Firestorm: FMLS (vector, 2S) measurements

Code:

  fmls v0.2s, v1.2s, v2.2s

Initialization

  movi v0.16b, 1
  movi v1.16b, 2
  movi v2.16b, 3

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 1.000

Issues: 1.000

Integer unit issues: 0.000

Load/store unit issues: 0.000

SIMD/FP unit issues: 1.000

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

retire uop (01)	cycle (02)	03	19	1e	3f	4e	51	schedule uop (52)	schedule simd uop (54)	dispatch simd uop (57)	ldst uops in schedulers (5b)	60	69	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map simd uop (7e)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst simd alu (9a)	ac	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	f5	f6	f7	f8	fd
1004	4037	30	0	0	61	3407	25	1000	1000	1000	531908	0	4018	4037	4037	3258	3	3895	1000	1000	3000	4037	4037	1	1	1001	1000	0	73	1	16	1	1	3473	1000	4038	4038	4038	4038	4038
1004	4037	30	0	0	82	3407	25	1000	1000	1000	531908	0	4018	4037	4037	3258	3	3895	1000	1000	3000	4037	4037	1	1	1001	1000	0	73	1	16	1	1	3473	1000	4038	4038	4038	4038	4038
1004	4037	30	0	0	61	3407	25	1000	1000	1000	531908	0	4018	4037	4037	3258	3	3895	1000	1000	3000	4037	4037	1	1	1001	1000	0	73	1	16	1	1	3473	1000	4038	4038	4038	4038	4038
1004	4037	30	0	0	61	3407	25	1000	1000	1000	531908	0	4018	4037	4037	3258	3	3895	1000	1000	3000	4037	4037	1	1	1001	1000	6	73	1	16	2	2	3473	1000	4038	4038	4038	4038	4038
1004	4037	30	0	0	61	3407	25	1000	1000	1000	531908	0	4018	4037	4037	3258	3	3895	1000	1000	3000	4037	4037	1	1	1001	1000	0	73	1	16	1	1	3473	1000	4038	4038	4038	4038	4038
1004	4037	30	0	0	61	3407	25	1000	1000	1000	531908	0	4018	4037	4037	3258	3	3895	1000	1000	3000	4037	4037	1	1	1001	1000	0	73	1	16	2	1	3473	1000	4038	4038	4038	4038	4038
1004	4037	30	0	0	61	3407	25	1000	1000	1000	531908	0	4018	4037	4037	3258	3	3895	1000	1000	3000	4037	4037	1	1	1001	1000	0	73	1	16	1	1	3473	1000	4038	4038	4038	4038	4038
1004	4037	30	0	0	61	3407	25	1000	1000	1000	531908	0	4018	4037	4037	3258	3	3895	1000	1000	3000	4037	4037	1	1	1001	1000	0	73	1	16	2	2	3473	1000	4038	4038	4038	4038	4038
1004	4037	30	0	0	61	3407	25	1000	1000	1000	531908	0	4018	4037	4037	3258	3	3895	1000	1000	3000	4037	4037	1	1	1001	1000	0	73	1	16	2	2	3473	1000	4038	4038	4038	4038	4038
1004	4037	31	0	0	61	3407	25	1000	1000	1000	531908	0	4018	4037	4037	3258	3	3895	1000	1000	3000	4037	4037	1	1	1001	1000	0	73	1	16	1	1	3473	1000	4038	4038	4038	4038	4038

Test 2: Latency 1->1

Code:

  fmls v0.2s, v1.2s, v2.2s

Initialization

  movi v0.16b, 1
  movi v1.16b, 2
  movi v2.16b, 3

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 4.0037

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

retire uop (01)	cycle (02)	03	1e	3a	3f	4e	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	6d	6e	map stall dispatch (70)	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	d0	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10204	40037	299	0	0	61	39407	25	10100	100	10000	100	10000	500	5706908	40018	40037	40037	38108	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	710	1	2	16	2	2	39479	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	0	103	39407	25	10100	100	10000	100	10000	500	5706908	40018	40037	40037	38108	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	710	1	2	16	2	2	39479	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	0	61	39407	25	10100	100	10000	100	10000	588	5706908	40018	40037	40037	38108	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	710	1	2	16	2	2	39479	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	1	61	39407	25	10100	100	10000	100	10000	500	5706908	40018	40037	40037	38108	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	710	1	2	16	2	2	39479	10000	100	40038	40038	40038	40038	40038
10204	40037	299	0	1	61	39407	25	10100	100	10000	100	10000	500	5706908	40018	40037	40037	38108	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	3	710	1	2	16	2	2	39479	10000	100	40038	40038	40038	40038	40038
10204	40084	301	0	0	61	39407	25	10100	100	10000	100	10000	500	5706908	40018	40037	40037	38108	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	710	1	2	16	2	2	39479	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	0	61	39407	25	10100	100	10000	100	10000	500	5706908	40018	40037	40037	38108	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	6	710	1	2	16	2	3	39479	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	0	61	39407	25	10100	100	10000	100	10000	500	5706908	40018	40037	40037	38108	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	710	1	3	16	2	2	39479	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	0	103	39407	25	10100	100	10000	100	10000	500	5706908	40018	40037	40037	38108	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	710	1	2	16	2	2	39479	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	0	61	39407	25	10100	100	10000	100	10000	500	5706908	40018	40037	40037	38108	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	710	1	2	16	2	2	39479	10000	100	40038	40038	40038	40038	40038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

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

retire uop (01)	cycle (02)	03	1e	3f	4e	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	6d	6e	map stall dispatch (70)	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	st unit uop (a7)	l1d cache writeback (a8)	a9	ac	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10024	40037	300	0	61	39407	25	10010	10	10000	10	10000	50	5706908	40018	40037	40037	38130	3	38767	10010	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	3	0	3	640	3	16	2	2	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	61	39407	25	10010	10	10000	10	10000	50	5706908	40018	40037	40037	38130	3	38767	10010	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	640	2	16	2	2	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	299	0	61	39407	25	10010	10	10000	10	10000	50	5706908	40018	40037	40037	38130	3	38767	10010	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	640	2	16	2	2	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	120	61	39407	25	10010	10	10000	10	10000	60	5706908	40018	40037	40037	38130	3	38767	10010	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	640	2	16	2	2	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	61	39407	25	10010	10	10000	10	10000	50	5706908	40018	40037	40037	38130	3	38767	10010	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	640	2	16	2	2	39473	10000	10	40038	40038	40038	40038	40038
10024	40084	300	0	61	39407	25	10010	10	10000	10	10000	50	5706908	40018	40037	40037	38130	3	38767	10010	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	1	4	0	640	3	16	2	2	39473	10000	10	40086	40038	40038	40038	40038
10024	40037	300	0	61	39407	25	10010	10	10000	10	10000	50	5706908	40018	40037	40037	38130	3	38767	10010	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	640	2	16	2	2	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	61	39407	25	10010	10	10000	10	10000	50	5706908	40018	40037	40037	38130	3	38767	10010	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	640	2	16	2	2	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	61	39407	25	10010	10	10000	10	10000	50	5706908	40018	40037	40037	38130	3	38767	10010	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	640	2	16	2	2	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	61	39407	25	10010	10	10000	10	10000	50	5706908	40018	40037	40037	38130	3	38767	10010	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	640	2	16	2	2	39473	10000	10	40038	40038	40038	40038	40038

Test 3: Latency 1->2

Code:

  fmls v0.2s, v0.2s, v1.2s

Initialization

  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 4.0037

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

retire uop (01)	cycle (02)	03	1e	3f	4e	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	6b	6d	6e	map stall dispatch (70)	simd prf full (72)	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 tlb access (a0)	l1d tlb miss (a1)	l1d cache writeback (a8)	ac	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10204	40037	300	0	61	39407	25	10100	100	10000	100	10000	500	5706908	0	40018	0	40037	40037	38108	0	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	710	1	16	1	1	39479	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	61	39407	25	10100	100	10000	100	10000	500	5706908	0	40018	0	40037	40037	38108	0	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	710	1	16	1	1	39479	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	726	39407	25	10118	100	10000	100	10000	500	5706908	1	40018	0	40037	40037	38108	0	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	710	1	16	1	1	39479	10000	100	40038	40038	40038	40038	40038
10204	40037	299	0	61	39407	25	10100	100	10000	100	10000	500	5706908	0	40018	0	40037	40037	38108	0	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	710	1	16	1	1	39479	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	61	39407	25	10100	100	10000	100	10000	500	5706908	0	40018	0	40037	40037	38108	0	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	0	3	710	1	16	1	1	39479	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	61	39407	25	10100	100	10000	100	10000	500	5706908	0	40018	0	40037	40037	38108	0	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	710	1	16	1	1	39479	10000	100	40038	40038	40038	40038	40038
10204	40037	299	0	156	39407	25	10100	100	10000	100	10000	500	5706908	0	40018	0	40037	40037	38108	0	3	38745	10260	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	710	1	16	1	1	39479	10000	100	40038	40038	40038	40038	40038
10204	40037	299	0	104	39407	25	10100	100	10000	100	10000	500	5706908	0	40018	0	40037	40037	38108	0	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	710	1	16	1	1	39479	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	61	39407	25	10100	100	10000	100	10000	500	5706908	0	40018	0	40037	40037	38108	0	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	710	1	16	1	1	39479	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	61	39407	25	10100	100	10000	100	10000	500	5706908	0	40018	0	40037	40037	38108	0	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	710	1	16	1	1	39479	10000	100	40038	40038	40038	40038	40038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

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

retire uop (01)	cycle (02)	03	l2 tlb miss data (0b)	18	1e	3f	4e	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	6d	6e	map stall dispatch (70)	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 tlb access (a0)	l1d tlb miss (a1)	l1d cache writeback (a8)	ac	branch mispred nonspec (cb)	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10024	40037	300	0	0	0	367	39407	25	10010	10	10000	10	10000	50	5706908	40018	40037	40037	38130	3	38767	10010	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	640	3	16	3	3	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	0	0	1341	39407	25	10010	10	10000	10	10000	50	5706908	40018	40037	40037	38130	3	38767	10010	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	640	3	16	3	3	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	299	0	0	0	1013	39407	25	10010	10	10000	10	10000	50	5706908	40018	40037	40037	38130	3	38767	10010	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	640	3	16	3	3	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	0	0	1147	39407	25	10010	10	10000	10	10000	50	5706908	40018	40037	40037	38130	3	38767	10010	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	640	3	16	3	3	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	0	0	61	39407	25	10010	10	10000	10	10000	50	5706908	40018	40037	40037	38130	3	38767	10010	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	640	3	16	3	3	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	299	0	0	0	273	39407	25	10010	10	10000	10	10000	50	5706908	40018	40037	40037	38130	3	38767	10010	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	0	1	3	0	640	3	16	3	3	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	0	162	187	39407	25	10010	10	10000	10	10000	50	5706908	40018	40037	40037	38130	3	38767	10010	20	10000	20	30132	40083	40084	1	1	10021	10	9	10	10	10000	10	2	2	1	0	0	640	3	16	3	3	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	299	0	0	15	233	39407	25	10010	10	10000	10	10000	50	5706908	40018	40037	40037	38130	3	38767	10010	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	640	3	16	3	3	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	2	0	293	39407	25	10010	10	10000	10	10000	50	5706908	40018	40037	40037	38130	3	38767	10010	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	0	0	3	0	640	3	16	5	3	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	0	0	1754	39407	25	10010	10	10000	10	10000	50	5706908	40018	40037	40037	38130	3	38767	10010	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	640	3	16	3	3	39473	10000	10	40038	40038	40075	40038	40038

