Firestorm: USRA (vector, 16B) measurements

Code:

  usra 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	mmu table walk data (08)	l2 tlb miss data (0b)	18	19	1e	1f	3f	4e	51	schedule uop (52)	schedule simd uop (54)	dispatch simd uop (57)	ldst uops in schedulers (5b)	60	69	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map simd uop (7e)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst simd alu (9a)	l1d tlb miss (a1)	ld unit uop (a6)	l1d cache writeback (a8)	a9	ac	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	f5	f6	f7	f8	fd
1004	3037	24	0	0	0	0	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	0	0	0	0	73	1	16	1	1	2667	1000	3107	3084	3086	3086	3086
1004	3083	23	1	1	1	1	12	88	741	2539	49	1008	1000	1149	399670	0	3054	3112	3084	2418	6	2914	1000	1000	2336	3083	3085	1	1	1001	1000	2	0	0	0	2803	79	1	40	1	1	2659	1000	3085	3086	3086	3086	3085
1004	3085	24	1	0	1	0	132	88	1064	2539	44	1008	1000	1149	399670	0	3054	3085	3084	2415	7	2914	1149	1168	2326	3084	3085	2	1	1001	1000	0	0	2	2	2840	94	1	24	1	1	2665	1000	3086	3085	3038	3038	3085
1004	3084	24	0	0	2	1	147	88	704	2548	25	1000	1000	1000	398313	0	3018	3037	3037	2415	3	2895	1000	1000	2000	3037	3037	1	1	1001	1000	0	0	0	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	0	0	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	0	0	0	3	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	24	0	0	0	0	12	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	0	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	24	0	0	0	0	0	0	346	2548	25	1000	1000	1000	398313	0	3018	3037	3037	2415	3	2895	1000	1000	2000	3037	3037	1	1	1001	1000	0	0	0	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	0	0	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	4	0	0	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	0	0	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	0	0	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	0	0	0	0	61	2548	25	1000	1000	1000	398313	1	3018	3037	3037	2415	3	2895	1000	1000	2000	3037	3037	1	1	1001	1000	0	0	0	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038

Test 2: Latency 1->1

Code:

  usra 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 tlb access (a0)	l1d tlb miss (a1)	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	30037	232	0	187	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	1	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	232	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	11058	710	1	16	1	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	233	0	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	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	233	12	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	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	233	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	710	1	16	1	1	29634	10000	100	30086	30086	30135	30085	30038
10204	30037	233	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	233	0	61	29548	25	10100	100	10000	100	10000	500	4277313	0	30018	30037	30037	28265	3	28745	10100	200	10000	200	20000	30037	30037	33	1	10201	100	99	100	100	10000	100	0	0	0	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	232	0	103	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	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	232	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	233	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	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	mmu table walk data (08)	09	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	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 access (a0)	l1d tlb miss (a1)	ld unit uop (a6)	st unit uop (a7)	l1d cache writeback (a8)	a9	ac	c2	cf	d0	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? int output thing (e9)	ec	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10024	30037	233	0	0	0	0	0	0	0	0	1000	29548	25	10010	10	10000	10	10000	50	4277313	1	5	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	0	640	5	3	16	3	4	29630	0	0	10000	10	30038	30038	30038	30038	30038
10024	30037	232	0	0	0	0	0	0	0	0	1167	29548	25	10010	10	10000	10	10000	50	4277313	1	5	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	0	640	5	4	16	4	3	29630	0	0	10000	10	30038	30038	30038	30038	30038
10024	30037	233	0	0	0	0	0	0	0	0	1194	29548	25	10010	10	10000	10	10000	50	4277313	1	5	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	0	640	5	4	16	4	4	29630	0	0	10000	10	30038	30038	30038	30038	30038
10024	30037	233	0	0	0	0	0	0	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	1	5	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	0	640	5	4	16	3	4	29630	0	0	10000	10	30038	30085	30085	30085	30038
10024	30037	241	0	0	0	0	0	0	0	0	1289	29548	25	10017	10	10000	10	10000	50	4277313	1	5	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	0	640	5	4	16	4	3	29630	0	0	10000	10	30038	30038	30038	30038	30038
10024	30037	233	0	0	0	0	0	0	0	0	1078	29548	25	10010	10	10000	10	10000	50	4277313	1	5	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	0	640	5	3	16	4	4	29630	0	0	10000	10	30038	30038	30038	30038	30038
10024	30037	233	0	0	0	0	0	0	0	0	1180	29548	25	10010	10	10000	10	10000	50	4277313	1	5	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	15	0	640	5	4	16	4	3	29630	0	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	0	0	0	0	1092	29548	25	10010	10	10000	10	10000	50	4277313	1	5	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	0	640	5	4	16	4	4	29630	0	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	0	0	0	0	968	29548	25	10010	10	10000	10	10000	50	4277313	1	5	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	0	640	5	3	16	3	4	29630	0	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	0	189	0	0	875	29548	25	10010	10	10000	10	10000	50	4277313	1	5	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	0	640	5	4	16	3	4	29630	0	0	10000	10	30038	30038	30038	30038	30038

