added cx16.MCIOUT() kernal call

correct case of several other cx16 kernal calls.

corrected to upper case: cx16 kernal calls CLOSE_ALL, LKUPLA, LKUPSA, JSRFAR, PRIMM, MACPTR.

codeGenCpu6502/src/prog8/codegen/cpu6502/BuiltinFunctionsAsmGen.kt

@@ -183,7 +183,7 @@ internal class BuiltinFunctionsAsmGen(private val program: PtProgram,
         asmgen.out("  sta  (+)+0 |  sty  (+)+1")
         asmgen.assignExpressionToRegister(fcall.args[2], RegisterOrPair.AY)     // uword argument
         asmgen.out("""
-            jsr  cx16.jsrfar
+            jsr  cx16.JSRFAR
 +           .word  0
 +           .byte  0""")
         // note that by convention the values in A+Y registers are now the return value of the call.

compiler/res/prog8lib/cx16/diskio.p8

@@ -301,22 +301,22 @@ close_end:
     sub f_read(uword bufferpointer, uword num_bytes) -> uword {
         ; -- read from the currently open file, up to the given number of bytes.
         ;    returns the actual number of bytes read.  (checks for End-of-file and error conditions)
-        ;    NOTE: cannot be used to load into VRAM.  Use vload() or call cx16.macptr() yourself with the vera data register as address.
+        ;    NOTE: cannot be used to load into VRAM.  Use vload() or call cx16.MACPTR() yourself with the vera data register as address.
         if not iteration_in_progress or not num_bytes
             return 0
 
         reset_read_channel()
         list_blocks = 0     ; we reuse this variable for the total number of bytes read
 
-        ; commander X16 supports fast block-read via macptr() kernal call
+        ; commander X16 supports fast block-read via MACPTR() kernal call
         uword readsize
         while num_bytes {
             readsize = 255
             if num_bytes<readsize
                 readsize = num_bytes
-            readsize = cx16.macptr(lsb(readsize), bufferpointer, false)
+            readsize = cx16.MACPTR(lsb(readsize), bufferpointer, false)
             if_cs
-                goto byte_read_loop     ; macptr block read not supported, do fallback loop
+                goto byte_read_loop     ; MACPTR block read not supported, do fallback loop
             list_blocks += readsize
             bufferpointer += readsize
             if msb(bufferpointer) == $c0
@@ -329,7 +329,7 @@ close_end:
         }
         return list_blocks  ; number of bytes read
 
-byte_read_loop:         ; fallback if macptr() isn't supported on the device
+byte_read_loop:         ; fallback if MACPTR isn't supported on the device
         %asm {{
             lda  bufferpointer
             sta  m_in_buffer+1
@@ -360,7 +360,7 @@ m_in_buffer     sta  $ffff
     ; optimized for Commander X16 to use MACPTR block read kernal call
     sub f_read_all(uword bufferpointer) -> uword {
         ; -- read the full contents of the file, returns number of bytes read.
-        ;    NOTE: cannot be used to load into VRAM.  Use vload() or call cx16.macptr() yourself with the vera data register as address.
+        ;    NOTE: cannot be used to load into VRAM.  Use vload() or call cx16.MACPTR() yourself with the vera data register as address.
         if not iteration_in_progress
             return 0
 

compiler/res/prog8lib/cx16/syslib.p8

@@ -331,17 +331,16 @@ cx16 {
 ; spelling of the names is taken from the Commander X-16 rom sources
 
