Firestorm: SSRA (vector, 8H) measurements

Code:

  ssra v0.8h, v1.8h, #3

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	3f	4e	51	schedule uop (52)	schedule simd uop (54)	dispatch simd uop (57)	ldst uops in schedulers (5b)	69	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map simd uop (7e)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst simd alu (9a)	l1d cache writeback (a8)	ac	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	f5	f6	f7	f8	fd
1004	3037	22	61	2548	25	1000	1000	1000	398313	3018	3037	3037	2415	3	2895	1000	1000	2000	3037	3037	1	1	1001	1000	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	61	2548	25	1000	1000	1000	398313	3018	3037	3037	2415	3	2895	1000	1000	2000	3037	3037	1	1	1001	1000	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	61	2548	25	1000	1000	1000	398313	3018	3037	3037	2415	3	2895	1000	1000	2000	3037	3037	1	1	1001	1000	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	61	2548	25	1000	1000	1000	398313	3018	3037	3037	2415	3	2895	1000	1000	2000	3037	3037	1	1	1001	1000	1	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	61	2548	25	1000	1000	1000	398313	3018	3037	3037	2415	3	2895	1000	1000	2000	3037	3037	1	1	1001	1000	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	61	2548	25	1000	1000	1000	398313	3018	3037	3037	2415	3	2895	1000	1000	2000	3037	3037	1	1	1001	1000	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	61	2548	25	1000	1000	1000	398313	3018	3037	3037	2415	3	2895	1000	1000	2000	3037	3037	1	1	1001	1000	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	61	2548	25	1000	1000	1000	398313	3018	3037	3037	2415	3	2895	1000	1000	2000	3037	3037	1	1	1001	1000	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	61	2548	25	1000	1000	1000	398313	3018	3037	3037	2415	3	2895	1000	1000	2000	3037	3037	1	1	1001	1000	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	61	2548	25	1000	1000	1000	398313	3018	3037	3037	2415	3	2895	1000	1000	2000	3037	3037	1	1	1001	1000	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038

Test 2: Latency 1->1

Code:

  ssra v0.8h, v1.8h, #3

Initialization

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

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

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

retire uop (01)	cycle (02)	03	mmu table walk data (08)	l2 tlb miss data (0b)	18	19	1e	1f	3a	3f	4e	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	60	69	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d tlb access (a0)	l1d tlb miss (a1)	st unit uop (a7)	l1d cache writeback (a8)	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	224	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	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10251	200	10000	200	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	52	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	5	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	204	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	0	0	66	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038

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	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	6b	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d tlb access (a0)	l1d tlb miss (a1)	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	1425	29548	25	10010	10	10000	10	10000	50	4277313	0	30018	0	30037	30037	28287	3	28767	10010	20	10000	20	20000	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	536	29548	25	10010	10	10000	10	10000	50	4277313	0	30018	0	30037	30037	28287	3	28767	10010	20	10000	20	20000	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	61	29548	25	10010	10	10000	10	10000	50	4277313	0	30018	0	30037	30037	28287	3	28767	10010	20	10168	20	20326	30084	30085	2	1	10021	10	9	10	10	10000	10	2	2	2	1	5646	2	682	3	33	3	3	29702	1	10000	10	30133	30132	30132	30131	30132
10024	30037	225	1	2	348	192	1337	29530	65	10029	12	10016	12	10298	71	4278670	0	30018	0	30037	30037	28287	3	28767	10161	20	10000	20	20000	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	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	0	30037	30037	28287	3	28767	10010	20	10000	20	20000	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	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	0	30037	30037	28287	3	28767	10010	20	10000	20	20000	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	61	29548	25	10010	10	10000	10	10000	50	4277313	0	30018	0	30037	30037	28287	3	28767	10010	20	10000	20	20000	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	12	0	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	0	30037	30037	28287	3	28767	10010	20	10000	20	20000	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	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	0	30037	30037	28287	3	28767	10010	20	10000	20	20000	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	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	0	30037	30037	28287	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	3	0	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038

