Firestorm: UADALP (vector, 4H) measurements

Code:

  uadalp v0.4h, v1.8b

Initialization

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

(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 tlb miss (a1)	l1d cache writeback (a8)	ac	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	f5	f6	f7	f8	fd
1004	3037	22	0	61	2548	25	1000	1000	1000	398313	1	3018	3037	3037	2415	3	2895	1000	1000	2000	3037	3037	1	1	1001	1000	0	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	1	3018	3037	3037	2415	3	2895	1000	1000	2000	3037	3037	1	1	1001	1000	0	1	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	61	2548	25	1000	1000	1000	398313	1	3018	3037	3037	2415	3	2895	1000	1000	2000	3037	3037	1	1	1001	1000	0	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	18	61	2548	25	1000	1000	1000	398313	1	3018	3037	3037	2415	3	2895	1000	1000	2000	3037	3037	1	1	1001	1000	0	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	1	3018	3037	3037	2415	3	2895	1000	1000	2000	3037	3037	1	1	1001	1000	2	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	1	3018	3037	3037	2415	3	2895	1000	1000	2000	3037	3037	1	1	1001	1000	0	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	1	3018	3037	3037	2415	3	2895	1000	1000	2000	3037	3037	1	1	1001	1000	0	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	1	3018	3037	3037	2415	3	2895	1000	1000	2000	3037	3037	1	1	1001	1000	0	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	1	3018	3037	3037	2415	3	2895	1000	1000	2000	3037	3037	1	1	1001	1000	0	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	1	3018	3037	3037	2415	3	2895	1000	1000	2000	3037	3037	1	1	1001	1000	0	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038

Test 2: Latency 1->1

Code:

  uadalp v0.4h, v1.8b

Initialization

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

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

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

retire uop (01)	cycle (02)	03	18	1e	3f	4e	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	60	69	6d	6e	map stall dispatch (70)	simd prf full (72)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	a9	ac	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? int output thing (e9)	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10204	30037	225	0	0	233	29548	25	10100	100	10000	100	10000	500	4277313	0	30018	30037	30037	28265	0	3	28745	10100	200	10000	200	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	710	2	16	2	2	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	0	30018	30037	30037	28265	0	3	28745	10100	200	10000	200	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	710	2	16	2	2	29634	0	10000	100	30038	30085	30038	30085	30038
10204	30037	225	0	0	170	29548	25	10100	100	10000	100	10000	500	4277313	0	30018	30037	30037	28265	0	3	28745	10100	200	10000	200	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	710	2	16	2	2	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	224	0	0	124	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	0	3	28745	10100	200	10000	200	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	710	2	16	2	2	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	124	29548	25	10100	100	10000	100	10000	500	4277313	0	30018	30037	30037	28265	0	3	28745	10100	200	10000	200	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	710	2	16	2	2	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	124	29548	25	10100	100	10000	100	10000	500	4277313	0	30018	30037	30037	28265	0	3	28745	10100	200	10000	200	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	710	2	16	2	2	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	360	29548	25	10100	100	10000	100	10000	500	4277313	0	30018	30037	30037	28265	0	3	28745	10100	200	10000	200	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	710	2	16	2	2	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	536	29548	25	10100	100	10000	100	10000	500	4277313	0	30018	30037	30037	28265	0	3	28745	10100	200	10000	200	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	710	2	16	2	2	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	789	29548	25	10100	100	10000	100	10000	500	4277313	0	30018	30037	30037	28265	0	3	28800	10573	200	10000	200	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	710	2	16	2	2	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	0	30018	30037	30037	28265	0	3	28745	10100	200	10000	200	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	710	2	16	2	2	29634	0	10000	100	30038	30038	30038	30038	30038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

