Firestorm: NEGS (register, asr, 32-bit) measurements

Code:

  negs w0, w0, asr #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	mmu table walk data (08)	1e	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 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
1004	2035	15	0	0	61	1000	1862	25	2000	2000	1000	126235	0	2035	2035	1729	3	1866	1000	1000	1000	2035	41	1	1	1001	1000	0	0	73	2	43	1	1	1920	2000	1000	2036	2036	2036	2036	2036
1004	2035	15	0	0	61	1000	1862	25	2000	2000	1000	126235	0	2035	2035	1729	3	1866	1000	1000	1000	2035	41	1	1	1001	1000	0	0	73	1	43	1	1	1920	2000	1000	2036	2036	2036	2036	2036
1004	2035	15	0	0	170	1000	1862	25	2000	2000	1000	126235	0	2035	2035	1729	3	1866	1000	1000	1000	2035	41	1	1	1001	1000	0	0	73	1	43	1	1	1920	2000	1000	2036	2036	2036	2036	2036
1004	2035	16	0	0	61	1000	1862	25	2000	2000	1000	126235	0	2035	2035	1729	3	1866	1000	1000	1000	2035	41	1	1	1001	1000	0	0	73	1	43	1	1	1920	2000	1000	2036	2036	2036	2036	2036
1004	2035	15	0	0	61	1000	1862	25	2000	2000	1000	126235	0	2035	2035	1729	3	1866	1000	1000	1000	2035	41	1	1	1001	1000	0	3	73	1	43	1	1	1920	2000	1000	2036	2036	2036	2036	2036
1004	2035	15	0	0	61	1000	1862	25	2000	2000	1000	126235	0	2035	2035	1729	3	1866	1000	1000	1000	2035	41	1	1	1001	1000	0	0	73	1	43	1	1	1920	2000	1000	2036	2036	2036	2036	2036
1004	2035	15	0	0	61	1000	1862	25	2000	2000	1000	126235	0	2035	2035	1729	3	1866	1000	1000	1000	2035	41	1	1	1001	1000	0	0	73	1	43	1	1	1920	2000	1000	2036	2036	2036	2036	2036
1004	2035	16	0	0	61	1000	1862	25	2000	2000	1000	126235	0	2035	2035	1729	3	1866	1000	1000	1000	2035	41	1	1	1001	1000	0	0	73	1	43	1	1	1920	2000	1000	2036	2036	2036	2036	2036
1004	2035	15	0	0	61	1000	1862	25	2000	2000	1000	126235	0	2035	2035	1729	3	1866	1000	1000	1000	2035	41	1	1	1001	1000	0	0	73	1	43	1	1	1920	2000	1000	2036	2036	2036	2036	2036
1004	2035	15	0	54	124	1000	1862	25	2000	2000	1000	126235	1	2035	2035	1729	3	1866	1000	1000	1000	2035	41	1	1	1001	1000	0	0	73	1	43	1	1	1920	2000	1000	2036	2036	2036	2036	2036

Test 2: Latency 1->2

Code:

  negs w0, w0, asr #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	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	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	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	150	0	0	61	10000	19862	25	20100	20100	10100	1305121	0	49	16955	20035	20035	18581	3	18720	10100	10200	10200	20035	41	1	1	10201	100	99	100	10100	100	0	0	710	1	39	1	1	19922	20000	10100	20036	20036	20036	20036	20036
10204	20035	150	0	0	61	10000	19862	25	20100	20100	10100	1305121	0	49	16955	20035	20035	18581	3	18720	10100	10200	10200	20035	41	1	1	10201	100	99	100	10100	100	0	0	710	1	39	1	1	19922	20000	10100	20036	20036	20036	20036	20036
10204	20035	150	0	0	61	10000	19862	25	20100	20100	10100	1305121	0	49	16955	20035	20035	18581	3	18720	10100	10200	10200	20035	41	1	1	10201	100	99	100	10100	100	0	0	710	1	39	1	1	19922	20000	10100	20036	20036	20036	20036	20036
10204	20035	150	0	0	61	10000	19862	25	20100	20100	10100	1305121	0	49	16955	20035	20035	18581	3	18720	10100	10200	10200	20035	41	1	1	10201	100	99	100	10100	100	0	0	710	1	39	1	1	19922	20000	10100	20036	20036	20036	20036	20036
10204	20035	150	0	0	61	10000	19862	25	20100	20100	10100	1305121	0	49	16955	20035	20035	18581	3	18720	10100	10200	10200	20035	41	1	1	10201	100	99	100	10100	100	0	0	710	1	39	1	1	19922	20000	10100	20036	20036	20036	20036	20036
10204	20035	150	0	0	61	10000	19862	25	20100	20100	10100	1305121	0	49	16955	20035	20035	18581	3	18720	10100	10200	10200	20035	41	1	1	10201	100	99	100	10100	100	0	0	710	1	39	1	1	19922	20000	10100	20036	20036	20036	20036	20036
10204	20035	150	0	0	61	10000	19862	25	20100	20100	10100	1305121	0	49	16955	20035	20035	18581	3	18720	10100	10200	10200	20035	41	1	1	10201	100	99	100	10100	100	0	0	710	1	39	1	1	19922	20000	10100	20036	20036	20036	20036	20036
10204	20035	150	0	0	61	10000	19862	25	20100	20100	10100	1305121	0	49	16955	20035	20035	18581	3	18720	10100	10200	10200	20035	41	1	1	10201	100	99	100	10100	100	0	0	710	1	39	1	1	19922	20000	10100	20036	20036	20036	20036	20036
10204	20035	150	0	0	536	10000	19862	25	20100	20100	10100	1305121	0	49	16955	20035	20035	18581	3	18720	10100	10200	10200	20035	41	1	1	10201	100	99	100	10100	100	0	0	710	1	39	1	1	19922	20000	10100	20036	20036	20036	20036	20036
10204	20035	150	0	0	61	10000	19862	25	20100	20100	10100	1305121	0	49	16955	20035	20035	18581	3	18720	10100	10200	10200	20035	41	1	1	10201	100	99	100	10100	100	0	0	710	1	39	1	1	19922	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	1e	3f	4c	4d	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	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	150	0	61	10000	19862	25	20010	20010	10010	1305229	49	16955	20035	20035	18603	3	18740	10010	10020	10020	20035	41	1	1	10021	10	9	10	10010	10	640	2	41	2	2	19930	20000	10010	20036	20036	20036	20036	20036
10024	20035	150	0	84	10000	19862	25	20010	20010	10010	1305229	49	16955	20035	20035	18603	3	18740	10010	10020	10020	20035	41	1	1	10021	10	9	10	10010	10	640	2	41	2	2	19930	20000	10010	20036	20036	20036	20036	20036
10024	20035	150	0	61	10000	19862	25	20010	20010	10010	1305229	49	16955	20035	20035	18603	3	18740	10010	10020	10020	20035	41	1	1	10021	10	9	10	10010	10	640	2	41	2	2	19930	20000	10010	20036	20036	20036	20036	20036
10024	20035	150	0	61	10000	19862	25	20010	20010	10010	1305229	49	16955	20035	20035	18603	3	18740	10010	10020	10020	20035	41	1	1	10021	10	9	10	10010	10	640	2	41	2	2	19930	20000	10010	20036	20036	20036	20036	20036
10024	20035	150	0	61	10000	19862	25	20010	20010	10010	1305229	49	16955	20035	20035	18603	3	18740	10010	10020	10020	20035	41	1	1	10021	10	9	10	10010	10	640	2	41	2	2	19930	20000	10010	20036	20036	20036	20036	20036
10024	20035	150	0	61	10000	19862	25	20010	20010	10010	1305229	49	16955	20035	20035	18603	3	18740	10010	10020	10020	20035	41	1	1	10021	10	9	10	10010	10	640	2	41	2	2	19930	20000	10010	20036	20036	20036	20036	20036
10024	20035	150	0	726	10000	19862	25	20010	20010	10010	1305229	49	16955	20035	20035	18603	3	18740	10010	10020	10020	20035	41	1	1	10021	10	9	10	10010	10	640	2	41	2	2	19930	20000	10010	20036	20036	20036	20036	20036
10024	20035	150	0	61	10000	19862	25	20010	20010	10010	1305229	49	16955	20035	20035	18603	3	18740	10010	10020	10020	20035	41	1	1	10021	10	9	10	10010	10	640	2	41	2	2	19930	20000	10010	20036	20036	20036	20036	20036
10024	20035	150	0	61	10000	19862	25	20010	20010	10010	1305229	49	16955	20035	20035	18603	3	18740	10010	10020	10020	20035	41	1	1	10021	10	9	10	10010	10	640	2	41	2	2	19930	20000	10010	20036	20036	20036	20036	20036
10024	20035	150	9	61	10000	19862	25	20010	20010	10010	1305229	49	16955	20035	20035	18603	3	18740	10010	10020	10020	20035	41	1	1	10021	10	9	10	10010	10	640	2	41	2	2	19930	20000	10010	20036	20036	20036	20036	20036

Test 3: Latency 3->2

Chain cycles: 1

Code:

  negs w0, w1, asr #17
  cset x1, cc

Initialization

  mov x0, 1
  mov x1, 2
  mov x2, 3
  mov x3, 4
  mov x4, 5

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code, minus 1 chain cycle): 2.0035

