Firestorm: SMLAL2 (vector, 2D) measurements

Code:

  smlal2 v0.2d, v1.4s, v2.4s

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	18	1e	3f	4e	51	schedule uop (52)	schedule simd uop (54)	dispatch simd uop (57)	ldst uops in schedulers (5b)	60	69	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map simd uop (7e)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst simd alu (9a)	l1d cache writeback (a8)	ac	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	f5	f6	f7	f8	fd
1004	3037	23	0	0	82	2539	25	1000	1000	1000	398313	1	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	61	2548	25	1000	1000	1000	398313	1	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	0	0	61	2548	25	1000	1000	1000	398313	1	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	82	2548	25	1000	1000	1000	398313	1	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	0	0	61	2548	25	1000	1000	1000	398313	1	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	61	2548	25	1000	1008	1000	398313	1	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	0	0	61	2548	25	1000	1000	1000	398313	1	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	0	0	61	2548	25	1000	1000	1000	398313	1	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	73	2	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	61	2548	25	1000	1000	1000	398313	1	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	61	2548	25	1000	1000	1000	398313	1	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038

Test 2: Latency 1->1

Code:

  smlal2 v0.2d, v1.4s, v2.4s

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): 3.0037

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

retire uop (01)	cycle (02)	03	09	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	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	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	30037	225	0	0	54	0	61	29548	25	10100	100	10000	100	10000	500	4277313	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	710	1	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	27	0	61	29548	25	10100	100	10000	100	10000	500	4277313	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	710	1	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	129	0	61	29548	25	10100	100	10000	100	10000	500	4277313	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	710	1	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	710	1	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	710	1	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	710	1	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	710	1	2	16	2	3	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	710	1	2	16	2	3	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	710	1	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	224	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	710	1	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

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	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10025	30037	225	372	0	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	543	0	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	1	0	640	2	16	3	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	224	30	0	61	29548	25	10010	10	10000	10	10000	50	4277313	0	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	27	0	61	29548	25	10010	10	10000	10	10000	50	4277313	0	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	30	0	61	29548	25	10010	10	10000	10	10000	50	4277313	0	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	12	0	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	224	36	0	61	29548	25	10010	10	10000	10	10000	50	4277313	0	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	30	0	61	29548	25	10010	10	10000	10	10000	50	4277313	0	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	224	42	0	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038

Test 3: Latency 1->2

Code:

  smlal2 v0.2d, v0.4s, v1.4s

Initialization

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

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

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

retire uop (01)	cycle (02)	03	mmu table walk data (08)	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	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	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	30037	225	0	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	0	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	195	710	2	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	224	0	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	0	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	138	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	224	0	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	153	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	3	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	726	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30084	30180	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	114	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	251	29548	25	10100	100	10000	100	10000	500	4277313	0	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	114	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	251	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	102	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	156	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	135	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	422	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	105	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	251	29548	25	10100	100	10000	100	10000	500	4277313	0	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	710	0	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

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	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	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	30037	224	0	0	0	0	441	29548	25	10010	10	10000	10	10000	50	4277313	0	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	117	640	4	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	0	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	147	640	2	16	2	2	29668	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	0	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	9	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	0	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	129	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	224	0	0	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	138	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	111	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	0	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	144	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	224	0	0	0	0	103	29548	25	10010	10	10000	10	10000	50	4277313	0	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	117	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	30037	30037	28287	25	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	111	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	114	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038

Test 4: Latency 1->3

Code:

  smlal2 v0.2d, v1.4s, v0.4s

Initialization

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

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

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

retire uop (01)	cycle (02)	03	l2 tlb miss data (0b)	1e	3f	4e	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	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	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10204	30037	225	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	0	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	43	6	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	226	0	12	61	29548	25	10100	100	10000	100	10000	500	4277313	0	30018	30037	30037	28265	0	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	43	114	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	0	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	34	0	710	1	16	1	1	29706	10000	100	30085	30038	30038	30038	30038
10204	30037	225	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	0	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	40	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	6	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	0	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	3	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	61	29548	25	10100	107	10000	100	10000	500	4277313	1	30018	30037	30037	28265	0	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	35	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30084	225	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	0	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	39	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	0	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	37	0	740	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	224	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	0	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	43	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	0	30018	30037	30037	28265	0	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	6	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

