Firestorm: SMLSL (by element, 2D) measurements

Code:

  smlsl v0.2d, v1.2s, v2.s[1]

Initialization

  movi v0.16b, 1
  movi v1.16b, 2
  movi v2.16b, 3

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 1.000

Issues: 1.000

Integer unit issues: 0.000

Load/store unit issues: 0.000

SIMD/FP unit issues: 1.000

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

retire uop (01)	cycle (02)	03	1e	3f	4e	51	schedule uop (52)	schedule simd uop (54)	dispatch simd uop (57)	ldst uops in schedulers (5b)	69	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map simd uop (7e)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst simd alu (9a)	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	0	84	2548	25	1000	1000	1000	398313	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	73	2	16	2	2	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	216	61	2548	25	1000	1000	1000	398313	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	73	2	16	2	2	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	0	61	2548	25	1000	1000	1000	398313	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	73	2	16	2	2	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	0	61	2548	25	1000	1000	1000	398313	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	1	0	73	2	16	2	2	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	61	2548	25	1000	1000	1000	398313	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	73	2	16	2	2	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	0	61	2548	25	1000	1000	1000	398313	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	73	2	16	2	2	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	61	2548	25	1000	1000	1000	398313	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	73	2	16	2	2	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	6	61	2548	25	1000	1000	1000	398313	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	73	2	16	2	2	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	0	61	2548	25	1000	1000	1000	398313	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	73	2	16	2	2	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	61	2548	25	1000	1000	1000	398313	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	73	2	16	2	2	2630	1000	3038	3038	3038	3038	3038

Test 2: Latency 1->1

Code:

  smlsl v0.2d, v1.2s, v2.s[1]

Initialization

  movi v0.16b, 1
  movi v1.16b, 2
  movi v2.16b, 3

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

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

retire uop (01)	cycle (02)	03	1e	3a	3f	4e	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	60	69	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d cache writeback (a8)	ac	cf	d0	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10204	30037	225	30	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	710	1	3	16	2	2	29634	10000	100	30038	30038	30038	30084	30038
10204	30037	225	282	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	710	1	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	224	258	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	710	1	2	16	3	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	372	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	712	1	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	450	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	710	1	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	224	0	0	61	29538	45	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	710	1	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	444	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	710	1	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	426	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	710	1	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	396	0	1177	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	710	1	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	303	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	48	6	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	mmu table walk data (08)	l2 tlb miss data (0b)	1e	1f	3f	4e	50	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	ld unit uop (a6)	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	0	0	61	29548	0	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	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	15	0	61	29548	30021	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	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	15	0	61	29548	21119	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	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	24	0	61	29548	0	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	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	61	29548	0	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	0	640	2	16	2	3	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	24	0	61	29548	0	25	10010	10	10000	10	10000	50	4277313	0	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	2	1	10021	10	9	10	10	10000	10	0	0	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	27	0	61	29548	0	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	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	15	0	61	29548	0	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	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	15	0	61	29548	0	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	0	640	2	16	2	3	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	61	29548	0	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	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038

Test 3: Latency 1->2

Code:

  smlsl v0.2d, v0.2s, v1.s[1]

