#include "sux.h"
#include <assert.h>

#if getclk
uint64_t clk[THREADS];	/* Per Thread Clock cycles. */
uint64_t tclk;		/* Total Clock cycles. */
#endif

const uint16_t tv = 0xFF50; /* Starting address of the Thread Vectors. */

#if !IO
uint64_t inst[THREADS];
#endif

#if bench
uint64_t inss;
#endif

#if debug
uint8_t subdbg;
#endif

pthread_mutex_t mutex = PTHREAD_MUTEX_INITIALIZER;
pthread_mutex_t main_mutex = PTHREAD_MUTEX_INITIALIZER;
pthread_cond_t cond = PTHREAD_COND_INITIALIZER;
pthread_cond_t main_cond = PTHREAD_COND_INITIALIZER;

uint8_t threads_done = 0;
uint8_t step = 0;
uint8_t esc = 0;

uint8_t *addr;

uint8_t kbd_rdy;

WINDOW *scr;

struct suxthr {
	struct sux sx;
	uint8_t th;
};

#if bench
double ipc;
struct timeval str[THREADS], en[THREADS];
#endif

inline uint8_t get_addrsize(uint8_t prefix, uint8_t addrmode) {
	uint8_t id = (prefix & 0x0C) >> 2;
	switch (addrmode) {
		case ZM:
			switch (id) {
				case 2: return 5;
				case 3: return 3;
				case 1: return 2;
				case 0: return 0;
			}
			break;
		case ABS:
			switch (id) {
				case 3: return 7;
				case 2: return 6;
				case 1: return 4;
				case 0: return 1;
			}
			break;
	}
	return 0;
}

void *run(void *args) {
	struct suxthr *thr = (void *)args;
	struct sux *cpu = &thr->sx;
	uint8_t thread = thr->th;
	uint8_t prefix = 0;
	uint8_t opcode = 0;
	union reg address;
	union reg value;
	#if getclk
	uint64_t iclk = 0;
	#endif
	#if !IO
	uint64_t ins = 0;
	#endif
#if !bench
	uint8_t lines = (6*thread)+2;
#endif
#if debug && !bench
	if (!subdbg) {
		addr[STEP_ADDR] = 1;
		step = 1;
	}
	#if keypoll
	pthread_mutex_lock(&mutex);
	#endif
	werase(scr);
	#if keypoll
	pthread_mutex_unlock(&mutex);
	#endif
#endif
	uint64_t tmpaddr = 0;
#if bench
	gettimeofday(&str[thread], 0);
#endif
	for (;;) {
		address.u64 = 0;
		value.u64 = 0;
		#if debug && !bench
		if (lines > 24*(thread+1)) {
			lines = (24*thread)+2;
		}
		#if keypoll
		pthread_mutex_lock(&mutex);
		#endif
		for (uint8_t i = (24*thread)+2; i <= 24*(thread+1); i++) {
			wmove(scr, i, 0);
			waddch(scr, (i == lines) ? '>' : ' ');
		}
		wmove(scr, lines, 1);
		wclrtoeol(scr);
		wprintw(scr, "pc: $%04"PRIX64  , cpu->pc);
		wprintw(scr, ", a: $%016"PRIX64, cpu->a);
		wprintw(scr, ", b: $%016"PRIX64, cpu->b);
		wprintw(scr, ", x: $%016"PRIX64, cpu->x);
		wprintw(scr, ", y: $%016"PRIX64, cpu->y);
		wprintw(scr, ", sp: $%04X", cpu->sp);
		wprintw(scr, ", ps: $%02X", cpu->ps.u8[thread]);
		wprintw(scr, ", inst: ");
		#if keypoll
		pthread_mutex_unlock(&mutex);
		#endif
		#endif
		prefix = addr[cpu->pc];
		if ((prefix & 0x03) != 0x03) {
			prefix = 0;
		}
		cpu->pc += ((prefix & 0x03) == 0x03);
		opcode = addr[cpu->pc];
		address.u64 = cpu->pc;
		++cpu->pc;
		#if getclk
		++iclk;
		#endif
		if (optype[opcode] != IMPL) {
			address.u64 = get_addr(cpu, &tmpaddr, opcode, prefix, thread);

