Firestorm: CCMP (register, 32-bit) measurements

Code:

  ccmp w0, w1, #0, hi

Initialization

  mov x0, 1
  mov x1, 2

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 1.000

Issues: 1.000

Integer unit issues: 1.000

Load/store unit issues: 0.000

SIMD/FP unit issues: 0.000

All non-zero counters (first 10 of 64 runs)

retire uop (01)	cycle (02)	03	l2 tlb miss data (0b)	18	1e	3f	4d	51	schedule uop (52)	schedule int uop (53)	dispatch int uop (56)	int uops in schedulers (59)	60	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map int uop inputs (7f)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst int alu (97)	9f	ld unit uop (a6)	st unit uop (a7)	l1d cache writeback (a8)	ac	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? int output thing (e9)	f5	f6	f7	f8	fd
1004	1035	8	0	0	0	61	917	25	1000	1000	1000	62250	0	1035	1035	805	3	882	1000	1000	3000	1035	104	1	1	1001	1000	1000	0	0	0	0	73	1	27	1	1	990	1000	1036	1036	1036	1036	1036
1004	1035	8	0	0	0	61	917	25	1000	1000	1000	62250	0	1035	1035	805	3	882	1000	1000	3000	1035	104	1	1	1001	1000	1000	0	0	0	0	73	1	27	1	1	990	1000	1036	1036	1036	1036	1036
1004	1035	8	0	0	0	61	917	25	1000	1000	1000	62250	1	1035	1035	805	3	882	1000	1000	3000	1035	104	1	1	1001	1000	1000	0	0	0	0	73	1	27	1	1	990	1000	1036	1036	1036	1036	1036
1004	1035	8	0	0	0	61	917	25	1000	1000	1000	62250	1	1035	1035	805	3	882	1000	1000	3000	1035	104	1	1	1001	1000	1000	0	0	0	0	73	1	27	1	1	990	1000	1036	1036	1036	1036	1036
1004	1035	7	0	0	0	61	917	25	1000	1000	1000	62250	1	1035	1035	805	3	882	1000	1000	3000	1035	104	1	1	1001	1000	1000	0	0	0	0	73	1	27	1	1	990	1000	1036	1036	1036	1036	1036
1004	1035	8	0	0	0	61	917	25	1000	1000	1000	62250	1	1035	1035	805	3	882	1000	1000	3000	1035	104	1	1	1001	1000	1000	0	0	0	0	73	1	27	1	1	990	1000	1036	1036	1036	1036	1036
1004	1035	8	0	0	0	61	917	25	1000	1000	1000	62250	1	1035	1035	805	3	882	1000	1000	3000	1035	104	1	1	1001	1000	1000	0	0	0	0	73	1	27	1	1	990	1000	1036	1036	1036	1036	1036
1004	1035	7	0	0	0	61	917	25	1000	1000	1000	62250	1	1035	1035	805	3	882	1000	1000	3000	1035	104	1	1	1001	1000	1000	0	0	0	0	73	1	27	1	1	990	1000	1036	1036	1036	1036	1036
1004	1035	8	0	0	0	61	917	25	1000	1000	1000	62250	0	1035	1035	805	3	882	1000	1000	3000	1035	104	1	1	1001	1000	1000	0	0	0	0	73	1	27	1	1	990	1000	1036	1036	1036	1036	1036
1004	1035	8	0	0	0	61	917	25	1000	1000	1000	62250	0	1035	1035	805	3	882	1000	1000	3000	1035	104	1	1	1001	1000	1000	0	0	0	0	73	1	27	1	1	990	1000	1036	1036	1036	1036	1036

Test 2: Latency 3->1

Chain cycles: 1

Code:

  ccmp w0, w1, #0, hi
  cset x0, cc

Initialization

  mov x0, 1
  mov x1, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code, minus 1 chain cycle): 1.0035

All non-zero counters (first 10 of 64 runs)

