Firestorm: FMLS (by element, S) measurements

Code:

  fmls s0, s1, v2.s[1]

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	09	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)	l1d tlb access (a0)	st unit uop (a7)	l1d cache writeback (a8)	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	0	0	0	73	2	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	0	1	0	73	2	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	0	0	0	73	2	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	0	27	3	73	2	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	0	0	3675	73	2	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	0	0	0	73	2	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	0	0	69	73	2	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	0	0	105	73	2	16	2	2	3473	1000	4038	4038	4038	4038	4038
1004	4037	30	0	0	61	3407	25	1000	1000	1000	531908	1	4018	4037	4037	3258	3	3895	1000	1000	3000	4037	4037	1	1	1001	1000	0	0	0	6	73	2	16	2	2	3473	1000	4038	4038	4038	4038	4038
1004	4037	30	0	0	61	3407	25	1000	1000	1000	531908	1	4018	4037	4037	3258	3	3895	1000	1000	3000	4037	4037	1	1	1001	1000	0	0	0	0	73	2	16	2	2	3476	1000	4038	4038	4038	4038	4038

Test 2: Latency 1->1

Code:

  fmls s0, s1, v2.s[1]

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	mmu table walk data (08)	19	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)	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 cache writeback (a8)	a9	ac	c2	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	300	0	0	0	0	61	39407	25	10100	100	10000	100	10000	500	5706908	1	40018	40037	40037	38108	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	710	0	3	16	3	3	39479	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	0	0	0	61	39407	25	10100	100	10000	100	10000	500	5706908	0	40018	40037	40037	38108	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	1	0	0	710	1	3	16	3	3	39479	10000	100	40038	40086	40038	40038	40038
10204	40037	300	0	0	0	0	61	39407	25	10100	100	10000	100	10000	500	5706908	0	40018	40037	40037	38108	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	710	1	3	16	3	3	39479	10000	100	40038	40038	40038	40038	40038
10204	40037	299	0	0	0	0	61	39407	25	10100	100	10000	100	10000	500	5706908	0	40018	40037	40037	38108	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	710	1	3	16	4	3	39479	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	0	0	0	61	39407	25	10100	100	10000	100	10000	500	5706908	0	40018	40037	40037	38108	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	710	1	3	16	3	3	39479	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	0	0	0	61	39407	25	10100	100	10000	100	10000	500	5706908	0	40018	40037	40037	38108	3	38745	10100	200	10000	200	30000	40037	40085	2	1	10201	100	99	100	100	10000	100	0	0	0	0	710	1	3	16	3	3	39479	10000	100	40038	40038	40038	40038	40038
10204	40037	299	0	0	0	0	61	39407	25	10100	100	10000	100	10000	500	5706908	0	40018	40037	40037	38108	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	710	1	4	16	4	3	39479	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	0	0	0	94	39407	25	10100	100	10006	100	10000	500	5706908	0	40018	40037	40037	38108	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	710	1	3	16	3	3	39479	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	0	0	1	61	39407	25	10100	100	10000	100	10000	500	5706908	0	40018	40037	40037	38108	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	710	1	3	16	3	3	39479	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	0	0	0	61	39407	25	10100	100	10000	100	10000	500	5706908	0	40018	40037	40037	38108	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	710	1	3	16	3	3	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	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)	60	69	6b	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)	a9	ac	branch cond mispred nonspec (c5)	cd	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10024	40037	299	0	0	0	0	61	39407	25	10010	10	10000	10	10000	50	5706908	1	40018	0	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	6	16	3	3	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	0	0	0	61	39407	25	10010	10	10000	10	10000	50	5706908	1	40018	0	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	4	16	3	4	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	0	0	0	61	39407	25	10010	10	10000	10	10000	50	5706908	1	40018	0	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	0	61	39407	25	10010	10	10000	10	10000	50	5706908	1	40018	0	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	5	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	299	0	0	0	0	61	39407	25	10010	10	10000	10	10000	50	5706908	1	40018	0	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	0	61	39407	25	10010	10	10000	10	10000	50	5706908	1	40018	0	40037	40037	38130	3	38767	10010	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	1	0	0	0	0	640	4	16	4	3	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	0	0	0	61	39407	25	10010	10	10000	10	10000	50	5706908	1	40018	0	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	4	16	3	3	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	0	0	0	61	39407	25	10010	10	10000	10	10000	50	5706908	1	40018	0	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	4	3	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	0	0	0	61	39407	25	10010	10	10000	10	10000	50	5706908	1	40018	0	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	4	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	0	0	0	61	39407	25	10010	10	10000	10	10000	50	5706908	1	40018	0	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	4	16	4	3	39473	10000	10	40038	40038	40038	40038	40038

