diff --git a/README.md b/README.md
index ed35679..6a7ecf3 100644
--- a/README.md
+++ b/README.md
@@ -1,14 +1,14 @@
 # Print unsigned 16-bit
 
-6502 assembly code to print an unsigned 16-bit.
+6502 assembly code to print an unsigned 16-bit in decimal.
 
 Features:
 
 * Highly optimized for space
-* No zero-page usage   [version](print_uint16.s)    81 ($51) bytes
+* No zero-page usage   [version](print_uint16.s)    79 ($4F) bytes
 * With zero-page usage [version](print_uint16_zp.s) 69 ($45) bytes
 * With stack var usage [version](print_uint16_sp.s) 83 ($53) bytes
-* Only 2 ROM entry points: COUT, SCRN2
+* Only 2 ROM entry points used: PRHEXZ, SCRN2
 * Includes 7 byte demo
 
 # Machine Code
@@ -19,16 +19,16 @@ Sans-Zero-Page version:
 
 ```asm
 0800:A9 12 A2 34 4C 07 08 8E
-0808:57 08 48 A2 00 8E 54 08
-0810:8E 55 08 8E 56 08 A2 10
-0818:F8 0E 57 08 68 2A 48 A0
-0820:FD B9 57 07 79 57 07 99
-0828:57 07 C8 D0 F4 CA D0 E9
-0830:68 D8 A0 03 B9 53 08 20
-0838:41 08 88 D0 F7 8A F0 0E
-0840:60 48 20 7B F8 20 4B 08
-0848:68 29 0F D0 01 CA E8 F0
-0850:EF 4C E5 FD 00 00 00 00
+0808:55 08 A2 00 8E 52 08 8E
+0810:53 08 8E 54 08 A2 10 F8
+0818:0E 55 08 2A 48 A0 FD B9
+0820:55 07 79 55 07 99 55 07
+0828:C8 D0 F4 68 CA D0 E9 D8
+0830:A0 03 B9 51 08 20 3F 08
+0838:88 D0 F7 8A F0 0E 60 48
+0840:20 7B F8 20 49 08 68 29
+0848:0F D0 01 CA E8 F0 EF 4C
+0850:E5 FD 00 00 00 00
 ```
 
 With-Zero-Page version:
diff --git a/print_uint16 b/print_uint16
index b8cfe95..e559b16 100644
Binary files a/print_uint16 and b/print_uint16 differ
diff --git a/print_uint16.s b/print_uint16.s
index 9a74f1d..5ce54d4 100644
--- a/print_uint16.s
+++ b/print_uint16.s
@@ -21,12 +21,11 @@ SCRN2   = $F879
 ; ======================================================================
 PrintUint16
         STX _temp  
-        PHA             ; Optimized: STA _temp+1
 
-        LDX #0
-        STX _bcd+0
-        STX _bcd+1
-        STX _bcd+2
+        LDX #0          ; Optional 65C02 version
+        STX _bcd+0      ; STZ _bcd+0
+        STX _bcd+1      ; STZ _bcd+1
+        STX _bcd+2      ; STZ _bcd+2
 
 Dec2BCD
         LDX   #16       ; 16 bits
@@ -35,9 +34,8 @@ _Dec2BCD                ; https://en.wikipedia.org/wiki/Double_dabble
         ASL _temp+0     ;     abcd efgh | ijkl mnop |
 ;       ROL _temp+1     ; C=a bcde fghi | jklm nop0 |
 ;                       ; Bit 7654_3210 | 7654_3210 |
-        PLA
         ROL
-        PHA
+        PHA             ; Optimized: STA _temp+1
 
         LDY #$FD        ; $00-$FD=-3 bcd[0] bcd[1] bcd[2] bcd[3]
 _DoubleDabble           ;              Y=FD   Y=FE   Y=FF   Y=00
@@ -46,10 +44,10 @@ _DoubleDabble           ;              Y=FD   Y=FE   Y=FF   Y=00
         STA _bcd-$FD,Y
         INY
         BNE _DoubleDabble
+        PLA
         DEX
         BNE _Dec2BCD
 
-        PLA             ; keep stack
         CLD             ; X=0 = output length
 
 DecWidth