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

retire uop (01)	cycle (02)	03	l2 tlb miss data (0b)	1e	3f	4e	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	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	cd	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10024	30037	225	1	0	61	29548	25	10010	10	10000	10	10000	50	4277313	0	30018	30037	30037	28287	0	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	81	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	30037	30037	28287	0	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	96	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	30037	30037	28287	0	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	18	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	30037	30037	28287	0	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	8	6	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	30037	30037	28287	0	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	43	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	30037	30037	28287	0	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	43	3	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	30037	30037	28287	0	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	46	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	30037	30037	28287	0	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	49	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	30037	30037	28287	0	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	54	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	30037	30037	28287	0	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	42	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  smlal2 v0.2d, v8.4s, v9.4s
  movi v1.16b, 0
  smlal2 v1.2d, v8.4s, v9.4s
  movi v2.16b, 0
  smlal2 v2.2d, v8.4s, v9.4s
  movi v3.16b, 0
  smlal2 v3.2d, v8.4s, v9.4s
  movi v4.16b, 0
  smlal2 v4.2d, v8.4s, v9.4s
  movi v5.16b, 0
  smlal2 v5.2d, v8.4s, v9.4s
  movi v6.16b, 0
  smlal2 v6.2d, v8.4s, v9.4s
  movi v7.16b, 0
  smlal2 v7.2d, v8.4s, v9.4s

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 miss (a1)	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	20090	151	0	0	0	0	39	25	80100	100	80000	100	80000	500	640000	0	20045	20064	20064	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	0	0	0	10111	2	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	0	39	39	25	80100	100	80000	100	80000	500	640000	0	20045	20064	20064	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	1	0	0	10111	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	0	0	39	25	80100	100	80000	100	80000	500	640000	0	20045	20064	20064	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	2	0	0	10111	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	1	0	39	159	80100	100	80000	100	80000	500	640000	0	20045	20064	20064	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	1	0	0	10111	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	151	0	0	0	0	39	25	80100	100	80000	100	80000	500	640000	0	20045	20064	20064	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	3	0	0	10111	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	0	0	39	25	80100	100	80000	100	80000	500	640000	0	20045	20064	20064	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	9	0	0	10111	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	0	0	39	25	80100	100	80000	100	80000	500	640000	0	20045	20064	20064	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	0	0	0	10111	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	0	0	39	25	80100	100	80000	100	80000	500	640000	0	20045	20064	20064	3	105	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	1	0	0	10111	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	0	0	39	25	80100	100	80000	100	80000	500	640000	0	20045	20064	20064	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	1	0	2	10111	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	0	0	81	25	80100	100	80000	100	80000	500	640000	0	20045	20064	20064	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	2	0	0	10111	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065

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 data (08)	09	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)	5f	60	69	6b	6d	6e	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d cache writeback (a8)	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	20071	150	0	0	0	0	6	45	25	80012	12	80000	12	80000	62	640000	1	1	20027	0	20050	20050	3	22	80012	20	80000	20	240000	20046	20046	1	1	160021	10	9	10	10	160000	10	0	0	10033	3	2	2	5	20	4	2	2	4	6	20047	2	15	160000	10	20051	20051	20047	20051	20047
160024	20046	150	0	0	0	0	0	45	25	80012	12	80000	12	80000	62	640000	1	1	20027	0	20050	20050	3	22	80012	20	80000	20	240000	20050	20050	1	1	160021	10	9	10	10	160000	10	0	33	10029	6	2	2	4	20	4	2	2	4	4	20047	2	15	160000	10	20051	20047	20051	20051	20051
160024	20050	150	0	0	1	1	0	1818	25	80012	12	80000	12	80000	62	640000	1	1	20027	0	20046	20046	3	22	80012	20	80000	20	240000	20046	20046	1	1	160021	10	9	10	10	160000	10	0	0	10032	6	1	1	4	20	2	1	1	4	3	20043	2	15	160000	10	20047	20047	20047	20051	20051
160024	20046	150	0	0	0	0	0	45	25	80012	12	80000	12	80000	62	640000	1	1	20027	0	20046	20046	3	22	80012	20	80000	20	240000	20046	20046	1	1	160021	10	9	10	10	160000	10	0	114	10027	3	1	1	4	20	2	1	1	7	7	20043	2	15	160000	10	20047	20047	20047	20047	20051
160024	20046	151	0	0	0	0	0	45	25	80012	12	80000	12	80000	62	640000	1	1	20027	0	20046	20046	3	22	80012	20	80000	20	240000	20046	20046	1	1	160021	10	9	10	10	160000	10	2	0	10027	3	1	1	4	20	2	1	1	4	7	20043	2	15	160000	10	20047	20047	20047	20047	20047
160024	20046	150	0	0	0	0	0	45	25	80012	12	80000	12	80000	62	640000	1	1	20027	0	20046	20046	3	22	80012	20	80000	20	240000	20046	20046	1	1	160021	10	9	10	10	160000	10	0	3	10027	3	1	1	4	20	2	1	1	7	7	20043	2	15	160000	10	20047	20047	20047	20047	20047
160024	20046	150	0	0	0	0	0	45	25	80012	12	80000	12	80000	62	640000	1	1	20027	0	20046	20046	3	22	80012	20	80000	20	240000	20046	20046	1	1	160021	10	9	10	10	160000	10	0	0	10027	3	1	1	6	20	2	1	1	4	7	20043	2	15	160000	10	20047	20047	20047	20047	20051
160024	20046	150	0	0	4	0	18	66	25	80012	12	80000	12	80000	62	640000	1	1	20027	0	20046	20046	3	22	80012	20	80000	20	240000	20046	20046	1	1	160021	10	9	10	10	160000	10	3	0	10027	3	1	1	3	20	2	1	1	4	4	20043	2	15	160000	10	20047	20047	20047	20047	20047
160024	20046	150	0	0	0	0	0	45	25	80012	12	80000	12	80000	62	640000	1	1	20027	0	20046	20046	3	22	80012	20	80000	20	240000	20046	20046	1	1	160021	10	9	10	10	160000	10	0	42	10027	3	1	1	4	20	2	1	1	6	6	20043	2	15	160000	10	20047	20047	20047	20047	20047
160024	20046	150	0	0	0	0	12	87	25	80012	12	80000	12	80000	62	640000	1	1	20027	0	20046	20046	3	22	80012	20	80000	20	240000	20046	20046	1	1	160021	10	9	10	10	160000	10	0	0	10027	3	1	1	4	20	2	1	1	4	7	20043	2	15	160000	10	20047	20047	20047	20129	20051

