Firestorm: SQRDMLAH (scalar, H) measurements

Code:

  sqrdmlah h0, h1, h2

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	18	1e	1f	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)	ld unit uop (a6)	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	0	0	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	0	73	2	16	1	2	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	0	0	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	3	73	1	16	1	2	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	0	0	0	170	2548	25	1000	1000	1000	398313	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	0	0	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	6	73	1	16	2	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	174	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	6	73	2	16	2	2	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	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	0	73	2	16	1	2	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	0	129	0	251	2548	25	1000	1000	1000	398313	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	0	73	1	16	2	2	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	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	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	0	0	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	0	73	2	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	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	0	73	1	16	2	2	2630	1000	3038	3038	3038	3038	3038

Test 2: Latency 1->1

Code:

  sqrdmlah h0, h1, h2

Initialization

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

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

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

retire uop (01)	cycle (02)	03	mmu table walk data (08)	09	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 cache writeback (a8)	ac	c2	cf	d0	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10204	30180	232	0	0	6	3	336	0	0	61	29548	25	10100	106	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	710	1	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	0	0	103	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	1	0	0	710	1	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	0	0	124	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	710	1	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	3	0	710	1	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	15	0	0	691	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	1	0	0	710	1	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	710	1	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	710	1	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	156	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	710	1	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	710	1	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	30	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28272	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	710	1	2	16	2	2	29634	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	ld unit uop (a6)	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	567	61	29548	25	10010	10	10000	10	10000	50	4277313	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	640	3	16	3	3	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	378	61	29548	25	10010	10	10000	10	10000	50	4277313	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	640	3	16	3	3	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	414	146	29548	25	10010	10	10000	10	10000	50	4277313	30018	30037	30037	28287	3	28767	10608	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	640	3	16	3	3	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	224	498	61	29548	25	10010	10	10000	10	10000	50	4277313	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	640	3	16	3	3	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	339	61	29548	25	10010	10	10000	10	10000	50	4277313	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	640	3	16	3	3	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	3	103	29548	25	10010	10	10000	10	10000	50	4277313	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30084	3	1	10021	10	9	10	10	10000	10	0	0	0	661	3	24	4	3	29630	10000	10	30226	30038	30038	30038	30038
10024	30037	225	12	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	2	0	640	3	16	3	3	29630	10000	10	30038	30038	30038	30084	30038
10024	30037	225	288	61	29548	25	10010	10	10000	10	10000	50	4277313	30018	30037	30037	28287	3	28767	10310	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	3	640	3	16	3	3	29630	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	10159	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	640	4	16	3	3	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	346	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	1	3	640	3	16	3	3	29630	10000	10	30038	30038	30038	30038	30038

Test 3: Latency 1->2

Code:

  sqrdmlah h0, h0, h1

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)	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	9	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	16	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	710	2	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	345	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	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	6	1899	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	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	0	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	224	6	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	224	6	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	3	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	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	39	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	710	1	16	1	1	29634	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	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	6	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	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	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)	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)	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	78	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	3	16	3	3	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	36	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	3	16	3	3	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	27	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	3	16	3	3	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	18	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	3	16	3	3	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	39	0	61	29548	25	10010	10	10000	10	10000	50	4277313	30018	30037	30037	28287	3	28767	10460	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	640	3	16	4	3	29668	10000	10	30038	30038	30038	30038	30038
10024	30037	225	309	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	3	16	3	3	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	57	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	3	16	3	3	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	60	0	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	3	16	3	3	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	224	45	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	3	16	3	3	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	36	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	3	16	3	3	29630	10000	10	30038	30038	30038	30038	30038

