Start optimizing the emulator.

I also added a new input testing program called
input-3.s, which contains a mostly working editor.

1 files changed, 110 insertions, 84 deletions

diff --git a/sux.c b/sux.c
index 1fc8fe2..8cfecdb 100644
--- a/sux.c
+++ b/sux.c
@@ -14,18 +14,21 @@
 #endif
 
 #define THREADS	1
-#define BENCH_INST 100000000*THREADS
+#define BENCH_INST 100000000 << THREADS-1
 #define CTRL_ADDR 0xC000
 #define TX_ADDR 0xC001
 #define RX_ADDR 0xC002
 #define CURSES_BACKSPACE 0x7F
 
+#define setflag(flag, bit) (flag) ? (cpu->ps |= (bit << (thread << 3))) : (cpu->ps &= ~(bit << (thread << 3)))
+
 uint64_t clk[THREADS];	/* Per Thread Clock cycles. */
 uint64_t tclk;		/* Total Clock cycles. */
 uint64_t inst[THREADS];
 uint64_t inss;
 uint8_t threads_done = 0;
 uint8_t kbd_rdy = 0;
+uint8_t kbd_ln = 0;
 uint8_t wai = 0;
 uint8_t irq = 0;
 #if !bench
@@ -85,7 +88,7 @@ void *run(void *args) {
 			addr[(cpu->stk_st[thread] << 16)+cpu->sp[thread]] = (uint64_t)cpu->ps >> 8*thread;
 			cpu->sp[thread]--;
 			cpu->i[thread] = 1;
-			(cpu->i[thread]) ? (cpu->ps |= (I << 8*thread)) : (cpu->ps &= ~(I << 8*thread));
+			setflag(cpu->i[thread], I);
 			cpu->pc[thread] = (uint64_t)addr[0xFFA0]
 					| (uint64_t)addr[0xFFA1] << 8
 					| (uint64_t)addr[0xFFA2] << 16
@@ -314,7 +317,15 @@ void *run(void *args) {
 				break;
 
 		}
-		mvwprintw(scr, 29, 0, "address: $%016llx\r", address);
+		mvwprintw(scr, 29, 0, "address: $%016llx, scr_row: %02u, scr_col: %02u, scr_lnst: $%04x, scr_lncnt: $%04x\r", address, addr[0], addr[1], addr[2] | (addr[3] << 8), addr[4] | (addr[5] << 8));
+		mvwprintw(scr, 32, 0, "%02x %02x %02x %02x %02x %02x %02x %02x "
+				      "%02x %02x %02x %02x %02x %02x %02x %02x\r"
+				       , addr[0x4000], addr[0x4001], addr[0x4002], addr[0x4003], addr[0x4004], addr[0x4005], addr[0x4006], addr[0x4007]
+				       , addr[0x4008], addr[0x4009], addr[0x400A], addr[0x400B], addr[0x400C], addr[0x400D], addr[0x400E], addr[0x400F]);
+		mvwprintw(scr, 33, 0, "%02x %02x %02x %02x %02x %02x %02x %02x "
+				      "%02x %02x %02x %02x %02x %02x %02x %02x\r"
+				       , addr[0x4010], addr[0x4011], addr[0x4012], addr[0x4013], addr[0x4014], addr[0x4015], addr[0x4016], addr[0x4017]
+				       , addr[0x4018], addr[0x4019], addr[0x401A], addr[0x401B], addr[0x401C], addr[0x401D], addr[0x401E], addr[0x401F]);
 		wrefresh(scr);
 		#if keypoll
 		pthread_mutex_unlock(&mutex);
@@ -345,16 +356,17 @@ void *run(void *args) {
 				cpu->n[thread] = (sum >> 63);
 				cpu->v[thread] = !((cpu->a[thread]^value) & 0x8000000000000000) && ((cpu->a[thread]^sum) & 0x8000000000000000);
 				cpu->c[thread] = (sum < value);
-				(cpu->z[thread]) ? (cpu->ps |= (Z << 8*thread)) : (cpu->ps &= ~(Z << 8*thread));
-				(cpu->n[thread]) ? (cpu->ps |= (N << 8*thread)) : (cpu->ps &= ~(N << 8*thread));
-				(cpu->v[thread]) ? (cpu->ps |= (V << 8*thread)) : (cpu->ps &= ~(V << 8*thread));