			if (address.u64 > mem_size-1) {
				addr[STEP_ADDR] = 1;
				step = 1;
			}
			setreg_sw(value.u8, 0, addr, address.u64, prefix, 0, RS);
			if (optype[opcode] == REL) {
				switch ((prefix >> 4) & 3) {
					default: address.u64 = cpu->pc + (int8_t )value.u8[0] ; break;
					case 1 : address.u64 = cpu->pc + (int16_t)value.u16[0]; break;
					case 2 : address.u64 = cpu->pc + (int32_t)value.u32[0]; break;
					case 3 : address.u64 = cpu->pc + (int64_t)value.u64   ; break;
				}
			}
			#if getclk
			++iclk;
			#endif
		}
	#if debug && !bench
		#if keypoll
		pthread_mutex_lock(&mutex);
		#endif
		uint64_t operands[3];
		operands[0] = value.u64;
		operands[1] = address.u64;
		operands[2] = tmpaddr;
		disasm(cpu, operands, lines, opcode, prefix, thread);
		lines+=1;
		#if keypoll
		pthread_mutex_unlock(&mutex);
		#endif
	#endif
		uint8_t size = (1 << ((prefix >> 4) & 3))-1;
		switch(opcode) {
			case CPS_IMP: /* Clear Processor Status. */
				cpu->ps.u64 = 0;
				break;
			case ADC_B: /* ADC B register. */
				value.u64 = cpu->b; /* Falls Through. */
			case ADC_IMM:  /* ADC Immediate. */
			case ADC_AB: /* ADC Absolute. */
			case ADC_Z: /* ADC Zero Matrix. */
				adc(cpu, value.u64, thread);
				break;
			case PHP_IMP: push(cpu, cpu->ps.u8[thread],    0, thread); break; /* PusH Processor status to stack. */
			case PHA_IMP: push(cpu, cpu->a            , size, thread); break; /* PusH Accumulator to stack. */
			case PHB_IMP: push(cpu, cpu->b            , size, thread); break; /* PusH B register to stack. */
			case PHY_IMP: push(cpu, cpu->y            , size, thread); break; /* PusH Y register to stack. */
			case PHX_IMP: push(cpu, cpu->x            , size, thread); break; /* PusH X register to stack. */
			case TAY_IMP: /* Transfer Accumulator to Y. */
			case TAX_IMP: /* Transfer Accumulator to Y. */
			case TYX_IMP: /* Transfer Y to X. */
			case TYA_IMP: /* Transfer Y to Accumulator. */
			case TXA_IMP: /* Transfer X to Accumulator. */
			case TXY_IMP: /* Transfer X to Y. */
			case TAB_IMP: /* Transfer Accumulator to B. */
			case TSX_IMP: /* Transfer Stack pointer to X. */
			case TBA_IMP: /* Transfer B to Accumulator. */
			case TXS_IMM: /* Transfer X to Stack pointer. */
				transfer(cpu, value.u64, opcode, prefix, thread);
				break;
			case BRA_REL: /* BRA Relative. */
			case JMP_AB: /* JMP Absolute. */
			case JMP_Z: /* JMP Zero Matrix. */
			case JMP_IN: /* JMP Indirect. */
				cpu->pc = address.u64;
				break;
			case SBC_B: /* SBC B register. */
				value.u64 = cpu->b; /* Falls Through. */
			case SBC_IMM: /* SBC Immediate. */
			case SBC_AB: /* SBC Absolute. */
			case SBC_Z: /* SBC Zero Matrix. */
				sbc(cpu, value.u64, thread);
				break;
			case PLP_IMP: cpu->ps.u8[thread] = pull(cpu,    0, thread); break; /* PuLl Processor status from stack. */
			case PLA_IMP: cpu->a             = pull(cpu, size, thread); break; /* PuLl Accumulator from stack. */
			case PLB_IMP: cpu->b             = pull(cpu, size, thread); break; /* PuLl B register from stack. */
			case PLY_IMP: cpu->y             = pull(cpu, size, thread); break; /* PuLl Y register from stack. */
			case PLX_IMP: cpu->x             = pull(cpu, size, thread); break; /* PuLl X register from stack. */