retire uop (01)	cycle (02)	03	mmu table walk data (08)	l2 tlb miss data (0b)	18	19	1e	1f	3f	4d	51	schedule uop (52)	schedule int uop (53)	dispatch int uop (56)	int uops in schedulers (59)	60	69	6a	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map int uop inputs (7f)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	9f	l1d tlb access (a0)	l1d tlb miss (a1)	ld unit uop (a6)	l1d cache writeback (a8)	a9	ac	c2	cf	d0	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? int output thing (e9)	? int retires (ef)	f5	f6	f7	f8	fd
20204	20035	150	0	0	0	0	0	0	61	19926	25	20100	20100	20100	1297150	1	49	16955	20035	20035	17406	3	17481	20100	20200	40200	20035	104	1	1	20201	100	99	100	20100	20100	0	0	0	0	0	0	0	1310	1	4	34	2	2	19992	20000	10100	20036	20036	20036	20036	20036
20204	20035	150	0	0	0	0	0	0	84	19926	25	20100	20100	20100	1297150	1	49	16955	20035	20035	17406	3	17481	20100	20200	40200	20035	104	1	1	20201	100	99	100	20100	20100	0	0	0	0	0	0	0	1310	1	2	28	2	2	19992	20000	10100	20036	20036	20036	20036	20036
20204	20035	150	0	0	0	0	0	0	82	19926	25	20100	20100	20100	1297150	1	49	16955	20035	20035	17406	3	17481	20100	20200	40200	20035	104	1	1	20201	100	99	100	20100	20100	0	0	0	0	0	0	0	1310	1	2	28	2	2	19992	20000	10100	20036	20036	20036	20036	20036
20204	20035	150	0	0	0	0	0	0	84	19926	25	20100	20100	20100	1297150	1	49	16955	20035	20035	17406	3	17481	20100	20200	40200	20035	104	1	1	20201	100	99	100	20100	20100	0	0	0	0	0	0	0	1310	1	2	28	2	2	19992	20000	10100	20036	20036	20036	20036	20036
20204	20035	150	0	0	0	0	0	0	107	19926	25	20100	20100	20100	1297150	1	49	16955	20035	20035	17406	3	17481	20100	20200	40200	20035	104	1	1	20201	100	99	100	20100	20100	0	0	0	0	0	0	0	1310	1	2	28	2	2	19992	20000	10100	20036	20036	20036	20036	20036
20204	20035	150	0	0	0	0	0	0	61	19926	25	20100	20100	20100	1297150	1	49	16955	20035	20035	17406	3	17481	20100	20200	40200	20035	104	1	1	20201	100	99	100	20100	20100	0	0	0	0	0	0	0	1310	1	2	28	2	2	19992	20000	10100	20036	20036	20036	20036	20036
20204	20035	150	0	0	0	0	0	0	128	19926	25	20100	20100	20100	1297150	1	49	16955	20035	20035	17406	3	17481	20100	20200	40200	20035	104	1	1	20201	100	99	100	20100	20100	0	0	0	0	0	0	0	1310	1	2	28	2	2	19992	20000	10100	20036	20036	20036	20036	20036
20204	20035	149	0	0	0	0	0	0	400	19926	25	20100	20100	20100	1297150	1	49	16955	20035	20035	17406	3	17481	20100	20200	40200	20035	104	1	1	20201	100	99	100	20100	20100	0	0	0	0	0	0	0	1310	1	2	28	2	2	19992	20000	10100	20036	20036	20036	20036	20036
20204	20035	150	0	0	0	0	0	0	1066	19926	25	20100	20100	20100	1297150	1	49	16955	20035	20035	17406	3	17481	20100	20200	40200	20035	104	1	1	20201	100	99	100	20100	20100	0	0	0	0	0	0	0	1310	1	2	28	2	2	19992	20000	10100	20036	20036	20036	20036	20036
20204	20035	150	0	0	0	0	0	0	1501	19926	25	20100	20100	20100	1297150	1	49	16955	20035	20035	17406	3	17481	20100	20200	40200	20035	104	1	1	20201	100	99	100	20100	20100	0	0	0	0	0	0	0	1310	1	2	28	2	2	19992	20000	10100	20036	20036	20036	20036	20036

1000 unrolls and 10 iterations

Result (median cycles for code, minus 1 chain cycle): 1.0035

All non-zero counters (first 10 of 64 runs)

retire uop (01)	cycle (02)	03	1e	3f	4d	51	schedule uop (52)	schedule int uop (53)	dispatch int uop (56)	int uops in schedulers (59)	60	69	6a	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map int uop inputs (7f)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	9f	ld unit uop (a6)	l1d cache writeback (a8)	ac	cd	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? int output thing (e9)	? int retires (ef)	f5	f6	f7	f8	fd
20024	20035	150	0	61	19918	25	20010	20010	20010	1297247	1	49	16955	20035	20035	17428	3	17504	20010	20020	40020	20035	104	1	1	20021	10	9	10	20010	20010	0	0	0	0	1270	1	27	2	1	19995	20000	10010	20036	20036	20036	20036	20036
20024	20035	150	0	61	19918	25	20010	20010	20010	1297247	0	49	16955	20035	20035	17428	3	17504	20010	20020	40020	20035	104	1	1	20021	10	9	10	20010	20010	0	0	0	0	1270	1	27	1	1	19995	20000	10010	20036	20036	20036	20036	20036
20024	20035	150	0	61	19918	25	20010	20010	20010	1297247	0	49	16955	20035	20035	17428	3	17504	20010	20020	40020	20035	104	1	1	20021	10	9	10	20010	20010	0	0	0	0	1270	1	27	1	1	19995	20000	10010	20036	20036	20036	20036	20036
20024	20035	150	0	61	19918	25	20010	20010	20010	1297247	0	49	16955	20035	20035	17428	3	17504	20010	20020	40020	20035	104	1	1	20021	10	9	10	20010	20010	0	0	0	0	1270	1	27	1	1	19995	20000	10010	20036	20036	20036	20036	20036
20024	20035	150	0	61	19918	25	20010	20010	20010	1297247	0	49	16955	20035	20035	17428	3	17504	20010	20020	40020	20035	104	1	1	20021	10	9	10	20010	20010	0	0	0	0	1270	2	27	1	1	19995	20000	10010	20036	20036	20036	20036	20036
20024	20035	150	0	61	19918	25	20010	20010	20010	1297247	0	49	16955	20035	20035	17428	3	17504	20010	20020	40020	20035	104	1	1	20021	10	9	10	20010	20010	0	0	0	0	1270	1	27	1	1	19995	20000	10010	20036	20036	20036	20036	20036
20024	20035	150	0	61	19918	25	20010	20010	20010	1297247	0	49	16955	20035	20035	17428	3	17504	20010	20020	40020	20035	104	1	1	20021	10	9	10	20010	20010	0	0	0	0	1270	1	27	1	1	19995	20000	10010	20036	20036	20036	20036	20036
20024	20035	150	0	61	19918	25	20010	20010	20010	1297247	0	49	16955	20035	20035	17428	3	17504	20010	20020	40020	20035	104	1	1	20021	10	9	10	20010	20010	0	0	0	0	1270	1	27	1	1	19995	20000	10010	20036	20036	20036	20036	20036
20024	20035	150	0	103	19918	25	20010	20010	20010	1297247	0	49	16955	20035	20035	17428	3	17504	20010	20020	40020	20035	104	1	1	20021	10	9	10	20010	20010	0	0	0	0	1270	1	27	1	1	19995	20000	10010	20036	20036	20036	20036	20036
20024	20035	150	0	61	19918	25	20010	20010	20010	1297247	0	49	16955	20035	20035	17428	3	17504	20010	20020	40020	20035	104	1	1	20021	10	9	10	20010	20010	0	0	0	0	1270	1	27	1	1	19995	20000	10010	20036	20036	20036	20036	20036

