Firestorm: SSRA (vector, 16B) measurements

Code:

  ssra v0.16b, v1.16b, #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	18	1e	3f	4e	51	schedule uop (52)	schedule simd uop (54)	dispatch simd uop (57)	ldst uops in schedulers (5b)	60	69	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map simd uop (7e)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst simd alu (9a)	l1d cache writeback (a8)	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	f5	f6	f7	f8	fd
1004	3037	23	0	0	251	2548	25	1000	1000	1000	398313	0	3018	3037	3037	2415	3	2895	1000	1000	2000	3037	3037	1	1	1001	1000	0	73	2	16	3	3	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	0	0	61	2548	25	1000	1000	1000	398313	0	3018	3037	3037	2415	3	2895	1000	1000	2000	3037	3037	1	1	1001	1000	0	73	3	16	3	3	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	61	2548	25	1000	1000	1000	398313	0	3018	3037	3037	2415	3	2895	1000	1000	2000	3037	3037	1	1	1001	1000	0	73	3	16	3	3	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	0	0	61	2548	25	1000	1000	1000	398313	0	3018	3037	3037	2415	3	2895	1000	1000	2000	3037	3037	1	1	1001	1000	0	73	3	16	3	3	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	61	2548	25	1000	1000	1000	398313	0	3018	3037	3037	2415	3	2895	1000	1000	2000	3037	3037	1	1	1001	1000	0	73	3	16	3	3	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	82	2548	25	1000	1000	1000	398313	0	3018	3037	3037	2415	3	2895	1000	1000	2000	3037	3037	1	1	1001	1000	0	73	3	16	3	3	2630	1000	3038	3086	3038	3038	3038
1004	3037	22	0	0	61	2548	25	1000	1000	1000	398313	0	3018	3037	3037	2415	3	2895	1000	1000	2000	3037	3037	1	1	1001	1000	0	73	3	16	3	2	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	61	2548	25	1000	1000	1000	398313	0	3018	3037	3037	2415	3	2895	1000	1000	2000	3037	3037	1	1	1001	1000	0	73	3	16	3	3	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	61	2548	25	1000	1000	1000	398313	0	3018	3037	3037	2415	3	2895	1000	1000	2000	3037	3037	1	1	1001	1000	2	73	3	16	3	3	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	0	0	61	2548	25	1000	1000	1000	398313	0	3018	3037	3037	2415	3	2895	1000	1000	2000	3037	3037	1	1	1001	1000	0	73	3	16	2	2	2630	1000	3038	3038	3038	3038	3038

Test 2: Latency 1->1

Code:

  ssra v0.16b, v1.16b, #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	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)	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	60	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28272	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	42	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28272	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	18	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	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	408	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	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	224	432	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	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	36	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	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	24	61	29548	25	10100	100	10000	100	10000	500	4277313	0	30018	30037	30037	28265	11	28745	10100	200	10000	200	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	252	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	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	405	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	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	411	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	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	l1i tlb fill (04)	mmu table walk instruction (07)	mmu table walk data (08)	09	l2 tlb miss instruction (0a)	l2 tlb miss data (0b)	18	19	1e	1f	3a	3f	4e	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	60	69	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d tlb miss (a1)	ld unit uop (a6)	st unit uop (a7)	l1d cache writeback (a8)	a9	ac	c2	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? int output thing (e9)	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10024	30037	225	0	0	0	0	0	0	0	0	0	0	2	66	29548	25	10010	10	10000	10	10000	50	4277313	0	30018	30037	30037	28287	3	28767	10460	20	10000	20	20000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	0	644	11	16	10	10	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	0	0	0	0	0	0	2	5652	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	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	0	644	5	16	5	10	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	0	0	0	0	0	0	2	66	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	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	0	644	12	16	10	10	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	0	0	0	0	729	0	2	66	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	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	0	644	10	16	10	10	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	0	0	0	0	0	0	2	66	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	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	0	644	10	16	10	12	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	224	0	0	0	0	0	0	0	0	0	0	2	66	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	30037	30037	28287	3	28785	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	0	644	10	16	10	10	29695	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	0	0	0	0	0	0	2	66	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	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	0	644	10	16	10	10	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	0	0	0	0	0	0	2	66	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	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	3	0	644	12	16	8	8	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	0	0	0	0	0	0	2	66	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	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	0	644	10	16	10	10	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	0	0	0	0	0	0	2	66	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	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	0	644	10	16	10	10	29630	0	10000	10	30038	30038	30038	30038	30038