				break;
			case AND_B: /* AND B register. */
				value.u64 = cpu->b; /* Falls Through. */
			case AND_IMM: /* AND Immediate. */
			case AND_AB: /* AND Absolute. */
			case AND_Z: /* AND Zero Matrix. */
				and(cpu, value.u64, thread);
				break;
			case BPO_REL: /* BPO Relative. */
				if (!getflag(N)) {
					cpu->pc = address.u64;
				}
				break;
			case ORA_B: /* ORA B register. */
				value.u64 = cpu->b; /* Falls Through. */
			case ORA_IMM: /* ORA Immediate. */
			case ORA_AB: /* ORA Absolute. */
			case ORA_Z: /* ORA Zero Matrix. */
				or(cpu, value.u64, thread);
				break;
			case SEI_IMP: /* SEt Interrupt. */
				setflag(1, I);
				break;
			case BNG_REL: /* BNG Relative. */
				if (getflag(N)) {
					cpu->pc = address.u64;
				}
				break;
			case XOR_B: /* XOR B register. */
				value.u64 = cpu->b; /* Falls Through. */
			case XOR_IMM: /* XOR Immediate. */
			case XOR_AB: /* XOR Absolute. */
			case XOR_Z: /* XOR Zero Matrix. */
				xor(cpu, value.u64, thread);
				break;
			case CLI_IMP: /* CLear Interrupt. */
				setflag(0, I);
				break;
			case BCS_REL: /* BCS Relative. */
				if (getflag(C)) {
					cpu->pc = address.u64;
				}
				break;
			case LSL_B: /* LSL B register. */
				value.u64 = cpu->b; /* Falls Through. */
			case LSL_IMM: /* LSL Immediate. */
			case LSL_AB: /* LSL Absolute. */
			case LSL_Z: /* LSL Zero Matrix. */
				lsl(cpu, value.u64, thread);
				break;
			case SEC_IMP: /* SEt Carry flag.*/
				setflag(1, C);
				break;
			case STA_AB: /* STA Absolute. */
			case STA_Z: /* STA Zero Matrix. */
			case STA_ZX: /* STA Zero Matrix, Indexed with X. */
			case STA_ZY: /* STA Zero Matrix, Indexed with Y. */
			case STA_IN: /* STA Indirect. */
			case STA_IX: /* STA Indexed Indirect. */
			case STA_IY: /* STA Indirect Indexed. */
				store(cpu, address.u64, cpu->a, prefix, thread);
				break;
			case STY_AB: /* STY Absolute. */
			case STY_Z: /* STY Zero Matrix. */
			case STY_IN: /* STY Indirect. */
				store(cpu, address.u64, cpu->y, prefix, thread);
				break;
			case STX_AB: /* STX Absolute. */
			case STX_Z: /* STX Zero Matrix. */
			case STX_IN: /* STX Indirect. */
				store(cpu, address.u64, cpu->x, prefix, thread);
				break;
			case STB_AB: /* STB Absolute. */
			case STB_Z: /* STB Zero Matrix. */
			case STB_ZX: /* STB Zero Matrix, Indexed with X. */
			case STB_ZY: /* STB Zero Matrix, Indexed with Y. */
			case STB_IN: /* STB Indirect. */
			case STB_IX: /* STB Indexed Indirect. */
			case STB_IY: /* STB Indirect Indexed. */
				store(cpu, address.u64, cpu->b, prefix, thread);
				break;
			case BCC_REL: /* BCC Relative. */
				if (!getflag(C)) {
					cpu->pc = address.u64;
				}
				break;
			case LSR_B: /* LSR B register. */
				value.u64 = cpu->b; /* Falls Through. */
			case LSR_IMM: /* LSR Immediate. */
			case LSR_AB: /* LSR Absolute. */
			case LSR_Z: /* LSR Zero Matrix. */
				lsr(cpu, value.u64, thread);
				break;
			case ASR_B: /* ASR B register. */
				value.u64 = cpu->b; /* Falls Through. */
			case ASR_IMM: /* ASR Immediate. */
			case ASR_AB: /* ASR Absolute. */
			case ASR_Z: /* ASR Zero Matrix. */
				asr(cpu, value.u64, thread);
				break;
			case CLC_IMP: /* CLear Carry flag. */
				setflag(0, C);
				break;