Test 3: Latency 1->2

Code:

  ssra v0.8h, v0.8h, #3

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	l1i tlb fill (04)	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)	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	224	0	12	0	61	29547	25	10100	100	10000	100	10000	500	4277160	0	30018	30037	30080	28252	6	28733	10100	200	10000	200	20016	30037	30037	1	1	10201	100	99	100	100	10000	100	0	1	1	1	717	1	16	1	1	29645	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	24	0	82	29547	25	10100	100	10000	100	10000	500	4277160	0	30018	30037	30037	28271	7	28741	10100	200	10008	200	20016	30037	30037	1	1	10201	100	99	100	100	10000	100	0	1	1	1	718	1	16	1	1	29646	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	61	29547	25	10100	100	10000	100	10000	500	4277160	0	30018	30037	30037	28271	7	28741	10100	200	10008	200	20016	30037	30037	1	1	10201	100	99	100	100	10000	100	0	1	1	1	718	1	16	1	1	29646	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	6	0	61	29547	25	10100	100	10000	100	10000	500	4277160	0	30018	30037	30037	28271	6	28741	10100	200	10008	200	20016	30037	30037	1	1	10201	100	99	100	100	10000	100	0	1	1	1	717	1	16	1	1	29645	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	61	29547	25	10100	100	10000	100	10000	500	4277160	0	30018	30037	30037	28271	6	28740	10100	200	10008	200	20016	30037	30037	1	1	10201	100	99	100	100	10000	100	0	1	1	1	717	1	16	1	1	29646	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	6	0	61	29547	25	10100	100	10000	100	10000	500	4277160	0	30018	30037	30037	28271	6	28741	10100	200	10008	200	20016	30037	30037	1	1	10201	100	99	100	100	10000	100	0	1	1	1	717	1	16	1	1	29645	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	345	0	61	29547	44	10100	100	10000	100	10000	500	4277160	0	30018	30037	30037	28271	6	28740	10100	200	10008	200	20016	30037	30037	1	1	10201	100	99	100	100	10000	100	0	1	1	1	717	1	16	1	1	29646	10000	100	30038	30038	30038	30038	30038
10204	30037	240	0	39	0	61	29547	25	10100	100	10000	100	10000	500	4277160	0	30018	30037	30037	28271	6	28740	10100	200	10008	200	20016	30037	30037	1	1	10201	100	99	100	100	10000	100	0	1	1	1	718	1	16	1	1	29645	10000	100	30038	30038	30038	30038	30038
10204	30037	224	0	576	0	61	29547	25	10100	100	10000	100	10000	500	4277160	0	30018	30037	30037	28271	6	28740	10100	200	10008	200	20016	30037	30037	1	1	10201	100	99	100	100	10000	100	0	1	1	1	718	1	16	1	1	29646	10000	100	30038	30038	30038	30038	30038
10204	30037	224	0	6	0	61	29547	25	10100	100	10005	100	10000	500	4277160	0	30018	30037	30037	28271	6	28741	10100	200	10008	200	20016	30037	30037	1	1	10201	100	99	100	100	10000	100	0	1	1	1	717	1	16	1	1	29645	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)	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	branch cond mispred nonspec (c5)	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	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	3	16	3	3	29629	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	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	3	16	3	3	29629	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	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	3	16	3	3	29629	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	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	3	16	2	4	29701	0	10000	10	30038	30038	30038	30038	30134
10024	30037	225	0	0	696	29547	25	10010	10	10000	10	10000	50	4279864	1	30018	30037	30037	28286	3	28767	10010	20	10000	20	20334	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	640	3	16	3	3	29629	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	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	1	0	0	640	3	16	3	3	29629	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	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	3	16	3	3	29629	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	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	3	16	3	3	29629	0	10000	10	30038	30038	30038	30038	30038
10024	30037	224	0	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	3	16	3	3	29629	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	61	29547	25	10010	10	10000	10	10000	50	4277160	0	30018	30037	30037	28286	3	28767	10010	20	10000	20	20564	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	640	3	16	3	3	29629	0	10000	10	30038	30038	30038	30038	30038

