Firestorm: SQDMLSL2 (by element, 4S) measurements

Code:

  sqdmlsl2 v0.4s, v1.8h, v2.h[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	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	22	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	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	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	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	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	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	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	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	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	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	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	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	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	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	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	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	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	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	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038

Test 2: Latency 1->1

Code:

  sqdmlsl2 v0.4s, v1.8h, v2.h[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): 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)	69	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d tlb miss (a1)	ld unit uop (a6)	l1d cache writeback (a8)	ac	cf	d0	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? int output thing (e9)	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10204	30037	225	0	0	0	0	0	0	0	71	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	0	0	710	1	3	16	2	2	29634	0	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	533	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	0	0	710	1	2	16	2	2	29634	0	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	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	2	16	2	2	29634	0	10000	100	30082	30038	30038	30038	30038
10204	30037	225	0	0	0	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	0	0	710	1	2	16	2	2	29634	0	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	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	2	16	2	2	29634	0	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	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	2	16	3	2	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	12	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	3	3	710	1	2	16	2	2	29634	0	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	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	2	16	2	2	29634	0	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	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	2	16	2	2	29634	0	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	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	2	16	2	2	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	1e	1f	3f	4e	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	60	69	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d cache writeback (a8)	ac	c2	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	61	29548	101	10010	10	10000	10	10000	50	4277313	0	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30083	2	1	10021	10	9	10	10	10000	10	5	0	0	640	4	16	3	4	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	2	0	0	640	3	16	3	3	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	2	0	0	640	3	16	3	3	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	0	640	3	16	3	6	29668	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	598	61	29548	25	10010	10	10000	10	10000	50	4277313	0	30018	30037	30037	28287	3	28767	10161	20	10163	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	2	0	0	640	3	16	3	3	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	233	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	3	16	3	3	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	224	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	2	0	0	640	3	16	3	3	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	1	0	0	640	3	16	3	3	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	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	1	0	0	640	3	16	3	3	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	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	3	16	3	3	29630	10000	10	30038	30038	30038	30038	30038

Test 3: Latency 1->2

Code:

  sqdmlsl2 v0.4s, v0.8h, v1.h[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): 3.0037

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

retire uop (01)	cycle (02)	03	18	19	1e	1f	3f	4e	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	60	69	6b	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d tlb miss (a1)	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
10204	30037	225	0	0	0	0	239	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	0	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	2	1	11413	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	24	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	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	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	492	29548	25	10100	100	10000	100	10000	500	4277313	0	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	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	6	0	84	29548	25	10100	100	10000	100	10000	500	4277313	1	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	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	224	0	0	15	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	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	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	124	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	0	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	3	1	10201	100	99	100	100	10000	100	0	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30181
10204	30085	225	0	0	0	0	107	29548	25	10100	100	10000	100	10000	500	4277313	1	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	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	1	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	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	108	189	29548	25	10100	100	10000	100	10000	500	4277313	1	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	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	191	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	0	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	51	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	1e	3f	4e	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	60	69	6b	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d cache writeback (a8)	ac	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
10024	30037	225	0	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	0	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	61	29548	25	10010	10	10000	10	10000	50	4277313	0	30018	0	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	30133	30038	30038	30038	30038
10024	30037	225	0	964	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	0	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	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	0	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	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	0	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	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	0	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	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	0	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	30179	30038	30038
10024	30037	225	0	61	29548	25	10010	10	10000	12	10000	50	4277313	1	30018	0	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	75	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	0	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	3	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	224	0	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	0	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

Test 4: Latency 1->3

Code:

  sqdmlsl2 v0.4s, v1.8h, v0.h[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): 3.0037

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

retire uop (01)	cycle (02)	03	18	19	1e	3f	4e	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	60	69	6d	6e	map stall dispatch (70)	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	0	212	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	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	0	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	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	0	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	61	29548	44	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	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	0	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	710	1	16	1	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	224	0	0	6	61	29548	25	10100	100	10000	100	10000	500	4277313	0	30018	30037	30037	28265	0	3	28745	10100	200	10000	200	30000	30085	30037	1	1	10201	100	99	100	100	10000	100	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	0	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	224	0	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	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	0	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	710	1	33	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	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