			case LDB_IMM: /* LDB Immediate. */
			case LDB_AB: /* LDB Absolute. */
			case LDB_Z: /* LDB Zero Matrix. */
			case LDB_ZX: /* LDB Zero Matrix, Indexed with X. */
			case LDB_ZY: /* LDB Zero Matrix, Indexed with Y. */
			case LDB_IN: /* LDB Indirect. */
			case LDB_IX: /* LDB Indexed Indirect. */
			case LDB_IY: /* LDB Indirect Indexed. */
				cpu->b = load(cpu, address.u64, cpu->b, prefix, thread);
				break;
			case LDA_IMM: /* LDA Immediate. */
			case LDA_AB: /* LDA Absolute. */
			case LDA_Z: /* LDA Zero Matrix. */
			case LDA_ZX: /* LDA Zero Matrix, Indexed with X. */
			case LDA_ZY: /* LDA Zero Matrix, Indexed with Y. */
			case LDA_IN: /* LDA Indirect. */
			case LDA_IX: /* LDA Indexed Indirect. */
			case LDA_IY: /* LDA Indirect Indexed. */
				cpu->a = load(cpu, address.u64, cpu->a, prefix, thread);
				break;
			case LDY_IMM: /* LDY Immediate. */
			case LDY_AB: /* LDY Absolute. */
			case LDY_Z: /* LDY Zero Matrix. */
			case LDY_IN: /* LDY Indirect. */
				cpu->y = load(cpu, address.u64, cpu->y, prefix, thread);
				break;
			case LDX_IMM: /* LDX Immediate. */
			case LDX_AB: /* LDX Absolute. */
			case LDX_Z: /* LDX Zero Matrix. */
			case LDX_IN: /* LDX Indirect. */
				cpu->x = load(cpu, address.u64, cpu->x, prefix, thread);
				break;
			case BEQ_REL: /* BEQ Relative. */
				if (getflag(Z)) {
					cpu->pc = address.u64;
				}
				break;
			case ROL_B: /* ROL B register. */
				value.u64 = cpu->b; /* Falls Through. */
			case ROL_IMM: /* ROL Immediate. */
			case ROL_AB: /* ROL Absolute. */
			case ROL_Z: /* ROL Zero Matrix. */
				rol(cpu, value.u64, thread);
				break;
			case BNE_REL: /* BNE Relative. */
				if (!getflag(Z)) {
					cpu->pc = address.u64;
				}
				break;
			case ROR_B: /* ROR B register. */
				value.u64 = cpu->b; /* Falls Through. */
			case ROR_IMM: /* ROR Immediate. */
			case ROR_AB: /* ROR Absolute. */
			case ROR_Z: /* ROR Zero Matrix. */
				ror(cpu, value.u64, thread);
				break;
			case BVS_REL: /* BVS Relative. */
				if (getflag(V)) {
					cpu->pc = address.u64;
				}
				break;
			case MUL_B: /* MUL B register. */
				value.u64 = cpu->b; /* Falls Through. */
			case MUL_IMM: /* MUL Immediate. */
			case MUL_AB: /* MUL Absolute. */
			case MUL_Z: /* MUL Zero Matrix. */
				mul(cpu, value.u64, thread);
				break;
			case BVC_REL: /* BVC Relative. */
				if (!getflag(V)) {
					cpu->pc = address.u64;
				}
				break;
			case DIV_IMM: /* DIV Immediate. */
			case DIV_B: /* DIV B register. */
			case DIV_AB: /* DIV Absolute. */
			case DIV_Z: /* DIV Zero Matrix. */
				divd(cpu, value.u64, opcode, thread);
				break;
			case CLV_IMP: /* CLear oVerflow flag. */
				setflag(0, V);
				break;
			case CPB_IMM: /* CPB Immediate. */
			case CPB_AB: /* CPB Absolute. */
			case CPB_Z: /* CPB Zero Matrix. */
			case CPB_IN: /* CPB Indirect. */
			case CPB_IX: /* CPB Indexed Indirect. */
			case CPB_IY: /* CPB Indirect Indexed. */
				cmp(cpu, value.u64, cpu->b, thread);
				break;
			case CMP_B: /* CMP B register. */
				value.u64 = cpu->b; /* Falls Through. */
			case CMP_IMM: /* CMP Immediate. */
			case CMP_AB: /* CMP Absolute. */
			case CMP_Z: /* CMP Zero Matrix. */
			case CMP_IN: /* CMP Indirect. */
			case CMP_IX: /* CMP Indexed Indirect. */
