Firestorm: BFI (64-bit) measurements

Code:

  bfi x0, x1, #3, #7

Initialization

  mov x0, 1

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 1.000

Issues: 1.000

Integer unit issues: 1.000

Load/store unit issues: 0.000

SIMD/FP unit issues: 0.000

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)	dispatch int uop (56)	int uops in schedulers (59)	60	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map int uop inputs (7f)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst int alu (97)	l1d tlb access (a0)	l1d cache writeback (a8)	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? int output thing (e9)	? int retires (ef)	f5	f6	f7	f8	fd
1004	1036	8	0	47	25	1000	1000	1000	5999	1	1036	1036	864	3	894	1000	1000	2000	1036	164	1	1	1001	1000	0	0	73	1	16	1	1	1032	1000	1000	1037	1037	1037	1037	1037
1004	1036	8	0	47	25	1000	1000	1000	5999	1	1036	1036	864	3	894	1000	1000	2000	1036	164	1	1	1001	1000	0	0	73	1	16	1	1	1032	1000	1000	1037	1037	1037	1037	1037
1004	1036	8	0	47	25	1000	1000	1000	5999	1	1036	1036	864	3	894	1000	1000	2000	1036	164	1	1	1001	1000	0	0	73	1	16	1	1	1032	1000	1000	1037	1037	1037	1037	1037
1004	1036	8	0	47	25	1000	1000	1000	5999	1	1036	1036	864	3	894	1000	1000	2000	1036	164	1	1	1001	1000	0	0	73	1	16	1	1	1032	1000	1000	1037	1037	1037	1037	1037
1004	1036	8	0	47	25	1000	1000	1000	5999	1	1036	1036	864	3	894	1000	1000	2000	1036	164	1	1	1001	1000	0	0	73	1	16	1	1	1032	1000	1000	1037	1037	1037	1037	1037
1004	1036	7	0	47	25	1000	1000	1000	5999	1	1036	1036	864	3	894	1000	1000	2000	1036	164	1	1	1001	1000	0	0	73	1	16	1	1	1032	1000	1000	1037	1037	1037	1037	1037
1004	1036	8	0	47	25	1000	1000	1000	5999	1	1036	1036	864	3	894	1000	1000	2000	1036	164	1	1	1001	1000	0	0	73	1	16	1	1	1032	1000	1000	1037	1037	1037	1037	1037
1004	1036	8	0	47	25	1000	1000	1000	5999	1	1036	1036	864	3	894	1000	1000	2000	1036	164	1	1	1001	1000	0	0	73	1	16	1	1	1032	1000	1000	1037	1037	1037	1037	1037
1004	1036	8	0	47	25	1000	1000	1000	5999	1	1036	1036	864	3	894	1000	1000	2000	1036	164	1	1	1001	1000	0	0	73	1	16	1	1	1032	1000	1000	1037	1037	1037	1037	1037
1004	1036	7	0	47	25	1000	1000	1000	5999	1	1036	1036	864	3	894	1000	1000	2000	1036	164	1	1	1001	1000	0	0	73	1	16	1	1	1032	1000	1000	1037	1037	1037	1037	1037

Test 2: Latency 1->1

Code:

  bfi x0, x1, #3, #7

Initialization

  mov x0, 1

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 1.0036

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

retire uop (01)	cycle (02)	03	l2 tlb miss data (0b)	18	19	1e	3f	51	schedule uop (52)	schedule int uop (53)	dispatch int uop (56)	int uops in schedulers (59)	60	69	6a	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map int uop inputs (7f)	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)	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	? int output thing (e9)	? int retires (ef)	f5	f6	f7	f8	fd
10204	10037	75	0	0	0	0	59	25	10100	10100	10100	60499	1	49	6956	10036	10036	8721	6	8739	10100	10208	20216	10037	162	1	1	10201	100	99	100	10100	100	0	0	1	1	1	717	1	16	1	1	10033	10000	10100	10037	10037	10037	10037	10037
10204	10036	75	0	0	0	0	267	25	10100	10100	10100	60499	1	49	6956	10036	10036	8721	7	8739	10100	10208	20216	10036	162	1	1	10201	100	99	100	10100	100	0	0	1	1	1	718	1	16	1	1	10033	10000	10100	10037	10037	10037	10037	10037
10204	10036	75	0	1	0	0	36	25	10100	10100	10100	60499	1	49	6956	10036	10036	8721	7	8740	10100	10208	20216	10036	162	1	1	10201	100	99	100	10100	100	14	0	1	1	1	718	1	16	1	1	10033	10000	10100	10037	10037	10037	10037	10037
10204	10036	75	0	0	0	0	36	25	10100	10100	10100	60499	1	49	6956	10036	10036	8721	7	8740	10100	10208	20216	10036	162	1	1	10201	100	99	100	10100	100	0	0	1	1	1	717	1	16	1	1	10033	10000	10100	10037	10037	10037	10037	10037
10204	10036	75	0	0	0	0	100	25	10100	10100	10100	60499	1	49	6956	10036	10036	8721	6	8740	10100	10208	20216	10036	162	1	1	10201	100	99	100	10100	100	0	0	1	1	1	718	1	16	1	1	10033	10000	10100	10037	10037	10037	10037	10037
10204	10036	75	0	0	0	0	99	25	10100	10100	10100	60499	1	49	6956	10036	10036	8721	7	8739	10100	10208	20216	10036	162	1	1	10201	100	99	100	10100	100	0	0	1	1	1	717	1	16	1	1	10033	10000	10100	10037	10037	10037	10037	10037
10204	10036	75	0	0	0	0	203	25	10100	10100	10100	60499	1	49	6956	10036	10036	8721	7	8739	10100	10208	20216	10036	162	1	1	10201	100	99	100	10100	100	0	0	1	1	1	718	1	16	1	1	10033	10000	10100	10037	10037	10037	10037	10037
10204	10036	75	0	0	0	0	35	25	10100	10100	10100	60499	1	49	6956	10036	10036	8721	7	8739	10100	10208	20216	10036	162	1	1	10201	100	99	100	10100	100	1	0	1	1	1	718	1	16	1	1	10033	10000	10100	10037	10037	10037	10037	10037
10204	10036	75	0	0	0	0	36	25	10100	10100	10100	60499	1	49	6956	10036	10036	8721	6	8739	10100	10208	20216	10036	162	1	1	10201	100	99	100	10100	100	0	0	1	1	1	718	1	16	1	1	10033	10000	10100	10037	10037	10037	10037	10037
10204	10036	75	0	0	0	0	400	25	10100	10100	10100	60499	1	49	6956	10036	10036	8721	6	8740	10100	10208	20216	10036	162	1	1	10201	100	99	100	10100	100	0	0	1	1	1	718	1	16	1	1	10033	10000	10100	10037	10037	10037	10037	10037

