Skip to content

Fix canny_opencl tests for Intel CPUs #3164

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
9prady9 merged 2 commits into from
Jul 30, 2021
Merged

Fix canny_opencl tests for Intel CPUs #3164

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
61ba252
Fix the edgeTraceKernel for CPU devices
umar456 Jul 29, 2021
b4714c1
Formatting changes accompanying the edgeTraceKernel changes
umar456 Jul 29, 2021
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
46 changes: 24 additions & 22 deletions src/backend/opencl/kernel/trace_edge.cl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,15 +7,15 @@
* http://arrayfire.com/licenses/BSD-3-Clause
********************************************************/

__constant int STRONG = 1;
__constant int WEAK = 2;
__constant int NOEDGE = 0;
#define STRONG 1
#define WEAK 2
#define NOEDGE 0

#if defined(INIT_EDGE_OUT)
kernel void initEdgeOutKernel(global T* output, KParam oInfo,
global const T* strong, KParam sInfo,
global const T* weak, KParam wInfo,
unsigned nBBS0, unsigned nBBS1) {
global const T* strong, KParam sInfo,
global const T* weak, KParam wInfo,
unsigned nBBS0, unsigned nBBS1) {
// batch offsets for 3rd and 4th dimension
const unsigned b2 = get_group_id(0) / nBBS0;
const unsigned b3 = get_group_id(1) / nBBS1;
Expand Down Expand Up @@ -55,8 +55,7 @@ kernel void initEdgeOutKernel(global T* output, KParam oInfo,

#if defined(EDGE_TRACER)
kernel void edgeTrackKernel(global T* output, KParam oInfo, unsigned nBBS0,
unsigned nBBS1,
global volatile int* hasChanged) {
unsigned nBBS1, global volatile int* hasChanged) {
// shared memory with 1 pixel border
// strong and weak images are binary(char) images thus,
// occupying only (16+2)*(16+2) = 324 bytes per shared memory tile
Expand Down Expand Up @@ -102,13 +101,11 @@ kernel void edgeTrackKernel(global T* output, KParam oInfo, unsigned nBBS0,

int tid = lx + get_local_size(0) * ly;

bool continueIter = 1;
bool continueIter = true;

int mycounter = 0;
while (continueIter) {
int nw, no, ne, we, ea, sw, so, se;

if (outMem[j][i] == WEAK) {
int nw, no, ne, we, ea, sw, so, se;
nw = outMem[j - 1][i - 1];
no = outMem[j - 1][i];
ne = outMem[j - 1][i + 1];
Expand All @@ -129,14 +126,17 @@ kernel void edgeTrackKernel(global T* output, KParam oInfo, unsigned nBBS0,

predicates[tid] = false;
if (outMem[j][i] == STRONG) {
bool nw, no, ne, we, ea, sw, so, se;
// clang-format off
nw = outMem[j - 1][i - 1] == WEAK && VALID_BLOCK_IDX(j - 1, i - 1);
no = outMem[j - 1][i] == WEAK && VALID_BLOCK_IDX(j - 1, i);
no = outMem[j - 1][i] == WEAK && VALID_BLOCK_IDX(j - 1, i);
ne = outMem[j - 1][i + 1] == WEAK && VALID_BLOCK_IDX(j - 1, i + 1);
we = outMem[j][i - 1] == WEAK && VALID_BLOCK_IDX(j, i - 1);
ea = outMem[j][i + 1] == WEAK && VALID_BLOCK_IDX(j, i + 1);
we = outMem[j][i - 1] == WEAK && VALID_BLOCK_IDX(j, i - 1);
ea = outMem[j][i + 1] == WEAK && VALID_BLOCK_IDX(j, i + 1);
sw = outMem[j + 1][i - 1] == WEAK && VALID_BLOCK_IDX(j + 1, i - 1);
so = outMem[j + 1][i] == WEAK && VALID_BLOCK_IDX(j + 1, i);
so = outMem[j + 1][i] == WEAK && VALID_BLOCK_IDX(j + 1, i);
se = outMem[j + 1][i + 1] == WEAK && VALID_BLOCK_IDX(j + 1, i + 1);
// clang-format on

bool hasWeakNeighbour =
nw || no || ne || ea || se || so || sw || we;
Expand All @@ -146,15 +146,18 @@ kernel void edgeTrackKernel(global T* output, KParam oInfo, unsigned nBBS0,
barrier(CLK_LOCAL_MEM_FENCE);

// Following Block is equivalent of __syncthreads_or in CUDA
for (int nt = TOTAL_NUM_THREADS / 2; nt > 0; nt >>= 1) {
for (int nt = TOTAL_NUM_THREADS >> 1; nt > 0; nt >>= 1) {
if (tid < nt) {
predicates[tid] = predicates[tid] || predicates[tid + nt];
}
barrier(CLK_LOCAL_MEM_FENCE);
}

continueIter = predicates[0];
};

// Needed for Intel OpenCL implementation targeting CPUs
barrier(CLK_LOCAL_MEM_FENCE);
}

// Check if any 1-pixel border ring
// has weak pixels with strong candidates
Expand Down Expand Up @@ -195,7 +198,7 @@ kernel void edgeTrackKernel(global T* output, KParam oInfo, unsigned nBBS0,

#if defined(SUPPRESS_LEFT_OVER)
kernel void suppressLeftOverKernel(global T* output, KParam oInfo,
unsigned nBBS0, unsigned nBBS1) {
unsigned nBBS0, unsigned nBBS1) {
// batch offsets for 3rd and 4th dimension
const unsigned b2 = get_group_id(0) / nBBS0;
const unsigned b3 = get_group_id(1) / nBBS1;
Expand All @@ -208,9 +211,8 @@ kernel void suppressLeftOverKernel(global T* output, KParam oInfo,

// Offset input and output pointers to second pixel of second coloumn/row
// to skip the border
global T* oPtr = output +
(b2 * oInfo.strides[2] + b3 * oInfo.strides[3]) +
oInfo.strides[1] + 1;
global T* oPtr = output + (b2 * oInfo.strides[2] + b3 * oInfo.strides[3]) +
oInfo.strides[1] + 1;

if (gx < (oInfo.dims[0] - 2) && gy < (oInfo.dims[1] - 2)) {
int idx = gx * oInfo.strides[0] + gy * oInfo.strides[1];
Expand Down