Firestorm: SMLAL (by element, 2D) measurements

Code:

  smlal 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)	60	69	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map simd uop (7e)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst simd alu (9a)	l1d cache writeback (a8)	ac	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	f5	f6	f7	f8	fd
1004	3037	23	15	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	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	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	82	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	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	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	24	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	0	82	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	12	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	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	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	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	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	61	2548	25	1000	1000	1000	398313	0	3018	3037	3037	2415	8	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:

  smlal 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	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)	69	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d tlb access (a0)	l1d tlb miss (a1)	l1d cache writeback (a8)	ac	c2	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
10204	30037	225	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	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	0	0	1	1	1	717	0	16	0	0	29646	10000	100	30038	30038	30038	30038	30038
10204	30037	224	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	30018	30037	30037	28272	6	28741	10100	200	10008	200	30024	30037	30037	1	1	10201	100	99	100	100	10000	100	2	4	0	0	0	1	1	1	717	0	16	0	0	29646	10000	100	30038	30038	30038	30038	30038
10204	30037	225	4	0	0	147	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	0	0	0	0	710	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	471	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	1	0	0	0	0	0	710	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	147	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	0	0	0	0	710	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	707	29548	65	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	0	0	0	0	710	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	1022	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	0	0	0	0	710	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	417	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	0	0	0	0	710	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	223	29548	25	10100	100	10000	100	10000	500	4277313	30059	30037	30037	28265	3	28745	10100	200	10168	204	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	0	0	710	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	631	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	0	0	0	0	710	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 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)	60	69	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d tlb access (a0)	ld unit uop (a6)	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)	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10024	30037	225	0	0	0	0	0	0	0	0	536	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	0	0	0	0	640	6	16	3	3	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	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	0	0	24	0	640	3	16	3	3	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	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	0	0	0	0	640	3	16	3	3	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	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	0	0	0	0	640	3	16	3	3	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	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	0	0	0	0	640	3	16	3	3	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	6	3	411	528	0	3289	29485	140	10059	11	10048	13	10991	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	2	0	1	4	19469	2	788	5	49	4	4	29882	0	10000	10	30405	30418	30228	30322	30369
10024	30368	226	1	1	1	5	5	936	528	2	4292	29485	143	10066	14	10056	11	11043	72	4282741	0	30306	30413	30452	28339	37	28918	10457	22	11311	26	31491	30416	30451	9	1	10021	10	9	10	10	10000	10	2	0	0	1	4	22490	2	809	4	80	4	5	29918	1	10000	10	30463	30465	30465	30466	30466
10024	30416	227	0	0	0	0	0	0	0	0	145	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	2	2	1	0	24850	0	829	3	24	7	4	29920	1	10000	10	30457	30452	30468	30509	30467
10024	30462	228	0	1	0	4	9	1065	792	0	61	29548	25	10010	10	10000	10	10000	50	4277313	0	30018	30037	30037	28287	3	28767	10010	20	10000	20	33435	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	3	0	0	0	640	3	16	3	3	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	0	9	0	0	1976	29536	82	10038	12	10032	12	10596	50	4282741	0	30162	30226	30224	28303	15	28824	10457	20	10486	20	30000	30131	30083	3	1	10021	10	9	10	10	10000	10	0	0	0	0	2	0	0	640	6	32	3	3	29749	0	10000	10	30086	30084	30086	30132	30229

Test 3: Latency 1->2

Code:

  smlal 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	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	ld unit uop (a6)	l1d cache writeback (a8)	a9	ac	c2	cd	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? int output thing (e9)	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10204	30037	225	0	0	0	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	0	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	710	2	16	1	1	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	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	0	0	710	1	16	1	1	29634	0	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	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	0	0	710	1	16	1	1	29634	0	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	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	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	233	0	0	0	0	0	0	0	683	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	0	0	710	1	16	1	1	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	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	0	0	710	1	16	1	1	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	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	0	0	710	1	16	1	1	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	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	0	0	710	1	16	1	1	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	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	0	0	710	1	16	1	1	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	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	0	0	710	1	32	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)	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 tlb access (a0)	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
10024	30037	225	0	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	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	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	0	0	640	2	16	3	2	29630	10000	10	30038	30038	30038	30038	30083
10024	30037	224	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	0	30037	30037	28287	8	28786	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	640	2	16	3	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	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	0	0	640	2	17	3	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	191	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	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	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	0	0	640	2	16	2	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	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	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	0	30037	30085	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	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	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	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	0	0	640	2	16	3	2	29630	10000	10	30038	30038	30038	30038	30038