Test 3: Latency 1->2

Code:

  fmls s0, s0, v1.s[1]

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)	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 miss (a1)	l1d cache writeback (a8)	a9	ac	c2	branch cond mispred nonspec (c5)	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	eb	? 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	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	0	0	710	1	16	1	1	39479	0	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	61	39407	25	10100	100	10000	100	10000	500	5706908	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	27	0	0	710	1	16	1	1	39479	0	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	726	39407	25	10100	100	10000	100	10000	500	5706908	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	1	0	144	0	0	710	1	16	1	1	39479	0	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	61	39407	25	10100	100	10000	100	10000	500	5706908	40018	0	40037	40037	38108	0	12	38779	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	0	99	4	0	710	1	16	1	1	39479	0	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	61	39407	25	10100	100	10000	100	10000	500	5706908	40018	0	40037	40037	38108	0	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10202	100	99	100	100	10000	100	0	0	0	18	0	0	710	1	16	1	1	39479	0	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	61	39407	25	10100	100	10000	100	10000	500	5706908	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	21	0	0	710	1	16	1	1	39479	0	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	61	39407	25	10100	100	10000	100	10000	500	5706908	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	42	0	0	710	1	16	1	1	39479	0	10000	100	40038	40038	40038	40038	40038
10204	40037	299	0	61	39407	25	10100	100	10000	100	10000	500	5706908	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	30	0	0	710	1	16	1	1	39479	0	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	61	39407	25	10100	100	10000	100	10000	585	5709700	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	2	117	0	0	710	1	16	1	1	39479	0	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	61	39407	25	10100	100	10000	100	10000	500	5706908	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	21	0	0	710	2	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	09	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	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	c2	branch mispred nonspec (cb)	cd	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	61	39407	25	10010	10	10000	10	10000	50	5706908	0	40018	40037	40037	38130	3	38767	10010	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	2	0	12	0	0	0	640	2	16	2	2	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	0	61	39407	25	10010	10	10000	10	10000	50	5706908	1	40018	40037	40037	38130	3	38767	10010	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	1	0	3	0	0	0	640	2	16	2	2	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	0	61	39407	25	10010	10	10000	10	10000	50	5706908	1	40018	40037	40037	38130	3	38767	10010	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	23	0	0	0	0	0	640	2	16	2	2	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	0	61	39407	25	10010	10	10000	10	10000	50	5706908	1	40018	40037	40037	38130	3	38767	10010	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	1	0	6	0	0	0	640	2	16	2	2	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	299	0	0	61	39407	25	10010	10	10000	10	10000	50	5706908	1	40018	40037	40037	38130	3	38767	10010	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	40	0	6	0	0	0	640	2	16	2	2	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	0	61	39407	25	10010	10	10000	10	10000	50	5706908	0	40018	40037	40037	38130	3	38767	10010	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	8	0	9	0	0	0	640	2	16	2	2	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	0	61	39407	25	10010	10	10000	10	10000	50	5706908	0	40018	40037	40037	38130	3	38767	10010	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	32	0	0	0	0	0	640	2	16	2	2	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	0	61	39407	25	10010	10	10000	10	10000	50	5706908	1	40018	40037	40037	38130	3	38767	10010	20	10000	22	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	11	0	6	0	0	0	640	2	16	2	2	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	0	61	39407	25	10010	10	10000	10	10000	50	5706908	0	40018	40037	40037	38130	3	38767	10010	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	18	0	12	0	0	0	640	2	16	2	2	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	299	0	0	103	39407	25	10010	10	10000	10	10000	50	5706908	1	40018	40131	40037	38130	3	38767	10010	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	14	2	0	2	0	0	640	1	33	2	2	39473	10000	10	40038	40038	40038	40038	40038