Test 3: Latency 3->2

Chain cycles: 1

Code:

  ccmp w0, w1, #0, hi
  cset x1, cc

Initialization

  mov x0, 1
  mov x1, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code, minus 1 chain cycle): 1.0035

All non-zero counters (first 10 of 64 runs)

retire uop (01)	cycle (02)	03	mmu table walk data (08)	1e	3f	4d	51	schedule uop (52)	schedule int uop (53)	dispatch int uop (56)	int uops in schedulers (59)	60	69	6a	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map int uop inputs (7f)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	9f	l1d cache writeback (a8)	ac	branch mispred nonspec (cb)	cf	d0	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? int output thing (e9)	? int retires (ef)	f5	f6	f7	f8	fd
20204	20035	150	0	0	518	19926	25	20100	20100	20100	1297150	1	49	16955	20035	20035	17406	3	17481	20100	20200	40200	20035	104	1	1	20201	100	99	100	20100	20100	0	0	0	1310	1	2	28	2	2	19992	20000	10100	20036	20036	20036	20036	20036
20204	20035	150	0	0	61	19926	25	20100	20100	20100	1297150	1	49	16955	20035	20035	17406	3	17481	20100	20200	40200	20035	104	1	1	20201	100	99	100	20100	20100	0	0	0	1310	1	2	28	2	2	19992	20000	10100	20036	20036	20036	20036	20036
20204	20035	150	0	0	303	19926	25	20100	20100	20100	1297150	1	49	16955	20035	20035	17406	3	17481	20100	20200	40200	20035	104	1	1	20201	100	99	100	20100	20100	0	0	0	1310	1	2	28	3	2	19992	20000	10100	20036	20036	20036	20036	20036
20204	20035	150	0	0	149	19926	25	20100	20100	20100	1297150	1	49	16955	20035	20035	17406	3	17481	20100	20200	40200	20035	104	1	1	20201	100	99	100	20100	20100	0	0	0	1310	1	1	28	2	2	19992	20000	10100	20036	20036	20036	20036	20036
20204	20035	150	0	0	126	19926	25	20100	20100	20100	1297150	0	49	16955	20035	20035	17406	3	17481	20100	20200	40200	20035	104	1	1	20201	100	99	100	20100	20100	0	0	0	1310	1	3	28	2	3	19992	20000	10100	20036	20036	20036	20036	20036
20204	20035	150	0	0	748	19926	25	20100	20100	20100	1297150	0	49	16955	20035	20035	17406	3	17481	20100	20200	40200	20035	104	1	1	20201	100	99	100	20100	20100	0	0	0	1310	1	3	28	3	2	19992	20000	10100	20036	20036	20036	20036	20036
20204	20035	149	0	0	168	19926	25	20100	20100	20100	1297150	1	49	16955	20035	20035	17406	3	17481	20100	20200	40200	20035	104	1	1	20201	100	99	100	20100	20100	0	0	0	1310	1	3	28	3	2	19992	20000	10100	20036	20036	20036	20036	20036
20204	20035	150	0	0	61	19926	25	20100	20100	20100	1297150	0	49	16955	20035	20035	17406	3	17481	20100	20200	40200	20035	104	1	1	20201	100	99	100	20100	20100	0	3	0	1310	1	2	28	3	3	19992	20000	10100	20036	20036	20036	20036	20036
20204	20035	150	0	0	149	19926	25	20100	20100	20100	1297150	0	49	16955	20035	20035	17406	3	17481	20100	20200	40200	20035	104	1	1	20201	100	99	100	20100	20100	0	0	0	1310	1	3	28	3	2	19992	20000	10100	20036	20036	20036	20036	20036
20204	20035	150	0	0	61	19926	25	20100	20100	20100	1297150	0	49	16955	20035	20035	17406	3	17481	20100	20200	40200	20035	104	1	1	20201	100	99	100	20100	20100	0	3	0	1310	1	2	28	2	3	19992	20000	10100	20036	20036	20036	20036	20036

1000 unrolls and 10 iterations

Result (median cycles for code, minus 1 chain cycle): 1.0035

All non-zero counters (first 10 of 64 runs)