Test 4: throughput

Count: 8

Code:

  movi v0.16b, 0
  ssra v0.8h, v8.8h, #3
  movi v1.16b, 0
  ssra v1.8h, v8.8h, #3
  movi v2.16b, 0
  ssra v2.8h, v8.8h, #3
  movi v3.16b, 0
  ssra v3.8h, v8.8h, #3
  movi v4.16b, 0
  ssra v4.8h, v8.8h, #3
  movi v5.16b, 0
  ssra v5.8h, v8.8h, #3
  movi v6.16b, 0
  ssra v6.8h, v8.8h, #3
  movi v7.16b, 0
  ssra v7.8h, v8.8h, #3

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	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	61	69	6d	6e	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d tlb access (a0)	l1d tlb miss (a1)	l1d cache writeback (a8)	ac	c2	branch cond mispred nonspec (c5)	branch mispred nonspec (cb)	cd	cf	d0	d2	l1i cache miss demand (d3)	d5	map dispatch bubble (d6)	d9	da	db	dd	fetch restart (de)	e0	ea	ec	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
160204	20089	150	0	9	0	29	25	80116	100	80016	100	80028	500	640196	1	5	20057	20065	20065	6	12	80128	200	80028	200	160056	20065	20065	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	1	1	1	10127	0	0	0	7	16	0	0	0	8	8	20062	0	0	160000	100	20066	20079	20078	20079	20066
160204	20065	150	0	0	0	29	25	80116	100	80016	100	80028	500	640196	0	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	0	1	1	1	10127	0	0	0	8	16	0	0	0	6	3	20074	21	0	160000	100	20078	20078	20078	20078	20066
160204	20065	150	0	30	0	29	25	80116	100	80016	100	80028	500	640196	0	5	20045	20065	20146	29	12	80129	200	80028	200	160056	20065	20065	1	1	160201	100	99	100	100	160000	100	0	0	0	0	2	1	1	1	10127	0	1	0	7	16	0	0	0	7	7	20062	0	0	160000	100	20169	20066	20066	20066	20066
160204	20065	151	1	12	108	319	25	80117	100	80122	100	80029	500	640196	0	0	20057	20065	20065	6	12	80128	200	80028	200	160056	20065	20065	1	1	160201	100	99	100	100	160000	100	0	0	0	0	4	1	1	1	10127	5	0	0	11	49	0	0	0	8	8	20203	0	0	160000	100	20066	20066	20066	20066	20066
160204	20065	150	0	0	0	29	25	80116	100	80016	100	80029	500	640196	0	5	20045	20065	20077	10	12	80131	200	80031	200	160062	20078	20077	1	1	160201	100	99	100	100	160000	100	0	0	0	3	0	2	2	2	10134	0	1	0	9	23	0	0	0	9	9	20075	0	0	160000	100	20078	20078	20079	20078	20078
160204	20077	150	0	0	0	65	29	80119	100	80019	100	80031	500	640220	0	0	20056	20077	20078	10	12	80131	200	80031	200	160062	20078	20078	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	2	2	2	10140	0	3	1	8	23	0	0	0	9	8	20074	0	0	160000	100	20090	20078	20079	20078	20091
160204	20077	150	0	0	0	65	31	80119	100	80019	100	80031	500	640220	0	0	20056	20077	20077	10	12	80131	200	80031	200	160062	20078	20078	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	2	2	2	10138	0	0	0	9	23	1	0	0	9	9	20074	0	0	160000	100	20079	20078	20078	20079	20078
160204	20077	151	0	6	0	65	81	80225	100	80019	100	80137	500	640220	0	0	20056	20078	20398	16	12	80131	200	80031	200	160062	20077	20077	1	1	160201	100	99	100	100	160000	100	2	0	0	0	0	2	2	2	10138	0	1	0	9	23	0	0	0	9	9	20074	21	1	160000	100	20090	20090	20091	20091	20090
160204	20077	150	0	6	0	71	29	80119	100	80019	100	80031	500	640220	0	0	20056	20078	20078	9	12	80131	200	80031	200	160062	20077	20077	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	2	2	2	10138	0	0	0	10	23	0	0	0	9	9	20074	0	0	160000	100	20078	20078	20079	20078	20132
160204	20077	151	0	0	0	65	32	80119	100	80019	100	80031	500	640220	0	0	20056	20078	20078	10	12	80131	200	80031	200	160062	20078	20077	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	2	2	2	10141	8	0	0	8	34	0	0	0	9	9	20074	0	0	160000	100	20078	20078	20078	20079	20078