Test 4: Latency 1->3

Code:

  fmls s0, s1, v0.s[1]

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)	19	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 cache writeback (a8)	ac	branch mispred nonspec (cb)	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	299	0	0	0	136	39407	25	10100	100	10000	100	10148	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	5	0	0	710	1	16	1	1	39479	0	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	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	28	0	0	710	1	16	1	1	39479	0	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	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	59	0	0	710	1	16	1	1	39479	0	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	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	9	15	0	710	1	16	1	1	39479	0	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	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	9	12	0	710	1	16	1	1	39479	0	10000	100	40038	40038	40038	40038	40038
10204	40037	299	0	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	4	15	0	710	1	16	1	1	39551	0	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	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	7	12	0	710	1	16	1	1	39479	0	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	0	0	61	39407	25	10100	100	10006	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	7	9	0	710	1	16	1	1	39479	0	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	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	1	57	0	710	1	16	1	1	39479	0	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	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	8	12	1	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	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)	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	ld unit uop (a6)	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	299	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	1	0	0	640	2	16	2	2	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	299	0	0	61	39407	25	10035	10	10000	10	10000	50	5706908	40018	40084	40085	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	0	536	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	0	640	2	16	2	2	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	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	4	0	0	640	2	16	2	2	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	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	4	0	0	640	2	16	2	2	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	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	3	0	0	640	2	16	2	2	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	0	726	39407	104	10010	12	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	4	0	0	640	2	16	2	2	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	0	943	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	0	640	2	16	2	2	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	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	2	0	0	640	2	16	2	2	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	57	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	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 s0, s8, v9.s[1]
  movi v1.16b, 0
  fmls s1, s8, v9.s[1]
  movi v2.16b, 0
  fmls s2, s8, v9.s[1]
  movi v3.16b, 0
  fmls s3, s8, v9.s[1]
  movi v4.16b, 0
  fmls s4, s8, v9.s[1]
  movi v5.16b, 0
  fmls s5, s8, v9.s[1]
  movi v6.16b, 0
  fmls s6, s8, v9.s[1]
  movi v7.16b, 0
  fmls s7, s8, v9.s[1]