Test 4: Latency 1->3

Code:

  smlal 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	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 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
10204	30037	225	0	264	61	29548	25	10100	100	10000	100	10000	500	4277313	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30085	2	1	10201	100	99	100	100	10000	100	0	0	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	243	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	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	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	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	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	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	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	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	258	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	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	45	0	84	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	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	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	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	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	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	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	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 data (08)	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 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	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	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	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	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	543	0	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	1	0	0	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	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	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	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	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	468	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	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	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	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	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	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	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	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	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	2	2	29630	0	10000	10	30038	30038	30038	30038	30038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  smlal v0.2d, v8.2s, v9.s[1]
  movi v1.16b, 0
  smlal v1.2d, v8.2s, v9.s[1]
  movi v2.16b, 0
  smlal v2.2d, v8.2s, v9.s[1]
  movi v3.16b, 0
  smlal v3.2d, v8.2s, v9.s[1]
  movi v4.16b, 0
  smlal v4.2d, v8.2s, v9.s[1]
  movi v5.16b, 0
  smlal v5.2d, v8.2s, v9.s[1]
  movi v6.16b, 0
  smlal v6.2d, v8.2s, v9.s[1]
  movi v7.16b, 0
  smlal 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	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 cache writeback (a8)	a9	ac	branch cond mispred nonspec (c5)	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	20078	150	704	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	1	0	6	0	0	10111	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	151	39	25	80100	100	80000	100	80000	500	640000	0	20045	20064	20064	3	22	80100	200	80136	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	1	0	0	1	0	10111	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20307
160204	20064	150	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	1	0	0	0	0	10111	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	150	39	25	80100	100	80000	100	80000	500	640000	0	20045	20064	20064	3	22	80100	200	80000	200	240000	20064	20064	2	1	160201	100	99	100	100	160000	100	0	0	0	0	0	10111	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	150	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	10111	1	16	1	1	20061	160000	100	20224	20065	20065	20065	20065
160204	20064	150	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	10111	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	150	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	1	0	0	0	0	10111	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	150	39	25	80100	100	80000	102	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	10111	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	150	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	10111	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	150	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	1	0	0	0	0	10111	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2506

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

retire uop (01)	cycle (02)	03	l1i tlb fill (04)	mmu table walk instruction (07)	l2 tlb miss instruction (0a)	l2 tlb miss data (0b)	19	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	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)	a9	ac	c2	cf	d0	d2	l1i cache miss demand (d3)	l1i tlb miss demand (d4)	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	156	0	0	1	0	0	12	0	0	168	27	80012	12	80000	12	80000	62	640000	0	1	0	20045	20062	20051	3	22	80012	20	80000	20	240000	20051	20051	1	1	160021	10	9	10	10	160000	10	1	0	0	0	10042	8	3	1	0	32	25	2	1	2	21	26	20048	2	20	1	160000	10	20063	20052	20052	20052	20052
160024	20051	155	0	0	3	0	0	18	0	1	154	29	80012	12	80000	12	80000	62	640000	0	1	5	20043	20062	20062	3	22	80012	20	80000	20	240000	20062	20063	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10055	11	6	2	0	30	36	3	2	2	24	29	20059	2	41	2	160000	10	20063	20063	20063	20052	20063
160024	20062	156	0	1	2	0	0	0	0	0	3533	29	80012	12	80000	12	80000	62	640000	1	1	5	20043	20062	20062	3	22	80012	20	80000	20	240000	20062	20062	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10054	11	6	2	0	30	36	3	2	2	16	31	20059	2	41	2	160000	10	20063	20063	20063	20063	20063
160024	20062	155	0	2	2	0	0	0	0	0	69	29	80012	12	80000	12	80000	62	640000	1	1	5	20043	20062	20062	3	22	80012	20	80000	20	240000	20062	20051	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10040	8	5	1	0	22	25	2	1	1	28	17	20048	2	20	1	160000	10	20052	20052	20052	20052	20052
160024	20051	153	0	2	1	0	0	0	0	0	57	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	0	0	10054	11	6	1	0	30	36	2	2	2	17	29	20048	2	20	1	160000	10	20063	20052	20063	20052	20052
160024	20051	153	0	2	3	0	0	0	0	0	63	29	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	0	0	10045	8	5	1	0	22	25	2	1	1	29	22	20048	2	20	1	160000	10	20052	20063	20052	20052	20052
160024	20051	153	0	1	2	0	0	0	0	0	57	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	0	0	10052	8	5	1	0	30	25	2	1	1	29	30	20048	2	20	1	160000	10	20052	20063	20052	20052	20052
160024	21453	163	0	0	0	0	0	0	0	0	45	25	80012	12	80000	12	80000	62	640000	1	1	0	20027	20046	20046	3	22	80012	20	80000	20	240000	20046	20046	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10052	3	1	1	0	29	20	2	1	1	23	29	20043	2	15	0	160000	10	20047	20047	20047	20047	20047
160024	20046	150	0	2	0	0	0	0	0	0	57	25	80012	12	80000	12	80000	62	640000	1	1	0	20027	20046	20046	3	22	80012	20	80000	20	240000	20291	20046	1	1	160021	10	9	10	10	160000	10	0	0	3	0	10054	3	1	1	0	29	20	2	1	1	17	29	20043	2	15	0	160000	10	20047	20126	20047	20047	20049
160024	20135	150	0	2	2	0	0	0	0	0	57	25	80012	12	80000	12	80000	62	640000	1	1	0	20027	20046	20046	3	22	80012	20	80000	20	240000	20046	20046	1	1	160021	10	9	10	10	160000	10	1	0	0	2	10052	3	1	1	0	29	20	2	1	1	22	29	20110	3	15	0	160000	10	20047	20047	20047	20047	20047

