Firestorm: FRINTM (vector, 2S) measurements

Code:

  frintm v0.2s, v0.2s

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	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)	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	61	2547	25	1000	1000	1000	398160	0	3018	3037	3037	2414	3	2895	1000	1000	1000	3037	3037	1	1	1001	1000	0	0	0	73	1	16	1	1	2629	1000	3038	3038	3038	3038	3038
1004	3037	23	0	61	2547	25	1000	1000	1000	398160	0	3018	3037	3037	2414	3	2895	1000	1000	1000	3037	3037	1	1	1001	1000	2	0	0	73	1	16	1	1	2629	1000	3038	3038	3038	3038	3038
1004	3037	23	0	61	2547	25	1000	1000	1000	398160	0	3018	3037	3073	2414	3	2895	1000	1000	1000	3037	3037	1	1	1001	1000	0	0	0	73	1	16	1	1	2629	1000	3038	3038	3038	3038	3038
1004	3037	23	0	89	2547	25	1000	1000	1000	398160	0	3018	3037	3037	2414	3	2895	1000	1000	1000	3037	3037	1	1	1001	1000	0	0	0	73	1	16	1	1	2629	1000	3038	3038	3038	3038	3038
1004	3037	23	0	61	2547	25	1000	1000	1000	398160	0	3018	3037	3037	2414	3	2895	1000	1000	1000	3037	3037	1	1	1001	1000	0	0	0	73	1	16	1	1	2629	1000	3038	3038	3038	3038	3038
1004	3037	24	0	61	2547	25	1000	1000	1000	398160	0	3018	3037	3037	2414	3	2895	1000	1000	1000	3037	3037	1	1	1001	1000	0	0	0	73	1	16	1	1	2629	1000	3038	3038	3038	3038	3038
1004	3037	23	0	61	2547	25	1000	1000	1000	398160	0	3018	3037	3037	2414	3	2895	1000	1000	1000	3037	3037	1	1	1001	1000	0	0	0	73	1	16	1	1	2629	1000	3038	3038	3038	3038	3038
1004	3037	24	0	61	2547	25	1000	1000	1000	399512	0	3018	3037	3037	2414	3	2895	1000	1000	1000	3037	3037	1	1	1001	1000	0	0	0	73	1	16	1	1	2629	1000	3038	3038	3038	3038	3038
1004	3037	24	0	61	2547	25	1000	1000	1000	398160	0	3018	3037	3037	2414	3	2895	1000	1000	1000	3037	3037	1	1	1001	1000	0	0	0	73	1	16	1	1	2629	1000	3038	3038	3038	3038	3038
1004	3037	24	0	61	2547	25	1000	1000	1000	398160	0	3018	3037	3037	2414	3	2895	1000	1000	1000	3037	3037	1	1	1001	1000	3	0	0	73	1	16	1	1	2629	1000	3038	3038	3038	3038	3038

Test 2: Latency 1->2

Code:

