Firestorm: FMLA (by element, 2D) measurements

Code:

  fmla v0.2d, v1.2d, v2.d[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)	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)	a9	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	82	3407	25	1000	1000	1000	531908	4018	4037	4037	3258	3	3895	1000	1000	3000	4037	4037	1	1	1001	1000	0	0	73	2	16	1	2	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	73	1	16	2	2	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	18	73	2	16	2	1	3473	1000	4038	4038	4038	4038	4038
1004	4037	30	0	0	309	3407	25	1000	1000	1000	531908	4018	4037	4037	3258	3	3895	1000	1000	3000	4037	4037	1	1	1001	1000	0	0	73	1	16	2	2	3473	1000	4038	4038	4038	4038	4038
1004	4037	30	0	0	84	3407	25	1000	1000	1000	531908	4018	4037	4037	3258	3	3895	1000	1000	3000	4037	4037	1	1	1001	1000	0	0	73	1	16	2	1	3473	1000	4038	4038	4038	4038	4038
1004	4037	30	0	0	61	3407	25	1000	1000	1000	531908	4018	4037	4037	3258	3	3895	1000	1000	3000	4037	4037	1	1	1001	1000	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	15	73	2	16	1	1	3473	1000	4038	4038	4038	4038	4038
1004	4037	31	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	73	2	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	73	2	16	2	1	3473	1000	4038	4038	4038	4038	4038
1004	4037	30	0	0	152	3407	25	1000	1000	1000	531908	4018	4037	4037	3258	3	3895	1000	1000	3000	4037	4037	1	1	1001	1000	0	0	73	2	16	1	1	3473	1000	4038	4038	4038	4038	4038

Test 2: Latency 1->1

Code:

  fmla v0.2d, v1.2d, v2.d[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)	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	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	ld unit uop (a6)	l1d cache writeback (a8)	ac	cf	d0	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10204	40037	300	0	0	0	0	61	39407	25	10100	100	10000	100	10000	500	5706908	0	40053	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	710	0	4	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	1	40018	0	40037	40037	38108	0	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	0	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	1	40018	0	40037	40037	38108	0	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	0	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	1	40018	0	40037	40037	38108	0	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	0	710	1	4	16	4	3	39549	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	0	0	0	61	39407	25	10100	100	10000	100	10000	500	5706908	1	40018	0	40037	40037	38108	0	3	38745	10100	200	10000	200	30000	40037	40085	1	1	10201	100	99	100	100	10000	100	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	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	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	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	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	0	40037	40037	38108	0	3	38745	10100	200	10000	200	30000	40037	40037	2	1	10201	100	99	100	100	10000	100	0	0	0	710	1	4	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	1	40018	0	40037	40037	38108	0	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	0	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	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	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	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 access (a0)	l1d tlb miss (a1)	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	300	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	640	2	16	2	2	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	0	0	61	39407	43	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	640	2	16	2	2	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	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	640	2	16	2	2	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	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	1	0	0	0	640	2	16	2	2	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	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	640	2	16	2	2	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	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	640	2	16	2	2	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	299	0	0	0	61	39407	25	10010	10	10000	10	10000	50	5708304	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	640	2	16	2	3	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	299	0	0	0	61	39407	25	10010	10	10000	10	10000	50	5706908	1	40018	40037	40037	38130	3	38767	10157	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	640	2	16	2	2	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	0	0	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	640	2	16	2	2	39473	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	0	0	61	39407	25	10010	10	10000	10	10000	50	5706908	1	40018	40037	40037	38130	3	38767	10010	20	10172	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	640	2	16	2	2	39473	10000	10	40038	40038	40038	40038	40038

