add omult32 - 16x16 -> 16 (low bytes) unsigned multiply

go

@@ -149,3 +149,4 @@ test "smult12" 0xa00
 #test "omult29" 0x200
 #test "omult30" 0x200
 #test "omult31" 0xa00
+#test "omult32" 0x200

tests/omult32.a

@@ -0,0 +1,72 @@
+;-------------------------------------------------------------------------
+;   _mulint.s - routine for 16x16 -> 16 multiplication (low bytes only) 
+;
+;   Copyright (C) 2025, Gabriele Gorla
+;
+;   This library is free software; you can redistribute it and/or modify it
+;   under the terms of the GNU General Public License as published by the
+;   Free Software Foundation; either version 2, or (at your option) any
+;   later version.
+;
+;   This library is distributed in the hope that it will be useful,
+;   but WITHOUT ANY WARRANTY; without even the implied warranty of
+;   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+;   GNU General Public License for more details.
+;
+;   You should have received a copy of the GNU General Public License
+;   along with this library; see the file COPYING. If not, write to the
+;   Free Software Foundation, 51 Franklin Street, Fifth Floor, Boston,
+;   MA 02110-1301, USA.
+;
+;   As a special exception, if you link this library with other files,
+;   some of which are compiled with SDCC, to produce an executable,
+;   this library does not by itself cause the resulting executable to
+;   be covered by the GNU General Public License. This exception does
+;   not however invalidate any other reasons why the executable file
+;   might be covered by the GNU General Public License.
+;-------------------------------------------------------------------------
+
+* = $0200
+
+F1	= $02   ; 2 bytes
+F2	= $04   ; 2 bytes
+res	= $06   ; 2 bytes
+
+
+; On Entry:
+;   (F1, F1+1): multiplier 2 bytes
+;   (F2, F2+1): multiplicand 2 bytes
+; On Exit:
+;   (res, res+1): 16 bit product
+
+mult
+	lda #0
+	sta res+0
+	ldy #8
+loop1
+	lsr F2+0
+	bcc skip1
+	clc
+	tax
+	lda res+0
+	adc F1+0
+	sta res+0
+	txa
+	adc F1+1
+skip1
+	asl F1+0
+	rol F1+1
+	dey
+	bne loop1
+
+loop2
+	lsr F2+1
+	bcc skip2
+	clc
+	adc F1+1
+skip2
+	asl F1+1
+	bne loop2
+
+	sta res+1
+	rts

tests/omult32.c

@@ -0,0 +1,41 @@
+// omult32.c
+
+// specify range of input values
+static const uint64_t INPUT_START = 0UL;
+static const uint64_t INPUT_END   = 65536UL * 65536UL;
+
+// **************************************************************************************
+void test_pre(thread_context_t* threadContext, uint64_t input) {
+    zuint8* memory = threadContext->machine.context;
+
+    memory[2] = input & 255UL;
+    memory[3] = (input / 256UL) & 255UL;
+    memory[4] = (input/65536UL) & 255UL;
+    memory[5] = (input/65536UL) / 256UL;
+}
+
+// **************************************************************************************
+uint64_t test_post(thread_context_t* threadContext) {
+    zuint8* memory = threadContext->machine.context;
+
+    uint64_t a = memory[6];
+    uint64_t b = memory[7];
+
+    return a + 256UL*b;
+}
+
+// **************************************************************************************
+int is_correct(thread_context_t* threadContext, uint64_t input, uint64_t actual_result, uint64_t* expected) {
+    uint64_t x = input & 65535UL;
+    uint64_t y = input / 65536UL;
+    uint64_t e = x * y & 65535;
+    *expected = e;
+
+    return actual_result == e;
+}
+
+
+// **************************************************************************************
+void test_cleanup()
+{
+}