Firestorm: FMOV (register, S) measurements

Code:

  fmov 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	map dispatch bubble (d6)	e0	? simd retires (ee)	f5	f6	f7	f8	fd
1004	2037	16	0	82	1686	25	1000	1000	1000	264521	0	2018	2037	2037	1571	3	1895	1000	1000	1000	2037	2037	1	1	1001	1000	0	0	73	16	1786	1000	2038	2038	2038	2038	2038
1004	2037	16	0	123	1686	25	1000	1000	1000	264521	0	2018	2037	2037	1571	3	1895	1000	1000	1000	2037	2037	1	1	1001	1000	1	3	73	16	1786	1000	2038	2038	2038	2038	2038
1004	2037	16	0	587	1686	25	1000	1000	1000	264521	0	2018	2037	2037	1571	3	1895	1000	1000	1000	2037	2037	1	1	1001	1000	0	0	73	16	1786	1000	2038	2038	2038	2038	2038
1004	2037	16	0	206	1686	25	1000	1000	1000	264521	0	2018	2037	2037	1571	3	1895	1000	1000	1000	2037	2037	1	1	1001	1000	0	0	73	16	1786	1000	2038	2038	2038	2038	2038
1004	2037	16	0	61	1686	25	1000	1000	1000	264521	0	2018	2037	2037	1571	3	1895	1000	1000	1000	2037	2037	1	1	1001	1000	0	0	73	16	1786	1000	2038	2038	2038	2038	2038
1004	2037	16	0	109	1686	25	1000	1000	1000	264521	0	2018	2037	2037	1571	3	1895	1000	1000	1000	2037	2037	1	1	1001	1000	0	0	73	16	1786	1000	2038	2038	2038	2038	2038
1004	2037	16	0	61	1686	25	1000	1000	1000	264521	0	2018	2037	2037	1571	3	1895	1000	1000	1000	2037	2037	1	1	1001	1000	0	0	73	16	1786	1000	2038	2038	2038	2038	2038
1004	2037	16	0	61	1686	25	1000	1000	1000	264521	0	2018	2037	2037	1571	3	1895	1000	1000	1000	2037	2037	1	1	1001	1000	0	0	73	16	1786	1000	2038	2038	2038	2038	2038
1004	2037	16	0	61	1686	25	1000	1000	1000	264521	0	2018	2037	2037	1571	3	1895	1000	1000	1000	2037	2037	1	1	1001	1000	0	0	73	16	1786	1000	2038	2038	2038	2038	2038
1004	2037	16	0	61	1686	25	1000	1000	1000	264521	0	2018	2037	2037	1571	3	1895	1000	1000	1000	2037	2037	1	1	1001	1000	0	0	73	16	1786	1000	2038	2038	2038	2038	2038

Test 2: Latency 1->2

Code:

  fmov 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): 2.0037

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

retire uop (01)	cycle (02)	03	mmu table walk data (08)	18	19	1e	1f	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)	ld unit uop (a6)	l1d cache writeback (a8)	a9	ac	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	20037	160	0	0	0	0	0	125	19686	25	10100	100	10000	100	10000	500	2847521	20018	20037	20037	18421	3	18745	10100	200	10000	200	10000	20037	20037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	710	1	16	1	1	19791	0	10000	100	20038	20038	20038	20038	20038
10204	20037	160	0	0	0	30	0	61	19686	25	10100	100	10000	100	10000	500	2847521	20018	20037	20037	18421	3	18745	10100	200	10165	200	10168	20037	20037	2	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	710	1	16	1	1	19791	0	10000	100	20038	20038	20038	20038	20038
10204	20037	160	0	0	0	33	0	110	19686	25	10100	100	10000	100	10000	500	2847521	20018	20037	20037	18421	3	18745	10100	200	10000	200	10000	20037	20037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	710	1	16	1	1	19791	0	10000	100	20038	20038	20038	20038	20038
10204	20037	161	0	0	0	33	0	103	19686	25	10100	100	10000	100	10000	500	2847521	20018	20037	20037	18421	3	18745	10100	200	10000	200	10000	20037	20037	1	1	10201	100	99	100	100	10000	100	0	0	0	1	0	0	710	1	16	1	1	19791	0	10000	100	20038	20038	20038	20038	20038
10204	20037	161	0	0	0	30	0	117	19686	25	10100	100	10000	100	10000	500	2847521	20018	20037	20037	18421	3	18745	10100	200	10000	200	10000	20037	20037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	710	1	16	1	1	19791	0	10000	100	20038	20038	20038	20038	20038
10204	20037	161	0	0	0	39	0	82	19686	25	10100	100	10000	100	10000	500	2847521	20018	20037	20037	18421	3	18745	10100	200	10000	200	10000	20037	20037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	710	1	16	1	1	19791	0	10000	100	20038	20038	20038	20038	20038
10204	20037	161	0	0	0	21	0	306	19686	25	10119	100	10000	100	10000	626	2847521	20018	20037	20084	18421	7	18745	10100	200	10000	200	10000	20037	20037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	710	1	16	1	1	19791	0	10000	100	20038	20038	20038	20038	20038
10204	20037	160	0	0	0	42	0	103	19686	25	10100	100	10000	100	10000	500	2847521	20018	20037	20037	18421	3	18745	10100	200	10000	200	10000	20037	20037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	710	1	16	1	1	19791	0	10000	100	20038	20038	20038	20038	20038
10204	20037	161	0	0	0	51	176	61	19686	25	10100	100	10000	100	10000	500	2847521	20018	20037	20037	18421	3	18745	10100	200	10000	200	10000	20037	20037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	710	1	16	1	1	19791	0	10000	100	20038	20038	20038	20038	20038
10204	20037	161	0	0	0	33	0	138	19686	25	10100	100	10000	100	10000	500	2847521	20018	20037	20037	18421	3	18745	10100	200	10000	200	10000	20037	20037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	710	1	16	1	1	19791	0	10000	100	20038	20038	20038	20038	20038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

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

retire uop (01)	cycle (02)	03	mmu table walk data (08)	09	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)	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	20037	161	0	0	0	0	0	9	0	145	19686	25	10010	10	10000	10	10000	50	2847521	0	20018	20037	20037	18443	3	18767	10010	20	10000	20	10000	20037	20037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	1	0	0	0	640	1	16	1	2	19786	2	10000	10	20038	20038	20038	20038	20038
10024	20037	161	0	0	0	0	0	0	0	61	19686	25	10010	10	10000	10	10000	50	2847521	0	20018	20037	20037	18443	3	18767	10010	20	10000	20	10000	20037	20037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	0	0	640	1	16	1	1	19786	0	10000	10	20038	20038	20038	20038	20038
10024	20037	161	0	0	0	0	0	3	0	61	19686	25	10010	10	10000	10	10000	50	2847521	0	20018	20037	20037	18443	3	18767	10010	20	10000	20	10000	20037	20037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	0	0	640	1	16	1	1	19786	0	10000	10	20038	20038	20038	20038	20038
10024	20037	161	0	0	0	0	0	3	0	61	19686	25	10010	10	10000	10	10000	50	2847521	0	20018	20037	20037	18443	3	18767	10010	20	10000	20	10000	20037	20037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	0	0	640	1	16	1	1	19786	0	10000	10	20038	20038	20038	20038	20038
10024	20037	161	0	0	0	0	0	6	352	61	19686	25	10010	10	10000	10	10000	50	2847521	0	20018	20037	20037	18443	3	18767	10010	20	10000	20	10000	20037	20037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	0	0	640	1	16	1	1	19786	0	10000	10	20038	20038	20038	20038	20038
10024	20037	160	0	0	0	0	0	3	0	61	19686	25	10010	10	10000	10	10000	50	2847521	0	20018	20037	20037	18443	3	18767	10010	20	10000	20	10000	20037	20037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	0	0	640	1	16	1	1	19786	0	10000	10	20038	20038	20085	20038	20038
10024	20037	160	0	0	0	0	0	3	0	82	19686	25	10010	10	10000	10	10000	50	2847521	0	20018	20037	20037	18443	3	18767	10010	20	10000	20	10000	20037	20037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	0	0	640	1	16	1	1	19786	0	10000	10	20038	20038	20038	20038	20038
10024	20037	161	0	0	0	0	0	3	0	498	19686	25	10010	10	10000	10	10000	50	2847521	0	20018	20037	20037	18443	3	18767	10010	20	10000	20	10000	20037	20037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	0	0	640	1	16	1	1	19786	0	10000	10	20038	20038	20038	20038	20038
10024	20037	160	0	0	0	0	0	3	0	61	19686	25	10010	10	10000	10	10000	50	2847521	0	20018	20037	20037	18443	3	18767	10010	20	10000	20	10000	20037	20037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	1	0	0	0	640	1	16	1	1	19786	0	10000	10	20038	20038	20038	20038	20038
10024	20037	161	0	0	0	0	0	153	88	103	19686	25	10010	10	10000	10	10000	50	2847521	0	20018	20037	20037	18443	3	18767	10010	20	10000	20	10000	20037	20037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	0	0	640	1	16	1	1	19786	0	10000	10	20038	20038	20038	20038	20038