Test 3: Latency 1->2

Code:

  fmla v0.2d, v0.2d, v1.d[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)	09	18	1e	3f	4e	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	60	69	6d	6e	map stall dispatch (70)	simd prf full (72)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d cache writeback (a8)	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
10204	40037	300	0	0	0	0	82	39407	25	10100	100	10000	100	10000	500	5706908	1	40018	40037	40037	38108	0	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	0	710	1	16	1	1	40034	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	0	0	0	2997	39407	25	10100	100	10000	100	10000	500	5706908	1	40018	40037	40037	38108	0	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	0	710	1	16	1	1	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	1	40018	40037	40037	38108	0	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	0	710	1	16	1	1	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	1	40018	40037	40037	38108	0	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	1	710	1	16	1	1	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	1	40018	40037	40037	38108	0	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	0	710	1	16	1	1	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	1	40018	40037	40037	38108	0	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	0	710	1	16	1	1	39479	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	0	0	0	726	39407	25	10100	100	10000	100	10000	500	5706908	1	40018	40037	40037	38108	0	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	0	710	1	16	1	1	39479	10000	100	40038	40038	40038	40038	40038
10204	40037	300	0	0	0	0	61	39407	44	10100	100	10000	100	10000	500	5706908	1	40018	40037	40037	38108	0	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	0	710	1	16	1	1	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	1	40018	40037	40037	38108	0	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	0	710	1	17	1	1	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	1	40018	40037	40037	38108	0	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	0	0	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	1e	3f	4e	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	69	6d	6e	map stall dispatch (70)	simd prf full (72)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d tlb access (a0)	ld unit uop (a6)	st unit uop (a7)	l1d cache writeback (a8)	a9	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	299	0	61	39407	25	10010	10	10000	10	10000	50	5706908	40018	40037	40037	38130	0	3	38767	10010	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	72	640	2	16	2	2	39473	0	10000	10	40038	40038	40038	40038	40038
10024	40037	299	0	61	39407	25	10010	10	10000	10	10000	50	5706908	40018	40037	40037	38130	0	3	38767	10010	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	640	2	16	2	2	39473	0	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	61	39407	25	10018	10	10000	10	10000	50	5706908	40018	40037	40037	38130	0	3	38767	10010	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	141	640	2	16	2	2	39473	0	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	61	39407	25	10010	10	10006	11	10000	50	5706908	40018	40037	40037	38130	0	3	38767	10010	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	141	640	2	16	2	2	39473	0	10000	10	40038	40038	40038	40038	40038
10024	40037	299	0	61	39407	25	10010	10	10000	10	10000	50	5706908	40018	40037	40037	38130	0	3	38767	10010	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	135	640	2	16	2	2	39473	0	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	61	39407	25	10010	10	10000	10	10000	50	5706908	40018	40037	40037	38130	0	3	38767	10010	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	640	2	16	2	2	39473	0	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	61	39407	25	10010	10	10000	10	10000	50	5706908	40018	40037	40037	38130	0	3	38767	10010	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	0	0	79	0	3	640	2	16	2	2	39473	0	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	61	39407	25	10010	10	10000	10	10000	50	5706908	40018	40037	40037	38130	0	3	38767	10010	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	0	0	18	0	9	640	2	16	2	2	39473	0	10000	10	40038	40038	40038	40038	40038
10024	40085	300	0	61	39398	25	10010	10	10000	10	10000	50	5706908	40018	40037	40037	38130	0	3	38767	10010	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	3	640	2	16	3	3	39473	0	10000	10	40038	40038	40038	40038	40038
10024	40037	299	0	61	39407	25	10010	10	10000	10	10000	50	5706908	40018	40037	40037	38130	0	3	38767	10010	20	10000	20	30000	40037	40037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	640	2	16	2	2	39473	0	10000	10	40038	40038	40038	40038	40038

