diff --git a/contrib/toacme/docs/README b/contrib/toacme/docs/README
index 1d9dca3..83aabb4 100644
--- a/contrib/toacme/docs/README
+++ b/contrib/toacme/docs/README
@@ -9,7 +9,7 @@ Copyright
 ---------
 
 ToACME - a source code converter for the ACME crossassembler
-Copyright (C) 1998-2015 Marco Baye
+Copyright (C) 1998-2016 Marco Baye
 
 This program is free software; you can redistribute it and/or modify
 it under the terms of the GNU General Public License as published by
@@ -71,7 +71,7 @@ giga        C64: Giga-Assembler                 ok
 vis         C64: VisAss                   untested
 ab3         C64: AssBlaster 3.0 to 3.2        good
 f8ab        C64: Flash8-AssBlaster              ok
-
+prof        C64: Professional Assembler       poor (work in progress)
 
 
 Contacting the author
@@ -90,3 +90,4 @@ Credits
 Thanks to Stefan Hübner for fixing the AssBlaster macro conversion code.
 Thanks to Andreas Paul for helping with the Giga-Assembler mode.
 Thanks to Arndt Dettke for helping with the Hypra-Assembler mode.
+Thanks to Hoogo for helping with the Professional Assembler mode.
diff --git a/contrib/toacme/src/Makefile b/contrib/toacme/src/Makefile
index ec773a3..254dde8 100644
--- a/contrib/toacme/src/Makefile
+++ b/contrib/toacme/src/Makefile
@@ -37,12 +37,14 @@ pet2iso.o: config.h pet2iso.h pet2iso.c
 
 platform.o: config.h platform.h platform.c
 
+prof.o: config.h prof.c
+
 scr2iso.o: config.h scr2iso.h scr2iso.c
 
 version.o: config.h version.c
 
-toacme: vis.o ab.o ab3.o acme.o f8ab.o giga.o gighyp.o hypra.o io.o main.o mnemo.o obj.o pet2iso.o platform.o scr2iso.o version.o
-	$(CC) $(LIBS) $(CFLAGS) -o toacme vis.o ab.o ab3.o acme.o f8ab.o giga.o gighyp.o hypra.o io.o main.o mnemo.o obj.o pet2iso.o platform.o scr2iso.o version.o
+toacme: vis.o ab.o ab3.o acme.o f8ab.o giga.o gighyp.o hypra.o io.o main.o mnemo.o obj.o pet2iso.o platform.o prof.o scr2iso.o version.o
+	$(CC) $(LIBS) $(CFLAGS) -o toacme vis.o ab.o ab3.o acme.o f8ab.o giga.o gighyp.o hypra.o io.o main.o mnemo.o obj.o pet2iso.o platform.o prof.o scr2iso.o version.o
 	strip toacme
 