Test 3: throughput

Count: 8

Code:

  fmov s0, s8
  fmov s1, s8
  fmov s2, s8
  fmov s3, s8
  fmov s4, s8
  fmov s5, s8
  fmov s6, s8
  fmov 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)	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)	ac	branch cond mispred nonspec (c5)	branch mispred nonspec (cb)	cd	cf	d0	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
80204	20061	161	0	0	0	0	0	352	538	25	80108	100	80008	100	80020	500	640132	20059	20038	20139	9977	6	9989	80120	200	80032	200	80032	20038	20038	2	1	80201	100	99	100	100	80000	100	0	2	0	0	0	1	1	1	5118	0	0	16	0	0	20035	80000	100	20039	20039	20039	20039	20039
80204	20038	161	0	0	0	0	9	0	420	25	80108	100	80008	100	80020	511	640132	20019	20038	20038	9977	6	9989	80120	200	80032	200	80134	20048	20048	1	1	80201	100	99	100	100	80000	100	0	0	0	0	3	2	2	2	5160	1	2	23	2	2	20045	80000	100	20039	20039	20039	20039	20039
80204	20038	161	0	1	1	0	0	0	328	25	80108	100	80008	100	80020	500	640940	20019	20038	20038	9977	6	10014	80120	200	80032	200	80032	20038	20089	1	1	80201	100	99	100	100	80000	100	2	0	0	0	0	1	1	1	5118	0	1	16	0	0	20035	80000	100	20039	20039	20090	20039	20039
80204	20038	161	0	0	0	0	21	0	101	25	80108	100	80108	100	80020	500	640132	20019	20038	20038	9977	6	9989	80120	200	80032	200	80135	20038	20038	1	1	80201	100	99	100	100	80000	100	0	0	0	0	3	1	1	1	5135	0	0	16	2	0	20035	80000	100	20039	20039	20039	20039	20039
80204	20038	161	0	0	0	0	21	0	484	26	80211	100	80016	100	80028	500	640196	20028	20049	20048	9976	9	9986	80128	200	80038	200	80136	20049	20049	2	1	80201	100	99	100	100	80000	100	0	0	0	1	460	2	2	2	5128	1	2	23	2	2	20045	80000	100	20049	20076	20049	20049	20049
80204	20049	161	0	0	0	1	159	0	64	26	80116	100	80016	100	80028	500	640968	20028	20100	20048	9976	10	9986	80128	200	80038	200	80038	20048	20049	2	1	80201	100	99	100	100	80000	100	0	0	0	1	3	2	2	2	5128	1	3	23	2	2	20045	80000	100	20050	20049	20049	20049	20049
80204	20048	161	0	0	1	0	15	0	306	26	80116	100	80016	100	80028	500	640196	20028	20048	20048	9976	10	9986	80128	200	80038	200	80038	20048	20048	1	1	80201	100	99	100	100	80000	100	0	0	0	1	6	2	2	2	5128	1	2	36	2	2	20045	80000	100	20049	20101	20050	20049	20049
80204	20048	161	0	0	1	0	69	0	64	25	80108	100	80008	100	80126	500	640132	20019	20038	20038	9977	6	10013	80120	200	80032	200	80032	20038	20038	1	1	80201	100	99	100	100	80000	100	0	0	0	0	0	1	1	1	5118	0	1	16	0	0	20035	80000	100	20039	20039	20039	20039	20039
80204	20038	160	0	0	0	0	9	0	185	25	80108	100	80008	100	80020	500	640132	20019	20038	20038	9977	6	9989	80120	200	80032	200	80032	20038	20038	1	1	80201	100	99	100	100	80000	100	0	0	0	0	0	1	1	1	5118	0	0	16	2	0	20035	80000	100	20039	20039	20039	20039	20147
80204	20038	161	0	0	0	0	24	0	29	25	80108	100	80008	100	80020	500	640132	20019	20038	20038	9977	6	9989	80120	200	80032	200	80032	20038	20038	1	1	80201	100	99	100	100	80000	100	0	0	0	0	0	1	1	1	5118	0	0	16	0	0	20035	80000	100	20039	20039	20039	20039	20039