retire uop (01)	cycle (02)	03	1e	3f	4d	51	schedule uop (52)	schedule int uop (53)	dispatch int uop (56)	int uops in schedulers (59)	60	69	6a	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map int uop inputs (7f)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	9f	ld unit uop (a6)	ac	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? int output thing (e9)	? int retires (ef)	f5	f6	f7	f8	fd
20024	20035	150	0	61	19918	25	20010	20010	20010	1297247	1	49	16955	20035	20035	17428	3	17504	20010	20020	40020	20035	104	1	1	20021	10	9	10	20010	20010	0	0	1270	1	27	1	1	19995	20000	10010	20036	20036	20036	20036	20036
20024	20035	150	0	61	19918	25	20010	20010	20010	1297247	0	49	16955	20035	20035	17428	3	17504	20010	20020	40020	20035	104	1	1	20021	10	9	10	20010	20010	0	0	1270	1	27	1	1	19995	20000	10010	20036	20036	20036	20036	20036
20024	20035	150	0	61	19918	25	20010	20010	20010	1297247	0	98	16955	20035	20035	17428	3	17504	20010	20020	40020	20035	104	1	1	20021	10	9	10	20010	20010	0	3	1270	1	27	1	1	19995	20000	10010	20036	20036	20036	20036	20036
20024	20035	150	0	61	19918	25	20010	20010	20010	1297247	0	49	16955	20035	20035	17428	3	17504	20010	20020	40020	20035	104	1	1	20021	10	9	10	20010	20010	0	0	1270	1	27	1	1	19995	20000	10010	20036	20036	20036	20036	20036
20024	20035	150	0	61	19918	25	20010	20010	20010	1297247	0	49	16955	20035	20035	17428	3	17504	20010	20020	40020	20035	104	1	1	20021	10	9	10	20010	20010	0	0	1270	1	27	2	1	19995	20000	10010	20036	20036	20036	20036	20036
20024	20035	150	0	61	19918	25	20010	20010	20010	1297247	0	49	16955	20035	20035	17428	3	17504	20010	20020	40020	20035	104	1	1	20021	10	9	10	20010	20010	0	0	1270	1	27	1	1	19995	20000	10010	20036	20036	20036	20036	20036
20024	20035	150	0	61	19918	25	20010	20010	20010	1297247	0	49	16955	20035	20035	17428	3	17504	20010	20020	40020	20035	104	1	1	20021	10	9	10	20010	20010	0	0	1270	1	27	1	1	19995	20000	10010	20036	20036	20036	20036	20036
20024	20035	150	0	61	19918	25	20010	20010	20010	1297247	1	49	16955	20035	20035	17428	3	17504	20010	20020	40020	20035	104	1	1	20021	10	9	10	20010	20010	0	0	1270	1	27	1	2	19995	20000	10010	20036	20036	20036	20036	20036
20024	20035	150	435	61	19918	25	20010	20010	20010	1297247	0	49	16955	20035	20035	17428	3	17504	20010	20020	40020	20035	104	1	1	20021	10	9	10	20010	20010	0	0	1270	1	27	1	1	19995	20000	10010	20036	20036	20036	20036	20036
20024	20035	150	0	61	19918	25	20010	20010	20010	1297247	0	49	16955	20035	20035	17428	3	17504	20010	20020	40020	20035	104	1	1	20021	10	9	10	20010	20010	0	0	1270	1	27	1	1	19995	20000	10010	20036	20036	20036	20036	20036

Test 4: Latency 3->3

Code:

  ccmp w0, w1, #0, hi

Initialization

  mov x0, 1
  mov x1, 2

(non-fused SUB/CBNZ loop)

100 unrolls and 100 iterations

Result (median cycles for code): 1.0035

All non-zero counters (first 10 of 64 runs)

retire uop (01)	cycle (02)	03	1e	3f	4d	51	schedule uop (52)	schedule int uop (53)	dispatch int uop (56)	int uops in schedulers (59)	60	69	6a	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map int uop inputs (7f)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst int alu (97)	9f	l1d cache writeback (a8)	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? int output thing (e9)	? int retires (ef)	f5	f6	f7	f8	fd
10204	10035	75	36	61	9920	25	10200	10200	10200	647652	1	49	6955	10035	10035	8656	3	8732	10200	10200	30200	10035	110	1	1	10201	100	99	10100	10000	0	710	2	27	2	2	9990	10100	100	10036	10036	10036	10036	10036
10204	10035	75	0	61	9920	25	10200	10200	10200	647652	1	49	6955	10035	10035	8656	3	8732	10200	10200	30200	10035	110	1	1	10201	100	99	10100	10000	0	710	2	27	2	2	9990	10100	100	10036	10036	10036	10036	10036
10204	10035	75	0	61	9920	25	10200	10200	10200	647652	1	49	6955	10035	10035	8656	3	8732	10200	10200	30200	10035	110	1	1	10201	100	99	10100	10000	0	710	2	27	2	3	9990	10100	100	10036	10036	10036	10036	10036
10204	10035	75	0	61	9920	25	10200	10200	10200	647652	1	49	6955	10035	10035	8656	3	8732	10200	10200	30200	10035	110	1	1	10201	100	99	10100	10000	0	710	2	27	2	2	9990	10100	100	10036	10036	10036	10036	10036
10204	10035	75	0	145	9920	25	10200	10200	10200	647652	1	49	6955	10035	10035	8656	3	8732	10200	10200	30200	10035	110	1	1	10201	100	99	10100	10000	0	710	2	27	2	2	9990	10100	100	10036	10036	10036	10036	10036
10204	10035	75	0	61	9920	25	10200	10200	10200	647652	1	49	6955	10035	10035	8656	3	8732	10200	10200	30200	10035	110	1	1	10201	100	99	10100	10000	0	710	2	27	2	2	9990	10100	100	10036	10036	10036	10036	10036
10204	10035	75	0	61	9920	25	10200	10200	10200	647652	1	49	6955	10035	10035	8656	3	8732	10200	10200	30200	10035	110	1	1	10201	100	99	10100	10000	0	710	2	27	2	2	9990	10100	100	10036	10036	10036	10036	10036
10204	10035	75	0	61	9920	25	10200	10200	10200	647652	1	49	6955	10035	10035	8656	3	8732	10200	10200	30200	10035	110	1	1	10201	100	99	10100	10000	0	710	3	27	2	2	9990	10100	100	10036	10036	10036	10036	10036
10204	10035	75	0	61	9920	25	10200	10200	10200	647652	1	49	6955	10035	10035	8656	3	8732	10200	10200	30200	10035	110	1	1	10201	100	99	10100	10000	0	710	2	27	2	2	9990	10100	100	10036	10036	10036	10036	10036
10204	10035	75	0	61	9920	25	10200	10200	10200	647652	1	49	6955	10035	10035	8656	3	8732	10200	10200	30200	10035	110	1	1	10201	100	99	10100	10000	0	710	2	27	2	2	9990	10100	100	10036	10036	10036	10036	10036