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	mmu table walk data (08)	l2 tlb miss instruction (0a)	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	61	69	6b	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 miss (a1)	ld unit uop (a6)	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	ec	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
160024	20095	151	0	0	0	0	0	9	0	45	27	80010	10	80000	10	80000	50	640000	1	1	5	20045	0	20051	20051	3	22	80010	20	80000	20	160000	20051	20051	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10027	8	4	1	6	25	2	1	1	4	2	20048	20	1	160000	10	20052	20052	20052	20052	20052
160024	20051	150	0	0	0	0	0	6	0	45	27	80010	10	80000	10	80000	50	640000	1	1	5	20032	0	20051	20051	3	22	80010	20	80000	20	160000	20131	20187	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10025	8	5	1	2	25	2	1	1	2	4	20048	20	1	160000	10	20052	20052	20052	20052	20052
160024	20051	151	0	0	0	0	0	0	0	45	27	80010	10	80000	10	80000	50	640000	1	1	5	20032	0	20051	20051	3	22	80010	20	80000	20	160000	20051	20051	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10027	8	5	1	2	25	2	1	1	4	4	20048	20	1	160000	10	20052	20052	20052	20052	20052
160024	20051	150	0	0	0	0	0	0	0	45	27	80010	10	80000	10	80000	50	640000	1	1	5	20032	0	20051	20051	3	22	80010	20	80000	20	160000	20051	20051	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10027	8	5	1	4	25	2	1	1	2	4	20114	20	1	160000	10	20142	20141	20140	20138	20133
160024	20150	151	1	0	1	1	1	138	176	881	67	80115	10	80210	10	80104	50	641680	1	1	5	20098	0	20165	20131	10	22	80010	20	80000	20	160000	20051	20051	1	1	160021	10	9	10	10	160000	10	2	2	0	0	10025	8	5	1	4	25	2	1	1	4	4	20048	20	1	160000	10	20052	20052	20052	20052	20052
160024	20051	150	0	0	0	0	0	0	0	45	27	80010	10	80000	10	80000	50	640000	1	1	5	20032	0	20051	20051	3	22	80010	20	80000	20	160000	20051	20051	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10025	8	5	1	2	25	2	1	1	2	4	20048	20	1	160000	10	20052	20052	20052	20052	20052
160024	20051	150	0	0	0	0	0	0	0	235	27	80010	10	80000	10	80000	50	640000	1	1	5	20032	0	20051	20051	3	22	80010	20	80000	20	160000	20051	20051	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10025	8	5	1	2	25	2	1	1	2	4	20048	20	1	160000	10	20052	20052	20052	20052	20052
160024	20051	150	0	0	0	0	0	0	0	45	27	80010	10	80000	10	80000	50	640000	1	1	5	20032	0	20051	20051	3	22	80010	20	80000	20	160000	20051	20051	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10025	8	5	1	2	25	2	1	1	4	2	20048	20	1	160000	10	20052	20052	20052	20052	20052
160024	20051	150	0	0	0	0	0	0	0	45	27	80010	10	80000	10	80000	50	640000	1	1	5	20032	0	20051	20051	3	22	80010	20	80000	20	160000	20051	20051	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10027	8	5	2	4	25	2	1	1	2	4	20048	20	1	160000	10	20052	20052	20052	20052	20052
160024	20051	150	0	0	0	0	0	0	0	45	27	80010	10	80000	10	80000	50	640000	1	1	5	20032	0	20051	20051	3	22	80010	20	80000	20	160000	20051	20051	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10027	8	5	1	4	25	2	1	1	4	2	20057	20	1	160000	10	20052	20052	20052	20052	20052

