Skip to content

chacha20poly1305: Implement SIMD optimizations for tag comparison #258

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
matbech wants to merge 2 commits into from
Closed

chacha20poly1305: Implement SIMD optimizations for tag comparison #258

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
9cceb5a
Implement SIMD optimizations for tag comparison
matbech Sep 3, 2026
64d9a8a
added AArch64 (ARMv8) implementation
matbech Sep 3, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
24 changes: 24 additions & 0 deletions src/chacha20poly1305.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,6 +10,14 @@
#include "mystdint.h"
#include <string.h>

#if defined(__wasm_simd128__)
#include <wasm_simd128.h>
#elif defined(__SSE4_1__)
#include <immintrin.h>
#elif defined(__aarch64__)
#include <arm_neon.h>
#endif

#define ROL32(x, c) (((x) << (c)) | ((x) >> (32-(c))))
#define ROR32(x, c) (((x) >> (c)) | ((x) << (32-(c))))

Expand Down Expand Up @@ -215,6 +223,21 @@ void poly1305(const uint8_t* msg, size_t n, const uint8_t key[32],
SQLITE_PRIVATE
int poly1305_tagcmp(const uint8_t tag1[16], const uint8_t tag2[16])
{
#if defined(__wasm_simd128__)
v128_t tagDifference = wasm_v128_xor(
wasm_v128_load(tag1), wasm_v128_load(tag2));
return wasm_v128_any_true(tagDifference);
#elif defined(__SSE4_1__)
__m128i tag1_vec = _mm_loadu_si128((const __m128i*)tag1);
__m128i tag2_vec = _mm_loadu_si128((const __m128i*)tag2);
__m128i tagDifference = _mm_xor_si128(tag1_vec, tag2_vec);
return !_mm_testz_si128(tagDifference, tagDifference);
#elif defined(__aarch64__)
uint8x16_t tag1_vec = vld1q_u8(tag1);
uint8x16_t tag2_vec = vld1q_u8(tag2);
uint8x16_t tagDifference = veorq_u8(tag1_vec, tag2_vec);
return vmaxvq_u8(tagDifference) != 0;
#else
uint8_t d = 0;
d |= tag1[ 0] ^ tag2[ 0];
d |= tag1[ 1] ^ tag2[ 1];
Expand All @@ -233,6 +256,7 @@ int poly1305_tagcmp(const uint8_t tag1[16], const uint8_t tag2[16])
d |= tag1[14] ^ tag2[14];
d |= tag1[15] ^ tag2[15];
return (int) d;
#endif
}

/*
Expand Down
Loading