Firestorm: EON (register, lsr, 32-bit) measurements

Code:

  eon w0, w0, w1, lsr #17

Initialization

  mov x0, 1
  mov x1, 2

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 1.000

Issues: 2.000

Integer unit issues: 2.000

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	18	19	1e	1f	3a	3f	4c	4d	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 miss (a1)	st unit uop (a7)	ac	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? int output thing (e9)	? int retires (ef)	f5	f6	f7	f8	fd
1004	2081	16	0	1	0	0	0	103	1000	1735	25	2000	2000	1000	32570	0	2035	2035	1575	3	1842	1000	1000	2000	2035	42	2	1	1001	1000	0	0	0	73	1	67	1	1	1781	2000	1000	2036	2036	2036	2036	2036
1004	2035	16	0	0	0	0	0	103	1009	1735	25	2000	2000	1000	32570	1	2035	2081	1575	3	1853	1000	1000	2000	2035	42	1	1	1001	1000	0	0	0	73	1	67	1	1	1815	2000	1000	2036	2036	2036	2036	2036
1004	2035	15	0	0	0	0	0	61	1000	1735	25	2000	2000	1000	32570	0	2035	2035	1575	3	1842	1000	1000	2000	2035	42	1	1	1001	1000	0	0	0	73	1	67	1	1	1781	2000	1000	2036	2036	2036	2036	2036
1004	2035	16	0	0	0	0	0	61	1000	1735	25	2000	2000	1000	32570	1	2035	2035	1575	3	1842	1000	1000	2000	2035	42	1	1	1001	1000	0	0	0	73	1	67	1	1	1781	2000	1000	2036	2036	2036	2036	2036
1004	2035	16	0	0	0	0	0	61	1000	1735	25	2000	2000	1000	32570	1	2035	2035	1575	3	1842	1000	1000	2000	2035	42	1	1	1001	1000	0	0	0	73	1	67	1	1	1781	2000	1000	2036	2036	2036	2036	2036
1004	2035	16	0	0	0	0	0	61	1000	1735	25	2000	2000	1000	32570	1	2035	2035	1575	3	1866	1000	1000	2000	2035	42	1	1	1001	1000	0	2	0	91	1	67	1	1	1781	2000	1000	2036	2036	2036	2036	2036
1004	2035	16	1	0	0	0	0	89	1000	1735	25	2000	2000	1000	32570	1	2035	2035	1575	3	1842	1000	1000	2000	2035	42	1	1	1001	1000	0	0	0	73	1	67	1	1	1781	2000	1000	2036	2036	2036	2036	2036
1004	2035	16	0	0	0	0	0	110	1000	1735	25	2000	2000	1000	32570	0	2035	2035	1575	3	1842	1000	1000	2000	2035	42	1	1	1001	1000	2	0	220	73	1	67	1	1	1781	2000	1000	2036	2081	2036	2036	2036
1004	2035	16	0	0	0	0	0	318	1000	1735	25	2000	2000	1000	32570	1	2035	2080	1575	3	1842	1000	1000	2000	2035	42	1	1	1001	1000	0	0	0	73	1	67	1	1	1781	2000	1000	2036	2036	2036	2036	2036
1004	2035	15	0	0	0	0	0	61	1000	1735	25	2000	2000	1000	32570	1	2035	2035	1575	3	1842	1000	1000	2000	2035	42	1	1	1001	1000	0	0	0	73	1	67	1	1	1781	2000	1000	2036	2036	2036	2036	2036

Test 2: Latency 1->2

Code:

  eon w0, w0, w1, lsr #17

Initialization

  mov x0, 1
  mov x1, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 2.0035

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

retire uop (01)	cycle (02)	03	19	1e	1f	3f	4c	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)	ac	branch cond mispred nonspec (c5)	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
10204	20035	156	0	0	0	61	10000	19803	25	20100	20100	10100	185342	1	49	16955	20035	20035	18429	21	18700	10100	10200	20200	20035	42	1	1	10201	100	99	100	10100	100	0	0	0	0	710	1	59	1	1	19791	20000	10100	20036	20083	20036	20081	20036
10204	20035	155	0	27	0	61	10000	19803	25	20100	20100	10100	185342	1	49	16955	20035	20035	18429	3	18700	10100	10200	20200	20035	42	1	1	10201	100	99	100	10100	100	0	0	0	0	710	1	59	1	1	19791	20000	10100	20036	20036	20036	20036	20036
10204	20035	156	0	6	0	726	10000	19803	25	20100	20100	10100	185342	1	49	16955	20035	20035	18429	3	18700	10100	10200	20200	20035	42	1	1	10201	100	99	100	10100	100	0	0	0	0	710	1	59	1	1	19791	20000	10100	20036	20036	20036	20036	20036
10204	20035	155	0	9	0	61	10000	19803	25	20100	20100	10100	185342	1	49	16955	20035	20035	18429	3	18700	10100	10200	20200	20035	42	1	1	10201	100	99	100	10100	100	1	0	0	0	710	1	59	1	1	19791	20000	10100	20036	20036	20036	20036	20036
10204	20035	155	0	6	0	61	10000	19803	25	20100	20100	10100	185342	1	49	16955	20035	20035	18429	3	18700	10100	10200	20200	20035	42	1	1	10201	100	99	100	10100	100	1	0	0	0	710	1	59	1	1	19791	20000	10100	20036	20036	20036	20036	20036
10204	20035	155	0	0	0	103	10000	19803	25	20100	20100	10100	185342	0	49	16955	20035	20035	18429	3	18700	10100	10200	20200	20035	42	1	1	10201	100	99	100	10100	100	0	0	0	0	710	1	59	1	1	19791	20000	10100	20083	20036	20036	20036	20036
10204	20035	156	0	12	0	61	10000	19803	25	20100	20100	10100	185342	1	49	16955	20035	20035	18429	3	18700	10100	10200	20200	20035	42	1	1	10201	100	99	100	10100	100	0	0	0	0	710	1	59	1	1	19791	20000	10100	20036	20036	20036	20036	20036
10204	20035	155	0	6	0	61	10000	19803	25	20100	20100	10100	185342	1	49	16955	20035	20035	18429	3	18700	10100	10200	20200	20035	42	1	1	10201	100	99	100	10100	100	0	0	0	0	710	1	59	1	1	19791	20000	10100	20036	20036	20036	20036	20036
10204	20035	155	0	27	0	61	10000	19803	25	20100	20100	10100	185342	0	49	16955	20035	20035	18429	3	18700	10100	10200	20200	20035	42	1	1	10201	100	99	100	10100	100	0	0	0	0	710	1	59	1	1	19791	20000	10100	20036	20036	20036	20036	20036
10204	20035	156	0	9	0	61	10000	19803	25	20100	20100	10100	185342	1	49	16955	20035	20035	18429	3	18700	10100	10200	20200	20035	42	1	1	10201	100	99	100	10100	100	0	0	0	0	710	1	59	1	1	19791	20000	10100	20036	20036	20036	20036	20036