Test 4: Latency 1->3

Code:

  fmla v0.2d, v1.2d, v0.d[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	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	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
10204	40037	300	0	0	0	61	39407	25	10100	100	10000	100	10000	500	5706908	1	40018	0	40037	40037	38108	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	9	3	710	1	16	1	1	39479	10000	100	40038	40038	40038	40038	40038
10204	40037	299	0	0	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	47	3	710	1	16	0	1	39479	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	0	40037	40037	38108	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	50	0	710	1	16	1	1	39479	10000	100	40038	40038	40038	40038	40038
10204	40037	299	0	0	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	50	6	710	1	16	1	1	39479	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	0	40037	40037	38108	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	45	9	710	1	16	1	1	39479	10000	100	40038	40038	40038	40038	40038
10204	40227	300	0	0	0	61	39407	25	10100	100	10006	100	10000	500	5706908	1	40018	0	40037	40037	38108	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	8	3	710	1	16	1	1	39479	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	0	40037	40037	38108	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	0	66	710	1	16	1	1	39479	10000	100	40038	40038	40038	40038	40038
10204	40037	299	0	0	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	0	0	0	61	39407	25	10100	100	10000	100	10000	500	5706908	1	40018	0	40037	40037	38108	26	38745	10100	202	10000	200	30000	40084	40037	1	1	10201	100	99	100	100	10000	100	39	3	710	1	16	1	1	39479	10000	100	40085	40038	40038	40038	40038
10204	40037	300	0	0	0	61	39407	25	10100	100	10000	100	10000	500	5706908	0	40018	3	40037	40037	38108	3	38745	10100	200	10000	200	30000	40037	40037	1	1	10201	100	99	100	100	10000	100	1	0	710	1	16	1	1	39479	10000	100	40038	40038	40038	40038	40185