1000 unrolls and 10 iterations

Result (median cycles for code): 1.0035

All non-zero counters (first 10 of 64 runs)

retire uop (01)	cycle (02)	03	mmu table walk data (08)	09	18	1e	1f	3f	4d	51	schedule uop (52)	schedule int uop (53)	dispatch int uop (56)	int uops in schedulers (59)	60	69	6a	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map int uop inputs (7f)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst int alu (97)	9f	ld unit uop (a6)	l1d cache writeback (a8)	ac	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? int output thing (e9)	? int retires (ef)	f5	f6	f7	f8	fd
10024	10035	75	0	0	0	0	0	61	9918	25	10020	10020	10020	647296	0	49	6955	10035	10035	8678	3	8754	10020	10020	30020	10035	104	1	1	10021	10	9	10010	10000	0	0	0	640	2	27	2	2	9993	10010	10	10036	10118	10081	10036	10036
10024	10035	75	0	0	0	0	0	61	9918	25	10020	10020	10020	647296	0	49	6955	10035	10035	8678	3	8754	10020	10020	30020	10035	104	1	1	10021	10	9	10010	10000	0	0	0	640	2	27	2	2	9993	10010	10	10036	10036	10036	10036	10036
10024	10035	75	0	0	0	0	0	61	9918	25	10020	10020	10020	647296	0	49	6955	10035	10035	8678	3	8754	10020	10020	30020	10035	104	1	1	10021	10	9	10010	10000	0	0	102	640	2	27	2	2	9993	10010	10	10036	10036	10036	10036	10036
10024	10035	75	0	0	0	0	0	61	9918	25	10020	10020	10020	647296	0	49	6955	10035	10035	8678	3	8754	10020	10020	30020	10035	104	1	1	10021	10	9	10010	10000	0	0	0	640	2	27	2	2	9993	10010	10	10036	10036	10036	10036	10036
10024	10035	75	0	0	0	0	0	61	9918	25	10020	10020	10020	647296	0	49	6955	10035	10035	8678	3	8754	10020	10020	30020	10035	104	1	1	10021	10	9	10010	10000	0	0	0	640	2	27	2	2	9993	10010	10	10036	10036	10036	10036	10036
10024	10035	75	0	0	0	0	0	61	9918	25	10020	10020	10020	647296	1	49	6955	10035	10035	8678	3	8754	10020	10020	30020	10035	104	1	1	10021	10	9	10010	10000	0	0	0	640	2	27	3	2	9993	10010	10	10036	10036	10036	10036	10036
10024	10035	75	0	0	0	0	0	61	9918	25	10020	10020	10020	647296	0	49	6955	10035	10035	8678	3	8754	10020	10020	30020	10035	104	1	1	10021	10	9	10010	10000	0	0	0	640	2	27	2	2	9993	10010	10	10036	10036	10036	10036	10036
10024	10035	75	0	0	0	0	0	61	9918	25	10020	10020	10020	647296	0	49	6955	10035	10035	8678	3	8754	10020	10020	30020	10035	104	1	1	10021	10	9	10010	10000	0	0	0	640	2	27	2	2	9993	10010	10	10036	10036	10036	10036	10036
10024	10035	75	0	0	0	18	0	61	9918	25	10020	10020	10020	647296	0	49	6955	10035	10035	8678	3	8754	10020	10020	30020	10035	104	1	1	10021	10	9	10010	10000	0	0	0	640	2	27	2	2	9993	10010	10	10036	10036	10036	10036	10036
10024	10035	75	0	0	0	0	88	61	9918	25	10020	10020	10020	647296	0	49	6955	10035	10035	8678	3	8779	10020	10212	30020	10035	104	1	1	10021	10	9	10010	10000	0	0	0	640	2	27	2	2	9993	10010	10	10036	10036	10036	10036	10036

Test 5: throughput

Count: 8

Code:

  ands xzr, xzr, xzr
  ccmp w0, w1, #0, hi
  ands xzr, xzr, xzr
  ccmp w0, w1, #0, hi
  ands xzr, xzr, xzr
  ccmp w0, w1, #0, hi
  ands xzr, xzr, xzr
  ccmp w0, w1, #0, hi
  ands xzr, xzr, xzr
  ccmp w0, w1, #0, hi
  ands xzr, xzr, xzr
  ccmp w0, w1, #0, hi
  ands xzr, xzr, xzr
  ccmp w0, w1, #0, hi
  ands xzr, xzr, xzr
  ccmp w0, w1, #0, hi