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

retire uop (01)	cycle (02)	03	18	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)	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	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	279	29548	25	10010	10	10000	10	10000	50	4277313	30018	30037	30037	28287	0	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	10	10	10000	10	1	12	0	640	3	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	30018	30037	30037	28287	0	3	28767	10010	20	10000	20	20000	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	254	29548	25	10010	10	10000	10	10000	50	4277313	30018	30132	30085	28287	0	3	28767	10161	20	10000	20	20000	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	224	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	30018	30037	30037	28287	0	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10023	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	103	29548	25	10010	10	10000	10	10000	50	4277313	30018	30037	30037	28287	0	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	640	2	16	2	2	29630	2	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	82	29548	25	10010	10	10000	10	10000	50	4277313	30018	30037	30037	28287	0	3	28767	10010	20	10000	20	20000	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	61	29548	25	10010	10	10000	10	10000	50	4277313	30018	30037	30037	28287	0	3	28767	10010	20	10000	20	20000	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	224	0	0	147	29548	25	10010	10	10000	10	10000	50	4277313	30018	30037	30037	28287	0	3	28767	10010	20	10000	20	20000	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	61	29548	25	10010	10	10000	10	10000	50	4277313	30018	30037	30037	28287	0	3	28767	10010	20	10000	20	20000	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	61	29548	25	10010	10	10000	10	10000	50	4277313	30018	30037	30037	28287	0	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	3	0	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038

Test 3: Latency 1->2

Code:

  uadalp v0.4h, v0.8b

Initialization

  movi v0.16b, 1

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

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

retire uop (01)	cycle (02)	03	1e	3a	3f	4e	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	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	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	631	29547	25	10100	100	10000	100	10000	500	4277160	30018	30037	30037	28271	7	28741	10100	200	10008	200	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	1	1	1	722	2	24	2	2	29629	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	1	97	29547	25	10100	100	10000	100	10000	500	4277160	30018	30037	30037	28252	6	28733	10100	200	10000	200	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	1	1	1	722	2	24	2	2	29629	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	1	97	29547	25	10100	100	10000	100	10000	500	4277160	30018	30037	30037	28252	6	28733	10100	200	10000	200	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	1	1	1	722	2	24	2	2	29629	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	1	97	29547	25	10100	100	10000	100	10000	500	4277160	30018	30037	30037	28252	6	28740	10100	200	10008	200	20016	30037	30037	5	1	10201	100	99	100	100	10000	100	0	0	1	1	1	717	0	16	0	0	29645	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	61	29547	25	10100	100	10000	100	10000	500	4277160	30018	30037	30037	28271	7	28741	10100	200	10008	200	20016	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	1	1	1	717	0	16	0	0	29646	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	61	29547	25	10100	100	10000	100	10000	500	4277160	30018	30037	30037	28271	7	28741	10100	200	10008	200	20016	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	1	1	1	718	0	16	0	0	29645	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	61	29547	25	10100	100	10000	100	10000	500	4277160	30018	30037	30037	28271	7	28741	10100	200	10008	200	20016	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	1	1	1	718	0	16	0	0	29646	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	61	29547	25	10100	100	10000	100	10000	500	4277160	30018	30037	30037	28271	6	28741	10100	200	10008	200	20016	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	1	1	1	718	0	16	0	0	29645	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	61	29547	25	10100	100	10000	100	10000	500	4277160	30018	30037	30037	28271	6	28740	10100	200	10008	200	20016	30037	30037	5	1	10201	100	99	100	100	10000	100	0	0	1	1	1	717	0	16	0	0	29645	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	61	29547	25	10100	100	10000	100	10000	500	4277160	30018	30037	30037	28271	6	28741	10100	200	10008	200	20016	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	1	1	1	718	0	16	0	0	29646	10000	100	30038	30038	30038	30038	30038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

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

retire uop (01)	cycle (02)	03	1e	3f	4e	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	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	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10024	30037	225	0	1525	29547	25	10010	10	10000	10	10000	50	4277160	1	30018	30037	30037	28286	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	640	2	16	2	2	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	61	29547	25	10010	10	10000	10	10000	50	4277160	0	30018	30037	30037	28286	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	640	2	16	2	2	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	61	29547	25	10010	10	10000	10	10000	50	4277160	0	30018	30037	30037	28286	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	640	2	16	2	2	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	61	29547	25	10010	10	10000	10	10000	50	4277160	0	30018	30037	30037	28286	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	640	2	16	2	2	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	61	29547	25	10010	10	10000	10	10000	50	4277160	0	30018	30037	30037	28286	3	28767	10010	20	10658	20	20324	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	640	2	16	2	2	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	61	29547	25	10010	10	10000	10	10000	50	4277160	1	30018	30037	30037	28286	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	640	2	16	2	2	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	61	29547	25	10010	10	10000	10	10000	50	4277160	1	30018	30037	30037	28286	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	640	2	16	2	2	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	61	29547	25	10010	10	10000	10	10000	50	4277160	0	30018	30037	30037	28286	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	640	2	16	2	2	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	61	29547	25	10010	10	10000	10	10000	50	4277160	0	30018	30037	30037	28286	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	640	2	16	2	2	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	61	29547	25	10010	10	10000	10	10000	50	4277160	0	30018	30037	30037	28286	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	640	2	16	2	1	29629	10000	10	30038	30038	30038	30038	30038