-				(cpu->c[thread]) ? (cpu->ps |= (C << 8*thread)) : (cpu->ps &= ~(C << 8*thread));
+				setflag(cpu->z[thread], Z);
+				setflag(cpu->n[thread], N);
+				setflag(cpu->v[thread], V);
+				setflag(cpu->c[thread], C);
+			setflag(cpu->i[thread], I);
 				break;
 			case PHB: /* PusH B register to stack. */
 				tmp = addr[cpu->pc[thread]++];
 				if (tmp > 7)
 					tmp = 7;
-				for (int8_t i = tmp*8; i >= 0; i-=8) {
+				for (int8_t i = tmp<<3; i >= 0; i-=8) {
 					if (i)
 						addr[(cpu->stk_st[thread] << 16)+cpu->sp[thread]] = (uint64_t)cpu->b[thread] >> i;
 					else
@@ -366,7 +378,7 @@ void *run(void *args) {
 				tmp = addr[cpu->pc[thread]++];
 				if (tmp > 7)
 					tmp = 7;
-				for (int8_t i = tmp*8; i >= 0; i-=8) {
+				for (int8_t i = tmp<<3; i >= 0; i-=8) {
 					if (i)
 						addr[(cpu->stk_st[thread] << 16)+cpu->sp[thread]] = (uint64_t)cpu->ps >> i;
 					else
@@ -378,7 +390,7 @@ void *run(void *args) {
 				tmp = addr[cpu->pc[thread]++];
 				if (tmp > 7)
 					tmp = 7;
-				for (int8_t i = tmp*8; i >= 0; i-=8) {
+				for (int8_t i = tmp<<3; i >= 0; i-=8) {
 					if (i)
 						addr[(cpu->stk_st[thread] << 16)+cpu->sp[thread]] = (uint64_t)cpu->a[thread] >> i;
 					else
@@ -390,7 +402,7 @@ void *run(void *args) {
 				tmp = addr[cpu->pc[thread]++];
 				if (tmp > 7)
 					tmp = 7;
-				for (int8_t i = tmp*8; i >= 0; i-=8) {
+				for (int8_t i = tmp<<3; i >= 0; i-=8) {
 					if (i)
 						addr[(cpu->stk_st[thread] << 16)+cpu->sp[thread]] = (uint64_t)cpu->y[thread] >> i;
 					else
@@ -451,14 +463,14 @@ void *run(void *args) {
 					cpu->z[thread] = (cpu->x[thread] == 0);
 					cpu->n[thread] = (cpu->x[thread] >> 63);
 				}
-				(cpu->z[thread]) ? (cpu->ps |= (Z << 8*thread)) : (cpu->ps &= ~(Z << 8*thread));
-				(cpu->n[thread]) ? (cpu->ps |= (N << 8*thread)) : (cpu->ps &= ~(N << 8*thread));
+				setflag(cpu->z[thread], Z);
+				setflag(cpu->n[thread], N);
 				break;
 			case PHX: /* PusH X register to stack. */
 				tmp = addr[cpu->pc[thread]++];
 				if (tmp > 7)
 					tmp = 7;
-				for (int8_t i = tmp*8; i >= 0; i-=8) {
+				for (int8_t i = tmp<<3; i >= 0; i-=8) {
 					if (i)
 						addr[(cpu->stk_st[thread] << 16)+cpu->sp[thread]] = (uint64_t)cpu->x[thread] >> i;
 					else
@@ -481,17 +493,17 @@ void *run(void *args) {
 				cpu->n[thread] = (sum >> 63);
 				cpu->v[thread] = ((cpu->a[thread]^value) & 0x8000000000000000) && ((cpu->a[thread]^sum) & 0x8000000000000000);
 				cpu->c[thread] = (sum > value);
-				(cpu->z[thread]) ? (cpu->ps |= (Z << 8*thread)) : (cpu->ps &= ~(Z << 8*thread));
-				(cpu->n[thread]) ? (cpu->ps |= (N << 8*thread)) : (cpu->ps &= ~(N << 8*thread));
-				(cpu->v[thread]) ? (cpu->ps |= (V << 8*thread)) : (cpu->ps &= ~(V << 8*thread));
-				(cpu->c[thread]) ? (cpu->ps |= (C << 8*thread)) : (cpu->ps &= ~(C << 8*thread));
+				setflag(cpu->z[thread], Z);
+				setflag(cpu->n[thread], N);
+				setflag(cpu->v[thread], V);