Test 3: Latency 1->2

Code:

  ssra v0.16b, v0.16b, #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	18	19	1e	1f	3a	3f	4e	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	60	69	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d tlb access (a0)	l1d tlb miss (a1)	ld unit uop (a6)	st unit uop (a7)	l1d cache writeback (a8)	a9	ac	c2	branch cond mispred nonspec (c5)	branch mispred nonspec (cb)	cd	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? int output thing (e9)	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10204	30037	225	0	0	0	0	0	61	29547	25	10100	100	10000	100	10000	500	4277160	1	30018	30037	30037	28271	7	28741	10100	200	10008	200	20016	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	0	0	1	1	1	718	0	16	0	0	29646	0	10000	100	30038	30038	30038	30038	30038
10205	30037	225	0	0	0	0	0	2019	29547	25	10100	100	10000	100	10000	500	4277160	1	30018	30037	30037	28271	6	28740	10100	200	10008	200	20016	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	0	0	1	1	1	717	0	16	0	0	29645	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	61	29547	25	10100	100	10000	100	10000	500	4277160	1	30018	30037	30037	28271	7	28740	10100	200	10008	200	20016	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	0	0	1	1	1	718	0	16	0	0	29645	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	61	29547	25	10100	100	10000	100	10000	500	4277160	1	30018	30037	30037	28271	6	28741	10100	200	10008	200	20016	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	0	0	1	1	1	717	0	16	0	0	29645	0	10000	100	30038	30038	30038	30038	30038
10204	30037	224	0	0	0	0	0	61	29547	25	10100	100	10000	100	10000	500	4277160	1	30018	30037	30037	28271	7	28741	10100	200	10008	200	20016	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	0	0	1	1	1	718	0	16	0	0	29645	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	61	29547	25	10100	100	10000	100	10000	500	4277160	1	30018	30037	30037	28271	7	28740	10100	200	10008	200	20016	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	0	0	1	1	1	718	0	16	0	0	29645	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	61	29547	25	10100	100	10000	100	10000	516	4277160	1	30018	30037	30037	28271	6	28741	10100	200	10008	200	20016	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	0	0	1	1	1	718	0	16	0	0	29646	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	61	29547	25	10100	100	10000	100	10000	500	4277160	1	30018	30037	30037	28271	6	28741	10100	200	10008	200	20016	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	47	0	0	0	1	1	1	718	0	16	0	0	29646	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	61	29547	25	10100	100	10000	100	10000	500	4277160	1	30018	30037	30037	28271	7	28740	10100	200	10008	200	20016	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	0	0	1	1	1	718	0	16	0	0	29646	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	61	29547	25	10100	100	10000	100	10000	500	4277160	1	30018	30037	30037	28271	6	28740	10100	200	10008	200	20016	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	0	0	1	1	1	718	0	16	0	0	29645	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	1e	3a	3f	4e	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	60	69	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d cache writeback (a8)	ac	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10024	30037	225	0	0	61	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	640	2	16	2	2	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	225	12	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	640	2	16	2	2	29629	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	640	2	16	2	2	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	631	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	640	2	16	2	2	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	224	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	640	2	16	2	2	29629	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	640	2	16	2	2	29629	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	640	2	16	2	2	29629	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	640	2	16	2	2	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	726	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	640	2	16	2	2	29629	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	640	2	16	2	2	29629	10000	10	30038	30038	30038	30038	30038