Initialization

  mov x0, 1
  mov x1, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.6675

All non-zero counters (first 10 of 64 runs)

retire uop (01)	cycle (02)	03	19	1e	1f	3f	51	schedule uop (52)	schedule int uop (53)	dispatch int uop (56)	int uops in schedulers (59)	60	61	69	6a	6b	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map int uop inputs (7f)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	9f	l1d cache writeback (a8)	ac	cf	d0	d2	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? int output thing (e9)	? int retires (ef)	f5	f6	f7	f8	fd
160204	53408	400	0	0	0	37	25	160100	160100	160100	1063588	1	5	49	50324	0	53404	53404	33339	3	33359	160100	160200	240200	53404	66	1	1	160201	100	99	100	160100	80100	1	0	10110	5	0	1	19	1	2	53400	160000	100	53405	53405	53405	53405	53405
160204	53404	400	0	0	0	37	25	160100	160100	160100	1063588	1	0	49	50324	0	53404	53404	33339	3	33359	160100	160200	240200	53404	66	2	1	160201	100	99	100	160100	80100	0	0	10110	0	0	1	19	1	2	53400	160000	100	53405	53405	53405	53405	53405
160204	53404	400	0	0	0	37	25	160100	160100	160100	1063588	0	5	49	50324	0	53404	53404	33339	8	33395	160100	160200	240200	53404	66	1	1	160201	100	99	100	160100	80100	0	0	10110	5	0	1	19	1	2	53400	160000	100	53405	53405	53405	53405	53445
160204	53404	400	0	0	0	37	25	160100	160100	160100	1063588	1	5	49	50324	0	53404	53404	33339	3	33359	160100	160200	240200	53404	66	1	1	160201	100	99	100	160100	80100	0	0	10110	0	0	1	19	1	1	53400	160000	100	53405	53405	53405	53405	53405
160204	53404	400	0	0	0	37	25	160100	160100	160209	1063588	1	5	49	50324	0	53404	53404	33339	3	33359	160100	160200	240200	53404	66	1	1	160201	100	99	100	160100	80100	0	0	10110	5	1	1	19	1	2	53400	160000	100	53405	53405	53405	53405	53405
160204	53404	400	0	0	0	37	25	160100	160100	160100	1063588	0	5	49	50324	0	53404	53404	33339	3	33359	160100	160200	240200	53404	66	1	1	160201	100	99	100	160100	80100	0	0	10110	5	1	1	19	1	2	53400	160000	100	53405	53405	53405	53405	53405
160204	53404	400	0	0	0	37	25	160100	160100	160100	1063588	1	0	49	50324	0	53404	53404	33339	3	33359	160100	160200	240200	53404	66	1	1	160201	100	99	100	160100	80100	0	0	10110	0	0	1	19	1	2	53400	160000	100	53405	53405	53405	53405	53405
160204	53404	400	0	0	0	37	25	160100	160100	160100	1063588	0	5	49	50324	0	53404	53404	33339	3	33359	160100	160200	240200	53404	66	1	1	160201	100	99	100	160100	80100	0	3	10110	5	0	1	19	1	2	53400	160000	100	53405	53405	53405	53405	53405
160204	53404	400	0	0	0	276	25	160100	160100	160100	1063588	1	0	49	50324	0	53404	53404	33339	3	33359	160100	160200	240200	53404	66	1	1	160201	100	99	100	160100	80100	0	0	10110	5	1	1	19	1	2	53400	160000	100	53405	53405	53405	53405	53405
160204	53404	399	0	0	0	37	25	160100	160100	160100	1063588	0	5	49	50324	0	53404	53404	33339	3	33359	160100	160200	240200	53404	66	1	1	160201	100	99	100	160100	80100	0	0	10110	0	0	1	19	1	2	53400	160000	100	53405	53405	53405	53405	53405

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.6672

All non-zero counters (first 10 of 64 runs)