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 instruction (07)	mmu table walk data (08)	l2 tlb miss instruction (0a)	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)	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	l1d tlb access (a0)	ld unit uop (a6)	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	30037	224	1	0	1	0	0	0	0	0	2	110	29548	25	10010	10	10000	10	10000	50	4277313	30018	0	30037	30037	28287	0	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	644	10	16	5	10	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	1	0	1	0	0	0	0	0	2	110	29548	25	10010	10	10000	10	10000	50	4277313	30018	0	30037	30037	28287	0	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	644	10	16	10	10	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	224	1	0	1	0	0	0	0	0	2	196	29548	25	10010	10	10000	10	10000	50	4277313	30018	0	30037	30037	28287	0	3	28767	10010	20	10000	20	30000	30037	30080	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	644	10	16	11	10	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	1	0	1	0	0	0	0	0	2	175	29548	25	10010	10	10000	10	10000	50	4277313	30018	0	30037	30037	28287	0	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	644	10	16	10	5	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	1	0	1	0	0	0	0	0	2	89	29548	25	10010	10	10000	10	10000	50	4277313	30018	0	30037	30037	28287	0	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	644	10	16	10	11	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	1	0	1	0	0	0	0	0	2	198	29548	25	10010	10	10000	10	10000	50	4277313	30018	0	30037	30037	28287	0	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10022	10	9	10	10	10000	10	0	0	0	0	0	644	8	16	11	8	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	1	0	1	0	0	0	0	0	2	131	29548	25	10010	10	10000	10	10000	50	4277313	30018	0	30037	30037	28287	0	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	644	5	16	11	10	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	1	0	1	0	0	0	0	0	2	173	29548	25	10010	10	10000	10	10000	50	4277313	30018	0	30037	30037	28287	0	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	644	10	16	10	10	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	1	0	1	0	0	0	0	0	2	303	29548	25	10010	10	10000	10	10000	50	4277313	30018	0	30037	30037	28287	0	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	644	10	16	10	10	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	1	0	1	0	0	0	0	0	2	131	29548	25	10010	10	10000	10	10000	50	4277313	30018	0	30037	30037	28287	0	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	644	10	16	10	12	29630	0	10000	10	30038	30038	30038	30038	30038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  sqdmlsl2 v0.4s, v8.8h, v9.h[1]
  movi v1.16b, 0
  sqdmlsl2 v1.4s, v8.8h, v9.h[1]
  movi v2.16b, 0
  sqdmlsl2 v2.4s, v8.8h, v9.h[1]
  movi v3.16b, 0
  sqdmlsl2 v3.4s, v8.8h, v9.h[1]
  movi v4.16b, 0
  sqdmlsl2 v4.4s, v8.8h, v9.h[1]
  movi v5.16b, 0
  sqdmlsl2 v5.4s, v8.8h, v9.h[1]
  movi v6.16b, 0
  sqdmlsl2 v6.4s, v8.8h, v9.h[1]
  movi v7.16b, 0
  sqdmlsl2 v7.4s, v8.8h, v9.h[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	mmu table walk instruction (07)	mmu table walk data (08)	l2 tlb miss instruction (0a)	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)	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	branch cond mispred nonspec (c5)	branch mispred nonspec (cb)	cd	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