+				setflag(cpu->c[thread], C);
 				cpu->a[thread] = sum;
 				break;
 			case PLB: /* PuLl B register from stack. */
 				tmp = addr[cpu->pc[thread]++];
 				if (tmp > 7)
 					tmp = 7;
-				for (uint8_t i = 0; i < (tmp+1)*8; i+=8) {
+				for (uint8_t i = 0; i < (tmp+1)<<3; i+=8) {
 					cpu->sp[thread]++;
 					if (i)
 						cpu->b[thread] += (uint64_t)addr[(cpu->stk_st[thread] << 16)+cpu->sp[thread]] << i;
@@ -503,7 +515,7 @@ void *run(void *args) {
 				tmp = addr[cpu->pc[thread]++];
 				if (tmp > 7)
 					tmp = 7;
-				for (uint8_t i = 0; i < (tmp+1)*8; i+=8) {
+				for (uint8_t i = 0; i < (tmp+1)<<3; i+=8) {
 					cpu->sp[thread]++;
 					if (i)
 						cpu->ps += (uint64_t)addr[(cpu->stk_st[thread] << 16)+cpu->sp[thread]] << i;
@@ -515,7 +527,7 @@ void *run(void *args) {
 				tmp = addr[cpu->pc[thread]++];
 				if (tmp > 7)
 					tmp = 7;
-				for (uint8_t i = 0; i < (tmp+1)*8; i+=8) {
+				for (uint8_t i = 0; i < (tmp+1)<<3; i+=8) {
 					cpu->sp[thread]++;
 					if (i)
 						cpu->a[thread] += (uint64_t)addr[(cpu->stk_st[thread] << 16)+cpu->sp[thread]] << i;
@@ -527,7 +539,7 @@ void *run(void *args) {
 				tmp = addr[cpu->pc[thread]++];
 				if (tmp > 7)
 					tmp = 7;
-				for (uint8_t i = 0; i < (tmp+1)*8; i+=8) {
+				for (uint8_t i = 0; i < (tmp+1)<<3; i+=8) {
 					cpu->sp[thread]++;
 					if (i)
 						cpu->y[thread] += (uint64_t)addr[(cpu->stk_st[thread] << 16)+cpu->sp[thread]] << i;
@@ -539,7 +551,7 @@ void *run(void *args) {
 				tmp = addr[cpu->pc[thread]++];
 				if (tmp > 7)
 					tmp = 7;
-				for (uint8_t i = 0; i < (tmp+1)*8; i+=8) {
+				for (uint8_t i = 0; i < (tmp+1)<<3; i+=8) {
 					cpu->sp[thread]++;
 					if (i)
 						cpu->x[thread] += (uint64_t)addr[(cpu->stk_st[thread] << 16)+cpu->sp[thread]] << i;
@@ -555,7 +567,7 @@ void *run(void *args) {
 					stksize = 24;
 				else
 					stksize = 0;
-				for (int8_t i = 24; i >= 0; i-=8) {
+				for (int8_t i = stksize; i >= 0; i-=8) {
 					if (i)
 						addr[(cpu->stk_st[thread] << 16)+cpu->sp[thread]] = (uint64_t)cpu->pc[thread] >> i;
 					else
@@ -574,21 +586,21 @@ void *run(void *args) {
 				cpu->a[thread] &= value;
 				cpu->z[thread] = (value == 0);
 				cpu->n[thread] = (value >> 63);
-				(cpu->z[thread]) ? (cpu->ps |= (Z << 8*thread)) : (cpu->ps &= ~(Z << 8*thread));
-				(cpu->n[thread]) ? (cpu->ps |= (N << 8*thread)) : (cpu->ps &= ~(N << 8*thread));
+				setflag(cpu->z[thread], Z);
+				setflag(cpu->n[thread], N);
 				break;
 			case STT: /* STart Thread. */
 				cpu->crt |= value;
 				for (uint8_t i = 0; i < 7; i++) {
 					if ((value >> i) & 1) {
-						address = (uint64_t)addr[tv+(8*i)]
-								| (uint64_t)addr[tv+1+(8*i)] << 8
-								| (uint64_t)addr[tv+2+(8*i)] << 16
-								| (uint64_t)addr[tv+3+(8*i)] << 24
-								| (uint64_t)addr[tv+4+(8*i)] << 32
-								| (uint64_t)addr[tv+5+(8*i)] << 40
-								| (uint64_t)addr[tv+6+(8*i)] << 48