  frintm v0.2s, v0.2s

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	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	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 cache writeback (a8)	ac	branch cond mispred nonspec (c5)	branch mispred nonspec (cb)	cd	cf	d0	d2	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	0	251	29547	25	10100	100	10000	100	10000	500	4277160	1	0	30018	30037	30037	28264	3	28745	10100	200	10000	200	10000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	710	0	0	1	16	1	1	29633	0	10000	100	30038	30038	30038	30038	30038
10204	30037	232	0	61	29547	25	10100	100	10000	100	10000	500	4277160	1	0	30018	30037	30037	28264	3	28745	10100	200	10000	200	10000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	710	0	0	1	16	1	1	29647	0	10000	100	30038	30038	30038	30038	30038
10204	30037	232	0	61	29547	25	10100	100	10000	100	10000	500	4277160	1	5	30018	30037	30037	28264	3	28745	10100	200	10000	200	10000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	710	5	5	1	16	1	1	29633	0	10000	100	30038	30038	30038	30038	30038
10204	30037	233	0	61	29547	25	10100	100	10000	100	10000	500	4277160	1	0	30018	30037	30037	28264	3	28745	10100	200	10000	200	10000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	710	0	0	1	16	1	1	29633	0	10000	100	30038	30038	30038	30038	30038
10204	30037	233	0	156	29547	25	10100	100	10000	100	10000	500	4277160	1	0	30018	30037	30037	28264	3	28745	10100	200	10000	200	10000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	710	0	0	1	16	1	1	29633	0	10000	100	30038	30038	30038	30038	30038
10204	30037	233	0	61	29547	25	10100	100	10000	100	10000	500	4277160	1	0	30018	30037	30037	28264	3	28745	10100	200	10000	200	10000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	710	0	0	1	16	1	1	29633	0	10000	100	30038	30038	30038	30038	30038
10204	30037	233	0	61	29547	25	10100	100	10000	100	10000	500	4277160	1	0	30018	30037	30037	28264	3	28745	10100	200	10000	200	10000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	710	0	0	1	16	1	1	29633	0	10000	100	30038	30038	30038	30038	30038
10204	30037	233	0	61	29547	25	10100	100	10000	100	10000	500	4277160	1	0	30018	30037	30037	28264	3	28745	10100	200	10000	200	10000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	710	5	0	1	16	1	1	29633	0	10000	100	30038	30038	30038	30038	30038
10204	30037	233	0	61	29547	25	10110	100	10000	100	10000	500	4277160	1	0	30018	30037	30037	28264	3	28745	10100	200	10000	200	10000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	710	5	0	1	16	1	1	29633	0	10000	100	30038	30038	30038	30038	30038
10204	30037	232	0	61	29547	25	10100	100	10000	100	10000	500	4277160	0	5	30018	30037	30037	28264	3	28745	10100	200	10000	200	10000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	710	0	0	1	16	1	1	29633	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)	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)	ld unit uop (a6)	l1d cache writeback (a8)	ac	branch cond mispred nonspec (c5)	cd	cf	d5	map dispatch bubble (d6)	da	dd	fetch restart (de)	e0	eb	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10024	30037	225	0	0	0	0	0	2	66	29547	25	10010	10	10000	10	10000	50	4277160	0	30018	30037	30037	28286	3	28767	10010	20	10000	20	10000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	644	11	16	0	10	10	29629	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	0	2	66	29547	25	10010	10	10000	10	10000	50	4277160	0	30018	30037	30037	28286	3	28767	10010	20	10000	20	10000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	3	3	0	0	644	11	16	0	5	10	29629	0	10000	10	30038	30038	30038	30038	30038
10024	30037	224	0	0	0	0	0	2	390	29547	25	10010	10	10000	10	10000	50	4277160	0	30018	30037	30037	28286	3	28767	10010	20	10000	20	10000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	42	0	0	0	644	11	16	0	10	10	29629	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	0	2	541	29547	25	10010	10	10000	10	10000	50	4277160	0	30018	30037	30037	28286	3	28767	10010	20	10000	20	10000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	644	10	16	0	11	11	29629	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	0	2	161	29547	25	10010	10	10000	10	10000	50	4277160	0	30018	30037	30037	28286	3	28767	10010	20	10000	20	10000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	644	8	16	0	10	8	29629	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	0	2	66	29547	25	10010	10	10000	10	10000	50	4277160	0	30018	30037	30037	28286	3	28767	10010	20	10000	20	10000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	644	11	16	0	11	10	29629	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	0	2	66	29547	25	10010	10	10000	10	10000	50	4277160	0	30018	30037	30037	28286	3	28767	10010	20	10000	20	10000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	644	10	16	0	10	10	29629	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	0	2	62	29547	25	10010	10	10000	10	10000	50	4277160	0	30018	30037	30037	28286	3	28767	10010	20	10000	20	10000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	644	10	16	0	10	10	29629	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	0	2	62	29547	25	10010	10	10000	10	10000	50	4277160	1	30018	30037	30037	28286	3	28767	10010	20	10000	20	10000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	644	10	16	0	10	5	29629	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	0	2	62	29547	25	10010	10	10000	10	10000	50	4277160	1	30018	30037	30037	28286	3	28767	10010	20	10000	20	10000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	644	10	16	0	10	10	29629	0	10000	10	30038	30038	30038	30038	30038

Test 3: throughput

Count: 8

Code:

  frintm v0.2s, v8.2s
  frintm v1.2s, v8.2s
  frintm v2.2s, v8.2s
  frintm v3.2s, v8.2s
  frintm v4.2s, v8.2s
  frintm v5.2s, v8.2s
  frintm v6.2s, v8.2s
  frintm 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): 0.2505