Test 3: Latency 1->2

Code:

  usra 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	mmu table walk data (08)	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 tlb access (a0)	l1d tlb miss (a1)	l1d cache writeback (a8)	a9	ac	branch cond mispred nonspec (c5)	branch mispred nonspec (cb)	cd	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10204	30037	233	0	72	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	0	0	0	1	1	1	722	3	24	2	2	29629	10000	100	30038	30038	30038	30038	30038
10204	30037	233	0	66	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	0	0	0	1	1	1	722	3	31	2	2	29629	10000	100	30038	30038	30038	30038	30038
10204	30037	232	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	0	0	0	1	1	1	722	5	24	2	2	29629	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	0	0	0	0	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	7	28741	10100	200	10008	200	20016	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	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	28741	10100	200	10008	200	20016	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	1	0	0	1	1	1	717	0	16	0	0	29717	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	28292	7	28741	10100	200	10008	200	20016	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	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	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	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	28741	10100	200	10008	200	20016	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	1	1	1	718	0	16	0	0	29646	10000	100	30038	30038	30038	30038	30038
10204	30037	233	0	0	0	726	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	0	0	0	1	1	1	717	0	16	0	0	29645	10000	100	30038	30038	30038	30038	30038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

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

retire uop (01)	cycle (02)	03	18	1e	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)	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	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10024	30037	233	0	12	0	61	29547	25	10010	10	10000	10	10000	50	4277160	30018	30037	30037	28286	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	640	2	16	2	2	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	233	0	3	0	61	29547	25	10010	10	10000	10	10000	50	4277160	30018	30037	30037	28286	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	640	2	16	2	2	29629	10000	10	30085	30038	30038	30038	30038
10024	30037	241	0	0	0	61	29547	25	10010	10	10000	10	10000	50	4277160	30018	30037	30037	28286	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	640	2	16	2	2	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	233	0	0	0	61	29547	25	10010	10	10000	10	10000	50	4277160	30018	30037	30037	28286	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	640	2	16	2	2	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	233	0	0	0	61	29547	25	10010	10	10000	10	10000	50	4277160	30018	30037	30037	28286	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	640	2	16	2	2	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	233	0	0	0	61	29547	25	10010	10	10000	10	10000	50	4277160	30018	30037	30037	28286	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	10	10	10000	10	1	0	0	640	2	16	2	2	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	232	0	0	0	441	29547	25	10010	10	10000	10	10000	50	4277160	30018	30037	30037	28286	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	640	2	16	2	2	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	233	0	0	0	61	29547	25	10010	10	10000	10	10000	50	4277160	30018	30037	30037	28286	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	640	2	16	2	2	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	241	0	0	0	61	29547	25	10010	10	10000	10	10000	50	4277160	30018	30037	30037	28286	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	640	2	16	2	2	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	232	0	0	0	61	29547	25	10010	10	10000	10	10000	50	4277160	30018	30037	30037	28286	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	640	2	16	2	2	29629	10000	10	30038	30038	30038	30038	30038

