Firestorm: FMLS (by element, 2S) measurements

Code:

  fmls v0.2s, v1.2s, 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	19	1e	3f	4e	51	schedule uop (52)	schedule simd uop (54)	dispatch simd uop (57)	ldst uops in schedulers (5b)	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)	ld unit uop (a6)	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	31	0	0	61	3407	25	1000	1000	1000	531908	4018	4037	4037	3258	3	3895	1000	1000	3000	4037	4037	1	1	1001	1000	0	0	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	4018	4037	4037	3258	3	3895	1000	1000	3000	4037	4037	1	1	1001	1000	0	0	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	4018	4037	4037	3258	3	3895	1000	1000	3000	4037	4037	1	1	1001	1000	0	0	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	4018	4037	4037	3258	3	3895	1000	1000	3000	4037	4037	1	1	1001	1000	0	0	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	4018	4037	4037	3258	3	3895	1000	1000	3000	4037	4037	1	1	1001	1000	0	0	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	4018	4037	4037	3258	3	3895	1000	1000	3000	4037	4037	1	1	1001	1000	0	0	0	73	1	16	1	1	3473	1000	4038	4038	4038	4038	4038
1004	4037	30	0	0	251	3407	25	1000	1000	1000	531908	4018	4037	4037	3258	3	3895	1000	1000	3000	4037	4037	1	1	1001	1000	0	0	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	4018	4037	4037	3258	3	3895	1000	1000	3000	4037	4037	1	1	1001	1000	0	0	0	73	1	16	1	1	3473	1000	4038	4038	4038	4038	4038
1004	4037	30	0	207	61	3407	25	1000	1000	1000	533304	4018	4037	4037	3258	3	3895	1000	1163	3000	4037	4037	1	1	1001	1000	0	0	0	73	1	16	1	1	3473	1000	4038	4038	4038	4038	4038
1004	4037	30	0	0	156	3407	25	1000	1000	1096	531908	4018	4037	4037	3258	3	3895	1000	1000	3000	4037	4037	1	1	1001	1000	2	1	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.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	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	l1d cache writeback (a8)	branch cond mispred nonspec (c5)	branch mispred nonspec (cb)	cd	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	61	39407	25	10100	100	10000	100	10000	500	5706908	1	40018	40037	40037	38115	6	38740	10100	200	10008	200	30024	40037	40037	1	1	10201	100	99	100	100	10000	100	0	1	1	1	718	0	0	16	0	0	39490	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	61	39407	25	10100	100	10000	100	10000	500	5706908	1	40018	40037	40037	38115	7	38741	10100	200	10008	200	30024	40037	40037	1	1	10201	100	99	100	100	10000	100	0	1	1	1	718	0	0	16	0	0	39489	10000	100	40038	40038	40038	40038	40038
10204	40037	300	45	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	1	2	16	2	2	39479	10000	100	40038	40038	40038	40038	40038
10204	40037	299	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	2	16	2	2	39479	10000	100	40038	40086	40038	40038	40038
10204	40037	300	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	1	2	16	2	2	39479	10000	100	40038	40038	40038	40038	40038
10204	40037	299	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	1	2	16	2	2	39479	10000	100	40038	40038	40038	40038	40038
10204	40037	300	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	2	16	2	2	39479	10000	100	40085	40038	40038	40038	40038
10204	40037	300	0	61	39407	25	10100	102	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	1	2	16	2	2	39479	10000	100	40038	40038	40038	40038	40038
10204	40037	300	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	712	1	2	16	2	2	39479	10000	100	40038	40038	40038	40038	40038
10204	40037	300	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	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	mmu table walk data (08)	09	l2 tlb miss data (0b)	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	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	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
10024	40037	300	0	0	0	0	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	0	0	640	2	16	2	2	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	0	0	0	39	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	0	0	640	2	16	1	3	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	0	0	0	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	0	0	640	2	16	2	2	39473	10000	10	40132	40085	40038	40038	40086
10024	40037	300	1	0	0	0	171	176	1698	39389	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	0	0	640	2	16	2	2	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	0	0	0	0	0	61	39407	25	10010	10	10000	10	10000	50	5706908	1	40018	40037	40037	38130	3	38767	10010	20	10000	20	30516	40037	40037	1	1	10021	10	9	10	10	10000	10	1	3	0	640	2	16	2	2	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	0	0	0	12	0	726	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	0	0	640	2	16	2	2	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	0	0	0	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	0	0	640	2	16	2	2	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	0	0	0	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	0	0	640	2	16	2	2	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	1	0	0	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	0	0	640	2	16	2	2	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	0	0	0	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	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.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	09	l2 tlb miss data (0b)	18	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	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	c2	branch cond mispred nonspec (c5)	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	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	1	16	1	1	39479	0	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	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	40083	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	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	1	16	1	1	39479	0	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	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	758	1	32	1	1	39479	17	10000	100	40038	40038	40038	40038	40038
10204	40037	299	0	1	1	1185	104	103	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	1	16	1	1	39479	0	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	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	1	16	1	1	39479	0	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	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	1	16	1	1	39479	0	10000	100	40038	40038	40038	40038	40038
10204	40037	299	0	0	0	0	0	726	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	1	16	1	1	39479	0	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	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	1	16	1	1	39479	0	10000	100	40038	40038	40038	40038	40038
10204	40037	300	1	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	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)	l2 tlb miss data (0b)	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	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 cache writeback (a8)	ac	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	93	0	61	39407	25	10010	10	10000	10	10000	50	5706908	40018	0	40037	40037	38135	3	38767	10010	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	640	3	16	3	3	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	0	0	0	346	39407	44	10010	10	10000	10	10000	50	5706908	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	640	3	16	3	3	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	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	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	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	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	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	640	3	16	3	3	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	1	0	0	61	39407	25	10010	10	10000	10	10000	50	5706908	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	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	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	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	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	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	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	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	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	640	3	16	3	3	39473	10000	10	40038	40038	40038	40038	40038