-								| (uint64_t)addr[tv+7+(8*i)] << 56;
+						address = (uint64_t)addr[tv+(i<<3)]
+								| (uint64_t)addr[tv+1+(i<<3)] << 8
+								| (uint64_t)addr[tv+2+(i<<3)] << 16
+								| (uint64_t)addr[tv+3+(i<<3)] << 24
+								| (uint64_t)addr[tv+4+(i<<3)] << 32
+								| (uint64_t)addr[tv+5+(i<<3)] << 40
+								| (uint64_t)addr[tv+6+(i<<3)] << 48
+								| (uint64_t)addr[tv+7+(i<<3)] << 56;
 						cpu->pc[i+1] = address;
 					}
 				}
@@ -608,12 +620,12 @@ void *run(void *args) {
 				cpu->a[thread] |= value;
 				cpu->z[thread] = (value == 0);
 				cpu->n[thread] = (value >> 63);
-				(cpu->z[thread]) ? (cpu->ps |= (Z << 8*thread)) : (cpu->ps &= ~(Z << 8*thread));
-				(cpu->n[thread]) ? (cpu->ps |= (N << 8*thread)) : (cpu->ps &= ~(N << 8*thread));
+				setflag(cpu->z[thread], Z);
+				setflag(cpu->n[thread], N);
 				break;
 			case SEI: /* SEt Interrupt. */
 				cpu->i[thread] = 1;
-				(cpu->ps |= (I << 8*thread));
+				setflag(cpu->i[thread], I);
 				break;
 			case BNG: /* BNG Absolute. */
 			case 0x74: /* BNG Zero Matrix. */
@@ -630,12 +642,12 @@ void *run(void *args) {
 				cpu->a[thread] ^= value;
 				cpu->z[thread] = (value == 0);
 				cpu->n[thread] = (value >> 63);
-				(cpu->z[thread]) ? (cpu->ps |= (Z << 8*thread)) : (cpu->ps &= ~(Z << 8*thread));
-				(cpu->n[thread]) ? (cpu->ps |= (N << 8*thread)) : (cpu->ps &= ~(N << 8*thread));
+				setflag(cpu->z[thread], Z);
+				setflag(cpu->n[thread], N);
 				break;
 			case CLI: /* CLear Interrupt. */
 				cpu->i[thread] = 0;
-				(cpu->ps &= ~(I << 8*thread));
+				setflag(cpu->i[thread], I);
 				break;
 			case BCS: /* BCS Absolute. */
 			case 0x84: /* BCS Zero Matrix. */
@@ -654,13 +666,13 @@ void *run(void *args) {
 				cpu->n[thread] = (sum >> 63);
 				cpu->c[thread] = cpu->a[thread] >> 64-value;
 				cpu->a[thread] = sum;
-				(cpu->z[thread]) ? (cpu->ps |= (Z << 8*thread)) : (cpu->ps &= ~(Z << 8*thread));
-				(cpu->n[thread]) ? (cpu->ps |= (N << 8*thread)) : (cpu->ps &= ~(N << 8*thread));
-				(cpu->c[thread]) ? (cpu->ps |= (C << 8*thread)) : (cpu->ps &= ~(C << 8*thread));
+				setflag(cpu->z[thread], Z);
+				setflag(cpu->n[thread], N);
+				setflag(cpu->c[thread], C);
 				break;
 			case SEC: /* SEt Carry flag.*/
 				cpu->c[thread] = 1;
-				(cpu->ps |= (C << 8*thread));
+				setflag(cpu->c[thread], C);
 				break;
 			case STA: /* STA Absolute. */
 			case STY: /* STY Absolute. */
@@ -760,7 +772,11 @@ void *run(void *args) {
 								break;
 						}
 					} else {
-						if (addr[address] == CURSES_BACKSPACE || addr[address] == '\b') {
+						if (addr[address] == 0xC) {
+							x=0,y=0;
+							wclear(scr);
+							wmove(scr, y, x);
+						} else if (addr[address] == CURSES_BACKSPACE || addr[address] == '\b') {
 							if (x > 0) {
 								x--;
 								wmove(scr, y, x);
@@ -820,6 +836,7 @@ void *run(void *args) {
 								else
 									x = ((bcd[1]*10) + bcd[0]);