 clean:
diff --git a/contrib/toacme/src/prof.c b/contrib/toacme/src/prof.c
new file mode 100644
index 0000000..258ebc5
--- /dev/null
+++ b/contrib/toacme/src/prof.c
@@ -0,0 +1,91 @@
+// ToACME - converts other source codes to ACME format.
+// Copyright (C) 1999-2016 Marco Baye
+// Have a look at "main.c" for further info
+//
+// "Professional Ass by Oliver Stiller" stuff (NOT "Profi-Ass" by Data Becker!)
+// Kickoff:
+// http://www.forum64.de/wbb4/index.php?thread/60047-toacme-demn%C3%A4chst-als-win32-release/
+
+#include <stdio.h>
+//#include "config.h"
+//#include "acme.h"
+//#include "mnemo.h"
+#include "io.h"
+#include "scr2iso.h"
+
+// format of input files:
+// load address, lo
+// load address, hi
+// for each line:
+//	total line length, including this byte
+//	amount of indentation
+//	actual line as screen code (this part might be missing in case of empty line)
+//	total line length, including this byte (yes, the same value again, for upscrolling)
+// that's it!
+
+// special directives:
+// '.' is for pseudo opcodes?
+//	.setpc is *=
+//	.fill (length, data)	?
+//	.b is !by, .w is !wo, .macro reads a macro argument?
+//	.goto is used to skip macro definitions?!
+//	what do .begin and .end do? local label scope?
+//	.print str$(*-$1060)	wow... O_o
+// '-' prefix means local label definition?
+// '+' prefix means global label definition?
+// '_' starts a macro definition? ".endmacro" ends definition?
+// '*' prefix is a macro call?
+
+#define TABSIZE		8	// anything else is heresy
+#define REV_START	";-=#"
+#define REV_END		"#=-"
+
+// main
+void prof_main(void)
+{
+	int	length1,
+		indent,
+		ii,
+		byte,
+		hibit,
+		length2;
+
+	IO_set_input_padding(0);
+	IO_process_load_address();
+	for (;;) {
+		length1 = IO_get_byte();
+		if (length1 == EOF)
+			break;
+		if (length1 < 3) {
+			fprintf(stderr, "Error: Short line (%d bytes)\n", length1);
+		}
+		// read amount of indentation and output tabs/spaces
+		indent = IO_get_byte();
+		if (indent < 0) {
+			fprintf(stderr, "Error: Negative indentation (%d)\n", indent);
+		} else {
+			for (ii = 0; ii + TABSIZE <= indent; ii += TABSIZE)
+				IO_put_byte('\t');
+			for (; ii < indent; ii++)
+				IO_put_byte(' ');
+		}
+		// now convert line
+		hibit = 0;
+		for (ii = 0; ii < length1 - 3; ii++) {
+			byte = IO_get_byte();
+			if ((byte & 128) != hibit) {
+				hibit = byte & 128;
+				IO_put_string(hibit ? REV_START : REV_END);
+			}
+			IO_put_byte(SCR2ISO(byte & 127));
+		}
+		if (hibit)
+			IO_put_string(REV_END);
+		// and add newline
+		IO_put_byte('\n');
+		// now check second length byte
+		length2 = IO_get_byte();
+		if (length1 != length2)
+			fprintf(stderr, "Error: Length bytes differ (%d != %d)\n", length1, length2);
+	}
+}
diff --git a/contrib/toacme/src/version.c b/contrib/toacme/src/version.c
index 48ee5bb..99c38f0 100644
--- a/contrib/toacme/src/version.c
+++ b/contrib/toacme/src/version.c
@@ -4,12 +4,12 @@
 //
 // Version
 
-#define RELEASE_NUMBER	"0.12"		// change before release (FIXME)
-#define CHANGE_DATE	"4 Feb"		// change before release
-#define CHANGE_YEAR	"2015"		// change before release
+#define RELEASE_NUMBER	"0.13"		// change before release (FIXME)
+#define CHANGE_DATE	"16 Feb"		// change before release
+#define CHANGE_YEAR	"2016"		// change before release
 #define HOME_PAGE	"http://sourceforge.net/projects/acme-crossass/"
 //			"http://home.pages.de/~mac_bacon/smorbrod/acme/"
-#define FILE_TAG	";ACME 0.95.4"	// check before release
+#define FILE_TAG	";ACME 0.95.6"	// check before release
 
 #include <stdio.h>
 #include <string.h>
@@ -33,6 +33,7 @@ PLATFORM_VERSION "\n"
 "Thanks to Stefan Hübner for fixing the AssBlaster macro conversion code.\n"
 "Thanks to Andreas Paul for helping with the Giga-Assembler mode.\n"
 "Thanks to Arndt Dettke for helping with the Hypra-Assembler mode.\n"
+"Thanks to Hoogo for helping with the Professional Assembler mode.\n"
 "\n"
 "The newest version can be found at the ACME homepage:\n"
 HOME_PAGE "\n"
@@ -51,6 +52,7 @@ HOME_PAGE "\n"
 "vis         C64: VisAss                   untested\n"
 "ab3         C64: AssBlaster 3.0 to 3.2        good\n"
 "f8ab        C64: Flash8-AssBlaster              ok\n"
+"prof        C64: Professional Assembler       poor (work in progress)\n"
 "\n"
 	, program_name);
 }
@@ -62,6 +64,7 @@ extern void f8ab_main(void);
 extern void giga_main(void);
 extern void hypra_main(void);
 extern void obj_main(void);
+extern void prof_main(void);
 