1000 unrolls and 10 iterations

Result (median cycles for code): 1.0036

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)	dispatch int uop (56)	int uops in schedulers (59)	69	6a	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map int uop inputs (7f)	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)	9f	l1d tlb miss (a1)	l1d cache writeback (a8)	ac	c2	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? int output thing (e9)	? int retires (ef)	f5	f6	f7	f8	fd
10024	10037	75	0	47	25	10010	10010	10010	60049	49	6956	10036	10036	8736	3	8766	10010	10020	20020	10036	164	1	1	10021	10	9	10	10010	10	0	0	0	2	640	2	16	2	2	10032	10000	10010	10037	10037	10037	10037	10037
10024	10036	75	0	47	25	10010	10010	10010	60049	49	6956	10036	10036	8736	3	8766	10010	10020	20020	10036	164	1	1	10021	10	9	10	10010	10	0	2	6	0	640	2	16	2	2	10032	10000	10010	10037	10037	10037	10037	10037
10024	10036	75	0	47	25	10010	10010	10010	60049	49	6956	10036	10036	8736	3	8766	10010	10020	20020	10036	164	1	1	10021	10	9	10	10010	10	0	0	0	0	640	2	16	2	2	10032	10000	10010	10037	10037	10037	10037	10037
10024	10036	75	0	47	25	10010	10010	10010	60049	49	6956	10036	10036	8736	3	8766	10010	10020	20020	10036	164	1	1	10021	10	9	10	10010	10	0	0	0	0	640	2	16	2	2	10032	10000	10010	10037	10037	10037	10037	10037
10024	10036	75	0	47	25	10010	10010	10010	60049	49	6956	10036	10036	8736	3	8766	10010	10020	20020	10036	164	1	1	10021	10	9	10	10010	10	0	0	0	0	640	2	16	2	2	10032	10000	10010	10037	10037	10037	10037	10037
10024	10036	75	0	47	25	10010	10010	10010	60049	49	6956	10036	10036	8736	3	8766	10010	10020	20020	10036	164	1	1	10021	10	9	10	10010	10	0	1	3	0	640	2	16	2	2	10032	10000	10010	10037	10037	10037	10037	10037
10024	10036	75	0	47	25	10010	10010	10010	60049	49	6956	10036	10036	8736	3	8766	10010	10020	20020	10036	164	1	1	10021	10	9	10	10010	10	0	0	0	0	640	2	16	2	2	10032	10000	10010	10037	10037	10037	10037	10037
10024	10036	75	0	47	25	10010	10010	10010	60049	49	6956	10036	10036	8736	3	8766	10010	10020	20020	10036	164	1	1	10021	10	9	10	10010	10	0	0	0	0	640	2	16	2	2	10032	10000	10010	10037	10037	10037	10037	10037
10024	10036	75	0	47	25	10010	10010	10010	60049	49	6956	10036	10036	8736	3	8766	10010	10020	20020	10036	164	1	1	10021	10	9	10	10010	10	0	1	0	0	640	2	16	2	2	10032	10000	10010	10037	10037	10037	10037	10037
10024	10036	75	0	47	25	10010	10010	10010	60049	49	6956	10036	10036	8736	3	8766	10010	10020	20020	10036	164	1	1	10021	10	9	10	10010	10	0	0	0	0	640	2	16	2	2	10032	10000	10010	10037	10037	10037	10037	10037

Test 3: Latency 1->2

Chain cycles: 1

Code:

  add x1, x0, x0
  mov x0, 0
  bfi x0, x1, #3, #7

Initialization

  mov x0, 1

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code, minus 1 chain cycle): 1.0035

