doom_py/src/vizdoom/game-music-emu/gme/Ay_Cpu.cpp [366:808]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
	CASE7( C7, CF, D7, DF, E7, EF, F7 ):
		data = pc;
		pc = opcode & 0x38;
		goto push_data;

// PUSH/POP
	case 0xF5: // PUSH AF
		data = rg.a * 0x100u + flags;
		goto push_data;
	
	case 0xC5: // PUSH BC
	case 0xD5: // PUSH DE
	case 0xE5: // PUSH HL
		data = R16( opcode, 4, 0xC5 );
	push_data:
		sp = uint16_t (sp - 2);
		WRITE_WORD( sp, data );
		goto loop;
	
	case 0xF1: // POP AF
		flags = READ( sp );
		rg.a = READ( sp + 1 );
		sp = uint16_t (sp + 2);
		goto loop;
	
	case 0xC1: // POP BC
	case 0xD1: // POP DE
	case 0xE1: // POP HL
		R16( opcode, 4, 0xC1 ) = READ_WORD( sp );
		sp = uint16_t (sp + 2);
		goto loop;
	
// ADC/ADD/SBC/SUB
	case 0x96: // SUB (HL)
	case 0x86: // ADD (HL)
		flags &= ~C01;
	case 0x9E: // SBC (HL)
	case 0x8E: // ADC (HL)
		data = READ( rp.hl );
		goto adc_data;
	
	case 0xD6: // SUB A,imm
	case 0xC6: // ADD imm
		flags &= ~C01;
	case 0xDE: // SBC A,imm
	case 0xCE: // ADC imm
		pc++;
		goto adc_data;
	
	CASE7( 90, 91, 92, 93, 94, 95, 97 ): // SUB r
	CASE7( 80, 81, 82, 83, 84, 85, 87 ): // ADD r
		flags &= ~C01;
	CASE7( 98, 99, 9A, 9B, 9C, 9D, 9F ): // SBC r
	CASE7( 88, 89, 8A, 8B, 8C, 8D, 8F ): // ADC r
		data = R8( opcode & 7, 0 );
	adc_data: {
		int result = data + (flags & C01);
		data ^= rg.a;
		flags = opcode >> 3 & N02; // bit 4 is set in subtract opcodes
		if ( flags )
			result = -result;
		result += rg.a;
		data ^= result;
		flags |=(data & H10) |
				((data - -0x80) >> 6 & V04) |
				SZ28C( result & 0x1FF );
		rg.a = result;
		goto loop;
	}

// CP
	case 0xBE: // CP (HL)
		data = READ( rp.hl );
		goto cp_data;
	
	case 0xFE: // CP imm
		pc++;
		goto cp_data;
	
	CASE7( B8, B9, BA, BB, BC, BD, BF ): // CP r
		data = R8( opcode, 0xB8 );
	cp_data: {
		int result = rg.a - data;
		flags = N02 | (data & (F20 | F08)) | (result >> 8 & C01);
		data ^= rg.a;
		flags |=(((result ^ rg.a) & data) >> 5 & V04) |
				(((data & H10) ^ result) & (S80 | H10));
		if ( (uint8_t) result )
			goto loop;
		flags |= Z40;
		goto loop;
	}
	
// ADD HL,rp
	
	case 0x39: // ADD HL,SP
		data = sp;
		goto add_hl_data;
	
	case 0x09: // ADD HL,BC
	case 0x19: // ADD HL,DE
	case 0x29: // ADD HL,HL
		data = R16( opcode, 4, 0x09 );
	add_hl_data: {
		blargg_ulong sum = rp.hl + data;
		data ^= rp.hl;
		rp.hl = (uint16_t)sum;
		flags = (flags & (S80 | Z40 | V04)) |
				(sum >> 16) |
				(sum >> 8 & (F20 | F08)) |
				((data ^ sum) >> 8 & H10);
		goto loop;
	}
	
	case 0x27:{// DAA
		int a = rg.a;
		if ( a > 0x99 )
			flags |= C01;
		
		int adjust = 0x60 & -(flags & C01);
		
