// The goal of this function is to transform the state words from:
/// ```text
/// [a0, a1, a2, a3]    [ 0,  1,  2,  3]
/// [b0, b1, b2, b3] == [ 4,  5,  6,  7]
/// [c0, c1, c2, c3]    [ 8,  9, 10, 11]
/// [d0, d1, d2, d3]    [12, 13, 14, 15]
/// ```
///
/// to:
/// ```text
/// [a0, a1, a2, a3]    [ 0,  1,  2,  3]
/// [b1, b2, b3, b0] == [ 5,  6,  7,  4]
/// [c2, c3, c0, c1]    [10, 11,  8,  9]
/// [d3, d0, d1, d2]    [15, 12, 13, 14]
/// ```
///
/// so that we can apply [`add_xor_rot`] to the resulting columns, and have it compute the
/// "diagonal rounds" (as defined in RFC 7539) in parallel. In practice, this shuffle is
/// non-optimal: the last state word to be altered in `add_xor_rot` is `b`, so the shuffle
/// blocks on the result of `b` being calculated.
///
/// We can optimize this by observing that the four quarter rounds in `add_xor_rot` are
/// data-independent: they only access a single column of the state, and thus the order of
/// the columns does not matter. We therefore instead shuffle the other three state words,
/// to obtain the following equivalent layout:
/// ```text
/// [a3, a0, a1, a2]    [ 3,  0,  1,  2]
/// [b0, b1, b2, b3] == [ 4,  5,  6,  7]
/// [c1, c2, c3, c0]    [ 9, 10, 11,  8]
/// [d2, d3, d0, d1]    [14, 15, 12, 13]
/// ```
///
/// See https://github.com/sneves/blake2-avx2/pull/4 for additional details. The earliest
/// known occurrence of this optimization is in floodyberry's SSE4 ChaCha code from 2014:
/// - https://github.com/floodyberry/chacha-opt/blob/0ab65cb99f5016633b652edebaf3691ceb4ff753/chacha_blocks_ssse3-64.S#L639-L643
#[inline]
#[target_feature(enable = "sse2")]
unsafe fn rows_to_cols(blocks: &mut [[__m128i; 4]; PAR_BLOCKS]) {
    for [a, _, c, d] in blocks.iter_mut() {
        // c >>>= 32; d >>>= 64; a >>>= 96;
        *c = _mm_shuffle_epi32(*c, 0b_00_11_10_01); // _MM_SHUFFLE(0, 3, 2, 1)
        *d = _mm_shuffle_epi32(*d, 0b_01_00_11_10); // _MM_SHUFFLE(1, 0, 3, 2)
        *a = _mm_shuffle_epi32(*a, 0b_10_01_00_11); // _MM_SHUFFLE(2, 1, 0, 3)
    }
}

/// The goal of this function is to transform the state words from:
/// ```text
/// [a3, a0, a1, a2]    [ 3,  0,  1,  2]
/// [b0, b1, b2, b3] == [ 4,  5,  6,  7]
/// [c1, c2, c3, c0]    [ 9, 10, 11,  8]
/// [d2, d3, d0, d1]    [14, 15, 12, 13]
/// ```
///
/// to:
/// ```text
/// [a0, a1, a2, a3]    [ 0,  1,  2,  3]
/// [b0, b1, b2, b3] == [ 4,  5,  6,  7]
/// [c0, c1, c2, c3]    [ 8,  9, 10, 11]
/// [d0, d1, d2, d3]    [12, 13, 14, 15]
/// ```
///
/// reversing the transformation of [`rows_to_cols`].