Test 4: throughput

Count: 8

Code:

  movi v0.16b, 0
  ssra v0.16b, v8.16b, #3
  movi v1.16b, 0
  ssra v1.16b, v8.16b, #3
  movi v2.16b, 0
  ssra v2.16b, v8.16b, #3
  movi v3.16b, 0
  ssra v3.16b, v8.16b, #3
  movi v4.16b, 0
  ssra v4.16b, v8.16b, #3
  movi v5.16b, 0
  ssra v5.16b, v8.16b, #3
  movi v6.16b, 0
  ssra v6.16b, v8.16b, #3
  movi v7.16b, 0
  ssra v7.16b, v8.16b, #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	3f	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	60	69	6d	6e	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d cache writeback (a8)	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	20090	150	29	25	80116	104	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	1	1	1	10119	0	16	0	0	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	150	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	1	1	1	10119	0	16	0	0	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	150	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	1	1	1	10119	0	16	0	0	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	151	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	1	1	1	10119	0	16	0	0	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	150	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	117	1	1	1	10119	0	16	0	0	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	150	29	25	80116	100	80016	102	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	1	1	1	10119	0	16	0	0	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	151	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	1	1	1	10119	0	16	0	0	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	150	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	1	1	1	10119	0	16	0	0	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	151	52	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	102	1	1	1	10119	0	16	0	0	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	150	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	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	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 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	c9	cf	d0	d2	l1i cache miss demand (d3)	d5	map dispatch bubble (d6)	d9	da	db	dd	fetch restart (de)	e0	ea	eb	ec	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
160024	20075	186	12	45	27	80010	10	80000	10	80000	50	640000	1	1	5	20032	20051	20051	3	22	80010	20	80000	20	160000	20051	20051	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10030	8	3	1	5	25	4	2	2	6	8	20057	40	0	2	160000	10	20061	20061	20061	20061	20061
160024	20060	185	0	45	27	80010	10	80000	10	80000	50	640000	1	1	5	20041	20060	20060	3	22	80010	20	80000	20	160000	20060	20060	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10026	8	2	1	5	25	2	1	1	5	3	20048	20	0	2	160000	10	20052	20052	20052	20052	20052
160024	20051	186	0	51	29	80010	10	80000	10	80000	50	640000	1	1	5	20032	20051	20051	3	22	80010	20	80000	20	160000	20051	20051	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10031	11	3	2	4	34	4	2	2	3	6	20057	40	0	2	160000	10	20061	20061	20061	20061	20061
160024	20051	186	0	45	27	80010	10	80000	10	80000	50	640000	0	1	5	20041	20060	20060	3	22	80010	20	80000	20	160000	20060	20060	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10031	11	3	2	7	25	2	2	2	8	8	20057	40	0	2	160000	10	20061	20061	20061	20061	20061
160024	20060	174	0	782	27	80010	10	80000	10	80000	50	640000	0	1	5	20041	20060	20060	3	22	80010	20	80000	20	160000	20060	20060	1	1	160021	10	9	10	10	160000	10	0	0	540	0	10028	8	2	1	7	25	2	1	2	4	7	20048	20	0	1	160000	10	20052	20052	20052	20052	20052
160024	20051	173	0	51	29	80010	10	80000	10	80000	50	640000	1	1	5	20032	20051	20051	3	22	80010	20	80000	20	160000	20051	20051	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10031	11	3	2	6	34	4	2	2	7	5	20057	40	0	2	160000	10	20061	20061	20061	20061	20061
160024	20060	174	0	45	27	80010	10	80000	10	80129	50	640000	1	1	5	20032	20051	20051	3	22	80010	20	80000	20	160000	20051	20051	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10032	11	3	2	5	34	4	2	2	4	6	20057	40	0	2	160000	10	20061	20061	20061	20061	20052
160024	20060	174	12	87	27	80010	10	80000	10	80000	50	640000	0	1	5	20041	20060	20060	3	22	80010	20	80000	20	160000	20060	20060	1	1	160021	10	9	10	10	160000	10	0	1	3	0	10034	8	2	1	8	25	4	1	1	3	5	20048	20	0	1	160000	10	20052	20052	20052	20052	20061
160024	20051	161	12	4278	29	80010	10	80000	10	80000	50	640000	1	1	5	20032	20051	20051	3	22	80010	20	80000	20	160000	20051	20051	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10033	11	3	2	4	34	4	2	2	5	3	20057	40	0	2	160000	10	20061	20061	20061	20052	20061
160024	20060	160	45	45	29	80010	10	80000	10	80000	50	640000	0	1	5	20041	20060	20060	3	22	80010	20	80000	20	160000	20060	20060	1	1	160021	10	9	10	10	160000	10	0	0	0	3	10031	3	1	806	9	20	2	1	1	3	6	20043	15	0	0	160000	10	20047	20047	20047	20047	20047