			case CMP_IY: /* CMP Indirect Indexed. */
				cmp(cpu, value.u64, cpu->a, thread);
				break;
			case CPY_IMM: /* CPY Immediate. */
			case CPY_AB: /* CPY Absolute. */
			case CPY_Z: /* CPY Zero Matrix. */
				cmp(cpu, value.u64, cpu->y, thread);
				break;
			case CPX_IMM: /* CPX Immediate. */
			case CPX_AB: /* CPX Absolute. */
			case CPX_Z: /* CPX Zero Matrix. */
				cmp(cpu, value.u64, cpu->x, thread);
				break;
			case INC_IMP: cpu->a = idr(cpu, cpu->a, 1, thread); break;
			case INB_IMP: cpu->b = idr(cpu, cpu->b, 1, thread); break;
			case INY_IMP: cpu->y = idr(cpu, cpu->y, 1, thread); break;
			case INX_IMP: cpu->x = idr(cpu, cpu->x, 1, thread); break;
			case DEC_IMP: cpu->a = idr(cpu, cpu->a, 0, thread); break;
			case DEB_IMP: cpu->b = idr(cpu, cpu->b, 0, thread); break;
			case DEY_IMP: cpu->y = idr(cpu, cpu->y, 0, thread); break;
			case DEX_IMP: cpu->x = idr(cpu, cpu->x, 0, thread); break;
			case JSR_IN: /* JSR Indirect. */
			case JSR_AB: /* Jump to SubRoutine. */
			case JSR_Z: /* JSR Zero Matrix. */
				push(cpu, cpu->pc, 7, thread);
				cpu->pc = address.u64;
				break;
			case INC_AB: /* INC Absolute. */
			case INC_Z: /* INC Zero Matrix. */
				idm(cpu, address.u64, prefix, 1, thread);
				break;
			case NOP_IMP: /* No OPeration. */
				break;
			case RTI_IMP: /* ReTurn from Interrupt routine. */
				cpu->ps.u64 = pull(cpu, 0, thread);
			case RTS_IMP: /* ReTurn from Subroutine. */
				cpu->pc = pull(cpu, 7, thread);
				break;
			case DEC_AB: /* DEC Absolute. */
			case DEC_Z: /* DEC Zero Matrix. */
				idm(cpu, address.u64, prefix, 0, thread);
				break;
			case BRK_IMP: /* BReaK. */
			case WAI_IMP: /* WAit for Interrupt. */
				if (opcode == WAI_IMP) {
					pthread_mutex_lock(&main_mutex);
					pthread_cond_signal(&main_cond);
					pthread_mutex_unlock(&main_mutex);
					pthread_mutex_lock(&mutex);
					pthread_cond_wait(&cond, &mutex);
					pthread_mutex_unlock(&mutex);
				}
				push(cpu, cpu->pc, 7, thread);
				push(cpu, cpu->ps.u8[thread], 0, thread);
				setflag(1, I);
				setreg(value.u8, +, 0, addr, +, (opcode == BRK) ? 0xFFE0 : 0xFFA0, 7);
				if (opcode == WAI_IMP) {
					kbd_rdy &= (uint8_t)~(1 << thread);
				}
				cpu->pc = value.u64;
			default:
				break;
		}
		#if !IO
		ins++;
		#endif
		#if !bench
		if (step) {
			pthread_mutex_lock(&main_mutex);
			pthread_cond_signal(&main_cond);
			pthread_mutex_unlock(&main_mutex);
			pthread_mutex_lock(&mutex);
			pthread_cond_wait(&cond, &mutex);
			pthread_mutex_unlock(&mutex);
			#if debug
			wrefresh(scr);
			#endif
		}
		#endif
		#if debug && !bench
		#if keypoll
		pthread_mutex_lock(&mutex);
		#endif
		wmove(scr, (6*thread)+1, 0);
		wprintw(scr, "Instructions executed: %"PRIu64, ins);
		#if getclk
		wprintw(scr, ", Clock cycles: %"PRIu64, iclk);
		#endif
		if (step && !subdbg) {
			wrefresh(scr);
		}
		#if keypoll
		pthread_mutex_unlock(&mutex);
		#endif
		#elif bench
		if (ins >= BENCH_INST) {
			pthread_mutex_lock(&main_mutex);
			threads_done++;
			inst[thread] = ins;
			#if getclk
			clk[thread] = iclk;
			#endif
			pthread_cond_signal(&main_cond);
			pthread_mutex_unlock(&main_mutex);
			gettimeofday(&en[thread], 0);
			break;
		}
		#endif
	}
	return NULL;
}

