Firestorm: SUQADD (vector, 2S) measurements

Code:

  suqadd v0.2s, v1.2s

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)	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	3037	22	0	0	156	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	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	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	3	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	80	2548	25	1000	1000	1000	398313	0	3018	3037	3037	2415	3	2895	1000	1000	2000	3037	3037	1	1	1001	1000	0	6	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	61	2548	25	1000	1000	1000	398313	0	3018	3037	3037	2415	3	2895	1000	1000	2000	3037	3037	1	1	1001	1000	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	0	0	61	2548	25	1000	1000	1000	398313	0	3018	3037	3037	2415	3	2895	1000	1000	2000	3037	3037	1	1	1001	1000	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	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	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	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	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	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	9	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	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	4	3	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038

Test 2: Latency 1->1

Code:

  suqadd v0.2s, v1.2s

Initialization

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

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

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

retire uop (01)	cycle (02)	03	mmu table walk data (08)	l2 tlb miss data (0b)	18	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)	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)	ld unit uop (a6)	l1d cache writeback (a8)	ac	branch mispred nonspec (cb)	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? int output thing (e9)	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10204	30037	225	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	30018	30037	30037	28265	3	28745	10100	200	10000	200	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	124	29548	25	10100	100	10000	100	10000	500	4277313	30018	30037	30037	28265	3	28745	10100	200	10000	200	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	170	29548	25	10100	100	10000	100	10000	500	4277313	30018	30037	30037	28265	3	28745	10100	200	10000	200	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	480	29548	25	10100	100	10000	100	10000	500	4277313	30018	30037	30037	28265	3	28745	10100	200	10000	200	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	317	29548	25	10100	100	10000	100	10000	500	4277313	30018	30037	30037	28265	3	28745	10100	200	10000	200	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	1	0	61	29548	25	10100	100	10000	116	10000	500	4277313	30018	30037	30084	28265	3	28745	10100	200	10000	200	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	123	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	170	29548	25	10100	100	10000	100	10000	500	4277313	30018	30037	30037	28265	3	28745	10416	200	10000	200	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	1	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	1	0	3	61	29548	25	10100	100	10000	100	10000	500	4277313	30018	30037	30037	28265	3	28745	10100	204	10000	200	20330	30037	30037	1	1	10201	100	99	100	100	10000	100	2	2	0	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	145	29548	25	10100	100	10000	100	10000	500	4277313	30018	30037	30037	28265	3	28745	10100	200	10000	200	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	145	29548	25	10100	100	10000	100	10000	500	4277313	30018	30037	30037	28265	3	28745	10100	200	10000	200	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	710	1	16	1	1	29634	0	10000	100	30085	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)	18	19	1e	1f	3a	3f	4e	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	60	69	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d tlb access (a0)	l1d tlb miss (a1)	ld unit uop (a6)	st unit uop (a7)	l1d cache writeback (a8)	a9	ac	c2	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? int output thing (e9)	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10024	30037	225	0	0	0	0	0	0	84	29548	25	10010	10	10000	10	10000	50	4277313	0	30018	30131	30226	28298	25	28837	10712	20	10000	20	21302	30272	30228	6	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	0	0	640	2	16	3	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	5	4	15	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	0	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	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	9	0	0	181	29548	25	10010	10	10000	10	10000	50	4277313	0	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	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	4	660	264	0	61	29548	25	10010	10	10000	10	10000	50	4277313	0	30018	30037	30037	28287	36	28898	11354	20	10000	20	20000	30037	30037	1	1	10021	10	9	10	10	10000	10	2	0	0	1	0	0	11120	0	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30074	30038
10024	30037	225	0	0	0	0	0	0	737	29548	25	10010	10	10000	10	10000	50	4277313	0	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	11135	0	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	30037	30037	28287	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	10	10	10000	10	4	0	0	0	0	0	0	0	788	4	98	2	2	29630	0	10000	10	30038	30038	30038	30132	30038
10024	30037	225	0	0	0	531	616	0	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	30037	30037	28287	3	28767	10912	22	11140	24	21980	30369	30084	8	1	10021	10	9	10	10	10000	10	0	0	0	0	1	2	19728	0	640	2	51	3	4	29882	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	0	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	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	30037	30037	28287	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	0	0	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	0	0	61	29539	25	10010	10	10000	10	10000	50	4277313	0	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	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038