		if ( flags & H10 || (a & 0x0F) > 9 )
			adjust |= 0x06;
		
		if ( flags & N02 )
			adjust = -adjust;
		a += adjust;
		
		flags = (flags & (C01 | N02)) |
				((rg.a ^ a) & H10) |
				SZ28P( (uint8_t) a );
		rg.a = a;
		goto loop;
	}
	/*
	case 0x27:{// DAA
		// more optimized, but probably not worth the obscurity
		int f = (rg.a + (0xFF - 0x99)) >> 8 | flags; // (a > 0x99 ? C01 : 0) | flags
		int adjust = 0x60 & -(f & C01); // f & C01 ? 0x60 : 0
		
		if ( (((rg.a + (0x0F - 9)) ^ rg.a) | f) & H10 ) // flags & H10 || (rg.a & 0x0F) > 9
			adjust |= 0x06;
		
		if ( f & N02 )
			adjust = -adjust;
		int a = rg.a + adjust;
		
		flags = (f & (N02 | C01)) | ((rg.a ^ a) & H10) | SZ28P( (uint8_t) a );
		rg.a = a;
		goto loop;
	}
	*/
	
// INC/DEC
	case 0x34: // INC (HL)
		data = READ( rp.hl ) + 1;
		WRITE( rp.hl, data );
		goto inc_set_flags;
	
	CASE7( 04, 0C, 14, 1C, 24, 2C, 3C ): // INC r
		data = ++R8( opcode >> 3, 0 );
	inc_set_flags:
		flags = (flags & C01) |
				(((data & 0x0F) - 1) & H10) |
				SZ28( (uint8_t) data );
		if ( data != 0x80 )
			goto loop;
		flags |= V04;
		goto loop;
	
	case 0x35: // DEC (HL)
		data = READ( rp.hl ) - 1;
		WRITE( rp.hl, data );
		goto dec_set_flags;
	
	CASE7( 05, 0D, 15, 1D, 25, 2D, 3D ): // DEC r
		data = --R8( opcode >> 3, 0 );
	dec_set_flags:
		flags = (flags & C01) | N02 |
				(((data & 0x0F) + 1) & H10) |
				SZ28( (uint8_t) data );
		if ( data != 0x7F )
			goto loop;
		flags |= V04;
		goto loop;

	case 0x03: // INC BC
	case 0x13: // INC DE
	case 0x23: // INC HL
		R16( opcode, 4, 0x03 )++;
		goto loop;
	
	case 0x33: // INC SP
		sp = uint16_t (sp + 1);
		goto loop;
	
	case 0x0B: // DEC BC
	case 0x1B: // DEC DE
	case 0x2B: // DEC HL
		R16( opcode, 4, 0x0B )--;
		goto loop;
	
	case 0x3B: // DEC SP
		sp = uint16_t (sp - 1);
		goto loop;
	
// AND
	case 0xA6: // AND (HL)
		data = READ( rp.hl );
		goto and_data;
	
	case 0xE6: // AND imm
		pc++;
		goto and_data;
	
	CASE7( A0, A1, A2, A3, A4, A5, A7 ): // AND r
		data = R8( opcode, 0xA0 );
	and_data:
		rg.a &= data;
		flags = SZ28P( rg.a ) | H10;
		goto loop;
	
// OR
	case 0xB6: // OR (HL)
		data = READ( rp.hl );
		goto or_data;
	
	case 0xF6: // OR imm
		pc++;
		goto or_data;
	
	CASE7( B0, B1, B2, B3, B4, B5, B7 ): // OR r
		data = R8( opcode, 0xB0 );
	or_data:
		rg.a |= data;
		flags = SZ28P( rg.a );
		goto loop;

// XOR
	case 0xAE: // XOR (HL)
		data = READ( rp.hl );
		goto xor_data;
	
	case 0xEE: // XOR imm
		pc++;
		goto xor_data;
	
	CASE7( A8, A9, AA, AB, AC, AD, AF ): // XOR r
		data = R8( opcode, 0xA8 );
	xor_data:
		rg.a ^= data;
		flags = SZ28P( rg.a );
		goto loop;