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

retire uop (01)	cycle (02)	03	l2 tlb miss data (0b)	19	1e	3f	4d	51	schedule uop (52)	schedule int uop (53)	dispatch int uop (56)	int uops in schedulers (59)	60	69	6a	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map int uop inputs (7f)	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)	9f	l1d cache writeback (a8)	a9	ac	branch cond mispred nonspec (c5)	branch mispred nonspec (cb)	cd	cf	l1i cache miss demand (d3)	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? int output thing (e9)	? int retires (ef)	f5	f6	f7	f8	fd
30204	20035	150	0	0	27	61	9951	25	20100	20100	20106	1288657	0	49	16955	20035	20035	16160	7	16236	20106	20211	40222	20035	57	1	1	30201	100	99	100	30100	100	0	0	0	1	1	1	1919	0	1	16	1	1	20007	20000	30100	20036	20036	20036	20036	20036
30204	20035	150	0	0	9	61	9951	25	20100	20100	20106	1288657	1	49	16955	20035	20035	16160	7	16237	20106	20211	40222	20035	57	1	1	30201	100	99	100	30100	100	0	0	0	1	1	1	1919	0	1	16	1	1	20007	20000	30100	20036	20036	20036	20036	20036
30204	20035	150	0	0	0	61	9951	25	20100	20100	20106	1288657	1	49	16955	20080	20035	16160	7	16236	20106	20211	40222	20035	57	1	1	30201	100	99	100	30100	100	0	0	0	1	1	1	1919	0	1	16	1	1	20007	20000	30100	20036	20036	20036	20036	20036
30204	20035	150	0	0	0	61	9951	25	20100	20100	20106	1288657	1	49	16955	20035	20035	16160	7	16236	20106	20211	40222	20035	57	1	1	30201	100	99	100	30100	100	0	0	0	1	1	1	1919	0	1	16	1	1	20007	20000	30100	20036	20036	20036	20067	20036
30204	20035	150	0	0	0	61	9951	25	20100	20100	20106	1288657	0	49	16955	20035	20035	16160	7	16236	20106	20211	40222	20035	57	1	1	30201	100	99	100	30100	100	0	0	0	1	1	1	1919	0	1	16	1	1	20007	20000	30100	20036	20036	20036	20036	20036
30204	20035	150	0	0	0	61	9951	25	20100	20100	20106	1288657	1	49	16955	20035	20035	16160	7	16236	20106	20211	40222	20035	57	1	1	30201	100	99	100	30100	100	0	0	0	1	1	1	1919	0	1	16	1	1	20007	20000	30100	20036	20036	20036	20036	20036
30204	20035	150	0	0	0	61	9951	25	20100	20100	20106	1288657	0	49	16955	20035	20035	16160	7	16236	20106	20211	40222	20035	57	1	1	30201	100	99	100	30100	100	0	0	0	1	1	1	1919	0	1	16	1	1	20007	20000	30100	20036	20036	20036	20036	20036
30204	20035	150	0	0	0	61	9951	25	20100	20100	20106	1288841	0	49	16955	20035	20035	16160	7	16237	20106	20211	40222	20035	57	1	1	30201	100	99	100	30100	100	0	0	0	1	1	1	1919	0	1	16	1	1	20007	20000	30100	20036	20036	20036	20067	20036
30204	20035	150	0	0	0	61	9951	25	20100	20100	20106	1288657	0	49	16955	20035	20035	16160	7	16236	20106	20211	40222	20035	57	1	1	30201	100	99	100	30100	100	0	0	0	1	1	1	1919	0	1	16	1	1	20010	20000	30100	20036	20036	20036	20036	20036
30204	20035	150	0	0	0	61	9951	25	20100	20100	20106	1288657	0	49	16955	20035	20035	16160	7	16236	20106	20211	40222	20035	57	1	1	30201	100	99	100	30100	100	0	0	0	1	1	1	1919	0	1	16	1	1	20007	20000	30100	20036	20036	20036	20036	20036

