Add performance optimisiation for line_up_inv.s

wip-hugo/routines/line/line_down.s

@@ -51,7 +51,6 @@
         Sub_16 >D, <D, dx, #$00
 
         jsr pixel_draw ;;only used first pixel. after this relative position is abused
-        ;LDY #$00
         LDX X_pos
 for_x:
         ;; Paints A to address i btp_mem_pos* + Y

wip-hugo/routines/line/line_down_inv.s

@@ -45,7 +45,6 @@
         Sub_16 >D, <D, dy, #$00
 
         jsr pixel_draw ;;only used first pixel. after this relative position is abused
-        LDY #$00
         LDX Y_pos
 for_y:
         LDA byte_to_paint

wip-hugo/routines/line/line_up.s

@@ -12,15 +12,6 @@
 .proc line_up
         .include "line.inc"; Defines memory positions, ex X_pos
 
-        ;LDA #$20
-        ;STA X_pos
-        ;STA Y_pos
-        ;LDA #$10
-        ;STA Y_end
-        ;LDA #$40
-        ;STA X_end
-
-
         ;;We need to clear this memory
         LDA #$00
         STA <V
@@ -62,9 +53,6 @@
         Sub_16 >D, <D, dx, #$00
 
         jsr pixel_draw
-        ;INY ; Dont want underflow
-        ;LDY #$09
-        ;Sub_16 >btp_mem_pos, <btp_mem_pos, #$40, #$01 ;-320
         LDX X_pos
 for_x:
         LDA byte_to_paint

wip-hugo/routines/line/line_up_inv.s

@@ -44,20 +44,39 @@
         STA <D
         Add_16 >D, <D, #$ff, #$01
         Sub_16 >D, <D, dy, #$00
-for_y:
-        jsr pixel_draw
-        ;;Increment Y until Y_pos = Y_end and X_pos = X_end
-        DEC Y_pos
-        LDY Y_pos
-        CPY Y_end
-        BEQ end
 
+        jsr pixel_draw
+        LDX Y_pos
+for_y:
+        LDA byte_to_paint
+        ORA (>btp_mem_pos), Y
+        STA (>btp_mem_pos), Y
+decrement_y_pos:
+        DEY
+        CPY #$ff
+        BNE decrement_y_pos_end
+move_8px_up:
+        LDY #$07
+        Sub_16>btp_mem_pos, <btp_mem_pos,#$40 , #$01; ; +320 bytes
+decrement_y_pos_end:
+        DEX
+        CPX Y_end
+        BEQ end
         ;;If D <  %00000010 00000000:  case_2
         ;;else case 1.
         Lag_16 >D, <D, #$00, #$02, case_2
 case_1:
-        INC X_pos
-        Sub_16 >D, <D, >V, <V; D = D - V
+        Sub_16 >D, <D, >V, <V, !; D = D - V
+increment_pixel_x:
+        LDA byte_to_paint
+        LSR byte_to_paint
+        BCC for_y
+move_8px_left:
+        ;; add +8 to btp_mem_pos. Find more of why in pixel_draw
+        Add_16 >btp_mem_pos, <btp_mem_pos, #$08, #$00
+        ;; reset byte_to_paint
+        LDA #%10000000
+        STA byte_to_paint
         JMP for_y
 case_2:
         Add_16 >D, <D, >dx_2, <dx_2;D = D + 2*dy

wip-hugo/routines/memory/pixel_draw.s

@@ -46,24 +46,12 @@ end__:
 	;; Adding inside chunk offset
 	LDA #%00000111 ; A = y (mod 8)
 	AND Y_pos ;; offset to add
-
-
-	;;ading offset, same as psudocode bellow
-	;;Add_16 >btp_mem_pos, <btp_mem_pos, A, #$00
-	;CLC ; Y = b_low
-	;ADC >btp_mem_pos
-	;STA >btp_mem_pos
-	;LDA #$00
-	;ADC <btp_mem_pos ; C =0
-	;STA <btp_mem_pos
-
 	TAY
-	CLC
 
 	LDA #$00
 	STA $4B
-
 	;;y =8 translates to 320 bytes.
+	CLC
 	LDA #%11111000 ; A =  y - [y (mod 8)]
 	AND Y_pos
 	STA >C
@@ -91,7 +79,6 @@ end__:
 	Add_16 >btp_mem_pos, <btp_mem_pos, #<Bitmap, #>Bitmap, !
 
 	;;Let draw some stuff
-	;LDY #$00
 	LDA byte_to_paint ;; note that both bytes are used!
 	ORA (>btp_mem_pos), Y
 	STA (>btp_mem_pos), Y