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	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)	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
80204	20059	155	0	0	0	0	0	0	158	25	80108	100	80008	100	80020	500	640132	20020	20039	20039	9977	6	9990	80120	200	80032	200	80032	20039	20039	1	1	80201	100	99	100	100	80000	100	0	0	3	1	1	1	5118	0	16	0	1	20036	80000	100	20040	20040	20040	20040	20040
80204	20039	155	0	0	0	0	0	0	74	25	80108	100	80008	100	80020	500	640132	20020	20039	20039	9977	6	9990	80120	200	80032	200	80032	20039	20039	1	1	80201	100	99	100	100	80000	100	0	0	0	1	1	1	5118	0	16	0	0	20036	80000	100	20040	20040	20040	20040	20040
80204	20039	155	0	0	0	0	27	0	505	25	80108	100	80008	100	80020	500	640132	20020	20039	20039	9977	6	9990	80120	200	80032	200	80032	20039	20191	1	1	80201	100	99	100	100	80000	100	0	0	0	1	1	1	5118	0	16	0	0	20036	80000	100	20040	20040	20040	20040	20040
80204	20039	160	0	0	0	0	0	0	376	25	80108	100	80008	100	80020	500	640132	20020	20039	20198	9977	6	9990	80120	200	80032	200	80032	20039	20039	5	1	80201	100	99	100	100	80000	100	0	0	0	1	1	1	5118	0	16	0	0	20036	80000	100	20040	20040	20040	20040	20040
80204	20039	155	0	0	0	0	0	0	177	25	80108	100	80008	100	80020	500	640132	20020	20039	20039	9977	6	9990	80120	200	80032	200	80032	20039	20039	1	1	80201	100	99	100	100	80000	100	0	0	3	1	1	1	5118	0	16	0	0	20036	80000	100	20040	20040	20040	20040	20040
80204	20039	155	0	0	0	0	0	0	156	25	80108	100	80008	100	80020	500	640132	20020	20039	20039	9977	6	9990	80120	200	80032	200	80032	20039	20039	1	1	80201	100	99	100	100	80000	100	0	0	0	1	1	1	5118	0	16	0	0	20036	80000	100	20040	20040	20040	20040	20040
80204	20039	155	0	0	0	0	0	0	114	25	80108	100	80008	100	80020	500	640132	20020	20039	20039	9977	6	9990	80120	200	80032	200	80032	20039	20039	1	1	80201	100	99	100	100	80000	100	0	0	0	1	1	1	5118	0	16	1	0	20036	80000	100	20040	20040	20040	20040	20040
80204	20039	155	0	0	0	0	0	0	522	25	80108	100	80008	100	80020	500	640132	20020	20039	20039	9977	6	9990	80120	200	80032	200	80032	20039	20039	1	1	80201	100	99	100	100	80000	100	0	0	0	1	1	1	5118	0	16	0	0	20036	80000	100	20040	20040	20040	20040	20040
80204	20039	156	0	0	0	0	0	0	317	25	80108	100	80008	100	80020	500	640132	20020	20039	20039	9977	6	9990	80120	200	80032	200	80032	20039	20241	1	1	80201	100	99	100	100	80000	100	0	0	0	1	1	1	5118	0	16	0	0	20036	80000	100	20040	20040	20040	20040	20040
80204	20039	155	0	0	0	0	0	0	30	25	80108	100	80008	100	80020	500	640132	20020	20039	20039	9977	6	9990	80120	200	80241	200	80032	20039	20039	1	1	80201	100	99	100	100	80000	100	0	0	0	1	1	1	5118	0	16	0	0	20036	80000	100	20040	20040	20040	20040	20040