Test 4: throughput

Count: 8

Code:

  movi v0.16b, 0
  usra v0.16b, v8.16b, #3
  movi v1.16b, 0
  usra v1.16b, v8.16b, #3
  movi v2.16b, 0
  usra v2.16b, v8.16b, #3
  movi v3.16b, 0
  usra v3.16b, v8.16b, #3
  movi v4.16b, 0
  usra v4.16b, v8.16b, #3
  movi v5.16b, 0
  usra v5.16b, v8.16b, #3
  movi v6.16b, 0
  usra v6.16b, v8.16b, #3
  movi v7.16b, 0
  usra 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	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 rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d tlb access (a0)	l1d tlb miss (a1)	l1d cache writeback (a8)	ac	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
160204	20065	155	0	29	25	80116	100	80016	100	80028	500	640196	20045	20065	20065	6	12	80128	200	80028	200	160056	20065	20065	1	1	160201	100	99	100	100	160000	100	0	0	0	3	1	1	1	10119	2	16	0	0	20062	0	160000	100	20066	20066	20066	20066	20066
160204	20065	155	0	29	25	80116	100	80016	100	80028	500	640196	20045	20065	20065	6	12	80128	200	80028	200	160056	20065	20065	1	1	160201	100	99	100	100	160000	100	0	0	0	0	1	1	1	10119	0	16	0	0	20062	0	160000	100	20066	20066	20066	20066	20066
160204	20065	155	0	29	25	80116	100	80016	100	80028	500	640196	20045	20065	20065	6	12	80128	200	80028	200	160056	20065	20065	1	1	160201	100	99	100	100	160000	100	0	0	0	0	1	1	1	10119	0	16	0	0	20062	0	160000	100	20066	20066	20066	20066	20066
160204	20065	156	0	29	25	80116	100	80016	100	80028	500	640196	20045	20065	20065	6	12	80128	200	80028	200	160056	20065	20065	1	1	160201	100	99	100	100	160000	100	0	0	0	0	1	1	1	10119	0	16	0	0	20062	0	160000	100	20066	20066	20066	20066	20066
160204	20065	155	12	29	25	80116	100	80016	100	80028	500	640196	20045	20065	20065	6	12	80128	200	80028	200	160056	20065	20065	1	1	160201	100	99	100	100	160000	100	0	0	0	0	1	1	1	10119	0	16	0	0	20062	0	160000	100	20066	20066	20066	20066	20066
160204	20065	155	0	29	25	80116	100	80016	100	80028	500	640196	20045	20065	20065	6	12	80128	200	80028	200	160056	20065	20065	1	1	160201	100	99	100	100	160000	100	0	0	0	0	1	1	1	10119	0	16	0	0	20062	0	160000	100	20066	20066	20066	20066	20066
160204	20065	155	0	29	25	80116	100	80016	100	80028	500	640196	20045	20065	20065	6	12	80128	200	80028	200	160056	20065	20065	1	1	160201	100	99	100	100	160000	100	7	2	1	0	1	1	1	10119	0	16	0	0	20062	0	160000	100	20066	20066	20066	20066	20066
160204	20065	156	0	29	25	80116	100	80016	100	80028	500	640196	20045	20065	20065	6	12	80128	200	80028	200	160056	20065	20065	1	1	160201	100	99	100	100	160000	100	0	0	0	0	1	1	1	10119	0	16	0	0	20062	0	160000	100	20066	20066	20066	20066	20066
160204	20065	161	0	65	29	80119	100	80019	100	80031	500	640220	20056	20077	20077	10	12	80131	200	80031	200	160062	20077	20078	1	1	160201	100	99	100	100	160000	100	0	0	0	0	2	2	2	10130	1	23	1	1	20074	0	160000	100	20078	20078	20078	20078	20078
160204	20077	156	0	65	29	80119	100	80019	100	80031	500	640220	20056	20077	20078	9	12	80131	200	80031	200	160062	20077	20077	1	1	160201	100	99	100	100	160000	100	0	0	0	0	2	2	2	10130	1	23	1	1	20074	0	160000	100	20078	20079	20079	20078	20078