Test 4: throughput

Count: 8

Code:

  movi v0.16b, 0
  uadalp v0.4h, v8.8b
  movi v1.16b, 0
  uadalp v1.4h, v8.8b
  movi v2.16b, 0
  uadalp v2.4h, v8.8b
  movi v3.16b, 0
  uadalp v3.4h, v8.8b
  movi v4.16b, 0
  uadalp v4.4h, v8.8b
  movi v5.16b, 0
  uadalp v5.4h, v8.8b
  movi v6.16b, 0
  uadalp v6.4h, v8.8b
  movi v7.16b, 0
  uadalp v7.4h, v8.8b

Initialization

  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

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

retire uop (01)	cycle (02)	03	mmu table walk data (08)	l2 tlb miss data (0b)	18	1e	1f	3f	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	60	69	6d	6e	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d tlb access (a0)	ld unit uop (a6)	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
160204	20088	150	0	0	0	0	0	29	25	80116	100	80016	100	80028	500	640196	0	20045	20065	20065	6	12	80128	200	80028	200	160056	20065	20305	1	1	160201	100	99	100	100	160000	100	0	0	0	0	1	1	1	10119	5	16	0	0	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	151	0	1	0	0	0	50	25	80116	100	80016	100	80028	500	640196	0	20045	20065	20065	6	12	80128	200	80028	200	160056	20065	20065	1	1	160201	100	99	100	100	160000	100	0	0	0	0	1	1	1	10119	0	16	0	0	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	150	0	0	0	0	0	913	25	80116	100	80016	100	80028	500	640196	0	20045	20065	20065	6	12	80128	200	80028	200	160056	20065	20065	1	1	160201	100	99	100	100	160000	100	0	0	0	0	1	1	1	10119	0	16	0	0	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	150	0	0	0	0	0	29	25	80116	100	80016	100	80028	500	640196	1	20045	20065	20065	6	12	80128	200	80028	200	160056	20065	20065	1	1	160201	100	99	100	100	160000	100	0	0	0	0	1	1	1	10119	0	16	0	0	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	150	0	0	0	0	0	29	25	80116	100	80016	100	80028	500	640196	0	20045	20065	20065	6	12	80128	200	80028	200	160056	20065	20065	1	1	160201	100	99	100	100	160000	100	0	0	0	0	1	1	1	10119	0	16	0	0	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	150	0	0	0	0	0	29	25	80116	100	80016	100	80028	500	640196	0	20045	20065	20065	6	12	80128	200	80028	200	160056	20065	20065	1	1	160201	100	99	100	100	160000	100	0	0	0	0	1	1	1	10119	0	16	0	0	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	150	0	0	0	9	0	29	25	80116	100	80016	100	80028	500	640196	0	20045	20065	20065	6	12	80128	200	80028	200	160056	20065	20065	1	1	160201	100	99	100	100	160000	100	0	0	0	0	1	1	1	10119	0	16	0	0	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	150	0	0	0	0	0	29	25	80116	100	80016	100	80028	500	640196	0	20045	20065	20065	6	12	80128	200	80028	200	160056	20065	20065	1	1	160201	100	99	100	100	160000	100	0	0	0	0	1	1	1	10119	0	16	0	0	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	151	0	0	0	0	0	96	25	80116	100	80016	100	80028	500	640196	0	20045	20065	20065	6	12	80128	200	80028	200	160056	20065	20065	1	1	160201	100	99	100	100	160000	100	0	0	0	0	1	1	1	10119	0	16	0	0	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	150	0	0	0	0	0	29	25	80116	100	80016	100	80028	500	640196	0	20045	20065	20065	6	12	80128	200	80028	200	160056	20065	20065	1	1	160201	100	99	100	100	160000	100	0	0	0	0	1	1	1	10119	0	16	0	0	20062	160000	100	20066	20066	20066	20066	20066