Test 4: Latency 1->3

Code:

  fmls v0.2s, v1.2s, v0.2s

Initialization

  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 4.0037

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)	1e	3f	4e	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	6d	6e	map stall dispatch (70)	simd prf full (72)	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)	a9	ac	cd	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? int output thing (e9)	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10204	40037	300	0	0	0	1218	39407	25	10100	100	10000	100	10000	500	5706908	40018	40037	40037	38108	0	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	710	1	16	1	1	39479	27	10000	100	40038	40038	40038	40038	40038
10204	40037	299	0	0	0	1160	39407	25	10100	100	10000	100	10000	500	5706908	40018	40037	40037	38108	0	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	1	0	3	0	710	1	16	1	1	39479	0	10000	100	40038	40038	40038	40038	40038
10204	40037	299	0	0	0	1299	39407	25	10100	100	10000	100	10000	500	5706908	40018	40037	40037	38108	0	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	710	1	16	1	1	39479	0	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	0	0	362	39407	25	10100	100	10000	100	10000	500	5706908	40018	40037	40037	38108	0	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	710	1	16	1	1	39479	0	10000	100	40038	40038	40038	40038	40038
10204	40037	299	0	0	0	622	39407	25	10100	100	10000	100	10147	500	5706908	40018	40037	40037	38108	0	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	710	1	16	1	1	39479	0	10000	100	40038	40038	40038	40038	40038
10204	40037	299	0	0	0	1195	39407	25	10100	100	10000	100	10000	500	5706908	40018	40037	40037	38108	0	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	710	1	16	1	1	39479	0	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	0	0	513	39407	25	10100	100	10000	100	10000	500	5706908	40018	40037	40037	38108	0	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	710	1	16	1	1	39479	0	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	0	0	1290	39407	25	10100	100	10000	100	10000	500	5706908	40018	40037	40037	38108	0	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	710	1	16	1	1	39479	0	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	0	0	2066	39407	25	10100	100	10000	100	10000	500	5706908	40018	40037	40037	38108	0	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	710	1	16	1	1	39479	0	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	0	0	1246	39407	25	10100	100	10000	100	10000	500	5706908	40018	40037	40037	38108	0	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	710	1	16	1	1	39479	0	10000	100	40038	40038	40038	40038	40038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

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

retire uop (01)	cycle (02)	03	mmu table walk data (08)	09	l2 tlb miss data (0b)	18	19	1e	1f	3f	4e	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	6d	6e	map stall dispatch (70)	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 tlb access (a0)	l1d tlb miss (a1)	ld unit uop (a6)	l1d cache writeback (a8)	ac	c2	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10024	40037	300	0	0	0	0	0	0	0	939	39407	25	10010	10	10000	10	10000	50	5706908	40018	40037	40037	38130	3	38767	10010	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	640	2	16	2	2	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	299	0	0	0	0	0	0	0	681	39407	25	10010	10	10000	10	10000	50	5706908	40018	40037	40037	38130	3	38767	10010	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	640	2	16	2	2	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	0	0	0	0	0	0	932	39407	25	10010	10	10000	10	10000	50	5706908	40018	40037	40037	38130	3	38767	10010	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	640	2	16	2	2	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	0	0	0	0	141	0	945	39407	25	10010	10	10000	10	10000	50	5706908	40018	40037	40037	38130	3	38767	10010	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	640	2	16	2	2	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	0	0	0	0	0	0	831	39407	25	10010	10	10000	10	10000	50	5706908	40018	40037	40037	38130	3	38767	10010	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	640	2	16	2	2	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	0	0	0	0	0	0	712	39407	25	10010	10	10000	10	10000	50	5706908	40018	40037	40037	38130	3	38767	10010	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	640	2	16	2	2	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	299	0	0	0	0	0	0	0	893	39407	25	10010	10	10000	10	10000	50	5706908	40018	40037	40037	38130	3	38767	10010	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	640	2	16	2	2	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	0	0	0	0	0	0	210	39407	25	10010	10	10000	10	10000	50	5706908	40018	40037	40037	38130	3	38767	10010	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	640	2	16	2	2	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	299	0	0	0	0	0	0	0	314	39407	25	10010	10	10000	10	10000	50	5706908	40018	40037	40037	38130	3	38767	10010	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	640	2	16	2	3	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	0	0	0	0	0	0	145	39407	25	10010	10	10000	10	10000	50	5706908	40018	40037	40037	38130	3	38767	10010	20	10000	20	30000	40037	40084	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	640	2	16	2	2	39473	10000	10	40038	40038	40038	40038	40038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  fmls v0.2s, v8.2s, v9.2s
  movi v1.16b, 0
  fmls v1.2s, v8.2s, v9.2s
  movi v2.16b, 0
  fmls v2.2s, v8.2s, v9.2s
  movi v3.16b, 0
  fmls v3.2s, v8.2s, v9.2s
  movi v4.16b, 0
  fmls v4.2s, v8.2s, v9.2s
  movi v5.16b, 0
  fmls v5.2s, v8.2s, v9.2s
  movi v6.16b, 0
  fmls v6.2s, v8.2s, v9.2s
  movi v7.16b, 0
  fmls v7.2s, v8.2s, v9.2s

