Firestorm: AESIMC measurements

Code:

  aesimc v0.16b, v0.16b

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	2037	15	6	61	1686	25	1000	1000	1000	264521	1	2018	2037	2037	1571	3	1895	1000	1000	1000	2037	2037	1	1	1001	1000	0	0	73	3	16	3	3	1786	1000	2038	2038	2038	2038	2038
1004	2037	15	0	61	1686	25	1000	1000	1000	264521	1	2018	2037	2037	1571	3	1895	1000	1000	1000	2037	2037	1	1	1001	1000	0	0	73	3	16	3	3	1786	1000	2038	2038	2038	2038	2038
1004	2037	15	0	61	1686	25	1000	1000	1000	264521	1	2018	2037	2037	1571	3	1895	1000	1000	1000	2037	2037	1	1	1001	1000	0	0	73	3	16	3	3	1786	1000	2038	2038	2038	2038	2038
1004	2037	15	0	61	1686	25	1000	1000	1000	264521	1	2018	2037	2037	1571	3	1895	1000	1000	1000	2037	2037	1	1	1001	1000	0	0	73	3	16	3	3	1786	1000	2038	2038	2038	2038	2038
1004	2037	15	0	61	1686	25	1000	1000	1000	264521	1	2018	2037	2037	1571	3	1895	1000	1000	1000	2037	2037	1	1	1001	1000	0	0	73	3	16	3	3	1786	1000	2038	2038	2038	2038	2038
1004	2037	15	3	61	1686	25	1000	1000	1000	264521	1	2018	2037	2037	1571	3	1895	1000	1000	1000	2037	2037	1	1	1001	1000	0	0	73	3	16	3	3	1786	1000	2038	2038	2038	2038	2038
1004	2037	15	0	61	1686	25	1000	1000	1000	264521	1	2018	2037	2037	1571	3	1895	1000	1000	1000	2037	2037	1	1	1001	1000	0	0	73	3	16	3	3	1786	1000	2038	2038	2038	2038	2038
1004	2037	15	0	61	1686	25	1000	1000	1000	264521	1	2018	2037	2037	1571	3	1895	1000	1000	1000	2037	2037	1	1	1001	1000	0	0	73	3	16	2	2	1786	1000	2038	2038	2038	2038	2038
1004	2037	15	0	61	1686	25	1000	1000	1000	264521	1	2018	2037	2037	1571	3	1895	1000	1000	1000	2037	2037	1	1	1001	1000	0	0	73	3	16	3	3	1786	1000	2038	2038	2038	2038	2038
1004	2037	15	0	61	1686	25	1000	1000	1000	264521	1	2018	2037	2037	1571	3	1895	1000	1000	1000	2037	2037	1	1	1001	1000	0	0	73	3	16	3	3	1786	1000	2038	2038	2038	2038	2038

Test 2: Latency 1->2

Code:

  aesimc v0.16b, v0.16b

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)	09	l2 tlb miss data (0b)	18	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)	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)	dd	fetch restart (de)	e0	? int output thing (e9)	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10204	20037	155	0	0	0	0	0	0	0	145	19686	25	10100	100	10000	100	10000	500	2847521	20018	0	20037	20084	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	0	710	2	16	2	2	19791	0	10000	100	20038	20038	20038	20038	20038
10204	20037	155	0	0	0	0	0	0	0	61	19686	25	10100	100	10000	100	10000	500	2847521	20018	0	20037	20037	18421	3	18745	10100	200	10000	200	10000	20037	20037	2	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	0	710	2	16	2	2	19791	0	10000	100	20038	20038	20038	20038	20038
10204	20037	155	0	0	0	0	0	0	0	61	19686	25	10135	100	10000	100	10000	500	2847521	20018	0	20037	20037	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	0	710	2	16	2	2	19791	0	10000	100	20038	20038	20038	20038	20038
10204	20037	156	0	0	0	0	0	0	0	61	19686	25	10100	100	10000	100	10000	500	2847521	20018	0	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	0	710	2	16	2	2	19791	0	10000	100	20038	20085	20038	20038	20038
10204	20037	155	0	0	0	0	0	0	0	61	19686	25	10100	100	10000	100	10000	500	2847521	20018	0	20037	20037	18421	3	18745	10100	200	10000	200	10000	20037	20037	1	1	10201	100	99	100	100	10000	100	0	0	0	46	0	3	0	710	2	16	2	2	19791	0	10000	100	20086	20038	20038	20038	20038
10204	20037	155	0	0	0	0	0	0	0	61	19686	25	10100	100	10000	121	10000	500	2847521	20018	0	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	0	710	2	16	2	2	19860	0	10000	100	20038	20038	20038	20038	20038
10204	20037	155	0	0	0	0	0	0	0	61	19686	25	10100	100	10000	100	10000	500	2847521	20018	0	20037	20037	18421	3	18745	10100	200	10000	200	10000	20037	20037	1	1	10201	100	99	100	100	10000	100	0	2	0	0	0	0	0	710	2	16	2	2	19791	0	10000	100	20038	20038	20038	20038	20038
10204	20037	156	0	0	0	0	0	0	0	61	19686	25	10100	100	10000	100	10000	500	2847521	20018	0	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	0	710	2	16	2	2	19862	0	10000	100	20038	20038	20133	20085	20038
10204	20037	155	0	0	0	0	0	0	0	61	19686	25	10100	100	10000	100	10000	500	2847521	20018	0	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	0	710	2	16	2	2	19791	0	10000	100	20038	20038	20038	20038	20038
10204	20037	155	0	0	0	0	0	0	0	1131	19686	45	10100	100	10024	117	10000	500	2847521	20018	0	20037	20037	18421	3	18745	10100	200	10331	200	10000	20037	20037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	0	710	2	16	2	2	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	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)	l1d tlb miss (a1)	ld unit uop (a6)	st unit uop (a7)	l1d cache writeback (a8)	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	156	0	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	640	2	16	2	2	19786	0	10000	10	20133	20038	20038	20038	20038
10024	20037	155	0	0	0	0	0	0	0	0	61	19686	25	10010	10	10000	10	10000	50	2847521	0	20018	20037	20037	18443	8	18767	10010	20	10000	20	10000	20037	20037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	0	640	2	16	2	2	19786	0	10000	10	20038	20038	20038	20038	20038
10024	20037	155	0	0	0	0	0	0	0	0	61	19686	25	10010	10	10000	10	10000	50	2847521	1	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	640	2	16	2	2	19786	0	10000	10	20038	20038	20038	20038	20038
10024	20037	156	0	0	0	0	0	0	0	1	61	19686	25	10010	10	10000	10	10000	50	2850049	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	640	2	16	2	2	19786	0	10000	10	20038	20038	20038	20038	20038
10024	20037	155	0	0	0	0	1	0	320	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	640	2	16	2	2	19786	0	10000	10	20038	20038	20038	20038	20038
10024	20037	155	0	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	640	2	16	2	2	19786	0	10000	10	20038	20038	20038	20038	20038
10024	20037	155	0	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	2	0	0	0	0	0	640	2	16	2	2	19786	0	10000	10	20038	20038	20038	20038	20038
10024	20037	155	0	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	640	2	16	2	2	19786	0	10000	10	20038	20038	20038	20038	20038
10024	20037	155	0	0	1	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	640	2	16	2	2	19786	0	10000	10	20038	20038	20038	20038	20038
10024	20037	156	0	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	2	0	2	0	0	6115	0	640	2	16	2	2	19786	0	10000	10	20038	20038	20038	20038	20038

Test 3: throughput

Count: 8

Code:

  aesimc v0.16b, v8.16b
  aesimc v1.16b, v8.16b
  aesimc v2.16b, v8.16b
  aesimc v3.16b, v8.16b
  aesimc v4.16b, v8.16b
  aesimc v5.16b, v8.16b
  aesimc v6.16b, v8.16b
  aesimc v7.16b, v8.16b

