Firestorm: SRI (vector, 4H) measurements

Code:

  sri v0.4h, v1.4h, #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	19	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)	ac	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	f5	f6	f7	f8	fd
1004	2037	15	0	0	61	1687	25	1000	1000	1000	264680	1	2018	2037	2037	1572	3	1895	1000	1000	2000	2037	2037	1	1	1001	1000	0	0	73	4	16	1	1	1787	1000	2038	2038	2038	2038	2038
1004	2037	15	0	0	61	1687	25	1000	1000	1000	264680	1	2018	2037	2037	1572	3	1895	1000	1000	2000	2037	2037	1	1	1001	1000	0	0	73	1	16	1	1	1787	1000	2038	2038	2038	2038	2038
1004	2037	15	0	0	61	1687	25	1000	1000	1000	264680	1	2018	2037	2037	1572	3	1895	1000	1000	2000	2037	2037	1	1	1001	1000	0	0	73	1	16	1	1	1787	1000	2038	2038	2038	2038	2038
1004	2037	15	0	0	82	1687	25	1000	1000	1000	264680	1	2018	2037	2037	1572	3	1895	1000	1000	2000	2037	2037	1	1	1001	1000	0	0	73	1	16	1	1	1787	1000	2038	2038	2038	2038	2038
1004	2037	15	0	0	61	1687	25	1000	1000	1000	264680	1	2018	2037	2037	1572	3	1895	1000	1000	2000	2037	2037	1	1	1001	1000	0	0	73	1	16	1	1	1787	1000	2038	2038	2038	2038	2038
1004	2037	15	0	0	84	1687	25	1000	1000	1000	264680	1	2018	2037	2037	1572	3	1895	1000	1000	2000	2037	2037	1	1	1001	1000	1	0	73	1	16	1	1	1787	1000	2038	2038	2038	2038	2038
1004	2037	15	0	0	61	1687	25	1000	1000	1000	264680	1	2018	2037	2037	1572	3	1895	1000	1000	2000	2037	2037	1	1	1001	1000	0	0	73	1	16	1	1	1787	1000	2038	2038	2038	2038	2038
1004	2037	15	0	0	61	1687	25	1000	1000	1000	264680	1	2018	2037	2037	1572	3	1895	1000	1000	2000	2037	2037	1	1	1001	1000	0	3	73	2	16	1	1	1787	1000	2038	2038	2038	2038	2038
1004	2037	16	0	0	61	1687	25	1000	1000	1000	264680	1	2018	2037	2037	1572	3	1895	1000	1000	2000	2037	2037	1	1	1001	1000	0	0	73	1	16	1	1	1787	1000	2038	2038	2038	2038	2038
1004	2037	15	0	0	61	1687	25	1000	1000	1000	264680	1	2018	2037	2037	1572	3	1895	1000	1000	2000	2037	2037	1	1	1001	1000	0	0	73	1	16	1	1	1787	1000	2038	2038	2038	2038	2038

Test 2: Latency 1->1

Code:

  sri v0.4h, v1.4h, #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): 2.0037

