{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import numpy as np\n",
"import math\n",
"# source: http://www.qmtpro.com/~nes/misc/nestest.log"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"with open('6502_test_opcodes.txt') as f:\n",
" lines = f.readlines()"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"opcode_array = [\"00\" for _ in range(int(math.pow(2,16)))]\n"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'JMP'"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"lines[0][16:19]"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"instructions = [lines[x][16:19] for x in range(len(lines))]"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'JSR'"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"instructions[872]"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'CFDB A1 80 LDA ($80,X) @ 80 = 0200 = 5A A:5D X:00 Y:69 P:27 SP:FB PPU: 22,139 CYC:2547\\n'"
]
},
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"lines[1086]"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"address_w_opcodes = [lines[x][:16] for x in range(len(lines))]\n",
"addresses = [address_w_opcodes[x][:4] for x in range(len(address_w_opcodes)) ]\n",
"addresses = [int(address, 16) for address in addresses]"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [],
"source": [
"opcodes = [address_w_opcodes[x][4:] for x in range(len(address_w_opcodes))]\n",
"opcodes = [opcode_seq.lstrip().rstrip() for opcode_seq in opcodes]\n",
"opcodes = [opcode_seq.split() for opcode_seq in opcodes ]"
]
},
{
"cell_type": "code",
"execution_count": 28,
"metadata": {},
"outputs": [],
"source": [
"working_opcodes = opcodes[:1100]"
]
},
{
"cell_type": "code",
"execution_count": 29,
"metadata": {},
"outputs": [],
"source": [
"import itertools\n",
"flat_opcode_list = list(itertools.chain(*working_opcodes))"
]
},
{
"cell_type": "code",
"execution_count": 33,
"metadata": {},
"outputs": [],
"source": [
"total_opcode_list = list(itertools.chain(*opcodes))"
]
},
{
"cell_type": "code",
"execution_count": 39,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Total amount of opcodes(w/ addressing modes) = 254\n",
"Total amount of consecutive working opcodes(w/ addressing modes) = 171\n"
]
}
],
"source": [
"print(\"Total amount of opcodes(w/ addressing modes) = \", len(set(total_opcode_list)))\n",
"print(\"Total amount of consecutive working opcodes(w/ addressing modes) = \", len(set(set(flat_opcode_list))))"
]
},
{
"cell_type": "code",
"execution_count": 36,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0.6732283464566929"
]
},
"execution_count": 36,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"171/254"
]
},
{
"cell_type": "code",
"execution_count": 32,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'00',\n",
