Firestorm: FMLA (by element, S) measurements

Code:

  fmla 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	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)	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	1	4018	4037	4037	3258	3	3895	1000	1000	3000	4037	4037	1	1	1001	1000	73	1	16	1	1	3473	1000	4038	4038	4038	4038	4038
1004	4037	30	0	0	82	3407	25	1000	1000	1000	531908	1	4018	4037	4037	3258	3	3895	1000	1000	3000	4037	4037	1	1	1001	1000	73	1	16	1	1	3473	1000	4038	4038	4038	4038	4038
1004	4037	30	0	0	103	3407	25	1000	1000	1000	531908	1	4018	4037	4037	3258	3	3895	1000	1000	3000	4037	4037	1	1	1001	1000	73	1	16	1	1	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	73	1	16	1	1	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	73	1	16	1	1	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	73	1	16	1	1	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	73	1	16	1	1	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	73	1	16	1	1	3473	1000	4038	4038	4038	4038	4038
1004	4037	30	0	6	251	3407	25	1000	1000	1000	531908	1	4018	4037	4037	3258	3	3895	1000	1000	3000	4037	4037	1	1	1001	1000	73	1	16	1	1	3473	1000	4038	4038	4038	4038	4038
1004	4037	30	0	24	61	3407	25	1000	1000	1000	531908	1	4018	4037	4037	3258	3	3895	1000	1000	3000	4037	4037	1	1	1001	1000	73	1	16	1	1	3549	1000	4038	4038	4038	4038	4038

Test 2: Latency 1->1

Code:

  fmla 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	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)	branch mispred nonspec (cb)	cf	d0	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	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	710	1	2	16	2	2	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	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	710	1	2	16	2	2	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	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	710	1	2	16	2	2	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	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	710	1	2	16	2	2	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	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	710	1	2	16	2	2	39479	0	10000	100	40038	40086	40038	40038	40038
10204	40037	299	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	712	1	2	16	2	2	39479	0	10000	100	40038	40038	40038	40038	40038
10204	40037	299	0	0	0	147	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	710	1	2	16	2	2	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	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	710	1	2	16	2	2	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	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	710	1	2	16	2	3	39479	0	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	0	0	61	39407	25	10100	100	10000	100	10000	500	5707439	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	710	1	3	16	2	2	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	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)	ac	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
10024	40037	300	0	0	0	61	39407	25	10010	10	10000	10	10000	50	5706908	0	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	640	4	16	3	3	39473	0	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	0	0	61	39407	45	10010	10	10000	10	10000	50	5706908	0	40018	0	40037	40037	38130	3	38767	10010	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	3	640	3	16	3	4	39473	0	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	0	0	61	39407	25	10010	10	10000	10	10000	50	5706908	0	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	640	3	16	3	3	39473	0	10000	10	40038	40038	40038	40038	40038
10024	40037	299	0	0	0	61	39407	25	10010	10	10000	10	10000	50	5706908	0	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	640	3	16	3	4	39473	0	10000	10	40038	40038	40038	40038	40038
10024	40037	299	0	0	0	726	39407	25	10010	10	10000	10	10000	50	5706908	0	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	640	3	16	3	3	39473	0	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	0	0	61	39407	25	10010	10	10000	10	10000	50	5706908	0	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	640	3	16	3	4	39473	0	10000	10	40038	40038	40038	40071	40038
10024	40037	299	0	0	0	61	39407	25	10010	10	10000	10	10000	50	5706908	0	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	640	3	16	3	4	39473	0	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	0	0	61	39407	25	10010	10	10000	10	10000	50	5706908	0	40018	3	40037	40037	38130	3	38767	10010	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	0	640	3	16	3	4	39473	0	10000	10	40038	40038	40038	40038	40038
10024	40037	299	0	0	0	61	39407	25	10010	10	10000	10	10000	50	5706908	0	40018	0	40037	40037	38130	3	38767	10010	20	10172	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	0	640	3	16	3	3	39473	0	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	0	0	82	39407	25	10010	10	10000	10	10000	50	5706908	0	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	640	3	16	3	3	39473	0	10000	10	40038	40038	40038	40038	40038