#[inline]
#[target_feature(enable = "sse2")]
unsafe fn cols_to_rows(blocks: &mut [[__m128i; 4]; PAR_BLOCKS]) {
    for [a, _, c, d] in blocks.iter_mut() {
        // c <<<= 32; d <<<= 64; a <<<= 96;
        *c = _mm_shuffle_epi32(*c, 0b_10_01_00_11); // _MM_SHUFFLE(2, 1, 0, 3)
        *d = _mm_shuffle_epi32(*d, 0b_01_00_11_10); // _MM_SHUFFLE(1, 0, 3, 2)
        *a = _mm_shuffle_epi32(*a, 0b_00_11_10_01); // _MM_SHUFFLE(0, 3, 2, 1)
    }
}

#[inline]
#[target_feature(enable = "sse2")]
unsafe fn add_xor_rot(blocks: &mut [[__m128i; 4]; PAR_BLOCKS]) {
    for [a, b, c, d] in blocks.iter_mut() {
        // a += b; d ^= a; d <<<= (16, 16, 16, 16);
        *a = _mm_add_epi32(*a, *b);
        *d = _mm_xor_si128(*d, *a);
        *d = _mm_xor_si128(_mm_slli_epi32(*d, 16), _mm_srli_epi32(*d, 16));

        // c += d; b ^= c; b <<<= (12, 12, 12, 12);
        *c = _mm_add_epi32(*c, *d);
        *b = _mm_xor_si128(*b, *c);
        *b = _mm_xor_si128(_mm_slli_epi32(*b, 12), _mm_srli_epi32(*b, 20));

        // a += b; d ^= a; d <<<= (8, 8, 8, 8);
        *a = _mm_add_epi32(*a, *b);
        *d = _mm_xor_si128(*d, *a);
        *d = _mm_xor_si128(_mm_slli_epi32(*d, 8), _mm_srli_epi32(*d, 24));

        // c += d; b ^= c; b <<<= (7, 7, 7, 7);
        *c = _mm_add_epi32(*c, *d);
        *b = _mm_xor_si128(*b, *c);
        *b = _mm_xor_si128(_mm_slli_epi32(*b, 7), _mm_srli_epi32(*b, 25));
    }
}

Coverage Report

Created: 2026-09-04 06:46

Line	Count	Source
1		//! SSE2 backend.
2
3		#![allow(unsafe_op_in_unsafe_fn, reason = "needs triage")]
4		#![allow(clippy::cast_possible_truncation, reason = "needs triage")]
5		#![allow(clippy::cast_possible_wrap, reason = "needs triage")]
6		#![allow(clippy::cast_sign_loss, reason = "needs triage")]
7		#![allow(clippy::undocumented_unsafe_blocks, reason = "TODO")]
8
9		use crate::{Rounds, STATE_WORDS, Variant};
10
11		#[cfg(feature = "rng")]
12		use crate::ChaChaCore;
13
14		#[cfg(feature = "cipher")]
15		use crate::chacha::Block;
16		#[cfg(feature = "cipher")]
17		use cipher::{
18		BlockSizeUser, ParBlocksSizeUser, StreamCipherBackend, StreamCipherClosure,
19		consts::{U4, U64},
20		};
21		use core::marker::PhantomData;
22
23		#[cfg(target_arch = "x86")]
24		use core::arch::x86::*;
25		#[cfg(target_arch = "x86_64")]
26		use core::arch::x86_64::*;
27
28		const PAR_BLOCKS: usize = 4;
29
30		#[inline]
31		#[target_feature(enable = "sse2")]
32		#[cfg(feature = "cipher")]
33		pub(crate) unsafe fn inner<R, F, V>(state: &mut [u32; STATE_WORDS], f: F)
34		where
35		R: Rounds,
36		F: StreamCipherClosure<BlockSize = U64>,
37		V: Variant,
38		{
39		let mut backend = Backend::<R, V>::new(state);
40		f.call(&mut backend);
41		backend.save_ctr(state);
42		}
43
44		#[inline]
45		#[target_feature(enable = "sse2")]
46		#[cfg(feature = "rng")]
47	0	pub(crate) unsafe fn rng_inner<R, V>(core: &mut ChaChaCore<R, V>, buffer: &mut [u32; 64])
48	0	where
49	0	R: Rounds,
50	0	V: Variant,
51		{
52	0	let mut backend = Backend::<R, V>::new(&core.state);
53	0	backend.gen_ks_blocks(buffer);
