diff --git a/examples/Makefile b/examples/Makefile
index ad80afd..5cd4e79 100644
--- a/examples/Makefile
+++ b/examples/Makefile
@@ -15,7 +15,7 @@ RK6502LIB=../src/librk65c02.a
 VASM=vasm6502_std
 VASMFLAGS=-Fbin -wdc02
 
-EXAMPLES=min3
+EXAMPLES=min3 mul_8bit_to_8bits
 EXAMPLES_ROMS:=$(addsuffix .rom,$(basename $(wildcard *.s)))
 
 all : $(EXAMPLES) $(EXAMPLES_ROMS)
@@ -23,6 +23,9 @@ all : $(EXAMPLES) $(EXAMPLES_ROMS)
 min3 : min3.o $(RK6502LIB)
 	$(CC) -o $@ $(LDFLAGS) $< $(RK6502LIB)
 
+mul_8bit_to_8bits : mul_8bit_to_8bits.o $(RK6502LIB)
+	$(CC) -o $@ $(LDFLAGS) $< $(RK6502LIB)
+
 %.rom : %.s
 	$(VASM) $(VASMFLAGS) -o $@ $<
 
diff --git a/examples/mul_8bit_to_8bits.c b/examples/mul_8bit_to_8bits.c
new file mode 100644
index 0000000..f75946c
--- /dev/null
+++ b/examples/mul_8bit_to_8bits.c
@@ -0,0 +1,32 @@
+#include <stdio.h>
+#include <stdint.h>
+
+#include "rk65c02.h"
+#include "bus.h"
+#include "log.h"
+#include "instruction.h"
+
+static const uint16_t load_addr = 0xC000;
+
+int main(void)
+{
+	uint8_t num1, num2;
+	uint8_t res;
+
+	rk65c02emu_t e;
+
+	e = rk65c02_load_rom("mul_8bit_to_8bits.rom", load_addr, NULL);
+
+	e.regs.SP = 0xFF;
+	e.regs.PC = load_addr;
+	num1 = 4; num2 = 8;
+
+	stack_push(&e, num1);
+	stack_push(&e, num2);
+
+	rk65c02_start(&e);
+
+	res = stack_pop(&e);
+	printf("Result of multiplication: %d\n", res);
+}
+
diff --git a/examples/mul_8bit_to_8bits.s b/examples/mul_8bit_to_8bits.s
new file mode 100644
index 0000000..a07a5da
--- /dev/null
+++ b/examples/mul_8bit_to_8bits.s
@@ -0,0 +1,50 @@
+.org 0xC000
+start:	jsr mul_8bit_to_8bits
+	stp
+
+; mul_8bit_to_8bits
+; Multiplies 2 numbers (passed on stack) and returns result on stack.
+
+; General 8bit * 8bit = 8bit multiply
+; by White Flame 20030207
+; adapted as rk65c02 example by rkujawa
+
+; Instead of using a bit counter, this routine early-exits when num2 reaches
+; zero, thus saving iterations.
+
+; .X and .Y are preserved
+; num1 and num2 get clobbered
+.set num1,0x10
+.set num2,0x11
+.set retl,0x12
+.set reth,0x13
+
+mul_8bit_to_8bits:
+	pla		; pull return address
+	sta retl
+	pla
+	sta reth
+	pla		; pull num1 from stack
+	sta num1
+	pla		; pull num2 from stack
+	sta num2
+
+	lda #0x00
+	beq enterl
+doAdd:	clc
+	adc num1
+loop:	asl num1
+; For an accumulating multiply (A = A + num1 * num2), 
+; set up num1 and num2, then enter here.
+enterl:	lsr num2
+	bcs doAdd
+	bne loop
+end:
+	pha		; save result to stack
+	lda reth	; restore return address
+	pha
+	lda retl
+	pha
+	rts		; return from function
+
+