Test 4: Latency 1->3

Code:

  fmls v0.2s, v1.2s, 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	09	l2 tlb miss data (0b)	18	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	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)	l1d cache writeback (a8)	ac	c2	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	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	147	0	0	710	1	16	1	1	39479	0	10000	100	40038	40038	40038	40038	40038
10204	40037	299	0	0	0	0	0	145	39407	25	10100	100	10000	100	10000	522	5708304	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	21	0	0	710	1	16	1	1	39479	0	10000	100	40038	40038	40038	40038	40038
10204	40037	299	0	0	0	0	0	61	39407	25	10100	100	10000	128	10000	500	5706908	0	40018	40037	40037	38108	3	38745	10100	200	10000	200	30000	40037	40084	1	1	10201	100	99	100	100	10000	100	0	0	138	0	0	710	1	16	1	1	39479	0	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	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	135	0	0	710	1	16	1	1	39479	0	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	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	135	0	0	710	1	16	1	1	39479	0	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	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	138	0	1	710	1	16	1	1	39479	0	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	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	153	0	0	710	1	16	0	1	39479	0	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	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	162	0	0	710	1	16	1	1	39479	0	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	0	0	0	0	441	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	192	0	0	710	1	16	1	1	39479	0	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	0	0	0	0	61	39407	25	10100	100	10000	100	10000	500	5706908	1	40018	40037	40037	38108	3	38745	10100	200	10000	204	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	162	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	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	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	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
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	129	0	640	3	16	3	3	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	144	0	640	3	16	3	3	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	0	349	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	132	0	640	3	16	3	3	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	0	0	640	3	16	3	3	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	135	0	640	3	16	3	3	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	120	0	640	3	16	3	3	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	123	0	640	3	16	3	3	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	147	0	640	3	16	3	3	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	138	0	640	3	16	3	3	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	132	0	640	3	16	3	3	39473	10000	10	40038	40038	40038	40038	40038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  fmls v0.2s, v8.2s, v9.s[1]
  movi v1.16b, 0
  fmls v1.2s, v8.2s, v9.s[1]
  movi v2.16b, 0
  fmls v2.2s, v8.2s, v9.s[1]
  movi v3.16b, 0
  fmls v3.2s, v8.2s, v9.s[1]
  movi v4.16b, 0
  fmls v4.2s, v8.2s, v9.s[1]
  movi v5.16b, 0
  fmls v5.2s, v8.2s, v9.s[1]
  movi v6.16b, 0
  fmls v6.2s, v8.2s, v9.s[1]
  movi v7.16b, 0
  fmls v7.2s, v8.2s, 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	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	c2	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
