diff --git a/gr-sim/tfv_flying_6502.c b/gr-sim/tfv_flying_6502.c
index 49611029..dc45d74c 100644
--- a/gr-sim/tfv_flying_6502.c
+++ b/gr-sim/tfv_flying_6502.c
@@ -838,7 +838,7 @@ match:
 
 			ram[SCREEN_X]++;
 			if (ram[SCREEN_X] >= LOWRES_W) break;
-							cycles.mode7+=43;
+							cycles.mode7+=41;
 
 
 			/* cache last value */
diff --git a/tfv/OPTIMIZATION b/tfv/OPTIMIZATION
index 094edc05..dcd9c55d 100644
--- a/tfv/OPTIMIZATION
+++ b/tfv/OPTIMIZATION
@@ -186,5 +186,19 @@ In-line unsigned multiply inside of signed multiply (save 12 cycles)
 	Frame Rate = 5.42 fps
 
 
+Have loop counter count down from 40 instead of count up (avoid compare)
+	Cycles: flying=             187
+	Cycles: getkey=              46
+	Cycles: page_flip=           26
+	Cycles: multiply=        40,888
+	Cycles: mode7=          115,538
+	Cycles: lookup_map=      22,747
+	Cycles: put_sprite=       2,561
+	================================
+	Total =                 181,993
+	Frame Rate = 5.49 fps
+
+
+
 Each cycle removed from inner X loop saves
 	32*40=1280 cycles
diff --git a/tfv/tfv_flying.s b/tfv/tfv_flying.s
index 916b7eec..f971a8d2 100644
--- a/tfv/tfv_flying.s
+++ b/tfv/tfv_flying.s
@@ -935,8 +935,7 @@ calc_horizontal_scale:
 
 	; brk	; space_y = f7:04
 
-	; FIXME: start at 40 and decrement?
-	ldx	#0	; was SCREEN_X					; 2
+	ldx	#40	; was SCREEN_X					; 2
 								;==========
 								;	 22
 screenx_loop:
@@ -994,11 +993,10 @@ dyi_label:
 	adc	#0							; 2
 	sta	SPACEY_I						; 3
 
-	inx	;inc	SCREEN_X					; 2
-	cpx	#40			; LOWRES width			; 2
-	beq	done_screenx_loop					; 2nt/3
+	dex	; decrement	SCREEN_X				; 2
+	beq	done_screenx_loop	; branch until we've done 40	; 2nt/3
 								;=============
-								;	43
+								;	41
 
 
 	; cache color and return if same as last time