diff --git a/src/search.c b/src/search.c
index 26fb94d8..b3b84c9b 100644
--- a/src/search.c
+++ b/src/search.c
@@ -216,7 +216,7 @@ static unsigned hexagon_search(const encoder_state * const encoder_state, unsign
                              block_width, block_width, max_lcu_below);
       cost += calc_mvd_cost(encoder_state, mv.x + pattern->x, mv.y + pattern->y, mv_cand,merge_cand,num_cand,ref_idx, &bitcost);
 
-      PERFORMANCE_MEASURE_END(_DEBUG_PERF_SEARCH_PIXELS, encoder_state->encoder_control->threadqueue, "type=sad,step=large_hexbs,frame=%d,ref=%d,px_x=%d-%d,px_y=%d-%d,ref_px_x=%d-%d,ref_px_y=%d-%d", encoder_state->global->frame, ref->poc - encoder_state->global->poc, orig->x, orig->x + block_width, orig->y, orig->y + block_width, 
+      PERFORMANCE_MEASURE_END(_DEBUG_PERF_SEARCH_PIXELS, encoder_state->encoder_control->threadqueue, "type=sad,step=large_hexbs,frame=%d,tile=%d,ref=%d,px_x=%d-%d,px_y=%d-%d,ref_px_x=%d-%d,ref_px_y=%d-%d", encoder_state->global->frame, encoder_state->tile->id, ref->poc - encoder_state->global->poc, orig->x, orig->x + block_width, orig->y, orig->y + block_width, 
                               orig->x + mv.x + pattern->x, 
                               orig->x + mv.x + pattern->x + block_width, 
                               orig->y + mv.y + pattern->y, 
@@ -240,7 +240,7 @@ static unsigned hexagon_search(const encoder_state * const encoder_state, unsign
                              (encoder_state->tile->lcu_offset_y * LCU_WIDTH) + orig->y,
                              block_width, block_width, max_lcu_below);
       cost += calc_mvd_cost(encoder_state, 0, 0, mv_cand,merge_cand,num_cand,ref_idx, &bitcost);
-      PERFORMANCE_MEASURE_END(_DEBUG_PERF_SEARCH_PIXELS, encoder_state->encoder_control->threadqueue, "type=sad,step=00vector,frame=%d,ref=%d,px_x=%d-%d,px_y=%d-%d,ref_px_x=%d-%d,ref_px_y=%d-%d", encoder_state->global->frame, ref->poc - encoder_state->global->poc, orig->x, orig->x + block_width, orig->y, orig->y + block_width, 
+      PERFORMANCE_MEASURE_END(_DEBUG_PERF_SEARCH_PIXELS, encoder_state->encoder_control->threadqueue, "type=sad,step=00vector,frame=%d,tile=%d,ref=%d,px_x=%d-%d,px_y=%d-%d,ref_px_x=%d-%d,ref_px_y=%d-%d", encoder_state->global->frame, encoder_state->tile->id, ref->poc - encoder_state->global->poc, orig->x, orig->x + block_width, orig->y, orig->y + block_width, 
                               orig->x, 
                               orig->x + block_width, 
                               orig->y, 
@@ -265,7 +265,7 @@ static unsigned hexagon_search(const encoder_state * const encoder_state, unsign
                                  (encoder_state->tile->lcu_offset_y * LCU_WIDTH) + orig->y + pattern->y,
                                  block_width, block_width, max_lcu_below);
           cost += calc_mvd_cost(encoder_state, pattern->x, pattern->y, mv_cand,merge_cand,num_cand,ref_idx, &bitcost);
-          PERFORMANCE_MEASURE_END(_DEBUG_PERF_SEARCH_PIXELS, encoder_state->encoder_control->threadqueue, "type=sad,step=large_hexbs_around00,frame=%d,ref=%d,px_x=%d-%d,px_y=%d-%d,ref_px_x=%d-%d,ref_px_y=%d-%d", encoder_state->global->frame, ref->poc - encoder_state->global->poc, orig->x, orig->x + block_width, orig->y, orig->y + block_width, 