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0035

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

retire uop (01)	cycle (02)	03	l1i tlb fill (04)	mmu table walk data (08)	l2 tlb miss data (0b)	18	19	1e	1f	3f	4c	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)	a9	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	20035	155	1	0	0	0	0	0	0	71	10000	19743	25	20010	20010	10010	185310	0	49	16955	20035	20035	18451	3	18718	10010	10020	20020	20035	42	1	1	10021	10	9	10	10010	10	0	0	0	0	0	0	0	640	3	63	3	3	19792	20000	10010	20036	20036	20036	20036	20036
10024	20035	155	0	0	0	0	0	0	0	61	10000	19743	25	20010	20010	10010	185310	0	49	16955	20035	20035	18451	3	18718	10010	10020	20020	20035	42	1	1	10021	10	9	10	10010	10	0	0	0	0	0	0	0	640	3	75	3	3	19792	20000	10010	20036	20036	20036	20036	20036
10024	20035	156	0	0	0	0	0	0	0	61	10000	19743	25	20010	20010	10010	185310	1	49	16955	20035	20035	18451	3	18718	10010	10020	20020	20035	42	1	1	10021	10	9	10	10010	10	0	0	0	0	0	0	0	640	3	63	3	3	19792	20000	10010	20036	20036	20036	20036	20036
10024	20035	156	0	0	0	0	0	0	0	61	10000	19743	25	20010	20010	10010	185310	1	49	16955	20035	20035	18451	3	18718	10010	10020	20020	20035	42	1	1	10021	10	9	10	10010	10	0	0	0	0	0	0	0	640	3	63	3	3	19792	20000	10010	20036	20036	20036	20036	20036
10024	20035	155	0	0	0	0	0	0	0	61	10000	19743	25	20010	20010	10010	185310	0	49	16955	20035	20035	18451	3	18718	10010	10020	20020	20035	42	1	1	10021	10	9	10	10010	10	0	0	0	0	0	0	0	640	3	63	3	3	19792	20000	10010	20036	20036	20036	20036	20036
10024	20035	155	0	0	0	0	0	0	0	61	10000	19743	25	20010	20010	10010	185310	1	49	16955	20035	20035	18451	3	18718	10010	10020	20020	20035	42	1	1	10021	10	9	10	10010	10	0	0	0	0	0	0	0	640	3	63	3	3	19792	20000	10010	20036	20036	20036	20036	20036
10024	20035	155	0	0	0	0	0	0	0	61	10000	19743	25	20010	20010	10010	185310	1	49	16955	20035	20035	18451	3	18718	10010	10020	20020	20035	42	1	1	10021	10	9	10	10010	10	0	0	0	0	0	0	0	640	3	63	3	3	19792	20000	10010	20036	20036	20036	20036	20036
10024	20035	155	0	0	0	0	0	0	0	61	10000	19743	25	20010	20010	10010	185310	0	49	16955	20035	20035	18451	3	18718	10010	10020	20020	20035	42	1	1	10021	10	9	10	10010	10	0	0	0	0	0	0	0	640	3	63	3	3	19792	20000	10010	20036	20036	20036	20036	20036
10024	20035	155	0	0	0	0	0	0	0	61	10000	19743	25	20010	20010	10010	185310	1	49	16955	20035	20035	18451	3	18718	10010	10020	20020	20035	42	1	1	10021	10	9	10	10010	10	0	0	0	0	0	0	0	640	3	63	3	3	19792	20000	10010	20036	20036	20036	20036	20036
10024	20035	155	0	0	0	0	0	0	0	86	10000	19743	25	20010	20010	10010	185310	0	49	16955	20035	20035	18451	3	18718	10010	10020	20020	20035	42	1	1	10021	10	9	10	10010	10	0	0	0	0	0	0	0	640	3	63	3	3	19792	20000	10010	20036	20036	20036	20036	20036

Test 3: Latency 1->3

Code:

  eon w0, w1, w0, lsr #17

Initialization

  mov x0, 1
  mov x1, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 2.0035

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

retire uop (01)	cycle (02)	03	09	18	19	1e	1f	3a	3f	4c	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)	ac	c2	cf	d5	map dispatch bubble (d6)	da	dd	fetch restart (de)	e0	? int output thing (e9)	eb	? int retires (ef)	f5	f6	f7	f8	fd
10204	20035	155	0	0	0	0	0	0	82	10000	19803	25	20100	20100	10100	185342	0	49	16955	20035	20035	18429	3	18700	10100	10200	20200	20035	42	1	1	10201	100	99	100	10100	100	0	0	0	0	0	0	0	710	1	59	0	1	1	19791	20000	0	10100	20036	20036	20036	20036	20036
10204	20035	155	0	0	0	0	0	0	110	10000	19803	25	20100	20100	10100	185342	0	49	16955	20035	20035	18429	3	18700	10100	10200	20200	20035	42	1	1	10201	100	99	100	10100	100	0	0	0	0	0	3	0	710	1	59	0	1	1	19791	20000	0	10100	20036	20036	20036	20036	20036
10204	20035	156	1	0	0	0	0	0	61	10000	19803	25	20100	20100	10100	185342	1	49	16955	20035	20035	18429	3	18700	10100	10200	20200	20035	42	1	1	10201	100	99	100	10100	100	0	0	0	0	0	0	0	710	1	59	0	1	1	19791	20000	0	10100	20036	20036	20036	20036	20036
10204	20035	156	0	0	0	0	0	0	61	10000	19803	25	20100	20100	10100	185342	0	49	16955	20035	20035	18429	3	18700	10100	10200	20200	20035	42	1	1	10201	100	99	100	10100	100	0	0	0	0	0	0	0	710	1	59	0	1	1	19791	20000	0	10100	20036	20036	20036	20036	20036
10204	20035	155	0	0	0	0	0	0	61	10000	19803	25	20100	20100	10100	185342	1	49	16955	20035	20035	18429	3	18700	10100	10200	20200	20035	42	1	1	10201	100	99	100	10100	100	0	0	0	0	0	0	0	710	1	59	0	1	1	19791	20000	0	10100	20036	20036	20036	20036	20036
10204	20035	155	0	0	0	0	0	0	110	10000	19803	25	20100	20100	10100	185342	0	49	16955	20035	20035	18429	3	18700	10100	10200	20200	20035	42	1	1	10201	100	99	100	10100	100	0	0	0	0	0	0	0	710	1	59	0	1	1	19791	20000	0	10100	20036	20036	20036	20036	20036
10204	20035	156	0	0	0	0	0	0	61	10000	19803	25	20100	20100	10100	185342	0	49	16955	20035	20035	18429	3	18700	10100	10200	20200	20035	42	1	1	10201	100	99	100	10100	100	0	0	0	0	0	0	0	710	1	59	0	1	1	19791	20000	0	10100	20036	20036	20036	20036	20036
10204	20035	155	0	0	0	0	0	0	124	10000	19803	25	20100	20100	10100	185342	1	49	16955	20035	20035	18429	3	18700	10100	10200	20200	20035	42	1	1	10201	100	99	100	10100	100	0	0	0	0	1	0	0	710	1	59	0	1	1	19791	20023	0	10100	20036	20036	20036	20036	20036
10204	20035	155	0	0	0	0	0	0	126	10000	19803	25	20100	20100	10100	185342	0	49	16955	20035	20035	18429	3	18700	10100	10200	20200	20035	42	1	1	10201	100	99	100	10100	100	0	0	0	0	1	3	0	710	1	59	0	1	1	19791	20000	0	10100	20036	20036	20036	20036	20036
10204	20035	155	0	0	0	0	0	0	61	10000	19803	25	20100	20100	10100	185342	0	49	16955	20035	20035	18429	3	18700	10100	10200	20200	20035	42	1	1	10201	100	99	100	10100	100	0	0	0	0	0	0	0	710	1	59	0	1	1	19791	20000	0	10100	20036	20036	20036	20036	20036