160204	20089	150	1	0	1	0	0	29	25	80116	100	80016	100	80028	500	640196	20045	20065	20065	6	12	80128	200	80028	200	240084	20065	20065	1	1	160201	100	99	100	100	160000	100	0	0	1	1	1	10119	3	16	1	1	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	150	1	0	1	0	0	29	25	80116	100	80016	100	80028	500	640196	20045	20065	20065	6	12	80128	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	10112	2	16	2	2	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	0	0	0	39	25	80100	100	80000	100	80000	500	640000	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	10112	2	16	2	2	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	0	0	0	81	25	80100	100	80000	100	80000	500	640000	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	10112	2	16	2	2	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	0	0	6	39	25	80100	100	80000	100	80000	500	640000	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	10112	2	16	2	2	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	0	0	312	39	25	80100	100	80000	100	80000	500	640000	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	10112	2	16	2	2	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	0	0	0	39	25	80100	100	80000	100	80000	500	640000	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	10112	2	49	2	2	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	0	0	0	39	25	80100	100	80000	100	80000	500	640000	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	10112	2	16	2	2	20061	160000	100	20065	20065	20065	20146	20065
160204	20144	150	0	1	0	1	0	39	25	80100	100	80000	100	80000	500	640000	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	10112	2	16	2	2	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	0	0	0	419	25	80100	100	80000	100	80000	500	640000	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	10112	2	16	2	2	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 instruction (07)	l2 tlb miss instruction (0a)	1e	1f	3a	3f	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	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	branch cond mispred nonspec (c5)	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	20079	150	0	0	0	0	0	927	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	0	10029	3	1	1	6	20	2	1	1	8	8	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	0	20027	0	20046	20046	3	22	80012	20	80000	20	240000	20046	20046	1	1	160021	10	9	10	10	160000	10	0	0	0	10031	3	1	1	9	20	2	1	1	6	9	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	0	10029	3	1	1	9	20	2	1	1	9	9	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	20050	20050	1	1	160021	10	9	10	10	160000	10	0	0	0	10031	3	2	2	9	26	4	2	2	6	9	20049	2	15	160000	10	20053	20053	20051	20051	20053
160024	20052	150	0	0	0	0	0	51	25	80012	12	80000	12	80000	62	640000	0	1	20027	0	20050	20046	3	22	80012	20	80000	20	240000	20050	20050	1	1	160021	10	9	10	10	160000	10	0	0	0	10031	3	2	2	6	24	4	2	2	6	9	20047	2	30	160000	10	20053	20053	20051	20051	20053
160024	20050	150	0	0	0	0	0	56	25	80012	12	80000	12	80000	62	640000	0	1	20031	0	20050	20050	3	22	80012	20	80000	20	240000	20050	20050	1	1	160021	10	9	10	10	160000	10	0	0	1	10035	6	2	2	9	59	4	2	2	6	9	20047	2	31	160000	10	20053	20053	20051	20051	20051
160024	20050	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	20050	20050	1	1	160021	10	9	10	10	160000	10	0	530	0	10030	3	1	1	10	20	2	1	1	6	6	20043	2	15	160000	10	20047	20047	20047	20047	20047
160024	20046	150	0	0	6	0	0	51	25	80012	12	80000	12	80000	62	640000	0	0	20031	0	20050	20050	3	22	80012	20	80000	20	240000	20050	20050	1	1	160021	10	9	10	10	160000	10	0	0	0	10029	3	1	1	9	20	2	1	1	9	9	20043	2	15	160000	10	20047	20047	20047	20047	20047
160024	20046	150	0	0	0	0	0	51	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	0	10029	3	1	1	8	20	2	1	1	5	5	20043	2	15	160000	10	20047	20047	20047	20047	20047
160024	20046	150	0	0	0	0	0	45	25	80012	12	80000	13	80000	62	640000	1	0	20027	0	20046	20046	3	22	80012	20	80000	20	240000	20046	20046	1	1	160021	10	9	10	10	160000	10	0	0	0	10029	3	1	1	9	20	2	1	1	9	6	20043	2	15	160000	10	20047	20047	20047	20047	20047