retire uop (01)	cycle (02)	03	mmu table walk instruction (07)	mmu table walk data (08)	09	l2 tlb miss instruction (0a)	l2 tlb miss data (0b)	18	19	1e	1f	3a	3f	51	schedule uop (52)	schedule int uop (53)	dispatch int uop (56)	int uops in schedulers (59)	5f	60	61	69	6a	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map int uop inputs (7f)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	9f	l1d tlb access (a0)	l1d tlb miss (a1)	ld unit uop (a6)	l1d cache writeback (a8)	a9	ac	c2	cf	d0	d2	l1i cache miss demand (d3)	d5	map dispatch bubble (d6)	d9	da	db	dd	fetch restart (de)	e0	? int output thing (e9)	ea	eb	? int retires (ef)	f5	f6	f7	f8	fd
160024	53391	399	0	0	0	0	0	0	0	27	0	0	43	25	160010	160010	160010	1029388	0	1	10	49	50294	53374	53374	33331	3	33351	160010	160020	240020	53374	66	1	1	160021	10	9	10	160010	80010	0	0	0	0	0	0	0	10022	13	6	1	32	19	4	2	2	17	11	53370	160000	40	22	10	53375	53375	53375	53375	53375
160024	53374	400	0	0	0	0	0	0	0	12	0	0	43	25	160010	160010	160010	993295	1	1	0	49	50294	53374	53374	33331	3	33351	160010	160020	240020	53374	66	1	1	160021	10	9	10	160010	80010	0	0	0	0	0	0	0	10024	16	5	1	12	19	4	2	2	12	21	53370	160000	40	22	10	53375	53375	53375	53375	53375
160024	53374	400	0	0	0	0	0	0	0	0	0	0	49	25	160010	160010	160010	1029388	0	1	10	49	50294	53374	53374	33331	3	33351	160010	160020	240020	53374	66	1	1	160021	10	9	10	160010	80010	0	0	0	0	0	3	0	10024	16	7	2	17	19	4	2	2	22	12	53370	160000	40	22	10	53375	53375	53375	53375	53375
160024	53374	400	0	0	0	0	0	0	0	0	0	0	49	25	160010	160010	160010	1029388	0	1	10	49	50294	53374	53374	33331	3	33351	160010	160020	240020	53374	66	1	1	160021	10	9	10	160010	80010	0	0	0	0	0	0	0	10024	13	6	2	12	19	2	2	2	11	16	53370	160000	20	22	10	53375	53375	53375	53375	53375
160024	53374	400	0	0	0	0	0	0	0	0	0	0	43	25	160010	160010	160010	1029388	1	0	10	49	50294	53374	53374	33331	3	33351	160010	160020	240020	53374	66	1	1	160021	10	9	10	160010	80010	0	0	0	0	0	0	0	10024	13	6	2	16	19	4	1	2	16	10	53370	160000	20	22	10	53375	53375	53375	53375	53375
160024	53374	400	0	0	0	0	0	0	0	0	0	0	49	25	160010	160010	160010	1029388	0	1	0	49	50294	53374	53374	33331	3	33351	160010	160020	240020	53374	66	1	1	160021	10	9	10	160010	80010	0	0	0	0	0	0	0	10024	6	7	2	16	19	4	2	1	17	18	53370	160000	20	22	10	53375	53375	53375	53375	53375
160024	53374	400	0	0	0	0	0	0	0	6	0	0	43	25	160010	160010	160010	1029388	0	1	10	49	50294	53374	53374	33331	3	33351	160010	160020	240020	53374	66	1	1	160021	10	9	10	160010	80010	0	0	0	0	0	0	0	10024	13	5	2	13	19	4	1	2	15	11	53370	160000	40	22	10	53375	53375	53375	53375	53375
160024	53374	400	0	0	0	0	0	0	0	0	0	0	49	25	160010	160010	160010	1029388	0	1	0	49	50294	53374	53374	33331	3	33351	160010	160020	240020	53374	66	1	1	160021	10	9	10	160010	80010	0	0	0	0	0	0	0	10022	16	2	2	14	19	4	2	2	13	12	53370	160000	40	22	10	53375	53375	53375	53375	53375
160024	53374	400	0	0	0	0	0	0	0	0	0	0	49	25	160010	160010	160010	1029388	1	0	10	49	50294	53374	53374	33331	3	33351	160010	160020	240020	53374	66	1	1	160021	10	9	10	160010	80010	0	0	0	0	0	0	0	10024	13	7	1	13	19	4	1	2	19	13	53370	160000	40	22	10	53375	53375	53375	53375	53375
160024	53374	400	0	0	0	0	0	0	0	0	0	0	714	25	160010	160010	160010	1029388	0	1	0	49	50294	53374	53374	33331	3	33351	160010	160020	240020	53374	132	1	1	160021	10	9	10	160010	80010	0	0	0	0	0	0	0	10024	16	7	2	13	19	4	2	2	14	13	53370	160000	40	22	10	53375	53375	53375	53470	53423

Test 6: throughput

Count: 4

Code:

  fcmp s0, s0
  ccmp w0, w1, #0, hi
  ccmp w0, w1, #0, hi
  ccmp w0, w1, #0, hi
  ccmp w0, w1, #0, hi

Initialization

  mov x0, 1
  mov x1, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.3353

All non-zero counters (first 10 of 64 runs)

retire uop (01)	cycle (02)	03	1e	3f	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	69	6b	6d	6e	map stall dispatch (70)	flags prf full (73)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d cache writeback (a8)	ac	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? int output thing (e9)	? int retires (ef)	f5	f6	f7	f8	fd
50204	13442	100	0	66	25	50100	40100	10000	40100	10000	574757	80000	13385	0	13414	13414	6128	2456	3	7119	50100	40200	10000	120200	20000	13414	13414	1	1	50201	100	99	100	40100	10000	40100	0	0	3210	1	19	1	1	13411	40000	100	13415	13415	13415	13415	13415
50204	13414	100	0	45	25	50100	40100	10000	40100	10000	574757	80000	13385	0	13414	13414	6130	2456	3	7119	50100	40200	10000	120200	20000	13414	13414	1	1	50201	100	99	100	40100	10000	40100	0	0	3210	1	19	1	1	13411	40075	100	13415	13415	13415	13415	13415
50204	13414	100	0	66	25	50100	40100	10000	40100	10000	574757	80000	13385	0	13499	13414	6128	2456	3	7119	50100	40200	10000	120200	20000	13414	13414	1	1	50201	100	99	100	40100	10000	40100	0	0	3210	1	19	1	1	13411	40000	100	13415	13415	13415	13415	13415
50204	13414	100	0	133	25	50100	40100	10000	40100	10000	574757	80000	13385	0	13414	13414	6130	2456	3	7119	50100	40200	10000	120200	20000	13414	13414	1	1	50201	100	99	100	40100	10000	40100	0	0	3210	1	19	1	1	13411	40000	100	13415	13415	13415	13415	13415
50204	13414	101	0	66	25	50100	40100	10000	40100	10000	574757	80000	13385	0	13414	13414	6128	2456	3	7119	50100	40200	10000	120200	20000	13414	13414	1	1	50201	100	99	100	40100	10000	40100	0	6	3210	1	19	2	1	13411	40156	100	13415	13415	13415	13415	13482
50204	13414	100	12	173	25	50213	40100	10000	40100	10000	574757	80000	13435	0	13414	13414	6130	2456	3	7160	50100	40200	10000	120200	20052	13414	13587	1	1	50201	100	99	100	40100	10000	40100	0	0	3210	1	19	2	1	13411	40000	100	13415	13415	13415	13415	13415
50204	13414	101	12	45	25	50100	40100	10000	40100	10000	574757	80000	13385	0	13414	13414	6130	2456	3	7119	50100	40200	10000	120200	20000	13414	13414	1	1	50201	100	99	100	40100	10000	40100	0	0	3210	1	19	2	1	13411	40070	100	13415	13415	13415	13415	13415
50204	13414	100	0	520	25	50100	40100	10000	40100	10000	574757	80000	13385	0	13414	13414	6128	2467	3	7119	50100	40200	10000	120200	20000	13414	13414	1	1	50201	100	99	100	40100	10000	40100	0	0	3210	1	19	2	1	13411	40000	100	13415	13415	13415	13415	13415
50204	13414	100	0	108	25	50100	40100	10000	40100	10000	574757	80000	13385	0	13414	13414	6128	2467	3	7119	50100	40200	10000	120200	20000	13414	13414	1	1	50201	100	99	100	40100	10000	40100	0	3	3210	1	19	1	1	13411	40000	100	13415	13415	13415	13415	13415
50204	13414	100	0	108	25	50100	40100	10000	40100	10000	574757	80000	13385	0	13414	13414	6130	2467	3	7119	50100	40200	10000	120200	20000	13414	13414	1	1	50201	100	99	100	40100	10000	40100	0	3	3210	1	19	1	1	13411	40000	100	13415	13415	13415	13415	13415