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0035

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

retire uop (01)	cycle (02)	03	l2 tlb miss data (0b)	18	1e	3f	4c	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)	int prf full (71)	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 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
10024	20035	155	0	0	0	768	10000	19743	25	20010	20010	10010	185310	1	49	16955	20035	20035	18451	0	3	18718	10010	10020	20020	20035	42	1	1	10021	10	9	10	10010	10	0	0	0	640	3	63	2	2	19792	20000	10010	20036	20036	20036	20036	20036
10024	20035	155	0	0	0	61	10000	19743	25	20010	20010	10010	185310	1	49	16955	20035	20035	18451	0	3	18718	10010	10020	20020	20035	42	1	1	10021	10	9	10	10010	10	0	0	0	640	2	63	2	2	19792	20000	10010	20036	20036	20036	20036	20036
10024	20035	155	0	0	0	61	10000	19743	25	20010	20010	10010	185310	1	49	16955	20035	20035	18451	0	3	18718	10010	10020	20020	20035	42	1	1	10021	10	9	10	10010	10	0	0	0	640	2	63	2	2	19792	20000	10010	20036	20036	20036	20036	20036
10024	20035	155	0	0	0	61	10000	19743	25	20010	20010	10010	185310	0	49	16955	20035	20035	18451	0	3	18718	10010	10020	20020	20035	42	1	1	10021	10	9	10	10010	10	0	0	0	640	2	63	2	2	19792	20000	10010	20036	20036	20036	20036	20036
10024	20035	155	0	0	0	61	10000	19743	25	20010	20010	10010	185310	0	49	16955	20035	20035	18451	0	3	18718	10010	10020	20020	20035	42	1	1	10021	10	9	10	10010	10	0	0	0	640	2	63	2	2	19792	20000	10010	20036	20036	20036	20036	20036
10024	20035	155	0	0	0	61	10000	19743	25	20010	20010	10010	185310	0	49	16955	20035	20035	18451	0	3	18718	10010	10020	20020	20035	42	1	1	10021	10	9	10	10010	10	0	0	0	640	2	63	2	2	19792	20000	10010	20036	20036	20036	20036	20036
10024	20035	155	0	0	0	61	10000	19743	25	20010	20010	10010	185310	0	49	16955	20035	20035	18451	0	3	18718	10010	10020	20020	20035	42	1	1	10021	10	9	10	10010	10	0	0	0	640	2	63	2	2	19792	20000	10010	20036	20036	20036	20036	20036
10024	20035	155	0	0	0	61	10000	19743	25	20010	20010	10010	185310	1	49	16955	20035	20035	18451	0	3	18718	10010	10020	20020	20035	42	1	1	10021	10	9	10	10010	10	0	0	0	640	2	63	2	2	19792	20000	10010	20036	20036	20036	20036	20036
10024	20035	155	0	0	0	61	10000	19743	25	20010	20010	10010	185310	0	49	16955	20035	20035	18451	0	3	18718	10010	10020	20020	20035	42	1	1	10021	10	9	10	10010	10	0	0	0	640	2	63	2	2	19792	20000	10010	20036	20036	20036	20036	20036
10024	20035	155	0	0	0	61	10000	19743	25	20010	20010	10010	185310	1	49	16955	20035	20035	18451	0	3	18718	10010	10020	20020	20035	42	1	1	10021	10	9	10	10010	10	0	0	0	640	2	63	2	7	19792	20000	10010	20036	20036	20036	20036	20036