160204	20089	150	0	40	28	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	0	10111	1	16	1	1	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	150	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	10111	1	16	1	1	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	150	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	28	24	0	10111	1	16	1	1	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	150	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	10111	1	16	1	1	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	150	0	40	28	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	0	0	10111	1	16	1	1	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	150	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	0	10111	1	16	1	1	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	150	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	0	10111	1	16	1	1	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	151	0	515	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	144	0	10111	1	16	1	1	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	151	0	61	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	0	10111	1	16	1	1	20062	160000	100	20066	20066	20066	20066	20066
160204	20147	151	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	47	123	0	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	mmu table walk instruction (07)	l2 tlb miss instruction (0a)	l2 tlb miss data (0b)	18	3a	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	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	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	20088	150	1	1	0	0	0	576	27	80012	12	80000	12	80000	62	640000	1	1	0	20033	20052	20052	3	23	80012	20	80000	20	240000	20052	20052	1	1	160021	10	9	10	10	160000	10	0	0	10046	8	1	1	23	25	2	1	1	21	22	20049	2	20	1	160000	10	20053	20053	20053	20053	20053
160024	20052	151	0	1	0	0	0	155	27	80012	12	80000	12	80000	62	640000	1	1	0	20033	20052	20052	3	23	80012	20	80000	20	240000	20052	20052	1	1	160021	10	9	10	10	160000	10	0	0	10044	8	1	1	21	25	2	1	1	22	21	20049	2	20	1	160000	10	20053	20053	20053	20053	20053
160024	20052	150	1	1	0	0	0	80	27	80012	12	80000	12	80000	62	640000	1	1	0	20033	20052	20052	3	23	80012	20	80000	20	240000	20052	20052	1	1	160021	10	9	10	10	160000	10	29	156	10046	8	1	1	23	25	2	1	1	22	23	20049	2	20	1	160000	10	20053	20053	20053	20053	20053
160024	20052	150	1	0	0	0	0	130	27	80012	12	80000	12	80000	62	640000	1	0	0	20033	20052	20052	3	23	80012	20	80000	20	240000	20052	20052	1	1	160021	10	9	10	10	160000	10	0	0	10043	3	2	1	21	25	2	1	1	21	23	20049	2	20	1	160000	10	20053	20053	20053	20053	20053
160024	20052	150	2	3	0	0	0	68	27	80012	12	80000	12	80000	62	640000	1	1	5	20033	20052	20052	3	23	80012	20	80000	20	240000	20052	20052	1	1	160021	10	9	10	10	160000	10	0	0	10046	8	3	1	24	25	2	1	1	23	23	20049	2	20	1	160000	10	20053	20053	20053	20053	20053
160024	20052	150	0	1	0	0	0	106	27	80012	12	80000	12	80000	62	640000	1	1	5	20033	20052	20052	3	23	80012	20	80000	20	240000	20052	20052	1	1	160021	10	9	10	10	160000	10	0	0	10048	8	2	1	23	25	2	1	1	22	23	20049	2	20	1	160000	10	20053	20053	20053	20053	20053
160024	20052	150	1	1	0	0	0	68	27	80012	12	80000	12	80000	62	640000	1	0	5	20033	20052	20052	3	23	80012	20	80000	20	240000	20052	20052	1	1	160021	10	9	10	10	160000	10	0	0	10044	8	2	1	23	25	2	1	1	22	22	20049	2	20	1	160000	10	20055	20055	20053	20053	20053
160024	20052	150	2	2	0	0	0	222	27	80012	12	80000	12	80000	62	640000	1	1	5	20033	20052	20052	3	23	80012	20	80000	20	240000	20052	20052	1	1	160021	10	9	10	10	160000	10	0	0	10045	3	1	1	23	25	2	1	1	26	23	20049	2	20	1	160000	10	20053	20053	20053	20053	20053
160024	20052	150	2	2	0	0	0	132	69	80012	12	80000	12	80000	62	640000	1	0	5	20033	20052	20052	3	23	80012	20	80000	20	240000	20052	20052	1	1	160021	10	9	10	10	160000	10	0	0	10045	3	1	1	22	25	2	1	1	22	22	20049	2	20	1	160000	10	20053	20062	20053	20053	20053
160024	20052	150	1	1	0	0	0	88	27	80012	12	80000	12	80000	62	640000	1	0	5	20033	20052	20052	3	23	80012	20	80000	20	240000	20052	20052	1	1	160021	10	9	10	10	160000	10	37	12	10046	8	2	1	23	25	2	1	1	23	23	20049	2	20	1	160000	10	20062	20053	20053	20053	20062