Test 3: Latency 1->2

Code:

  fmla 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)	60	61	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	ac	branch mispred nonspec (cb)	cf	d0	d2	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	61	39407	25	10100	100	10000	100	10000	500	5706908	0	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	710	0	0	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	0	40018	40037	40037	38108	3	38745	10263	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	710	0	0	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	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	710	0	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	5	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	5	1	2	16	2	2	39479	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	551	39407	25	10100	100	10000	100	10000	500	5706908	0	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	710	0	0	2	16	5	2	39479	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	61	39407	25	10100	100	10000	100	10000	500	5706908	0	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	710	0	0	2	16	2	2	39479	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	346	39407	25	10100	100	10000	100	10000	500	5706908	1	0	40053	40037	40037	38108	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	9	0	710	0	0	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	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	710	0	0	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	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	710	0	0	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	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	710	0	0	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)	l2 tlb miss data (0b)	18	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)	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)	a9	ac	c2	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
10024	40037	299	0	0	0	0	0	726	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	0	0	0	0	640	3	16	2	2	39473	0	10000	10	40038	40038	40038	40038	40038
10024	40037	300	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	4	1	0	0	0	640	2	24	2	2	39473	0	10000	10	40038	40038	40038	40038	40038
10024	40037	300	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	0	0	0	0	640	2	16	2	2	39473	0	10000	10	40038	40038	40038	40038	40038
10024	40037	300	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	0	0	0	0	640	2	16	2	2	39473	0	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	1	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	0	0	0	0	640	2	16	2	2	39473	0	10000	10	40038	40038	40038	40038	40038
10024	40037	300	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	0	0	0	0	640	2	16	2	2	39473	0	10000	10	40084	40038	40038	40038	40038
10024	40037	300	0	0	0	0	0	61	39407	25	10010	10	10000	10	10000	50	5706908	0	40053	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	0	640	2	16	2	2	39473	0	10000	10	40038	40038	40038	40038	40038
10024	40037	300	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	0	0	0	0	640	2	16	2	2	39473	0	10000	10	40038	40038	40038	40038	40038
10024	40037	299	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	0	0	0	0	640	2	16	2	2	39473	0	10000	10	40038	40038	40038	40038	40038
10024	40037	300	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	0	0	0	0	640	2	16	2	2	39473	0	10000	10	40038	40038	40038	40038	40038

Test 4: Latency 1->3

Code:

  fmla 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	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)	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	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10205	40037	300	39	61	39407	25	10100	100	10000	100	10000	500	5706908	0	40018	0	40037	40037	38108	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	710	2	16	1	1	39479	10000	100	40038	40038	40038	40038	40038
10204	40037	299	51	61	39407	25	10100	100	10000	100	10000	500	5706908	0	40018	0	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	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	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	710	1	16	1	1	39479	10000	100	40038	40038	40038	40038	40038
10204	40037	300	39	61	39407	25	10100	100	10000	100	10000	500	5706908	0	40018	0	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	16	1	1	39479	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	458	39407	25	10100	100	10000	100	10000	500	5706908	0	40018	0	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	16	1	1	39479	10000	100	40038	40038	40038	40038	40038
10204	40037	300	84	61	39407	25	10100	100	10000	100	10000	500	5706908	0	40018	0	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	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	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	710	1	16	1	1	39479	10000	100	40038	40038	40038	40038	40038
10204	40037	300	21	61	39407	25	10100	100	10000	100	10000	500	5706908	0	40018	0	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	16	1	1	39479	10000	100	40038	40038	40038	40038	40038
10204	40037	301	84	61	39407	25	10100	100	10000	100	10000	500	5706908	0	40018	0	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	16	1	1	39479	10000	100	40038	40038	40038	40038	40038
10204	40037	300	75	61	39407	25	10100	100	10000	100	10000	500	5706908	0	40018	0	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	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	mmu table walk instruction (07)	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)	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)	l1d tlb miss (a1)	ld unit uop (a6)	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
10024	40037	300	1	0	0	0	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	0	0	0	640	3	16	3	3	39473	0	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	0	0	0	0	0	219	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	0	0	0	640	3	16	3	3	39473	0	10000	10	40038	40038	40077	40038	40038
10024	40037	299	0	0	0	0	0	0	51	0	61	39407	25	10010	10	10000	10	10000	83	5712492	0	40158	0	40413	40178	38147	3	38767	10010	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	0	0	640	3	16	3	3	39473	0	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	0	0	0	0	0	27	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	0	0	0	640	3	16	3	3	39473	0	10000	10	40038	40038	40038	40038	40038
10024	40037	299	0	0	0	0	0	0	51	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	0	0	0	640	3	16	3	3	39473	0	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	0	0	0	0	0	36	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	0	0	0	640	3	16	3	3	39545	0	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	0	0	0	0	0	27	0	61	39407	25	10010	10	10000	10	10000	50	5706908	0	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	0	0	0	640	3	16	3	3	39473	0	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	0	0	0	0	0	45	0	61	39407	25	10010	10	10000	10	10000	50	5706908	0	40018	0	40037	40037	38130	3	38767	10012	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	0	0	640	3	16	3	3	39473	0	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	0	0	0	0	0	48	0	726	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	0	0	0	640	3	16	3	3	39473	0	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	0	0	0	0	1	27	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	0	0	0	640	3	16	3	3	39473	0	10000	10	40038	40038	40038	40038	40038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  fmla s0, s8, v9.s[1]
  movi v1.16b, 0
  fmla s1, s8, v9.s[1]
  movi v2.16b, 0
  fmla s2, s8, v9.s[1]
  movi v3.16b, 0
  fmla s3, s8, v9.s[1]
  movi v4.16b, 0
  fmla s4, s8, v9.s[1]
  movi v5.16b, 0
  fmla s5, s8, v9.s[1]
  movi v6.16b, 0
  fmla s6, s8, v9.s[1]
  movi v7.16b, 0
  fmla 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	l2 tlb miss data (0b)	18	19	1e	1f	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)	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 tlb access (a0)	l1d tlb miss (a1)	ld unit uop (a6)	st unit uop (a7)	l1d cache writeback (a8)	a9	ac	c2	branch cond mispred nonspec (c5)	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