Initialization

  movi v8.16b, 9
  movi v9.16b, 10

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2508

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

retire uop (01)	cycle (02)	03	1e	1f	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 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)	a9	ac	branch cond mispred nonspec (c5)	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
160204	20065	150	0	0	40	25	80100	100	80000	100	80000	500	640000	1	20046	20065	20065	3	23	80100	200	80000	200	240000	20065	20065	1	1	160201	100	99	100	100	160000	100	0	0	0	0	10114	2	16	4	5	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	150	0	0	86	25	80100	100	80000	100	80000	500	640000	1	20046	20065	20065	3	23	80100	200	80000	200	240000	20065	20065	1	1	160201	100	99	100	100	160000	100	0	0	0	0	10114	4	16	3	5	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	150	0	0	705	25	80100	100	80000	100	80000	500	640000	1	20046	20065	20065	3	23	80100	200	80000	200	240000	20065	20065	1	1	160201	100	99	100	100	160000	100	1	0	0	0	10114	5	16	4	5	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	150	0	0	147	25	80100	100	80000	100	80000	500	640000	1	20046	20065	20065	3	23	80100	200	80000	200	240000	20065	20065	1	1	160201	100	99	100	100	160000	100	0	0	0	0	10114	4	16	5	4	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	150	12	108	128	25	80100	100	80000	100	80000	500	640000	1	20046	20065	20065	3	23	80100	200	80000	200	240000	20065	20065	1	1	160201	100	99	100	100	160000	100	0	0	0	0	10114	5	16	5	5	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	150	0	0	149	25	80100	100	80000	100	80000	500	640000	1	20046	20065	20065	3	23	80100	200	80000	200	240000	20065	20065	1	1	160201	100	99	100	100	160000	100	0	0	0	0	10115	5	16	5	5	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	150	0	0	325	25	80100	100	80000	100	80000	500	640000	1	20046	20065	20065	3	23	80100	200	80000	200	240000	20065	20065	1	1	160201	100	99	100	100	160000	100	0	0	0	0	10114	4	16	4	3	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	150	0	0	282	25	80100	100	80000	100	80000	500	640000	1	20046	20065	20065	3	23	80100	200	80000	200	240000	20065	20065	1	1	160201	100	99	100	100	160000	100	0	0	0	0	10114	4	16	4	4	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	151	0	0	105	25	80100	100	80000	100	80000	500	640000	1	20046	20065	20065	3	23	80100	200	80000	200	240000	20065	20065	1	1	160201	100	99	100	100	160000	100	1	0	0	0	10115	5	16	5	4	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	151	0	0	40	25	80100	100	80000	100	80000	500	640000	1	20046	20065	20065	3	23	80100	200	80000	200	240000	20065	20065	1	1	160201	100	99	100	100	160000	100	0	0	0	0	10114	5	16	4	5	20062	160000	100	20066	20066	20066	20066	20066

