Firestorm: SQDMLAL (vector, 2D) measurements

Code:

  sqdmlal v0.2d, v1.2s, v2.2s

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	mmu table walk data (08)	l2 tlb miss data (0b)	1e	1f	3f	4e	51	schedule uop (52)	schedule simd uop (54)	dispatch simd uop (57)	ldst uops in schedulers (5b)	60	69	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map simd uop (7e)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst simd alu (9a)	l1d tlb miss (a1)	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	? simd retires (ee)	f5	f6	f7	f8	fd
1004	3037	22	0	0	0	0	61	2548	25	1000	1000	1000	398313	0	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	0	0	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	0	0	61	2548	25	1000	1000	1000	398313	0	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	0	0	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	0	0	0	0	61	2548	25	1000	1000	1000	398313	0	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	0	0	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	0	0	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	0	0	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	0	0	0	0	61	2548	25	1000	1000	1000	398313	0	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	0	0	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	0	0	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	0	0	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	0	0	891	2548	25	1000	1000	1000	398313	0	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	0	1	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	0	0	116	2548	25	1000	1000	1000	398313	1	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	0	0	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	0	0	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	0	0	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	0	0	61	2548	25	1000	1000	1000	398313	0	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	0	0	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038

Test 2: Latency 1->1

Code:

  sqdmlal v0.2d, v1.2s, v2.2s

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	mmu table walk data (08)	l2 tlb miss data (0b)	18	19	1e	1f	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)	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	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	1	710	1	3	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	224	0	0	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	0	710	1	2	16	3	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	0	1	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	0	710	1	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	224	0	0	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	0	710	1	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	224	0	0	0	0	0	0	0	103	29548	25	10100	100	10000	100	10149	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	0	710	1	2	16	2	3	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	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	0	710	1	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	224	0	0	0	0	0	0	0	103	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	0	710	1	2	16	3	2	29778	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	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	0	710	1	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	0	0	61	29548	25	10100	100	10000	104	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	0	710	1	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	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	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	l2 tlb miss data (0b)	1e	1f	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)	ac	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	0	0	0	0	868	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	12	640	8	16	8	9	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	3	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	0	640	8	16	8	7	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	783	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	7	16	8	8	29630	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	0	640	7	16	6	8	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	684	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	8	16	8	7	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	82	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	8	16	8	6	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	224	0	0	0	0	247	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	7	16	7	8	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	1644	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	9	16	7	9	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	839	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	8	16	8	7	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	872	29548	25	10019	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	7	16	7	7	29630	10000	10	30038	30038	30038	30038	30038

Test 3: Latency 1->2

Code:

  sqdmlal v0.2d, v0.2s, v1.2s

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	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 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
10204	30037	225	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	0	0	0	0	710	2	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	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	0	0	0	0	710	1	16	1	1	29644	10000	100	30038	30038	30038	30038	30038
10204	30037	224	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	0	0	6	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	964	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	0	0	0	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	1	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	0	0	0	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	12	0	61	29548	25	10100	120	10008	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	204	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	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	0	0	0	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	0	30018	30037	30037	28265	3	28745	10100	204	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	82	29548	25	10100	100	10000	100	10148	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	0	0	4	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	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	0	0	0	0	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	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)	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)	a9	ac	c2	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	0	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	640	3	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	640	2	16	2	2	29630	10000	10	30085	30038	30038	30038	30133
10024	30037	233	0	3	0	103	29548	25	10010	10	10000	10	10000	50	4277313	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	2	1	0	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	224	0	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	640	2	16	2	2	29774	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038

Test 4: Latency 1->3

Code:

  sqdmlal v0.2d, v1.2s, v0.2s

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	19	1e	1f	3a	3f	4e	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	69	6b	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d tlb access (a0)	a9	ac	branch mispred nonspec (cb)	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? int output thing (e9)	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10204	30037	224	0	0	0	0	82	29548	25	10100	100	10000	100	10000	500	4277313	30018	0	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	710	1	16	1	1	29634	0	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	0	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	12	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	30018	3	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	61	29548	25	10100	104	10000	100	10000	500	4277313	30018	0	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	61	29548	25	10100	100	10000	100	10148	500	4277313	30065	0	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	159	1	710	1	16	1	1	29634	0	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	0	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	710	1	16	1	1	29634	0	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	0	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	6	0	734	1	16	1	1	29634	0	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	0	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	710	1	16	1	1	29634	0	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	0	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	710	1	16	1	1	29634	0	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	0	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	710	1	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)	19	1e	1f	3f	4e	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	60	69	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d tlb miss (a1)	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
10024	30037	225	0	0	0	0	0	251	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	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	238	0	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	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	224	0	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	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	0	30018	30037	30037	28287	25	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	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	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	224	0	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	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	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	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	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	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	12	88	726	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	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	224	0	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	0	0	640	2	16	4	2	29630	10000	10	30038	30038	30038	30038	30038

