Firestorm: SQDMLSL2 (vector, 2D) measurements

Code:

  sqdmlsl2 v0.2d, v1.4s, v2.4s

Initialization

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

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 1.000

Issues: 1.000

Integer unit issues: 0.000

Load/store unit issues: 0.000

SIMD/FP unit issues: 1.000

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

retire uop (01)	cycle (02)	03	mmu table walk data (08)	l2 tlb miss instruction (0a)	18	19	1e	1f	3f	4e	51	schedule uop (52)	schedule simd uop (54)	dispatch simd uop (57)	ldst uops in schedulers (5b)	60	69	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map simd uop (7e)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst simd alu (9a)	l1d tlb miss (a1)	ld unit uop (a6)	st unit uop (a7)	l1d cache writeback (a8)	a9	ac	c2	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	f5	f6	f7	f8	fd
1004	3037	23	0	0	0	0	0	0	61	2548	25	1000	1000	1000	398313	1	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	0	0	0	0	0	73	2	16	2	2	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	0	0	0	0	61	2548	25	1000	1000	1000	398313	1	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	0	0	0	0	0	73	2	16	2	2	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	0	0	0	0	0	0	61	2548	25	1000	1000	1000	398313	1	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	0	0	0	0	0	73	2	16	2	2	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	0	0	0	0	61	2548	25	1000	1000	1000	398313	1	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	0	0	0	0	0	73	2	16	2	2	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	0	0	0	0	61	2548	25	1000	1000	1000	398313	1	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	0	0	0	0	0	73	2	16	2	2	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	0	0	0	0	61	2548	25	1000	1000	1000	398313	1	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	0	0	0	0	0	73	2	16	2	2	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	0	0	0	0	61	2548	25	1000	1000	1000	398313	1	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	0	0	0	0	0	73	2	16	2	2	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	0	0	0	0	61	2548	25	1000	1000	1000	398313	1	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	0	0	0	0	0	73	2	16	2	2	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	0	0	0	0	132	0	61	2548	25	1000	1000	1000	398313	1	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	0	0	0	0	0	73	2	16	2	2	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	0	0	0	0	0	0	61	2548	25	1000	1000	1000	398313	1	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	0	0	0	0	0	73	2	16	2	2	2630	1000	3038	3038	3038	3038	3038

Test 2: Latency 1->1

Code:

  sqdmlsl2 v0.2d, v1.4s, v2.4s

Initialization

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

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

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

retire uop (01)	cycle (02)	03	18	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	c2	branch cond mispred nonspec (c5)	branch mispred nonspec (cb)	cd	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	61	29548	25	10100	100	10000	100	10000	500	4277313	0	30018	30037	30037	28272	7	28740	10100	200	10008	200	30024	30037	30037	1	1	10201	100	99	100	100	10000	100	0	9	0	1	1	1	717	0	1	16	0	0	29646	0	10000	100	30038	30038	30038	30038	30038
10204	30037	224	0	0	0	61	29548	25	10110	102	10000	100	10000	500	4277313	0	30018	30037	30037	28272	7	28740	10100	200	10008	200	30024	30037	30037	1	1	10201	100	99	100	100	10000	100	0	6	0	1	1	1	718	0	0	16	0	0	29646	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	506	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	3	0	1	1	1	717	0	0	16	0	0	29646	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28272	6	28741	10100	200	10008	200	30024	30037	30037	1	1	10201	100	99	100	100	10000	100	0	186	0	1	1	1	717	0	0	16	0	0	29647	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	726	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	27	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	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	60	0	0	0	0	710	1	2	16	2	2	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	226	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	2	16	2	2	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	87	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	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	111	0	0	0	0	710	1	2	16	2	2	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	224	0	0	0	82	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	710	1	3	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	mmu table walk data (08)	09	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
10024	30037	225	0	0	0	156	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	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	640	2	17	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	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	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	0	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	1	0	0	103	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	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	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	224	0	0	0	103	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	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	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	0	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038