1000 unrolls and 10 iterations

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

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

retire uop (01)	cycle (02)	03	l2 tlb miss data (0b)	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	61	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 tlb access (a0)	l1d tlb miss (a1)	l1d cache writeback (a8)	ac	cf	d0	d2	l1i cache miss demand (d3)	d5	map dispatch bubble (d6)	d9	da	db	dd	fetch restart (de)	e0	ea	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
160024	20063	150	0	0	0	45	25	80010	10	80000	10	80000	50	640000	1	1	5	20027	20046	20046	0	3	22	80010	20	80000	20	160000	20046	20046	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10026	77	2	1	8	20	2	1	1	5	3	20043	15	160000	10	20047	20047	20047	20047	20047
160024	20046	150	0	0	0	4596	25	80010	10	80000	10	80000	50	640000	1	1	5	20027	20046	20046	0	3	22	80010	20	80000	20	160000	20046	20233	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10032	89	3	1	6	20	2	1	1	7	8	20043	15	160000	10	20047	20047	20047	20047	20047
160024	20046	150	1	0	0	89	25	80010	10	80000	10	80000	50	640000	1	1	5	20027	20046	20046	0	3	22	80010	20	80000	20	160000	20050	20050	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10035	68	4	2	3	24	4	2	2	4	5	20047	30	160000	10	20051	20051	20051	20051	20051
160024	20050	151	0	0	0	51	25	80010	10	80000	10	80000	50	640000	0	1	5	20031	20050	20050	0	3	22	80010	20	80000	20	160000	20050	20050	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10031	65	4	2	4	24	4	2	2	10	5	20047	30	160000	10	20051	20051	20051	20051	20051
160024	20050	150	0	0	0	51	25	80010	10	80000	10	80000	50	640000	0	1	5	20031	20050	20050	0	3	22	80010	20	80000	20	160000	20050	20046	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10032	56	3	1	4	20	4	1	1	5	3	20043	30	160000	10	20047	20047	20047	20047	20047
160024	20046	150	0	0	0	216	25	80010	10	80000	10	80000	50	640000	1	1	5	20027	20046	20046	0	3	22	80010	20	80000	20	160000	20046	20047	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10028	53	3	1	6	20	2	1	1	6	3	20043	15	160000	10	20047	20047	20047	20047	20047
160024	20046	150	0	0	0	45	25	80010	10	80000	10	80000	50	640000	1	1	5	20027	20046	20046	0	3	22	80010	20	80000	20	160000	20046	20046	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10028	56	3	1	10	20	2	1	1	9	9	20043	15	160000	10	20047	20047	20047	20047	20047
160024	20046	150	0	0	0	45	25	80010	10	80000	10	80000	50	640000	1	1	5	20027	20046	20046	0	3	22	80010	20	80000	20	160000	20046	20046	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10032	56	3	1	10	20	2	1	1	10	5	20043	15	160000	10	20047	20047	20047	20047	20047
160024	20046	150	0	0	0	45	25	80010	10	80000	10	80000	50	640000	1	1	5	20027	20046	20046	0	3	22	80010	20	80000	20	160000	20046	20046	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10028	53	3	1	4	20	2	1	1	3	5	20043	15	160000	10	20047	20047	20047	20047	20047
160024	20046	150	0	0	0	45	25	80010	10	80000	10	80000	50	640000	1	1	5	20027	20046	20046	0	3	22	80010	20	80000	20	160000	20046	20046	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10026	53	3	1	4	20	2	1	1	9	3	20043	15	160000	10	20047	20047	20047	20047	20047