Test 5: throughput

Count: 8

Code:

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

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	mmu table walk data (08)	09	19	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)	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)	st unit uop (a7)	l1d cache writeback (a8)	ac	branch mispred nonspec (cb)	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	0	0	514	25	80100	100	80000	100	80000	500	640000	1	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	0	0	10111	1	16	1	1	20061	0	160000	100	20065	20065	20065	20065	20065
160204	20064	151	0	0	0	0	0	39	42	80101	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	270	0	0	10111	1	16	1	1	20061	0	160000	100	20065	20065	20065	20065	20065
160204	20064	151	0	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	0	0	10111	1	16	1	1	20061	0	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	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	0	0	10111	1	16	1	1	20061	0	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	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	0	0	10111	1	16	1	1	20061	0	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	0	0	0	518	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	0	0	10111	1	16	1	1	20061	0	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	0	3	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	1	3	0	0	10111	1	16	1	1	20061	0	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	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	0	0	10111	1	16	1	1	20192	0	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	0	0	0	39	25	80100	100	80000	100	80000	500	640000	0	20045	20064	20156	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	1	1	3	0	0	10111	1	16	1	1	20061	12	160000	100	20065	20065	20065	20065	20065
160204	20146	150	0	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	0	0	10111	1	16	1	1	20061	0	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 instruction (07)	09	l2 tlb miss data (0b)	1e	3f	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	5f	60	61	69	6d	6e	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d cache writeback (a8)	ac	cf	d0	d2	l1i cache miss demand (d3)	d5	map dispatch bubble (d6)	d9	da	db	dd	fetch restart (de)	e0	? int output thing (e9)	ea	ec	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
160024	20087	151	0	0	0	30	51	27	80012	12	80000	12	80000	62	640000	1	1	5	20032	20060	20060	3	22	80012	20	80000	20	240000	20051	20060	1	1	160021	10	9	10	10	160000	10	0	0	10030	8	2	27	8	34	4	1	1	4	7	20057	2	40	2	160000	10	20061	20174	20061	20061	20052
160024	20060	150	0	0	0	0	45	27	80012	12	80000	12	80000	62	640000	0	1	5	20032	20060	20060	3	22	80012	20	80000	20	240000	20051	20060	1	1	160021	10	9	10	10	160000	10	0	0	10029	8	2	26	9	34	2	1	1	3	7	20057	2	40	2	160000	10	20052	20061	20052	20061	20052
160024	20051	150	0	0	0	0	51	27	80012	12	80000	12	80000	62	640000	1	0	5	20041	20051	20060	3	22	80012	20	80000	20	240000	20051	20051	1	1	160021	10	9	10	10	160000	10	0	0	10026	8	1	25	3	25	2	1	1	5	6	20048	2	20	1	160000	10	20052	20052	20052	20052	20052
160024	20051	150	0	0	0	0	45	27	80012	12	80000	12	80000	62	640000	1	1	5	20032	20051	20051	3	22	80012	20	80000	20	240000	20051	20051	1	1	160021	10	9	10	10	160000	10	0	0	10028	8	4	25	5	25	2	1	1	5	7	20048	2	20	1	160000	10	20052	20052	20052	20052	20052
160024	20051	150	0	0	0	0	45	27	80012	12	80000	12	80000	62	640000	1	1	0	20032	20051	20051	3	22	80012	20	80000	20	240000	20051	20051	1	1	160021	10	9	10	10	160000	10	0	0	10026	8	4	25	5	25	2	1	1	5	5	20048	2	20	1	160000	10	20052	20052	20052	20052	20052
160024	20051	150	0	0	0	0	45	27	80012	12	80000	12	80000	62	640000	1	1	5	20032	20051	20051	3	22	80012	20	80000	20	240000	20051	20051	1	1	160021	10	9	10	10	160000	10	0	0	10026	8	4	21	5	25	2	1	1	5	11	20048	2	20	1	160000	10	20052	20052	20052	20052	20052
160024	20051	150	0	0	0	0	45	27	80012	12	80000	12	80000	62	640000	1	1	5	20032	20051	20051	3	22	80012	20	80000	20	240000	20051	20051	1	1	160021	10	9	10	10	160000	10	0	0	10028	8	4	20	5	25	2	1	2	9	4	20048	2	20	1	160000	10	20052	20052	20052	20052	20052
160024	20051	150	0	0	0	0	45	27	80012	12	80000	12	80000	62	640000	1	1	5	20032	20051	20051	3	22	80012	20	80000	20	240000	20062	20051	1	1	160021	10	9	10	10	160000	10	0	0	10028	8	4	20	5	34	2	2	1	6	4	20048	2	20	1	160000	10	20052	20061	20052	20052	20052
160024	20051	150	0	0	0	0	45	29	80012	12	80000	12	80000	62	640000	1	1	5	20032	20051	20060	3	22	80012	20	80000	20	240000	20051	20060	1	1	160021	10	9	10	10	160000	10	0	0	10026	11	4	19	3	25	2	2	1	5	6	20048	2	20	1	160000	10	20052	20052	20052	20052	20052
160024	20051	150	0	0	0	0	45	27	80012	12	80000	12	80000	62	640000	1	1	5	20032	20051	20051	3	22	80012	20	80000	20	240000	20051	20060	1	1	160021	10	9	10	10	160000	10	0	0	10028	8	4	19	5	25	2	1	1	9	4	20048	2	20	1	160000	10	20052	20052	20052	20052	20052