Test 5: throughput

Count: 16

Code:

  ssra v0.16b, v16.16b, #3
  ssra v1.16b, v16.16b, #3
  ssra v2.16b, v16.16b, #3
  ssra v3.16b, v16.16b, #3
  ssra v4.16b, v16.16b, #3
  ssra v5.16b, v16.16b, #3
  ssra v6.16b, v16.16b, #3
  ssra v7.16b, v16.16b, #3
  ssra v8.16b, v16.16b, #3
  ssra v9.16b, v16.16b, #3
  ssra v10.16b, v16.16b, #3
  ssra v11.16b, v16.16b, #3
  ssra v12.16b, v16.16b, #3
  ssra v13.16b, v16.16b, #3
  ssra v14.16b, v16.16b, #3
  ssra v15.16b, v16.16b, #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	mmu table walk data (08)	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)	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
160204	40061	299	0	0	30	25	160108	100	160008	100	160020	500	1280132	40020	40039	40039	19977	6	19990	160120	200	160032	200	320064	40039	40039	1	1	160201	100	99	100	100	160000	100	0	0	1	1	1	10118	1	16	3	2	40036	160000	100	40040	40040	40040	40040	40040
160204	40039	299	0	0	30	25	160108	100	160008	100	160020	500	1280132	40020	40039	40039	19977	6	19990	160120	200	160032	200	320064	40039	40039	1	1	160201	100	99	100	100	160000	100	0	0	1	1	1	10118	1	16	4	1	40036	160000	100	40040	40040	40040	40040	40040
160204	40039	300	0	0	30	25	160108	100	160008	100	160020	500	1280132	40071	40039	40039	19977	6	19990	160120	200	160032	200	320064	40039	40039	1	1	160201	100	99	100	100	160000	100	0	0	1	1	1	10118	2	16	3	2	40036	160000	100	40040	40040	40040	40040	40040
160204	40039	300	0	0	30	25	160108	100	160008	100	160020	500	1280132	40020	40039	40039	19977	6	19990	160120	200	160032	200	320064	40039	40039	1	1	160201	100	99	100	100	160000	100	0	0	1	1	1	10118	1	16	3	1	40036	160000	100	40040	40040	40040	40040	40040
160204	40039	300	0	0	30	25	160108	100	160008	100	160020	500	1280132	40020	40039	40039	19977	6	19990	160120	200	160032	200	320064	40039	40039	1	1	160201	100	99	100	100	160000	100	0	0	1	1	1	10118	2	16	3	2	40036	160000	100	40040	40040	40040	40040	40040
160204	40039	299	0	0	30	25	160108	100	160008	100	160020	500	1280132	40020	40039	40039	19977	6	19990	160120	200	160032	200	320064	40039	40039	1	1	160201	100	99	100	100	160000	100	0	0	1	1	1	10118	2	16	3	2	40036	160000	100	40040	40040	40040	40040	40040
160204	40039	300	0	0	30	25	160108	100	160008	100	160020	500	1280132	40020	40039	40039	19977	6	19990	160120	200	160032	200	320064	40039	40039	1	1	160201	100	99	100	100	160000	100	0	0	1	1	1	10118	2	16	3	2	40036	160000	100	40040	40040	40040	40040	40040
160204	40039	300	0	0	30	25	160108	100	160008	100	160020	500	1280132	40020	40039	40039	19977	6	19990	160120	200	160032	200	320064	40039	40039	1	1	160201	100	99	100	100	160000	100	0	0	1	1	1	10118	2	16	2	1	40036	160000	100	40040	40040	40040	40040	40040
160204	40039	300	0	0	30	25	160108	100	160008	100	160020	500	1280132	40020	40039	40039	19977	6	19990	160120	200	160032	200	320064	40039	40039	1	1	160201	100	99	100	100	160000	100	2	0	1	1	1	10118	1	16	2	2	40036	160000	100	40040	40040	40040	40040	40040