160204	20090	150	0	0	0	15	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	0	0	0	0	0	0	10111	4	16	1	1	20062	0	160000	100	20066	20066	20066	20066	20066
160204	20065	150	0	0	0	0	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	0	0	0	0	0	0	0	0	10111	1	16	1	1	20062	0	160000	100	20066	20066	20066	20066	20066
160204	20065	150	0	0	0	18	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	0	0	0	2	0	0	0	0	10111	1	16	1	1	20062	0	160000	100	20066	20066	20066	20066	20066
160204	20065	150	0	0	0	6	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	0	0	0	0	0	0	0	0	10111	1	16	1	1	20062	0	160000	100	20066	20066	20066	20066	20066
160204	20065	150	0	0	0	18	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	0	0	0	0	0	0	10111	1	48	1	1	20062	0	160000	100	20066	20066	20066	20066	20066
160204	20065	150	0	0	0	0	0	0	40	25	80100	100	80000	100	80000	500	640000	0	20046	20065	20171	3	23	80100	200	80000	200	240000	20065	20065	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	0	0	0	0	0	10111	1	16	1	1	20062	0	160000	100	20066	20066	20066	20066	20066
160204	20065	150	0	0	0	345	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	0	0	0	0	0	0	10111	1	16	1	1	20062	0	160000	100	20066	20066	20066	20066	20066
160204	20065	151	0	0	0	12	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	0	0	0	0	0	0	10111	1	16	1	1	20062	0	160000	100	20066	20066	20066	20066	20066
160204	20065	150	0	0	0	0	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	0	0	0	0	0	0	10111	1	16	1	1	20062	0	160000	100	20066	20066	20066	20066	20066
160204	20065	151	0	0	0	15	0	0	74	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	0	0	0	0	0	0	0	10111	1	16	1	1	20062	0	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	1e	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	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
160024	20049	150	42	0	46	25	80012	12	80000	12	80000	62	640000	1	1	0	20049	20051	20051	3	23	80012	20	80000	20	240000	20051	20051	1	1	160021	10	9	10	10	160000	10	0	0	10048	8	3	1	24	20	2	1	1	24	23	20044	2	30	160000	10	20052	20052	20052	20052	20052
160024	20051	150	9	0	52	25	80012	12	80000	12	80000	62	640000	0	1	5	20048	20047	20047	3	23	80012	20	80000	20	240000	20047	20047	1	1	160021	10	9	10	10	160000	10	0	0	10044	8	4	1	23	20	2	1	1	25	27	20044	2	15	160000	10	20048	20048	20048	20048	20048
160024	20047	150	0	0	52	25	80012	12	80000	12	80000	62	640000	0	1	5	20037	20047	20047	3	23	80012	20	80000	20	240000	20047	20047	1	1	160021	10	9	10	10	160000	10	0	0	10046	8	4	1	24	20	2	1	1	23	24	20044	2	15	160000	10	20048	20048	20048	20048	20048
160024	20047	150	0	0	46	25	80012	12	80000	12	80000	62	640000	1	1	5	20048	20047	20047	3	23	80012	20	80000	20	240000	20047	20047	1	1	160021	10	9	10	10	160000	10	1	3	10049	8	4	1	24	20	2	1	1	23	24	20044	2	15	160000	10	20048	20048	20048	20048	20048
160024	20047	150	0	0	217	25	80012	12	80000	12	80000	62	640000	1	1	5	20047	20047	20047	3	23	80012	20	80000	20	240000	20047	20047	1	1	160021	10	9	10	10	160000	10	0	0	10044	8	4	1	23	20	2	1	1	22	23	20044	2	15	160000	10	20048	20048	20048	20048	20048
160024	20047	150	0	0	46	25	80012	12	80000	12	80000	62	640000	1	1	5	20037	20047	20047	3	23	80012	20	80000	20	240000	20047	20047	1	1	160021	10	9	10	10	160000	10	0	0	10047	8	4	1	26	20	2	1	1	25	20	20044	2	15	160000	10	20048	20048	20048	20048	20048
160024	20047	150	6	0	46	25	80012	12	80000	12	80000	62	640000	1	1	5	20036	20047	20047	3	23	80012	20	80000	20	240000	20047	20047	1	1	160021	10	9	10	10	160000	10	0	0	10046	8	4	1	23	20	2	1	1	24	23	20044	2	15	160000	10	20048	20048	20048	20048	20048
160024	20047	150	0	0	46	25	80012	12	80000	12	80000	62	640000	1	1	5	20037	20047	20047	3	23	80012	20	80000	20	240000	20047	20047	1	1	160021	10	9	10	10	160000	10	0	0	10047	8	4	1	24	20	2	1	1	23	24	20044	2	28	160000	10	20048	20048	20048	20048	20048
160024	20047	150	0	0	388	25	80012	12	80000	12	80000	62	640000	1	1	5	20047	20047	20047	3	23	80012	20	80000	20	240000	20047	20047	1	1	160021	10	9	10	10	160000	10	0	0	10045	8	4	1	23	20	2	1	1	24	23	20044	2	15	160000	10	20048	20048	20048	20048	20048
160024	20047	150	0	0	52	25	80012	12	80000	12	80000	62	640000	0	1	5	20036	20047	20047	3	23	80012	20	80000	20	240000	20047	20047	1	1	160021	10	9	10	10	160000	10	0	0	10049	11	5	2	25	24	4	2	2	25	24	20048	2	30	160000	10	20052	20052	20052	20052	20052

