Firestorm: FCVTZS (vector, integer, 2D) measurements

Code:

  fcvtzs v0.2d, v0.2d

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	19	1e	3f	4e	51	schedule uop (52)	schedule simd uop (54)	dispatch simd uop (57)	ldst uops in schedulers (5b)	60	69	6b	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	24	0	0	103	2547	25	1000	1000	1000	398160	0	3018	0	3037	3037	2414	3	2895	1000	1000	1000	3037	3037	1	1	1001	1000	6	0	73	1	16	1	1	2629	1000	3038	3038	3038	3038	3038
1004	3037	24	0	0	61	2547	25	1000	1000	1000	398160	0	3018	0	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	23	0	0	71	2547	25	1000	1000	1000	398160	0	3018	0	3037	3037	2414	3	2895	1000	1000	1000	3037	3037	1	1	1001	1000	1	0	73	1	16	1	1	2629	1000	3038	3038	3038	3038	3038
1004	3037	24	0	0	61	2547	25	1000	1000	1000	398160	0	3018	0	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	0	61	2547	25	1000	1000	1000	398160	0	3018	0	3037	3037	2414	3	2895	1000	1043	1000	3037	3037	1	1	1001	1000	2	0	73	1	16	1	1	2629	1000	3038	3038	3038	3038	3038
1004	3037	24	0	0	61	2547	25	1000	1000	1043	398160	0	3018	0	3037	3037	2414	3	2895	1000	1000	1000	3037	3037	1	1	1001	1000	1	3	73	1	16	1	1	2629	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	61	2547	25	1000	1000	1000	398160	0	3018	0	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	23	0	12	61	2547	25	1000	1000	1000	398160	0	3018	0	3037	3037	2414	3	2895	1000	1000	1000	3037	3037	1	1	1001	1000	1	0	73	1	16	1	1	2629	1000	3038	3038	3038	3038	3038
1004	3037	24	0	0	61	2547	25	1000	1000	1000	398160	1	3018	0	3037	3037	2414	3	2895	1000	1000	1000	3037	3037	1	1	1001	1000	0	0	73	1	16	1	1	2700	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	61	2547	25	1000	1000	1000	398160	0	3018	0	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

Test 2: Latency 1->2

Code:

  fcvtzs v0.2d, v0.2d

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 instruction (07)	l2 tlb miss instruction (0a)	1e	3f	4e	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	60	69	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	ld unit uop (a6)	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	233	0	0	12	124	29547	25	10100	100	10000	100	10000	500	4277160	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	2	16	2	2	29633	0	10000	100	30038	30038	30038	30038	30038
10204	30037	232	0	0	0	405	29547	25	10100	100	10000	100	10000	500	4277160	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	2	16	2	2	29633	0	10000	100	30038	30038	30038	30038	30038
10204	30037	232	0	0	0	131	29547	25	10100	100	10000	100	10000	500	4277160	0	30018	30037	30037	28264	3	28745	10100	200	10000	200	10000	30037	30037	1	1	10201	100	99	100	100	10000	100	2	0	0	0	0	0	710	2	16	2	2	29633	0	10000	100	30038	30038	30038	30038	30038
10204	30037	233	0	0	0	948	29547	25	10100	100	10000	100	10000	500	4277160	0	30018	30037	30037	28264	3	28745	10124	200	10179	200	10008	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	21	1	1	1	717	1	16	1	1	29649	0	10000	100	30038	30038	30038	30038	30038
10204	30037	232	1	1	0	61	29547	25	10100	100	10000	100	10000	500	4277160	0	30018	30037	30037	28271	6	28740	10100	200	10008	200	10008	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	710	2	16	2	2	29633	0	10000	100	30038	30038	30038	30038	30038
10204	30037	233	0	0	0	82	29547	25	10100	100	10000	100	10000	500	4277160	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	2	16	2	2	29633	0	10000	100	30038	30038	30038	30038	30038
10204	30037	233	0	0	0	124	29547	25	10100	100	10000	100	10000	500	4277160	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	2	16	2	2	29633	0	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	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	2	2	29633	0	10000	100	30038	30038	30038	30038	30038
10204	30037	233	0	0	0	460	29547	25	10100	100	10000	100	10000	500	4277160	0	30064	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	2	2	29633	0	10000	100	30038	30038	30038	30038	30038
10204	30037	233	0	0	0	232	29547	25	10100	100	10000	100	10000	500	4277160	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	2	16	2	2	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	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)	60	69	6b	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d cache writeback (a8)	ac	branch mispred nonspec (cb)	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10024	30037	225	0	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	640	2	16	2	2	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	232	0	0	61	29547	25	10010	10	10000	10	10000	50	4277160	1	30018	0	30085	30132	28286	3	28767	10010	20	10000	20	10000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	682	2	16	2	2	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	61	29547	25	10010	10	10000	10	10000	50	4277160	1	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	640	2	16	2	2	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	61	29547	25	10010	10	10000	10	10000	50	4277160	1	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	640	2	16	2	2	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	61	29547	25	10010	10	10000	10	10000	50	4277160	1	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	640	2	16	2	2	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	61	29547	25	10010	10	10000	10	10000	50	4277160	1	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	640	2	16	2	2	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	61	29547	25	10010	12	10000	10	10000	50	4277160	1	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	640	2	16	2	2	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	61	29547	25	10010	10	10000	10	10000	50	4277160	1	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	640	2	16	2	2	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	61	29547	25	10010	10	10000	10	10000	50	4277160	1	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	640	2	16	2	1	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	233	0	0	61	29547	25	10010	10	10000	10	10000	50	4277160	1	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	640	2	16	2	2	29629	10000	10	30038	30038	30038	30038	30038

