diff --git a/firmware/src/leds.pio b/firmware/src/leds.pio
index 7f5aef9..5b6ec8c 100644
--- a/firmware/src/leds.pio
+++ b/firmware/src/leds.pio
@@ -1,45 +1,49 @@
 .define public irq_did_latch 0
 .define public irq_delaying 1
 
+; TODO: check if delays can be lowered with a PCB
+.define public srclk_0_delay 1
+.define public srclk_1_delay 2
+.define public rclk_1_delay 3
+
 .program leds_px_pusher
 .side_set 1 opt
-public entry_point:
+entry_point:
 .wrap_target
   ; get 32 bits from fifo (not required with autopull, useful for debug)
   ; pull
   ; push 24 bits to the shift registers
   ; also, return latch bit to 0
-  set x, 23      side 0
+  set x, 23                     side 0
 loop:
-  ; TODO: check if delays can be lowered with a PCB
   ; set bit; lower clock edge
-  out pins, 1    side 0 [1]
+  out pins, 1                   side 0  [srclk_0_delay]
   ; loop; latch bit (rising edge)
-  jmp x-- loop   side 1 [2]
+  jmp x-- loop                  side 1  [srclk_1_delay]
 end:
   ; ignore unused bits
   ; load MSBs into x
   ; lower clock edge
   out x, 8    side 0
   ; MSB=1 indicates end of row
-  jmp x-- end_of_row
-  .wrap
+  jmp !x entry_point
 end_of_row:
   ; wait until previous row's delay is complete
   wait 0 irq irq_delaying
   ; signal that row is processed
   irq set irq_did_latch
   ; clock RCLK (latch onto register output stage)
-  set pins, 1 [3]
+  set pins, 1                           [rclk_1_delay]
   set pins, 0
   ; wait for next row
-  jmp entry_point
+  .wrap
 
 .program leds_delay
 .side_set 1 opt
 .define public output_on 0
 .define public output_off 1
-public entry_point:
+entry_point:
+.wrap_target
   ; begin only after data is latched
   wait 1 irq irq_did_latch
   ; signal that delay is ongoing
@@ -54,3 +58,4 @@ end:
   ; signal that delay is complete
   ; disable output
   irq clear irq_delaying        side output_off
+  .wrap
diff --git a/firmware/src/leds.pio.h b/firmware/src/leds.pio.h
index 9fe2bb7..6d581aa 100644
--- a/firmware/src/leds.pio.h
+++ b/firmware/src/leds.pio.h
@@ -10,15 +10,16 @@
 
 #define irq_did_latch 0
 #define irq_delaying 1
+#define srclk_0_delay 1
+#define srclk_1_delay 2
+#define rclk_1_delay 3
 
 // -------------- //
 // leds_px_pusher //
 // -------------- //
 
 #define leds_px_pusher_wrap_target 0
-#define leds_px_pusher_wrap 4
-
-#define leds_px_pusher_offset_entry_point 0u
+#define leds_px_pusher_wrap 8
 
 static const uint16_t leds_px_pusher_program_instructions[] = {
             //     .wrap_target
@@ -26,19 +27,18 @@ static const uint16_t leds_px_pusher_program_instructions[] = {
     0x7101, //  1: out    pins, 1         side 0 [1] 
     0x1a41, //  2: jmp    x--, 1          side 1 [2] 
     0x7028, //  3: out    x, 8            side 0     
-    0x0045, //  4: jmp    x--, 5                     
-            //     .wrap
+    0x0020, //  4: jmp    !x, 0                      
     0x2041, //  5: wait   0 irq, 1                   
     0xc000, //  6: irq    nowait 0                   
     0xe301, //  7: set    pins, 1                [3] 
     0xe000, //  8: set    pins, 0                    
-    0x0000, //  9: jmp    0                          
+            //     .wrap
 };
 
 #if !PICO_NO_HARDWARE
 static const struct pio_program leds_px_pusher_program = {
     .instructions = leds_px_pusher_program_instructions,
-    .length = 10,
+    .length = 9,
     .origin = -1,
 };
 
@@ -60,8 +60,6 @@ static inline pio_sm_config leds_px_pusher_program_get_default_config(uint offse
 #define leds_delay_output_on 0
 #define leds_delay_output_off 1
 
-#define leds_delay_offset_entry_point 0u
-
 static const uint16_t leds_delay_program_instructions[] = {
             //     .wrap_target
     0x20c0, //  0: wait   1 irq, 0