112
edits
Changes
→Kernel Optimization Attempts
Change : Replaces the boolean array hasSeen with a single int & uses bitwise operators
Theory : Since local array variables of threads are stored in Global memory this was an attempt to move that into the a register
Result : No speed up noticed, suggesting that more is happening beyond arrays stored in Global memory, perhaps some type of paging, more testing would be needed on something less erratic then a Sudoku Solver
{| class="wikitable mw-collapsible mw-collapsed"
}
|}
Change : Remove the counters, and logic which checks for a section needing a value in one place Theory : The counting logic requires a additional nested loop each solve cycle and created more thread divergence Result : The algorithm is slower, probably because 'sections requiring a single value' adds more values early in the kernel resulting in less passes overall Also this kernel is similar to one of my earlier builds, which was unable to solve the 9x9 getting stuck on every square having more then one possible value
{| class="wikitable mw-collapsible mw-collapsed"
! Dropping Section Logic (Kernel)
|-
|
__global__ void solve(int* d_a) { // Used to remember which row | col | box ( section ) have which values __shared__ bool rowHas[N][N]; __shared__ bool colHas[N][N]; __shared__ bool boxHas[N][N]; // Used to ensure that the table has changed __shared__ bool changed; // Number of spaces which can place the number in each section // Where the square is located in the Sudoku int row = threadIdx.x; int col = threadIdx.y; int box = row / BOX_W + (col / BOX_W) * BOX_W; // Unique identifier for each square in row, col, box // Corresponds to the generic Sudoku Solve // Using a Sudoku to solve a Sudoku !!! int offset = col + (row % BOX_W) * BOX_W + (box % BOX_W); // Square's location in the Sudoku int gridIdx = col * N + row; int at = d_a[gridIdx]; bool notSeen[N]; for (int i = 0; i < N; ++i) notSeen[i] = true; rowHas[col][row] = false; colHas[col][row] = false; boxHas[col][row] = false; __syncthreads(); if (at != UNASSIGNED) { rowHas[row][at - 1] = true; colHas[col][at - 1] = true; boxHas[box][at - 1] = true; } // Previous loop has not changed any values do { // RESET counters __syncthreads(); if (gridIdx == 0) // forget previous change changed = false; int count = 0; // number of values which can fit in this square int guess = 0; // last value found which can fit in this square for (int idx = 0; idx < N; ++idx) { // Ensures that every square in each section is working on a different number in the section int num = (idx + offset) % N; if (at == UNASSIGNED && notSeen[num]) { if (rowHas[row][num] || boxHas[box][num] || colHas[col][num]) notSeen[num] = false; else { ++count; guess = num; } } __syncthreads(); } if (count == 1) { at = guess + 1; rowHas[row][guess] = true; colHas[col][guess] = true; boxHas[box][guess] = true; changed = true; } __syncthreads(); } while (changed); //SOLVED CHECK if (!(rowHas[row][col] || colHas[row][col] || boxHas[row][col])) changed = true; __syncthreads(); if (changed && gridIdx == 0) at = 0; d_a[gridIdx] = at; }
|}
{| class="wikitable mw-collapsible mw-collapsed"
|-
|
__global__ void solve(int* d_a) { // Used to remember which row | col | box ( section ) have which values __shared__ bool rowHas[N][N]; __shared__ bool colHas[N][N]; __shared__ bool boxHas[N][N]; // Used to ensure that the table has changed __shared__ bool changed; // Number of spaces which can place the number in each section __shared__ int rowCount[N][N]; __shared__ int colCount[N][N]; __shared__ int boxCount[N][N]; // Where the square is located in the Sudoku int row = threadIdx.x; int col = threadIdx.y; int box = row / BOX_W + (col / BOX_W) * BOX_W; // Unique identifier for each square in row, col, box // Corresponds to the