Test 4: throughput

Count: 8

Code:

  eon w0, w8, w9, lsr #17
  eon w1, w8, w9, lsr #17
  eon w2, w8, w9, lsr #17
  eon w3, w8, w9, lsr #17
  eon w4, w8, w9, lsr #17
  eon w5, w8, w9, lsr #17
  eon w6, w8, w9, lsr #17
  eon w7, w8, w9, lsr #17

Initialization

  mov x8, 9
  mov x9, 10

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.3341

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

retire uop (01)	cycle (02)	03	mmu table walk instruction (07)	l2 tlb miss data (0b)	1e	3f	4c	4d	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 tlb miss (a1)	l1d cache writeback (a8)	ac	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? int output thing (e9)	? int retires (ef)	f5	f6	f7	f8	fd
80204	26769	208	0	0	0	61	80000	26094	25	160100	160100	80100	164318	1	49	23645	0	26725	26725	16615	3	16677	80100	80200	160200	26725	39	1	1	80201	100	99	100	80100	100	0	0	0	5110	2	22	2	1	26717	160000	80100	26726	26726	26726	26726	26726
80204	26725	207	0	0	0	61	80000	26094	25	160100	160100	80100	164318	1	49	23645	0	26725	26725	16615	3	16677	80100	80200	160200	26725	39	1	1	80201	100	99	100	80100	100	0	0	0	5110	1	22	1	1	26717	160000	80100	26726	26726	26726	26726	26726
80204	26725	207	0	0	0	89	80000	26094	25	160100	160100	80100	164318	1	49	23645	0	26725	26725	16615	3	16677	80100	80200	160200	26725	39	1	1	80201	100	99	100	80100	100	0	0	0	5110	1	22	1	1	26717	160000	80100	26726	26726	26726	26726	26726
80204	26725	207	0	0	0	61	80000	26094	25	160100	160100	80100	164318	1	49	23645	0	26725	26725	16615	3	16677	80100	80200	160200	26725	39	1	1	80201	100	99	100	80100	100	0	0	0	5110	1	22	1	1	26717	160000	80100	26726	26726	26726	26726	26726
80204	26725	207	0	0	0	61	80000	26094	25	160100	160100	80100	164318	1	49	23645	0	26725	26725	16615	3	16677	80100	80411	160200	26725	39	1	1	80201	100	99	100	80100	100	0	0	0	5110	1	22	1	1	26717	160000	80100	26726	26726	26726	26726	26726
80204	26725	207	0	0	0	1841	80080	26094	25	160100	160100	80539	167878	1	49	23645	0	26725	26725	16615	3	16677	80100	80200	160200	26725	39	1	1	80201	100	99	100	80100	100	0	0	0	5110	1	22	1	1	26717	160000	80100	26726	26726	26726	26726	26726
80204	26725	207	0	0	0	145	80000	26094	25	160100	160100	80100	164318	1	49	23645	0	26725	26725	16615	3	16701	80100	80200	160200	26725	39	1	1	80201	100	99	100	80100	100	0	1	0	5110	1	22	1	1	26717	160000	80100	26726	26726	26726	26726	26726
80204	26725	207	0	0	0	441	80000	26094	25	160100	160100	80100	164318	1	49	23645	0	26725	26725	16615	3	16682	80100	80200	160200	26725	39	1	1	80201	100	99	100	80100	100	0	0	0	5110	1	22	1	1	26717	160000	80100	26726	26726	26726	26726	26726
80204	26725	208	0	0	0	61	80000	26094	25	160100	160100	80100	164318	1	49	23645	0	26725	26725	16615	3	16677	80100	80200	160200	26725	39	1	1	80201	100	99	100	80100	100	0	1	0	5110	1	22	1	1	26717	160000	80100	26726	26726	26726	26726	26726
80204	26725	207	0	0	0	61	80000	26094	25	160100	160125	80100	164318	1	49	23645	0	26725	26725	16620	3	16677	80100	80200	160200	26725	39	1	1	80201	100	99	100	80100	100	0	0	0	5110	1	22	1	1	26717	160000	80100	26726	26726	26726	26726	26726

