Firestorm: USRA (vector, 2D) measurements

Code:

  usra v0.2d, v1.2d, #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	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)	ld unit uop (a6)	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	103	2548	25	1000	1000	1000	398313	0	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	0	61	2548	25	1000	1000	1000	398313	1	3018	3037	3037	2415	3	2895	1000	1000	2000	3037	3037	1	1	1001	1000	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3074
1004	3037	24	0	61	2548	25	1000	1000	1000	398313	1	3018	3037	3037	2415	3	2915	1000	1000	2000	3037	3037	1	1	1001	1000	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3074	3038
1004	3037	24	0	61	2548	25	1000	1000	1149	398313	0	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	0	103	2548	25	1000	1000	1000	398313	0	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	24	0	61	2548	25	1000	1000	1000	398313	1	3018	3037	3037	2415	3	2895	1000	1000	2000	3037	3037	1	1	1001	1000	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	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	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	24	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	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	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	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	24	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	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038

Test 2: Latency 1->1

Code:

  usra v0.2d, v1.2d, #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	l2 tlb miss instruction (0a)	1e	3f	4e	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	60	69	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d tlb miss (a1)	l1d cache writeback (a8)	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	233	2	45	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	4	0	0	710	2	16	2	2	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	233	2	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	710	2	16	2	2	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	233	2	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	710	2	16	2	2	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	233	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	710	2	16	2	2	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	233	2	6	536	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	710	2	16	2	2	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	233	0	6	61	29548	25	10100	100	10000	100	10000	500	4277313	0	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	710	2	16	2	2	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	232	2	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	710	2	16	2	2	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	232	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	710	2	16	2	2	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	233	2	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	710	2	16	2	2	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	232	2	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	710	2	16	2	2	29634	0	10000	100	30038	30038	30038	30038	30038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

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

retire uop (01)	cycle (02)	03	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)	5e	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)	91	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d tlb access (a0)	ld unit uop (a6)	l1d cache writeback (a8)	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
10024	30037	233	0	0	0	0	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	0	0	30018	30037	30037	28287	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	0	10	10	10000	10	0	0	0	0	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	232	0	0	0	0	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	0	0	30018	30037	30037	28287	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	0	10	10	10000	10	0	0	0	0	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	233	0	0	0	0	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	0	1	30018	30037	30037	28287	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	0	10	10	10000	10	0	0	0	0	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	232	0	0	0	0	0	0	82	29548	25	10010	10	10000	10	10000	50	4277313	0	1	30018	30037	30037	28287	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	0	10	10	10000	10	0	0	0	0	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	232	0	0	0	0	0	0	89	29548	25	10010	10	10000	10	10000	50	4277313	0	1	30018	30037	30037	28287	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	0	10	10	10000	10	0	0	0	3	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	233	0	0	0	0	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	0	0	30018	30037	30037	28287	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	0	10	10	10000	10	0	0	0	0	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	233	0	0	0	0	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	0	1	30018	30037	30037	28287	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	0	10	10	10000	10	0	0	0	0	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	232	0	0	0	0	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	0	1	30018	30037	30037	28287	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	0	10	10	10000	10	0	0	1	0	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	233	0	0	0	0	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	1	1	30018	30037	30037	28287	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	0	10	10	10000	10	0	0	1	0	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	232	0	0	0	0	0	0	536	29548	25	10010	10	10000	10	10000	50	4277313	0	0	30018	30037	30037	28287	3	28767	10010	22	10000	20	20000	30037	30037	1	1	10021	10	9	0	10	10	10000	10	0	0	0	0	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038

Test 3: Latency 1->2

Code:

  usra v0.2d, v0.2d, #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	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 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	233	0	0	1	97	29547	25	10100	100	10000	100	10000	500	4277160	0	30018	30037	30037	28252	6	28733	10100	200	10000	200	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	64	0	1	1	1	722	2	24	2	2	29629	10000	100	30038	30038	30038	30038	30038
10204	30037	233	0	0	1	97	29547	25	10100	100	10000	100	10000	500	4277160	0	30018	30037	30037	28252	6	28733	10100	200	10000	200	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	1	1	1	722	2	24	2	2	29629	10000	100	30038	30038	30038	30038	30038
10204	30037	232	0	0	1	97	29547	25	10100	100	10032	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	3	3	1	1	1	717	0	16	0	0	29646	10000	100	30038	30038	30038	30038	30038
10204	30037	233	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	0	1	1	1	718	0	16	0	0	29645	10000	100	30038	30038	30038	30038	30038
10204	30037	233	0	0	0	61	29547	25	10100	100	10000	100	10000	500	4277160	0	30018	30037	30037	28271	7	28740	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	233	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	1	0	1	1	1	717	0	16	0	0	29645	10000	100	30038	30038	30038	30038	30038
10204	30037	233	0	0	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	0	1	1	1	717	0	16	0	0	29646	10000	100	30038	30038	30038	30038	30038
10204	30037	233	0	0	0	61	29547	25	10100	113	10000	100	10000	522	4277160	0	30018	30037	30037	28271	6	28741	10100	200	10008	200	20016	30037	30037	1	1	10201	100	99	100	100	10000	100	6	3	1	1	1	718	0	16	0	0	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	37	0	1	1	1	718	0	16	0	0	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	28741	10100	200	10008	200	20016	30037	30037	1	1	10201	100	99	100	100	10000	100	23	0	1	1	1	717	4	24	2	2	29629	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	mmu table walk instruction (07)	mmu table walk data (08)	l2 tlb miss instruction (0a)	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	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 cache writeback (a8)	ac	c2	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10024	30358	235	3	1	1	8	8	942	704	3	3957	29493	153	10066	12	10056	12	10900	61	4286624	1	30270	0	30369	30361	28313	31	28898	10913	20	11147	22	21982	30367	30371	7	1	10021	10	9	10	10	10000	10	0	19545	2	793	16	73	15	14	29883	10000	10	30038	30038	30038	30038	30038
10024	30037	233	1	0	1	0	0	15	0	2	69	29547	25	10010	10	10000	10	10000	50	4277160	1	30018	0	30037	30037	28286	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	644	10	16	10	10	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	233	1	0	1	0	0	0	0	2	68	29547	25	10010	10	10000	10	10000	50	4277160	1	30018	0	30037	30037	28286	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	644	10	16	10	11	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	233	1	0	1	0	0	0	0	2	68	29547	25	10010	10	10000	10	10000	50	4277160	0	30018	0	30037	30037	28286	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	644	10	16	10	10	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	232	1	0	1	0	0	0	0	2	1001	29547	25	10010	10	10000	10	10000	50	4277160	0	30018	0	30037	30037	28286	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	644	10	16	11	10	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	233	1	0	1	0	0	12	0	2	68	29547	25	10010	10	10000	10	10000	50	4277160	1	30018	0	30037	30037	28286	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	644	10	16	10	5	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	232	1	0	1	0	0	0	0	2	68	29547	25	10010	10	10000	10	10000	50	4277160	1	30018	0	30228	30037	28286	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	644	11	16	11	10	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	233	1	0	1	0	0	0	0	2	68	29547	25	10010	10	10000	10	10000	50	4277160	1	30018	0	30037	30037	28286	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	6	0	644	10	16	10	10	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	233	1	0	1	0	0	0	0	2	68	29547	25	10010	10	10000	10	10000	50	4277160	0	30018	0	30037	30037	28286	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	644	10	16	10	10	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	232	1	0	1	0	0	0	0	2	89	29547	25	10010	10	10000	10	10000	50	4277160	0	30018	0	30037	30037	28286	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	644	10	16	10	10	29629	10000	10	30038	30038	30038	30038	30038

Test 4: throughput

Count: 8

Code:

  movi v0.16b, 0
  usra v0.2d, v8.2d, #3
  movi v1.16b, 0
  usra v1.2d, v8.2d, #3
  movi v2.16b, 0
  usra v2.2d, v8.2d, #3
  movi v3.16b, 0
  usra v3.2d, v8.2d, #3
  movi v4.16b, 0
  usra v4.2d, v8.2d, #3
  movi v5.16b, 0
  usra v5.2d, v8.2d, #3
  movi v6.16b, 0
  usra v6.2d, v8.2d, #3
  movi v7.16b, 0
  usra v7.2d, v8.2d, #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	l2 tlb miss data (0b)	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	rob full (74)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d cache writeback (a8)	ac	branch cond mispred nonspec (c5)	branch mispred nonspec (cb)	cd	cf	d0	d2	l1i cache miss demand (d3)	d5	map dispatch bubble (d6)	d9	db	dd	fetch restart (de)	e0	ea	ec	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
160204	20091	155	0	0	29	25	80116	100	80016	100	80028	500	640196	0	0	20045	20065	20065	0	6	12	80128	200	80028	200	160056	20065	20065	1	1	160201	100	99	100	100	160000	100	1	0	1	1	1	10122	0	0	0	2	16	0	0	3	3	20062	0	0	160000	100	20066	20066	20066	20066	20066
160204	20065	156	0	0	29	25	80116	100	80016	100	80028	500	640196	0	0	20045	20065	20065	0	6	12	80128	200	80028	200	160056	20065	20065	1	1	160201	100	99	100	100	160000	100	0	0	1	1	1	10123	0	0	0	3	16	0	0	4	4	20062	0	0	160000	100	20066	20066	20066	20066	20066
160204	20065	155	0	0	29	25	80116	100	80016	100	80028	500	640196	0	0	20045	20065	20065	0	6	12	80128	200	80028	200	160056	20065	20065	1	1	160201	100	99	100	100	160000	100	0	0	1	1	1	10122	0	0	0	3	16	0	0	4	3	20062	0	0	160000	100	20066	20066	20066	20066	20066
160204	20065	155	0	0	29	25	80116	100	80016	100	80028	500	640196	0	0	20045	20065	20065	0	6	12	80128	200	80028	200	160056	20065	20065	1	1	160201	100	99	100	100	160000	100	0	3	1	1	1	10123	0	0	0	3	16	0	0	3	4	20062	0	0	160000	100	20066	20066	20066	20066	20066
160204	20065	155	0	0	29	161	80116	100	80016	100	80028	500	640196	0	0	20045	20065	20065	0	6	12	80128	200	80028	200	160056	20065	20065	1	1	160201	100	99	100	100	160000	100	0	0	1	1	1	10122	0	0	0	3	16	0	0	3	3	20062	0	0	160000	100	20066	20066	20066	20066	20066
160204	20065	155	0	0	29	25	80116	100	80016	100	80028	500	640196	0	0	20045	20065	20065	0	6	12	80128	200	80028	200	160056	20065	20065	1	1	160201	100	99	100	100	160000	100	0	0	1	1	1	10122	0	0	0	2	16	0	0	3	4	20062	0	0	160000	100	20066	20066	20066	20066	20066
160204	20065	156	0	0	29	25	80116	100	80016	100	80028	500	640196	0	0	20045	20065	20065	0	6	12	80128	200	80028	200	160056	20065	20065	1	1	160201	100	99	100	100	160000	100	1	0	1	1	1	10122	0	0	0	4	16	0	0	5	4	20129	0	0	160000	100	20066	20066	20066	20066	20066
160204	20065	155	0	12	29	25	80116	100	80016	100	80028	500	640196	0	0	20045	20065	20065	0	6	12	80128	200	80028	200	160056	20065	20065	1	1	160201	100	99	100	100	160000	100	0	0	1	1	1	10122	0	0	0	3	16	0	0	3	3	20062	0	0	160000	100	20066	20066	20066	20066	20066
160204	20065	156	1	0	29	25	80116	100	80016	100	80028	500	640196	0	0	20045	20065	20065	0	6	12	80128	200	80028	200	160056	20065	20065	1	1	160201	100	99	100	100	160000	100	0	0	1	1	1	10122	0	0	0	4	16	0	0	4	4	20062	0	0	160000	100	20066	20066	20066	20066	20066