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2506

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

retire uop (01)	cycle (02)	03	18	19	1e	1f	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)	5f	60	69	6d	6e	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	cd	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	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
160024	20053	150	0	0	0	0	90	25	80012	12	80000	12	80000	62	640000	1	1	20028	20047	20047	3	23	80012	20	80000	20	240000	20047	20047	1	1	160021	10	9	10	10	160000	10	0	0	0	10030	3	1	1	9	20	2	1	1	6	7	20044	2	15	160000	10	20048	20048	20048	20048	20048
160024	20047	150	0	0	0	0	134	25	80012	12	80000	12	80000	62	640000	1	1	20028	20047	20047	3	23	80012	20	80000	20	240000	20047	20047	1	1	160021	10	9	10	10	160000	10	2	0	0	10030	3	1	1	7	20	2	1	1	7	4	20044	2	15	160000	10	20048	20048	20048	20048	20048
160024	20047	150	0	0	0	0	174	25	80012	12	80000	12	80000	62	640000	1	1	20028	20047	20047	3	23	80012	20	80000	20	240000	20047	20047	1	1	160021	10	9	10	10	160000	10	0	0	0	10030	3	1	1	4	20	2	1	1	4	7	20044	2	15	160000	10	20048	20048	20048	20048	20048
160024	20047	150	0	0	0	0	67	25	80012	12	80000	12	80000	62	640000	1	1	20028	20047	20047	3	23	80012	20	80000	20	240000	20047	20047	1	1	160021	10	9	10	10	160000	10	0	0	0	10027	3	1	1	7	20	2	1	1	6	4	20044	2	15	160000	10	20048	20048	20048	20048	20048
160024	20047	150	0	0	9	0	46	25	80012	12	80000	12	80000	50	640000	1	1	20028	20047	20047	3	23	80012	20	80000	20	240000	20047	20047	1	1	160021	10	9	10	10	160000	10	0	0	0	10030	3	1	1	7	20	2	1	1	7	6	20044	2	15	160000	10	20048	20048	20048	20048	20048
160024	20047	150	0	0	0	132	46	25	80012	12	80000	12	80000	62	640000	1	1	20028	20047	20047	3	23	80012	20	80000	20	240000	20047	20047	1	1	160021	10	9	10	10	160000	10	0	0	0	10027	3	1	1	6	20	2	1	1	7	4	20044	2	15	160000	10	20048	20048	20048	20048	20048
160024	20047	150	0	0	0	0	136	25	80012	12	80000	12	80000	62	640000	1	1	20028	20047	20047	3	23	80012	20	80000	20	240000	20047	20047	1	1	160021	10	9	10	10	160000	10	0	0	0	10030	3	1	1	7	20	2	1	1	4	7	20044	2	15	160000	10	20048	20048	20048	20048	20048
160024	20047	151	0	0	0	0	134	25	80012	12	80000	12	80000	62	640000	1	1	20028	20047	20047	3	23	80012	20	80000	20	240000	20047	20047	1	1	160021	10	9	10	10	160000	10	0	0	0	10027	3	1	1	5	20	2	1	1	7	5	20044	2	15	160000	10	20048	20048	20048	20048	20048
160024	20047	150	0	0	0	0	46	25	80012	12	80000	12	80000	62	640000	1	1	20028	20047	20047	3	23	80012	20	80000	20	240000	20047	20047	1	1	160021	10	9	10	10	160000	10	0	0	0	10030	3	1	1	7	20	2	1	1	7	4	20112	2	15	160000	10	20048	20048	20048	20048	20048
160024	20047	150	0	0	0	0	46	25	80012	12	80000	12	80000	62	640000	1	1	20028	20047	20047	3	23	80012	20	80000	20	240000	20047	20047	1	1	160021	10	9	10	10	160000	10	0	0	0	10030	3	1	1	7	20	2	1	1	4	7	20044	2	15	160000	10	20048	20048	20048	20048	20048

Test 6: throughput

Count: 16

Code:

  fmls v0.2s, v16.2s, v17.2s
  fmls v1.2s, v16.2s, v17.2s
  fmls v2.2s, v16.2s, v17.2s
  fmls v3.2s, v16.2s, v17.2s
  fmls v4.2s, v16.2s, v17.2s
  fmls v5.2s, v16.2s, v17.2s
  fmls v6.2s, v16.2s, v17.2s
  fmls v7.2s, v16.2s, v17.2s
  fmls v8.2s, v16.2s, v17.2s
  fmls v9.2s, v16.2s, v17.2s
  fmls v10.2s, v16.2s, v17.2s
  fmls v11.2s, v16.2s, v17.2s
  fmls v12.2s, v16.2s, v17.2s
  fmls v13.2s, v16.2s, v17.2s
  fmls v14.2s, v16.2s, v17.2s
  fmls v15.2s, v16.2s, v17.2s