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.3339

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

retire uop (01)	cycle (02)	03	l2 tlb miss instruction (0a)	l2 tlb miss data (0b)	18	19	1e	1f	3a	3f	4c	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)	l1d cache writeback (a8)	a9	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
80024	26717	209	0	1	0	2	0	0	0	819	80000	21280	96	160010	160010	80010	175462	1	49	23724	26711	26711	16623	3	16752	80645	80020	161322	26711	39	1	1	80021	10	9	10	80010	10	0	2	2	0	0	0	2	5120	3	22	1	1	26837	160000	80010	26712	26887	26712	26770	26883
80024	26711	208	0	0	0	0	0	0	0	117	80000	21280	25	160010	160568	80010	163142	1	49	23631	26882	26711	16625	10	16685	80642	80020	160020	26881	39	4	1	80021	10	9	10	80010	10	0	0	0	1	0	0	0	5044	1	48	1	1	26832	160000	80010	26883	26712	26816	26712	26712
80024	26711	207	0	0	0	0	0	0	0	61	80247	21280	25	160195	160010	80010	163142	0	49	23631	26711	26711	16630	3	16685	80010	80020	160020	26711	39	1	1	80021	10	9	10	80010	10	0	0	0	0	0	0	0	5020	2	22	1	1	26704	160000	80010	26885	26712	26712	26947	26712
80024	26885	214	0	1	0	4	0	0	0	76	80000	21280	25	160010	160010	80010	163142	1	49	23631	26711	26711	16623	34	16685	80010	80020	160020	26711	39	1	1	80021	10	9	10	80010	10	0	0	0	1	2	0	0	5020	1	22	2	1	26704	160000	80010	26712	26712	26712	26712	26712
80024	26711	207	0	0	0	0	0	0	0	61	80000	21280	25	160010	160010	80219	163142	1	49	23631	26711	26711	16623	3	16685	80010	80020	160020	26711	39	1	1	80021	10	9	10	80010	10	0	0	0	0	0	0	0	5020	1	22	1	1	26704	160000	80010	26712	26712	27065	26712	26712
80024	26711	207	0	0	0	0	0	0	0	631	80000	21280	25	160010	160010	80010	163142	0	49	23631	26711	26711	16623	27	16685	80010	80020	160020	26711	39	1	1	80021	10	9	10	80010	10	0	0	0	0	0	0	0	5020	1	22	1	2	26704	160000	80010	26712	26712	26712	26712	26712
80024	26711	207	0	0	0	0	0	264	0	61	80000	21280	25	160010	160010	80010	163142	1	49	23631	26711	26711	16623	3	16753	80010	80020	160020	26711	39	1	1	80021	10	9	10	80010	10	0	0	0	1	0	0	0	5020	1	22	1	1	26704	160000	80010	26712	26712	26712	26942	26712
80024	26711	207	0	0	0	0	0	0	0	61	80000	21280	25	160010	160010	80010	163142	0	49	23631	26711	26711	16623	3	16685	80010	80876	160020	26711	39	1	1	80021	10	9	10	80010	10	0	0	0	1	0	0	0	5020	1	22	1	1	26704	160000	80010	26712	26712	26712	26712	26712
80024	26711	207	0	0	3	0	0	0	0	61	80000	21280	25	160010	160010	80010	163142	0	49	23631	26711	26711	16623	3	16685	80010	80020	160020	26711	39	1	1	80021	10	9	10	80010	10	0	0	0	0	0	0	0	5020	1	22	1	1	26704	160000	80010	26712	26712	26712	26827	26712
80024	26711	207	0	0	0	0	0	0	0	795	80000	21280	25	160010	160010	80010	163142	0	49	23631	26711	26711	16623	3	16685	80010	80020	160020	26711	39	1	1	80021	10	9	10	80010	10	0	0	0	0	0	0	0	5020	1	22	1	1	26704	160000	80010	26712	26770	26712	26712	26712

EON (register, lsr, 32-bit)

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: Latency 1->3

100 unrolls and 100 iterations

1000 unrolls and 10 iterations

Test 4: throughput

100 unrolls and 100 iterations

1000 unrolls and 10 iterations