highperfocused/bitcoin
1
0
Fork 0
mirror of https://github.com/bitcoin/bitcoin.git synced 2025-08-27 20:11:47 +02:00
Code Issues Packages Projects Releases Wiki Activity

optimization: peel align-head and unroll body to 64 bytes

Browse Source 
Benchmarks indicated that obfuscating multiple bytes already gives an order of magnitude speed-up, but:
* GCC still emitted scalar code;
* Clang’s auto-vectorized loop ran on the slow unaligned-load path.

Fix contains:
* peeling the misaligned head enabled the hot loop starting at an 8-byte address;
* `std::assume_aligned<8>` tells the optimizer the promise holds - required to keep Apple Clang happy;
* manually unrolling the body to 64 bytes enabled GCC to auto-vectorize.

Note that `target.size() > KEY_SIZE` condition is just an optimization, the aligned and unaligned loops work without it as well - it's why the alignment calculation still contains `std::min`.

>  C++ compiler .......................... GNU 14.2.0

|             ns/byte |              byte/s |    err% |        ins/byte |        cyc/byte |    IPC |       bra/byte |   miss% |     total | benchmark
|--------------------:|--------------------:|--------:|----------------:|----------------:|-------:|---------------:|--------:|----------:|:----------
|                0.03 |   32,464,658,919.11 |    0.0% |            0.50 |            0.11 |  4.474 |           0.08 |    0.0% |      5.29 | `ObfuscationBench`

> C++ compiler .......................... Clang 20.1.7

|             ns/byte |              byte/s |    err% |        ins/byte |        cyc/byte |    IPC |       bra/byte |   miss% |     total | benchmark
|--------------------:|--------------------:|--------:|----------------:|----------------:|-------:|---------------:|--------:|----------:|:----------
|                0.02 |   41,231,547,045.17 |    0.0% |            0.30 |            0.09 |  3.463 |           0.02 |    0.0% |      5.47 | `ObfuscationBench`

Co-authored-by: Hodlinator <172445034+hodlinator@users.noreply.github.com>
This commit is contained in:
Lőrinc
2025-05-22 11:45:15 +02:00
parent e7114fc6dc
commit 248b6a27c3
1 changed files with 21 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
src/util/obfuscation.h
View File

@@ -14,6 +14,7 @@
#include <bit> #include <bit>
#include <climits> #include <climits>
#include <ios> #include <ios>
#include <memory>
class Obfuscation class Obfuscation
{ {
@@ -33,10 +34,27 @@ public:
{ {
if (!*this) return; if (!*this) return;
const KeyType rot_key{m_rotations[key_offset % KEY_SIZE]}; // Continue obfuscation from where we left off KeyType rot_key{m_rotations[key_offset % KEY_SIZE]}; // Continue obfuscation from where we left off
if (target.size() > KEY_SIZE) {
// Obfuscate until 64-bit alignment boundary
if (const auto misalign{std::bit_cast<uintptr_t>(target.data()) % KEY_SIZE}) {
const size_t alignment{std::min(KEY_SIZE - misalign, target.size())};
XorWord(target.first(alignment), rot_key);
target = {std::assume_aligned<KEY_SIZE>(target.data() + alignment), target.size() - alignment};
rot_key = m_rotations[(key_offset + alignment) % KEY_SIZE];
}
// Aligned obfuscation in 64-byte chunks
for (constexpr auto unroll{8}; target.size() >= KEY_SIZE * unroll; target = target.subspan(KEY_SIZE * unroll)) {
for (size_t i{0}; i < unroll; ++i) {
XorWord(target.subspan(i * KEY_SIZE, KEY_SIZE), rot_key);
}
}
// Aligned obfuscation in 64-bit chunks
for (; target.size() >= KEY_SIZE; target = target.subspan(KEY_SIZE)) { for (; target.size() >= KEY_SIZE; target = target.subspan(KEY_SIZE)) {
XorWord(target.first<KEY_SIZE>(), rot_key); XorWord(target.first<KEY_SIZE>(), rot_key);
} }
}
XorWord(target, rot_key); XorWord(target, rot_key);
} }