 								mvwprintw(scr, 30, 0, "x: %i, y: %i  ", x, y);
+								mvwprintw(scr, 31, 0, "bcd[3-2]: {%u, %u}, bcd[1-0]: {%u, %u}", bcd[3], bcd[2], bcd[1], bcd[0]);
 								wrefresh(scr);
 								idx = 3;
 								bcd[0] = 0;
@@ -893,9 +910,9 @@ void *run(void *args) {
 				cpu->n[thread] = (sum >> 63);
 				cpu->c[thread] = cpu->a[thread] & 1;
 				cpu->a[thread] = sum;
-				(cpu->z[thread]) ? (cpu->ps |= (Z << 8*thread)) : (cpu->ps &= ~(Z << 8*thread));
-				(cpu->n[thread]) ? (cpu->ps |= (N << 8*thread)) : (cpu->ps &= ~(N << 8*thread));
-				(cpu->c[thread]) ? (cpu->ps |= (C << 8*thread)) : (cpu->ps &= ~(C << 8*thread));
+				setflag(cpu->z[thread], Z);
+				setflag(cpu->n[thread], N);
+				setflag(cpu->c[thread], C);
 				break;
 			case ASR: /* ASR Immediate. */
 			case ARB: /* Arithmetic shift Right accumulator by B. */
@@ -909,13 +926,13 @@ void *run(void *args) {
 				cpu->n[thread] = (sum >> 63);
 				cpu->c[thread] = cpu->a[thread] & 1;
 				cpu->a[thread] = sum;
-				(cpu->z[thread]) ? (cpu->ps |= (Z << 8*thread)) : (cpu->ps &= ~(Z << 8*thread));
-				(cpu->n[thread]) ? (cpu->ps |= (N << 8*thread)) : (cpu->ps &= ~(N << 8*thread));
-				(cpu->c[thread]) ? (cpu->ps |= (C << 8*thread)) : (cpu->ps &= ~(C << 8*thread));
+				setflag(cpu->z[thread], Z);
+				setflag(cpu->n[thread], N);
+				setflag(cpu->c[thread], C);
 				break;
 			case CLC: /* CLear Carry flag. */
 				cpu->c[thread] = 0;
-				(cpu->ps &= ~(C << 8*thread));
+				setflag(cpu->c[thread], C);
 				break;
 			case LDB: /* LDB Immediate. */
 			case LDA: /* LDA Immediate. */
@@ -978,8 +995,8 @@ void *run(void *args) {
 					cpu->x[thread] = value;
 				cpu->z[thread] = (value == 0);
 				cpu->n[thread] = (value >> 63);
-				(cpu->z[thread]) ? (cpu->ps |= (Z << 8*thread)) : (cpu->ps &= ~(Z << 8*thread));
-				(cpu->n[thread]) ? (cpu->ps |= (N << 8*thread)) : (cpu->ps &= ~(N << 8*thread));
+				setflag(cpu->z[thread], Z);
+				setflag(cpu->n[thread], N);
 				break;
 			case BEQ: /* BEQ Absolute. */
 			case 0xA4: /* BEQ Zero Matrix. */
@@ -999,13 +1016,13 @@ void *run(void *args) {
 				cpu->n[thread] = (sum >> 63);
 				cpu->c[thread] = cpu->a[thread] >> (uint64_t)64-value;
 				cpu->a[thread] = sum;
-				(cpu->z[thread]) ? (cpu->ps |= (Z << 8*thread)) : (cpu->ps &= ~(Z << 8*thread));
-				(cpu->n[thread]) ? (cpu->ps |= (N << 8*thread)) : (cpu->ps &= ~(N << 8*thread));
-				(cpu->c[thread]) ? (cpu->ps |= (C << 8*thread)) : (cpu->ps &= ~(C << 8*thread));
+				setflag(cpu->z[thread], Z);
+				setflag(cpu->n[thread], N);
+				setflag(cpu->c[thread], C);
 				break;
 			case SSP: /* Set Stack Protection flag. */
 				cpu->s[thread] = 1;
-				(cpu->ps |= (S << 8*thread));
+				setflag(cpu->s[thread], S);
 				break;
 			case BNE: /* BNE Absolute. */
 			case 0xB4: /* BNE Zero Matrix. */
@@ -1025,13 +1042,13 @@ void *run(void *args) {
 				cpu->n[thread] = (sum >> 63);
 				cpu->c[thread] = cpu->a[thread] & 1;