generic Sudoku Solve // Using a Sudoku to solve a Sudoku !!! int offset = col + (row % BOX_W) * BOX_W + (box % BOX_W); // Square's location in the Sudoku int gridIdx = col * N + row; int at = d_a[gridIdx]; bool notSeen[N]; for (int i = 0; i < N; ++i) notSeen[i] = true; rowHas[col][row] = false; colHas[col][row] = false; boxHas[col][row] = false; __syncthreads(); __shared__ int notify; if (at != UNASSIGNED) { rowHas[row][at - 1] = true; colHas[col][at - 1] = true; boxHas[box][at - 1] = true; } // Previous loop has not changed any values do { // RESET counters rowCount[col][row] = 0; colCount[col][row] = 0; boxCount[col][row] = 0; __syncthreads(); if (gridIdx == 0) { // forget previous change changed = false; notify = -1; } int count = 0; // number of values which can fit in this square int guess = 0; // last value found which can fit in this square for (int idx = 0; idx < N; ++idx) { // Ensures that every square in each section is working on a different number in the section int num = (idx + offset) % N; if (at == UNASSIGNED && notSeen[num]) { if (rowHas[row][num] || boxHas[box][num] || colHas[col][num]) notSeen[num] = false; else { ++count; guess = num; rowCount[row][num]++; colCount[col][num]++; boxCount[box][num]++; } } __syncthreads(); } if (rowCount[row][col] == 1 || colCount[row][col] == 1 || boxCount[row][col] == 1) notify = col; __syncthreads(); // Find values which can go in only one spot in the section if (notify > 0 && at == UNASSIGNED && notSeen[notify] && (rowCount[row][notify] == 1 || boxCount[box][notify] == 1 || colCount[col][notify] == 1)) { // In this section this value can only appear in this square guess = notify; count = 1; } if (count == 1) { at = guess + 1; rowHas[row][guess] = true; colHas[col][guess] = true; boxHas[box][guess] = true; changed = true; } __syncthreads(); } while (changed); //SOLVED CHECK if (!(rowHas[row][col] || colHas[row][col] || boxHas[row][col])) changed = true; __syncthreads(); if (changed && gridIdx == 0) at = 0; d_a[gridIdx] = at; }
|}
{| class="wikitable mw-collapsible mw-collapsed"
|-
|
__global__ void solve(int* d_a) { // Used to remember which row | col | box ( section ) have which values __shared__ bool rowHas[N][N]; __shared__ bool colHas[N][N]; __shared__ bool boxHas[N][N]; // Used to ensure that the table has changed __shared__ bool changed; // Number of spaces which can place the number in each section __shared__ int rowCount[N][N]; __shared__ int colCount[N][N]; __shared__ int boxCount[N][N]; // Where the square is located in the Sudoku int row = threadIdx.x; int col = threadIdx.y; int box = row / BOX_W + (col / BOX_W) * BOX_W; int gridIdx = col * N + row; int at = d_a[gridIdx]; // Unique identifier for each square in row, col, box // Corresponds to the generic Sudoku Solve // Using a Sudoku to solve a Sudoku !!! int offset = col + (row % BOX_W) * BOX_W + (box % BOX_W); // Square's location in the Sudoku int count = 0; //Number of values which can fit in this square int notSeen = 0; //Boolean Array as an Integer if (gridIdx == 0) changed = true; rowHas[col][row] = false; colHas[col][row] = false; boxHas[col][row] = false; rowCount[col][row] = 0; colCount[col][row] = 0; boxCount[col][row] = 0; __syncthreads(); if (at != UNASSIGNED) { rowHas[row][at - 1] = true; colHas[col][at - 1] = true; boxHas[box][at - 1] = true; } __syncthreads(); int guess; int b_shuttle = 1; for (int idx = 0; idx < N; ++idx) { int num = (idx + offset) % N; if (at == UNASSIGNED && !(rowHas[row][num] || boxHas[box][num] || colHas[col][num])) { notSeen |= b_shuttle; //this value can go here ++count; //how many values this square can have guess = num; //how many values this section can have rowCount[row][num]++; colCount[col][num]++; boxCount[box][num]++; } __syncthreads(); b_shuttle <<= 1; }
if (count == 1) {