Test 6: throughput

Count: 12

Code:

  fmls v0.2s, v12.2s, v13.s[1]
  fmls v1.2s, v12.2s, v13.s[1]
  fmls v2.2s, v12.2s, v13.s[1]
  fmls v3.2s, v12.2s, v13.s[1]
  fmls v4.2s, v12.2s, v13.s[1]
  fmls v5.2s, v12.2s, v13.s[1]
  fmls v6.2s, v12.2s, v13.s[1]
  fmls v7.2s, v12.2s, v13.s[1]
  fmls v8.2s, v12.2s, v13.s[1]
  fmls v9.2s, v12.2s, v13.s[1]
  fmls v10.2s, v12.2s, v13.s[1]
  fmls v11.2s, v12.2s, 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	mmu table walk data (08)	09	l2 tlb miss data (0b)	18	1e	1f	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)	st unit uop (a7)	l1d cache writeback (a8)	a9	ac	c2	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
120204	40039	299	0	0	0	0	9	0	0	1016	9961	25	120101	100	120000	100	120000	500	5630640	0	40020	41687	40039	25370	3	24997	120100	200	120000	200	360000	40039	41688	1	1	120201	100	99	100	100	120000	100	0	0	0	0	0	0	0	7610	3	16	1	1	41682	0	120000	100	40040	40040	41689	40040	40040
120204	40039	300	1	0	0	0	264	0	1	763	9961	25	120279	100	120002	100	120000	500	5630640	0	40020	40039	40492	24932	3	26649	120100	200	120000	200	360000	40039	40039	1	1	120201	100	99	100	100	120000	100	0	0	0	0	0	0	2	7610	1	16	1	1	40030	0	120000	100	40565	41688	40040	40040	40040
120204	40039	312	0	0	0	1	0	0	1	61	9961	25	120267	100	120000	100	120000	500	5630640	1	40020	40039	40708	24932	3	24997	120100	200	120000	200	360000	40809	40039	1	1	120201	100	99	100	100	120000	100	0	0	0	0	0	0	0	7656	1	16	1	1	40030	0	120000	100	40040	40040	41689	40040	41689
120204	40039	300	0	0	0	0	0	0	3	82	9961	25	120101	100	120000	100	120000	500	5630640	1	40020	42338	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	0	0	7610	1	16	1	1	40030	0	120000	100	40040	40040	40040	42471	40040
120204	40039	312	0	0	0	0	0	0	0	559	9961	25	120101	100	120000	100	120000	500	5630640	1	40020	40039	41688	24932	3	24997	120100	200	120000	200	360000	40039	41688	1	1	120201	100	99	100	100	120000	100	0	0	0	0	0	0	0	7657	1	16	1	1	41692	0	120000	100	41689	41692	41700	41702	40040
120204	40039	313	0	0	0	0	0	0	0	416	9961	25	120101	100	120000	100	120000	500	5630640	1	40020	40039	40039	24932	16	24997	120100	200	120000	200	360000	40039	41688	1	1	120201	100	99	100	100	120000	100	0	0	0	0	0	0	0	7610	1	16	1	1	40030	0	120000	100	40040	40040	41689	40040	41689
120204	41216	300	0	0	0	0	0	0	0	210	37199	25	120100	100	120000	100	120000	500	5856942	1	40020	41688	40039	26579	3	26645	120100	200	120000	200	360000	41688	40525	1	1	120201	100	99	100	100	120000	100	0	0	0	0	0	0	0	7610	1	16	1	1	41682	0	120000	100	40040	40040	41689	40040	40040
120204	41687	300	0	0	0	0	0	0	0	534	9961	25	120100	100	120000	100	120000	500	5630640	0	40020	40039	41688	24932	3	24997	120100	200	120000	200	360000	40039	41688	1	1	120201	100	99	100	100	120000	100	0	0	0	0	0	0	0	7610	1	16	1	1	40030	0	120000	100	41689	40040	40040	41688	40040
120204	41687	299	0	0	0	0	0	0	1	641	9961	25	120100	100	120000	100	120000	500	5630640	1	40020	40039	41688	24932	3	24997	120100	200	120000	200	360000	40039	41688	1	1	120201	100	99	100	100	120000	100	0	0	0	0	0	0	0	7610	1	16	1	1	40030	0	120000	100	40040	41689	40040	40040	40040