" '01',\n",
" '02',\n",
" '03',\n",
" '04',\n",
" '05',\n",
" '07',\n",
" '08',\n",
" '09',\n",
" '0A',\n",
" '0B',\n",
" '0D',\n",
" '0F',\n",
" '10',\n",
" '11',\n",
" '12',\n",
" '13',\n",
" '14',\n",
" '15',\n",
" '16',\n",
" '17',\n",
" '18',\n",
" '19',\n",
" '1A',\n",
" '1B',\n",
" '1C',\n",
" '1D',\n",
" '1E',\n",
" '1F',\n",
" '20',\n",
" '21',\n",
" '22',\n",
" '23',\n",
" '24',\n",
" '25',\n",
" '27',\n",
" '28',\n",
" '29',\n",
" '2A',\n",
" '2B',\n",
" '2C',\n",
" '2D',\n",
" '2E',\n",
" '2F',\n",
" '30',\n",
" '31',\n",
" '32',\n",
" '33',\n",
" '34',\n",
" '35',\n",
" '37',\n",
" '38',\n",
" '39',\n",
" '3B',\n",
" '3D',\n",
" '3F',\n",
" '40',\n",
" '41',\n",
" '44',\n",
" '47',\n",
" '48',\n",
" '49',\n",
" '4A',\n",
" '4B',\n",
" '4C',\n",
" '4D',\n",
" '4E',\n",
" '50',\n",
" '54',\n",
" '55',\n",
" '56',\n",
" '57',\n",
" '58',\n",
" '5A',\n",
" '5B',\n",
" '5C',\n",
" '5D',\n",
" '5E',\n",
" '5F',\n",
" '60',\n",
" '62',\n",
" '63',\n",
" '64',\n",
" '65',\n",
" '66',\n",
" '67',\n",
" '68',\n",
" '69',\n",
" '6A',\n",
" '6B',\n",
" '6D',\n",
" '6E',\n",
" '6F',\n",
" '70',\n",
" '71',\n",
" '72',\n",
" '76',\n",
" '77',\n",
" '78',\n",
" '7B',\n",
" '7D',\n",
" '7E',\n",
" '7F',\n",
" '80',\n",
" '81',\n",
" '82',\n",
" '83',\n",
" '84',\n",
" '85',\n",
" '86',\n",
" '87',\n",
" '88',\n",
" '8A',\n",
" '8D',\n",
" '8E',\n",
" '90',\n",
" '91',\n",
" '96',\n",
" '98',\n",
" '99',\n",
" '9A',\n",
" '9D',\n",
" '9F',\n",
" 'A0',\n",
" 'A1',\n",
" 'A2',\n",
" 'A5',\n",
" 'A8',\n",
" 'A9',\n",
" 'AA',\n",
" 'AB',\n",
" 'AC',\n",
" 'AD',\n",
" 'AE',\n",
" 'AF',\n",
" 'B0',\n",
" 'B8',\n",
" 'BA',\n",
" 'C0',\n",
" 'C5',\n",
" 'C6',\n",
" 'C7',\n",
" 'C8',\n",
" 'C9',\n",
" 'CA',\n",
" 'CB',\n",
" 'CC',\n",
" 'CD',\n",
" 'CE',\n",
" 'CF',\n",
" 'D0',\n",
" 'D8',\n",
" 'D9',\n",
" 'DB',\n",
" 'DE',\n",
" 'E0',\n",
" 'E3',\n",
" 'E7',\n",
" 'E8',\n",
" 'E9',\n",
" 'EA',\n",
" 'EE',\n",
" 'EF',\n",
" 'F0',\n",
" 'F3',\n",
" 'F5',\n",
" 'F8',\n",
" 'F9',\n",
" 'FB',\n",
" 'FE',\n",
" 'FF'}"
]
},
"execution_count": 32,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"set(flat_opcode_list)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [],
"source": [
"for step, index in enumerate(addresses): \n",
" for i in range(len(opcodes[step])):\n",
" opcode_array[index + i] = opcodes[step][i]"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [],
"source": [
"hexdump = [opcode_array[x:x+16] for x in range(0, len(opcode_array), 16)]"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [],
"source": [
"with open('../test_opcodes.txt', 'w') as f:\n",
" for line in hexdump:\n",
" f.write(''.join(line))\n",
" f.write('\\n')"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [],