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

retire uop (01)	cycle (02)	03	mmu table walk data (08)	1e	1f	3f	4e	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	60	69	6d	6e	map stall dispatch (70)	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
10204	20037	149	0	0	0	147	19687	25	10100	100	10000	100	10000	500	2847680	1	20018	20037	20037	18422	3	18745	10100	200	10000	200	20000	20037	20037	1	1	10201	100	99	100	100	10000	100	1	0	710	2	16	1	0	19791	10000	100	20038	20038	20038	20038	20038
10204	20037	150	0	0	0	61	19687	25	10100	100	10000	100	10000	500	2847680	1	20018	20037	20037	18422	3	18745	10100	200	10000	200	20000	20037	20037	1	1	10201	100	99	100	100	10000	100	0	0	710	1	16	1	1	19791	10000	100	20038	20038	20038	20038	20038
10204	20037	150	0	0	0	61	19687	25	10100	100	10000	100	10000	500	2847680	1	20018	20037	20037	18422	3	18745	10100	200	10000	200	20000	20037	20037	1	1	10201	100	99	100	100	10000	100	0	0	710	1	16	1	1	19791	10000	100	20038	20038	20038	20038	20038
10204	20037	150	0	210	0	1231	19687	25	10100	100	10000	100	10000	500	2847680	1	20018	20037	20037	18422	3	18745	10100	200	10000	200	20000	20037	20037	1	1	10201	100	99	100	100	10000	100	0	0	710	1	16	1	1	19791	10000	100	20038	20038	20038	20038	20038
10204	20037	150	0	0	0	61	19687	25	10100	100	10000	100	10000	500	2847680	1	20018	20037	20037	18422	3	18745	10100	200	10000	200	20000	20037	20037	1	1	10201	100	99	100	100	10000	100	0	0	710	2	16	1	1	19791	10000	100	20038	20038	20038	20038	20038
10204	20037	150	0	0	0	1036	19687	25	10100	100	10000	100	10000	500	2847680	1	20018	20037	20037	18422	3	18745	10100	200	10000	200	20000	20037	20037	1	1	10201	100	99	100	100	10000	100	0	0	710	1	16	1	1	19791	10000	100	20038	20038	20038	20038	20038
10204	20037	150	0	0	0	61	19687	25	10100	100	10000	100	10000	500	2847680	1	20018	20037	20037	18422	3	18745	10100	200	10000	200	20000	20037	20037	1	1	10201	100	99	100	100	10000	100	0	0	710	1	16	1	1	19791	10000	100	20038	20038	20038	20038	20038
10204	20037	150	0	0	0	61	19687	25	10100	100	10000	100	10000	500	2847680	1	20018	20037	20037	18422	3	18745	10100	200	10000	200	20000	20037	20037	1	1	10201	100	99	100	100	10000	100	0	0	710	1	16	1	1	19791	10000	100	20038	20038	20038	20038	20038
10204	20037	150	0	0	0	61	19687	25	10100	100	10000	100	10000	500	2847680	1	20018	20037	20037	18422	3	18745	10100	200	10000	200	20000	20037	20037	1	1	10201	100	99	100	100	10000	100	0	0	710	1	16	1	1	19791	10000	100	20038	20038	20038	20038	20038
10204	20037	150	0	0	0	61	19687	25	10100	100	10000	100	10000	500	2847680	1	20018	20037	20037	18422	3	18745	10100	200	10000	200	20000	20037	20037	1	1	10201	100	99	100	100	10000	100	0	0	710	1	16	1	1	19791	10000	100	20038	20038	20038	20038	20038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