 
 // check id string. returns whether illegal.
@@ -79,6 +82,8 @@ int version_parse_id(const char id[])
 		client_main = hypra_main;
 	else if (strcmp(id, "object") == 0)
 		client_main = obj_main;
+	else if (strcmp(id, "prof") == 0)
+		client_main = prof_main;
 	return client_main ? 0 : 1;
 }
 
diff --git a/docs/AllPOs.txt b/docs/AllPOs.txt
index 4d53310..de4c33c 100644
--- a/docs/AllPOs.txt
+++ b/docs/AllPOs.txt
@@ -27,29 +27,85 @@ Examples:	!08 127, symbol, -128	; output some values
 
 
 Call:		!16 EXPRESSION [, EXPRESSION]*
-Purpose:	Insert 16-bit values.
+Purpose:	Insert 16-bit values in chosen CPU's byte order.
 Parameters:	EXPRESSION: Any formula the value parser accepts.
-Aliases:	"!wo", "!word"
+Aliases:	"!wo", "!word" (and because all currently supported CPUs are
+		little-endian, "!le16" is in fact another alias)
 Examples:	!16 65535, symbol, -32768	; output some values
 		!wo 14, $4f35, %100101010010110, &36304, *, "c"
 		!word 3000 - 4, a1 AND a2, 2 ^ tz, (3+4)*70, l1 & .j2
 
+Call:		!le16 EXPRESSION [, EXPRESSION]*
+Purpose:	Insert 16-bit values in little-endian byte order.
+Parameters:	EXPRESSION: Any formula the value parser accepts.
+Aliases:	None (but because all currently supported CPUs are
+		little-endian, "!16/!wo/!word" are in fact aliases)
+Examples:	!le16 65535, symbol, -32768	; output some values
+		!le16 14, $4f35, %100101010010110, &36304, *, "c"
+		!le16 3000 - 4, a1 AND a2, 2 ^ tz, (3+4)*70, l1 & .j2
+
+Call:		!be16 EXPRESSION [, EXPRESSION]*
+Purpose:	Insert 16-bit values in big-endian byte order.
+Parameters:	EXPRESSION: Any formula the value parser accepts.
+Aliases:	None
+Examples:	!be16 65535, symbol, -32768	; output some values
+		!be16 14, $4f35, %100101010010110, &36304, *, "c"
+		!be16 3000 - 4, a1 AND a2, 2 ^ tz, (3+4)*70, l1 & .j2
+
 
 Call:		!24 EXPRESSION [, EXPRESSION]*
-Purpose:	Insert 24-bit values.
+Purpose:	Insert 24-bit values in chosen CPU's byte order.
 Parameters:	EXPRESSION: Any formula the value parser accepts.
+Aliases:	None (but because all currently supported CPUs are
+		little-endian, "!le24" is in fact an alias)
 Examples:	!24 16777215, symbol, -8388608, 14, $6a4f35
 		!24 %10010110100101010010110, &47336304, *, "c"
 		!24 300000 - 4, a1 AND a2, 2 ^ tz, (3+4)*70, l1 & .j2
 
+Call:		!le24 EXPRESSION [, EXPRESSION]*
+Purpose:	Insert 24-bit values in little-endian byte order.
+Parameters:	EXPRESSION: Any formula the value parser accepts.
+Aliases:	None (but because all currently supported CPUs are
+		little-endian, "!24" is in fact an alias)
+Examples:	!le24 16777215, symbol, -8388608, 14, $6a4f35
+		!le24 %10010110100101010010110, &47336304, *, "c"
+		!le24 300000 - 4, a1 AND a2, 2 ^ tz, (3+4)*70, l1 & .j2
+
+Call:		!be24 EXPRESSION [, EXPRESSION]*
+Purpose:	Insert 24-bit values in big-endian byte order.
+Parameters:	EXPRESSION: Any formula the value parser accepts.
+Aliases:	None
+Examples:	!be24 16777215, symbol, -8388608, 14, $6a4f35
+		!be24 %10010110100101010010110, &47336304, *, "c"
+		!be24 300000 - 4, a1 AND a2, 2 ^ tz, (3+4)*70, l1 & .j2
+
 