Initialization

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

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 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	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 cache writeback (a8)	ac	branch cond mispred nonspec (c5)	branch mispred nonspec (cb)	cd	cf	map dispatch bubble (d6)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10204	30037	225	84	61	29548	25	10100	100	10000	100	10000	500	4277313	0	30018	30037	30037	28272	7	28741	10100	200	10008	200	30024	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	1	1	1	717	16	29647	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	61	29548	25	10100	100	10000	100	10000	500	4277313	0	30018	30037	30037	28272	6	28740	10100	200	10008	200	30024	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	1	1	1	717	16	29647	10000	100	30038	30038	30038	30038	30038
10204	30037	225	21	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28272	7	28741	10100	200	10008	200	30024	30037	30037	1	1	10201	100	99	100	100	10000	100	0	1	0	1	1	1	718	16	29646	10000	100	30038	30038	30038	30038	30038
10204	30037	225	6	61	29548	25	10100	100	10000	100	10000	500	4277313	0	30018	30037	30037	28272	6	28741	10100	200	10008	200	30024	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	1	1	1	717	16	29647	10000	100	30038	30038	30085	30038	30038
10204	30037	225	9	61	29548	25	10100	100	10000	100	10000	500	4277313	0	30018	30037	30037	28289	7	28757	10100	200	10008	202	30024	30037	30037	2	1	10201	100	99	100	100	10000	100	2	0	0	1	1	1	718	16	29646	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	103	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28272	7	28740	10100	200	10008	200	30024	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	1	1	1	718	16	29647	10000	100	30038	30038	30038	30038	30038
10204	30037	225	6	82	29548	25	10100	100	10000	100	10000	500	4277313	0	30018	30037	30037	28272	6	28741	10100	200	10008	200	30024	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	1	1	1	717	16	29646	10000	100	30038	30038	30038	30038	30038
10204	30037	225	12	61	29548	25	10100	100	10000	100	10000	500	4277313	0	30018	30037	30037	28272	6	28741	10100	200	10008	200	30024	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	3	1	1	1	717	16	29646	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	61	29548	25	10100	100	10000	100	10000	500	4277313	0	30018	30037	30037	28272	6	28740	10100	200	10008	200	32016	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	6	1	1	1	717	24	29646	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	61	29548	25	10100	100	10000	100	10000	500	4277313	0	30018	30037	30037	28272	6	28740	10100	200	10008	200	30024	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	1	1	1	718	16	29646	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)	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	225	42	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	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	27	726	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	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	21	726	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	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	9	536	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	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	251	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	1	0	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	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	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	18	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	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	536	29548	25	10010	10	10000	10	10000	50	4277313	30018	30037	30037	28287	3	28786	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	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	1	0	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	224	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	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038

Test 4: Latency 1->3

Code:

  smlsl v0.2d, v1.2s, v0.s[1]

Initialization

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

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

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

retire uop (01)	cycle (02)	03	19	1e	3f	4e	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	60	69	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d 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	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	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	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	1	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	21	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	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	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	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	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	224	0	0	61	29548	25	10100	121	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	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	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	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	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	9	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	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	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

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	09	18	1e	1f	3f	4e	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	60	69	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d tlb access (a0)	l1d tlb miss (a1)	ld unit uop (a6)	l1d cache writeback (a8)	ac	c3	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	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	0	0	0	640	2	16	2	2	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	0	5	0	30013	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	6	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	0	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	132	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	0	0	0	640	2	16	2	2	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	0	0	0	0	640	2	16	2	2	29630	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	0	0	0	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	226	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	0	0	0	640	2	16	2	2	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	0	0	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	89	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	0	0	0	640	2	16	2	2	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	0	0	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
  smlsl v0.2d, v8.2s, v9.s[1]
  movi v1.16b, 0
  smlsl v1.2d, v8.2s, v9.s[1]
  movi v2.16b, 0
  smlsl v2.2d, v8.2s, v9.s[1]
  movi v3.16b, 0
  smlsl v3.2d, v8.2s, v9.s[1]
  movi v4.16b, 0
  smlsl v4.2d, v8.2s, v9.s[1]
  movi v5.16b, 0
  smlsl v5.2d, v8.2s, v9.s[1]
  movi v6.16b, 0
  smlsl v6.2d, v8.2s, v9.s[1]
  movi v7.16b, 0
  smlsl v7.2d, v8.2s, v9.s[1]