+          PERFORMANCE_MEASURE_END(_DEBUG_PERF_SEARCH_PIXELS, encoder_state->encoder_control->threadqueue, "type=sad,step=large_hexbs_around00,frame=%d,tile=%d,ref=%d,px_x=%d-%d,px_y=%d-%d,ref_px_x=%d-%d,ref_px_y=%d-%d", encoder_state->global->frame, encoder_state->tile->id, ref->poc - encoder_state->global->poc, orig->x, orig->x + block_width, orig->y, orig->y + block_width, 
                         orig->x + pattern->x, 
                         orig->x + pattern->x + block_width, 
                         orig->y + pattern->y, 
@@ -309,7 +309,7 @@ static unsigned hexagon_search(const encoder_state * const encoder_state, unsign
                                orig->y + mv.y + offset->y,
                                block_width, block_width, max_lcu_below);
         cost += calc_mvd_cost(encoder_state, mv.x + offset->x, mv.y + offset->y, mv_cand,merge_cand,num_cand,ref_idx, &bitcost);
-        PERFORMANCE_MEASURE_END(_DEBUG_PERF_SEARCH_PIXELS, encoder_state->encoder_control->threadqueue, "type=sad,step=large_hexbs_iterative,frame=%d,ref=%d,px_x=%d-%d,px_y=%d-%d,ref_px_x=%d-%d,ref_px_y=%d-%d", encoder_state->global->frame, ref->poc - encoder_state->global->poc, orig->x, orig->x + block_width, orig->y, orig->y + block_width, 
+        PERFORMANCE_MEASURE_END(_DEBUG_PERF_SEARCH_PIXELS, encoder_state->encoder_control->threadqueue, "type=sad,step=large_hexbs_iterative,frame=%d,tile=%d,ref=%d,px_x=%d-%d,px_y=%d-%d,ref_px_x=%d-%d,ref_px_y=%d-%d", encoder_state->global->frame, encoder_state->tile->id, ref->poc - encoder_state->global->poc, orig->x, orig->x + block_width, orig->y, orig->y + block_width, 
               orig->x + mv.x + offset->x, 
               orig->x + mv.x + offset->x + block_width, 
               orig->y + mv.y + offset->y, 
@@ -341,7 +341,7 @@ static unsigned hexagon_search(const encoder_state * const encoder_state, unsign
                              (encoder_state->tile->lcu_offset_y * LCU_WIDTH) + orig->y + mv.y + offset->y,
                              block_width, block_width, max_lcu_below);
       cost += calc_mvd_cost(encoder_state, mv.x + offset->x, mv.y + offset->y, mv_cand,merge_cand,num_cand,ref_idx, &bitcost);
-      PERFORMANCE_MEASURE_END(_DEBUG_PERF_SEARCH_PIXELS, encoder_state->encoder_control->threadqueue, "type=sad,step=small_hexbs,frame=%d,ref=%d,px_x=%d-%d,px_y=%d-%d,ref_px_x=%d-%d,ref_px_y=%d-%d", encoder_state->global->frame, ref->poc - encoder_state->global->poc, orig->x, orig->x + block_width, orig->y, orig->y + block_width, 
+      PERFORMANCE_MEASURE_END(_DEBUG_PERF_SEARCH_PIXELS, encoder_state->encoder_control->threadqueue, "type=sad,step=small_hexbs,frame=%d,tile=%d,ref=%d,px_x=%d-%d,px_y=%d-%d,ref_px_x=%d-%d,ref_px_y=%d-%d", encoder_state->global->frame, encoder_state->tile->id, ref->poc - encoder_state->global->poc, orig->x, orig->x + block_width, orig->y, orig->y + block_width, 
             orig->x + mv.x + offset->x, 
             orig->x + mv.x + offset->x + block_width, 
             orig->y + mv.y + offset->y,