1000 unrolls and 10 iterations

Result (median cycles for code, minus 1 chain cycle): 1.0035

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

retire uop (01)	cycle (02)	03	l1i tlb fill (04)	mmu table walk data (08)	09	l2 tlb miss data (0b)	18	19	1e	1f	3f	4d	51	schedule uop (52)	schedule int uop (53)	dispatch int uop (56)	int uops in schedulers (59)	60	69	6a	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map int uop inputs (7f)	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)	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)	d9	dd	fetch restart (de)	e0	? int output thing (e9)	? int retires (ef)	f5	f6	f7	f8	fd
30024	20035	150	0	0	0	0	0	0	0	0	61	9951	25	20010	20010	20010	1287866	0	49	16955	20035	20035	16179	3	16265	20010	20020	40020	20035	57	1	1	30021	10	9	10	30010	10	0	0	0	0	0	0	3	0	1890	2	16	0	2	2	20003	20000	30010	20036	20036	20036	20036	20036
30024	20035	150	0	0	0	0	0	0	0	0	998	9951	25	20010	20010	20010	1287866	1	49	16955	20035	20035	16179	3	16265	20010	20020	40020	20035	57	1	1	30021	10	9	10	30010	10	0	2	0	0	0	0	0	0	1890	2	16	0	2	2	20003	20000	30010	20036	20036	20036	20036	20036
30024	20035	150	0	0	0	0	0	0	0	0	61	9951	25	20010	20010	20010	1287866	0	49	16955	20035	20035	16179	3	16265	20010	20020	40020	20035	57	1	1	30021	10	9	10	30010	10	0	0	0	0	0	0	0	0	1890	2	16	0	2	2	20003	20000	30010	20036	20036	20036	20036	20036
30024	20035	150	0	0	0	0	0	0	0	0	1126	9951	25	20010	20010	20010	1287866	0	49	16955	20035	20035	16179	3	16265	20010	20020	40020	20035	57	1	1	30021	10	9	10	30010	10	0	0	0	0	0	0	0	0	1890	2	16	0	2	2	20003	20000	30010	20036	20036	20036	20036	20036
30024	20035	150	0	0	0	0	0	0	0	0	61	9951	25	20010	20010	20010	1287866	0	49	16955	20035	20035	16179	3	16265	20010	20020	40020	20035	57	1	1	30021	10	9	10	30010	10	0	0	0	0	0	0	0	0	1890	2	16	0	2	2	20003	20000	30010	20036	20036	20036	20036	20036
30024	20035	150	0	0	0	0	0	0	0	0	61	9951	25	20010	20010	20010	1287866	1	49	16955	20035	20035	16179	3	16265	20010	20020	40020	20035	57	1	1	30021	10	9	10	30010	10	0	0	0	0	0	0	0	0	1890	2	16	0	2	2	20003	20000	30010	20036	20036	20036	20036	20036
30024	20035	150	0	0	0	0	0	0	0	0	1123	9951	25	20010	20010	20010	1287866	0	49	16955	20035	20035	16179	3	16265	20010	20020	40020	20035	57	1	1	30021	10	9	10	30010	10	0	0	0	0	0	0	0	0	1890	2	16	0	2	2	20003	20000	30010	20036	20036	20036	20036	20036
30024	20035	150	0	0	0	0	0	0	0	0	87	9951	25	20010	20010	20010	1287866	0	49	16955	20035	20035	16179	3	16265	20010	20020	40020	20035	57	1	1	30021	10	9	10	30010	10	0	0	0	0	20	0	0	0	1890	2	16	0	2	2	20003	20000	30010	20036	20036	20036	20036	20036
30024	20035	150	0	0	0	0	0	0	0	0	979	9951	25	20010	20010	20010	1287866	1	49	16955	20035	20035	16179	3	16265	20010	20020	40020	20035	57	1	1	30021	10	9	10	30010	10	0	0	0	0	0	0	0	0	1890	2	16	0	3	2	20003	20000	30010	20036	20036	20036	20036	20036
30024	20035	150	0	0	0	0	0	0	0	0	61	9951	25	20010	20010	20010	1287866	1	49	16955	20035	20035	16179	3	16265	20010	20020	40020	20035	57	1	1	30021	10	9	10	30010	10	0	0	0	0	0	0	0	0	1890	2	16	0	2	3	20003	20000	30010	20036	20036	20036	20036	20036

Test 4: throughput

Count: 8

Code:

  bfi x0, x8, #3, #7
  bfi x1, x8, #3, #7
  bfi x2, x8, #3, #7
  bfi x3, x8, #3, #7
  bfi x4, x8, #3, #7
  bfi x5, x8, #3, #7
  bfi x6, x8, #3, #7
  bfi x7, x8, #3, #7