 ; supported C128 additions
-romsub $ff4a = close_all(ubyte device @A)  clobbers(A,X,Y)
+romsub $ff4a = CLOSE_ALL(ubyte device @A)  clobbers(A,X,Y)
-romsub $ff59 = lkupla(ubyte la @A)  clobbers(A,X,Y)
+romsub $ff59 = LKUPLA(ubyte la @A)  clobbers(A,X,Y)
-romsub $ff5c = lkupsa(ubyte sa @Y)  clobbers(A,X,Y)
+romsub $ff5c = LKUPSA(ubyte sa @Y)  clobbers(A,X,Y)
 romsub $ff5f = screen_mode(ubyte mode @A, bool getCurrent @Pc)  clobbers(X, Y) -> ubyte @A, bool @Pc        ; note: X,Y size result is not supported, use SCREEN or get_screen_mode routine for that
 romsub $ff62 = screen_set_charset(ubyte charset @A, uword charsetptr @XY)  clobbers(A,X,Y)      ; incompatible with C128  dlchr()
 ; not yet supported: romsub $ff65 = pfkey()  clobbers(A,X,Y)
-romsub $ff6e = jsrfar()  ; following word = address to call, byte after that=rom/ram bank it is in
+romsub $ff6e = JSRFAR()  ; following word = address to call, byte after that=rom/ram bank it is in
 romsub $ff74 = fetch(ubyte bank @X, ubyte index @Y)  clobbers(X) -> ubyte @A
 romsub $ff77 = stash(ubyte data @A, ubyte bank @X, ubyte index @Y)  clobbers(X)
-romsub $ff7a = cmpare(ubyte data @A, ubyte bank @X, ubyte index @Y)  clobbers(X)
+romsub $ff7d = PRIMM()
-romsub $ff7d = primm()
 
 ; It's not documented what registers are clobbered, so we assume the worst for all following kernal routines...:
 
@@ -395,7 +394,8 @@ romsub $fed5 = console_set_paging_message(uword msgptr @R0)  clobbers(A,X,Y)
 romsub $fecf = entropy_get() -> ubyte @A, ubyte @X, ubyte @Y
 romsub $fecc = monitor()  clobbers(A,X,Y)
 
-romsub $ff44 = macptr(ubyte length @A, uword buffer @XY, bool dontAdvance @Pc)  clobbers(A) -> bool @Pc, uword @XY
+romsub $ff44 = MACPTR(ubyte length @A, uword buffer @XY, bool dontAdvance @Pc)  clobbers(A) -> bool @Pc, uword @XY
+romsub $feb1 = MCIOUT(ubyte length @A, uword buffer @XY, bool dontAdvance @Pc)  clobbers(A) -> bool @Pc, uword @XY
 romsub $ff47 = enter_basic(bool cold_or_warm @Pc)  clobbers(A,X,Y)
 romsub $ff4d = clock_set_date_time(uword yearmonth @R0, uword dayhours @R1, uword minsecs @R2, ubyte jiffies @R3)  clobbers(A, X, Y)
 romsub $ff50 = clock_get_date_time()  clobbers(A, X, Y)  -> uword @R0, uword @R1, uword @R2, ubyte @R3   ; result registers see clock_set_date_time()

docs/source/programming.rst

@@ -937,7 +937,7 @@ memory (name, size, alignment)
     You can only treat it as a pointer or use it in inline assembly.
 
 callfar (bank, address, argumentword) -> uword     ; NOTE: specific to cx16 target for now
-    Calls an assembly routine in another bank on the Commander X16 (using its ``jsrfar`` routine)
+    Calls an assembly routine in another bank on the Commander X16 (using its ``JSRFAR`` routine)
     Be aware that ram OR rom bank may be changed depending on the address it jumps to!
     The argumentword will be loaded into the A+Y registers before calling the routine.
     The uword value that the routine returns in the A+Y registers, will be returned.

docs/source/todo.rst

@@ -1,6 +1,8 @@
 TODO
 ====
 
+- make the adpcm example able to decode and play stereo music.
+
 - [on branch: shortcircuit] investigate McCarthy evaluation again? this may also reduce code size perhaps for things like if a>4 or a<2 ....
 - [on branch: ir-less-branch-opcodes] IR: reduce the number of branch instructions such as BEQ, BEQR, etc (gradually), replace with CMP(I) + status branch instruction
 - IR: reduce amount of CMP/CMPI after instructions that set the status bits correctly (LOADs? INC? etc), but only after setting the status bits is verified!
@@ -53,6 +55,8 @@ Compiler:
 
 Libraries:
 
+- gfx2 cs_innerloop640() extend number of bytes cleared, and use vera fx cached writes
+- gfx2 horizontal_line and vertical_line: use vera fx cached writes
 - port monogfx, gf2, graphics to the vm
 - use verafx transparent writes to speed up pixel plotting in gfx2 and monogfx modules (avoids read/mask/write)
 - fix the problems in atari target, and flesh out its libraries.