Test 3: Latency 1->2

Code:

  sqdmlsl2 v0.2d, v0.4s, v1.4s

Initialization

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

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

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

retire uop (01)	cycle (02)	03	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)	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	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	710	1	16	1	1	29634	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	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	91	29548	25	10100	100	10000	100	10000	500	4277313	0	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	224	0	810	29548	25	10100	100	10000	100	10000	500	4277313	0	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	224	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	710	1	16	1	1	29634	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	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	224	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	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	89	29548	25	10100	100	10000	100	10000	500	4277313	0	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	710	1	16	1	1	29634	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	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	2	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)	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)	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
10024	30037	225	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	1	0	0	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	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	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	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	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	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	15	0	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	224	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	1	0	0	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	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	1	0	0	640	2	16	2	2	29668	0	10000	10	30038	30038	30038	30038	30088
10024	30037	225	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	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30226
10024	30037	226	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	54	12	0	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	224	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	2	0	0	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	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	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038

Test 4: Latency 1->3

Code:

  sqdmlsl2 v0.2d, v1.4s, v0.4s

Initialization

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

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

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

retire uop (01)	cycle (02)	03	l2 tlb miss data (0b)	19	1e	1f	3f	4e	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	60	69	6d	6e	map stall dispatch (70)	simd prf full (72)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d cache writeback (a8)	ac	branch 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
10204	30037	225	0	0	0	0	147	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	0	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	567	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	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	491	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	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	497	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	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	0	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	126	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	0	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	522	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	0	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	511	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	0	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	3	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	527	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	0	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	410	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	0	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	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)	simd prf full (72)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d cache writeback (a8)	ac	branch mispred nonspec (cb)	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? 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	0	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	640	4	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	0	3	28767	10010	20	10000	20	30000	30037	30084	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	15	0	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	30037	30037	28287	0	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	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	0	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	103	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	30037	30037	28287	0	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	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	0	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	0	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	0	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	0	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	0	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
  sqdmlsl2 v0.2d, v8.4s, v9.4s
  movi v1.16b, 0
  sqdmlsl2 v1.2d, v8.4s, v9.4s
  movi v2.16b, 0
  sqdmlsl2 v2.2d, v8.4s, v9.4s
  movi v3.16b, 0
  sqdmlsl2 v3.2d, v8.4s, v9.4s
  movi v4.16b, 0
  sqdmlsl2 v4.2d, v8.4s, v9.4s
  movi v5.16b, 0
  sqdmlsl2 v5.2d, v8.4s, v9.4s
  movi v6.16b, 0
  sqdmlsl2 v6.2d, v8.4s, v9.4s
  movi v7.16b, 0
  sqdmlsl2 v7.2d, v8.4s, v9.4s

Initialization

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

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

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

retire uop (01)	cycle (02)	03	19	1e	3f	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	60	69	6d	6e	rob full (74)	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
160204	20065	150	0	0	209	25	80100	100	80000	100	80000	500	640000	0	20045	20064	20064	0	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	0	10112	2	16	2	2	20061	0	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	60	25	80100	100	80000	100	80000	500	640000	0	20045	20064	20064	0	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	0	10112	2	16	2	2	20061	0	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	39	25	80100	100	80000	100	80000	500	640000	1	20045	20064	20064	0	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	1	0	10112	2	16	2	4	20061	0	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	39	25	80100	100	80000	100	80000	500	640000	0	20045	20064	20064	0	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	0	10112	2	16	2	2	20061	0	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	60	25	80100	100	80000	100	80000	500	640000	0	20045	20064	20064	0	3	22	80246	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	0	10112	2	16	2	2	20061	0	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	39	25	80100	100	80000	100	80000	500	640000	0	20045	20064	20064	5	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	3	10159	2	16	2	2	20061	0	160000	100	20065	20065	20065	20065	20065
160204	20064	153	0	0	165	25	80100	100	80000	100	80000	500	640000	0	20045	20064	20064	0	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	0	10112	3	50	2	2	20061	0	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	144	25	80100	100	80000	100	80000	500	640000	0	20045	20064	20064	0	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	0	10112	2	16	2	2	20061	0	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	551	25	80100	100	80000	100	80000	500	640000	0	20045	20064	20064	0	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	0	10112	2	16	2	2	20061	0	160000	100	20065	20065	20065	20065	20065
160204	20064	151	0	0	81	25	80100	100	80000	100	80000	500	640000	0	20045	20064	20064	0	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	0	10112	2	16	4	3	20061	0	160000	100	20065	20065	20065	20065	20065