Test 5: throughput

Count: 16

Code:

  ssra v0.8h, v16.8h, #3
  ssra v1.8h, v16.8h, #3
  ssra v2.8h, v16.8h, #3
  ssra v3.8h, v16.8h, #3
  ssra v4.8h, v16.8h, #3
  ssra v5.8h, v16.8h, #3
  ssra v6.8h, v16.8h, #3
  ssra v7.8h, v16.8h, #3
  ssra v8.8h, v16.8h, #3
  ssra v9.8h, v16.8h, #3
  ssra v10.8h, v16.8h, #3
  ssra v11.8h, v16.8h, #3
  ssra v12.8h, v16.8h, #3
  ssra v13.8h, v16.8h, #3
  ssra v14.8h, v16.8h, #3
  ssra v15.8h, v16.8h, #3

Initialization

  movi v16.16b, 17

(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	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	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	branch cond mispred nonspec (c5)	branch mispred nonspec (cb)	cd	cf	d5	map dispatch bubble (d6)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
160204	40058	299	0	30	25	160108	100	160008	100	160020	500	1280132	0	40020	40039	40039	19977	0	6	19990	160120	200	160032	200	320064	40039	40039	1	1	160201	100	99	100	100	160000	100	0	0	150	1	1	1	10118	1	16	40036	160000	100	40040	40040	40040	40040	40040
160204	40039	300	0	51	25	160108	100	160008	100	160020	500	1280132	0	40020	40039	40039	19977	0	6	19990	160120	200	160032	200	320064	40039	40039	1	1	160201	100	99	100	100	160000	100	0	0	24	1	1	1	10118	0	16	40036	160000	100	40040	40040	40040	40040	40040
160204	40039	300	0	30	25	160108	100	160008	100	160020	500	1280132	0	40020	40039	40039	19977	0	6	19990	160120	200	160032	200	320064	40039	40039	1	1	160201	100	99	100	100	160000	100	0	0	0	1	1	1	10118	0	16	40036	160000	100	40040	40040	40040	40040	40040
160204	40039	300	0	63	25	160108	100	160008	100	160020	500	1280132	0	40020	40039	40039	19977	0	6	19990	160120	200	160032	200	320064	40039	40039	1	1	160201	100	99	100	100	160000	100	0	0	132	1	1	1	10118	0	16	40036	160000	100	40040	40040	40040	40040	40040
160204	40039	300	0	30	25	160108	100	160008	100	160020	500	1280132	0	40020	40039	40039	19977	0	6	19990	160120	200	160032	200	320064	40039	40039	1	1	160201	100	99	100	100	160000	100	0	0	192	1	1	1	10118	0	16	40036	160000	100	40040	40040	40040	40040	40040
160204	40039	300	0	30	25	160108	100	160008	100	160020	500	1280132	0	40020	40039	40039	19977	0	6	19990	160120	200	160032	200	320064	40039	40039	1	1	160201	100	99	100	100	160000	100	0	0	204	1	1	1	10118	0	16	40036	160000	100	40040	40040	40040	40040	40040
160204	40039	300	0	30	25	160108	100	160008	100	160020	500	1280132	1	40020	40039	40039	19977	0	6	19990	160120	200	160032	200	320064	40039	40039	1	1	160201	100	99	100	100	160000	100	0	0	213	1	1	1	10118	0	16	40036	160000	100	40040	40040	40040	40040	40040
160204	40039	299	0	30	25	160108	100	160008	100	160020	500	1280132	1	40020	40039	40039	19977	0	6	19990	160120	200	160032	200	320064	40039	40039	1	1	160201	100	99	100	100	160000	100	0	0	216	1	1	1	10118	0	16	40036	160000	100	40040	40040	40040	40040	40040
160204	40039	300	0	30	25	160108	100	160008	100	160020	500	1280132	1	40020	40039	40039	19977	0	6	19990	160120	200	160032	200	320064	40039	40039	1	1	160201	100	99	100	100	160000	100	0	0	144	1	1	1	10118	0	16	40036	160000	100	40040	40040	40040	40040	40040