// LD
	CASE7( 70, 71, 72, 73, 74, 75, 77 ): // LD (HL),r
		WRITE( rp.hl, R8( opcode, 0x70 ) );
		goto loop;
	
	CASE6( 41, 42, 43, 44, 45, 47 ): // LD B,r
	CASE6( 48, 4A, 4B, 4C, 4D, 4F ): // LD C,r
	CASE6( 50, 51, 53, 54, 55, 57 ): // LD D,r
	CASE6( 58, 59, 5A, 5C, 5D, 5F ): // LD E,r
	CASE6( 60, 61, 62, 63, 65, 67 ): // LD H,r
	CASE6( 68, 69, 6A, 6B, 6C, 6F ): // LD L,r
	CASE6( 78, 79, 7A, 7B, 7C, 7D ): // LD A,r
		R8( opcode >> 3 & 7, 0 ) = R8( opcode & 7, 0 );
		goto loop;
	
	CASE5( 06, 0E, 16, 1E, 26 ): // LD r,imm
		R8( opcode >> 3, 0 ) = data;
		pc++;
		goto loop;
	
	case 0x36: // LD (HL),imm
		pc++;
		WRITE( rp.hl, data );
		goto loop;
	
	CASE7( 46, 4E, 56, 5E, 66, 6E, 7E ): // LD r,(HL)
		R8( opcode >> 3, 8 ) = READ( rp.hl );
		goto loop;
	
	case 0x01: // LD rp,imm
	case 0x11:
	case 0x21:
		R16( opcode, 4, 0x01 ) = GET_ADDR();
		pc += 2;
		goto loop;
	
	case 0x31: // LD sp,imm
		sp = GET_ADDR();
		pc += 2;
		goto loop;
	
	case 0x2A:{// LD HL,(addr)
		fuint16 addr = GET_ADDR();
		pc += 2;
		rp.hl = READ_WORD( addr );
		goto loop;
	}
	
	case 0x32:{// LD (addr),A
		fuint16 addr = GET_ADDR();
		pc += 2;
		WRITE( addr, rg.a );
		goto loop;
	}
	
	case 0x22:{// LD (addr),HL
		fuint16 addr = GET_ADDR();
		pc += 2;
		WRITE_WORD( addr, rp.hl );
		goto loop;
	}
	
	case 0x02: // LD (BC),A
	case 0x12: // LD (DE),A
		WRITE( R16( opcode, 4, 0x02 ), rg.a );
		goto loop;
	
	case 0x0A: // LD A,(BC)
	case 0x1A: // LD A,(DE)
		rg.a = READ( R16( opcode, 4, 0x0A ) );
		goto loop;
	
	case 0xF9: // LD SP,HL
		sp = rp.hl;
		goto loop;
	
// Rotate
	
	case 0x07:{// RLCA
		fuint16 temp = rg.a;
		temp = (temp << 1) | (temp >> 7);
		flags = (flags & (S80 | Z40 | P04)) |
				(temp & (F20 | F08 | C01));
		rg.a = temp;
		goto loop;
	}
	
	case 0x0F:{// RRCA
		fuint16 temp = rg.a;
		flags = (flags & (S80 | Z40 | P04)) |
				(temp & C01);
		temp = (temp << 7) | (temp >> 1);
		flags |= temp & (F20 | F08);
		rg.a = temp;
		goto loop;
	}
	
	case 0x17:{// RLA
		blargg_ulong temp = (rg.a << 1) | (flags & C01);
		flags = (flags & (S80 | Z40 | P04)) |
				(temp & (F20 | F08)) |
				(temp >> 8);
		rg.a = (uint8_t)temp;
		goto loop;
	}
	
	case 0x1F:{// RRA
		fuint16 temp = (flags << 7) | (rg.a >> 1);
		flags = (flags & (S80 | Z40 | P04)) |
				(temp & (F20 | F08)) |
				(rg.a & C01);
		rg.a = temp;
		goto loop;
	}
	
