Firestorm: SCVTF (scalar, integer, S from S) measurements

Code:

  scvtf s0, s0

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)	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	0	3018	3037	3037	2414	3	2895	1000	1000	1000	3037	3037	1	1	1001	1000	0	0	73	3	16	1	1	2629	1000	3038	3038	3038	3038	3038
1004	3037	23	9	61	2547	25	1000	1000	1000	398160	1	3018	3037	3037	2414	3	2895	1000	1000	1000	3037	3037	1	1	1001	1000	0	3	73	1	16	1	1	2629	1000	3038	3038	3038	3038	3038
1004	3037	22	0	82	2547	25	1000	1000	1000	398160	1	3018	3037	3037	2414	3	2895	1000	1000	1000	3037	3037	1	1	1001	1000	0	3	73	1	16	1	1	2629	1000	3038	3038	3038	3038	3038
1004	3037	23	0	61	2547	25	1000	1000	1000	398160	1	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	22	3	61	2547	25	1000	1000	1000	398160	1	3018	3037	3037	2414	3	2895	1000	1000	1000	3037	3037	1	1	1001	1000	0	48	73	1	16	1	1	2629	1000	3038	3038	3038	3038	3038
1004	3037	23	12	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	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	1	126	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	73	1	16	1	1	2629	1000	3038	3038	3038	3038	3038
1004	3037	22	0	61	2547	25	1000	1000	1000	398160	1	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	23	0	61	2547	25	1000	1000	1000	398160	1	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

Test 2: Latency 1->2

Code:

  scvtf s0, s0

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	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)	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	0	0	138	29547	25	10100	100	10000	100	10000	500	4277160	1	30018	30037	30037	28271	6	28741	10100	200	10008	204	10008	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	1	0	1	1	1	717	0	16	0	1	29645	0	10000	100	30038	30038	30038	30038	30038
10204	30084	225	0	0	0	0	51	88	0	103	29547	25	10100	100	10000	100	10000	500	4277160	1	30018	30037	30037	28271	6	28741	10100	200	10008	200	10008	30086	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	1	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	12	0	0	166	29547	25	10100	100	10000	100	10000	500	4277160	1	30018	30037	30037	28264	3	28745	10100	200	10165	200	10000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	1	3	0	0	0	710	1	16	1	1	29633	0	10000	100	30038	30038	30038	30038	30038
10204	30037	224	0	0	0	0	0	0	1	170	29547	25	10100	100	10000	100	10000	500	4277160	1	30018	30037	30037	28264	3	28758	10100	200	10000	200	10000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	1	3	0	0	0	710	1	16	1	1	29633	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	12	0	0	103	29547	25	10100	100	10000	100	10000	500	4277160	1	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	1	3	0	0	0	710	1	16	1	1	29633	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	0	0	103	29547	25	10100	100	10000	100	10000	500	4277160	1	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	3	0	0	0	710	1	16	1	1	29633	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	12	0	0	61	29547	25	10100	100	10000	100	10000	500	4277160	1	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	3	0	0	0	710	1	16	1	1	29633	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	12	0	0	61	29547	25	10100	100	10000	100	10000	500	4277160	1	30018	30037	30037	28264	3	28745	10100	200	10000	200	10000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	1	1	3	0	0	0	710	1	16	1	1	29633	0	10000	100	30038	30038	30038	30038	30038
10204	30037	224	0	0	0	0	12	0	0	189	29547	25	10100	100	10000	100	10000	500	4277160	1	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	1	0	0	0	0	710	1	16	1	1	29633	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	12	0	0	103	29547	25	10100	100	10000	100	10000	500	4277160	1	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	3	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	mmu table walk data (08)	l2 tlb miss data (0b)	18	19	1e	1f	3a	3f	4e	4f	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)	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	12	0	0	126	29547	0	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	1	0	3	0	640	4	16	4	3	29629	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	12	0	0	124	29547	0	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	1	0	0	0	640	4	16	4	3	29629	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	12	0	0	126	29547	0	25	10010	10	10000	10	10000	50	4277160	0	30018	30037	30037	28286	3	28767	10010	20	10000	20	10000	30037	30037	2	1	10021	10	9	10	10	10000	10	0	0	0	10	2	3	0	640	4	16	4	2	29629	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	0	0	0	61	29547	0	25	10010	10	10000	10	10000	50	4277160	0	30018	30037	30037	28286	3	28767	10010	20	10000	20	10162	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	1	0	24798	2	830	4	56	4	3	29973	1	10000	10	30466	30320	30509	30510	30516
10024	30496	229	1	1	4	10	1197	880	0	6013	29457	0	98	10094	19	10080	15	11500	88	4290680	0	30378	30463	30464	28325	43	28954	11520	20	11474	26	10484	30507	30225	11	1	10021	10	9	10	10	10000	10	0	0	0	0	2	27983	0	851	7	96	7	5	29953	3	10000	10	30465	30461	30460	30466	30465
10024	30458	228	0	1	10	9	1320	880	1	6741	29547	0	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	2	2	2	0	2	11056	0	726	7	33	7	4	29629	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	1	8	6	672	440	0	3628	29511	0	25	10010	10	10000	10	10000	50	4277160	0	30018	30037	30037	28286	3	28767	10164	20	10000	20	11452	30178	30275	8	1	10021	10	9	10	10	10000	10	0	0	0	0	0	14075	0	640	3	16	4	4	29629	0	10000	10	30322	30038	30369	30372	30226
10024	30417	226	0	1	1	7	1188	352	0	3060	29538	0	185	10065	17	10000	10	10000	65	4277160	0	30018	30121	30405	28307	37	28823	10914	24	11311	20	10486	30463	30226	9	1	10021	10	9	10	10	10000	10	0	2	0	0	0	3	0	640	5	24	4	6	29629	2	10000	10	30038	30134	30038	30418	30038
10024	30263	226	0	0	8	4	150	0	0	5243	29547	462	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	0	640	4	16	4	3	29629	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	0	0	0	461	29547	0	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	0	640	4	16	3	4	29629	0	10000	10	30038	30038	30038	30038	30038