"source": [
"register_vals = [lines[x][48:73] for x in range(len(lines))]\n",
"register_vals = [sample_reg_val.split() for sample_reg_val in register_vals]\n",
"register_vals = np.array(register_vals, dtype = 'object')\n",
"A, X, Y, P, SP = np.split(register_vals, 5, axis = 1)\n",
"A, X, Y, P, SP = A.flatten().tolist(), X.flatten().tolist(), Y.flatten().tolist(), P.flatten().tolist(), SP.flatten().tolist()\n",
"A = [A[step][2:] for step in range(len(A))]\n",
"X = [X[step][2:] for step in range(len(X))]\n",
"Y = [Y[step][2:] for step in range(len(Y))]\n",
"P = [P[step][2:] for step in range(len(P))]\n",
"SP = [SP[step][3:] for step in range(len(SP))]\n",
"\n",
"A = [int(a, 16) for a in A]\n",
"X = [int(x, 16) for x in X]\n",
"Y = [int(y, 16) for y in Y]\n",
"P = [int(p, 16) for p in P]\n",
"SP = [int(sp, 16) for sp in SP]"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"8991"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"len(A)"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"116"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"int(\"74\", 16)"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"CDFA 85 01 STA $01 = FF A:FF X:FB Y:01 P:A5 SP:FB PPU: 17, 20 CYC:1939\n",
"\n",
"CDFC BA TSX A:FF X:FB Y:01 P:A5 SP:FB PPU: 17, 29 CYC:1942\n",
"\n",
"CDFD 8E FF 07 STX $07FF = FB A:FF X:FB Y:01 P:A5 SP:FB PPU: 17, 35 CYC:1944\n",
"\n",
"CE00 EA NOP A:FF X:FB Y:01 P:A5 SP:FB PPU: 17, 47 CYC:1948\n",
"\n",
"CE01 A2 80 LDX #$80 A:FF X:FB Y:01 P:A5 SP:FB PPU: 17, 53 CYC:1950\n",
"\n",
"CE03 9A TXS A:FF X:80 Y:01 P:A5 SP:FB PPU: 17, 59 CYC:1952\n",
"\n",
"CE04 A9 33 LDA #$33 A:FF X:80 Y:01 P:A5 SP:80 PPU: 17, 65 CYC:1954\n",
"\n",
"CE06 48 PHA A:33 X:80 Y:01 P:25 SP:80 PPU: 17, 71 CYC:1956\n",
"\n",
"CE07 A9 69 LDA #$69 A:33 X:80 Y:01 P:25 SP:7F PPU: 17, 80 CYC:1959\n",
"\n",
"CE09 48 PHA A:69 X:80 Y:01 P:25 SP:7F PPU: 17, 86 CYC:1961\n",
"\n",
"CE0A BA TSX A:69 X:80 Y:01 P:25 SP:7E PPU: 17, 95 CYC:1964\n",
"\n",
"CE0B E0 7E CPX #$7E A:69 X:7E Y:01 P:25 SP:7E PPU: 17,101 CYC:1966\n",
"\n",
"CE0D D0 20 BNE $CE2F A:69 X:7E Y:01 P:27 SP:7E PPU: 17,107 CYC:1968\n",
"\n",
"CE0F 68 PLA A:69 X:7E Y:01 P:27 SP:7E PPU: 17,113 CYC:1970\n",
"\n",
"CE10 C9 69 CMP #$69 A:69 X:7E Y:01 P:25 SP:7F PPU: 17,125 CYC:1974\n",
"\n",
"CE12 D0 1B BNE $CE2F A:69 X:7E Y:01 P:27 SP:7F PPU: 17,131 CYC:1976\n",
"\n",
"CE14 68 PLA A:69 X:7E Y:01 P:27 SP:7F PPU: 17,137 CYC:1978\n",
"\n",
"CE15 C9 33 CMP #$33 A:33 X:7E Y:01 P:25 SP:80 PPU: 17,149 CYC:1982\n",
"\n",
"CE17 D0 16 BNE $CE2F A:33 X:7E Y:01 P:27 SP:80 PPU: 17,155 CYC:1984\n",
"\n",
"CE19 BA TSX A:33 X:7E Y:01 P:27 SP:80 PPU: 17,161 CYC:1986\n",
"\n",
"CE1A E0 80 CPX #$80 A:33 X:80 Y:01 P:A5 SP:80 PPU: 17,167 CYC:1988\n",