// Misc
	case 0x2F:{// CPL
		fuint16 temp = ~rg.a;
		flags = (flags & (S80 | Z40 | P04 | C01)) |
				(temp & (F20 | F08)) |
				(H10 | N02);
		rg.a = temp;
		goto loop;
	}
	
	case 0x3F:{// CCF
		flags = ((flags & (S80 | Z40 | P04 | C01)) ^ C01) |
				(flags << 4 & H10) |
				(rg.a & (F20 | F08));
		goto loop;
	}
	
	case 0x37: // SCF
		flags = (flags & (S80 | Z40 | P04)) | C01 |
				(rg.a & (F20 | F08));
		goto loop;
	
	case 0xDB: // IN A,(imm)
		pc++;
		rg.a = IN( data + rg.a * 0x100 );
		goto loop;

	case 0xE3:{// EX (SP),HL
		fuint16 temp = READ_WORD( sp );
		WRITE_WORD( sp, rp.hl );
		rp.hl = temp;
		goto loop;
	}
	
	case 0xEB:{// EX DE,HL
		fuint16 temp = rp.hl;
		rp.hl = rp.de;
		rp.de = temp;
		goto loop;
	}
	
	case 0xD9:{// EXX DE,HL
		fuint16 temp = r.alt.w.bc;
		r.alt.w.bc = rp.bc;
		rp.bc = temp;
		
		temp = r.alt.w.de;
		r.alt.w.de = rp.de;
		rp.de = temp;
		
		temp = r.alt.w.hl;
		r.alt.w.hl = rp.hl;
		rp.hl = temp;
		goto loop;
	}
	
	case 0xF3: // DI
		r.iff1 = 0;
		r.iff2 = 0;
		goto loop;
	
	case 0xFB: // EI
		r.iff1 = 1;
		r.iff2 = 1;
		// TODO: delayed effect
		goto loop;
	
	case 0x76: // HALT
		goto halt;
	
//////////////////////////////////////// CB prefix
	{
	case 0xCB:
		unsigned data2;
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



doom_py/src/vizdoom/game-music-emu/gme/Kss_Cpu.cpp [400:842]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
	CASE7( C7, CF, D7, DF, E7, EF, F7 ):
		data = pc;
		pc = opcode & 0x38;
		goto push_data;

// PUSH/POP
	case 0xF5: // PUSH AF
		data = rg.a * 0x100u + flags;
		goto push_data;
	
	case 0xC5: // PUSH BC
	case 0xD5: // PUSH DE
	case 0xE5: // PUSH HL
		data = R16( opcode, 4, 0xC5 );
	push_data:
		sp = uint16_t (sp - 2);
		WRITE_WORD( sp, data );
		goto loop;
	
	case 0xF1: // POP AF
		flags = READ( sp );
		rg.a = READ( sp + 1 );
		sp = uint16_t (sp + 2);
		goto loop;
	
	case 0xC1: // POP BC
	case 0xD1: // POP DE
	case 0xE1: // POP HL
		R16( opcode, 4, 0xC1 ) = READ_WORD( sp );
		sp = uint16_t (sp + 2);
		goto loop;
	
// ADC/ADD/SBC/SUB
	case 0x96: // SUB (HL)
	case 0x86: // ADD (HL)
		flags &= ~C01;
	case 0x9E: // SBC (HL)
	case 0x8E: // ADC (HL)
		data = READ( rp.hl );
		goto adc_data;
	
	case 0xD6: // SUB A,imm
	case 0xC6: // ADD imm
		flags &= ~C01;
	case 0xDE: // SBC A,imm
	case 0xCE: // ADC imm
		pc++;
		goto adc_data;
	