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.3346

All non-zero counters (first 10 of 64 runs)

retire uop (01)	cycle (02)	03	mmu table walk instruction (07)	1e	3f	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	60	69	6d	6e	map stall dispatch (70)	flags prf full (73)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d cache writeback (a8)	ac	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? int output thing (e9)	eb	? int retires (ef)	f5	f6	f7	f8	fd
50024	13408	100	0	0	264	25	50010	40010	10000	40010	10000	573456	80000	1	13353	13382	13382	5575	3795	3	7109	50010	40020	10000	120020	20000	13382	13382	1	1	50021	10	9	10	40010	10000	40010	0	0	3140	1	19	2	1	13379	40076	0	10	13383	13383	13383	13383	13383
50024	13382	100	0	0	45	25	50010	40010	10000	40010	10000	573456	80000	1	13353	13382	13382	5575	3784	3	7109	50010	40122	10000	120020	20000	13382	13382	1	1	50021	10	9	10	40010	10000	40010	0	0	3140	1	19	3	2	13379	40000	0	10	13383	13383	13383	13383	13383
50024	13382	100	0	0	108	25	50010	40010	10000	40010	10000	573456	80000	1	13353	13382	13382	5575	3795	3	7109	50010	40020	10000	120020	20000	13382	13382	1	1	50021	10	9	10	40010	10000	40010	0	0	3140	1	19	1	1	13379	40000	0	10	13383	13383	13383	13383	13383
50024	13382	100	0	0	45	25	50010	40010	10000	40010	10000	573456	80000	0	13353	13382	13382	5577	3784	3	7109	50010	40020	10000	120020	20000	13382	13382	1	1	50021	10	9	10	40010	10000	40010	0	0	3140	1	19	1	1	13379	40000	0	10	13383	13383	13383	13383	13383
50024	13382	100	0	0	45	25	50010	40010	10000	40010	10000	573456	80000	0	13353	13382	13382	5577	3784	3	7109	50010	40020	10000	120020	20000	13382	13382	1	1	50021	10	9	10	40010	10000	40010	0	0	3140	1	19	1	1	13379	40000	0	10	13383	13383	13383	13383	13383
50024	13382	100	0	0	45	25	50010	40010	10000	40010	10000	573456	80000	1	13353	13382	13382	5575	3784	3	7109	50010	40020	10000	120020	20000	13382	13382	1	1	50021	10	9	10	40010	10000	40010	0	0	3140	1	19	1	1	13379	40000	0	10	13383	13383	13383	13383	13383
50024	13382	100	0	12	45	25	50010	40010	10000	40010	10000	573456	80000	0	13353	13382	13382	5575	3795	3	7109	50010	40020	10000	120020	20000	13382	13382	1	1	50021	10	9	10	40010	10000	40010	0	0	3140	1	19	1	1	13379	40000	0	10	13383	13383	13383	13383	13383
50024	13382	100	0	0	45	25	50010	40010	10000	40010	10000	573456	80000	1	13353	13382	13382	5575	3784	3	7109	50010	40020	10000	120020	20000	13382	13382	1	1	50021	10	9	10	40010	10000	40010	0	0	3140	1	19	1	2	13379	40000	0	10	13383	13383	13383	13383	13383
50024	13382	100	0	0	45	25	50010	40010	10000	40010	10000	573456	80000	1	13353	13382	13382	5575	3784	3	7109	50010	40020	10000	120020	20000	13382	13382	1	1	50021	10	9	10	40010	10000	40010	0	0	3140	1	19	2	3	13379	40000	0	10	13383	13383	13383	13383	13383
50024	13382	100	0	0	87	25	50010	40010	10000	40010	10000	573456	80000	1	13353	13382	13382	5577	3784	3	7109	50010	40020	10000	120020	20000	13382	13382	1	1	50021	10	9	10	40010	10000	40010	0	0	3140	1	19	1	1	13379	40000	0	10	13383	13383	13383	13448	13383

CCMP (register, 32-bit)

Test 1: uops

1000 unrolls and 1 iteration

Test 2: Latency 3->1

100 unrolls and 100 iterations

1000 unrolls and 10 iterations

Test 3: Latency 3->2

100 unrolls and 100 iterations

1000 unrolls and 10 iterations

Test 4: Latency 3->3

100 unrolls and 100 iterations

1000 unrolls and 10 iterations

Test 5: throughput

100 unrolls and 100 iterations

1000 unrolls and 10 iterations

Test 6: throughput

100 unrolls and 100 iterations

1000 unrolls and 10 iterations