1000 unrolls and 10 iterations

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

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

retire uop (01)	cycle (02)	03	18	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	l1d cache writeback (a8)	ac	cf	d0	d2	l1i cache miss demand (d3)	d5	map dispatch bubble (d6)	d9	da	db	dd	fetch restart (de)	e0	? int output thing (e9)	ea	ec	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
160024	20097	150	0	3833	27	80012	12	80000	12	80000	62	640000	1	0	20032	20051	20051	3	22	80012	20	80000	20	240000	20051	20051	1	1	160021	10	9	10	10	160000	10	1	0	10030	3	1	1	9	25	2	1	1	8	20	20061	2	20	1	160000	10	20061	20061	20052	20052	20052
160024	20051	150	0	704	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	10044	3	1	1	6	25	2	1	1	20	20	20061	2	20	1	160000	10	20052	20052	20052	20052	20052
160024	20060	150	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	10043	3	1	1	8	25	2	1	1	9	16	20061	2	20	1	160000	10	20052	20052	20052	20052	20052
160024	20051	150	0	108	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	5	0	10043	3	1	1	19	25	4	2	1	8	19	20083	2	40	1	160000	10	20052	20052	20052	20052	20052
160024	20051	150	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	10043	3	1	1	16	25	2	1	1	19	6	20083	2	20	1	160000	10	20052	20052	20052	20052	20052
160024	20051	150	0	129	27	80012	12	80000	12	80000	62	640000	1	0	20032	20051	20051	3	22	80012	20	80000	20	240000	20051	20051	1	1	160021	10	9	10	10	160000	10	0	0	10043	3	1	1	19	25	2	1	1	19	19	20083	2	20	1	160000	10	20052	20052	20052	20052	20052
160024	20051	150	0	66	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	10032	3	1	1	8	25	2	1	1	8	19	20083	2	20	1	160000	10	20052	20052	20052	20052	20052
160024	20051	150	0	129	27	80012	12	80000	12	80000	62	640000	1	0	20032	20051	20051	3	22	80012	20	80000	20	240000	20051	20051	1	1	160021	10	9	10	10	160000	10	0	0	10032	3	1	1	8	25	2	1	1	19	8	20061	2	20	1	160000	10	20052	20052	20052	20052	20052
160024	20051	150	0	66	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	10043	3	1	1	8	25	2	1	1	8	19	20083	2	20	1	160000	10	20052	20052	20052	20052	20052
160024	20051	150	0	175	27	80012	12	80000	12	80000	62	640000	1	0	20032	20051	20051	3	22	80012	20	80000	20	240000	20051	20051	1	1	160021	10	9	10	10	160000	10	0	0	10030	3	1	1	8	25	2	1	1	19	8	20083	2	20	1	160000	10	20052	20052	20052	20052	20052

Test 6: throughput

Count: 16

Code:

  sqdmlsl2 v0.2d, v16.4s, v17.4s
  sqdmlsl2 v1.2d, v16.4s, v17.4s
  sqdmlsl2 v2.2d, v16.4s, v17.4s
  sqdmlsl2 v3.2d, v16.4s, v17.4s
  sqdmlsl2 v4.2d, v16.4s, v17.4s
  sqdmlsl2 v5.2d, v16.4s, v17.4s
  sqdmlsl2 v6.2d, v16.4s, v17.4s
  sqdmlsl2 v7.2d, v16.4s, v17.4s
  sqdmlsl2 v8.2d, v16.4s, v17.4s
  sqdmlsl2 v9.2d, v16.4s, v17.4s
  sqdmlsl2 v10.2d, v16.4s, v17.4s
  sqdmlsl2 v11.2d, v16.4s, v17.4s
  sqdmlsl2 v12.2d, v16.4s, v17.4s
  sqdmlsl2 v13.2d, v16.4s, v17.4s
  sqdmlsl2 v14.2d, v16.4s, v17.4s
  sqdmlsl2 v15.2d, v16.4s, v17.4s

