added verafx.available()

compiler/res/prog8lib/cx16/verafx.p8

@@ -6,6 +6,21 @@
 verafx {
     %option no_symbol_prefixing
 
+    sub available() -> bool {
+        ; returns true if Vera FX is available (Vera V0.3.1 or later), false if not.
+        cx16.r1L = 0
+        cx16.r0L = cx16.VERA_CTRL
+        cx16.VERA_CTRL = $7e
+        if cx16.VERA_DC_VER0 == $56 {
+            ; Vera version number is valid.
+            ; Vera fx is available on Vera version 0.3.1 and later,
+            ; so no need to even check VERA_DC_VER1, which contains 0 (or higher)
+            cx16.r1L = mkword(cx16.VERA_DC_VER2, cx16.VERA_DC_VER3) >= $0301
+        }
+        cx16.VERA_CTRL = cx16.r0L
+        return cx16.r1L
+    }
+
     sub clear(ubyte vbank, uword vaddr, ubyte data, uword amountof32bits) {
         ; use cached 4-byte write to quickly clear a portion of the video memory to a given byte value
         ; this routine is around 3 times faster as gfx2.clear_screen()

compiler/res/prog8lib/virtual/math.p8

@@ -2,9 +2,6 @@
 
 math {
 
-    ; TODO: the VM doesn't yet store the full 32 bits result of a 16*16 multiplication, so there is NO mul16_last_upper() routine here at this time.
-
-
     sub sin8u(ubyte angle) -> ubyte {
         ubyte[256] sintab = [$80, $83, $86, $89, $8c, $8f, $92, $95, $98, $9b, $9e, $a2, $a5, $a7, $aa, $ad, $b0, $b3, $b6, $b9,
                              $bc, $be, $c1, $c4, $c6, $c9, $cb, $ce, $d0, $d3, $d5, $d7, $da, $dc, $de, $e0,

docs/source/libraries.rst

@@ -521,15 +521,18 @@ Available for the Cx16 target.
 Experimental routines that use the new Vera FX logic (hopefully coming in the Vera in new X16 boards,
 the emulators already support it).
 
+``available``
+    Returns true if Vera FX is available, false if not (that would be an older Vera chip)
+
 ``mult`` , ``muls``
-    For now, the hardware 16*16 multiplier is exposed via ``mult`` and ``muls`` routines (unsigned and signed respectively).
+    The hardware 16*16 multiplier is exposed via ``mult`` and ``muls`` routines (unsigned and signed respectively).
     They are about 4 to 5 times faster as the default 6502 cpu routine for word multiplication.
     But they depend on some Vera manipulation and 4 bytes in vram just below the PSG registers for storage.
     Note: there is a block level %option "verafxmuls" that automatically replaces all word multiplications in that block
     by calls to verafx.muls/mult, but be careful with it because it may interfere with other Vera operations or IRQs.
 
 ``clear``
-    There's also a ``clear`` routine here to very quickly clear a piece of vram to a given byte value (it writes 4 bytes at a time).
+    Very quickly clear a piece of vram to a given byte value (it writes 4 bytes at a time).
     The routine is around 3 times faster as a regular unrolled loop to clear vram.
 
 ``transparency``