160204	40039	300	0	30	25	160108	100	160008	100	160020	500	1280972	0	40020	40039	40039	19977	0	6	19990	160120	200	160032	200	320064	40039	40039	1	1	160201	100	99	100	100	160000	100	2	0	165	1	1	1	10118	0	16	40036	160000	100	40040	40040	40040	40040	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	09	18	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)	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 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	eb	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
160024	40039	300	0	0	0	46	25	160010	10	160000	10	160000	50	1280000	1	1	5	40020	40039	40039	19996	0	3	20019	160010	20	160000	20	320000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	10022	13	4	1	4	16	2	1	1	4	3	40036	20	6	160000	10	40040	40040	40040	40040	40040
160024	40039	300	0	0	0	46	25	160010	10	160000	10	160000	50	1280000	1	1	10	40020	40039	40039	19996	0	3	20019	160010	20	160000	20	320000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	10022	13	3	1	3	16	2	1	1	3	4	40036	20	6	160000	10	40040	40040	40040	40040	40040
160024	40039	299	0	0	0	46	25	160010	10	160000	10	160000	50	1280000	1	1	10	40020	40039	40039	19996	0	3	20019	160010	20	160000	20	320000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	10022	13	3	1	3	16	2	1	1	4	3	40036	20	6	160000	10	40040	40040	40040	40040	40040
160024	40039	299	0	0	0	616	25	160010	10	160000	10	160000	50	1280000	1	1	10	40020	40039	40039	19996	0	3	20019	160010	20	160000	20	320000	40039	40039	1	1	160021	10	9	10	10	160000	10	1	0	0	10022	13	3	1	3	16	2	1	1	3	2	40036	20	6	160000	10	40040	40040	40040	40040	40040
160024	40039	300	0	0	0	46	25	160010	10	160000	10	160000	50	1280000	1	1	10	40020	40039	40039	19996	0	3	20019	160010	20	160000	20	320000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	10022	13	3	1	3	16	2	1	1	3	3	40036	20	6	160000	10	40040	40040	40040	40040	40040
160024	40039	300	0	0	0	46	25	160010	10	160000	10	160000	50	1280000	1	1	10	40020	40039	40039	19996	0	3	20019	160010	20	160000	20	320000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	10022	13	6	1	4	16	2	1	1	3	2	40036	20	6	160000	10	40040	40040	40040	40040	40040
160024	40039	299	0	0	0	46	25	160010	10	160000	10	160000	50	1280000	1	1	10	40020	40039	40039	19996	0	3	20019	160010	20	160000	20	320000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	10022	13	6	1	4	16	2	1	1	3	3	40036	20	6	160000	10	40040	40040	40040	40040	40040
160024	40039	300	0	0	0	46	25	160010	10	160000	10	160000	50	1280000	1	1	10	40020	40039	40039	19996	0	3	20019	160010	20	160000	20	320000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	10022	13	6	1	2	16	2	1	1	3	2	40036	20	6	160000	10	40040	40040	40040	40040	40040
160024	40039	299	0	0	0	711	25	160010	10	160000	10	160000	50	1280000	1	1	10	40020	40039	40039	19996	0	3	20019	160010	20	160000	20	320000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	10022	13	6	1	3	16	2	1	1	2	4	40036	20	6	160000	10	40040	40040	40040	40040	40040
160024	40039	300	0	0	0	46	25	160010	10	160000	10	160000	50	1280000	1	1	10	40020	40039	40039	19996	0	3	20019	160010	20	160000	20	320000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	10022	13	6	1	4	16	2	1	1	2	3	40036	20	6	160000	10	40040	40040	40040	40040	40040

SSRA (vector, 8H)

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