Test 3: Latency 1->2

Code:

  suqadd v0.2s, v0.2s

Initialization

  movi v0.16b, 1

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

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

retire uop (01)	cycle (02)	03	18	19	1e	1f	3a	3f	4e	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	69	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d tlb miss (a1)	ld unit uop (a6)	st unit uop (a7)	l1d cache writeback (a8)	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
10204	30037	225	0	0	0	0	0	147	29547	25	10100	100	10000	100	10000	500	4277160	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	29646	0	10000	100	30038	30038	30038	30038	30038
10204	30037	224	0	0	0	0	0	84	29547	25	10100	100	10000	100	10000	500	4277160	30018	30037	30037	28271	6	28741	10100	200	10008	200	20016	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	1	1	1	718	0	16	0	0	29645	0	10000	100	30038	30038	30038	30038	30085
10204	30037	225	0	0	0	0	0	149	29547	25	10100	100	10000	100	10000	500	4277160	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	0	10000	100	30038	30038	30038	30038	30038
10204	30037	224	0	0	9	0	0	149	29547	25	10100	100	10000	100	10000	500	4277160	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	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	82	29547	25	10100	100	10000	100	10000	500	4277160	30018	30037	30037	28271	6	28741	10100	200	10008	200	20016	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	1	1	1	717	0	16	0	0	29646	0	10000	100	30038	30038	30038	30038	30038
10204	30037	224	0	0	0	0	0	61	29547	25	10100	100	10000	100	10000	500	4277160	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	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	107	29547	25	10100	100	10000	100	10000	500	4277160	30018	30037	30037	28271	6	28741	10100	200	10008	200	20016	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	1	1	1	718	0	16	0	0	29646	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	61	29547	25	10100	100	10000	100	10000	500	4277160	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	29646	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	84	29547	25	10100	100	10000	100	10000	500	4277160	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	29646	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	107	29547	25	10100	100	10000	100	10000	500	4277160	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	0	10000	100	30038	30038	30038	30038	30038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

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

retire uop (01)	cycle (02)	03	1e	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	6b	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d tlb access (a0)	ld unit uop (a6)	l1d cache writeback (a8)	a9	ac	cf	d0	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10024	30037	260	0	103	29547	25	10010	10	10000	10	10000	50	4277160	0	5	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	1	0	3	640	0	5	16	6	5	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	259	0	103	29547	25	10010	10	10000	10	10000	50	4277160	0	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	1	0	0	640	5	6	16	6	5	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	260	0	84	29547	25	10010	10	10000	10	10000	50	4277160	1	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	0	0	640	6	6	16	6	5	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	260	0	231	29547	25	10010	10	10000	10	10000	50	4277160	0	6	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	0	0	640	0	5	16	5	6	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	241	0	258	29547	25	10010	10	10000	10	10000	50	4277160	1	0	30018	0	30070	30037	28286	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	640	6	6	16	5	6	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	241	0	61	29547	25	10010	10	10000	10	10000	50	4277160	1	6	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	0	0	640	6	6	16	6	5	29629	10000	10	30038	30085	30133	30038	30038
10024	30037	241	0	243	29547	25	10010	10	10000	10	10000	50	4277160	1	6	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	0	0	640	6	5	16	5	5	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	242	0	166	29547	25	10010	10	10000	10	10000	50	4277160	1	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	1	0	3	640	6	5	16	5	6	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	233	0	256	29547	25	10010	10	10000	10	10000	50	4277160	1	6	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	0	0	640	0	5	16	6	5	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	233	0	216	29547	25	10010	10	10000	10	10000	50	4277160	0	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	0	0	640	0	6	16	6	5	29629	10000	10	30038	30038	30038	30038	30038