 Call:		!32 EXPRESSION [, EXPRESSION]*
-Purpose:	Insert 32-bit values.
+Purpose:	Insert 32-bit values in chosen CPU's byte order.
 Parameters:	EXPRESSION: Any formula the value parser accepts.
+Aliases:	None (but because all currently supported CPUs are
+		little-endian, "!le32" is in fact an alias)
 Examples:	!32 $7fffffff, symbol, -$80000000, 14, $46a4f35
 		!32 %1001011010010101001011010010, &4733630435, *, "c"
 		!32 300000 - 4, a AND a2, 2 ^ tz, (3+4)*70, l1 & .j2
 
+Call:		!le32 EXPRESSION [, EXPRESSION]*
+Purpose:	Insert 32-bit values in little-endian byte order.
+Parameters:	EXPRESSION: Any formula the value parser accepts.
+Aliases:	None (but because all currently supported CPUs are
+		little-endian, "!32" is in fact an alias)
+Examples:	!le32 $7fffffff, symbol, -$80000000, 14, $46a4f35
+		!le32 %1001011010010101001011010010, &4733630435, *, "c"
+		!le32 300000 - 4, a AND a2, 2 ^ tz, (3+4)*70, l1 & .j2
+
+Call:		!be32 EXPRESSION [, EXPRESSION]*
+Purpose:	Insert 32-bit values in big-endian byte order.
+Parameters:	EXPRESSION: Any formula the value parser accepts.
+Aliases:	None
+Examples:	!be32 $7fffffff, symbol, -$80000000, 14, $46a4f35
+		!be32 %1001011010010101001011010010, &4733630435, *, "c"
+		!be32 300000 - 4, a AND a2, 2 ^ tz, (3+4)*70, l1 & .j2
+
 
 Call:		!fill AMOUNT [, VALUE]
 Purpose:	Fill amount of memory with value.
diff --git a/docs/Changes.txt b/docs/Changes.txt
index 826cabf..5bb22e2 100644
--- a/docs/Changes.txt
+++ b/docs/Changes.txt
@@ -12,6 +12,18 @@ platform used. There should be another help file in this archive
 outlining the platform specific changes.
 
 
+----------------------------------------------------------------------
+Section:   New in release 0.95.7
+----------------------------------------------------------------------
+
+New pseudo opcodes:
+    "!be16", "!be24" and "!be32" for big-endian byte order output.
+    "!le16", "!le24" and "!le32" for little-endian byte order output.
+    The old pseudo opcodes ("!16", "!24", "!32") will now use the correct
+    byte order for the chosen CPU (which is always little-endian, because
+    there is no support for any big-endian CPU yet. ;))
+
+
 ----------------------------------------------------------------------
 Section:   New in release 0.95.6
 ----------------------------------------------------------------------
diff --git a/src/acme.c b/src/acme.c
index 4238d3d..f6fa04d 100644
--- a/src/acme.c
+++ b/src/acme.c
@@ -1,5 +1,5 @@
 // ACME - a crossassembler for producing 6502/65c02/65816 code.
-// Copyright (C) 1998-2015 Marco Baye
+// Copyright (C) 1998-2016 Marco Baye
 //
 // This program is free software; you can redistribute it and/or modify
 // it under the terms of the GNU General Public License as published by
@@ -15,10 +15,10 @@
 // along with this program; if not, write to the Free Software
 // Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 
-#define RELEASE		"0.95.6"	// update before release (FIXME)
+#define RELEASE		"0.95.7"	// update before release (FIXME)
 #define CODENAME	"Fenchurch"	// update before release
-#define CHANGE_DATE	"16 Aug"	// update before release
-#define CHANGE_YEAR	"2015"		// update before release
+#define CHANGE_DATE	"16 Feb"	// update before release
+#define CHANGE_YEAR	"2016"		// update before release
 //#define HOME_PAGE	"http://home.pages.de/~mac_bacon/smorbrod/acme/"	// FIXME
 #define HOME_PAGE	"http://sourceforge.net/p/acme-crossass/"	// FIXME
 