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 instruction (07)	mmu table walk data (08)	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 tlb miss (a1)	l1d cache writeback (a8)	ac	cf	d5	map dispatch bubble (d6)	d9	dd	fetch restart (de)	e0	? int output thing (e9)	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
80024	20058	161	0	0	33	0	39	25	80010	10	80000	10	80000	50	640000	20019	20038	20038	9996	3	10018	80010	20	80000	20	80000	20038	20038	1	1	80021	10	9	10	10	80000	10	0	0	0	0	5020	4	16	0	3	4	20035	0	80000	10	20039	20039	20039	20039	20039
80024	20038	161	0	0	3	352	39	25	80010	10	80000	10	80000	50	640000	20019	20038	20038	9996	3	10018	80010	20	80098	20	80000	20038	20038	1	1	80021	10	9	10	10	80000	10	0	0	0	0	5020	3	16	0	5	5	20035	0	80000	10	20039	20039	20039	20039	20039
80024	20038	161	0	0	501	0	514	25	80010	10	80000	10	80000	50	640000	20019	20038	20038	9996	3	10018	80010	20	80000	20	80000	20038	20038	1	1	80021	10	9	10	10	80000	10	0	0	0	0	5020	5	16	0	4	4	20035	0	80000	10	20039	20039	20039	20039	20039
80024	20038	161	0	0	3	0	39	25	80010	10	80000	10	80000	50	640000	20019	20038	20038	9996	3	10018	80010	20	80000	20	80000	20038	20038	1	1	80021	10	9	10	10	80000	10	0	0	0	0	5020	3	16	0	4	3	20035	0	80000	10	20039	20039	20039	20039	20039
80024	20038	160	0	0	6	0	81	25	80010	10	80000	10	80000	50	640000	20019	20038	20038	9996	3	10018	80010	20	80000	20	80000	20038	20038	1	1	80021	10	9	10	10	80000	10	0	0	0	0	5020	6	16	0	4	4	20035	0	80000	10	20039	20039	20039	20039	20039
80024	20038	161	0	0	3	0	109	25	80010	10	80000	10	80000	50	640000	20019	20038	20038	9996	3	10018	80010	20	80000	20	80000	20038	20038	1	1	80021	10	9	10	10	80000	10	0	0	0	0	5020	3	16	0	4	4	20035	0	80000	10	20039	20039	20039	20039	20039
80024	20038	161	0	0	153	0	39	25	80010	10	80000	10	80000	50	640000	20019	20038	20038	9996	3	10018	80010	20	80000	20	80000	20038	20038	1	1	80021	10	9	10	10	80000	10	0	0	0	0	5020	3	16	0	6	4	20035	0	80000	10	20039	20039	20039	20039	20039
80024	20038	161	0	0	6	0	60	25	80010	10	80000	10	80000	50	640000	20019	20038	20038	9996	3	10018	80010	20	80000	20	80000	20038	20038	1	1	80021	10	9	10	10	80000	10	0	0	0	0	5020	4	16	0	3	4	20035	0	80000	10	20039	20039	20039	20039	20039
80024	20038	161	0	0	15	0	39	25	80010	10	80000	10	80000	50	640000	20019	20038	20038	9996	25	10018	80010	20	80000	20	80000	20038	20038	1	1	80021	10	9	10	10	80000	10	0	0	0	3	5020	4	16	0	4	4	20035	0	80000	10	20039	20039	20039	20039	20039
80024	20038	161	0	0	6	0	39	25	80010	10	80000	10	80000	50	640000	20019	20038	20038	9996	3	10018	80010	20	80000	20	80000	20038	20038	1	1	80021	10	9	10	10	80000	10	0	0	0	3	5020	4	16	0	4	4	20035	0	80000	10	20039	20039	20039	20039	20039

FMOV (register, 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