Test 5: throughput

Count: 16

Code:

  uadalp v0.4h, v16.8b
  uadalp v1.4h, v16.8b
  uadalp v2.4h, v16.8b
  uadalp v3.4h, v16.8b
  uadalp v4.4h, v16.8b
  uadalp v5.4h, v16.8b
  uadalp v6.4h, v16.8b
  uadalp v7.4h, v16.8b
  uadalp v8.4h, v16.8b
  uadalp v9.4h, v16.8b
  uadalp v10.4h, v16.8b
  uadalp v11.4h, v16.8b
  uadalp v12.4h, v16.8b
  uadalp v13.4h, v16.8b
  uadalp v14.4h, v16.8b
  uadalp v15.4h, v16.8b

Initialization

  movi v16.16b, 17

(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	09	18	1e	37	3f	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	60	69	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d tlb miss (a1)	l1d cache writeback (a8)	a9	ac	branch cond mispred nonspec (c5)	branch mispred nonspec (cb)	cd	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
160204	40059	300	0	0	0	1	30	25	160108	100	160008	100	160020	500	1280132	0	40029	40131	40039	19977	6	19999	160120	200	160032	200	320064	40048	40039	1	1	160201	100	99	100	100	160000	100	0	0	0	0	1	1	1	10118	0	16	0	0	40045	160000	100	40040	40049	40040	40049	40040
160204	40039	299	0	0	0	17	39	25	160108	100	160008	100	160020	500	2399131	0	40029	40048	40039	19977	6	19999	160120	200	160032	200	320064	40048	40039	1	1	160201	100	99	100	100	160000	100	0	0	0	0	1	1	1	10118	0	16	0	0	40036	160000	100	40049	40040	40040	40049	40040
160204	40049	299	0	0	0	17	30	25	160108	100	160017	100	160020	500	1280132	0	40029	40048	40048	19977	6	19990	160120	200	160032	200	320064	40048	40039	1	1	160201	100	99	100	100	160000	100	0	0	0	0	1	1	1	10118	0	16	0	0	40045	160000	100	40049	40040	40049	40040	40049
160204	40048	300	0	0	6	0	30	25	160117	100	160017	100	160020	500	2399131	0	40030	40048	40039	19977	6	19990	160120	200	160032	200	320064	40048	40039	1	1	160201	100	99	100	100	160000	100	0	0	0	0	1	1	1	10118	0	16	0	0	40045	160000	100	40049	40040	40049	40040	40040
160204	40039	300	0	0	0	0	716	25	160108	100	160017	100	160020	500	1280132	0	40020	40039	40048	19977	6	19990	160120	200	160032	200	320064	40039	40039	1	1	160201	100	99	100	100	160000	100	0	0	0	0	1	1	1	10118	0	16	0	0	40036	160000	100	40049	40040	40049	40040	40049
160204	40039	300	0	0	0	17	39	25	160188	100	160017	100	160020	500	1280132	0	40029	40039	40048	19977	6	19990	160120	200	160032	200	320064	40048	40039	1	1	160201	100	99	100	100	160000	100	0	0	0	0	1	1	1	10118	0	16	0	0	40036	160000	100	40040	40050	40040	40040	40049
160204	40039	300	1	0	0	17	39	25	160108	100	160008	100	160020	500	2399131	0	40029	40048	40039	19977	6	19999	160120	200	160032	200	320064	40048	40039	1	1	160201	100	99	100	100	160000	100	0	0	0	0	1	1	1	10118	0	16	0	0	40036	160000	100	40040	40049	40040	40050	40040
160204	40039	300	0	0	0	0	39	25	160117	100	160017	100	160020	500	2438997	0	40029	40048	40039	19977	6	19990	160120	200	160032	200	320064	40048	40039	1	1	160201	100	99	100	100	160000	100	0	0	0	0	1	1	1	10118	0	16	0	0	40037	160000	100	40040	40049	40040	40040	40040
160204	40039	300	0	0	0	0	30	25	160108	100	160008	100	160020	500	2399131	0	40029	40048	40039	19977	6	19990	160120	200	160032	200	320064	40039	40048	1	1	160201	100	99	100	100	160000	100	0	0	0	0	1	1	1	10118	0	16	0	0	40045	160000	100	40049	40049	40040	40049	40040
160204	40049	299	0	0	0	17	729	27	160133	100	160033	100	160028	500	2387995	0	40030	40049	40049	19976	10	19986	160128	200	160038	200	320076	40048	40048	1	1	160201	100	99	100	100	160000	100	0	0	0	0	2	2	2	10128	1	23	1	1	40045	160000	100	40049	40050	40049	40049	40049