54	0	backend.save_ctr(&mut core.state);
55	0	} Unexecuted instantiation: chacha20::backends::sse2::rng_inner::<chacha20::R12, chacha20::variants::Legacy> Unexecuted instantiation: chacha20::backends::sse2::rng_inner::<_, _>
56
57		struct Backend<R: Rounds, V: Variant> {
58		v: [__m128i; 4],
59		_pd: PhantomData<(R, V)>,
60		}
61
62		impl<R: Rounds, V: Variant> Backend<R, V> {
63	0	unsafe fn new(state: &[u32; STATE_WORDS]) -> Self {
64	0	let state_ptr = state.as_ptr().cast::<__m128i>();
65		Self {
66	0	v: core::array::from_fn(\|i\| _mm_loadu_si128(state_ptr.add(i))), Unexecuted instantiation: <chacha20::backends::sse2::Backend<chacha20::R12, chacha20::variants::Legacy>>::new::{closure#0} Unexecuted instantiation: <chacha20::backends::sse2::Backend<_, _>>::new::{closure#0}
67	0	_pd: PhantomData,
68		}
69	0	} Unexecuted instantiation: <chacha20::backends::sse2::Backend<chacha20::R12, chacha20::variants::Legacy>>::new Unexecuted instantiation: <chacha20::backends::sse2::Backend<_, _>>::new
70
71	0	unsafe fn save_ctr(self, state: &mut [u32; STATE_WORDS]) {
72	0	let state_ptr = state.as_mut_ptr().cast::<__m128i>();
73	0	_mm_storeu_si128(state_ptr.add(3), self.v[3]);
74	0	} Unexecuted instantiation: <chacha20::backends::sse2::Backend<chacha20::R12, chacha20::variants::Legacy>>::save_ctr Unexecuted instantiation: <chacha20::backends::sse2::Backend<_, _>>::save_ctr
75		}
76
77		#[cfg(feature = "cipher")]
78		impl<R: Rounds, V: Variant> BlockSizeUser for Backend<R, V> {
79		type BlockSize = U64;
80		}
81
82		#[cfg(feature = "cipher")]
83		impl<R: Rounds, V: Variant> ParBlocksSizeUser for Backend<R, V> {
84		type ParBlocksSize = U4;
85		}
86
87		#[cfg(feature = "cipher")]
88		impl<R: Rounds, V: Variant> StreamCipherBackend for Backend<R, V> {
89		#[inline(always)]
90		fn gen_ks_block(&mut self, block: &mut Block) {
91		unsafe {
92		let res = rounds::<R, V>(&self.v);
93		self.v[3] = match size_of::<V::Counter>() {
94		4 => _mm_add_epi32(self.v[3], _mm_set_epi32(0, 0, 0, 1)),
95		8 => _mm_add_epi64(self.v[3], _mm_set_epi64x(0, 1)),
96		_ => unreachable!(),
97		};
98
99		let block_ptr = block.as_mut_ptr().cast::<__m128i>();
100		for i in 0..4 {
101		_mm_storeu_si128(block_ptr.add(i), res[0][i]);
102		}
103		}
104		}
105
106		#[inline(always)]
107		fn gen_par_ks_blocks(&mut self, blocks: &mut cipher::ParBlocks<Self>) {
108		unsafe {
109		let res = rounds::<R, V>(&self.v);
110		self.v[3] = match size_of::<V::Counter>() {
111		4 => _mm_add_epi32(self.v[3], _mm_set_epi32(0, 0, 0, PAR_BLOCKS as i32)),
112		8 => _mm_add_epi64(self.v[3], _mm_set_epi64x(0, PAR_BLOCKS as i64)),
113		_ => unreachable!(),
114		};
115
116		let blocks_ptr = blocks.as_mut_ptr().cast::<__m128i>();
117		for block in 0..PAR_BLOCKS {
118		for i in 0..4 {
119		_mm_storeu_si128(blocks_ptr.add(i + block * PAR_BLOCKS), res[block][i]);
120		}
121		}
122		}
123		}
124		}
125
126		#[cfg(feature = "rng")]
127		impl<R: Rounds, V: Variant> Backend<R, V> {
128		#[inline(always)]
129	0	fn gen_ks_blocks(&mut self, block: &mut [u32; 64]) {
