Firestorm: FRINT32Z (vector, 2S) measurements

Code:

  frint32z 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)	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	23	0	61	2547	25	1000	1000	1000	398160	3018	3037	3037	2414	3	2895	1000	1000	1000	3037	3037	1	1	1001	1000	0	0	75	2	16	2	2	2626	1000	3038	3038	3038	3038	3038
1004	3037	23	0	61	2547	25	1000	1000	1000	398160	3018	3037	3037	2414	3	2895	1000	1000	1000	3037	3037	1	1	1001	1000	0	0	73	2	16	2	1	2629	1000	3038	3038	3038	3038	3038
1004	3037	24	12	168	2547	25	1000	1000	1000	398160	3018	3037	3037	2414	3	2895	1000	1000	1000	3037	3037	1	1	1001	1000	1	0	75	2	16	2	2	2626	1000	3038	3038	3038	3038	3038
1004	3037	23	0	61	2547	25	1000	1000	1000	398160	3018	3037	3037	2413	3	2895	1000	1000	1000	3037	3037	1	1	1001	1000	0	0	73	1	16	2	2	2629	1000	3038	3038	3038	3038	3038
1004	3037	24	0	61	2547	25	1000	1000	1000	398160	3018	3037	3037	2414	3	2895	1000	1000	1000	3037	3037	1	1	1001	1000	0	0	73	1	16	2	2	2629	1000	3038	3038	3038	3038	3038
1004	3037	23	12	61	2547	25	1000	1000	1000	398160	3018	3037	3037	2413	3	2895	1000	1000	1000	3037	3037	1	1	1001	1000	0	0	73	1	16	2	2	2626	1000	3038	3038	3038	3038	3038
1004	3037	24	0	738	2547	25	1000	1000	1000	398160	3018	3037	3037	2413	3	2895	1000	1000	1000	3037	3037	1	1	1001	1000	0	0	73	2	16	1	1	2629	1000	3038	3038	3038	3038	3038
1004	3037	23	0	156	2547	25	1000	1000	1000	398160	3018	3037	3037	2414	3	2895	1000	1000	1000	3037	3037	1	1	1001	1000	0	0	73	1	16	1	2	2626	1000	3038	3038	3038	3038	3038
1004	3037	23	0	61	2547	25	1000	1000	1000	398160	3018	3037	3037	2414	3	2895	1000	1000	1000	3037	3037	1	1	1001	1000	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	3018	3037	3037	2414	3	2895	1000	1000	1000	3037	3037	1	1	1001	1000	0	0	73	2	16	1	1	2626	1000	3038	3038	3038	3038	3038

Test 2: Latency 1->2

Code:

  frint32z 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	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)	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	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
10204	30037	233	0	0	0	0	0	61	29547	25	10100	100	10000	100	10000	500	4277160	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	1	16	1	1	29633	0	10000	100	30038	30038	30038	30038	30038
10204	30037	233	0	0	0	0	0	85	29547	25	10100	100	10000	100	10000	500	4277160	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	1	16	1	1	29633	0	10000	100	30038	30038	30038	30038	30038
10204	30037	233	0	0	0	12	0	61	29547	25	10100	100	10000	100	10000	500	4277160	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	1	16	1	1	29633	0	10000	100	30038	30038	30038	30038	30038
10204	30037	232	0	0	0	0	0	61	29547	25	10100	100	10000	100	10000	500	4277160	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	1	16	1	1	29633	0	10000	100	30038	30038	30038	30038	30038
10204	30037	233	0	0	0	12	0	1825	29547	25	10100	100	10000	100	10000	500	4277160	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	2	16	1	1	29633	0	10000	100	30038	30038	30038	30038	30038
10204	30037	233	0	0	0	0	0	61	29547	25	10100	100	10000	100	10000	500	4277160	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	1	16	1	1	29633	0	10000	100	30038	30038	30038	30038	30038
10204	30037	241	0	0	0	0	0	2360	29547	25	10100	100	10008	143	10307	680	4285272	30018	30037	30037	28267	3	28818	10256	200	10824	226	11374	30416	30472	5	1	10201	100	99	100	100	10000	100	0	0	0	2	24923	2	838	1	89	2	1	29994	38	10000	100	30323	30517	30565	30552	30517
10204	30565	237	0	11	10	1329	880	7883	29465	233	10227	154	10088	129	11650	739	4291979	30414	30567	30564	28302	54	28947	11962	238	11771	236	11825	30515	30512	12	1	10201	100	99	100	100	10000	100	2	4	0	2	30125	0	868	3	81	2	2	30026	29	10000	100	30599	30568	30516	30559	30564
10204	30610	236	1	5	10	1206	880	6043	29502	212	10230	153	10072	144	11500	785	4289328	30378	30472	30512	28303	40	28873	11342	226	11323	216	10826	30421	30227	10	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	710	1	16	1	1	29633	0	10000	100	30038	30038	30038	30038	30038
10204	30037	233	0	0	0	15	0	61	29547	25	10100	100	10000	100	10000	500	4277160	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	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	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	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	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	86	29547	25	10010	10	10000	10	10000	50	4277160	0	30018	0	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	640	2	16	2	2	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	61	29547	25	10010	10	10000	10	10000	50	4277160	0	30018	0	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	640	2	16	2	2	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	61	29547	25	10010	10	10000	10	10000	50	4277160	0	30018	0	30037	30037	28286	3	28767	10010	20	10000	20	10000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	2	0	0	0	0	640	2	16	2	2	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	61	29547	25	10010	10	10000	10	10000	50	4277160	0	30018	0	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	640	2	16	2	2	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	61	29547	25	10010	10	10000	10	10000	50	4277160	0	30018	0	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	640	2	16	2	2	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	61	29547	25	10010	10	10000	10	10000	50	4277160	0	30018	0	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	640	2	16	2	2	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	61	29547	25	10010	10	10000	10	10000	50	4277160	0	30018	0	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	640	2	16	2	2	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	61	29547	25	10010	10	10000	10	10000	50	4277160	0	30018	0	30037	30037	28286	3	28767	10010	20	10000	20	10000	30037	30037	1	1	10021	10	9	10	10	10000	10	2	0	0	0	0	0	640	2	16	2	2	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	61	29547	25	10010	10	10000	10	10000	50	4277160	0	30018	0	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	640	2	16	2	2	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	61	29547	25	10010	10	10000	10	10000	50	4277160	0	30018	0	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	640	2	16	2	2	29629	10000	10	30038	30038	30038	30038	30038