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)	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)	ld unit uop (a6)	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	20059	155	0	1	0	1	0	0	436	25	80108	100	80008	100	80020	500	640132	1	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	0	1	1	1	5118	0	16	0	0	20035	0	80000	100	20039	20039	20039	20039	20039
80204	20038	156	0	0	0	0	0	0	29	25	80108	100	80008	100	80020	500	640132	1	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	0	1	1	1	5118	0	16	0	0	20035	0	80000	100	20039	20039	20039	20039	20039
80204	20038	155	0	0	0	0	0	0	138	25	80108	100	80008	100	80020	500	640132	1	20019	20038	20094	9977	6	9989	80120	200	80032	200	80135	20038	20038	1	1	80201	100	99	100	100	80000	100	0	0	0	0	0	0	1	1	1	5118	0	16	0	0	20035	0	80000	100	20039	20039	20039	20039	20039
80204	20038	155	0	0	2	0	0	0	739	25	80108	100	80008	100	80020	500	640132	1	20019	20038	20038	10004	6	9989	80120	200	80032	200	80032	20038	20038	1	1	80201	100	99	100	100	80000	100	0	0	0	0	0	4	1	1	1	5137	0	16	0	0	20035	0	80000	100	20039	20039	20039	20039	20039
80204	20038	156	0	0	0	0	0	0	52	25	80108	100	80008	100	80020	500	640132	1	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	0	1	1	1	5118	0	16	0	0	20035	0	80000	100	20039	20039	20039	20039	20039
80204	20038	155	0	0	0	0	0	132	151	25	80108	100	80008	100	80020	500	640132	0	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	4	1	1	1	5118	0	16	0	0	20035	0	80000	100	20039	20039	20039	20039	20039
80204	20038	155	0	0	0	0	0	0	136	25	80108	100	80008	100	80020	500	640132	1	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	0	1	1	1	5118	0	16	0	0	20035	0	80000	100	20039	20039	20039	20039	20039
80204	20038	155	0	0	0	0	0	0	136	25	80108	100	80008	100	80020	500	640132	1	20019	20038	20038	9977	6	9989	80120	200	80032	200	80032	20038	20038	1	1	80201	100	99	100	100	80000	100	0	0	1	0	0	0	1	1	1	5118	2	30	0	0	20035	0	80000	100	20039	20039	20039	20039	20039
80204	20038	156	0	0	0	0	0	0	918	25	80108	100	80008	100	80020	500	640132	1	20019	20038	20138	9977	6	9989	80120	200	80032	200	80032	20038	20038	1	1	80201	100	99	100	100	80000	100	0	0	0	0	0	0	1	1	1	5118	0	16	0	0	20035	0	80000	100	20039	20039	20039	20039	20039
80204	20108	156	0	0	0	0	0	0	92	25	80108	100	80008	100	80020	500	640132	1	20019	20038	20087	9985	6	9989	80120	200	80032	200	80032	20038	20038	1	1	80201	100	99	100	100	80000	100	0	0	0	0	0	0	1	1	1	5118	0	16	0	0	20035	0	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	l1i tlb fill (04)	mmu table walk data (08)	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	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)	ld unit uop (a6)	l1d cache writeback (a8)	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	20051	156	0	0	0	0	0	0	0	0	87	25	80102	10	80093	10	80000	50	640000	1	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	0	0	5020	2	16	5	5	20035	80000	10	20039	20039	20107	20039	20039
80024	20038	156	0	0	0	0	0	0	0	0	39	25	80010	10	80000	10	80000	50	640000	1	20019	20038	20038	9996	3	10018	80010	20	80000	20	80000	20038	20038	2	1	80021	10	9	10	10	80000	10	0	0	0	0	0	0	5020	4	16	3	4	20035	80000	10	20039	20039	20039	20039	20039
80024	20038	156	0	0	0	0	0	0	0	0	39	82	80010	10	80187	10	80000	50	640000	1	20076	20038	20088	9996	3	10018	80010	20	80097	20	80098	20038	20038	1	1	80021	10	9	10	10	80000	10	0	0	0	0	0	0	5020	3	16	3	3	20035	80000	10	20039	20039	20039	20039	20112
80024	20038	155	0	0	1	0	0	132	88	0	292	25	80010	10	80000	10	80000	50	640000	0	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	0	0	5020	4	16	4	5	20035	80000	10	20039	20039	20039	20039	20039
80024	20038	155	0	0	1	2	0	0	0	0	123	25	80010	10	80000	10	80000	50	640000	0	20019	20038	20038	9996	3	10071	80010	20	80000	20	80000	20038	20038	1	1	80021	10	9	10	10	80000	10	0	0	0	0	0	0	5020	7	16	3	4	20035	80000	10	20039	20089	20039	20039	20039
80024	20038	155	0	0	0	0	0	0	0	0	39	25	80010	10	80000	10	80000	50	640000	0	20019	20038	20090	9996	3	10018	80107	20	80000	20	80000	20038	20038	1	1	80021	10	9	10	10	80000	10	0	0	0	0	0	0	5020	2	16	5	5	20035	80000	10	20039	20039	20039	20039	20039
80024	20038	155	0	0	0	0	0	0	0	0	39	25	80198	10	80000	10	80097	50	640000	0	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	0	0	5020	4	16	4	4	20035	80000	10	20039	20088	20039	20039	20039
80024	20038	156	0	0	0	0	0	0	0	0	60	60	80010	10	80000	10	80000	50	640000	0	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	0	0	5020	4	40	3	4	20035	80000	10	20039	20039	20039	20039	20039
80024	20038	155	0	0	0	0	0	0	0	0	83	25	80010	10	80000	10	80000	50	640000	1	20019	20038	20038	9996	3	10018	80010	20	80000	20	80000	20038	20038	1	1	80021	10	9	10	10	80000	10	0	2	0	2	0	0	5020	3	16	5	5	20035	80000	10	20039	20039	20039	20039	20039
80024	20038	155	0	0	0	0	0	0	0	0	729	25	80010	10	80000	10	80000	50	640000	0	20019	20038	20038	9996	3	10018	80010	20	80000	20	80000	20109	20038	1	1	80021	10	9	10	10	80000	10	0	0	0	0	0	0	5020	3	16	4	4	20035	80000	10	20039	20039	20039	20039	20039

AESIMC

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