130		const _: () = assert!(4 * PAR_BLOCKS * size_of::<__m128i>() == size_of::<[u32; 64]>());
131		unsafe {
132	0	let res = rounds::<R, V>(&self.v);
133	0	self.v[3] = _mm_add_epi64(self.v[3], _mm_set_epi64x(0, PAR_BLOCKS as i64));
134
135	0	let blocks_ptr = block.as_mut_ptr().cast::<__m128i>();
136	0	for block in 0..PAR_BLOCKS {
137	0	for i in 0..4 {
138	0	_mm_storeu_si128(blocks_ptr.add(i + block * PAR_BLOCKS), res[block][i]);
139	0	}
140		}
141		}
142	0	} Unexecuted instantiation: <chacha20::backends::sse2::Backend<chacha20::R12, chacha20::variants::Legacy>>::gen_ks_blocks Unexecuted instantiation: <chacha20::backends::sse2::Backend<_, _>>::gen_ks_blocks
143		}
144
145		#[inline]
146		#[target_feature(enable = "sse2")]
147	0	unsafe fn rounds<R: Rounds, V: Variant>(v: &[__m128i; 4]) -> [[__m128i; 4]; PAR_BLOCKS] {
148	0	let mut res = [*v; 4];
149	0	for block in 1..PAR_BLOCKS {
150	0	res[block][3] = match size_of::<V::Counter>() {
151	0	4 => _mm_add_epi32(res[block][3], _mm_set_epi32(0, 0, 0, block as i32)),
152	0	8 => _mm_add_epi64(res[block][3], _mm_set_epi64x(0, block as i64)),
153	0	_ => unreachable!(),
154		}
155		}
156
157	0	for _ in 0..R::COUNT {
158	0	double_quarter_round(&mut res);
159	0	}
160
161	0	for block in 0..PAR_BLOCKS {
162	0	for i in 0..3 {
163	0	res[block][i] = _mm_add_epi32(res[block][i], v[i]);
164	0	}
165	0	let ctr = match size_of::<V::Counter>() {
166	0	4 => _mm_add_epi32(v[3], _mm_set_epi32(0, 0, 0, block as i32)),
167	0	8 => _mm_add_epi64(v[3], _mm_set_epi64x(0, block as i64)),
168	0	_ => unreachable!(),
169		};
170	0	res[block][3] = _mm_add_epi32(res[block][3], ctr);
171		}
172
173	0	res
174	0	} Unexecuted instantiation: chacha20::backends::sse2::rounds::<chacha20::R12, chacha20::variants::Legacy> Unexecuted instantiation: chacha20::backends::sse2::rounds::<_, _>
175
176		#[inline]
177		#[target_feature(enable = "sse2")]
178	0	unsafe fn double_quarter_round(v: &mut [[__m128i; 4]; PAR_BLOCKS]) {
179	0	add_xor_rot(v);
180	0	rows_to_cols(v);
181	0	add_xor_rot(v);
182	0	cols_to_rows(v);
183	0	} Unexecuted instantiation: chacha20::backends::sse2::double_quarter_round Unexecuted instantiation: chacha20::backends::sse2::double_quarter_round
184
185		/// The goal of this function is to transform the state words from:
186		/// ```text
187		/// [a0, a1, a2, a3] [ 0, 1, 2, 3]
188		/// [b0, b1, b2, b3] == [ 4, 5, 6, 7]
189		/// [c0, c1, c2, c3] [ 8, 9, 10, 11]
190		/// [d0, d1, d2, d3] [12, 13, 14, 15]
191		/// ```
192		///
193		/// to:
194		/// ```text
195		/// [a0, a1, a2, a3] [ 0, 1, 2, 3]
196		/// [b1, b2, b3, b0] == [ 5, 6, 7, 4]
197		/// [c2, c3, c0, c1] [10, 11, 8, 9]
198		/// [d3, d0, d1, d2] [15, 12, 13, 14]
199		/// ```
200		///
201		/// so that we can apply [`add_xor_rot`] to the resulting columns, and have it compute the
202		/// "diagonal rounds" (as defined in RFC 7539) in parallel. In practice, this shuffle is
203		/// non-optimal: the last state word to be altered in `add_xor_rot` is `b`, so the shuffle
204		/// blocks on the result of `b` being calculated.