examples/cx16/chunkedfile/mcf.p8

@@ -181,7 +181,7 @@ processchunk_call           jsr  $ffff      ; modified
             ubyte readsize = 255
             if msb(size)==0
                 readsize = lsb(size)
-            cx16.r2 = cx16.macptr(readsize, bonkbuffer, false)  ; can't macptr directly to bonk ram
+            cx16.r2 = cx16.MACPTR(readsize, bonkbuffer, false)  ; can't MACPTR directly to bonk ram
             cx16.rombank(bonk)
             sys.memcopy(bonkbuffer, cx16.r3, cx16.r2)   ; copy to bonk ram
             cx16.rombank(orig_rom_bank)
@@ -192,9 +192,9 @@ processchunk_call           jsr  $ffff      ; modified
 
     sub readblock(uword size, uword address, bool dontAdvance) -> uword {
         if msb(size)>=2
-            return cx16.macptr(0, address, dontAdvance)         ; read 512 bytes
+            return cx16.MACPTR(0, address, dontAdvance)         ; read 512 bytes
         if msb(size)
-            return cx16.macptr(255, address, dontAdvance)       ; read 255 bytes
+            return cx16.MACPTR(255, address, dontAdvance)       ; read 255 bytes
-        return cx16.macptr(lsb(size), address, dontAdvance)     ; read remaining number of bytes
+        return cx16.MACPTR(lsb(size), address, dontAdvance)     ; read remaining number of bytes
     }
 }

examples/test.p8

@@ -1,83 +1,18 @@
-%import diskio
-%import textio
-;%import math
-;%import verafx
-%zeropage basicsafe
-%option no_sysinit
-
 main {
-    %option verafxmuls
-
     sub start() {
-        word w1 = -123
+        cx16.r1H = %00000001        ; enable auto-indent
-        word w2 = 222
+        cx16.r2L = 4
-        ubyte b2 = 222
+        cx16.r2H = 80
-        byte sb2 = 111
+        cx16.r3L = 8
-        txt.print_w(w1*w2)
+        cx16.r3H = 11<<4 | 7;  background_color<<4 | text_color
-        txt.nl()
+        cx16.r4 = 0
-        txt.print_w(w1*222)
+        cx16.r1L = 0
-        txt.nl()
+        cx16.rombank($d)
-        w1 = -123
+        %asm {{
-        w1 *= 222
+            ldx #2
-        txt.print_w(w1)
+            ldy #64
-        txt.nl()
+            jmp $c006
-        w1 = -123
+        }}
-        w1 *= w2
-        txt.print_w(w1)
-        txt.nl()
-        w1 = -123
-        w1 *= (w2-1)
-        txt.print_w(w1)
-        txt.nl()
-        w1 = -123
-        w1 *= b2
-        txt.print_w(w1)
-        txt.nl()
-        w1 = -123
-        w1 *= sb2
-        txt.print_w(w1)
-        txt.nl()
-
-;        txt.print_uw(math.mul16_last_upper())
-;        txt.nl()
-;        uword value1=5678
-;        uword value2=9999
-;        uword result = value1*value2
-;        uword upper16 = math.mul16_last_upper()
-;        txt.print_uw(result)
-;        txt.spc()
-;        txt.print_uw(upper16)
-;        txt.nl()
-
-
-;        const word MULTIPLIER = 431
-;
-;        ; verify results:
-;        for value in -50 to 50 {
-;            if value*MULTIPLIER != verafx.muls(value, MULTIPLIER) {
-;                txt.print("verafx muls error\n")
-;                sys.exit(1)
-;            }
-;        }
-;
-;
-;        word value
-;        txt.print("verafx muls...")
-;        cbm.SETTIM(0,0,0)
-;        for value in -50 to 50 {
-;            repeat 250 void verafx.muls(value, MULTIPLIER)
-;        }
-;        txt.print_uw(cbm.RDTIM16())
-;        txt.nl()
-;
-;        txt.print("6502 muls...")
-;        cbm.SETTIM(0,0,0)
-;        for value in -50 to 50 {
-;            repeat 250 cx16.r0s = value*MULTIPLIER
-;        }
-;        txt.print_uw(cbm.RDTIM16())
-;        txt.nl()
-
     }
 }