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	3f	4e	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	60	69	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d tlb access (a0)	l1d tlb miss (a1)	ld unit uop (a6)	l1d cache writeback (a8)	ac	c2	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? int output thing (e9)	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10024	20037	150	0	0	0	0	0	0	61	19687	25	10010	10	10000	10	10000	50	2847680	1	20018	20037	20037	18444	3	18767	10010	20	10000	20	20000	20037	20037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	640	6	16	3	3	19785	0	10000	10	20038	20038	20038	20038	20038
10024	20037	150	0	0	0	0	0	0	61	19687	25	10010	10	10000	10	10000	50	2847680	1	20018	20037	20037	18444	3	18767	10010	20	10000	20	20000	20037	20037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	640	4	16	3	3	19785	0	10000	10	20038	20038	20038	20038	20038
10024	20037	150	0	0	0	0	0	0	61	19687	25	10010	10	10000	10	10000	50	2847680	1	20018	20037	20037	18444	3	18767	10010	20	10000	20	20000	20037	20037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	640	3	16	3	3	19785	0	10000	10	20038	20038	20038	20038	20038
10024	20037	150	0	0	0	0	0	0	61	19687	25	10010	10	10000	10	10000	50	2847680	1	20018	20037	20037	18444	3	18767	10010	20	10000	20	20000	20037	20037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	640	4	16	3	3	19785	0	10000	10	20038	20038	20038	20038	20038
10024	20037	150	0	0	0	0	0	0	61	19687	25	10010	10	10000	10	10000	50	2847680	1	20018	20037	20037	18444	3	18767	10010	20	10000	20	20000	20037	20037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	640	4	16	3	3	19785	0	10000	10	20038	20038	20038	20038	20038
10024	20037	150	0	0	0	0	0	0	61	19687	25	10010	10	10000	10	10000	50	2847680	1	20018	20037	20037	18444	3	18767	10010	20	10000	20	20000	20037	20037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	640	3	16	3	3	19785	0	10000	10	20038	20038	20038	20038	20038
10024	20037	150	0	0	0	0	0	0	61	19687	25	10010	10	10000	10	10000	50	2847680	1	20018	20037	20037	18444	3	18767	10010	20	10000	20	20000	20037	20037	1	1	10021	10	9	10	10	10000	10	0	0	0	1	0	0	640	3	16	3	3	19785	0	10000	10	20038	20038	20038	20038	20038
10024	20037	150	0	0	0	0	0	0	61	19687	25	10010	10	10000	10	10000	50	2847680	1	20018	20037	20037	18444	3	18767	10010	20	10000	20	20000	20037	20037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	640	3	16	3	3	19785	0	10000	10	20038	20038	20038	20038	20038
10024	20037	150	0	0	0	0	0	0	61	19687	25	10010	10	10000	10	10000	50	2847680	1	20018	20037	20037	18444	3	18767	10010	20	10000	20	20000	20037	20037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	640	3	16	3	3	19785	0	10000	10	20038	20038	20038	20038	20038
10024	20037	150	0	0	0	0	0	0	61	19687	25	10010	10	10000	10	10000	50	2847680	1	20018	20037	20037	18444	3	18767	10010	20	10000	20	20000	20037	20037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	640	3	16	3	3	19785	0	10000	10	20038	20038	20038	20038	20038

Test 3: Latency 1->2

Code:

  sri v0.4h, v0.4h, #3

Initialization

  movi v0.16b, 1

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 2.0037

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)	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	20037	150	0	0	9	0	0	61	19686	25	10100	100	10000	100	10000	500	2847521	1	20018	20037	20037	18409	6	18733	10100	200	10008	200	20016	20037	20037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	0	1	1	1	718	0	16	0	2	19787	0	10000	100	20038	20038	20038	20038	20038
10204	20037	150	0	0	0	0	1	97	19686	25	10100	100	10000	100	10000	500	2847521	0	20018	20037	20037	18409	6	18733	10100	200	10000	200	20000	20037	20037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	0	1	1	1	722	2	24	2	2	19787	0	10000	100	20038	20038	20038	20038	20038
10204	20037	150	0	0	0	0	1	97	19686	25	10100	100	10000	100	10000	500	2847521	0	20018	20037	20037	18409	6	18733	10100	200	10000	200	20000	20037	20037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	0	1	1	1	722	2	24	2	2	19787	0	10000	100	20085	20038	20038	20038	20038
10204	20037	150	0	0	0	0	0	61	19686	25	10100	100	10000	100	10000	500	2847521	0	20018	20037	20037	18428	7	18741	10100	200	10008	200	20016	20037	20037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	0	1	1	1	722	2	24	2	2	19787	0	10000	100	20038	20038	20062	20038	20038
10204	20037	150	0	0	42	0	0	61	19686	25	10100	100	10000	100	10000	500	2847521	0	20018	20037	20037	18428	7	18740	10100	200	10008	200	20016	20037	20037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	0	1	1	1	717	0	16	0	0	19801	0	10000	100	20038	20038	20038	20038	20038
10204	20037	150	0	0	0	0	0	61	19686	25	10100	100	10000	100	10000	500	2847521	1	20018	20037	20037	18428	6	18740	10100	200	10008	200	20016	20037	20037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	0	1	1	1	718	0	16	0	0	19801	0	10000	100	20038	20038	20038	20038	20038
10204	20037	150	0	0	48	0	0	61	19686	25	10100	100	10000	100	10000	500	2847521	1	20018	20037	20037	18428	7	18741	10100	200	10008	200	20016	20037	20037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	0	1	1	1	718	0	16	0	0	19800	0	10000	100	20038	20038	20038	20038	20038
10204	20037	150	0	0	30	0	0	61	19686	25	10100	100	10000	100	10000	500	2847521	0	20018	20037	20037	18428	6	18740	10100	200	10008	200	20016	20037	20037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	0	1	1	1	718	0	16	0	0	19800	0	10000	100	20038	20038	20038	20038	20038
10204	20037	150	0	0	537	0	0	61	19686	25	10100	100	10000	100	10000	500	2847521	1	20018	20037	20037	18428	7	18741	10100	200	10008	200	20016	20037	20037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	0	1	1	1	718	0	16	0	0	19800	0	10000	100	20038	20038	20038	20038	20038
10204	20037	150	0	0	0	0	0	61	19686	25	10100	100	10000	100	10000	500	2847521	0	20018	20037	20037	18428	6	18740	10100	200	10008	200	20016	20037	20037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	0	1	1	1	717	0	16	0	0	19801	0	10000	100	20038	20038	20038	20038	20038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