diff --git a/src/cpu.h b/src/cpu.h
index f5595c0..e91035e 100644
--- a/src/cpu.h
+++ b/src/cpu.h
@@ -21,6 +21,7 @@ struct cpu_type {
 #define	CPUFLAG_INDIRECTJMPBUGGY	(1u << 0)	// warn if "jmp ($xxff)" is assembled
 #define CPUFLAG_SUPPORTSLONGREGS	(1u << 1)	// allow "!al" and "!rl" pseudo opcodes
 #define CPUFLAG_8B_AND_AB_NEED_0_ARG	(1u << 2)	// warn if "ane/lxa #$xx" uses non-zero arg
+#define CPUFLAG_ISBIGENDIAN		(1u << 3)	// for 16/24/32-bit values, output msb first
 
 
 // if cpu type and value match, set register length variable to value.
diff --git a/src/output.c b/src/output.c
index cf78b7d..a445469 100644
--- a/src/output.c
+++ b/src/output.c
@@ -7,6 +7,7 @@
 // 25 Sep 2011	Fixed bug in !to (colons in filename could be interpreted as EOS)
 //  5 Mar 2014	Fixed bug where setting *>0xffff resulted in hangups.
 // 19 Nov 2014	Merged Johann Klasek's report listing generator patch
+// 22 Sep 2015	Added big-endian output functions
 #include "output.h"
 #include <stdlib.h>
 #include <string.h>	// for memset()
@@ -192,7 +193,19 @@ void output_8(intval_t value)
 }
 
 
-// output 16-bit value with range check
+// output 16-bit value with range check big-endian
+void output_be16(intval_t value)
+{
+	if ((value <= 0xffff) && (value >= -0x8000)) {
+		Output_byte(value >> 8);
+		Output_byte(value);
+	} else {
+		Throw_error(exception_number_out_of_range);
+	}
+}
+
+
+// output 16-bit value with range check little-endian
 void output_le16(intval_t value)
 {
 	if ((value <= 0xffff) && (value >= -0x8000)) {
@@ -204,7 +217,20 @@ void output_le16(intval_t value)
 }
 
 
-// output 24-bit value with range check
+// output 24-bit value with range check big-endian
+void output_be24(intval_t value)
+{
+	if ((value <= 0xffffff) && (value >= -0x800000)) {
+		Output_byte(value >> 16);
+		Output_byte(value >> 8);
+		Output_byte(value);
+	} else {
+		Throw_error(exception_number_out_of_range);
+	}
+}
+
+
+// output 24-bit value with range check little-endian
 void output_le24(intval_t value)
 {
 	if ((value <= 0xffffff) && (value >= -0x800000)) {
@@ -217,7 +243,21 @@ void output_le24(intval_t value)
 }
 