Initialization

  movi v16.16b, 17
  movi v17.16b, 18

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2502

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

retire uop (01)	cycle (02)	03	mmu table walk data (08)	19	1e	37	3f	4e	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)	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 tlb access (a0)	l1d tlb miss (a1)	l1d cache writeback (a8)	ac	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
160204	40427	300	0	0	0	0	42	0	25	160100	100	160000	100	160000	500	1280000	1	40021	40040	40040	19973	3	19998	160100	200	160000	200	480000	40040	40040	1	1	160201	100	99	100	100	160000	100	0	0	0	0	10110	2	16	1	1	40037	160000	100	40041	40041	40041	40041	41228
160204	40040	299	0	0	0	0	42	0	25	160100	100	160000	100	160000	500	1280000	1	40021	40040	40040	19973	3	19998	160100	200	160000	200	480000	41190	41205	1	1	160201	100	99	100	100	160000	100	0	0	0	0	10110	1	16	1	1	40037	160000	100	41228	40041	40041	40041	40041
160204	40040	300	0	0	0	0	707	0	25	160100	100	160000	100	160124	500	1280000	1	40021	40040	40040	19973	3	19998	160100	200	160000	200	480000	40040	41190	1	1	160201	100	99	100	100	160000	100	0	0	0	0	10110	1	16	1	1	40037	160000	100	40041	40044	42319	40041	40041
160204	40040	309	0	0	0	60	42	0	25	160122	100	160000	100	160000	500	1280000	0	40022	40041	41227	21095	3	19998	160100	200	160000	200	480000	40040	41227	1	1	160201	100	99	100	100	160000	100	0	0	0	0	10110	1	16	1	1	40037	160000	100	40041	41191	41206	41191	41228
160204	40040	309	0	0	0	1	42	0	25	160160	100	160022	100	160000	500	1280000	0	41208	40041	40040	21095	3	20001	160100	200	160000	200	480000	40040	40040	1	1	160201	100	99	100	100	160000	100	0	0	0	0	10110	1	16	1	1	41224	160000	100	40041	41228	40041	40041	40041
160204	40040	300	0	0	0	0	42	0	25	160100	100	160000	100	160000	500	1280000	0	41208	40040	41227	19973	3	19998	160100	200	160000	200	480000	40040	40040	1	1	160201	100	99	100	100	160000	100	0	0	0	0	10110	1	16	1	1	40037	160000	100	40041	40041	40041	40041	40041
160204	40040	300	0	0	0	0	42	0	25	160100	100	160000	100	160000	500	1280000	0	40021	41190	41205	19973	3	21148	160100	200	160000	200	480000	41204	40040	1	1	160201	100	99	100	100	160000	100	0	0	0	0	10110	1	16	1	1	40037	160000	100	40041	41191	41206	40041	41228
160204	40040	300	0	0	0	0	61	4485	25	160122	100	160022	100	160000	500	5717939	1	40021	40043	41190	19973	3	19998	160100	200	160000	200	480000	41190	41205	1	1	160201	100	99	100	100	160000	100	0	0	0	0	10110	1	16	1	1	41202	160000	100	40041	41191	41206	40041	41191
160204	40040	300	0	0	0	0	42	0	25	160100	100	160060	100	160000	500	5717939	1	40021	40040	40040	19973	3	21163	160100	200	160000	200	480000	40040	41227	1	1	160201	100	99	100	100	160000	100	0	0	0	0	10110	1	16	1	1	40037	160000	100	40041	40041	41228	40041	40041
160204	40040	308	0	0	0	0	517	4614	25	160100	100	160000	100	160000	500	1280000	1	40021	40040	40040	19973	3	19998	160100	200	160000	200	480000	40040	40040	1	1	160201	100	99	100	100	160000	100	0	0	0	0	10110	1	16	1	1	41224	160000	100	40041	41191	40044	40041	40041