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

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

retire uop (01)	cycle (02)	03	1e	3f	4e	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	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	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	103	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	0	10000	10	40038	40038	40038	40038	40038
10024	40037	300	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	2	640	2	16	2	2	39473	0	10000	10	40038	40038	40038	40038	40038
10024	40037	300	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	0	10000	10	40038	40038	40038	40038	40038
10024	40037	300	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	0	10000	10	40038	40038	40038	40038	40038
10024	40037	299	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	0	10000	10	40038	40038	40038	40038	40038
10024	40037	300	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	0	10000	10	40038	40038	40038	40038	40038
10024	40037	300	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	0	10000	10	40038	40038	40038	40038	40038
10024	40037	299	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	0	10000	10	40038	40038	40038	40038	40038
10024	40037	300	0	61	39407	25	10010	10	10000	10	10000	50	5706908	0	40018	40037	40037	38130	3	38767	10010	20	10000	20	30000	40083	40037	1	1	10021	10	9	10	10	10000	10	0	0	0	640	2	16	2	2	39473	0	10000	10	40038	40038	40038	40038	40038
10024	40037	300	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	62	3	0	640	2	16	2	2	39473	0	10000	10	40038	40038	40038	40038	40038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  fmla v0.2d, v8.2d, v9.d[1]
  movi v1.16b, 0
  fmla v1.2d, v8.2d, v9.d[1]
  movi v2.16b, 0
  fmla v2.2d, v8.2d, v9.d[1]
  movi v3.16b, 0
  fmla v3.2d, v8.2d, v9.d[1]
  movi v4.16b, 0
  fmla v4.2d, v8.2d, v9.d[1]
  movi v5.16b, 0
  fmla v5.2d, v8.2d, v9.d[1]
  movi v6.16b, 0
  fmla v6.2d, v8.2d, v9.d[1]
  movi v7.16b, 0
  fmla v7.2d, v8.2d, v9.d[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	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)	l1d cache writeback (a8)	a9	ac	cd	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
160204	20088	150	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	10111	1	16	1	1	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	150	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	10111	1	16	1	1	20062	160000	100	20066	20171	20171	20159	20066
160204	20065	150	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	1	10111	1	16	1	1	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	151	0	0	0	0	40	25	80100	100	80000	100	80000	500	640000	0	20046	20065	20065	40	23	80100	200	80000	200	240000	20065	20065	1	1	160201	100	99	100	100	160000	100	0	0	0	2	0	0	0	10111	1	16	1	1	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	150	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	10111	1	16	1	1	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	150	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	10111	1	16	1	1	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	151	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	10111	1	16	1	1	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	150	0	0	0	0	40	25	80100	100	80000	114	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	10111	1	16	1	1	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	150	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	10111	1	16	1	1	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	150	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	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	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	rob full (74)	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)	ld unit uop (a6)	l1d cache writeback (a8)	ac	c2	branch mispred nonspec (cb)	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	20086	151	0	0	292	27	80012	12	80000	12	80000	62	640000	1	0	0	20034	20052	20052	0	3	23	80012	20	80000	20	240000	20052	20052	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	0	10034	8	1	1	14	25	2	1	1	11	8	20049	2	60	1	160000	10	20053	20053	20053	20053	20053
160024	20052	151	0	0	211	27	80012	12	80000	12	80000	62	640000	1	0	5	20033	20052	20052	0	3	23	80012	20	80000	20	240000	20052	20052	1	1	160021	10	9	10	10	160000	10	0	0	2	0	2	0	10034	3	3	1	7	25	2	1	1	7	11	20049	2	40	1	160000	10	20053	20053	20053	20053	20053
160024	20053	150	12	0	1237	27	80012	12	80000	12	80000	62	640000	1	1	5	20110	20052	20052	0	3	23	80012	20	80000	20	240000	20052	20052	1	1	160021	10	9	10	10	160000	10	0	2	1	0	0	0	10034	8	3	1	11	25	2	1	1	8	13	20083	2	20	1	160000	10	20053	20053	20053	20054	20054
160024	20052	150	0	0	272	27	80012	12	80000	12	80000	62	640000	1	0	0	20033	20052	20052	0	3	23	80012	20	80000	20	240000	20052	20052	1	1	160021	10	9	10	10	160000	10	0	0	0	6	0	0	10034	8	1	1	11	25	2	1	1	11	7	20049	2	20	1	160000	10	20053	20053	20054	20053	20053
160024	20052	150	0	0	274	27	80012	12	80000	12	80000	62	640000	1	1	5	20033	20052	20052	0	3	23	80012	20	80000	20	240000	20052	20052	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	0	10030	8	3	1	11	25	2	1	1	11	7	20049	2	20	1	160000	10	20053	20053	20053	20053	20053
160024	20052	150	0	0	235	27	80012	12	80000	12	80000	62	640000	1	1	5	20033	20052	20052	0	3	23	80012	20	80000	20	240000	20052	20052	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	0	10030	8	3	1	7	25	2	1	1	7	11	20049	2	40	1	160000	10	20053	20053	20053	20053	20053
160024	20052	150	0	0	263	27	80012	12	80000	12	80000	62	640000	1	1	5	20033	20052	20052	5	3	23	80012	20	80000	20	240000	20052	20052	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	0	10034	8	3	1	13	25	2	1	1	11	11	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	20052	20052	0	3	23	80012	20	80000	20	240000	20052	20052	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	0	10030	8	3	1	11	25	2	1	1	11	7	20049	2	20	1	160000	10	20053	20053	20053	20053	20053
160024	20052	150	0	0	216	27	80012	12	80000	12	80000	62	640000	1	1	5	20033	20052	20052	0	3	23	80012	20	80000	20	240000	20052	20052	1	1	160021	10	9	10	10	160000	10	0	0	0	3	0	0	10030	8	3	1	11	25	2	1	1	11	9	20049	2	20	1	160000	10	20053	20053	20053	20053	20053
160024	20052	150	0	0	130	27	80012	12	80000	12	80000	62	640000	1	1	5	20033	20052	20061	0	3	23	80012	20	80000	20	240000	20052	20052	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	0	10030	8	3	1	11	25	2	1	1	11	11	20049	2	20	1	160000	10	20053	20053	20053	20053	20053