Test 3: throughput

Count: 8

Code:

  frint32z v0.2s, v8.2s
  frint32z v1.2s, v8.2s
  frint32z v2.2s, v8.2s
  frint32z v3.2s, v8.2s
  frint32z v4.2s, v8.2s
  frint32z v5.2s, v8.2s
  frint32z v6.2s, v8.2s
  frint32z 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	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 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	ec	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
80204	20058	155	12	139	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	1	1	1	5118	0	16	0	0	20036	0	80000	100	20040	20040	20040	20040	20040
80204	20039	155	0	30	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	1	1	1	5118	0	16	0	0	20036	0	80000	100	20040	20040	20040	20040	20040
80204	20039	155	0	76	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	1	1	1	5118	0	16	0	0	20036	0	80000	100	20040	20040	20040	20040	20040
80204	20039	155	0	75	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	1	1	1	5118	0	16	0	0	20036	0	80000	100	20040	20040	20040	20040	20040
80204	20039	155	0	1208	25	80108	100	80008	100	80020	500	640132	20020	20039	20039	9976	9	9986	80120	200	80032	200	80032	20039	20039	1	1	80201	100	99	100	100	80000	100	0	0	1	1	1	5118	0	16	0	0	20036	0	80000	100	20040	20040	20040	20040	20040
80204	20039	156	12	1108	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	1	0	1	1	1	5118	0	16	0	0	20036	0	80000	100	20040	20040	20040	20040	20040
80204	20039	155	0	30	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	1	1	1	5118	0	16	0	0	20036	0	80000	100	20040	20040	20040	20040	20040
80204	20039	155	0	505	25	80108	100	80008	100	80020	500	640132	20020	20039	20039	9977	6	9990	80120	200	80032	200	80032	20039	20039	1	1	80202	100	99	100	100	80000	100	0	0	1	1	1	5118	0	16	0	0	20036	0	80000	100	20040	20040	20040	20040	20040
80204	20039	161	0	30	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	3	1	1	1	5118	0	16	0	0	20036	0	80000	100	20040	20040	20040	20089	20040
80204	20039	155	12	107	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	1	1	1	5118	0	16	0	0	20036	0	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	l2 tlb miss data (0b)	0e	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)	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 tlb miss (a1)	a9	ac	c2	cf	d5	map dispatch bubble (d6)	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	1056	25	80010	10	80000	10	80000	50	640000	0	0	20020	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	5020	7	16	4	5	20036	80000	10	20040	20040	20040	20040	20040
80024	20039	155	0	0	0	0	0	0	0	991	25	80010	10	80000	10	80000	50	640000	1	0	20020	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	5020	3	16	4	5	20036	80000	10	20040	20040	20040	20040	20040
80024	20039	155	0	0	0	0	0	0	0	1468	25	80010	10	80000	10	80000	50	640000	0	0	20020	20039	20039	9996	3	10019	80010	20	80000	20	80000	20039	20039	1	1	80021	10	9	10	10	80000	10	0	0	3	0	5020	5	16	5	3	20036	80000	10	20040	20040	20040	20040	20040
80024	20039	155	0	0	0	0	0	0	0	895	25	80010	10	80000	10	80000	50	640000	0	0	20020	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	5020	5	16	4	6	20036	80000	10	20040	20040	20040	20040	20040
80024	20039	156	0	0	0	0	0	0	0	858	25	80010	10	80000	10	80000	50	640000	0	0	20020	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	5020	3	16	3	6	20036	80000	10	20040	20040	20040	20040	20040
80024	20039	155	0	0	0	0	0	0	0	82	25	80010	10	80000	10	80000	50	640000	0	0	20020	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	5020	3	16	3	6	20036	80000	10	20040	20040	20040	20040	20040
80024	20039	155	0	0	0	0	0	0	0	872	25	80010	10	80000	10	80000	50	640000	0	0	20020	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	5020	3	16	3	5	20036	80000	10	20040	20040	20040	20040	20040
80024	20039	156	0	0	0	0	0	0	0	40	25	80010	10	80000	10	80000	50	640000	0	0	20020	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	5020	7	16	3	5	20036	80000	10	20040	20040	20040	20040	20040
80024	20039	156	0	0	0	0	0	0	0	853	25	80010	10	80000	10	80000	50	640000	0	0	20020	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	5020	3	16	5	5	20036	80000	10	20040	20040	20040	20040	20040
80024	20039	156	0	0	0	0	0	0	0	1020	25	80010	10	80000	10	80000	50	640000	1	1	20020	20039	20039	9996	3	10019	80010	20	80000	20	80000	20039	20039	1	1	80021	10	9	10	10	80000	10	0	0	3	0	5020	6	16	3	5	20036	80000	10	20040	20040	20040	20040	20040

FRINT32Z (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