120204	40039	300	0	0	0	0	0	0	0	513	9961	25	120101	100	120000	100	120000	545	5630640	0	40020	41688	40039	26564	3	24997	120100	200	120000	200	360000	40039	41688	1	1	120201	100	99	100	100	120000	100	0	0	2	0	0	0	0	7610	1	25	1	1	40030	0	120000	100	40040	40452	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	l2 tlb miss data (0b)	19	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)	5f	60	61	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)	ac	cf	d0	d2	l1i cache miss demand (d3)	d5	map dispatch bubble (d6)	d9	da	db	dd	fetch restart (de)	e0	ea	eb	ec	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
120024	40039	300	0	0	0	0	14	349	9961	25	120010	10	120000	10	120000	50	5630640	1	1	5	40020	0	40039	40039	24955	3	26666	120010	20	120000	20	360000	40039	40039	1	1	120021	10	9	10	10	120000	10	0	0	7522	3	2	1	20	16	2	1	1	17	17	40030	15	9	4	120000	10	40040	40040	40040	40040	40040
120024	40039	299	0	0	0	0	7	176	9961	25	120010	10	120000	10	120000	50	5630640	1	1	5	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	7522	8	1	1	17	16	2	1	1	19	17	40030	15	9	4	120000	10	40040	40040	40040	40040	40040
120024	40039	300	0	0	0	0	7	111	9961	25	120010	10	120000	10	120000	50	5630640	0	0	5	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	7522	8	2	1	18	16	2	1	1	20	18	40030	15	9	4	120000	10	40040	40040	40040	40040	41687
120024	40039	299	0	0	0	0	6	233	9961	25	120010	10	120000	10	120000	50	5630640	1	0	5	40020	0	40039	41691	24955	3	25019	120010	20	120000	20	360000	40039	40039	1	1	120021	10	9	10	10	120000	10	0	0	7522	3	2	2	19	16	2	1	1	18	17	40030	15	9	4	120000	10	40040	40040	40040	40040	40040
120024	41691	300	0	0	0	0	6	176	9961	25	120010	10	120000	10	120000	50	5630640	1	1	5	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	7522	8	2	1	16	16	2	1	1	15	15	40030	15	9	4	120000	10	40040	40040	40040	40040	40040
120024	40039	299	0	0	0	0	9	220	9961	25	120010	10	120000	10	120000	50	5630640	1	1	5	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	7522	8	1	1	19	16	2	1	1	20	19	40030	15	9	4	120000	10	40040	40040	40040	40040	40040
120024	40039	300	0	0	0	0	6	155	9961	25	120010	10	120000	10	120000	50	5630640	1	1	0	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	7522	8	1	1	18	16	2	1	1	19	18	40030	15	9	4	120000	10	40040	40040	40040	40040	40040
120024	40039	300	0	0	0	0	6	161	9961	25	120010	10	120000	10	120000	50	5630640	1	0	5	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	7522	8	2	1	17	16	2	1	1	19	18	40030	15	9	4	120000	10	40040	40040	40040	40040	40040
120024	40039	300	0	0	0	0	7	197	9961	25	120010	10	120000	10	120000	50	5630640	1	1	5	41682	0	40039	40039	24955	3	25019	120010	20	120000	20	360000	40039	40039	1	1	120021	10	9	10	10	120000	10	0	0	7522	11	2	1	12	16	2	1	1	17	16	40030	15	9	7	120000	10	40040	41687	40040	40040	40040
120024	40039	299	0	0	0	0	5	161	9961	25	120010	10	120001	10	120000	50	5630640	0	1	5	40020	0	40039	40039	24955	3	27450	120010	20	120000	20	360000	40039	40039	1	1	120021	10	9	10	10	120000	10	0	0	7522	8	1	1	18	16	2	1	1	17	18	40030	15	8	4	120000	10	40040	40040	40040	40040	40040

FMLS (by element, 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