Test 6: throughput

Count: 12

Code:

  fmla v0.2d, v12.2d, v13.d[1]
  fmla v1.2d, v12.2d, v13.d[1]
  fmla v2.2d, v12.2d, v13.d[1]
  fmla v3.2d, v12.2d, v13.d[1]
  fmla v4.2d, v12.2d, v13.d[1]
  fmla v5.2d, v12.2d, v13.d[1]
  fmla v6.2d, v12.2d, v13.d[1]
  fmla v7.2d, v12.2d, v13.d[1]
  fmla v8.2d, v12.2d, v13.d[1]
  fmla v9.2d, v12.2d, v13.d[1]
  fmla v10.2d, v12.2d, v13.d[1]
  fmla v11.2d, v12.2d, v13.d[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 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
120204	40039	308	0	0	233	9961	25	120101	100	120001	100	120000	500	5630640	42451	40039	40039	24932	3	24997	120100	200	120000	200	360000	41691	40039	1	1	120201	100	99	100	100	120000	100	0	0	0	0	7610	1	16	1	1	40030	0	120000	100	40040	40040	40040	40040	40040
120204	40039	300	0	0	61	9961	25	120100	100	120000	100	120000	500	5630640	40020	42470	40039	27359	3	27428	120100	200	120000	200	360000	41691	40039	1	1	120201	100	99	100	100	120000	100	0	0	0	0	7610	1	16	1	1	40030	0	120000	100	40040	42471	40040	41692	40040
120204	40039	300	0	0	124	9961	25	120100	100	120000	100	120000	500	5630640	40020	40039	40039	24932	3	24997	120100	200	120000	200	360000	40039	40090	1	1	120201	100	99	100	100	120000	100	0	0	0	0	7610	1	16	1	1	40030	0	120000	100	40040	40040	42471	40040	40040
120204	41686	300	0	1	84	9961	25	120100	100	120000	100	120000	500	5630640	40020	40039	40039	24932	3	24997	120296	200	120000	200	360000	42470	40039	1	1	120201	100	99	100	100	120000	100	0	0	0	0	7610	1	16	1	1	40030	0	120000	100	40040	40040	40040	40040	40040
120204	40039	312	0	0	61	9961	25	120100	100	120000	100	120000	500	5630640	40020	40039	42470	27359	3	27428	120100	200	120000	200	360000	40039	42470	1	1	120201	100	99	100	100	120000	100	0	0	0	0	7610	1	16	1	1	40030	0	120000	100	40040	40040	40040	40040	40040
120204	40039	318	0	0	208	9961	25	120100	100	120000	100	120000	500	5966386	42451	42470	40039	24932	3	24997	120100	200	120000	200	360000	40039	40039	1	1	120201	100	99	100	100	120000	100	0	0	0	0	7610	1	16	1	1	42461	0	120000	100	40040	40040	40040	40040	40040
120204	40039	300	0	0	237	9961	25	120101	100	120000	100	120000	500	5630640	40020	40039	41675	24932	3	26649	120100	200	120000	200	360000	42470	40039	1	1	120201	100	99	100	100	120000	100	0	0	0	0	7610	1	16	1	1	40030	0	120000	100	42471	40040	42471	40040	40040
120204	40039	300	0	0	61	9961	25	120100	100	120001	100	120000	500	5630640	40020	42470	40039	24932	3	27428	120100	200	120000	200	360000	42470	40039	1	1	120201	100	99	100	100	120000	100	0	0	0	0	7610	1	16	1	1	40030	0	120000	100	40040	40040	40040	40040	42471
120204	42470	300	0	0	103	37966	25	120102	100	120000	100	120000	500	5630640	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	0	7610	1	16	1	1	40030	0	120000	100	40040	40040	40040	40040	40040