Test 4: throughput

Count: 8

Code:

  movi v0.16b, 0
  suqadd v0.2s, v8.2s
  movi v1.16b, 0
  suqadd v1.2s, v8.2s
  movi v2.16b, 0
  suqadd v2.2s, v8.2s
  movi v3.16b, 0
  suqadd v3.2s, v8.2s
  movi v4.16b, 0
  suqadd v4.2s, v8.2s
  movi v5.16b, 0
  suqadd v5.2s, v8.2s
  movi v6.16b, 0
  suqadd v6.2s, v8.2s
  movi v7.16b, 0
  suqadd v7.2s, v8.2s

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 instruction (0a)	l2 tlb miss data (0b)	18	1e	1f	3f	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	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	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	20091	150	0	0	0	0	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	160000	100	20066	20066	20066	20066	20066
160204	20065	150	0	0	0	0	0	675	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	3	0	1	1	1	10119	0	16	0	0	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	151	0	0	0	0	0	117	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	160000	100	20066	20066	20066	20134	20066
160204	20065	150	0	0	0	0	0	1130	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	160000	100	20066	20066	20066	20066	20066
160204	20065	150	0	0	0	0	0	29	25	80116	100	80016	100	80028	500	640196	20045	20065	20065	6	12	80128	200	80028	200	160056	20065	20065	2	1	160201	100	99	100	100	160000	100	0	0	0	0	1	1	1	10119	0	16	0	0	20062	160000	100	20066	20066	20066	20066	20066
160204	20065	150	0	0	0	0	0	515	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	160000	100	20066	20066	20066	20066	20066
160204	20065	151	0	0	0	0	0	136	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	160000	100	20066	20066	20066	20066	20066
160204	20065	150	0	0	0	0	0	94	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	160000	100	20066	20066	20066	20066	20066
160204	20065	150	0	0	0	0	0	113	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	160000	100	20066	20066	20066	20066	20066
160204	20065	150	0	0	0	0	0	801	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	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	18	19	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 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)	c2	cf	d0	d2	l1i cache miss demand (d3)	d5	map dispatch bubble (d6)	d9	da	db	dd	fetch restart (de)	e0	ea	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
160024	20057	150	0	0	1	292	25	80010	10	80000	10	80000	50	640000	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	10037	6	2	1	20	24	4	1	2	5	10	20043	15	160000	10	20047	20047	20047	20047	20051
160024	20050	150	0	0	0	198	25	80010	10	80000	10	80000	50	640000	0	1	20031	20050	20050	3	22	80010	20	80000	20	160000	20046	20050	1	1	160021	10	9	10	10	160000	10	0	0	10033	3	1	1	10	20	2	1	1	6	13	20043	15	160000	10	20051	20051	20047	20051	20047
160024	20050	150	0	0	0	488	25	80010	10	80000	10	80000	50	640000	1	1	20027	20046	20046	3	22	80010	20	80000	20	160000	20046	20046	1	1	160021	10	9	10	10	160000	10	0	4	10041	6	2	2	5	24	4	2	9	5	9	20043	15	160000	10	20051	20051	20051	20051	20051
160024	20050	150	0	0	0	87	25	80010	10	80000	10	80000	50	640000	1	1	20027	20046	20046	3	22	80010	20	80000	20	160000	20046	20046	1	1	160021	10	9	10	10	160000	10	2	0	10028	6	2	2	10	24	2	2	2	10	5	20047	15	160000	10	20047	20047	20047	20047	20047
160024	20046	150	0	0	0	154	25	80010	10	80000	10	80000	50	640000	0	1	20031	20050	20050	3	22	80010	20	80000	20	160000	20050	20050	1	1	160021	10	9	10	10	160000	10	0	0	10030	6	2	2	9	24	4	2	2	6	14	20047	30	160000	10	20051	20051	20051	20051	20051
160024	20050	150	0	0	0	211	25	80010	10	80000	10	80000	50	640000	0	1	20027	20050	20046	3	22	80010	20	80000	20	160000	20050	20050	1	1	160021	10	9	10	10	160000	10	0	0	10029	3	2	1	7	20	2	1	1	7	12	20043	15	160000	10	20047	20047	20047	20047	20047
160024	20046	150	0	0	0	95	25	80010	10	80000	10	80000	50	640000	0	1	20031	20046	20046	3	22	80010	20	80000	20	160000	20050	20050	1	1	160021	10	9	10	10	160000	10	0	0	10035	3	2	2	12	24	4	1	2	14	9	20047	30	160000	10	20047	20051	20051	20051	20051
160024	20050	150	0	0	0	171	25	80010	10	80000	10	80000	50	640000	0	1	20027	20050	20046	3	22	80010	20	80000	20	160000	20046	20046	1	1	160021	10	9	10	10	160000	10	0	0	10028	3	1	1	5	20	2	1	1	8	9	20047	15	160000	10	20047	20047	20047	20047	20047
160024	20050	150	0	0	0	45	25	80010	10	80000	10	80000	50	640000	1	1	20031	20046	20046	3	22	80010	20	80000	20	160000	20050	20046	1	1	160021	10	9	10	10	160000	10	0	0	10030	6	1	2	5	20	2	1	1	9	9	20043	15	160000	10	20047	20047	20051	20051	20047
160024	20046	150	0	0	0	45	25	80010	10	80000	10	80000	50	640000	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	10029	3	1	1	9	20	4	2	1	5	12	20043	15	160000	10	20051	20051	20047	20047	20047