Test 4: Latency 1->3

Code:

  sqrdmlah h0, h1, h0

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)	09	l2 tlb miss data (0b)	18	19	1e	1f	3a	3f	4e	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	69	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d tlb access (a0)	l1d tlb miss (a1)	ld unit uop (a6)	l1d cache writeback (a8)	a9	ac	c2	branch mispred nonspec (cb)	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
10204	30037	225	0	0	0	0	0	39	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	0	0	710	1	16	1	1	29634	0	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	0	1	710	1	16	1	1	29634	0	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	6	0	0	216	29548	25	10100	100	10000	100	10000	500	4277313	30018	30037	30228	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	1	16	1	1	29634	0	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	0	0	710	1	16	1	1	29634	0	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	0	0	710	1	16	1	1	29634	0	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	0	0	710	1	16	1	1	29634	1	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	0	0	0	757	29548	25	10100	100	10000	120	10000	500	4277313	30018	30084	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	1	16	1	1	29634	0	0	10000	100	30038	30038	30038	30038	30135
10204	30037	233	0	0	0	1	0	36	88	0	61	29548	25	10113	100	10008	100	10000	500	4277313	30036	30037	30037	28265	3	28745	10100	200	10165	212	31494	30177	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	1	0	0	0	0	732	1	16	1	1	29634	0	0	10000	100	30038	30038	30038	30038	30038
10204	30037	233	0	0	0	1	0	39	0	0	82	29476	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	2	0	0	1	0	3	0	0	710	1	145	1	1	29634	0	0	10000	100	30216	30181	30182	30181	30134
10204	30178	234	0	0	0	0	0	1338	0	0	82	29548	25	10100	105	10000	156	10000	500	4277313	30018	30037	30084	28265	3	28745	10100	200	10000	204	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	4	3	1	0	27858	0	0	780	1	41	1	1	30063	0	0	10000	100	30038	30075	30517	30038	30038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

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

retire uop (01)	cycle (02)	03	1e	3f	4e	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	60	69	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	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	9	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	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	224	309	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30054	30083	30132	28287	3	28767	10010	20	10000	20	30000	30037	30037	3	1	10021	10	9	10	10	10000	10	0	0	2	0	640	2	16	2	3	29630	10000	10	30038	30038	30086	30038	30038
10024	30037	225	306	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	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	30	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	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	315	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	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	51	147	29548	44	10010	10	10000	10	10298	50	4277313	0	30018	30084	30037	28287	3	28767	10160	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	3	1	0	2795	640	5	16	4	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	63	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	30037	30037	28287	3	28843	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	1	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	66	82	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	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	224	273	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	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	15	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	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  sqrdmlah h0, h8, h9
  movi v1.16b, 0
  sqrdmlah h1, h8, h9
  movi v2.16b, 0
  sqrdmlah h2, h8, h9
  movi v3.16b, 0
  sqrdmlah h3, h8, h9
  movi v4.16b, 0
  sqrdmlah h4, h8, h9
  movi v5.16b, 0
  sqrdmlah h5, h8, h9
  movi v6.16b, 0
  sqrdmlah h6, h8, h9
  movi v7.16b, 0
  sqrdmlah h7, h8, h9