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2502

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

retire uop (01)	cycle (02)	03	1e	37	3f	4e	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)	5f	60	69	6d	6e	map stall dispatch (70)	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 tlb miss (a1)	ld unit uop (a6)	l1d cache writeback (a8)	ac	c2	cf	d0	d2	l1i cache miss demand (d3)	d5	map dispatch bubble (d6)	d9	da	db	dd	fetch restart (de)	e0	ea	eb	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
160024	40049	316	0	0	47	0	25	160010	10	160000	10	160000	50	1280000	1	1	40021	40040	42294	19996	3	22261	160010	20	160000	20	480000	42294	40040	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	10022	3	1	1	20	16	2	1	1	20	7	40037	20	8	160000	10	40041	40041	40041	40041	42295
160024	40040	309	0	0	637	8896	25	160010	10	160000	10	160000	50	1280000	1	1	41226	40040	40040	19996	22	21225	160010	20	160000	20	480000	40040	42294	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	10026	6	2	1	16	16	2	2	2	19	9	40037	40	8	160000	10	40041	40041	40041	40041	40041
160024	40040	300	0	22	53	0	25	160010	10	160000	10	160000	50	1280000	0	1	42275	40040	41245	21173	3	21225	160010	20	160000	20	480000	40040	40040	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	10024	6	2	2	19	16	2	2	1	20	22	40039	40	8	160000	10	40041	40041	40041	40041	40041
160024	40040	300	0	0	53	0	25	160010	10	160035	10	160000	50	1280000	1	1	42275	42294	41245	19996	3	20020	160010	20	160000	20	480000	40040	42294	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	10024	6	1	2	19	16	4	1	2	9	22	40037	40	23	160000	10	40041	41246	42295	40041	42295
160024	40040	309	453	35	53	0	25	160010	10	160000	10	160000	50	1280000	0	1	42277	40040	40040	19996	3	20020	160010	20	160000	20	480000	42294	40040	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	10024	6	2	2	19	16	4	2	2	9	22	42315	40	16	160000	10	40041	40041	40041	41246	40042
160024	40040	300	0	0	73	0	25	160010	10	160035	10	160000	50	1280000	0	1	40021	40040	40040	19996	3	20020	160010	20	160000	20	480000	40040	41245	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	10024	6	2	2	19	16	4	2	2	20	23	40037	40	16	160000	10	40041	40041	40041	40041	40041
160024	40040	317	0	0	53	4695	25	160010	10	160000	10	160000	50	1280000	0	1	40021	40040	40040	19996	3	20020	160010	20	160000	20	480000	40040	40040	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	10024	6	2	2	8	16	4	2	2	19	9	40037	40	16	160000	10	40041	41246	40041	40041	42295
160024	40091	300	438	0	718	0	25	160010	10	160035	10	160000	50	5721073	1	1	40021	40040	40040	19996	3	22298	160010	20	160000	20	480000	42294	40040	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	10022	6	1	1	8	16	4	1	1	19	9	40037	40	7	160000	10	40041	40041	42282	42297	40041
160024	40040	300	0	0	67	8896	25	160010	10	160000	10	160000	50	1280000	1	1	40021	40040	40040	19996	3	22298	160010	20	160000	20	480000	40040	40040	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	10022	3	1	1	8	16	2	1	1	19	9	40037	20	8	160000	10	40041	42295	40041	40041	40041
160024	40040	317	0	53	47	0	25	160063	10	160053	10	160000	50	1280000	1	1	40021	40040	42318	19996	3	20020	160010	20	160000	20	480000	40040	40040	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	10022	3	1	2	19	16	2	2	1	20	8	40037	20	7	160000	10	40041	40041	40042	40041	40041

FMLS (vector, 2S)

Test 1: uops

1000 unrolls and 1 iteration

Test 2: Latency 1->1

100 unrolls and 100 iterations

1000 unrolls and 10 iterations

Test 3: Latency 1->2

100 unrolls and 100 iterations

1000 unrolls and 10 iterations

Test 4: Latency 1->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