Test 5: throughput

Count: 16

Code:

  suqadd v0.2s, v16.2s
  suqadd v1.2s, v16.2s
  suqadd v2.2s, v16.2s
  suqadd v3.2s, v16.2s
  suqadd v4.2s, v16.2s
  suqadd v5.2s, v16.2s
  suqadd v6.2s, v16.2s
  suqadd v7.2s, v16.2s
  suqadd v8.2s, v16.2s
  suqadd v9.2s, v16.2s
  suqadd v10.2s, v16.2s
  suqadd v11.2s, v16.2s
  suqadd v12.2s, v16.2s
  suqadd v13.2s, v16.2s
  suqadd v14.2s, v16.2s
  suqadd v15.2s, v16.2s

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	ld unit uop (a6)	l1d cache writeback (a8)	ac	branch cond mispred nonspec (c5)	branch mispred nonspec (cb)	cd	cf	map dispatch bubble (d6)	fetch restart (de)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
160204	40039	300	0	30	25	160108	100	160399	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	16	0	40036	160000	100	40040	40040	40040	40040	40040
160204	40039	300	0	30	25	160108	100	160008	100	160020	500	1280132	1	40020	40039	40039	19977	6	19990	160120	200	160032	200	320064	40039	40039	1	1	160201	100	99	100	100	160000	100	2	3	0	1	1	1	10118	16	0	40036	160000	100	40040	40040	40040	40040	40040
160204	40039	300	0	30	25	160108	100	160008	100	160020	500	1280132	1	40020	40039	40039	19977	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	16	0	40036	160000	100	40040	40040	40040	40040	40040
160204	40039	300	0	30	25	160108	100	160008	100	160020	500	1280132	1	40020	40039	40039	19977	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	16	0	40036	160000	100	40040	40040	40040	40040	40040
160204	40039	299	0	125	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	16	0	40036	160000	100	40040	40040	40040	40040	40040
160204	40039	300	0	30	25	160108	100	160008	100	160020	500	1280132	1	40020	40039	40039	19977	6	19990	160120	202	160032	200	320064	40039	40039	1	1	160201	100	99	100	100	160000	100	0	1	0	1	1	1	10118	16	0	40036	160000	100	40040	40040	40040	40040	40040
160204	40039	299	0	201	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	16	0	40036	160000	100	40040	40040	40040	40040	40040
160204	40039	300	0	30	25	160108	100	160008	100	160020	500	1280132	1	40020	40039	40039	19977	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	16	0	40036	160000	100	40040	40040	40040	40040	40040
160204	40039	300	0	30	25	160108	100	160008	100	160020	500	1280132	1	40020	40039	40039	19977	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	16	0	40036	160000	100	40040	40040	40040	40040	40040
160204	40039	300	0	30	25	160108	100	160008	100	160020	500	1280132	1	40020	40039	40039	19977	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	16	1	40036	160000	100	40040	40040	40040	40040	40040