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

retire uop (01)	cycle (02)	03	l2 tlb miss data (0b)	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	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d tlb access (a0)	l1d tlb miss (a1)	ld unit uop (a6)	l1d cache writeback (a8)	a9	ac	c2	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	20037	150	0	6	6	936	616	3004	19609	159	10096	12	10048	10	11064	72	2855105	0	20126	20356	20370	18464	34	18895	11076	22	11213	24	22000	20368	20368	7	1	10021	10	9	10	10	10000	10	0	0	0	0	2	14230	0	789	5	81	4	4	19964	1	10000	10	20276	20134	20274	20273	20324
10024	20228	152	0	0	0	0	0	61	19686	25	10010	10	10000	10	10000	50	2847521	1	20018	20037	20274	18458	24	18839	10010	20	10614	22	21344	20225	20085	5	1	10021	10	9	10	10	10000	10	0	0	0	0	2	9940	4	640	3	16	3	3	19786	0	10000	10	20038	20038	20038	20038	20038
10024	20084	150	0	2	5	267	440	1926	19631	142	10072	10	10072	10	10760	50	2855105	1	20018	20037	20037	18443	3	18767	10010	20	10000	20	20000	20037	20037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	2	8070	0	749	4	72	5	3	19967	2	10000	10	20181	20274	20227	20323	20038
10024	20037	150	0	0	0	0	0	61	19686	25	10010	10	10000	10	10456	50	2852577	1	20198	20274	20037	18459	29	18859	10771	24	10831	22	21672	20273	20037	6	1	10021	10	9	10	10	10000	10	2	0	0	0	0	0	0	640	3	16	3	3	19786	0	10000	10	20182	20181	20275	20227	20274
10024	20274	150	1	5	3	660	0	61	19686	25	10010	10	10000	10	10000	50	2847521	1	20018	20037	20037	18443	3	18767	10010	20	10000	20	20000	20037	20037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	0	640	3	16	3	3	19786	0	10000	10	20038	20038	20038	20038	20038
10024	20037	150	0	0	0	573	104	61	19686	25	10010	10	10000	10	10000	50	2847521	1	20018	20037	20037	18443	3	18767	10010	20	10000	20	20000	20037	20037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	0	640	3	16	3	3	19786	0	10000	10	20038	20038	20038	20038	20038
10024	20037	150	0	0	0	0	0	61	19686	25	10010	10	10000	10	10000	50	2847521	1	20018	20037	20037	18443	3	18767	10010	20	10000	20	20000	20037	20037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	0	640	3	16	3	3	19786	0	10000	10	20038	20038	20038	20038	20038
10024	20037	150	0	0	0	0	0	61	19686	25	10010	10	10000	10	10000	50	2847521	1	20018	20037	20083	18443	3	18767	10010	20	10000	20	20000	20037	20227	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	0	640	3	16	3	3	19786	0	10000	10	20038	20038	20038	20038	20038
10024	20037	150	0	0	0	0	0	742	19686	25	10010	10	10000	10	10000	50	2847521	1	20065	20037	20037	18443	3	18767	10010	20	10000	20	20000	20037	20037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	0	640	3	16	3	3	19786	0	10000	10	20038	20038	20038	20038	20038
10024	20037	150	0	0	0	0	0	61	19686	25	10010	10	10000	10	10000	50	2847521	1	20018	20037	20037	18443	3	18767	10010	20	10000	20	20000	20037	20037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	0	640	3	16	3	3	19786	0	10000	10	20038	20038	20038	20038	20038