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	09	l2 tlb miss data (0b)	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)	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 tlb access (a0)	ld unit uop (a6)	l1d cache writeback (a8)	a9	ac	cd	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? int output thing (e9)	ea	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
160204	20090	150	0	0	0	0	54	0	39	25	80100	100	80000	100	80000	500	640000	0	0	20045	20064	20064	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	0	10112	2	16	2	2	20061	0	0	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	0	0	0	0	39	25	80100	100	80000	100	80000	500	640000	0	0	20045	20064	20064	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	0	10112	2	16	2	2	20061	0	0	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	0	0	0	0	39	25	80100	100	80000	100	80000	500	640000	0	0	20045	20064	20064	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	0	10112	2	16	2	2	20061	0	0	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	0	0	0	0	39	25	80100	100	80000	100	80000	500	640000	0	1	20045	20064	20064	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	0	10112	2	16	2	2	20061	0	0	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	0	0	54	0	39	25	80100	100	80000	100	80000	500	640000	0	0	20045	20064	20064	3	22	80100	200	80000	200	241251	20064	20064	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	0	10112	2	16	2	2	20061	0	0	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	0	0	0	0	39	25	80100	100	80000	100	80000	500	640000	0	1	20045	20064	20064	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	0	10112	2	16	2	2	20061	0	0	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	0	0	0	0	39	25	80100	100	80000	100	80000	500	640000	0	1	20045	20064	20064	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	0	10112	2	16	2	2	20061	0	0	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	0	0	33	0	39	25	80100	100	80000	100	80000	500	640000	0	1	20045	20064	20064	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	0	10112	2	16	2	2	20061	0	45	160000	100	20065	20065	20065	20065	20065
160204	20064	151	0	0	0	0	0	0	39	25	80100	100	80000	100	80000	500	640000	0	1	20045	20064	20064	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	0	10112	2	16	2	2	20061	0	0	160000	100	20065	20065	20065	20065	20065
160204	20064	151	0	0	0	0	6	0	39	25	80100	100	80000	100	80000	500	640000	0	1	20045	20064	20064	3	108	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	0	10112	2	16	2	2	20061	0	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	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)	5f	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)	cf	d0	d2	l1i cache miss demand (d3)	d5	map dispatch bubble (d6)	d9	da	db	dd	fetch restart (de)	e0	? int output thing (e9)	ea	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
160024	20053	150	15	45	0	25	80012	12	80000	12	80000	62	640000	0	0	20264	20050	20052	0	3	22	80012	20	80000	20	240000	20050	20052	1	1	160021	10	9	10	10	160000	10	0	10035	6	2	2	12	24	3	2	2	9	12	20049	2	31	160000	10	20053	20051	20051	20051	20051
160024	20050	151	12	51	0	25	80012	12	80000	12	80000	62	640000	0	0	20221	20052	20052	0	3	22	80012	20	80000	20	240000	20052	20052	1	1	160021	10	9	10	10	160000	10	0	10035	6	2	2	8	24	4	2	2	10	10	20047	2	30	160000	10	20051	20051	20051	20047	20047
160024	20046	150	24	51	0	25	80012	12	80000	12	80000	62	640000	0	0	20260	20052	20046	0	3	22	80012	20	80000	20	240000	20050	20050	1	1	160021	10	9	10	10	160000	10	0	10033	6	2	2	11	24	4	1	1	11	9	20047	2	15	160000	10	20053	20051	20051	20051	20047
160024	20046	150	3	51	0	25	80012	12	80000	12	80000	62	640000	0	0	20196	20050	20050	0	3	64	80012	20	80000	20	240000	20050	20050	1	1	160021	10	9	10	10	160000	10	0	10037	6	2	2	9	26	4	2	2	12	12	20047	2	30	160000	10	20053	20053	20051	20053	20051
160024	20050	150	24	51	0	25	80012	12	80000	12	80000	62	640000	0	1	20201	20052	20050	0	3	22	80012	20	80000	20	240000	20050	20050	1	1	160021	10	9	10	10	160000	10	0	10037	6	2	2	9	25	3	2	1	12	9	20049	2	30	160000	10	20051	20051	20051	20051	20053
160024	20052	150	12	51	0	25	80012	12	80000	12	80000	62	640000	1	0	20200	20046	20052	0	3	22	80012	20	80000	20	240000	20050	20050	1	1	160021	10	9	10	10	160000	10	0	10032	6	2	2	10	26	3	2	2	8	10	20049	2	30	160000	10	20047	20051	20047	20051	20047
160024	20046	150	24	51	21092	25	80012	12	80000	12	80000	62	640000	0	0	20214	20046	20052	0	3	22	80012	20	80000	20	240000	20052	20050	1	1	160021	10	9	10	10	160000	10	0	10035	6	2	2	9	24	4	1	2	9	10	20049	2	31	160000	10	20051	20047	20053	20053	20053
160024	20052	150	0	51	0	25	80012	12	80000	12	80000	62	640000	0	1	20213	20052	20052	0	3	22	80012	20	80000	20	240000	20050	20050	1	1	160021	10	9	10	10	160000	10	0	10037	6	2	1	11	24	2	2	2	12	12	20047	2	30	160000	10	20053	20051	20051	20051	20053
160024	20052	150	15	45	0	25	80012	12	80000	12	80000	62	640000	1	0	20215	20050	20050	0	3	22	80012	20	80000	20	240000	20052	20050	1	1	160021	10	9	10	10	160000	10	0	10036	6	2	2	12	26	4	2	2	10	11	20047	2	30	160000	10	20051	20051	20053	20053	20053
160024	20050	150	15	45	0	25	80012	12	80000	12	80000	62	640000	0	1	20199	20052	20052	0	3	22	80012	20	80000	20	240000	20052	20050	1	1	160021	10	9	10	10	160000	10	0	10036	6	2	2	10	20	4	1	2	11	11	20043	2	15	160000	10	20053	20047	20053	20047	20053