Test 6: throughput

Count: 12

Code:

  sqdmlsl2 v0.4s, v12.8h, v13.h[1]
  sqdmlsl2 v1.4s, v12.8h, v13.h[1]
  sqdmlsl2 v2.4s, v12.8h, v13.h[1]
  sqdmlsl2 v3.4s, v12.8h, v13.h[1]
  sqdmlsl2 v4.4s, v12.8h, v13.h[1]
  sqdmlsl2 v5.4s, v12.8h, v13.h[1]
  sqdmlsl2 v6.4s, v12.8h, v13.h[1]
  sqdmlsl2 v7.4s, v12.8h, v13.h[1]
  sqdmlsl2 v8.4s, v12.8h, v13.h[1]
  sqdmlsl2 v9.4s, v12.8h, v13.h[1]
  sqdmlsl2 v10.4s, v12.8h, v13.h[1]
  sqdmlsl2 v11.4s, v12.8h, v13.h[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): 0.2503

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	19	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)	60	69	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d tlb miss (a1)	ld unit uop (a6)	l1d cache writeback (a8)	ac	c2	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? int output thing (e9)	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
120204	30060	225	0	0	0	0	156	0	17	0	231	0	25	120118	100	120000	100	120000	500	960000	1	30020	30039	30039	14973	3	14997	120100	200	120000	200	360000	30039	30039	1	1	120201	100	99	100	100	120000	100	0	0	0	0	0	7610	1	16	1	1	30919	25	120000	100	30040	31749	30040	30040	30040
120204	30039	225	0	0	0	0	0	0	0	0	41	0	25	120100	100	120001	100	120000	626	990000	0	30020	30039	30039	15828	3	16706	120100	200	120000	200	360000	30039	30041	1	1	120201	100	99	100	100	120000	100	0	0	0	0	0	7610	1	16	1	1	30036	0	120000	100	30040	30041	30040	30040	30040
120204	30039	237	0	0	0	0	0	0	1	0	41	0	25	120100	100	120000	100	120000	500	960000	1	30020	30041	30039	14973	3	16706	120100	200	120000	200	360000	30039	31748	1	1	120201	100	99	100	100	120000	100	0	0	0	0	0	7610	1	16	1	1	30036	25	120000	100	30040	31738	30040	30040	31738
120204	31737	225	0	0	0	0	0	0	0	0	41	0	25	120101	100	120018	100	120000	500	960000	1	30020	30922	30039	16653	3	16706	120100	200	120000	200	360000	30040	30039	1	1	120201	100	99	100	100	120000	100	0	0	0	0	0	7610	1	16	5	1	30036	0	120000	100	30040	30040	30040	30040	30041
120204	30039	225	0	0	2	2	321	324	1	1	248	0	25	120100	120	120154	114	120113	613	974255	1	30233	31559	30039	14973	10	15022	120222	200	120210	200	360948	30154	30266	2	1	120201	100	99	100	100	120000	100	0	0	0	945	0	7635	2	32	1	1	30086	0	120000	100	30040	30040	30040	30040	30170
120204	30106	228	0	0	1	1	132	104	0	0	83	3713	67	120100	100	120084	100	120000	500	960000	0	30020	30039	30039	16653	14	15027	120325	200	120000	200	360000	30039	30040	1	1	120201	100	99	100	100	120000	100	0	0	0	470	2	7610	1	16	1	1	31745	0	120000	100	30040	30040	31749	30044	31749
120204	31748	225	0	0	0	0	0	0	0	1	1374	0	177	121017	125	120734	123	121039	626	1849504	0	30861	30429	31187	15819	45	15262	121062	204	120950	200	362178	30927	30723	8	1	120201	100	99	100	100	120000	100	2	2	1	3680	2	7738	5	103	4	5	30656	28	120000	100	30499	30801	30907	30510	31060
120204	30479	226	6	1	10	10	1065	616	93	0	1811	0	195	121089	124	120897	124	121517	632	2180790	1	31168	31414	30716	15682	50	15513	121178	202	121067	202	362787	31017	30556	11	1	120201	100	99	100	100	120000	100	2	0	0	5103	4	7843	2	129	3	3	30454	22	120000	100	30865	31411	32460	30727	30514
120204	30876	230	0	0	0	0	15	0	18	0	103	0	25	120100	100	120000	100	120000	500	960000	1	31729	30040	30039	14973	3	15900	120100	200	120000	200	360000	30039	30039	1	1	120201	100	99	100	100	120000	100	0	0	0	0	0	7610	5	17	1	1	30037	0	120000	100	30040	30923	30040	30923	30040
120204	30039	225	0	0	0	0	0	0	0	0	423	0	25	120100	100	120000	100	120000	500	990000	1	30020	30039	31748	14973	3	16706	120100	200	120000	200	360000	30039	31748	1	1	120201	100	99	100	100	120000	100	0	0	0	0	0	7610	1	16	1	1	30036	0	120000	100	31749	30040	30040	30040	31749