Test 6: throughput

Count: 12

Code:

  fmla s0, s12, v13.s[1]
  fmla s1, s12, v13.s[1]
  fmla s2, s12, v13.s[1]
  fmla s3, s12, v13.s[1]
  fmla s4, s12, v13.s[1]
  fmla s5, s12, v13.s[1]
  fmla s6, s12, v13.s[1]
  fmla s7, s12, v13.s[1]
  fmla s8, s12, v13.s[1]
  fmla s9, s12, v13.s[1]
  fmla s10, s12, v13.s[1]
  fmla 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	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)	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)	c2	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
120204	41683	299	0	0	61	9961	25	120100	100	120000	100	120000	500	5630640	40024	40039	41691	26577	3	24997	120100	200	120000	200	360000	41691	40039	1	1	120201	100	99	100	100	120000	100	0	0	0	7610	1	16	1	1	41683	120000	100	40040	41692	40040	41692	40040
120204	40039	312	39	0	189	37966	25	120101	100	120001	100	120000	500	5630640	40020	40039	41691	26582	3	26649	120100	200	120000	200	360000	41691	40039	1	1	120201	100	99	100	100	120000	100	0	0	0	7610	1	16	1	1	41683	120000	100	40040	40040	40040	40040	40040
120204	40039	312	0	3	61	9961	25	120100	100	120000	100	120000	500	5851869	41672	41691	40039	24932	3	24997	120100	200	120000	200	360000	40039	41686	1	1	120201	100	99	100	100	120000	100	0	0	0	7610	1	16	1	1	40030	120000	100	41687	40040	41692	40040	41692
120204	41687	300	0	0	61	9961	25	120100	100	120000	100	120000	500	5851869	40020	40039	40039	24932	3	24997	120100	200	120000	200	360000	40039	40039	1	1	120201	100	99	100	100	120000	100	0	0	0	7610	1	16	1	1	40030	120000	100	40040	40040	40040	40040	40040
120204	40039	300	0	1	536	9961	25	120100	100	120000	100	120000	500	5851869	42451	41691	40039	24932	3	24997	120100	200	120000	200	360000	40039	41686	1	1	120201	100	99	100	100	120000	100	0	0	0	7610	1	16	1	1	40030	120000	100	40040	41687	40040	41692	40040
120204	40039	313	0	0	61	35689	25	120101	100	120001	100	120000	500	5630640	40020	40039	40039	24932	3	24997	120100	200	120000	200	360000	41691	40039	1	1	120201	100	99	100	100	120000	100	0	0	0	7610	1	16	1	1	41683	120000	100	40040	40040	40040	40040	40040
120204	40039	299	0	0	61	9961	25	120100	100	120000	100	120000	500	5851869	41667	41691	40039	24932	3	24997	120100	200	120000	200	360000	40039	41691	1	1	120201	100	99	100	100	120000	100	0	0	0	7610	1	16	1	1	40030	120000	100	40040	40040	40040	40040	40040
120204	40039	299	0	1	251	37966	50	120100	100	120000	100	120000	500	5851993	40020	40039	40039	24932	3	24997	120100	200	120000	200	360000	40039	41691	1	1	120201	100	99	100	100	120000	100	0	0	0	7610	1	16	1	1	40030	120000	100	41692	40040	41692	40040	41692
120204	41687	300	0	0	61	9961	25	120100	100	120000	100	120000	500	5630640	40020	40039	41691	26582	3	26649	120100	200	120000	200	360000	41686	40039	1	1	120201	100	99	100	100	120000	100	0	0	0	7610	1	16	1	1	41677	120000	100	40040	40040	40040	40040	40040
120204	40039	300	0	1	61	37966	25	120103	100	120001	100	120000	500	5630640	40020	41691	40039	24932	3	24997	120100	200	120000	200	360000	40039	41691	1	1	120201	100	99	100	100	120000	100	0	0	0	7610	1	16	1	1	40030	120000	100	40040	40040	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)	09	l2 tlb miss data (0b)	18	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	61	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	branch cond mispred nonspec (c5)	cf	d0	d2	d5	map dispatch bubble (d6)	db	dd	fetch restart (de)	e0	ea	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
120024	40039	311	0	0	0	0	0	0	0	61	9961	25	120010	10	120000	10	120000	50	5630640	0	0	40020	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	7520	0	0	21	16	0	16	19	40030	0	120000	10	40040	40040	40040	40040	40040
120024	40039	300	0	0	0	0	0	0	0	61	9961	25	120010	10	120000	10	120000	50	5630640	0	0	40020	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	7520	0	0	19	16	0	19	19	40030	0	120000	10	40040	40040	40040	40040	40040
120024	40039	300	0	0	0	0	0	0	0	61	9961	25	120010	10	120000	10	120000	50	5851869	0	0	40020	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	7520	5	2	19	16	0	9	19	40030	0	120000	10	40040	40040	40040	40040	40040
120024	40039	300	0	0	0	0	0	0	0	61	9961	25	120010	10	120000	10	120000	50	5630640	1	5	40020	40039	40039	24955	3	25019	120010	20	120000	20	360000	40039	40039	1	1	120021	10	9	10	10	120000	10	1	0	0	0	7520	0	0	19	16	0	19	19	40030	0	120000	10	40040	40040	40040	40040	41702
120024	40039	299	0	0	0	0	0	0	0	61	9961	25	120010	10	120000	10	120000	50	5630640	1	5	40020	40039	41691	24955	3	25019	120010	20	120000	20	360000	40039	40039	1	1	120021	10	9	10	10	120000	10	0	1	0	1	7520	5	2	19	16	0	19	19	40030	0	120000	10	40040	40040	40040	40040	40040
120024	40039	299	0	0	0	0	0	0	0	61	9961	25	120010	10	120000	10	120000	50	5630640	1	5	40020	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	7520	0	0	19	16	0	19	19	40030	0	120000	10	40040	40040	40040	40040	40040
120024	40039	300	0	0	0	0	0	0	0	61	9961	25	120010	10	120000	10	120000	50	5630640	1	5	40020	40039	40039	24961	3	25019	120010	20	120000	20	360000	40039	40039	1	1	120021	10	9	10	10	120000	10	0	0	0	0	7520	5	2	9	16	0	19	9	40030	0	120000	10	40040	40040	40040	40040	40040
120024	40039	299	0	0	0	0	0	0	0	61	9961	25	120010	10	120000	10	120000	50	5630640	0	5	40020	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	7520	5	0	19	16	0	19	19	40030	0	120000	10	40040	40040	40040	40040	40040
120024	40039	300	0	0	1	0	0	0	0	726	9961	25	120010	10	120000	10	120000	50	5630640	1	0	40020	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	7520	5	2	9	16	0	19	7	40030	0	120000	10	40040	40040	40040	40040	40040
120024	40039	300	0	0	0	0	0	0	0	61	9961	25	120010	10	120000	10	120000	50	5630640	1	0	40020	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	7520	0	0	19	16	0	7	19	40030	0	120000	10	40040	40040	40040	40040	40040

FMLA (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