 				cpu->a[thread] = sum;
-				(cpu->z[thread]) ? (cpu->ps |= (Z << 8*thread)) : (cpu->ps &= ~(Z << 8*thread));
-				(cpu->n[thread]) ? (cpu->ps |= (N << 8*thread)) : (cpu->ps &= ~(N << 8*thread));
-				(cpu->c[thread]) ? (cpu->ps |= (C << 8*thread)) : (cpu->ps &= ~(C << 8*thread));
+				setflag(cpu->z[thread], Z);
+				setflag(cpu->n[thread], N);
+				setflag(cpu->c[thread], C);
 				break;
 			case CSP: /* Clear Stack Protection flag. */
 				cpu->s[thread] = 0;
-				(cpu->ps &= ~(S << 8*thread));
+				setflag(cpu->s[thread], S);
 				break;
 			case BVS: /* BVS Absolute. */
 			case 0xC4: /* BVS Zero Matrix. */
@@ -1051,14 +1068,14 @@ void *run(void *args) {
 				cpu->n[thread] = (sum >> 63);
 				cpu->v[thread] = !((cpu->a[thread]^value) & 0x8000000000000000) && ((cpu->a[thread]^sum) & 0x8000000000000000);
 				cpu->c[thread] = (!((cpu->a[thread]^sum) && (cpu->a[thread]^value)) && (cpu->a[thread] >= ((uint64_t)1 << 32) && value >= ((uint64_t)1 << 32)));
-				(cpu->z[thread]) ? (cpu->ps |= (Z << 8*thread)) : (cpu->ps &= ~(Z << 8*thread));
-				(cpu->n[thread]) ? (cpu->ps |= (N << 8*thread)) : (cpu->ps &= ~(N << 8*thread));
-				(cpu->v[thread]) ? (cpu->ps |= (V << 8*thread)) : (cpu->ps &= ~(V << 8*thread));
-				(cpu->c[thread]) ? (cpu->ps |= (C << 8*thread)) : (cpu->ps &= ~(C << 8*thread));
+				setflag(cpu->z[thread], Z);
+				setflag(cpu->n[thread], N);
+				setflag(cpu->v[thread], V);
+				setflag(cpu->c[thread], C);
 				break;
 			case SEV: /* SEt oVerflow flag. */
 				cpu->v[thread] = 1;
-				(cpu->ps |= (V << 8*thread));
+				setflag(cpu->v[thread], V);
 				break;
 			case BVC: /* BVC Absolute. */
 			case 0xD4: /* BVC Zero Matrix. */
@@ -1079,12 +1096,12 @@ void *run(void *args) {
 				cpu->a[thread] = sum;
 				cpu->z[thread] = (sum == 0);
 				cpu->n[thread] = (sum >> 63);
-				(cpu->z[thread]) ? (cpu->ps |= (Z << 8*thread)) : (cpu->ps &= ~(Z << 8*thread));
-				(cpu->n[thread]) ? (cpu->ps |= (N << 8*thread)) : (cpu->ps &= ~(N << 8*thread));
+				setflag(cpu->z[thread], Z);
+				setflag(cpu->n[thread], N);
 				break;
 			case CLV: /* CLear oVerflow flag. */
 				cpu->v[thread] = 0;
-				(cpu->ps &= ~(V << 8*thread));
+				setflag(cpu->v[thread], V);
 				break;
 			case RTS: /* ReTurn from Subroutine. */
 				if (addrsize)
@@ -1138,10 +1155,10 @@ void *run(void *args) {
 				cpu->v[thread] = ((reg^value) & 0x8000000000000000) && ((reg^sum) & 0x8000000000000000);
 				cpu->z[thread] = (sum == 0) ? 1 : 0;
 				cpu->c[thread] = (sum > value) ? 1 : 0;
-				(cpu->n[thread]) ? (cpu->ps |= (N << 8*thread)) : (cpu->ps &= ~(N << 8*thread));
-				(cpu->v[thread]) ? (cpu->ps |= (V << 8*thread)) : (cpu->ps &= ~(V << 8*thread));
-				(cpu->z[thread]) ? (cpu->ps |= (Z << 8*thread)) : (cpu->ps &= ~(Z << 8*thread));
-				(cpu->c[thread]) ? (cpu->ps |= (C << 8*thread)) : (cpu->ps &= ~(C << 8*thread));
+				setflag(cpu->n[thread], N);