Test 3: throughput

Count: 8

Code:

  fcvtzs v0.2d, v8.2d
  fcvtzs v1.2d, v8.2d
  fcvtzs v2.2d, v8.2d
  fcvtzs v3.2d, v8.2d
  fcvtzs v4.2d, v8.2d
  fcvtzs v5.2d, v8.2d
  fcvtzs v6.2d, v8.2d
  fcvtzs v7.2d, v8.2d

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 instruction (0a)	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)	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	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
80204	20039	156	0	0	0	0	0	0	0	560	25	80108	100	80008	100	80020	500	640132	1	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	0	0	0	0	0	1	1	1	5118	1	16	1	2	20036	0	80000	100	20040	20040	20040	20040	20040
80204	20039	155	0	0	0	0	0	0	0	30	25	80108	100	80008	100	80020	500	640132	1	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	0	0	0	0	0	1	1	1	5118	2	16	1	2	20036	0	80000	100	20040	20040	20040	20040	20040
80204	20039	155	0	0	0	0	0	0	0	30	25	80108	100	80008	100	80020	500	640132	0	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	0	0	0	0	0	1	1	1	5118	1	16	2	2	20036	0	80000	100	20040	20040	20040	20040	20040
80204	20039	156	0	0	0	0	0	0	0	30	25	80108	100	80008	100	80020	500	640132	1	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	0	0	0	0	0	1	1	1	5118	2	16	3	1	20036	0	80000	100	20040	20040	20040	20040	20040
80204	20039	155	0	0	0	0	0	0	0	30	25	80108	100	80008	100	80020	500	640132	0	20020	20039	20039	9977	6	9990	80120	200	80032	200	80032	20039	20039	1	1	80201	100	99	100	100	80000	100	4	0	0	0	0	0	0	0	1	1	1	5118	2	16	0	2	20036	0	80000	100	20040	20040	20040	20040	20040
80204	20039	156	0	0	0	0	0	0	0	330	25	80108	100	80008	100	80020	500	640132	1	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	0	0	0	0	0	1	1	1	5118	2	16	3	2	20036	0	80000	100	20040	20040	20040	20040	20040
80204	20039	155	0	0	0	0	0	0	0	30	25	80108	100	80008	100	80020	500	640132	1	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	0	0	0	0	0	1	1	1	5118	3	16	1	2	20036	0	80000	100	20040	20040	20040	20040	20040
80204	20039	155	0	0	0	0	0	0	0	30	25	80108	100	80008	100	80020	500	640132	1	20020	20039	20039	9977	6	9990	80120	200	80032	200	80032	20039	20402	1	1	80201	100	99	100	100	80000	100	0	0	0	1	0	0	0	0	1	1	1	5239	4	28	2	1	20329	0	80000	100	20397	20445	20412	20399	20397
80204	20454	158	0	1	0	8	6	933	616	2036	81	80798	100	80697	102	80852	511	645910	0	20385	20405	20454	10049	23	10203	80937	202	80548	202	80972	20453	20451	9	1	80201	100	99	100	100	80000	100	0	2	2	0	1	0	3538	4	1	1	1	5185	4	115	3	5	20325	2	80000	100	20460	20470	20455	20466	20463
80204	20458	159	1	1	0	2	8	1149	704	3535	175	80891	103	80794	100	80950	500	646724	1	20387	20460	20454	10014	42	10205	81044	204	80853	202	80955	20148	20498	10	1	80201	100	99	100	100	80000	100	0	0	0	0	1	0	0	0	1	1	1	5118	2	16	2	2	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	18	1e	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	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)	cd	cf	d0	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
80024	20039	155	0	0	0	317	25	80010	10	80000	10	80000	50	640000	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	0	0	3	16	0	0	0	5	5	20036	0	80000	10	20040	20040	20040	20040	20040
80024	20039	155	0	3	0	63	25	80010	10	80000	10	80000	50	640000	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	0	0	5020	0	0	3	16	0	0	0	5	5	20036	0	80000	10	20040	20040	20040	20040	20040
80024	20039	155	0	12	0	40	25	80010	10	80000	10	80000	50	640000	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	0	0	3	16	0	0	0	3	3	20036	0	80000	10	20040	20040	20040	20040	20040
80024	20039	156	0	0	0	122	25	80010	10	80000	10	80000	50	640000	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	0	0	5	16	0	0	0	5	4	20036	0	80000	10	20040	20040	20040	20040	20040
80024	20039	156	0	0	0	84	25	80010	10	80000	10	80000	50	640000	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	0	0	3	16	0	0	0	4	4	20036	0	80000	10	20040	20040	20040	20040	20040
80024	20039	155	0	0	0	40	25	80010	10	80000	10	80000	50	640000	0	20020	20039	20039	9996	3	10019	80010	20	80000	20	80000	20039	20039	1	1	80021	10	9	10	10	80000	10	0	3	0	0	5020	0	0	3	16	0	0	0	7	7	20036	0	80000	10	20040	20040	20040	20040	20040
80024	20039	156	0	0	0	40	25	80010	10	80000	10	80000	50	640000	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	0	0	3	16	0	0	0	2	4	20036	0	80000	10	20040	20040	20040	20040	20040
80024	20039	156	0	0	0	40	25	80010	10	80000	10	80000	50	640000	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	0	0	4	16	0	0	0	4	4	20036	0	80000	10	20040	20040	20040	20040	20040
80024	20039	155	0	0	0	40	25	80010	10	80000	10	80000	50	640000	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	0	0	4	16	0	0	0	4	4	20036	0	80000	10	20040	20040	20040	20040	20040
80024	20039	155	0	0	0	40	25	80010	10	80000	10	80000	50	640000	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	0	0	3	16	0	0	0	3	4	20036	0	80000	10	20040	20040	20040	20040	20040

FCVTZS (vector, integer, 2D)

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