160204	20065	155	0	0	29	25	80116	100	80016	100	80028	500	640196	0	0	20045	20065	20065	0	6	12	80128	200	80028	200	160056	20065	20065	1	1	160201	100	99	100	100	160000	100	0	0	1	1	1	10122	0	0	0	4	16	0	0	3	4	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	mmu table walk data (08)	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)	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)	ld unit uop (a6)	l1d cache writeback (a8)	a9	ac	c2	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	20062	156	0	0	0	0	45	25	80010	10	80000	10	80000	50	640000	1	1	1	20027	20046	20046	3	22	80010	20	80000	20	160000	20046	20046	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	0	10042	4	1	1	25	20	2	1	1	17	18	20043	15	0	160000	10	20047	20047	20047	20047	20047
160024	20046	155	0	0	0	0	87	25	80010	10	80000	10	80000	50	640000	0	1	1	20031	20050	20050	3	22	80010	20	80000	20	160000	20050	20050	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	0	10039	4	1	1	13	20	2	1	1	18	19	20043	15	0	160000	10	20053	20051	20051	20051	20051
160024	20050	155	0	0	0	0	51	25	80010	10	80000	10	80000	50	640000	1	1	1	20027	20046	20046	3	22	80010	20	80000	20	160000	20046	20046	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	0	10044	4	1	1	19	20	2	1	1	21	14	20043	15	0	160000	10	20047	20047	20047	20047	20047
160024	20050	156	0	0	0	0	45	25	80010	10	80000	10	80000	50	640000	1	1	1	20027	20046	20046	3	22	80010	20	80000	20	160000	20046	20046	1	1	160021	10	9	10	10	160000	10	0	0	1	0	0	0	10044	7	2	2	18	26	4	2	2	20	20	20047	30	0	160000	10	20047	20047	20047	20047	20047
160024	20050	155	0	0	0	0	621	25	80010	10	80000	10	80000	50	640000	0	1	1	20031	20050	20050	3	22	80010	20	80000	20	160000	20050	20054	1	1	160021	10	9	10	10	160000	10	0	0	1	0	0	0	10040	4	1	1	18	20	2	1	1	22	18	20043	15	0	160000	10	20047	20047	20047	20047	20047
160024	20046	156	0	0	0	0	51	25	80010	10	80000	10	80000	50	640000	1	1	1	20027	20046	20046	3	22	80010	20	80000	20	160000	20046	20046	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	0	10041	4	1	1	13	20	2	1	1	18	20	20043	30	0	160000	10	20051	20051	20051	20051	20051
160024	20050	155	0	0	0	0	51	25	80010	10	80000	10	80000	50	640000	1	1	1	20027	20046	20046	3	22	80010	20	80000	20	160000	20046	20046	1	1	160021	10	9	10	10	160000	10	0	0	1	0	0	0	10044	7	1	2	20	24	4	2	2	18	18	20047	15	0	160000	10	20051	20051	20051	20051	20051
160024	20050	155	0	0	0	0	632	25	80010	10	80000	10	80000	50	640000	0	1	1	20031	20050	20050	3	22	80010	20	80000	20	160000	20050	20046	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	0	10036	7	2	1	19	24	4	2	2	14	19	20047	15	0	160000	10	20051	20051	20051	20052	20051
160024	20050	155	0	0	0	0	51	25	80010	10	80000	10	80000	50	640000	0	1	1	20031	20050	20046	3	22	80010	20	80000	20	160000	20050	20050	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	0	10045	7	2	2	17	20	4	2	2	17	17	20047	30	0	160000	10	20051	20053	20051	20051	20051
160024	20046	155	0	0	0	0	45	25	80010	10	80000	10	80000	50	640000	0	1	1	20027	20050	20046	3	22	80010	20	80000	20	160000	20050	20050	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	0	10043	7	2	2	20	24	4	2	2	17	19	20050	30	0	160000	10	20051	20051	20051	20047	20051