Test 6: throughput

Count: 16

Code:

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

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)	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)	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 mispred nonspec (cb)	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
160204	40059	300	0	0	0	0	41	25	160100	100	160000	100	160000	500	1280000	1	40020	40048	40039	19973	0	3	20006	160100	200	160000	200	480000	40039	40039	1	1	160201	100	99	100	100	160000	100	0	0	0	10110	1	16	1	1	40036	160000	100	40040	40040	40049	40049	40049
160204	40039	299	0	0	0	0	41	25	160100	100	160017	100	160000	500	1280000	1	40029	40039	40039	19973	0	3	19997	160100	200	160000	200	480000	40039	40048	1	1	160201	100	99	100	100	160000	100	0	0	0	10110	2	16	1	1	40036	160000	100	40040	40040	40049	40040	40040
160204	40048	299	0	0	0	0	41	25	160100	100	160001	100	160000	500	2398999	1	40029	40039	40039	19973	0	3	20007	160100	200	160000	200	480000	40048	40039	1	1	160201	100	99	100	100	160000	100	0	0	0	10110	2	16	1	2	40036	160000	100	40041	40050	40050	40050	40040
160204	40039	300	0	0	0	0	62	25	160117	100	160000	100	160000	500	1280000	1	40020	40039	40039	19973	0	3	19997	160100	200	160000	200	480000	40039	40039	1	1	160201	100	99	100	100	160000	100	0	0	0	10110	1	16	3	3	40036	160000	100	40040	40040	40040	40049	40040
160204	40040	300	0	0	0	0	41	25	160100	100	160000	100	160000	500	1280000	1	40020	40048	40039	19973	0	3	19997	160100	200	160000	200	480000	40039	40052	1	1	160201	100	99	100	100	160000	100	0	0	0	10110	2	16	1	2	40036	160000	100	40040	40040	40040	40040	40040
160204	40048	300	0	213	132	0	41	25	160100	100	160000	100	160000	500	1280000	1	40020	40039	40048	19973	0	3	20006	160100	200	160000	200	480000	40040	40049	2	1	160202	100	99	100	100	160000	100	2	0	0	10110	1	16	2	2	40045	160000	100	40040	40040	40040	40040	40040
160204	40039	300	0	0	0	0	51	25	160100	100	160000	100	160000	500	2398999	1	40020	40039	40040	19973	0	3	19997	160100	200	160000	200	480000	40040	40049	1	1	160201	100	99	100	100	160000	100	0	0	0	10110	1	16	2	1	40036	160000	100	40040	40040	40040	40040	40040
160204	40039	300	0	0	0	0	41	25	160100	100	160000	100	160000	500	1280000	1	40020	40049	40039	19973	0	3	19997	160100	200	160000	200	480000	40039	40039	1	1	160201	100	99	100	100	160000	100	0	0	0	10110	2	16	2	2	40046	160000	100	40040	40040	40040	40040	40040
160204	40090	300	0	0	0	1	41	25	160100	100	160001	100	160000	500	1280000	1	40020	40039	40039	19973	0	3	19997	160100	200	160000	200	480000	40039	40039	1	1	160201	100	99	100	100	160000	100	0	0	0	10110	2	16	2	2	40036	160000	100	40040	40040	40041	40040	40049
160204	40039	300	0	0	0	0	42	25	160100	100	160000	100	160000	500	1280000	1	40020	40049	40039	19973	0	3	19997	160100	200	160000	200	480000	40049	40048	1	1	160201	100	99	100	100	160000	100	0	0	0	10110	1	16	1	2	40036	160000	100	40040	40040	40040	40040	40040