1000 unrolls and 10 iterations

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

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

retire uop (01)	cycle (02)	03	mmu table walk instruction (07)	mmu table walk data (08)	l2 tlb miss instruction (0a)	l2 tlb miss data (0b)	18	1e	1f	3f	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	5f	60	61	69	6d	6e	map stall dispatch (70)	simd prf full (72)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d tlb miss (a1)	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	40040	300	1	0	0	0	0	0	0	52	25	160010	10	160000	10	160000	50	1280000	1	1	5	40020	40039	40039	19996	0	3	20019	160010	20	160000	20	320000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	10022	8	3	1	36	16	2	1	2	9	4	40036	20	6	160000	10	40040	40040	40040	40040	40040
160024	40039	300	0	0	0	1	0	0	0	46	25	160010	10	160000	10	160000	50	1280000	1	1	5	40020	40039	40039	19996	0	27	20019	160010	20	160000	20	320000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	10022	8	3	1	14	16	2	1	1	7	6	40036	20	6	160000	10	40040	40040	40040	40040	40040
160024	40039	300	0	0	0	0	0	0	0	46	25	160010	10	160000	10	160000	50	1280000	0	1	5	40020	40039	40039	19996	0	3	20019	160010	20	160000	20	320000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	10022	8	3	1	5	16	2	1	1	6	13	40036	20	6	160000	10	40040	40040	40040	40040	40040
160024	40039	300	0	0	0	0	0	0	0	46	25	160010	10	160000	10	160000	50	1280000	1	1	5	40020	40039	40039	19996	0	3	20019	160010	20	160000	20	320000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	10024	8	1	1	8	16	2	1	1	7	5	40036	20	6	160000	10	40040	40040	40040	40040	40040
160024	40039	300	0	0	0	0	0	0	0	46	25	160010	10	160000	10	160000	50	1280000	1	1	5	40020	40039	40039	19996	0	3	20019	160010	20	160000	20	320838	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	10099	8	3	1	6	16	2	1	1	14	9	40036	20	6	160000	10	40040	40040	40040	40040	40040
160024	40039	300	0	0	0	0	0	0	0	46	25	160010	10	160000	10	160000	50	1280000	1	1	5	40020	40039	40039	19996	0	3	20019	160010	20	160000	20	320000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	10022	8	3	1	7	16	2	1	1	7	6	40036	20	6	160000	10	40040	40040	40040	40040	40040
160024	40039	300	0	1	0	0	0	0	0	46	25	160010	10	160000	10	160000	50	1280000	1	1	5	40020	40039	40039	19996	0	3	20019	160010	20	160000	20	320000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	10022	8	2	1	7	16	2	1	1	6	6	40036	20	6	160000	10	40040	40040	40040	40040	40040
160024	40039	300	0	0	0	0	0	0	0	46	25	160010	10	160000	10	160000	50	1280000	1	1	5	40020	40039	40039	19996	0	3	20019	160010	20	160000	20	320000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	10022	8	3	1	12	16	2	1	1	7	11	40036	20	6	160000	10	40040	40040	40040	40040	40040
160024	40039	300	0	0	0	0	0	0	0	46	25	160010	10	160000	10	160000	50	1280000	1	1	5	40020	40039	40039	19996	0	3	20019	160010	20	160000	20	320000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	1	0	0	10022	8	3	1	13	16	2	1	1	13	8	40036	20	6	160000	10	40040	40040	40040	40040	40040
160024	40039	300	0	0	0	0	0	0	0	46	25	160010	10	160000	10	160000	50	1280000	1	1	5	40020	40039	40039	19996	0	3	20019	160010	20	160000	20	320000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	10022	11	3	1	5	16	2	1	1	6	6	40036	20	6	160000	10	40040	40040	40040	40040	40040

SUQADD (vector, 2S)

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