Test 4: throughput

Count: 8

Code:

  movi v0.16b, 0
  sri v0.4h, v8.4h, #3
  movi v1.16b, 0
  sri v1.4h, v8.4h, #3
  movi v2.16b, 0
  sri v2.4h, v8.4h, #3
  movi v3.16b, 0
  sri v3.4h, v8.4h, #3
  movi v4.16b, 0
  sri v4.4h, v8.4h, #3
  movi v5.16b, 0
  sri v5.4h, v8.4h, #3
  movi v6.16b, 0
  sri v6.4h, v8.4h, #3
  movi v7.16b, 0
  sri v7.4h, v8.4h, #3

Initialization

  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2509

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

retire uop (01)	cycle (02)	03	mmu table walk data (08)	09	l2 tlb miss data (0b)	18	19	1e	1f	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)	l1d tlb miss (a1)	ld unit uop (a6)	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)	eb	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
160204	20089	150	0	0	0	2	0	15	0	29	25	80116	100	80016	100	80028	500	640196	0	20044	20065	20065	6	12	80128	200	80028	200	160056	20065	20065	1	1	160201	100	99	100	100	160000	100	2	0	0	0	0	0	0	1	1	1	10119	0	16	0	0	20062	0	0	160000	100	20066	20066	20066	20066	20066
160204	20065	151	0	0	0	0	0	3	0	29	25	80116	100	80016	100	80028	500	640196	0	20044	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	0	0	1	1	1	10119	0	16	0	0	20062	0	0	160000	100	20066	20066	20066	20066	20066
160204	20065	151	0	0	0	0	0	0	0	29	25	80116	100	80016	100	80028	500	640196	0	20044	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	0	0	1	1	1	10119	0	16	0	0	20062	0	0	160000	100	20066	20066	20066	20066	20066
160204	20065	150	0	0	0	0	0	0	0	29	25	80116	100	80016	100	80028	500	640196	0	20044	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	0	0	1	1	1	10119	0	16	0	0	20062	0	0	160000	100	20066	20066	20066	20066	20066
160204	20065	150	0	0	0	0	0	0	0	29	25	80116	100	80016	100	80028	500	640196	0	20044	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	0	0	1	1	1	10119	0	16	0	0	20062	0	0	160000	100	20066	20066	20066	20066	20066
160204	20065	150	0	0	0	0	0	0	0	29	25	80116	100	80016	100	80028	500	640196	0	20044	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	0	0	1	1	1	10119	0	16	0	0	20062	0	0	160000	100	20066	20066	20066	20066	20066
160204	20065	150	0	0	0	0	0	0	0	29	25	80116	100	80016	100	80028	500	640196	0	20044	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	0	0	1	1	1	10119	0	16	0	0	20062	0	0	160000	100	20066	20066	20066	20066	20066
160204	20065	150	0	0	0	0	0	0	0	29	25	80116	100	80016	100	80028	500	640196	0	20044	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	0	0	1	1	1	10119	0	16	0	0	20062	0	0	160000	100	20066	20066	20066	20066	20066
160204	20065	150	0	0	0	0	0	0	0	29	25	80116	100	80016	100	80028	500	640196	0	20044	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	0	0	1	1	1	10119	0	16	0	0	20062	0	0	160000	100	20066	20066	20066	20066	20066