	CASE7( 90, 91, 92, 93, 94, 95, 97 ): // SUB r
	CASE7( 80, 81, 82, 83, 84, 85, 87 ): // ADD r
		flags &= ~C01;
	CASE7( 98, 99, 9A, 9B, 9C, 9D, 9F ): // SBC r
	CASE7( 88, 89, 8A, 8B, 8C, 8D, 8F ): // ADC r
		data = R8( opcode & 7, 0 );
	adc_data: {
		int result = data + (flags & C01);
		data ^= rg.a;
		flags = opcode >> 3 & N02; // bit 4 is set in subtract opcodes
		if ( flags )
			result = -result;
		result += rg.a;
		data ^= result;
		flags |=(data & H10) |
				((data - -0x80) >> 6 & V04) |
				SZ28C( result & 0x1FF );
		rg.a = result;
		goto loop;
	}

// CP
	case 0xBE: // CP (HL)
		data = READ( rp.hl );
		goto cp_data;
	
	case 0xFE: // CP imm
		pc++;
		goto cp_data;
	
	CASE7( B8, B9, BA, BB, BC, BD, BF ): // CP r
		data = R8( opcode, 0xB8 );
	cp_data: {
		int result = rg.a - data;
		flags = N02 | (data & (F20 | F08)) | (result >> 8 & C01);
		data ^= rg.a;
		flags |=(((result ^ rg.a) & data) >> 5 & V04) |
				(((data & H10) ^ result) & (S80 | H10));
		if ( (uint8_t) result )
			goto loop;
		flags |= Z40;
		goto loop;
	}
	
// ADD HL,rp
	
	case 0x39: // ADD HL,SP
		data = sp;
		goto add_hl_data;
	
	case 0x09: // ADD HL,BC
	case 0x19: // ADD HL,DE
	case 0x29: // ADD HL,HL
		data = R16( opcode, 4, 0x09 );
	add_hl_data: {
		blargg_ulong sum = rp.hl + data;
		data ^= rp.hl;
		rp.hl = (uint16_t)sum;
		flags = (flags & (S80 | Z40 | V04)) |
				(sum >> 16) |
				(sum >> 8 & (F20 | F08)) |
				((data ^ sum) >> 8 & H10);
		goto loop;
	}
	
	case 0x27:{// DAA
		int a = rg.a;
		if ( a > 0x99 )
			flags |= C01;
		
		int adjust = 0x60 & -(flags & C01);
		
		if ( flags & H10 || (a & 0x0F) > 9 )
			adjust |= 0x06;
		
		if ( flags & N02 )
			adjust = -adjust;
		a += adjust;
		
		flags = (flags & (C01 | N02)) |
				((rg.a ^ a) & H10) |
				SZ28P( (uint8_t) a );
		rg.a = a;
		goto loop;
	}
	/*
	case 0x27:{// DAA
		// more optimized, but probably not worth the obscurity
		int f = (rg.a + (0xFF - 0x99)) >> 8 | flags; // (a > 0x99 ? C01 : 0) | flags
		int adjust = 0x60 & -(f & C01); // f & C01 ? 0x60 : 0
		
		if ( (((rg.a + (0x0F - 9)) ^ rg.a) | f) & H10 ) // flags & H10 || (rg.a & 0x0F) > 9
			adjust |= 0x06;
		
		if ( f & N02 )
			adjust = -adjust;
		int a = rg.a + adjust;
		
		flags = (f & (N02 | C01)) | ((rg.a ^ a) & H10) | SZ28P( (uint8_t) a );
		rg.a = a;
		goto loop;
	}
	*/
	
// INC/DEC
	case 0x34: // INC (HL)
		data = READ( rp.hl ) + 1;
		WRITE( rp.hl, data );
		goto inc_set_flags;
	
	CASE7( 04, 0C, 14, 1C, 24, 2C, 3C ): // INC r
		data = ++R8( opcode >> 3, 0 );
	inc_set_flags:
		flags = (flags & C01) |
				(((data & 0x0F) - 1) & H10) |
				SZ28( (uint8_t) data );
		if ( data != 0x80 )
			goto loop;
		flags |= V04;
		goto loop;
	
	case 0x35: // DEC (HL)
		data = READ( rp.hl ) - 1;
		WRITE( rp.hl, data );
		goto dec_set_flags;
	