Initialization

  movi v8.16b, 9
  movi v9.16b, 10

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2508

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

retire uop (01)	cycle (02)	03	mmu table walk data (08)	09	18	19	1e	1f	3f	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	60	69	6d	6e	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d tlb access (a0)	ld unit uop (a6)	l1d cache writeback (a8)	a9	ac	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
160204	20089	150	0	0	0	0	30	0	62	25	80100	100	80000	100	80000	500	640000	1	20045	20064	20064	3	22	80427	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	0	17	0	9	10111	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	0	0	0	0	62	25	80100	107	80313	109	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	18	0	6	10111	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	1	0	0	21	0	83	25	80100	100	80000	106	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	2	0	6	10111	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	0	0	21	0	85	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	6	10111	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	151	0	0	0	0	912	108	498	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	2	0	6	10111	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	0	0	21	0	85	25	80100	100	80000	116	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	2	0	6	10111	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	0	0	21	0	39	25	80100	100	80000	125	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	5	0	0	10111	1	48	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	0	0	15	0	83	25	80100	100	80000	100	80000	644	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	2	0	6	10111	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	151	0	0	0	0	162	0	85	25	80100	100	80000	100	80000	500	640000	0	20045	20064	20064	3	22	80207	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	0	2	0	3	10111	1	50	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	151	0	0	0	0	21	0	85	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	3	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	l2 tlb miss instruction (0a)	1e	3a	3f	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	5f	60	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	ld unit uop (a6)	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	20078	150	0	0	0	45	27	80012	12	80000	12	80000	62	640000	1	1	20032	20051	20051	3	22	80012	20	80000	20	240000	20051	20051	1	1	160021	10	9	10	10	160000	10	0	0	10029	3	1	1	8	25	2	1	1	6	10	20048	2	20	1	160000	10	20052	20052	20052	20052	20052
160024	20051	150	0	0	0	45	27	80012	12	80000	12	80000	62	640000	1	1	20032	20051	20051	3	22	80012	20	80000	20	240000	20051	20051	1	1	160021	10	9	10	10	160000	10	0	0	10029	3	1	1	10	25	2	1	1	6	10	20048	2	20	1	160000	10	20052	20052	20052	20052	20052
160024	20051	150	0	0	0	45	27	80012	12	80000	12	80000	62	640000	1	1	20032	20051	20051	3	22	80012	20	80000	20	240000	20051	20051	1	1	160021	10	9	10	10	160000	10	0	0	10033	6	1	1	10	25	2	1	1	10	6	20048	2	20	1	160000	10	20052	20052	20052	20052	20061
160024	20051	150	0	0	0	51	27	80012	12	80000	12	80000	62	640000	1	1	20032	20051	20051	3	22	80012	20	80000	20	240000	20051	20051	1	1	160021	10	9	10	10	160000	10	0	0	10029	3	1	1	10	25	2	1	1	10	6	20048	2	20	1	160000	10	20052	20052	20052	20052	20052
160024	20051	151	0	0	0	45	27	80012	12	80000	12	80000	62	640000	0	1	20032	20051	20051	3	22	80012	20	80000	20	240000	20051	20051	1	1	160021	10	9	10	10	160000	10	0	0	10033	3	1	1	10	25	2	1	1	10	10	20048	2	20	1	160000	10	20052	20061	20052	20052	20052
160024	20051	150	0	0	0	45	27	80012	12	80000	12	80000	62	640832	1	1	20032	20051	20051	3	22	80012	20	80000	20	240000	20060	20051	1	1	160021	10	9	10	10	160000	10	0	0	10033	3	1	1	6	25	2	1	1	6	10	20048	2	20	1	160000	10	20052	20052	20052	20052	20052
160024	20051	150	2	0	0	51	27	80012	12	80000	12	80000	62	640000	1	1	20032	20051	20051	3	22	80012	20	80000	20	240000	20051	20051	1	1	160021	10	9	10	10	160000	10	0	0	10033	3	1	1	6	25	2	1	1	6	10	20048	2	20	1	160000	10	20052	20052	20052	20052	20052
160024	20051	150	0	0	0	45	27	80012	12	80000	12	80000	62	640000	1	1	20032	20051	20051	3	22	80012	20	80000	20	240000	20051	20051	1	1	160021	10	9	10	10	160000	10	0	0	10029	3	1	1	6	25	2	1	1	6	10	20048	2	20	1	160000	10	20052	20052	20052	20052	20052
160024	20051	150	0	0	0	45	27	80012	12	80000	12	80000	62	640000	1	1	20032	20051	20051	3	22	80012	20	80000	20	240000	20051	20051	1	1	160021	10	9	10	10	160000	10	0	0	10029	3	1	1	10	25	2	1	1	6	10	20048	2	20	1	160000	10	20052	20052	20052	20052	20052
160024	20051	150	0	6	0	45	27	80012	12	80000	12	80000	62	640000	1	1	20041	20051	20051	3	22	80012	20	80000	20	240000	20051	20051	1	1	160021	10	9	10	10	160000	10	0	0	10033	3	1	1	6	25	2	1	1	6	10	20048	2	20	1	160000	10	20052	20061	20052	20061	20052