"\n",
"CE1C D0 11 BNE $CE2F A:33 X:80 Y:01 P:27 SP:80 PPU: 17,173 CYC:1990\n",
"\n",
"CE1E AD 80 01 LDA $0180 = 33 A:33 X:80 Y:01 P:27 SP:80 PPU: 17,179 CYC:1992\n",
"\n",
"CE21 C9 33 CMP #$33 A:33 X:80 Y:01 P:25 SP:80 PPU: 17,191 CYC:1996\n",
"\n",
"CE23 D0 0A BNE $CE2F A:33 X:80 Y:01 P:27 SP:80 PPU: 17,197 CYC:1998\n",
"\n",
"CE25 AD 7F 01 LDA $017F = 69 A:33 X:80 Y:01 P:27 SP:80 PPU: 17,203 CYC:2000\n",
"\n",
"CE28 C9 69 CMP #$69 A:69 X:80 Y:01 P:25 SP:80 PPU: 17,215 CYC:2004\n",
"\n",
"CE2A D0 03 BNE $CE2F A:69 X:80 Y:01 P:27 SP:80 PPU: 17,221 CYC:2006\n",
"\n",
"CE2C 4C 33 CE JMP $CE33 A:69 X:80 Y:01 P:27 SP:80 PPU: 17,227 CYC:2008\n",
"\n",
"CE33 EA NOP A:69 X:80 Y:01 P:27 SP:80 PPU: 17,236 CYC:2011\n",
"\n",
"CE34 A2 80 LDX #$80 A:69 X:80 Y:01 P:27 SP:80 PPU: 17,242 CYC:2013\n",
"\n",
"CE36 9A TXS A:69 X:80 Y:01 P:A5 SP:80 PPU: 17,248 CYC:2015\n",
"\n",
"CE37 20 3D CE JSR $CE3D A:69 X:80 Y:01 P:A5 SP:80 PPU: 17,254 CYC:2017\n",
"\n",
"CE3D BA TSX A:69 X:80 Y:01 P:A5 SP:7E PPU: 17,272 CYC:2023\n",
"\n",
"CE3E E0 7E CPX #$7E A:69 X:7E Y:01 P:25 SP:7E PPU: 17,278 CYC:2025\n",
"\n",
"CE40 D0 19 BNE $CE5B A:69 X:7E Y:01 P:27 SP:7E PPU: 17,284 CYC:2027\n",
"\n",
"CE42 68 PLA A:69 X:7E Y:01 P:27 SP:7E PPU: 17,290 CYC:2029\n",
"\n"
]
}
],
"source": [
"for x in range(840, 877):\n",
" print(lines[x])\n"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [],
"source": [
"with open('../test_vals.h', 'w') as f:\n",
"\n",
" f.write(\" #ifndef TEST_VALS_H \\n #define TEST_VALS_H \\n #include \\\"6502.h\\\" \\n \")\n",
"\n",
" f.write(\"byte A[] = { \")\n",
" for a in A[:-1]:\n",
" f.write(\"%s ,\" % a)\n",
"\n",
" f.write(\"%s }; \\n\" % A[-1])\n",
"\n",
" f.write(\"byte X[] = { \")\n",
" for x in X[:-1]:\n",
" f.write(\"%s ,\" % x)\n",
"\n",
" f.write(\"%s }; \\n\" % X[-1])\n",
"\n",
" f.write(\"byte Y[] = { \")\n",
" for y in Y[:-1]:\n",
" f.write(\"%s ,\" % y)\n",
"\n",
" f.write(\"%s }; \\n\" % Y[-1])\n",
"\n",
" \"\"\"\n",
" f.write(\"byte P[] = { \")\n",
" for p in P[:-1]:\n",
" f.write(\"%s ,\" % p)\n",
"\n",
" f.write(\"%s }; \\n\" % P[-1]) \"\"\"\n",
"\n",
" f.write(\"byte SP[] = { \")\n",
" for sp in SP[:-1]:\n",
" f.write(\"%s ,\" % sp)\n",
"\n",
" f.write(\"%s }; \\n\" % SP[-1])\n",
"\n",
" f.write(\"address PCs[] = { \")\n",
" for address in addresses[:-1]:\n",
" f.write(\"%s ,\" % address)\n",
"\n",
" f.write(\"%s }; \\n\" % addresses[-1])\n",
"\n",
" f.write(\"#endif // TEST_VALS_H \")\n"
]
}
],
"metadata": {
"interpreter": {
"hash": "949777d72b0d2535278d3dc13498b2535136f6dfe0678499012e853ee9abcab1"
},
"kernelspec": {
"display_name": "Python 3.9.9 64-bit",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.9"
},
"orig_nbformat": 4
},
"nbformat": 4,
"nbformat_minor": 2
}