 
-// output 32-bit value (without range check)
+// output 32-bit value (without range check) big-endian
+void output_be32(intval_t value)
+{
+//  if ((Value <= 0x7fffffff) && (Value >= -0x80000000)) {
+	Output_byte(value >> 24);
+	Output_byte(value >> 16);
+	Output_byte(value >> 8);
+	Output_byte(value);
+//  } else {
+//	Throw_error(exception_number_out_of_range);
+//  }
+}
+
+
+// output 32-bit value (without range check) little-endian
 void output_le32(intval_t value)
 {
 //  if ((Value <= 0x7fffffff) && (Value >= -0x80000000)) {
diff --git a/src/output.h b/src/output.h
index 0607190..cf1fd41 100644
--- a/src/output.h
+++ b/src/output.h
@@ -46,11 +46,17 @@ extern void Output_fake(int size);
 extern void (*Output_byte)(intval_t);
 // Output 8-bit value with range check
 extern void output_8(intval_t);
-// Output 16-bit value with range check
+// Output 16-bit value with range check big-endian
+extern void output_be16(intval_t);
+// Output 16-bit value with range check little-endian
 extern void output_le16(intval_t);
-// Output 24-bit value with range check
+// Output 24-bit value with range check big-endian
+extern void output_be24(intval_t);
+// Output 24-bit value with range check little-endian
 extern void output_le24(intval_t);
-// Output 32-bit value (without range check)
+// Output 32-bit value (without range check) big-endian
+extern void output_be32(intval_t);
+// Output 32-bit value (without range check) little-endian
 extern void output_le32(intval_t);
 // define default value for empty memory ("!initmem" pseudo opcode)
 // returns zero if ok, nonzero if already set
diff --git a/src/pseudoopcodes.c b/src/pseudoopcodes.c
index 9e64a46..0f940dc 100644
--- a/src/pseudoopcodes.c
+++ b/src/pseudoopcodes.c
@@ -152,7 +152,17 @@ static enum eos po_byte(void)
 
 
 // Insert 16-bit values ("!16" / "!wo" / "!word" pseudo opcode)
-static enum eos po_word(void)
+static enum eos po_16(void)
+{
+	return iterate((CPU_state.type->flags & CPUFLAG_ISBIGENDIAN) ? output_be16 : output_le16);
+}
+// Insert 16-bit values big-endian ("!be16" pseudo opcode)
+static enum eos po_be16(void)
+{
+	return iterate(output_be16);
+}
+// Insert 16-bit values little-endian ("!le16" pseudo opcode)
+static enum eos po_le16(void)
 {
 	return iterate(output_le16);
 }
@@ -160,6 +170,16 @@ static enum eos po_word(void)
 
 // Insert 24-bit values ("!24" pseudo opcode)
 static enum eos po_24(void)
+{
+	return iterate((CPU_state.type->flags & CPUFLAG_ISBIGENDIAN) ? output_be24 : output_le24);
+}
+// Insert 24-bit values big-endian ("!be24" pseudo opcode)
+static enum eos po_be24(void)
+{
+	return iterate(output_be24);
+}
+// Insert 24-bit values little-endian ("!le24" pseudo opcode)
+static enum eos po_le24(void)
 {
 	return iterate(output_le24);
 }
@@ -167,6 +187,16 @@ static enum eos po_24(void)
 
 // Insert 32-bit values ("!32" pseudo opcode)
 static enum eos po_32(void)
+{
+	return iterate((CPU_state.type->flags & CPUFLAG_ISBIGENDIAN) ? output_be32 : output_le32);
+}
+// Insert 32-bit values big-endian ("!be32" pseudo opcode)
+static enum eos po_be32(void)
+{
+	return iterate(output_be32);
+}
+// Insert 32-bit values little-endian ("!le32" pseudo opcode)
+static enum eos po_le32(void)
 {
 	return iterate(output_le32);
 }
@@ -948,11 +978,17 @@ static struct ronode	pseudo_opcode_list[]	= {
 	PREDEFNODE(s_08,		po_byte),
 	PREDEFNODE("by",		po_byte),
 	PREDEFNODE("byte",		po_byte),
-	PREDEFNODE(s_16,		po_word),
-	PREDEFNODE("wo",		po_word),
-	PREDEFNODE("word",		po_word),
+	PREDEFNODE("wo",		po_16),
+	PREDEFNODE("word",		po_16),
+	PREDEFNODE(s_16,		po_16),
+	PREDEFNODE("be16",		po_be16),
+	PREDEFNODE("le16",		po_le16),
 	PREDEFNODE("24",		po_24),
+	PREDEFNODE("be24",		po_be24),
+	PREDEFNODE("le24",		po_le24),
 	PREDEFNODE("32",		po_32),
+	PREDEFNODE("be32",		po_be32),
+	PREDEFNODE("le32",		po_le32),
 	PREDEFNODE(s_cbm,		obsolete_po_cbm),
 	PREDEFNODE("ct",		po_convtab),
 	PREDEFNODE("convtab",		po_convtab),