Test 5: throughput

Count: 16

Code:

  usra v0.2d, v16.2d, #3
  usra v1.2d, v16.2d, #3
  usra v2.2d, v16.2d, #3
  usra v3.2d, v16.2d, #3
  usra v4.2d, v16.2d, #3
  usra v5.2d, v16.2d, #3
  usra v6.2d, v16.2d, #3
  usra v7.2d, v16.2d, #3
  usra v8.2d, v16.2d, #3
  usra v9.2d, v16.2d, #3
  usra v10.2d, v16.2d, #3
  usra v11.2d, v16.2d, #3
  usra v12.2d, v16.2d, #3
  usra v13.2d, v16.2d, #3
  usra v14.2d, v16.2d, #3
  usra v15.2d, v16.2d, #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)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d cache writeback (a8)	ac	c2	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	40049	310	0	51	25	160108	100	160008	100	160020	500	1280132	0	40020	40039	40039	19977	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	0	0	40036	160000	100	40040	40040	40040	40040	40040
160204	40039	310	0	160	25	160108	100	160008	100	160020	500	1280132	0	40020	40039	40039	19977	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	0	0	40036	160000	100	40040	40040	40040	40040	40040
160204	40039	310	0	30	25	160108	100	160008	100	160020	500	1280132	0	40020	40039	40039	19977	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	0	0	40036	160000	100	40040	40040	40040	40040	40040
160204	40039	311	0	30	25	160108	100	160008	100	160020	500	1280132	1	40020	40039	40039	19977	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	0	0	40036	160000	100	40040	40040	40040	40040	40040
160204	40039	311	0	58	25	160108	100	160008	100	160020	500	1280132	1	40020	40039	40039	19977	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	0	0	40036	160000	100	40040	40040	40040	40040	40040
160204	40039	311	0	30	25	160108	100	160008	100	160020	500	1280132	1	40020	40039	40039	19977	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	0	0	40036	160000	100	40040	40040	40040	40040	40088
160204	40039	310	0	53	25	160108	100	160008	100	160020	500	1280132	1	40020	40039	40039	19977	6	19990	160120	200	160032	200	320064	40039	40112	1	1	160201	100	99	100	100	160000	100	0	0	0	1	1	1	10118	0	16	0	0	40036	160000	100	40040	40040	40040	40040	40040
160204	40039	310	0	30	25	160108	100	160008	100	160020	500	1280132	0	40020	40039	40039	19977	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	0	0	40036	160000	100	40040	40040	40040	40040	40040
160204	40039	311	0	72	25	160108	100	160008	100	160020	500	1280132	1	40020	40039	40039	19977	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	0	0	40036	160000	100	40040	40040	40040	40040	40040
160204	40039	310	0	30	25	160108	100	160008	100	160020	500	1280132	0	40020	40039	40039	19977	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	0	0	40036	160000	100	40040	40040	40219	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	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)	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	cf	d0	d2	l1i cache miss demand (d3)	d5	map dispatch bubble (d6)	d9	da	db	dd	fetch restart (de)	df	e0	ea	eb	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
160024	40039	310	0	54	0	0	52	25	160010	10	160000	10	160000	50	1280000	1	1	40020	40039	40039	19996	3	20019	160010	20	160000	20	320000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	10026	3	1	1	7	16	2	1	1	3	5	3	40036	324	5	160000	10	40040	40040	40040	40040	40040
160024	40039	310	0	0	0	0	46	25	160010	10	160000	10	160000	50	1280000	1	1	40020	40039	40039	19996	3	20019	160010	20	160000	20	320000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	10026	3	1	1	4	16	2	1	1	4	4	3	40086	269	10	160000	10	40040	40040	40040	40040	40040
160024	40039	310	0	0	0	0	46	25	160010	10	160000	10	160000	50	1280000	1	1	40020	40039	40039	19996	3	20019	160010	20	160000	20	320000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	10026	3	1	1	4	16	2	1	1	4	4	3	40036	254	5	160000	10	40040	40040	40040	40040	40040
160024	40039	310	0	0	0	0	46	25	160010	10	160000	10	160000	50	1280000	1	1	40020	40039	40039	19996	3	20019	160010	20	160000	20	320000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	10026	3	1	1	6	16	2	1	1	5	4	3	40036	256	5	160000	10	40040	40040	40040	40040	40040
160024	40039	311	0	0	0	0	46	25	160010	10	160000	10	160000	50	1280000	1	1	40071	40039	40039	19996	3	20019	160010	20	160000	20	320000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	10026	3	1	1	4	16	2	1	1	3	4	3	40036	270	10	160000	10	40040	40040	40040	40040	40040
160024	40039	310	0	0	0	0	74	25	160010	10	160000	10	160000	50	1280000	1	1	40020	40039	40039	19996	3	20019	160010	20	160000	20	320000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	10026	3	1	1	4	16	2	1	1	4	3	3	40036	304	5	160000	10	40040	40040	40040	40040	40040
160024	40039	310	0	0	0	0	46	25	160010	10	160000	10	160000	50	1280000	1	1	40020	40039	40039	19996	3	20019	160010	20	160000	20	320000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	10026	3	1	1	5	16	2	1	1	4	3	3	40036	302	10	160000	10	40040	40040	40040	40040	40040
160024	40039	310	0	0	0	0	46	25	160010	10	160000	10	160000	50	1280000	1	1	40020	40039	40039	19996	3	20019	160010	20	160000	20	320000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	10026	3	1	1	3	16	2	1	1	5	4	3	40036	306	5	160000	10	40040	40040	40040	40040	40040
160024	40039	310	0	0	0	0	46	25	160010	10	160000	10	160000	50	1280000	1	1	40020	40039	40039	19996	3	20019	160010	20	160000	20	320000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	10026	3	2	1	5	16	2	1	1	4	4	3	40036	306	5	160000	10	40040	40040	40040	40040	40040
160024	40039	311	0	0	0	0	46	25	160010	10	160000	10	160000	50	1280000	0	1	40020	40039	40039	19996	3	20019	160010	20	160000	20	320280	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	10028	3	1	2	4	16	4	1	2	4	4	3	40036	685	5	160000	10	40040	40040	40040	40040	40040

USRA (vector, 2D)

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