+				setflag(cpu->v[thread], V);
+				setflag(cpu->z[thread], Z);
+				setflag(cpu->c[thread], C);
 				break;
 			case ENT: /* ENd Thread. */
 				cpu->crt &= ~value;
@@ -1181,8 +1198,8 @@ void *run(void *args) {
 					cpu->z[thread] = (cpu->x[thread] == 0);
 					cpu->n[thread] = (cpu->x[thread] >> 63);
 				}
-				(cpu->z[thread]) ? (cpu->ps |= (Z << 8*thread)) : (cpu->ps &= ~(Z << 8*thread));
-				(cpu->n[thread]) ? (cpu->ps |= (N << 8*thread)) : (cpu->ps &= ~(N << 8*thread));
+				setflag(cpu->z[thread], Z);
+				setflag(cpu->n[thread], N);
 				break;
 			case 0x04: /* JMP Indirect. */
 			case 0x14: /* JMP Indexed Indirect. */
@@ -1212,8 +1229,8 @@ void *run(void *args) {
 					cpu->z[thread] = (cpu->x[thread] == 0);
 					cpu->n[thread] = (cpu->x[thread] >> 63);
 				}
-				(cpu->z[thread]) ? (cpu->ps |= (Z << 8*thread)) : (cpu->ps &= ~(Z << 8*thread));
-				(cpu->n[thread]) ? (cpu->ps |= (N << 8*thread)) : (cpu->ps &= ~(N << 8*thread));
+				setflag(cpu->z[thread], Z);
+				setflag(cpu->n[thread], N);
 				break;
 			case JSL: /* Jump to Subroutine Long. */
 				if (addrsize)
@@ -1253,17 +1270,17 @@ void *run(void *args) {
 				addr[address]--;
 				break;
 			case BRK: /* BReaK. */
-				for (int8_t i = 56; i >= 0; i-=8) {
+				for (int8_t i = stksize; i >= 0; i-=8) {
 					if (i)
-						addr[(cpu->stk_st[thread] << 16)+cpu->sp[thread]] = (uint64_t)cpu->pc[thread]-1 >> i;
+						addr[(cpu->stk_st[thread] << 16)+cpu->sp[thread]] = (uint64_t)cpu->pc[thread] >> i;
 					else
-						addr[(cpu->stk_st[thread] << 16)+cpu->sp[thread]] = (uint64_t)cpu->pc[thread]-1 & 0xFF;
+						addr[(cpu->stk_st[thread] << 16)+cpu->sp[thread]] = (uint64_t)cpu->pc[thread] & 0xFF;
 					cpu->sp[thread]--;
 				}
-				addr[(cpu->stk_st[thread] << 16)+cpu->sp[thread]] = (uint64_t)cpu->ps >> 8*thread;
+				addr[(cpu->stk_st[thread] << 16)+cpu->sp[thread]] = (uint64_t)cpu->ps >> thread << 3;
 				cpu->sp[thread]--;
 				cpu->i[thread] = 1;
-				(cpu->i[thread]) ? (cpu->ps |= (I << 8*thread)) : (cpu->ps &= ~(I << 8*thread));
+				setflag(cpu->i[thread], I);
 				cpu->pc[thread] = (uint64_t)addr[0xFFE0]
 						| (uint64_t)addr[0xFFE1] << 8
 						| (uint64_t)addr[0xFFE2] << 16
@@ -1286,6 +1303,13 @@ void *run(void *args) {
 				break;
 		}
 		ins++;
+		/*if (!addr[CTRL_ADDR])
+			kbd_ln = 0;
+		else
+			kbd_ln = 1;
+		if (kbd_ln)
+			usleep(16666);
+			/*usleep(500000);*/
 	#if debug && !bench
 		#if keypoll
 		pthread_mutex_lock(&mutex);
@@ -1409,6 +1433,7 @@ int main(int argc, char **argv) {
 			curs_set(1);
 			c = 0;
 			addr[CTRL_ADDR] = 0;
+			kbd_ln = 0;
 		}
 		#if keypoll
 		pthread_mutex_lock(&mutex);
@@ -1426,7 +1451,8 @@ int main(int argc, char **argv) {
 			default:
 				addr[RX_ADDR] = (uint8_t)c;
 				addr[CTRL_ADDR] = 1;
-				kbd_rdy = 1;
+				if (c == '\n')
+					kbd_ln = 1;
 				#if !keypoll
 				pthread_mutex_lock(&mutex);
 				pthread_cond_signal(&cond);