Test 6: throughput

Count: 16

Code:

  sqrdmlah h0, h16, h17
  sqrdmlah h1, h16, h17
  sqrdmlah h2, h16, h17
  sqrdmlah h3, h16, h17
  sqrdmlah h4, h16, h17
  sqrdmlah h5, h16, h17
  sqrdmlah h6, h16, h17
  sqrdmlah h7, h16, h17
  sqrdmlah h8, h16, h17
  sqrdmlah h9, h16, h17
  sqrdmlah h10, h16, h17
  sqrdmlah h11, h16, h17
  sqrdmlah h12, h16, h17
  sqrdmlah h13, h16, h17
  sqrdmlah h14, h16, h17
  sqrdmlah h15, h16, h17

Initialization

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

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

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

retire uop (01)	cycle (02)	03	mmu table walk data (08)	1e	37	3f	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	5f	60	69	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d tlb access (a0)	l1d tlb miss (a1)	l1d cache writeback (a8)	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
160204	40040	300	0	18	1	41	25	160100	100	160000	100	160000	500	1280000	0	0	40020	40049	40039	19973	3	19997	160100	200	160000	200	480000	40049	40049	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	0	10110	1	16	1	1	40036	0	160000	100	40040	40050	40040	40049	40050
160204	40039	300	0	0	18	51	25	160100	100	160017	100	160000	500	1319999	0	1	40030	40039	40039	19973	3	19997	160100	200	160000	200	480000	40049	40039	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	0	10110	1	16	1	1	40046	0	160000	100	40050	40040	40040	40040	40050
160204	40039	300	0	0	0	51	25	160100	100	160000	100	160000	500	2438865	0	0	40020	40039	40039	19973	3	20006	160100	200	160000	200	480000	40049	40049	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	0	10110	1	16	1	1	40036	0	160000	100	40040	40040	40040	40040	40040
160204	40039	300	0	0	0	51	25	160117	100	160000	100	160000	500	1280000	0	1	40020	40039	40039	19973	3	19997	160100	200	160000	200	480000	40039	40039	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	0	10110	1	16	1	1	40036	0	160000	100	40040	40049	40050	40040	40049
160204	40039	299	0	0	0	41	25	160100	100	160000	100	160000	500	1280000	1	0	40020	40039	40039	19973	3	19997	160100	200	160000	200	480000	40039	40039	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	1	10110	1	16	1	1	40036	0	160000	100	40040	40040	40049	40040	40050
160204	40039	299	0	0	0	41	25	160100	100	160018	100	160000	500	2399082	0	1	40020	40039	40039	19973	3	19997	160100	200	160000	200	480000	40039	40039	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	0	10110	1	16	1	1	40036	0	160000	100	40040	40040	40040	40040	40040
160204	40039	300	0	0	0	41	25	160118	100	160000	100	160000	500	1280000	0	1	40020	40039	40040	19973	3	19997	160100	200	160000	200	480000	40039	40039	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	0	10110	1	16	1	1	40036	0	160000	100	40050	40050	40040	40049	40049
160204	40048	300	0	0	0	41	25	160117	100	160000	100	160000	500	2438865	0	1	40020	40039	40039	19973	3	20007	160100	200	160000	200	480000	40039	40039	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	0	10110	1	16	1	1	40046	0	160000	100	40050	40050	40050	40040	40040
160204	40048	300	0	0	0	41	25	160118	100	160000	100	160000	500	1320000	0	0	40020	40039	40040	19973	3	20007	160100	200	160000	200	480000	40039	40039	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	0	10110	1	16	1	1	40045	0	160000	100	40049	40040	40040	40040	40040
160204	40039	300	0	0	0	41	25	160118	100	160000	100	160000	500	1280000	0	0	40020	40039	40049	19973	3	19997	160100	200	160000	200	480000	40040	40048	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	0	10110	1	16	1	1	40036	0	160000	100	40040	40040	40040	40050	40050