	CASE7( 05, 0D, 15, 1D, 25, 2D, 3D ): // DEC r
		data = --R8( opcode >> 3, 0 );
	dec_set_flags:
		flags = (flags & C01) | N02 |
				(((data & 0x0F) + 1) & H10) |
				SZ28( (uint8_t) data );
		if ( data != 0x7F )
			goto loop;
		flags |= V04;
		goto loop;

	case 0x03: // INC BC
	case 0x13: // INC DE
	case 0x23: // INC HL
		R16( opcode, 4, 0x03 )++;
		goto loop;
	
	case 0x33: // INC SP
		sp = uint16_t (sp + 1);
		goto loop;
	
	case 0x0B: // DEC BC
	case 0x1B: // DEC DE
	case 0x2B: // DEC HL
		R16( opcode, 4, 0x0B )--;
		goto loop;
	
	case 0x3B: // DEC SP
		sp = uint16_t (sp - 1);
		goto loop;
	
// AND
	case 0xA6: // AND (HL)
		data = READ( rp.hl );
		goto and_data;
	
	case 0xE6: // AND imm
		pc++;
		goto and_data;
	
	CASE7( A0, A1, A2, A3, A4, A5, A7 ): // AND r
		data = R8( opcode, 0xA0 );
	and_data:
		rg.a &= data;
		flags = SZ28P( rg.a ) | H10;
		goto loop;
	
// OR
	case 0xB6: // OR (HL)
		data = READ( rp.hl );
		goto or_data;
	
	case 0xF6: // OR imm
		pc++;
		goto or_data;
	
	CASE7( B0, B1, B2, B3, B4, B5, B7 ): // OR r
		data = R8( opcode, 0xB0 );
	or_data:
		rg.a |= data;
		flags = SZ28P( rg.a );
		goto loop;

// XOR
	case 0xAE: // XOR (HL)
		data = READ( rp.hl );
		goto xor_data;
	
	case 0xEE: // XOR imm
		pc++;
		goto xor_data;
	
	CASE7( A8, A9, AA, AB, AC, AD, AF ): // XOR r
		data = R8( opcode, 0xA8 );
	xor_data:
		rg.a ^= data;
		flags = SZ28P( rg.a );
		goto loop;

// LD
	CASE7( 70, 71, 72, 73, 74, 75, 77 ): // LD (HL),r
		WRITE( rp.hl, R8( opcode, 0x70 ) );
		goto loop;
	
	CASE6( 41, 42, 43, 44, 45, 47 ): // LD B,r
	CASE6( 48, 4A, 4B, 4C, 4D, 4F ): // LD C,r
	CASE6( 50, 51, 53, 54, 55, 57 ): // LD D,r
	CASE6( 58, 59, 5A, 5C, 5D, 5F ): // LD E,r
	CASE6( 60, 61, 62, 63, 65, 67 ): // LD H,r
	CASE6( 68, 69, 6A, 6B, 6C, 6F ): // LD L,r
	CASE6( 78, 79, 7A, 7B, 7C, 7D ): // LD A,r
		R8( opcode >> 3 & 7, 0 ) = R8( opcode & 7, 0 );
		goto loop;
	
	CASE5( 06, 0E, 16, 1E, 26 ): // LD r,imm
		R8( opcode >> 3, 0 ) = data;
		pc++;
		goto loop;
	
	case 0x36: // LD (HL),imm
		pc++;
		WRITE( rp.hl, data );
		goto loop;
	
	CASE7( 46, 4E, 56, 5E, 66, 6E, 7E ): // LD r,(HL)
		R8( opcode >> 3, 8 ) = READ( rp.hl );
		goto loop;
	
	case 0x01: // LD rp,imm
	case 0x11:
	case 0x21:
		R16( opcode, 4, 0x01 ) = GET_ADDR();
		pc += 2;
		goto loop;
	
	case 0x31: // LD sp,imm
		sp = GET_ADDR();
		pc += 2;
		goto loop;
	
	case 0x2A:{// LD HL,(addr)
		fuint16 addr = GET_ADDR();
		pc += 2;
		rp.hl = READ_WORD( addr );
		goto loop;
	}
	