Test 6: throughput

Count: 16

Code:

  smlal2 v0.2d, v16.4s, v17.4s
  smlal2 v1.2d, v16.4s, v17.4s
  smlal2 v2.2d, v16.4s, v17.4s
  smlal2 v3.2d, v16.4s, v17.4s
  smlal2 v4.2d, v16.4s, v17.4s
  smlal2 v5.2d, v16.4s, v17.4s
  smlal2 v6.2d, v16.4s, v17.4s
  smlal2 v7.2d, v16.4s, v17.4s
  smlal2 v8.2d, v16.4s, v17.4s
  smlal2 v9.2d, v16.4s, v17.4s
  smlal2 v10.2d, v16.4s, v17.4s
  smlal2 v11.2d, v16.4s, v17.4s
  smlal2 v12.2d, v16.4s, v17.4s
  smlal2 v13.2d, v16.4s, v17.4s
  smlal2 v14.2d, v16.4s, v17.4s
  smlal2 v15.2d, v16.4s, v17.4s

Initialization

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

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

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

retire uop (01)	cycle (02)	03	mmu table walk data (08)	09	l2 tlb miss data (0b)	1e	1f	37	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 stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d tlb access (a0)	l1d tlb miss (a1)	l1d cache writeback (a8)	ac	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	40073	300	0	0	0	0	0	0	41	25	160100	100	160000	100	160000	500	1280000	1	40020	40039	40039	19973	3	19998	160100	200	160000	200	480000	40039	40039	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	10110	1	16	1	1	40036	0	160000	100	40050	40050	40040	40040	40040
160204	40039	300	0	0	0	0	0	1	41	25	160100	100	160000	100	160000	500	1280000	1	40020	40039	40039	19973	3	20007	160100	200	160000	200	480000	40039	40049	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	10110	1	16	1	1	40036	0	160000	100	40050	40050	40050	40050	40040
160204	40039	300	0	0	0	0	0	0	62	25	160100	100	160000	100	160000	500	1280000	1	40020	40039	40039	19973	3	19997	160100	200	160000	200	480000	40039	40039	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	10110	1	16	1	1	40046	0	160000	100	40040	40040	40040	40040	40040
160204	40039	300	0	0	0	0	0	18	72	25	160100	100	160000	100	160000	500	1280000	1	40020	40039	40039	19973	3	19997	160100	200	160000	200	480000	40039	40039	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	10110	1	16	1	1	40045	0	160000	100	40040	40040	40040	40040	40040
160204	40049	300	0	0	0	0	0	0	41	25	160100	100	160000	100	160000	500	1280000	1	40020	40049	40049	19973	3	19997	160100	200	160000	200	480000	40039	40039	1	1	160201	100	99	100	100	160000	100	0	0	0	0	1	10110	1	16	1	1	40036	0	160000	100	40040	40040	40040	40040	40040
160204	40040	300	0	0	0	0	0	0	41	25	160100	100	160000	100	160000	500	2438865	1	40020	40039	40039	19973	3	19997	160100	200	160000	200	480000	40039	40039	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	10110	1	16	1	1	40036	0	160000	100	40040	40040	40040	40040	40040
160204	40039	300	0	0	0	0	0	0	41	25	160100	100	160000	100	160000	500	1280000	1	40020	40039	40039	19973	3	19997	160100	200	160000	200	480000	40039	40039	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	10110	1	16	1	1	40046	0	160000	100	40040	40040	40040	40040	40040
160204	40039	300	0	0	0	0	0	0	62	25	160100	100	160000	100	160000	500	1280000	1	40020	40039	40090	19973	3	20007	160100	200	160000	200	480000	40039	40039	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	10110	1	16	1	1	40036	0	160000	100	40040	40040	40040	40040	40040
160204	40039	300	0	0	0	0	0	0	41	25	160100	100	160000	100	160000	500	1280000	1	40020	40039	40039	19973	3	19997	160100	200	160000	200	480000	40039	40039	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	10110	1	16	1	1	40036	0	160000	100	40050	40050	40050	40050	40050
160204	40039	300	0	0	0	0	0	0	231	25	160100	100	160000	100	160000	500	1280000	1	40020	40039	40039	19973	3	19997	160100	200	160000	200	480000	40039	40039	1	1	160201	100	99	100	100	160000	100	2	0	0	0	0	10110	1	16	1	1	40037	0	160000	100	40040	40040	40040	40040	40050