Test 6: throughput

Count: 12

Code:

  smlsl v0.2d, v12.2s, v13.s[1]
  smlsl v1.2d, v12.2s, v13.s[1]
  smlsl v2.2d, v12.2s, v13.s[1]
  smlsl v3.2d, v12.2s, v13.s[1]
  smlsl v4.2d, v12.2s, v13.s[1]
  smlsl v5.2d, v12.2s, v13.s[1]
  smlsl v6.2d, v12.2s, v13.s[1]
  smlsl v7.2d, v12.2s, v13.s[1]
  smlsl v8.2d, v12.2s, v13.s[1]
  smlsl v9.2d, v12.2s, v13.s[1]
  smlsl v10.2d, v12.2s, v13.s[1]
  smlsl v11.2d, v12.2s, v13.s[1]

Initialization

  movi v12.16b, 13
  movi v13.16b, 14

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

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

retire uop (01)	cycle (02)	03	37	3f	4e	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	60	69	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d cache writeback (a8)	branch cond mispred nonspec (c5)	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
120204	30346	225	0	106	0	25	120100	100	120000	100	120000	500	960000	0	30020	30039	30039	14973	3	14997	120100	200	120000	200	360000	30039	30039	1	1	120201	100	99	100	100	120000	100	0	0	7610	1	16	1	1	30036	120000	100	30040	30040	30040	30041	30040
120204	30040	225	1	41	0	25	120100	100	120000	100	120000	500	960000	0	30020	30039	30039	14973	3	14997	120100	200	120000	200	360000	30039	30039	1	1	120201	100	99	100	100	120000	100	0	0	7610	1	16	1	1	30037	120000	100	30040	30040	30040	30040	30040
120204	30039	225	0	41	0	25	120162	100	120000	100	120000	500	960000	0	30020	30039	30039	14973	3	14997	120100	200	120000	200	360000	30039	30039	1	1	120201	100	99	100	100	120000	100	0	0	7610	1	16	1	1	30919	120000	100	30040	30040	30040	30040	31775
120204	30039	225	0	62	0	25	120100	100	120000	100	120000	500	960000	0	30020	30039	30090	14973	3	14997	120100	200	120000	200	360000	30039	30040	1	1	120201	100	99	100	100	120000	100	0	0	7610	1	16	1	1	31733	120000	100	30093	31023	30040	30040	30040
120204	30039	225	0	125	0	25	120100	100	120000	100	120000	500	960000	0	30020	30039	30039	14973	3	14997	120100	200	120000	200	360000	30039	30039	1	1	120201	100	99	100	100	120000	100	0	0	7610	1	16	1	1	30036	120000	100	30040	30040	30040	30040	30041
120204	30039	225	0	129	0	25	120100	100	120000	100	120000	500	960000	0	30020	30039	30039	14973	3	14997	120100	200	120000	200	360000	30039	30039	1	1	120201	100	99	100	100	120000	100	0	0	7610	1	16	1	1	30039	120000	100	30040	30040	30040	30040	30040
120204	30039	225	0	41	0	25	120100	100	120000	100	120000	500	960000	0	30020	30039	30039	14973	3	14997	120100	200	120000	200	360000	30039	30039	1	1	120201	100	99	100	100	120000	100	0	0	7610	1	16	1	1	31750	120000	100	30040	30040	30040	30041	30042
120204	30039	225	0	64	0	25	120100	100	120081	100	120000	500	960000	0	30020	30039	30039	14973	3	14997	120100	200	120000	200	360000	30039	30039	1	1	120201	100	99	100	100	120000	100	0	0	7610	1	16	1	1	30919	120000	100	30040	30041	30040	30040	30040
120204	30039	225	1	106	0	25	120100	100	120000	100	120000	500	960000	0	30020	30039	30039	14973	3	14997	120100	200	120000	200	360000	30039	30039	1	1	120201	100	99	100	100	120000	100	0	0	7610	1	16	1	1	31750	120000	100	30040	30041	30040	30040	30040
120204	30039	225	0	41	0	25	120100	100	120000	100	120000	500	960000	0	30020	30039	30039	14973	3	14997	120100	200	120000	200	360000	30041	30039	1	1	120201	100	99	100	100	120000	100	0	0	7610	1	16	1	1	30039	120000	100	30040	30040	30040	30040	30040