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	l1i tlb fill (04)	l2 tlb miss instruction (0a)	1e	1f	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)	5f	60	61	69	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d 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	ea	eb	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
160024	40048	300	0	1	0	0	0	521	0	25	160010	10	160000	10	160000	50	1280000	1	1	5	40020	40039	40039	19996	3	20019	160010	20	160000	20	480000	40048	40039	1	1	160021	10	9	10	10	160000	10	0	0	10022	8	1	1	5	16	2	1	1	5	5	40036	20	6	160000	10	40040	40040	40040	40040	40040
160024	40039	300	0	0	0	0	0	52	0	25	160010	10	160000	10	160000	50	1280000	0	1	5	40029	40048	40039	19996	3	20019	160010	20	160000	20	480000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	10022	11	5	2	5	16	4	2	2	4	4	40045	40	12	160000	10	40040	40040	40040	40040	40041
160024	40048	300	0	0	0	0	0	52	0	25	160010	10	160017	10	160000	50	2398999	0	1	5	40020	40039	40039	19996	3	20019	160010	20	160000	20	480000	40039	40071	1	1	160021	10	9	10	10	160000	10	0	0	10024	11	5	2	2	16	4	2	2	5	4	40046	40	12	160000	10	40040	40040	40041	40041	40049
160024	40039	300	0	0	0	0	0	61	0	25	160010	10	160000	10	160000	50	2399055	0	1	5	40030	40039	40039	19996	3	20028	160010	20	160000	20	480000	40039	40039	3	1	160021	10	9	10	10	160000	10	0	0	10024	11	5	2	4	16	4	2	2	2	3	40045	40	12	160000	10	40049	40040	40049	40040	40049
160024	40039	299	0	0	0	0	0	52	0	25	160010	10	160000	10	160000	50	2398999	0	1	5	40020	40039	40048	19996	3	20019	160010	20	160000	20	480000	40039	40039	1	1	160021	10	9	10	10	160000	10	52	0	10024	11	5	2	5	16	4	2	2	5	5	40045	40	12	160000	10	40040	40040	40040	40072	40040
160024	40039	300	0	0	0	0	17	242	0	25	160027	10	160000	10	160000	50	1280000	0	1	5	40020	40039	40039	19996	3	20019	160010	20	160000	20	480000	40049	40039	1	1	160021	10	9	10	10	160000	10	0	0	10024	11	5	2	5	16	4	1	2	5	3	40068	40	12	160000	10	40040	40040	40040	40040	40041
160024	40039	300	0	0	0	0	61	52	0	25	160010	10	160000	10	160000	50	1320000	1	0	5	40020	40039	40039	19996	3	20019	160010	20	160000	20	480000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	10024	6	2	2	3	16	4	2	2	3	4	40036	40	18	160000	10	40049	40040	40049	40049	40040
160024	40039	300	0	0	0	0	0	52	0	25	160071	10	160061	10	160000	50	2398999	0	1	5	40020	40039	40039	19996	3	20019	160010	20	160000	20	480000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	10024	6	2	2	4	16	4	2	2	5	5	40036	40	12	160000	10	40040	40040	40040	40040	40040
160024	40039	300	0	0	0	0	1	52	0	25	160010	10	160000	10	160000	50	2398999	1	1	5	40020	40039	40039	19996	3	20019	160010	20	160000	20	480000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	10022	11	2	2	4	16	4	2	2	4	4	40036	40	12	160000	10	40040	40040	40040	40050	40040
160024	40048	300	0	0	0	0	1	52	0	25	160010	10	160000	10	160000	50	1280000	1	1	5	40020	40039	40039	19996	3	20019	160010	20	160000	20	480000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	10024	11	5	2	4	16	4	2	2	4	4	40036	40	12	160000	10	40040	40040	40040	40040	40040

SQRDMLAH (scalar, H)

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