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	19	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 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	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
160204	20077	150	0	0	40	25	80100	100	80000	100	80000	500	640000	0	20046	20065	20065	3	23	80100	200	80000	200	240000	20065	20065	1	1	160201	100	99	100	100	160000	100	0	0	10111	1	16	1	1	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	150	0	0	40	25	80100	100	80000	100	80000	500	640000	0	20046	20065	20065	3	23	80100	200	80000	200	240000	20065	20065	1	1	160201	100	99	100	100	160000	100	0	0	10111	1	16	1	1	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	150	0	0	40	25	80100	100	80000	100	80000	500	640000	0	20046	20065	20065	3	23	80100	200	80000	200	240000	20065	20065	1	1	160201	100	99	100	100	160000	100	0	0	10111	1	16	1	1	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	150	0	0	40	25	80100	100	80000	108	80109	500	640000	0	20046	20065	20065	3	23	80100	200	80000	200	240000	20065	20065	1	1	160201	100	99	100	100	160000	100	38	168	10111	1	16	1	1	20152	160000	100	20066	20066	20066	20066	20066
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	1	3	10111	1	16	1	1	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	150	0	0	40	25	80100	100	80000	100	80000	500	640000	0	20046	20065	20065	3	23	80100	200	80000	200	240000	20065	20065	1	1	160201	100	99	100	100	160000	100	1	0	10111	1	16	1	1	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	150	0	0	40	25	80100	100	80000	100	80000	500	640000	0	20046	20065	20065	3	23	80100	200	80000	200	240000	20065	20065	1	1	160201	100	99	100	100	160000	100	2	0	10111	1	16	1	1	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	150	0	9	40	25	80100	100	80000	100	80000	500	640000	0	20046	20065	20065	3	23	80100	200	80000	200	240000	20065	20065	1	1	160201	100	99	100	100	160000	100	1	0	10111	1	16	1	1	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	150	0	0	40	25	80562	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	50	96	10111	1	16	1	1	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	151	0	0	40	25	80100	100	80000	100	80000	500	640000	0	20046	20065	20065	3	23	80100	200	80000	200	240000	20065	20065	1	1	160201	100	99	100	100	160000	100	44	3	10111	1	16	1	1	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	l2 tlb miss data (0b)	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)	5f	60	61	69	6b	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	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	ec	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
160024	20062	150	0	0	46	27	80012	12	80000	12	80000	62	640000	1	1	5	20033	0	20052	20052	3	23	80012	20	80000	20	240000	20052	20061	1	1	160021	10	9	10	10	160000	10	0	0	0	10030	8	3	1	5	25	2	1	1	7	6	20049	2	20	1	160000	10	20053	20053	20053	20053	20053
160024	20052	150	0	0	46	27	80012	12	80000	12	80000	62	640000	1	1	5	20033	0	20052	20052	3	23	80012	20	80000	20	240000	20052	20052	1	1	160021	10	9	10	10	160000	10	1	0	0	10028	8	2	1	7	25	2	1	1	5	5	20049	2	20	1	160000	10	20053	20053	20053	20053	20053
160024	20052	150	0	0	46	27	80012	12	80000	12	80000	62	640000	1	1	5	20033	0	20052	20052	3	23	80012	20	80000	20	240000	20052	20052	1	1	160021	10	9	10	10	160000	10	1	0	0	10028	8	3	1	7	25	2	1	1	6	6	20049	2	20	1	160000	10	20053	20053	20053	20053	20053
160024	20052	150	0	0	46	27	80012	12	80000	12	80000	62	640000	1	1	5	20033	0	20052	20052	3	23	80012	20	80000	20	240000	20052	20052	1	1	160021	10	9	10	10	160000	10	0	0	0	10030	8	3	1	5	25	2	1	1	5	6	20049	2	20	1	160000	10	20053	20053	20053	20053	20053
160024	20052	150	0	0	46	27	80012	12	80000	12	80000	62	640000	1	1	5	20033	0	20052	20052	3	23	80012	20	80109	20	240000	20052	20052	1	1	160021	10	9	10	10	160000	10	49	0	0	10030	8	3	1	7	25	2	1	1	5	4	20049	2	20	1	160000	10	20053	20053	20053	20053	20053
160024	20052	150	0	0	46	27	80012	12	80000	12	80000	62	640000	1	1	5	20033	0	20052	20052	3	23	80012	20	80000	20	240000	20052	20052	1	1	160021	10	9	10	10	160000	10	0	0	0	10028	8	3	1	6	25	2	1	1	6	6	20049	2	20	1	160000	10	20053	20053	20053	20053	20053
160024	20052	150	0	0	46	27	80012	12	80000	12	80000	62	640000	1	1	5	20033	0	20052	20052	3	23	80012	20	80000	20	240000	20052	20052	1	1	160021	10	9	10	10	160000	10	0	0	0	10028	8	3	1	7	25	2	1	1	5	4	20049	2	20	1	160000	10	20053	20053	20053	20053	20053
160024	20052	150	0	0	46	27	80012	12	80000	12	80000	62	640000	1	1	5	20033	0	20052	20052	3	23	80012	20	80000	20	240000	20052	20052	1	1	160021	10	9	10	10	160000	10	44	0	3	10029	8	3	1	6	25	2	1	1	8	7	20049	2	20	1	160000	10	20053	20053	20053	20053	20053
160024	20052	150	0	0	46	27	80012	12	80000	12	80000	62	640000	1	1	5	20033	0	20052	20052	3	23	80012	20	80000	20	240000	20052	20052	1	1	160021	10	9	10	10	160000	10	0	0	0	10030	8	3	1	7	25	2	1	1	7	7	20049	2	20	1	160000	10	20053	20053	20053	20053	20053
160024	20052	150	0	0	46	85	80012	12	80217	12	80000	62	640000	1	1	5	20033	0	20052	20052	3	23	80012	20	80000	20	240000	20052	20052	1	1	160021	10	9	10	10	160000	10	0	0	0	10028	8	3	1	7	25	2	1	1	6	6	20049	2	20	1	160000	10	20053	20053	20053	20053	20053