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 1.0004

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

retire uop (01)	cycle (02)	03	l2 tlb miss data (0b)	18	1e	3a	3f	51	schedule uop (52)	schedule int uop (53)	dispatch int uop (56)	int uops in schedulers (59)	60	69	6a	6b	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map int uop inputs (7f)	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)	9f	ld unit uop (a6)	l1d cache writeback (a8)	a9	ac	c2	branch mispred nonspec (cb)	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? int output thing (e9)	? int retires (ef)	f5	f6	f7	f8	fd
80204	80035	599	0	0	0	0	46	25	80100	80100	80100	400500	0	49	76955	0	80035	80035	69964	3	69993	80100	80200	160200	80035	164	1	1	80201	100	99	100	80100	100	0	0	0	0	0	0	5110	3	16	2	2	80031	80000	80100	80036	80036	80036	80036	80036
80204	80035	599	0	0	0	0	920	25	80100	80100	80100	400500	1	49	76955	0	80035	80035	69964	3	69993	80100	80200	160200	80035	164	1	1	80201	100	99	100	80100	100	0	0	0	0	0	0	5110	2	16	2	2	80031	80000	80100	80036	80036	80036	80036	80036
80204	80035	599	0	0	0	0	46	25	80100	80100	80100	400500	0	49	76955	0	80035	80035	69964	3	69993	80100	80200	160200	80035	164	1	1	80201	100	99	100	80100	100	0	0	0	0	0	0	5110	2	16	2	2	80031	80000	80100	80036	80036	80036	80036	80036
80204	80035	600	0	0	0	0	46	25	80100	80100	80100	400500	0	49	76955	0	80035	80035	69964	3	69993	80100	80200	160200	80035	164	1	1	80201	100	99	100	80100	100	0	0	0	0	0	0	5110	2	16	2	2	80031	80000	80100	80036	80036	80036	80036	80036
80204	80035	599	0	0	0	0	711	25	80100	80134	80100	400500	0	49	76955	0	80035	80035	69964	3	69993	80100	80200	160200	80035	164	1	1	80201	100	99	100	80100	100	0	0	0	0	0	0	5110	2	16	2	2	80031	80000	80100	80036	80036	80036	80036	80036
80204	80035	599	0	0	0	0	2286	25	80100	80100	80100	400500	0	49	76955	0	80035	80035	69964	3	69993	80100	80200	160200	80035	164	1	1	80201	100	99	100	80100	100	0	0	0	0	0	0	5110	2	16	2	2	80031	80000	80100	80036	80036	80036	80036	80036
80204	80035	599	0	0	0	0	46	25	80100	80100	80100	400500	1	49	76955	0	80035	80035	69964	3	69993	80100	80200	160200	80035	164	1	1	80201	100	99	100	80100	100	0	0	0	0	0	0	5110	2	16	2	2	80031	80000	80100	80036	80036	80036	80036	80036
80204	80035	599	0	0	0	0	46	25	80100	80100	80100	400500	0	49	76955	0	80035	80035	69964	3	69993	80100	80200	160200	80035	164	1	1	80201	100	99	100	80100	100	0	0	0	0	0	1	5110	2	17	2	2	80031	80000	80100	80036	80036	80036	80036	80036
80204	80035	599	0	0	0	0	46	25	80100	80100	80100	400500	0	49	76955	0	80035	80035	69964	3	69993	80100	80200	160200	80035	164	1	1	80201	100	99	100	80100	100	0	0	0	0	0	0	5110	2	16	2	2	80031	80000	80100	80036	80036	80036	80036	80036
80204	80035	599	0	0	12	0	46	46	80100	80100	80100	400500	1	49	76955	0	80035	80079	69964	11	69993	80100	80232	160200	80035	164	1	1	80201	100	99	100	80100	100	0	1	0	3	0	0	5110	2	16	2	2	80031	80000	80100	80036	80036	80036	80036	80036