Initialization

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

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

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	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	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	ld unit uop (a6)	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	? int output thing (e9)	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
160204	40068	300	0	0	0	0	0	0	0	0	41	0	25	160101	100	160001	100	160000	500	1280000	0	40030	0	40040	40039	19973	0	3	19997	160100	200	160000	200	480000	40040	40039	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	0	0	10110	2	297	3	2	40320	21	160000	100	41558	40966	40040	40049	40049
160204	40048	313	1	1	14	13	2772	1980	304	0	2948	8	312	161876	123	161719	128	162533	613	1997770	0	41046	0	41023	40893	20237	0	75	20559	162183	208	162144	204	486003	41190	41294	23	1	160201	100	99	100	100	160000	100	3	0	8035	0	0	0	0	10439	2	195	1	1	40778	22	160000	100	41225	41470	41221	41223	40967
160204	41572	318	1	0	16	13	1863	792	503	1	4277	35	466	162482	120	161809	124	161963	616	1739904	0	40655	0	40576	40712	20142	0	76	20360	160821	200	160000	200	480000	40048	40039	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	2	1	10118	0	16	0	0	40037	0	160000	100	40049	40050	40040	40040	40040
160204	40048	300	0	0	0	0	0	0	0	0	30	0	25	160108	100	160008	100	160020	500	1280132	1	40020	0	40039	40039	19977	0	6	19990	160120	200	160032	200	480096	40039	40048	1	1	160201	100	99	100	100	160000	100	0	0	0	0	1	1	1	10118	0	16	0	0	40036	0	160000	100	40040	40040	40040	40040	40040
160204	40039	300	0	0	0	0	0	0	0	0	30	0	25	160108	100	160008	100	160020	500	1280132	0	40020	0	40039	40039	19977	0	6	19990	160120	200	160032	200	480096	40039	40039	1	1	160201	100	99	100	100	160000	100	0	1	0	0	1	1	1	10118	0	16	1	1	40036	0	160000	100	40040	40049	40040	40040	40040
160204	40039	300	0	0	0	0	0	0	17	0	50	0	25	160117	100	160000	100	160000	500	1280000	0	40020	0	40048	40039	19973	0	3	19997	160100	200	160000	200	480000	40048	40048	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	0	0	10110	1	16	1	1	40036	0	160000	100	40040	40040	40049	40040	40040
160204	40039	300	0	0	0	0	0	0	17	0	41	0	25	160117	100	160000	100	160000	500	1280000	0	40020	0	40048	40039	19973	0	3	19997	160100	200	160000	200	480000	40048	40048	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	0	0	10110	1	16	1	1	40036	0	160000	100	40040	40040	40049	40040	40049
160204	40039	300	0	0	0	0	0	0	0	0	50	0	25	160100	100	160000	100	160000	500	2398999	1	40030	0	40039	40039	19973	0	3	19997	160100	200	160000	200	480000	40048	40039	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	0	0	10110	1	16	1	1	40045	0	160000	100	40040	40040	40049	40040	40049
160204	40039	300	0	0	0	0	0	0	0	0	50	0	25	160100	100	160000	100	160000	500	2398999	0	40029	0	40048	40048	19973	0	3	20006	160100	202	160000	200	480000	40048	40039	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	0	0	10110	1	16	1	1	40036	0	160000	100	40040	40050	40041	40040	40049
160204	40049	300	0	0	0	0	0	0	0	0	706	0	25	160100	100	160017	100	160000	500	1280000	1	40020	0	40039	40039	19973	0	3	19997	160100	200	160000	200	480000	40039	40048	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	0	0	10110	1	16	1	1	40036	0	160000	100	40049	40049	40049	40049	40040