1000 unrolls and 10 iterations

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

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

retire uop (01)	cycle (02)	03	1e	37	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	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)	ld unit uop (a6)	l1d cache writeback (a8)	ac	c2	cf	d0	d2	l1i cache miss demand (d3)	d5	map dispatch bubble (d6)	d9	da	db	dd	fetch restart (de)	e0	? int output thing (e9)	ea	eb	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
160024	40048	300	0	0	0	55	25	160027	10	160017	10	160000	50	2398999	0	1	40029	40039	40039	19996	3	20028	160010	20	160000	20	480000	40039	40048	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	10022	3	1	1	28	16	2	1	1	25	25	40036	0	15	5	160000	10	40049	40040	40049	40040	40040
160024	40039	300	0	17	0	55	25	160027	10	160001	10	160000	50	1280000	2	1	40030	40048	40040	19996	3	20029	160010	20	160000	20	480000	40049	40048	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	10022	3	1	1	25	16	2	1	1	25	25	40045	0	15	5	160000	10	40050	40040	40040	40040	40040
160024	40039	300	0	17	0	616	25	160027	10	160001	10	160000	50	1319998	1	1	40021	40039	40040	19996	3	20019	160010	20	160000	20	480000	40049	40039	1	1	160021	10	9	10	10	160000	10	0	0	2	3	0	10022	3	1	1	25	16	2	1	1	12	25	40036	0	15	5	160000	10	40049	40049	40040	40049	40040
160024	40039	300	0	1	0	47	25	160010	10	160000	10	160000	50	1319998	1	1	40029	40039	40039	19996	3	20019	160010	20	160000	20	480000	40039	40048	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	10022	3	1	1	25	16	2	2	1	25	25	40036	0	15	5	160000	10	40040	40049	40040	40040	40049
160024	40048	300	0	0	0	55	25	160010	10	160017	10	160000	50	1280000	0	1	40030	40039	40039	19996	3	20019	160010	20	160000	20	480000	40048	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	10022	3	1	1	25	16	2	1	1	12	25	40045	0	15	5	160000	10	40040	40049	40040	40040	40040
160024	40039	300	0	0	0	55	25	160010	10	160000	10	160000	50	1280000	1	1	40021	40048	40048	19996	3	20028	160010	20	160000	20	480000	40048	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	10022	3	1	1	25	16	4	1	1	10	25	40037	0	15	5	160000	10	40049	40040	40049	40040	40041
160024	40039	300	0	0	0	47	25	160010	10	160001	10	160000	50	2398999	1	1	40020	40048	40039	19996	3	20019	160010	20	160000	20	480000	40048	40039	5	1	160021	10	9	10	10	160000	10	0	0	0	0	0	10024	6	2	2	12	16	4	2	2	25	13	40037	0	30	12	160000	10	40050	40050	40040	40040	40040
160024	40039	300	0	0	1	52	25	160027	10	160017	10	160000	50	2398999	1	1	40030	40049	40039	19996	3	20028	160010	20	160000	20	480000	40039	40048	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	10022	3	1	1	25	16	2	1	1	25	10	40045	0	15	5	160000	10	40040	40049	40041	40040	40040
160024	40048	300	0	1	0	46	61	160027	10	160017	10	160000	50	2398999	1	1	40029	40048	40039	19996	3	20028	160010	20	160000	20	480000	40048	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	10022	3	1	1	12	16	2	1	1	10	25	40045	0	15	5	160000	10	40050	40041	40040	40040	40040
160024	40039	300	0	17	0	46	25	160011	10	160000	10	160000	50	2398999	1	1	40030	40048	40039	19996	3	20029	160010	20	160000	20	480000	40048	40049	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	10022	3	1	1	25	16	2	1	1	12	25	40036	0	15	5	160000	10	40041	40049	40040	40040	40040

SMLAL2 (vector, 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