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 1.0004

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

retire uop (01)	cycle (02)	03	19	1e	1f	3f	51	schedule uop (52)	schedule int uop (53)	dispatch int uop (56)	int uops in schedulers (59)	60	69	6a	6b	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map int uop inputs (7f)	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)	9f	l1d cache writeback (a8)	a9	ac	c2	branch mispred nonspec (cb)	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? int output thing (e9)	? int retires (ef)	f5	f6	f7	f8	fd
80024	80035	600	0	0	0	483	25	80010	80010	80010	400050	0	49	76955	0	80035	80035	69986	3	70015	80010	80020	160020	80035	164	1	1	80021	10	9	10	80010	10	0	0	0	0	0	5020	3	16	2	4	80032	80000	80010	80036	80036	80036	80036	80036
80024	80035	599	0	0	0	513	25	80010	80010	80010	400050	0	49	76955	0	80035	80035	69986	3	70015	80010	80020	160020	80035	164	1	1	80021	10	9	10	80010	10	0	0	0	0	0	5020	4	16	4	2	80071	80000	80010	80036	80036	80036	80036	80036
80024	80035	599	0	0	0	1877	25	80010	80010	80010	400050	0	49	76955	0	80035	80035	69986	3	70015	80010	80020	160020	80035	164	1	1	80021	10	9	10	80010	10	0	0	0	0	0	5020	2	16	4	4	80032	80000	80010	80036	80036	80036	80036	80036
80024	80035	599	0	0	0	674	25	80010	80010	80010	400050	0	49	76955	0	80035	80035	69986	3	70015	80010	80020	160020	80035	164	1	1	80021	10	9	10	80010	10	0	0	0	0	0	5020	2	16	4	2	80032	80000	80010	80036	80036	80036	80036	80036
80024	80035	599	0	0	0	650	25	80010	80010	80010	400050	0	49	76955	0	80035	80035	69986	3	70015	80010	80020	160020	80035	164	1	1	80021	10	9	10	80010	10	0	0	0	0	0	5020	4	16	4	2	80032	80000	80010	80036	80036	80036	80036	80036
80024	80035	600	0	0	0	544	25	80010	80010	80010	400050	0	49	76955	3	80035	80035	69986	3	70015	80010	80064	160020	80035	164	1	1	80021	10	9	10	80010	10	0	0	0	0	0	5020	4	16	4	2	80032	80000	80010	80036	80036	80036	80036	80036
80024	80035	599	0	0	0	614	25	80010	80010	80010	400050	0	49	76955	0	80035	80035	69986	3	70015	80010	80020	160020	80035	164	1	1	80021	10	9	10	80010	10	0	0	0	0	0	5020	2	16	4	4	80032	80000	80010	80036	80036	80036	80036	80036
80024	80035	599	0	0	0	405	25	80010	80010	80010	400050	0	49	77000	0	80035	80124	70040	7	70049	80010	80053	160172	80035	164	1	1	80021	10	9	10	80010	10	0	2	578	0	0	5020	4	16	2	4	80032	80000	80010	80036	80036	80036	80036	80036
80024	80035	599	0	12	0	2073	25	80010	80010	80010	400050	0	49	76955	0	80035	80035	69986	3	70015	80010	80020	160020	80035	164	1	1	80021	10	9	10	80010	10	1	0	0	0	0	5047	5	16	4	5	80032	80000	80010	80081	80218	80036	80081	80171
80024	80035	599	0	0	0	595	25	80010	80010	80010	400050	0	49	76955	0	80035	80035	69986	3	70015	80010	80020	160020	80035	164	1	1	80021	10	9	10	80010	10	1	0	0	0	0	5020	4	16	4	4	80032	80000	80010	80036	80036	80036	80036	80036

BFI (64-bit)

Test 1: uops

1000 unrolls and 1 iteration

Test 2: Latency 1->1

100 unrolls and 100 iterations

1000 unrolls and 10 iterations

Test 3: Latency 1->2

100 unrolls and 100 iterations

1000 unrolls and 10 iterations

Test 4: throughput

100 unrolls and 100 iterations

1000 unrolls and 10 iterations