160204	20065	150	0	0	0	0	0	0	0	29	25	80116	100	80016	100	80028	500	640196	0	20044	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	0	0	1	1	1	10119	0	16	0	0	20062	0	0	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	19	1e	3f	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	5f	60	69	6d	6e	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d tlb access (a0)	l1d cache writeback (a8)	ac	branch mispred nonspec (cb)	cf	d0	d2	l1i cache miss demand (d3)	d5	map dispatch bubble (d6)	d9	da	db	dd	fetch restart (de)	e0	? int output thing (e9)	ea	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
160024	20065	150	0	0	44	25	80010	10	80000	10	80000	50	640000	1	1	20026	20045	20045	3	21	80010	20	80000	20	160000	20045	20045	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10028	3	1	1	4	20	2	1	1	4	4	20042	0	15	160000	10	20046	20046	20046	20046	20046
160024	20045	150	0	0	44	25	80010	10	80000	10	80000	50	640000	1	1	20026	20045	20045	3	21	80010	20	80000	20	160000	20045	20045	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10029	3	1	1	4	24	2	1	1	3	4	20046	0	15	160000	10	20046	20046	20046	20046	20046
160024	20045	150	0	42	44	25	80010	10	80000	10	80000	50	640000	1	1	20026	20045	20045	3	21	80010	20	80000	20	160000	20045	20045	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10027	3	1	1	4	20	2	1	1	4	3	20123	0	15	160000	10	20046	20046	20046	20046	20046
160024	20045	150	0	0	44	25	80010	10	80000	10	80000	50	640000	1	1	20026	20045	20045	3	21	80010	20	80000	20	160000	20045	20045	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10027	3	1	1	4	20	2	1	1	2	3	20042	0	30	160000	10	20046	20046	20046	20046	20046
160024	20045	150	0	0	44	25	80111	10	80000	10	80000	50	640000	1	1	20026	20049	20049	3	21	80010	20	80000	20	160000	20049	20049	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10027	3	1	1	5	20	2	1	1	4	4	20042	0	15	160000	10	20046	20046	20046	20046	20046
160024	20045	150	0	0	50	25	80010	10	80000	10	80000	50	640000	1	1	20026	20045	20045	3	21	80010	20	80000	20	160000	20045	20045	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10031	3	1	1	6	20	2	1	1	8	7	20042	0	15	160000	10	20046	20114	20046	20046	20046
160024	20045	150	0	0	44	25	80010	10	80000	10	80000	50	640000	1	1	20030	20049	20045	3	21	80010	20	80000	20	160000	20049	20049	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10030	3	2	2	3	24	4	2	2	3	3	20042	0	30	160000	10	20050	20050	20050	20050	20046
160024	20049	150	0	0	50	25	80010	10	80000	10	80000	50	640000	0	1	20030	20045	20049	3	21	80010	20	80000	20	160000	20045	20045	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10026	3	1	1	3	20	2	1	1	4	4	20042	0	15	160000	10	20046	20046	20046	20046	20046
160024	20045	150	0	0	44	25	80010	10	80000	10	80000	50	640000	1	1	20026	20045	20045	3	21	80010	20	80000	20	160000	20045	20045	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10027	3	1	1	4	20	2	1	1	5	3	20042	0	15	160000	10	20046	20046	20046	20046	20046
160024	20045	150	0	0	44	25	80010	10	80000	10	80000	50	640000	1	1	20026	20045	20045	3	21	80010	20	80000	20	160000	20049	20045	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10026	3	1	1	4	20	2	1	1	4	4	20042	0	15	160000	10	20046	20046	20046	20046	20046

Test 5: throughput

Count: 16

Code:

  sri v0.4h, v16.4h, #3
  sri v1.4h, v16.4h, #3
  sri v2.4h, v16.4h, #3
  sri v3.4h, v16.4h, #3
  sri v4.4h, v16.4h, #3
  sri v5.4h, v16.4h, #3
  sri v6.4h, v16.4h, #3
  sri v7.4h, v16.4h, #3
  sri v8.4h, v16.4h, #3
  sri v9.4h, v16.4h, #3
  sri v10.4h, v16.4h, #3
  sri v11.4h, v16.4h, #3
  sri v12.4h, v16.4h, #3
  sri v13.4h, v16.4h, #3
  sri v14.4h, v16.4h, #3
  sri v15.4h, v16.4h, #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	3f	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	5f	60	69	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d cache writeback (a8)	ac	branch cond mispred nonspec (c5)	branch mispred nonspec (cb)	cd	cf	d5	map dispatch bubble (d6)	db	dd	fetch restart (de)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
160204	40061	300	29	25	160108	100	160008	100	160020	500	1280132	0	1	40019	40038	40038	19977	6	19989	160120	200	160032	200	320064	40038	40038	1	1	160201	100	99	100	100	160000	100	0	0	1	1	1	10118	2	16	0	1	2	40035	160000	100	40039	40039	40039	40039	40039
160204	40038	300	29	25	160108	100	160008	100	160020	500	1280132	0	1	40019	40038	40038	19977	6	19989	160120	200	160032	200	320064	40038	40038	1	1	160201	100	99	100	100	160000	100	1	3	1	1	1	10118	2	16	0	2	2	40035	160000	100	40039	40039	40092	40039	40039
160204	40038	300	29	25	160108	100	160008	100	160020	500	1280132	0	0	40019	40038	40038	19977	6	19989	160120	200	160032	200	320064	40038	40038	1	1	160201	100	99	100	100	160000	100	0	0	1	1	1	10118	2	16	0	1	2	40035	160000	100	40039	40039	40039	40039	40039
160204	40038	300	29	25	160108	100	160008	100	160020	500	1280132	0	1	40019	40038	40038	19977	6	19989	160120	200	160032	200	320064	40038	40038	1	1	160201	100	99	100	100	160000	100	1	0	1	1	1	10118	2	16	1	2	2	40035	160000	100	40039	40039	40039	40039	40039
160204	40038	300	794	25	160108	100	160008	100	160020	500	1280132	0	0	40019	40038	40038	19977	6	19989	160120	200	160032	200	320064	40038	40038	1	1	160201	100	99	100	100	160000	100	0	0	1	1	1	10118	2	16	0	2	2	40035	160000	100	40039	40039	40039	40039	40039
160204	40038	300	219	25	160108	100	160008	100	160020	500	1280132	0	0	40019	40038	40038	19977	6	19989	160120	200	160032	200	320064	40038	40038	1	1	160201	100	99	100	100	160000	100	0	0	1	1	1	10118	2	16	0	2	2	40035	160000	100	40039	40039	40039	40039	40039
160204	40038	300	29	25	160108	100	160008	100	160020	500	1280132	0	0	40019	40038	40038	19977	6	19989	160120	200	160032	200	320064	40038	40038	1	1	160201	100	99	100	100	160000	100	0	0	1	1	1	10118	1	16	0	2	2	40035	160000	100	40039	40039	40090	40039	40039
160204	40038	300	29	25	160108	100	160008	100	160020	500	1280132	0	0	40019	40038	40038	19977	6	19989	160120	200	160032	200	320064	40038	40038	1	1	160201	100	99	100	100	160000	100	0	0	1	1	1	10118	2	16	0	2	3	40035	160000	100	40039	40039	40039	40039	40039
160204	40038	300	29	25	160108	100	160008	100	160020	500	1280132	0	1	40019	40038	40038	19977	6	19989	160120	200	160032	200	320064	40038	40038	1	1	160201	100	99	100	100	160000	100	2	0	1	1	1	10118	1	17	0	2	2	40035	160000	100	40039	40039	40039	40039	40039
160204	40038	300	29	25	160108	100	160008	100	160020	500	1280132	0	0	40019	40038	40038	19977	6	19989	160120	200	160032	200	320064	40038	40038	1	1	160201	100	99	100	100	160000	100	0	0	1	1	1	10118	2	16	0	2	2	40035	160000	100	40039	40039	40039	40039	40039