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2505

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

retire uop (01)	cycle (02)	03	mmu table walk data (08)	l2 tlb miss instruction (0a)	l2 tlb miss data (0b)	18	19	1e	1f	3a	3f	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	60	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)	l1d tlb miss (a1)	ld unit uop (a6)	l1d cache writeback (a8)	a9	ac	c2	cf	d5	map dispatch bubble (d6)	db	dd	fetch restart (de)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
80024	20039	155	0	0	0	0	0	0	0	0	40	25	80010	10	80000	10	80000	50	640000	1	20020	0	20039	20039	9996	3	10019	80010	20	80000	20	80000	20039	20039	1	1	80021	10	9	10	10	80000	10	0	0	0	0	0	0	0	5020	5	16	0	3	3	20036	80000	10	20040	20040	20040	20040	20040
80024	20039	155	0	0	0	0	0	0	0	0	40	25	80010	10	80000	10	80000	50	640000	0	20020	0	20039	20039	9996	3	10019	80010	20	80000	20	80000	20039	20039	1	1	80021	10	9	10	10	80000	10	0	0	0	0	0	0	0	5020	2	16	0	3	3	20036	80000	10	20040	20040	20040	20040	20040
80024	20039	155	0	0	0	0	0	0	0	0	63	25	80010	10	80000	10	80000	50	640000	0	20020	0	20039	20039	9996	3	10019	80010	20	80000	20	80000	20039	20039	1	1	80021	10	9	10	10	80000	10	0	0	0	0	0	0	0	5020	3	16	0	3	2	20036	80000	10	20040	20040	20040	20040	20040
80024	20039	156	0	0	0	0	0	0	0	0	40	25	80010	10	80000	10	80000	50	640000	1	20020	0	20039	20039	9996	3	10019	80010	20	80000	20	80000	20039	20039	1	1	80021	10	9	10	10	80000	10	0	0	0	0	0	0	0	5020	3	16	0	3	3	20036	80000	10	20040	20040	20040	20040	20040
80024	20039	156	0	0	0	0	0	0	0	0	458	25	80010	10	80000	10	80000	50	640000	1	20020	0	20039	20039	9996	3	10019	80010	20	80000	20	80000	20039	20039	1	1	80021	10	9	10	10	80000	10	0	0	0	0	0	0	0	5020	3	16	0	2	4	20118	80000	10	20115	20143	20093	20040	20199
80024	20039	156	0	0	0	0	0	0	0	0	177	25	80010	10	80000	10	80000	50	640000	0	20020	0	20039	20039	9996	3	10019	80010	20	80000	20	80000	20039	20039	1	1	80021	10	9	10	10	80000	10	0	0	0	0	0	0	0	5020	3	16	0	3	2	20036	80000	10	20040	20040	20040	20040	20040
80024	20039	155	0	0	0	0	0	0	0	0	61	25	80010	10	80000	10	80000	50	640000	0	20020	0	20039	20039	9996	3	10019	80010	20	80000	20	80000	20039	20039	1	1	80021	10	9	10	10	80000	10	0	0	0	0	0	0	0	5020	3	16	0	3	3	20036	80000	10	20040	20040	20040	20040	20040
80024	20039	156	0	0	0	0	0	0	0	0	103	25	80010	10	80000	10	80000	50	640000	1	20020	0	20039	20039	9996	3	10019	80010	20	80000	20	80000	20039	20039	1	1	80021	10	9	10	10	80000	10	0	0	0	0	0	0	0	5020	3	16	0	3	3	20036	80000	10	20040	20040	20040	20040	20040
80024	20039	155	0	0	0	0	0	0	0	2	107	25	80010	10	80000	10	80000	50	640000	0	20020	0	20039	20039	9996	3	10019	80010	20	80000	20	80000	20039	20039	1	1	80021	10	9	10	10	80000	10	0	0	0	0	0	0	0	5020	3	16	0	4	3	20036	80000	10	20040	20040	20040	20040	20040
80024	20039	155	0	0	0	0	0	0	0	0	198	25	80010	10	80000	10	80000	50	640000	1	20020	0	20039	20039	9996	3	10019	80010	20	80000	20	80000	20039	20039	1	1	80021	10	9	10	10	80000	10	0	0	0	0	0	0	0	5020	3	16	0	3	3	20036	80000	10	20040	20040	20040	20040	20040

FRINTM (vector, 2S)

Test 1: uops

1000 unrolls and 1 iteration

Test 2: Latency 1->2

100 unrolls and 100 iterations

1000 unrolls and 10 iterations

Test 3: throughput

100 unrolls and 100 iterations

1000 unrolls and 10 iterations