void init_scr() {
	if (!scr) {
		scr = initscr();
	}
	nodelay(scr, 0);
	wtimeout(scr, 8);
	crmode();
	noecho();
	nl();
	curs_set(1);
	scrollok(scr, 1);
	start_color();
	use_default_colors();
	init_pair(1, COLOR_WHITE, -1);
	attron(COLOR_PAIR(1) | A_BOLD);
}

int main(int argc, char **argv) {
	struct suxthr thr[THREADS];
	char *tmp = malloc(2048);
	addr = malloc(mem_size);
	memset(key, 0, sizeof(key));
	#if bench
	inss = 0;
	#endif
	int v = 0;

	if (argc != 2) {
		if (asmmon("stdin") == 2) {
			return 0;
		}
	} else {
		#if debug
		subdbg = !strcmp(argv[1], "programs/sub-suite/subsuite.s");
		#endif
		if (asmmon(argv[1]) == 2) {
			return 0;
		}
	}
	sprintf(tmp, "\033[2J\033[H");
	fwrite(tmp, sizeof(char), strlen(tmp), stdout);
	fflush(stdout);
	init_scr();
	werase(scr);
	wmove(scr, 0, 0);
	wrefresh(scr);
	pthread_t therads[THREADS];
	int result;
	uint16_t vec = 0xFFC0;
	uint8_t offset;
	for (int i = 0; i < THREADS; i++) {
		thr[i].sx.sp = 0xFFFF;
		thr[i].sx.stk_st = i+1;
		offset = (i) ? ((i-1) << 3) : 0;
		vec = (i) ? 0xFF50 : 0xFFC0;
		thr[i].sx.a = 0;
		thr[i].sx.b = 0;
		thr[i].sx.x = 0;
		thr[i].sx.y = 0;
		thr[i].sx.pc = (uint64_t)addr[vec+0+offset]
				| (uint64_t)addr[vec+1+offset] << 8
				| (uint64_t)addr[vec+2+offset] << 16
				| (uint64_t)addr[vec+3+offset] << 24
				| (uint64_t)addr[vec+4+offset] << 32
				| (uint64_t)addr[vec+5+offset] << 40
				| (uint64_t)addr[vec+6+offset] << 48
				| (uint64_t)addr[vec+7+offset] << 56;