1000 unrolls and 10 iterations

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

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

retire uop (01)	cycle (02)	03	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	ld unit uop (a6)	l1d cache writeback (a8)	ac	cf	d0	d2	l1i cache miss demand (d3)	d5	map dispatch bubble (d6)	d9	da	db	dd	fetch restart (de)	e0	ea	ec	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
160024	20085	150	12	87	27	80010	10	80000	10	80000	50	640000	1	1	5	20033	20060	20060	3	22	80010	20	80000	20	160000	20060	20060	1	1	160021	10	9	10	10	160000	10	0	0	0	10038	11	11	2	36	34	4	2	1	17	12	20057	40	2	160000	10	20052	20061	20061	20061	20052
160024	20060	150	12	51	27	80010	10	80000	10	80000	50	640000	0	1	5	20041	20060	20060	3	22	80010	20	80000	20	160000	20051	20060	1	1	160021	10	9	10	10	160000	10	0	0	0	10041	11	4	2	12	34	4	2	1	12	13	20057	40	1	160000	10	20061	20061	20052	20061	20061
160024	20060	150	0	51	29	80010	10	80000	10	80000	50	640000	1	1	5	20032	20051	20051	3	22	80010	20	80000	20	160000	20060	20060	1	1	160021	10	9	10	10	160000	10	0	0	0	10037	8	5	2	13	34	4	2	2	18	17	20057	40	1	160000	10	20061	20061	20061	20061	20052
160024	20051	151	12	93	29	80010	10	80000	10	80000	50	640000	0	1	5	20041	20069	20060	3	22	80010	20	80000	20	160000	20051	20060	1	1	160021	10	9	10	10	160000	10	0	0	0	10037	8	5	1	13	25	4	2	2	13	13	20057	40	1	160000	10	20061	20061	20061	20061	20052
160024	20060	150	0	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	34	0	10037	8	4	1	15	25	2	9	1	17	11	20048	20	1	160000	10	20052	20052	20052	20052	20052
160024	20051	151	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	10035	8	4	1	12	25	2	1	1	13	19	20048	20	1	160000	10	20052	20052	20052	20052	20052
160024	20051	150	12	202	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	10037	8	4	1	11	25	2	1	1	19	14	20048	20	1	160000	10	20052	20052	20052	20052	20052
160024	20051	150	0	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	10036	8	4	1	13	25	2	1	1	11	13	20048	20	1	160000	10	20052	20052	20052	20052	20052
160024	20051	151	0	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	10037	8	4	1	13	25	2	1	1	14	12	20048	20	1	160000	10	20052	20052	20052	20052	20052
160024	20051	150	0	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	10041	8	4	1	13	25	2	1	1	11	14	20048	20	1	160000	10	20052	20052	20052	20052	20052

Test 5: throughput

Count: 16

Code:

  usra v0.16b, v16.16b, #3
  usra v1.16b, v16.16b, #3
  usra v2.16b, v16.16b, #3
  usra v3.16b, v16.16b, #3
  usra v4.16b, v16.16b, #3
  usra v5.16b, v16.16b, #3
  usra v6.16b, v16.16b, #3
  usra v7.16b, v16.16b, #3
  usra v8.16b, v16.16b, #3
  usra v9.16b, v16.16b, #3
  usra v10.16b, v16.16b, #3
  usra v11.16b, v16.16b, #3
  usra v12.16b, v16.16b, #3
  usra v13.16b, v16.16b, #3
  usra v14.16b, v16.16b, #3
  usra 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	18	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)	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)	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	40057	310	0	0	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	0	0	0	0	1	1	1	10118	3	16	0	0	40036	160000	100	40040	40040	40040	40040	40040
160204	40039	311	0	0	0	30	25	160108	100	160008	100	160020	500	1280132	0	40020	40039	40039	19977	12	20045	160120	200	160032	200	320064	40039	40039	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	0	0	1	1	1	10118	0	16	0	0	40036	160000	100	40040	40040	40040	40040	40040
160204	40039	310	0	0	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	0	0	0	0	1	1	1	10118	0	16	0	0	40036	160000	100	40040	40040	40040	40040	40040
160204	40039	310	0	0	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	0	0	0	0	1	1	1	10118	0	16	0	0	40036	160000	100	40040	40040	40040	40040	40040
160204	40039	310	0	0	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	0	0	0	0	1	1	1	10118	0	16	0	0	40036	160000	100	40040	40040	40040	40040	40040
160204	40039	310	0	0	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	0	0	0	0	1	1	1	10118	0	16	0	0	40036	160000	100	40040	40040	40040	40040	40040
160204	40039	311	0	0	36	1175	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	4	0	0	0	0	0	1	1	1	10136	0	16	0	0	40036	160000	100	40040	40040	40040	40040	40040
160204	40039	310	0	0	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	0	0	0	0	1	1	1	10118	0	16	0	0	40036	160000	100	40040	40197	40040	40040	40040
160204	40039	310	0	0	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	0	0	0	0	1	1	1	10118	0	16	0	0	40036	160000	100	40040	40040	40040	40040	40040
160204	40039	310	0	0	0	30	25	160108	100	160008	100	160020	500	1280788	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	0	1	0	0	1	1	1	10118	0	16	0	0	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	l1i tlb fill (04)	mmu table walk instruction (07)	l2 tlb miss data (0b)	18	19	1e	1f	35	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	ld unit uop (a6)	l1d cache writeback (a8)	a9	ac	cf	d0	d2	l1i cache miss demand (d3)	d5	map dispatch bubble (d6)	d9	da	db	dd	fetch restart (de)	e0	ea	eb	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
160024	40050	310	0	0	0	0	0	0	0	0	1625	25	160010	10	160000	10	160000	50	1280000	0	1	40020	40039	40039	19996	3	20019	160010	20	160000	20	320000	40039	40111	2	1	160021	10	9	10	10	160000	10	0	0	0	0	10024	6	2	2	5	16	2	1	1	6	6	40036	15	5	160000	10	40040	40040	40040	40040	40040
160024	40039	311	0	0	0	0	0	0	0	0	52	25	160010	10	160068	10	160000	50	1280000	0	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	0	0	10024	6	2	2	6	16	4	2	2	4	6	40036	30	10	160000	10	40040	40040	40040	40040	40040
160024	40039	311	0	0	0	0	0	0	0	0	46	25	160010	10	160000	10	160000	50	1280000	2	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	0	0	10024	6	2	2	9	16	4	2	2	4	6	40036	30	10	160000	10	40040	40040	40040	40040	40040
160024	40039	310	0	0	0	0	0	0	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	0	0	10022	6	2	1	10	16	2	1	1	6	6	40036	15	8	160000	10	40040	40040	40040	40040	40040
160024	40039	311	0	0	0	0	0	0	0	0	46	25	160010	10	160000	10	160000	50	1280000	2	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	0	0	10022	3	2	2	4	16	2	1	1	6	9	40036	15	5	160000	10	40040	40040	40040	40040	40040
160024	40039	310	0	0	0	0	0	0	0	0	46	25	160010	10	160000	10	160000	50	1280000	2	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	0	0	10024	6	2	2	5	16	4	2	2	8	9	40036	30	10	160000	10	40040	40040	40040	40040	40040
160024	40039	311	0	0	0	0	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	320000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10022	3	1	1	9	16	2	1	1	8	5	40036	15	5	160000	10	40040	40040	40040	40040	40040
160024	40039	310	0	0	0	0	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	0	0	10022	6	1	1	6	16	2	1	1	7	4	40036	15	10	160000	10	40040	40040	40040	40040	40040
160024	40039	310	0	0	0	0	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	0	0	10022	3	1	1	5	16	2	1	1	5	6	40036	15	5	160000	10	40040	40040	40040	40040	40040
160024	40039	310	0	0	0	0	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	0	0	10024	3	1	1	9	16	2	1	1	9	8	40036	15	5	160000	10	40040	40040	40040	40040	40040

USRA (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