1000 unrolls and 10 iterations

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

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

retire uop (01)	cycle (02)	03	18	19	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	61	69	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	st unit uop (a7)	l1d cache writeback (a8)	ac	c2	cf	d0	d2	l1i cache miss demand (d3)	d5	map dispatch bubble (d6)	d9	da	db	dd	fetch restart (de)	e0	ea	eb	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
160024	40049	300	0	0	0	0	124	25	160010	10	160000	10	160000	50	1280000	1	1	0	40029	40048	40039	19996	3	20028	160010	20	160000	20	480000	40048	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10022	3	2	2	20	16	4	2	2	13	20	40045	30	5	160000	10	40049	40040	40050	40040	40049
160024	40048	300	0	0	0	17	55	25	160027	10	160017	10	160000	50	1280000	0	1	5	40020	40039	40039	19996	3	20019	160010	20	160000	20	480000	40039	40048	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10022	8	2	1	13	16	2	1	1	14	28	40045	15	5	160000	10	40040	40049	40040	40040	40040
160024	40048	300	0	0	0	17	46	25	160027	10	160017	10	160000	50	1280000	1	1	5	40029	40048	40039	19996	3	20028	160010	20	160000	20	480000	40048	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10022	11	2	1	12	16	2	1	2	10	32	40036	30	5	160000	10	40040	40049	40040	40040	40049
160024	40039	300	0	0	0	17	720	25	160010	10	160000	10	160000	50	2398999	1	1	5	40029	40039	40039	19996	3	20019	160010	20	160000	20	480000	40048	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10022	8	2	1	13	16	2	1	1	11	24	40045	15	5	160000	10	40049	40040	40049	40040	40049
160024	40039	300	0	0	0	17	55	25	160027	10	160017	10	160000	50	1280000	1	1	5	40020	40039	40048	19996	3	20028	160010	20	160000	20	480000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10024	8	2	1	19	16	2	1	1	11	24	40045	15	5	160000	10	40040	40049	40040	40109	40040
160024	40039	299	0	0	0	17	55	25	160027	10	160017	10	160000	50	1280000	1	1	5	40029	40048	40039	19996	3	20019	160010	20	160000	20	480000	40048	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10022	8	2	1	19	16	2	1	1	14	28	40036	30	5	160000	10	40040	40049	40040	40040	40049
160024	40049	300	0	0	0	17	46	25	160027	10	160000	10	160000	50	1280000	1	1	5	40029	40039	40048	19996	3	20028	160010	20	160000	20	480000	40048	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10022	8	2	1	14	16	2	1	1	19	23	40045	15	5	160000	10	40049	40040	40040	40040	40040
160024	40039	300	0	0	0	0	46	25	160010	10	160000	10	160000	50	2398999	1	1	5	40029	40048	40039	19996	3	20019	160010	20	160000	20	480000	40048	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10022	8	3	1	19	16	4	1	2	18	22	40036	45	5	160000	10	40049	40040	40049	40040	40040
160024	40039	300	0	0	0	0	88	25	160027	10	160017	10	160000	50	1280000	0	1	5	40029	40048	40039	19996	3	20028	160010	20	160000	20	480000	40039	40048	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10022	8	2	1	13	16	2	1	1	13	23	40036	15	5	160000	10	40049	40040	40049	40040	40049
160024	40039	300	0	0	0	0	52	25	160010	10	160000	10	160000	50	2398999	1	1	5	40079	40039	40048	19996	3	20019	160010	20	160000	20	480000	40048	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10022	8	3	1	20	16	4	1	1	20	26	40036	15	5	160000	10	40049	40040	40049	40040	40049

SQDMLSL2 (vector, 2D)

Test 1: uops

1000 unrolls and 1 iteration

Test 2: Latency 1->1

100 unrolls and 100 iterations

1000 unrolls and 10 iterations

Test 3: Latency 1->2

100 unrolls and 100 iterations

1000 unrolls and 10 iterations

Test 4: Latency 1->3

100 unrolls and 100 iterations

1000 unrolls and 10 iterations

Test 5: throughput

100 unrolls and 100 iterations

1000 unrolls and 10 iterations

Test 6: throughput

100 unrolls and 100 iterations

1000 unrolls and 10 iterations