1000 unrolls and 10 iterations

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

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

retire uop (01)	cycle (02)	03	l1i tlb fill (04)	18	1e	1f	3a	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 stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	st unit uop (a7)	l1d cache writeback (a8)	ac	cf	d0	d2	l1i cache miss demand (d3)	l1i tlb miss demand (d4)	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	40050	300	1	0	111	0	0	53	25	160010	10	160000	10	160000	50	1280000	1	5	40019	40038	40038	19996	3	20018	160010	20	160000	20	320000	40038	40038	1	1	160021	10	9	10	10	160000	10	0	0	0	10022	8	2	1	0	32	16	2	1	1	23	29	40035	15	5	160000	10	40039	40039	40039	40039	40039
160024	40038	300	0	0	0	0	0	51	25	160010	10	160000	10	160000	50	1280000	1	5	40019	40038	40038	19996	3	20018	160010	20	160000	20	320000	40038	40038	1	1	160021	10	9	10	10	160000	10	0	0	0	10026	11	6	2	1	31	16	3	2	2	31	31	40035	31	10	160000	10	40039	40039	40039	40039	40039
160024	40038	300	1	0	3	0	1	78	25	160196	10	160000	10	160000	50	1280000	1	5	40019	40038	40243	19996	3	20018	160010	20	160000	20	320000	40038	40038	1	1	160021	10	9	10	10	160000	10	0	0	0	10025	11	6	2	1	31	16	3	2	2	30	31	40035	31	10	160000	10	40039	40039	40039	40039	40039
160024	40038	300	1	0	0	0	0	57	25	160010	10	160000	10	160000	50	1280000	1	5	40019	40038	40038	19996	3	20018	160010	20	160000	20	320000	40038	40038	1	1	160021	10	9	10	10	160000	10	0	0	0	10026	11	6	2	1	29	16	3	2	2	18	30	40035	31	10	160000	10	40039	40039	40039	40039	40039
160024	40038	300	1	0	0	0	1	57	25	160010	10	160000	10	160000	50	1280000	1	5	40019	40038	40038	19996	3	20018	160010	20	160000	20	320000	40038	40038	1	1	160021	10	9	10	10	160000	10	0	0	0	10026	11	6	2	1	15	16	3	2	2	28	15	40035	31	10	160000	10	40245	40039	40039	40039	40039
160024	40038	300	1	0	0	0	0	57	25	160010	10	160000	10	160000	50	1280000	1	5	40019	40038	40038	19996	3	20018	160010	20	160000	20	320000	40038	40038	1	1	160021	10	9	10	10	160000	10	0	0	0	10025	11	6	2	1	29	16	3	2	2	17	29	40035	31	10	160000	10	40039	40039	40039	40039	40039
160024	40038	299	1	0	0	0	1	57	25	160010	10	160000	10	160000	50	1280764	1	5	40019	40038	40038	20001	3	20018	160010	20	160000	20	320000	40038	40038	1	1	160021	10	9	10	10	160000	10	0	0	6	10077	11	6	2	1	25	16	3	2	2	29	29	40035	31	10	160000	10	40039	40039	40039	40039	40237
160024	40038	300	1	0	0	0	0	51	25	160010	10	160000	10	160000	50	1280000	1	5	40019	40038	40038	19996	3	20018	160010	20	160000	20	320000	40038	40038	1	1	160021	10	9	10	10	160000	10	0	0	0	10025	11	6	2	1	18	16	3	2	2	31	31	40035	31	10	160000	10	40039	40039	40039	40039	40039
160024	40038	300	1	0	0	0	0	57	25	160010	10	160000	10	160000	50	1280000	1	5	40019	40038	40038	19996	3	20018	160010	20	160000	20	320782	40038	40038	1	1	160021	10	9	10	10	160000	10	0	0	0	10025	11	6	2	1	31	16	3	2	2	29	29	40035	31	10	160000	10	40039	40039	40039	40039	40039
160024	40038	300	1	0	0	0	1	51	25	160010	10	160000	10	160000	50	1280000	1	5	40019	40038	40038	19996	21	20018	160010	20	160000	20	320000	40038	40038	1	1	160021	10	9	10	10	160000	10	0	0	0	10026	11	6	2	1	17	16	3	2	2	29	23	40035	31	10	160000	10	40039	40039	40039	40039	40243

SRI (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