	case 0x32:{// LD (addr),A
		fuint16 addr = GET_ADDR();
		pc += 2;
		WRITE( addr, rg.a );
		goto loop;
	}
	
	case 0x22:{// LD (addr),HL
		fuint16 addr = GET_ADDR();
		pc += 2;
		WRITE_WORD( addr, rp.hl );
		goto loop;
	}
	
	case 0x02: // LD (BC),A
	case 0x12: // LD (DE),A
		WRITE( R16( opcode, 4, 0x02 ), rg.a );
		goto loop;
	
	case 0x0A: // LD A,(BC)
	case 0x1A: // LD A,(DE)
		rg.a = READ( R16( opcode, 4, 0x0A ) );
		goto loop;
	
	case 0xF9: // LD SP,HL
		sp = rp.hl;
		goto loop;
	
// Rotate
	
	case 0x07:{// RLCA
		fuint16 temp = rg.a;
		temp = (temp << 1) | (temp >> 7);
		flags = (flags & (S80 | Z40 | P04)) |
				(temp & (F20 | F08 | C01));
		rg.a = temp;
		goto loop;
	}
	
	case 0x0F:{// RRCA
		fuint16 temp = rg.a;
		flags = (flags & (S80 | Z40 | P04)) |
				(temp & C01);
		temp = (temp << 7) | (temp >> 1);
		flags |= temp & (F20 | F08);
		rg.a = temp;
		goto loop;
	}
	
	case 0x17:{// RLA
		blargg_ulong temp = (rg.a << 1) | (flags & C01);
		flags = (flags & (S80 | Z40 | P04)) |
				(temp & (F20 | F08)) |
				(temp >> 8);
		rg.a = (uint8_t)temp;
		goto loop;
	}
	
	case 0x1F:{// RRA
		fuint16 temp = (flags << 7) | (rg.a >> 1);
		flags = (flags & (S80 | Z40 | P04)) |
				(temp & (F20 | F08)) |
				(rg.a & C01);
		rg.a = temp;
		goto loop;
	}
	
// Misc
	case 0x2F:{// CPL
		fuint16 temp = ~rg.a;
		flags = (flags & (S80 | Z40 | P04 | C01)) |
				(temp & (F20 | F08)) |
				(H10 | N02);
		rg.a = temp;
		goto loop;
	}
	
	case 0x3F:{// CCF
		flags = ((flags & (S80 | Z40 | P04 | C01)) ^ C01) |
				(flags << 4 & H10) |
				(rg.a & (F20 | F08));
		goto loop;
	}
	
	case 0x37: // SCF
		flags = (flags & (S80 | Z40 | P04)) | C01 |
				(rg.a & (F20 | F08));
		goto loop;
	
	case 0xDB: // IN A,(imm)
		pc++;
		rg.a = IN( data + rg.a * 0x100 );
		goto loop;

	case 0xE3:{// EX (SP),HL
		fuint16 temp = READ_WORD( sp );
		WRITE_WORD( sp, rp.hl );
		rp.hl = temp;
		goto loop;
	}
	
	case 0xEB:{// EX DE,HL
		fuint16 temp = rp.hl;
		rp.hl = rp.de;
		rp.de = temp;
		goto loop;
	}
	
	case 0xD9:{// EXX DE,HL
		fuint16 temp = r.alt.w.bc;
		r.alt.w.bc = rp.bc;
		rp.bc = temp;
		
		temp = r.alt.w.de;
		r.alt.w.de = rp.de;
		rp.de = temp;
		
		temp = r.alt.w.hl;
		r.alt.w.hl = rp.hl;
		rp.hl = temp;
		goto loop;
	}
	
	case 0xF3: // DI
		r.iff1 = 0;
		r.iff2 = 0;
		goto loop;
	
	case 0xFB: // EI
		r.iff1 = 1;
		r.iff2 = 1;
		// TODO: delayed effect
		goto loop;
	
	case 0x76: // HALT
		goto halt;
	
//////////////////////////////////////// CB prefix
	{
	case 0xCB:
		unsigned data2;
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -