Fix word count issues for stm32f4lv and stm32f7lv

flashloaders/stm32f4lv.s

@@ -8,12 +8,18 @@ mycopy:
     add r10, r10, r12
 
 myloop:
-    # copy 1 bytes
+    # copy 1 byte each time and 4 times as one group
     ldrb r3, [r0]
+    ldrb r4, [r0, #1]
+    ldrb r5, [r0, #2]
+    ldrb r6, [r0, #3]
     strb r3, [r1]
+    strb r4, [r1, #1]
+    strb r5, [r1, #2]
+    strb r6, [r1, #3]
 
-    add r0, r0, #1
-    add r1, r1, #1
+    add r0, r0, #4
+    add r1, r1, #4
 
     # wait if FLASH_SR == 1
 mywait:

flashloaders/stm32f7lv.s

@@ -8,12 +8,18 @@ mycopy:
     add r10, r10, r12
 
 myloop:
-    # copy 1 byte
+    # copy 1 byte each time and 4 times as one group
     ldrb r3, [r0]
+    ldrb r4, [r0, #1]
+    ldrb r5, [r0, #2]
+    ldrb r6, [r0, #3]
     strb r3, [r1]
+    strb r4, [r1, #1]
+    strb r5, [r1, #2]
+    strb r6, [r1, #3]
 
-    add r0, r0, #1
-    add r1, r1, #1
+    add r0, r0, #4
+    add r1, r1, #4
 
     # memory barrier
     dsb sy