Skip to content

⚡ Optimize matrix memory layout in perten.h for better cache locality #13

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

Merged
perim merged 1 commit into from
Jul 16, 2026
Merged

⚡ Optimize matrix memory layout in perten.h for better cache locality #13

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
8 changes: 4 additions & 4 deletions perten.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -94,16 +94,16 @@ struct lazy_conditional_matrix
inline perten row(int r) { if (cache[r] == perten_max) calc(r); return cache[r]; }

/// modify one value and dirty its cache line
inline void modify(int c, int r, perten value) { matrix[c][r] = value; cache[r] = perten_max; }
inline void modify(int c, int r, perten value) { matrix[r][c] = value; cache[r] = perten_max; }

/// modify one condition and dirty relevant cache lines
void toggle(int c, bool v) { if (enabled[c] != v) { enabled[c] = v; for (unsigned r = 0; r < R; r++) if (matrix[c][r] != perten_full) cache[r] = perten_max; } }
void toggle(int c, bool v) { if (enabled[c] != v) { enabled[c] = v; for (unsigned r = 0; r < R; r++) if (matrix[r][c] != perten_full) cache[r] = perten_max; } }

inline bool is_enabled(int c) const { return enabled[c]; }

private:
void calc(int r) { cache[r] = perten_full; for (unsigned c = 0; c < C; c++) { if (enabled[c]) cache[r] = perten_multiply(cache[r], matrix[c][r]); } }
std::array<std::array<perten, R>, C> matrix;
void calc(int r) { cache[r] = perten_full; for (unsigned c = 0; c < C; c++) { if (enabled[c]) cache[r] = perten_multiply(cache[r], matrix[r][c]); } }
std::array<std::array<perten, C>, R> matrix;
std::array<uint_fast8_t, C> enabled;
std::array<perten, R> cache;
};
Loading