Test 6: throughput

Count: 12

Code:

  smlal v0.2d, v12.2s, v13.s[1]
  smlal v1.2d, v12.2s, v13.s[1]
  smlal v2.2d, v12.2s, v13.s[1]
  smlal v3.2d, v12.2s, v13.s[1]
  smlal v4.2d, v12.2s, v13.s[1]
  smlal v5.2d, v12.2s, v13.s[1]
  smlal v6.2d, v12.2s, v13.s[1]
  smlal v7.2d, v12.2s, v13.s[1]
  smlal v8.2d, v12.2s, v13.s[1]
  smlal v9.2d, v12.2s, v13.s[1]
  smlal v10.2d, v12.2s, v13.s[1]
  smlal 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	l2 tlb miss data (0b)	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	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
120204	31429	234	0	0	0	0	1	125	3489	25	120100	100	120053	100	120000	500	990000	1	30020	30943	30039	14973	3	14997	120100	200	120000	200	360000	30039	30039	1	1	120201	100	99	100	100	120000	100	0	7610	1	16	1	1	30919	0	120000	100	30040	30040	30944	30040	30923
120204	30039	225	0	0	0	1	1	169	0	25	120100	100	120053	100	120000	500	960000	0	30020	30042	30039	15850	3	15000	120100	200	120000	200	360000	30922	30039	1	1	120201	100	99	100	100	120000	100	0	7610	1	16	1	1	30036	0	120000	100	30040	30040	30923	30040	30040
120204	30943	225	0	0	0	0	1	64	0	25	120101	100	120000	100	120000	500	990000	0	30020	30042	30039	15850	3	15901	120100	200	120000	200	360000	30042	30039	1	1	120201	100	99	100	100	120000	100	0	7610	1	16	1	1	30038	0	120000	100	30923	30040	30040	30043	30040
120204	30042	225	0	0	0	1	1	322	0	25	120100	100	120000	100	120000	500	960000	0	30023	30039	30039	14973	20	14997	120100	200	120000	200	360000	30042	30039	1	1	120201	100	99	100	100	120000	100	0	7610	1	16	1	1	30036	0	120000	100	30040	30043	30040	30040	30040
120204	30039	225	0	0	0	0	1	147	0	47	120100	100	120000	100	120000	500	960000	0	30020	30039	30039	14973	3	14997	120100	200	120000	200	360000	30039	30922	1	1	120201	100	99	100	100	120000	100	0	7610	1	16	1	1	30039	0	120000	100	30040	30040	30944	30040	30041
120204	30039	225	0	0	0	0	1	64	0	25	120100	100	120000	100	120000	500	960000	0	30020	30039	30042	14973	25	16708	120100	200	120000	200	360000	30039	30042	1	1	120201	100	99	100	100	120000	100	0	7610	1	16	1	1	30036	0	120000	100	30040	30040	30944	30040	30043
120204	30039	224	0	0	0	0	1	64	0	25	120153	100	120000	100	120000	500	4283400	0	30020	30943	30039	15850	3	15000	120100	200	120000	200	360000	30042	30039	1	1	120201	100	99	100	100	120000	100	0	7610	1	16	1	1	30036	0	120000	100	30043	30040	30040	30944	30040
120204	31750	237	0	0	0	1	1	62	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	7610	1	16	1	1	30036	0	120000	100	30040	30040	30043	30040	30040
120204	30039	225	0	0	0	0	1	64	0	25	120101	100	120000	100	120000	500	990000	0	30020	30039	30042	14973	3	14997	120100	200	120000	200	360000	30039	30039	1	1	120201	100	99	100	100	120000	100	0	7610	1	16	1	1	30036	5	120000	100	30040	30944	30040	30040	30040
120204	30039	232	0	0	0	0	1	164	0	25	120153	100	120000	100	120000	500	990000	0	30020	30943	30039	14973	3	15000	120100	200	120000	200	360000	30943	30039	1	1	120201	100	99	100	100	120000	100	0	7610	1	16	1	1	30919	0	120000	100	30040	30043	31750	30040	30923