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	mmu table walk instruction (07)	mmu table walk data (08)	l2 tlb miss instruction (0a)	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 access (a0)	l1d tlb miss (a1)	ld unit uop (a6)	st unit uop (a7)	l1d cache writeback (a8)	a9	ac	c2	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? int output thing (e9)	eb	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
120024	30050	225	0	0	0	0	0	0	0	0	0	2	45	0	25	120010	10	120000	10	120000	50	960000	1	30020	30039	30039	14996	3	15074	120010	20	120000	20	360000	30039	30039	1	1	120021	10	9	10	10	120000	10	0	0	0	0	0	0	0	0	7524	8	16	15	13	30036	0	0	120000	10	30040	30040	30040	30040	30040
120024	30039	225	0	0	0	0	0	3	0	0	0	2	45	0	25	120010	10	120000	10	120000	50	960000	0	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	0	0	0	0	0	7524	17	16	18	14	30036	0	0	120000	10	30040	30040	30040	30040	30040
120024	30039	225	0	0	0	0	0	0	0	0	0	2	45	0	25	120010	10	120000	10	120000	50	960000	0	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	0	0	0	0	0	7524	15	16	16	18	30036	0	0	120000	10	30040	30040	30040	30040	30040
120024	30039	225	0	0	0	0	0	0	0	0	0	2	45	0	25	120010	10	120000	10	120000	50	960000	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	0	0	0	0	0	7524	14	16	16	15	30036	0	0	120000	10	30040	30040	30040	30040	30040
120024	30039	225	0	0	0	0	0	0	0	0	0	2	45	0	25	120028	10	120000	10	120000	50	960000	0	30020	30196	31010	14996	3	15019	120010	20	120000	20	360000	30039	30039	1	1	120021	10	9	10	10	120000	10	0	0	0	0	0	0	0	0	7524	15	16	14	16	30036	0	0	120000	10	30040	30040	30040	30040	30040
120024	30039	225	0	0	0	0	0	0	0	0	0	2	45	0	25	120010	10	120000	10	120000	50	960000	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	0	0	0	0	0	7524	12	16	15	14	30078	0	0	120000	10	30040	30040	30040	30040	30040
120024	30039	225	0	0	0	0	0	0	0	0	0	2	45	0	25	120010	10	120000	10	120000	50	960000	0	30020	30039	30039	14996	3	15019	120534	20	120000	20	360000	30039	30039	1	1	120021	10	9	10	10	120000	10	0	0	0	0	0	0	0	0	7524	11	16	8	15	30036	0	0	120000	10	30040	30040	30040	30641	30040
120024	30039	225	0	0	0	0	0	0	0	0	0	2	45	0	25	120010	10	120000	10	120000	50	960000	0	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	0	0	0	0	0	7524	15	16	16	17	30036	0	0	120000	10	30040	30040	30040	30040	30040
120024	30039	225	0	0	0	0	0	0	0	0	0	2	45	0	25	120010	10	120000	10	120000	50	960000	0	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	0	0	0	156	0	7524	15	16	9	15	30036	0	0	120000	10	30040	30040	30040	30040	30040
120024	30041	225	0	0	0	0	0	0	0	0	0	2	45	0	25	120010	10	120000	10	120000	50	960000	0	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	0	0	0	0	0	7524	12	16	20	18	30036	0	0	120000	10	30040	30040	30040	30040	30040

SMLSL (by element, 2D)

Test 1: uops

1000 unrolls and 1 iteration

Test 2: Latency 1->1

100 unrolls and 100 iterations

1000 unrolls and 10 iterations

Test 3: Latency 1->2

100 unrolls and 100 iterations

1000 unrolls and 10 iterations

Test 4: Latency 1->3

100 unrolls and 100 iterations

1000 unrolls and 10 iterations

Test 5: throughput

100 unrolls and 100 iterations

1000 unrolls and 10 iterations

Test 6: throughput

100 unrolls and 100 iterations

1000 unrolls and 10 iterations