160204	40039	300	0	0	30	25	160108	100	160008	100	160020	500	1280132	40020	40039	40039	19977	6	19990	160120	200	160032	200	320064	40039	40039	1	1	160201	100	99	100	100	160000	100	0	0	1	1	1	10118	2	16	2	2	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	mmu table walk data (08)	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)	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	cd	cf	d0	d2	l1i cache miss demand (d3)	d5	map dispatch bubble (d6)	d9	da	db	dd	fetch restart (de)	e0	ea	eb	ec	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
160024	40051	299	0	0	46	25	160010	10	160000	10	160000	50	1280000	1	1	0	40020	40039	40039	19996	3	20019	160010	20	160000	20	320000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10022	3	1	1	11	16	2	1	1	10	8	40036	15	5	10	160000	10	40040	40040	40040	40040	40040
160024	40039	300	0	0	46	25	160010	10	160000	10	160000	50	1280000	1	1	0	40020	40039	40039	19996	3	20019	160010	20	160000	20	320000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10022	3	1	1	12	16	2	1	1	8	18	40036	15	5	8	160000	10	40040	40040	40040	40040	40040
160024	40039	300	0	0	46	25	160010	10	160000	10	160000	50	1280000	1	1	0	40020	40039	40039	19996	3	20019	160010	20	160000	20	320000	40039	40039	1	1	160021	10	9	10	10	160000	10	1	0	0	0	10022	3	1	1	10	16	2	1	1	10	10	40036	15	5	9	160000	10	40040	40040	40040	40040	40040
160024	40039	300	0	0	46	25	160010	10	160000	10	160000	50	1280000	1	1	0	40020	40039	40039	19996	3	20019	160010	20	160000	20	320000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10022	3	1	1	10	16	2	1	1	10	7	40036	15	5	6	160000	10	40040	40040	40040	40040	40040
160024	40039	300	0	12	46	25	160010	10	160000	10	160000	50	1280000	1	1	0	40020	40039	40039	19996	3	20019	160010	20	160000	20	320280	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10022	3	1	1	8	16	2	1	1	10	7	40036	15	5	6	160000	10	40040	40040	40040	40040	40040
160024	40039	300	0	0	46	25	160010	10	160000	10	160000	50	1280000	1	1	0	40020	40039	40039	19996	3	20019	160010	20	160000	20	320000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10022	3	1	1	10	16	2	1	1	7	10	40036	15	5	7	160000	10	40040	40040	40040	40040	40040
160024	40039	299	0	0	46	25	160010	10	160000	10	160000	50	1280000	1	1	0	40020	40039	40039	19996	3	20019	160010	20	160000	20	320000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10022	3	2	1	8	16	2	1	1	7	10	40036	30	5	8	160000	10	40040	40040	40040	40040	40040
160024	40039	300	0	0	46	25	160010	10	160000	10	160000	50	1280000	0	1	0	40020	40039	40039	19996	3	20019	160010	20	160000	20	320000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10022	3	1	1	10	16	2	1	1	10	7	40036	15	5	7	160000	10	40040	40040	40040	40040	40040
160024	40039	300	0	0	46	25	160010	10	160000	10	160000	50	1280000	0	1	0	40020	40039	40039	19996	3	20019	160010	20	160000	20	320000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10022	3	1	1	10	16	2	1	1	10	7	40036	15	5	5	160000	10	40040	40040	40040	40040	40040
160024	40039	300	0	0	46	25	160010	10	160000	10	160000	50	1280000	1	1	0	40020	40039	40039	19996	3	20019	160010	20	160000	20	320000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10022	3	1	1	10	16	2	1	1	10	12	40036	15	5	8	160000	10	40040	40040	40040	40040	40040

SSRA (vector, 16B)

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