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2503

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

retire uop (01)	cycle (02)	03	18	1e	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	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	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
120024	30048	225	0	24	0	46	25	120010	10	120000	10	120000	50	960000	1	1	30020	30039	30039	14996	3	15019	120010	20	120000	20	360000	30039	30039	1	1	120021	10	9	10	10	120000	10	0	0	0	7524	6	1	1	18	16	2	1	2	10	6	30036	0	15	5	120000	10	30040	30923	30040	30040	30040
120024	30039	238	0	6	0	46	25	120010	10	120000	10	120000	50	960000	1	1	30020	30951	30041	14996	3	15019	120010	20	120000	20	360000	30039	30039	1	1	120021	10	9	10	10	120000	10	0	0	0	7522	3	1	1	4	16	2	1	1	12	8	30036	0	30	5	120000	10	30040	30040	30040	30040	30040
120024	30039	225	0	42	0	46	25	120010	10	120000	10	120000	50	960000	1	1	30020	30039	30039	14996	3	15019	120010	20	120000	20	360000	30039	30039	1	1	120021	10	9	10	10	120000	10	0	0	0	7522	3	1	1	4	16	2	1	1	8	6	30036	0	15	5	120000	10	30040	30040	30923	30040	30040
120024	30039	225	0	6	0	52	25	120134	10	120000	10	120000	50	960000	1	1	30020	30039	30039	14996	3	15019	120010	20	120000	20	360000	30039	30039	1	1	120021	10	9	10	10	120000	10	0	0	0	7522	3	1	1	6	16	2	1	1	6	5	30036	0	15	5	120000	10	30040	30040	30040	30040	30040
120024	30039	225	0	0	0	46	25	120010	10	120000	10	120000	50	960000	1	1	30020	30039	30042	14996	3	15019	120010	20	120000	20	360000	31748	30039	1	1	120021	10	9	10	10	120000	10	0	0	0	7522	3	1	1	4	16	2	1	1	10	4	30036	0	15	5	120000	10	30040	30040	30040	30040	30040
120024	30039	225	0	6	0	46	25	120010	10	120000	10	120000	50	960000	0	1	30020	30039	30039	14996	3	15902	120010	20	120000	20	360000	30039	30039	1	1	120021	10	9	10	10	120000	10	0	0	0	7522	3	1	1	10	16	2	1	1	6	4	30036	0	15	5	120000	10	30040	30040	30040	30040	30040
120024	30039	225	0	6	0	46	25	120010	10	120000	10	120000	50	960000	1	1	30020	30039	30039	16676	3	15019	120010	20	120000	20	360000	30039	31748	1	1	120021	10	9	10	10	120000	10	0	0	0	7522	6	2	1	10	16	2	1	1	4	10	30036	0	15	5	120000	10	30040	30040	30040	30040	30040
120024	30039	224	0	39	0	46	25	120045	10	120000	10	120000	50	960000	1	1	30020	30039	30039	14996	3	15019	120010	20	120000	20	360000	30039	30039	1	1	120021	10	9	10	10	120000	10	0	0	0	7522	3	1	1	10	16	2	1	1	6	4	30036	0	15	5	120000	10	30040	30040	30040	30040	30040
120024	31748	225	0	84	0	46	25	120010	10	120000	10	120000	50	960000	1	1	30020	30039	31750	14996	3	15019	120010	20	120000	20	360000	30039	30922	1	1	120021	10	9	10	10	120000	10	0	0	0	7522	3	1	1	4	16	2	1	1	4	10	30036	0	15	5	120000	10	30040	30040	30040	30040	30040
120024	30039	225	0	3	0	46	25	120010	10	120000	10	120000	50	960000	1	1	30020	30039	30040	14996	3	15019	120010	20	120000	20	360000	30039	30039	1	1	120021	10	9	10	10	120000	10	0	0	0	7524	6	1	1	4	16	2	1	1	4	6	30036	0	15	5	120000	10	30040	30040	30040	30040	30040

SQDMLSL2 (by element, 4S)

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