Test 6: throughput

Count: 12

Code:

  fmls s0, s12, v13.s[1]
  fmls s1, s12, v13.s[1]
  fmls s2, s12, v13.s[1]
  fmls s3, s12, v13.s[1]
  fmls s4, s12, v13.s[1]
  fmls s5, s12, v13.s[1]
  fmls s6, s12, v13.s[1]
  fmls s7, s12, v13.s[1]
  fmls s8, s12, v13.s[1]
  fmls s9, s12, v13.s[1]
  fmls s10, s12, v13.s[1]
  fmls s11, s12, v13.s[1]

Initialization

  movi v12.16b, 13
  movi v13.16b, 14

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.3337

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

retire uop (01)	cycle (02)	03	18	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	6b	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)	st unit uop (a7)	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
120204	40984	300	0	0	0	61	9961	25	120100	100	120000	100	120000	500	5851993	1	41672	0	41691	40039	24932	3	24997	120100	200	120000	200	360000	41687	40039	1	1	120201	100	99	100	100	120000	100	0	0	0	0	0	7610	1	16	1	1	40030	120000	100	41692	40040	41692	40040	41692
120204	41691	300	0	12	0	61	26081	25	120100	100	120000	100	120000	500	5851869	1	40020	0	40039	40039	24932	3	24997	120100	200	120000	200	360000	40039	40039	1	1	120201	100	99	100	100	120000	100	0	0	0	0	0	7610	1	16	1	1	40030	120000	100	41692	40040	41692	40040	41692
120204	41691	299	0	0	0	232	37966	25	120101	100	120001	100	120000	500	5630640	1	41672	0	41691	40039	24932	3	24997	120100	200	120000	200	360000	40039	41691	1	1	120201	100	99	100	100	120000	100	0	1	2	0	0	7610	1	16	1	1	40030	120000	100	41692	40040	41692	40040	41692
120204	41691	299	0	0	1	189	9961	25	120100	100	120000	100	120000	500	5630640	1	40020	0	40039	41691	26582	3	24997	120100	200	120000	200	360000	40039	41691	1	1	120201	100	99	100	100	120000	100	0	0	0	0	0	7610	1	16	1	1	40030	120000	100	40040	40040	41692	40040	41692
120204	41691	300	0	0	1	61	37966	25	120101	100	120001	100	120000	500	5851869	1	41672	0	41691	40039	24932	3	24997	120303	200	120000	200	360000	41691	41686	1	1	120201	100	99	100	100	120000	100	2	0	0	0	0	7610	1	16	1	1	40030	120000	100	40040	41692	40040	41226	41692
120204	41691	299	0	0	0	61	9961	25	120101	100	120001	100	120000	500	5630640	1	40020	0	40039	41691	26582	3	26644	120100	200	120000	200	360000	41691	40039	1	1	120201	100	99	100	100	120000	100	0	0	0	0	0	7610	1	16	1	1	40030	120000	100	40040	40040	41692	40040	41692
120204	41691	300	0	0	1	61	9961	25	120200	100	120000	100	120000	500	5851869	0	41667	0	41691	41686	24932	3	24997	120100	200	120000	200	360000	40039	41691	1	1	120201	100	99	100	100	120000	100	0	0	0	0	0	7610	1	16	1	1	40030	120000	100	40040	40040	40040	40040	40040
120204	40039	312	0	0	0	61	9961	25	120100	100	120000	100	120000	500	5851869	0	40020	0	40039	40039	24932	3	24997	120100	200	120000	200	360000	40039	41691	1	1	120201	100	99	100	100	120000	100	0	0	0	0	0	7610	1	16	1	1	40030	120000	100	40040	40040	41692	40040	41692
120204	41691	300	0	0	0	61	9961	25	120100	100	120000	100	120000	500	5851869	1	40020	0	40039	41691	24932	3	24997	120100	200	120000	200	360000	40039	40039	1	1	120201	100	99	100	100	120000	100	0	0	0	0	0	7610	1	16	1	1	41683	120000	100	40040	41692	40040	41687	41692
120204	41691	300	0	0	0	61	9961	25	120100	100	120000	100	120000	500	5851869	1	41667	0	41691	40039	24932	3	24997	120100	200	120000	200	360000	40039	41691	1	1	120201	100	99	100	100	120000	100	0	0	0	0	0	7610	1	16	1	1	40030	120000	100	40040	41692	40040	40040	40040