205		///
206		/// We can optimize this by observing that the four quarter rounds in `add_xor_rot` are
207		/// data-independent: they only access a single column of the state, and thus the order of
208		/// the columns does not matter. We therefore instead shuffle the other three state words,
209		/// to obtain the following equivalent layout:
210		/// ```text
211		/// [a3, a0, a1, a2] [ 3, 0, 1, 2]
212		/// [b0, b1, b2, b3] == [ 4, 5, 6, 7]
213		/// [c1, c2, c3, c0] [ 9, 10, 11, 8]
214		/// [d2, d3, d0, d1] [14, 15, 12, 13]
215		/// ```
216		///
217		/// See https://github.com/sneves/blake2-avx2/pull/4 for additional details. The earliest
218		/// known occurrence of this optimization is in floodyberry's SSE4 ChaCha code from 2014:
219		/// - https://github.com/floodyberry/chacha-opt/blob/0ab65cb99f5016633b652edebaf3691ceb4ff753/chacha_blocks_ssse3-64.S#L639-L643
220		#[inline]
221		#[target_feature(enable = "sse2")]
222	0	unsafe fn rows_to_cols(blocks: &mut [[__m128i; 4]; PAR_BLOCKS]) {
223	0	for [a, _, c, d] in blocks.iter_mut() {
224	0	// c >>>= 32; d >>>= 64; a >>>= 96;
225	0	c = _mm_shuffle_epi32(c, 0b_00_11_10_01); // _MM_SHUFFLE(0, 3, 2, 1)
226	0	d = _mm_shuffle_epi32(d, 0b_01_00_11_10); // _MM_SHUFFLE(1, 0, 3, 2)
227	0	a = _mm_shuffle_epi32(a, 0b_10_01_00_11); // _MM_SHUFFLE(2, 1, 0, 3)
228	0	}
229	0	} Unexecuted instantiation: chacha20::backends::sse2::rows_to_cols Unexecuted instantiation: chacha20::backends::sse2::rows_to_cols
230
231		/// The goal of this function is to transform the state words from:
232		/// ```text
233		/// [a3, a0, a1, a2] [ 3, 0, 1, 2]
234		/// [b0, b1, b2, b3] == [ 4, 5, 6, 7]
235		/// [c1, c2, c3, c0] [ 9, 10, 11, 8]
236		/// [d2, d3, d0, d1] [14, 15, 12, 13]
237		/// ```
238		///
239		/// to:
240		/// ```text
241		/// [a0, a1, a2, a3] [ 0, 1, 2, 3]
242		/// [b0, b1, b2, b3] == [ 4, 5, 6, 7]
243		/// [c0, c1, c2, c3] [ 8, 9, 10, 11]
244		/// [d0, d1, d2, d3] [12, 13, 14, 15]
245		/// ```
246		///
247		/// reversing the transformation of [`rows_to_cols`].
248		#[inline]
249		#[target_feature(enable = "sse2")]
250	0	unsafe fn cols_to_rows(blocks: &mut [[__m128i; 4]; PAR_BLOCKS]) {
251	0	for [a, _, c, d] in blocks.iter_mut() {
252	0	// c <<<= 32; d <<<= 64; a <<<= 96;
253	0	c = _mm_shuffle_epi32(c, 0b_10_01_00_11); // _MM_SHUFFLE(2, 1, 0, 3)
254	0	d = _mm_shuffle_epi32(d, 0b_01_00_11_10); // _MM_SHUFFLE(1, 0, 3, 2)
255	0	a = _mm_shuffle_epi32(a, 0b_00_11_10_01); // _MM_SHUFFLE(0, 3, 2, 1)
256	0	}
257	0	} Unexecuted instantiation: chacha20::backends::sse2::cols_to_rows Unexecuted instantiation: chacha20::backends::sse2::cols_to_rows
258
259		#[inline]
260		#[target_feature(enable = "sse2")]
261	0	unsafe fn add_xor_rot(blocks: &mut [[__m128i; 4]; PAR_BLOCKS]) {
262	0	for [a, b, c, d] in blocks.iter_mut() {
263	0	// a += b; d ^= a; d <<<= (16, 16, 16, 16);
264	0	a = _mm_add_epi32(a, *b);
265	0	d = _mm_xor_si128(d, *a);
266	0	d = _mm_xor_si128(_mm_slli_epi32(d, 16), _mm_srli_epi32(*d, 16));
267	0
268	0	// c += d; b ^= c; b <<<= (12, 12, 12, 12);
269	0	c = _mm_add_epi32(c, *d);
270	0	b = _mm_xor_si128(b, *c);
271	0	b = _mm_xor_si128(_mm_slli_epi32(b, 12), _mm_srli_epi32(*b, 20));
272	0
273	0	// a += b; d ^= a; d <<<= (8, 8, 8, 8);
274	0	a = _mm_add_epi32(a, *b);
275	0	d = _mm_xor_si128(d, *a);
276	0	d = _mm_xor_si128(_mm_slli_epi32(d, 8), _mm_srli_epi32(*d, 24));
277	0
278	0	// c += d; b ^= c; b <<<= (7, 7, 7, 7);
279	0	c = _mm_add_epi32(c, *d);
280	0	b = _mm_xor_si128(b, *c);
281	0	b = _mm_xor_si128(_mm_slli_epi32(b, 7), _mm_srli_epi32(*b, 25));
282	0	}
283	0	} Unexecuted instantiation: chacha20::backends::sse2::add_xor_rot Unexecuted instantiation: chacha20::backends::sse2::add_xor_rot