120204	40039	300	0	0	706	9961	25	120100	100	120001	100	120000	500	5630640	40020	42470	40039	24932	3	24997	120100	200	120000	200	360000	40039	40039	1	1	120201	100	99	100	100	120000	100	0	0	0	0	7610	1	16	1	1	40030	0	120000	100	42471	41702	42471	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 instruction (07)	l2 tlb miss data (0b)	18	1e	1f	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	69	6d	6e	map stall dispatch (70)	simd prf full (72)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d tlb access (a0)	l1d tlb miss (a1)	ld unit uop (a6)	l1d cache writeback (a8)	a9	ac	c2	cf	d0	d2	l1i cache miss demand (d3)	d5	map dispatch bubble (d6)	d9	da	db	dd	fetch restart (de)	e0	? int output thing (e9)	ea	eb	ec	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
120024	41104	300	0	0	0	0	0	0	0	61	9961	25	120010	10	120000	10	120000	50	5630640	0	1	40020	40039	40039	24955	0	3	25019	120010	20	120000	20	360000	40039	41691	1	1	120021	10	9	10	10	120000	10	0	0	0	0	0	0	0	7618	0	0	1	8	16	0	0	0	2	4	40030	0	0	0	0	120000	10	40040	40040	40040	40040	41692
120024	41686	299	0	0	0	0	0	0	0	61	9961	25	120010	10	120000	12	120000	60	5630640	0	1	41672	40039	40039	24955	0	3	25019	120010	20	120000	20	360000	40039	40039	1	1	120021	10	9	10	10	120000	10	0	0	0	0	0	0	0	7520	0	0	0	5	16	0	0	0	4	2	40030	0	0	0	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	1	40020	40039	40039	24955	0	3	25019	120010	20	120000	20	360000	40039	41701	1	1	120021	10	9	10	10	120000	10	0	0	0	0	0	0	0	7520	0	0	0	3	16	0	0	0	3	4	40030	0	0	0	0	120000	10	40040	40040	40040	40040	40040
120024	40039	300	0	0	0	0	0	0	0	837	9961	25	120010	10	120000	10	120000	50	5630640	0	1	40020	40039	40039	24955	0	3	25019	120010	20	120000	20	360000	40039	40039	1	1	120021	10	9	10	10	120000	10	0	0	0	1	0	2084	0	7520	0	0	0	4	16	0	0	0	3	4	40030	0	0	0	0	120000	10	41692	40040	40040	40040	40040
120024	40039	300	1	0	0	12	0	0	0	61	9961	25	120010	10	120000	10	120000	50	5630640	0	1	40020	40039	40039	24955	0	3	25019	120010	20	120000	20	360000	40039	40039	1	1	120021	10	9	10	10	120000	10	0	0	0	0	0	0	0	7520	0	0	0	2	16	0	0	0	2	6	40030	0	0	0	0	120000	10	40040	40040	40040	40040	40040
120024	40039	300	0	0	0	0	0	0	0	61	9961	25	120013	12	120000	12	120000	60	5630640	0	1	40020	40039	40039	24955	0	3	25019	120010	20	120000	20	360000	40039	40039	1	1	120021	10	9	10	10	120000	10	0	0	0	2	0	0	0	7520	0	0	1	5	16	2	0	0	6	2	40030	0	0	0	0	120000	10	40040	40040	40040	40040	40040
120024	40039	313	0	0	0	12	0	1	0	61	35689	25	120012	10	120000	10	120000	50	5630640	0	1	40020	40039	40039	24955	0	3	26668	120010	20	120000	20	360000	40039	40039	1	1	120021	10	9	10	10	120000	10	0	0	0	0	0	3	0	7520	0	0	0	4	16	0	0	0	4	2	40030	0	0	0	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	1	42451	40039	40039	24955	0	3	25019	120010	20	120000	20	360000	40039	40039	1	1	120021	10	9	10	10	120000	10	0	0	0	0	0	0	0	7520	0	0	0	2	16	0	0	0	5	7	40030	0	0	0	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	1	40020	40039	40039	24955	0	3	26671	120010	20	120000	20	360000	40039	40039	1	1	120021	10	9	10	10	120000	10	0	0	0	0	0	0	0	7520	0	0	0	4	16	0	0	0	2	4	40030	0	0	0	0	120000	10	40040	40040	40109	41772	40040
120024	40039	300	0	0	0	0	0	0	0	61	9961	25	120010	10	120000	10	120000	50	5630640	0	1	40020	40039	40039	24955	0	3	26668	120010	20	120000	20	360000	40039	40039	1	1	120021	10	9	10	10	120000	10	0	0	0	0	0	0	0	7520	0	0	0	2	16	0	0	0	4	2	40328	0	0	0	0	120000	10	40040	40040	40040	40040	40040

FMLA (by element, 2D)

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