Test 3: throughput

Count: 8

Code:

  scvtf s0, s8
  scvtf s1, s8
  scvtf s2, s8
  scvtf s3, s8
  scvtf s4, s8
  scvtf s5, s8
  scvtf s6, s8
  scvtf s7, s8

Initialization

  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 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	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)	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	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	20049	150	0	0	0	0	0	0	76	25	80108	100	80008	100	80020	500	640132	0	20108	20112	20039	9977	15	10015	80230	200	80032	200	80032	20039	20039	1	1	80201	100	99	100	100	80000	100	0	1	0	3	1	1	1	5118	1	35	0	0	20036	80000	100	20100	20091	20052	20093	20040
80204	20039	150	0	0	0	0	12	0	259	45	80212	100	80012	100	80128	500	640164	0	20061	20097	20100	9987	18	10017	80228	202	80143	200	80137	20098	20088	2	1	80201	100	99	100	100	80000	100	3	0	4	475	1	1	1	5136	0	52	0	0	20036	80000	100	20102	20099	20095	20103	20091
80204	20144	150	0	1	1	1	168	88	321	64	80213	100	80108	100	80132	500	640964	0	20062	20039	20039	9977	6	9990	80120	200	80138	202	80142	20109	20101	2	1	80201	100	99	100	100	80000	100	0	0	0	0	1	1	1	5118	0	51	0	0	20086	80000	100	20040	20040	20040	20040	20040
80204	20039	150	1	0	0	0	12	0	72	25	80108	100	80008	100	80020	500	640132	0	20073	20090	20090	9987	12	9990	80232	202	80133	200	80140	20098	20091	1	1	80201	100	99	100	100	80000	100	0	1	0	6	1	1	1	5118	0	16	0	1	20036	80000	100	20040	20040	20040	20040	20040
80204	20039	150	0	0	0	0	12	0	156	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	1	0	6	1	1	1	5118	0	16	0	0	20036	80000	100	20040	20040	20040	20040	20040
80204	20039	150	0	0	0	0	3	0	114	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	1	1	1	5118	0	16	0	0	20036	80000	100	20040	20040	20040	20040	20040
80204	20039	150	0	0	0	0	0	0	93	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	1	0	3	1	1	1	5118	0	16	0	0	20036	80000	100	20040	20040	20040	20040	20040
80204	20039	150	0	0	0	0	12	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	1	1	1	5118	0	16	0	0	20036	80000	100	20040	20040	20040	20040	20040
80204	20039	150	0	0	0	0	12	0	72	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	1	0	0	1	1	1	5118	0	16	0	0	20036	80000	100	20040	20040	20040	20040	20040
80204	20039	150	0	0	0	0	12	0	72	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	1	0	3	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	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	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	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
80024	20050	150	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	5020	15	16	6	16	20036	80000	10	20040	20040	20040	20040	20040
80024	20039	150	0	82	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	5020	6	16	6	16	20036	80000	10	20040	20040	20040	20040	20040
80024	20039	150	0	82	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	5020	16	16	5	13	20036	80000	10	20040	20040	20040	20040	20040
80024	20039	150	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	5020	16	16	15	16	20036	80000	10	20040	20040	20040	20040	20040
80024	20039	150	0	82	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	5020	16	16	16	5	20036	80000	10	20040	20040	20040	20040	20040
80024	20039	150	15	45	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	1	0	5020	16	16	14	6	20036	80000	10	20040	20040	20040	20040	20040
80024	20039	150	0	124	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	5020	6	16	16	6	20036	80000	10	20040	20040	20040	20040	20040
80024	20039	150	0	837	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	5020	16	16	13	16	20036	80000	10	20040	20040	20040	20040	20040
80024	20039	150	12	40	25	80010	10	80000	10	80000	50	640000	0	20020	20039	20039	9996	3	10019	80433	20	80000	20	80000	20039	20039	1	1	80021	10	9	10	10	80000	10	0	0	5020	6	16	13	16	20036	80000	10	20040	20040	20040	20040	20040
80024	20039	150	0	82	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	5020	16	16	6	16	20036	80000	10	20040	20040	20040	20040	20040

SCVTF (scalar, integer, S from S)

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