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.3337

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

retire uop (01)	cycle (02)	03	mmu table walk data (08)	1e	37	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	6b	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)	st unit uop (a7)	l1d cache writeback (a8)	a9	ac	cf	d0	d5	map dispatch bubble (d6)	d9	dd	fetch restart (de)	df	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
120024	40039	312	0	0	0	0	61	9961	25	120010	10	120000	10	120000	50	5630640	40020	0	40039	40039	24955	3	25019	120010	20	120000	20	360000	40039	41688	1	1	120021	10	9	10	10	120000	10	0	0	0	0	0	0	7520	0	12	16	0	10	11	0	40030	120000	10	40040	40040	40040	40040	40088
120024	40039	300	0	0	0	0	61	9961	25	120010	10	120000	10	120000	50	5630640	41667	0	40039	40039	24955	3	25019	120010	20	120000	20	360000	40039	41686	1	1	120021	10	9	10	10	120000	10	0	0	0	0	0	0	7530	0	11	16	0	11	11	0	40030	120000	10	40040	40040	40040	40040	40040
120024	40039	299	0	0	0	0	61	9961	25	120010	10	120000	10	120000	50	5630640	40020	0	40039	40039	24955	3	25019	120010	20	120000	20	360000	40039	40039	1	1	120021	10	9	10	10	120000	10	0	0	0	0	0	0	7520	0	13	16	0	12	11	0	40030	120000	10	40040	40040	40040	40040	40040
120024	41686	300	0	0	0	0	61	9961	25	120010	10	120000	10	120000	50	5630640	40020	0	40039	40039	24955	3	25019	120010	20	120000	20	360000	40039	41721	2	1	120021	10	9	10	10	120000	10	0	0	0	0	0	0	7520	0	10	16	0	11	10	0	41693	120000	10	40040	40040	41687	40040	40040
120024	40039	300	0	0	0	0	61	9961	25	120010	10	120000	10	120000	50	5851869	40020	0	41686	40039	24955	3	25019	120010	20	120000	20	360000	40039	40039	1	1	120021	10	9	10	10	120000	10	0	0	0	0	0	0	7520	0	12	16	0	10	12	0	40030	120000	10	40040	40040	40040	40040	40040
120024	40039	299	0	0	0	0	61	9961	25	120013	10	120004	10	120000	50	5630640	40020	0	40039	40039	24955	3	25019	120010	20	120000	20	360000	40039	40039	1	1	120021	10	9	10	10	120000	10	0	0	0	0	0	0	7520	0	10	16	0	11	12	0	40030	120000	10	41692	41692	41688	40040	40040
120024	40039	312	0	0	0	0	156	35689	25	120010	10	120000	10	120000	50	5851869	41667	0	40039	40039	24955	27	25019	120010	20	120000	20	360000	40039	40039	1	1	120021	10	9	10	10	120000	10	0	0	0	0	0	0	7520	0	12	16	0	10	12	0	40030	120000	10	40040	40040	40040	40040	40040
120024	41686	300	0	0	0	0	61	9961	25	120010	10	120000	10	120000	50	5851993	40020	0	40039	40039	24955	3	25019	120010	20	120000	20	360000	40039	40868	1	1	120021	10	9	10	10	120000	10	0	0	0	0	0	0	7520	0	12	16	0	13	10	2	40030	120000	10	40040	41687	40040	40040	40040
120024	40039	300	0	12	0	0	61	9961	25	120010	10	120000	10	120000	50	5630640	40020	0	41686	40039	24955	3	25019	120010	20	120000	20	360000	40039	41691	1	1	120021	10	9	10	10	120000	10	0	0	0	0	0	0	7520	0	13	16	2	12	11	0	40030	120000	10	40040	40040	40040	40040	40040
120024	40039	300	1	0	0	0	61	9961	25	120010	10	120000	10	120000	50	5630640	40020	0	40039	40039	24955	3	25019	120010	20	120000	20	360000	40039	40039	1	1	120021	10	9	10	10	120000	10	0	0	0	0	0	0	7520	6	13	16	0	12	12	0	40030	120000	10	40040	40040	40040	40040	40040

FMLS (by element, S)

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