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	1e	1f	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)	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	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	40051	300	0	0	18	58	25	160011	10	160001	10	160000	50	1280000	0	0	5	40030	40040	40039	19996	7	3	20019	160010	20	160000	20	320000	40048	40039	1	1	160021	10	9	10	10	160000	10	1	18	0	10024	16	2	2	7	16	2	2	1	4	7	40036	40	18	160000	10	40049	40040	40049	40040	40049
160024	40040	300	0	0	0	138	25	160010	10	160000	10	160000	50	1320000	0	0	0	40021	40048	40039	20011	0	3	20019	160010	20	160000	20	320000	40048	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	10024	13	2	1	4	16	4	1	2	5	3	40037	40	14	160000	10	40041	40040	40041	40040	40041
160024	40039	300	0	0	0	52	25	160010	10	160000	10	160000	50	2398999	0	1	10	40029	40048	40051	19996	0	3	20031	160010	20	160000	20	320000	40039	40049	1	1	160021	10	9	10	10	160000	10	0	0	0	10024	6	2	1	4	16	2	1	2	5	5	40045	40	6	160000	10	40052	40049	40052	40049	40040
160024	40040	300	0	0	0	47	25	160010	10	160000	10	160000	50	1280000	0	0	0	40020	40051	40049	19996	0	3	20028	160010	20	160000	20	320000	40049	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	10022	6	4	1	7	16	2	1	2	3	5	40036	20	12	160000	10	40049	40041	40041	40049	40040
160024	40051	300	0	0	0	61	25	160010	10	160000	10	160000	50	2398999	1	0	0	40029	40048	40039	19996	0	3	20019	160010	20	160000	20	320000	40040	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	10024	6	4	1	7	16	4	2	1	5	3	40037	40	12	160000	10	40049	40040	40049	40040	40049
160024	40040	300	0	0	0	52	25	160010	10	160000	10	160000	50	2438921	0	0	0	40020	40040	40039	19996	0	3	20019	160010	20	160000	20	320000	40048	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	10022	6	1	2	7	16	4	2	2	5	5	40045	40	12	160000	10	40041	40040	40041	40040	40041
160024	40039	299	0	0	17	62	25	160010	10	160000	10	160000	50	1320000	0	0	0	40021	40048	40039	19996	0	3	20019	160010	20	160000	20	320000	40039	40048	1	1	160021	10	9	10	10	160000	10	0	0	0	10024	16	3	1	7	16	4	1	2	8	8	40046	40	12	160000	10	40052	40041	40040	40049	40040
160024	40051	300	0	0	0	64	25	160010	10	160000	10	160000	50	2398999	1	0	0	40020	40040	40048	19996	0	3	20028	160010	20	160000	20	320000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	10022	16	3	2	8	16	2	2	2	8	4	40045	40	18	160000	10	40040	40049	40040	40049	40052
160024	40039	300	0	0	0	55	25	160011	10	160000	10	160000	50	1280000	0	1	10	40077	40048	40039	19996	0	3	20031	160010	20	160000	20	320000	40039	40048	1	1	160021	10	9	10	10	160000	10	0	0	0	10024	16	2	2	3	16	4	2	1	5	5	40045	40	6	160000	10	40040	40041	40040	40049	40040
160024	40051	300	0	0	0	52	25	160010	10	160000	10	160000	50	1280000	0	0	0	40030	40049	40039	19996	0	3	20019	160010	20	160000	20	320000	40039	40048	1	1	160021	10	9	10	10	160000	10	0	0	0	10024	16	2	2	7	16	4	2	1	4	7	40036	40	12	160000	10	40040	40050	40049	40041	40049

UADALP (vector, 4H)

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: throughput

100 unrolls and 100 iterations

1000 unrolls and 10 iterations

Test 5: throughput

100 unrolls and 100 iterations

1000 unrolls and 10 iterations