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	mmu table walk data (08)	09	l2 tlb miss instruction (0a)	l2 tlb miss data (0b)	18	19	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)	5f	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 tlb access (a0)	l1d tlb miss (a1)	ld unit uop (a6)	st unit uop (a7)	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	eb	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
160024	40048	300	0	0	0	0	0	0	0	0	1	46	44	160010	10	160000	10	160000	50	2398999	1	1	0	40020	40039	40039	19996	3	20028	160010	20	160000	20	480000	40040	40048	1	1	160021	10	9	10	10	160000	10	0	0	0	1	3	0	10085	8	4	1	7	16	2	1	1	5	7	40036	0	20	6	160000	10	40040	40050	40040	40040	40040
160024	40040	299	0	0	0	0	0	0	0	0	0	46	25	160010	10	160001	10	160000	50	1903324	1	1	5	40029	40039	40039	19996	3	20019	160010	20	160000	20	480000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	4	0	0	0	0	10080	8	2	1	5	16	2	1	1	7	7	40045	0	20	6	160000	10	40050	40040	40040	40040	40040
160024	40039	300	0	0	0	0	0	0	0	0	0	46	25	160027	10	160000	10	160000	50	1280000	1	1	5	40020	40039	40039	19996	3	20029	160010	20	160000	20	480000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	0	1	0	10090	6	4	1	8	16	2	1	1	7	8	40036	0	20	6	160000	10	40260	40049	40049	40040	40040
160024	40039	300	0	0	0	0	0	0	0	0	0	46	25	160010	10	160000	10	160000	50	1280000	1	1	5	40126	40039	40039	19996	3	20019	160010	20	160000	20	480000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	0	3	0	10069	11	5	2	6	60	2	2	2	10	7	40036	0	40	6	160000	10	40040	40040	40040	40040	40313
160024	40039	300	0	0	0	0	0	0	0	0	17	56	25	160010	10	160000	10	160000	50	1280000	1	1	5	40020	40049	40267	19996	3	20019	160010	20	160000	20	480000	40039	40048	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	3	10064	11	5	1	9	16	2	1	1	7	7	40045	0	20	6	160000	10	40049	40049	40040	40040	40040
160024	40039	299	0	0	0	0	0	0	0	0	0	712	25	160010	10	160000	10	160000	50	1280000	1	1	5	40020	40039	40039	19996	3	20029	160010	20	160000	20	480000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	0	10073	8	4	1	10	16	2	1	1	5	4	40046	0	20	9	160000	10	40040	40040	40041	40040	40040
160024	40049	300	0	0	0	0	0	0	0	0	0	67	25	160010	10	160000	10	160000	50	1280000	1	1	5	40021	40039	40039	19996	3	20019	160010	20	160000	20	480000	40048	40039	1	1	160021	10	9	10	10	160000	10	0	0	2	0	0	0	10064	8	4	1	4	16	2	1	1	4	5	40037	0	20	7	160000	10	40040	40040	40040	40040	40040
160024	40039	300	0	0	0	0	0	0	0	0	0	46	25	160010	10	160000	10	160000	50	1280000	1	1	5	40020	40039	40039	19996	3	20029	160010	20	160000	20	480000	40048	40048	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	0	10064	11	5	2	5	16	2	1	1	4	5	40036	0	20	7	160000	10	40040	40041	40050	40049	40040
160024	40039	299	0	0	0	0	0	0	0	0	0	46	25	160010	10	160000	10	160000	50	1280000	1	1	5	40020	40039	40039	19996	3	20019	160010	20	160000	20	480000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	0	10064	11	5	2	5	61	2	2	1	5	5	40045	0	20	6	160000	10	40040	40040	40050	40040	40040
160024	40049	300	0	0	0	0	0	0	9	0	0	46	25	160010	10	160000	10	160000	50	1280000	1	1	5	40020	40039	40039	19996	3	20019	160010	20	160000	20	480000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	0	10068	8	4	1	5	16	2	1	1	5	7	40036	0	20	6	160000	10	40040	40040	40040	40040	40040

SQDMLAL (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