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 data (08)	1e	37	3a	3f	4e	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	5f	60	61	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)	a9	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	30040	225	0	51	18	16	216	0	25	120010	10	120000	10	120000	50	960000	1	1	5	30020	0	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	8	3	1	15	16	2	1	1	20	20	30036	0	20	6	120000	10	30040	30040	30040	30040	30040
120024	30039	225	0	0	0	8	176	0	25	120010	10	120000	10	120000	50	960000	1	1	5	30020	0	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	8	3	1	20	16	2	1	1	21	20	30036	0	20	6	120000	10	30040	30040	30040	30040	30040
120024	30039	225	0	0	0	7	67	0	25	120010	10	120000	10	120000	50	960000	1	1	5	30020	0	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	8	3	1	14	16	2	1	1	19	13	30036	2	20	6	120000	10	30040	30040	30040	30040	30040
120024	30039	225	0	0	20	7	46	0	25	120010	10	120000	10	120000	50	960000	1	1	5	30020	0	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	8	3	1	19	16	2	1	1	20	20	30036	0	20	6	120000	10	30040	30040	30040	30040	30040
120024	30039	225	0	0	0	7	134	0	25	120010	10	120000	10	120000	50	960000	1	1	5	30020	0	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	8	3	1	18	16	2	1	1	18	19	30036	0	20	6	120000	10	30040	30040	30040	30040	30040
120024	30039	225	0	0	0	7	69	0	25	120010	10	120000	10	120000	50	960000	1	1	5	30020	0	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	8	3	1	15	16	2	1	1	18	19	30036	0	20	6	120000	10	30040	30040	30040	30040	30040
120024	30039	225	0	0	0	8	363	0	25	120010	10	120000	10	120000	50	960000	1	1	5	30020	0	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	8	3	1	18	16	2	1	1	19	18	30036	0	20	6	120000	10	30040	30040	30040	30040	30040
120024	30039	225	0	0	0	6	69	0	25	120010	10	120000	10	120000	50	960000	1	1	5	30020	0	30039	30039	14996	3	15019	120010	20	120000	20	360000	30922	30039	1	1	120021	10	9	10	10	120000	10	0	0	0	7522	8	3	1	20	16	2	1	1	19	19	30036	3	20	6	120000	10	30040	30040	30040	30040	30040
120024	30039	225	0	0	0	8	155	0	25	120010	10	120000	10	120000	50	960000	1	1	5	30020	0	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	8	3	1	19	16	2	1	1	19	19	30036	0	20	6	120000	10	30040	30040	30040	30040	30040
120024	30039	225	0	0	0	6	199	0	25	120010	10	120000	10	120000	50	960000	1	1	5	30020	0	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	8	3	1	18	16	2	1	1	18	20	30036	0	20	6	120000	10	30040	30040	30040	30040	30040

SMLAL (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