		thr[i].th = i;
		#if !IO
		inst[i] = 0;
		#endif
		result = pthread_create(&therads[i], NULL, run, &thr[i]);
		assert(!result);
	}
	int c = 0;
	uint8_t step_key = 0;
	uint8_t end = 0;
	werase(scr);
	while (threads_done < THREADS && !end) {
		#if !bench
		int x, y;
		if ((step_key && step && !kbd_rdy) || !step || kbd_rdy) {
			if ((c != EOF && c !=-1)) {
				#if !keypoll
				pthread_mutex_lock(&mutex);
				pthread_cond_signal(&cond);
				pthread_mutex_unlock(&mutex);
				#endif
				pthread_mutex_lock(&main_mutex);
				curs_set(0);
				pthread_cond_wait(&main_cond, &main_mutex);
				pthread_mutex_unlock(&main_mutex);
				curs_set(1);
				c = 0;
				step_key = 0;
				addr[CTRL_ADDR] = 0;
				wrefresh(scr);
			}
		}
		#if keypoll
		pthread_mutex_lock(&mutex);
		#endif
		c = get_key(scr);
		if (c == 19) {
			if (kbd_rdy) {

				c = get_key(scr);
			}
			step = 1;
		} else if (c == 0x11) {
			end = 1;
			continue;
		}
		if (step) {
			if (c != 19 && c != 18 && c != 0x11 && !isalnum(c)) {
				/*WINDOW *w;
				int maxcol = getmaxx(scr)/2;
				int maxrow = getmaxy(scr)/2;*/
				int keycode = get_keycode(key);
				switch (keycode) {
					case KEY_F(1):
						/*w = newwin(maxrow, maxcol, maxrow, maxcol);
						emumon(w);
						delwin(w);*/
						endwin();
						puts("Starting asmmon()");
						asmmon("stdin");
						puts("Reinitializing screen.");
						init_scr();
						wrefresh(scr);
						break;
				}
				#if debug && !bench
				wmove(scr, getmaxy(scr)-1, 0);
				wclrtoeol(scr);
				wprintw(scr, "c: %i", c);
				wmove(scr, y, x);
				#endif
			}
		}
		if (kbd_rdy) {
			switch (c) {
				case ERR:
					addr[CTRL_ADDR] = 0;
					break;
				case '\0': break;
				default:
					if (kbd_rdy && c < 0x100) {
						addr[RX_ADDR] = (uint8_t)c;
						addr[CTRL_ADDR] = 1;
						#if debug && !bench
						wmove(scr, getmaxy(scr)-1, 0);
						wclrtoeol(scr);
						wprintw(scr, "c: %i ", c);
						wprintw(scr, "key: ");
						for (int i = 0; key[i] != '\0'; i++) {
							wprintw(scr, "$%02X%s", key[i], (key[i+1] != '\0') ? ", " : "");
						}
						wmove(scr, y, x);
						#endif
					}
					break;
			}
		} else {
			if (step) {
				step = !(c == 18);
				step_key = (c == 19);
			}
		}
		addr[STEP_ADDR] = step;
		#if keypoll
		pthread_mutex_unlock(&mutex);
		#endif
		#else
		pthread_mutex_lock(&main_mutex);
		pthread_cond_wait(&main_cond, &main_mutex);
		pthread_mutex_unlock(&main_mutex);
		#endif
	}
	endwin();
#if bench
	if (threads_done == THREADS) {
		double tm_sec, tm_usec, tm[THREADS], ttm;
		#if getclk
		double clkspd;
		double mhz;
		#endif
		double ips[THREADS];
		double ipst;
		for (int i = 0; i < THREADS; i++) {
			tm_sec = (en[i].tv_sec - str[i].tv_sec);
			tm_usec = (en[i].tv_usec-str[i].tv_usec);
			tm[i] = (tm_sec*1000000)+(tm_usec);
			ips[i] = inst[i]/tm[i];
			if (i) {
				inss += inst[i];
				ttm += tm[i];
				ipst += ips[i];
				#if getclk
				tclk += clk[i];
				#endif
			} else {
				inss = inst[i];
				ttm = tm[i];
				ipst = ips[i];
				#if getclk
				tclk = clk[i];
				#endif
			}
			#if getclk
			clkspd = (tm[i]/1000000)*1000000/clk[i];
			mhz = 1000000.0/clkspd/1000000;
			#endif
			sprintf(tmp, "Instructions executed for thread %i: %"PRIu64", Instructions per Second for thread %i in MIPS: %f, tm: %f\n", i, inst[i], i, ips[i], tm[i]/1000000);
			fwrite(tmp, sizeof(char), strlen(tmp), stdout);
		}
		sprintf(tmp, "Total Instructions executed: %"PRIu64", Total Instructions per Second in MIPS: %f", inss, ipst);
		fwrite(tmp, sizeof(char), strlen(tmp), stdout);
		#if getclk
		clkspd = (ttm/1000000)*1000000/tclk;
		mhz = 1000000.0/clkspd/1000000;
		sprintf(tmp, ", Clock cycles: %"PRIu64", Clock Speed in MHz: %f", tclk, mhz);
		fwrite(tmp, sizeof(char), strlen(tmp), stdout);
		#endif
		sprintf(tmp, ", tm: %f\n", ttm/1000000);
		fwrite(tmp, sizeof(char), strlen(tmp), stdout);
		fflush(stdout);
		free(tmp);
	}
#endif
	free(addr);
	return 0;
}