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)	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)	l1d cache writeback (a8)	a9	ac	branch cond mispred nonspec (c5)	branch mispred nonspec (cb)	cd	cf	d5	map dispatch bubble (d6)	e0	? int output thing (e9)	? int retires (ef)	f5	f6	f7	f8	fd
20204	30035	225	0	0	0	0	61	10000	29899	25	30100	30100	20107	1956240	1	49	26955	30035	30035	27391	8	27486	20107	20224	20224	30035	85	1	1	20201	100	99	100	20100	10100	0	0	0	0	0	1	1	1	1319	1	16	29982	30000	20100	30036	30036	30036	30036	30036
20204	30035	225	0	0	0	0	61	10000	29899	25	30100	30100	20107	1956240	1	49	26955	30035	30035	27391	8	27486	20107	20224	20224	30035	85	1	1	20201	100	99	100	20100	10100	0	0	0	0	0	1	1	1	1320	1	16	29983	30000	20100	30036	30036	30036	30036	30036
20204	30035	225	0	0	0	0	61	10000	29899	25	30100	30100	20107	1956240	1	49	24644	30035	30035	27391	7	27486	20107	20224	20224	30035	85	1	1	20201	100	99	100	20100	10100	0	0	0	0	0	1	1	1	1320	1	16	29983	30000	20100	30036	30036	30036	30036	30036
20204	30035	225	0	0	0	0	61	10000	29899	25	30100	30100	20107	1956240	1	49	26955	30035	30035	27391	7	27485	20107	20224	20224	30035	85	1	1	20201	100	99	100	20100	10100	0	0	0	0	0	1	1	1	1320	1	16	29982	30000	20100	30036	30036	30036	30036	30036
20204	30035	225	0	0	0	0	61	10000	29899	25	30100	30100	20107	1956240	1	49	26955	30035	30035	27391	7	27486	20107	20224	20224	30035	85	1	1	20201	100	99	100	20100	10100	0	0	0	0	0	1	1	1	1320	0	16	29982	30000	20100	30036	30036	30036	30036	30036
20204	30035	225	0	0	0	0	61	10000	29899	25	30100	30100	20107	1956240	1	49	26955	30035	30035	27391	7	27485	20107	20224	20224	30035	85	1	1	20201	100	99	100	20100	10100	0	0	0	0	0	1	1	1	1320	0	16	29982	30000	20100	30036	30036	30036	30036	30036
20204	30035	225	0	0	0	0	61	10000	29899	25	30100	30100	20107	1956240	1	49	26955	30035	30035	27391	8	27486	20107	20224	20224	30035	85	1	1	20201	100	99	100	20100	10100	0	0	0	0	0	1	1	1	1319	1	16	29982	30000	20100	30036	30036	30036	30036	30036
20204	30035	224	0	0	0	0	61	10000	29899	25	30100	30100	20107	1956240	1	49	26955	30035	30035	27391	7	27485	20107	20224	20224	30035	85	1	1	20201	100	99	100	20100	10100	0	0	0	0	0	1	1	1	1319	0	16	29983	30000	20100	30036	30036	30036	30036	30036
20204	30035	225	0	0	0	0	61	10000	29899	25	30100	30100	20107	1956240	1	49	26955	30035	30035	27391	8	27485	20107	20224	20224	30035	85	1	1	20201	100	99	100	20100	10100	0	0	0	0	0	1	1	1	1319	1	16	29983	30000	20100	30036	30036	30036	30036	30036
20204	30035	225	0	0	0	0	61	10000	29899	25	30100	30100	20107	1956240	1	49	26955	30035	30035	27391	7	27485	20107	20224	20224	30035	85	1	1	20201	100	99	100	20100	10100	0	0	0	0	0	1	1	1	1320	1	16	29983	30000	20100	30036	30036	30036	30036	30036

1000 unrolls and 10 iterations

Result (median cycles for code, minus 1 chain cycle): 2.0035

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

retire uop (01)	cycle (02)	03	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)	a9	ac	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? int output thing (e9)	? int retires (ef)	f5	f6	f7	f8	fd
20024	30035	225	1197	616	2670	10054	29927	217	30187	30186	20697	1959938	0	49	27364	30035	30035	27391	3	27498	20010	20020	20020	30035	85	1	1	20021	10	9	10	20010	10010	2	0	0	1270	1	33	1	1	29959	30000	20010	30036	30036	30036	30036	30036
20024	30035	225	0	88	168	10000	29891	25	30032	30010	20010	1956289	0	49	26955	30035	30035	27391	7	27498	20010	20109	20108	30082	85	1	1	20021	10	9	10	20010	10010	0	0	0	1270	1	33	1	1	29959	30000	20010	30036	30036	30036	30036	30036
20024	30035	225	0	0	61	10000	29891	25	30010	30010	20010	1956289	0	49	26955	30035	30035	27391	3	27498	20010	20020	20020	30035	85	1	1	20021	10	9	10	20010	10010	0	0	3	1270	1	41	1	1	29959	30000	20010	30036	30036	30036	30036	30036
20024	30035	225	0	0	103	10000	29891	25	30010	30010	20010	1956289	0	49	26955	30035	30035	27391	3	27498	20010	20020	20020	30035	85	1	1	20021	10	9	10	20010	10010	0	0	0	1270	1	33	1	1	29959	30000	20010	30036	30036	30036	30036	30036
20024	30035	225	0	0	61	10000	29891	25	30010	30010	20010	1956289	0	49	27001	30035	30035	27391	3	27498	20010	20020	20020	30035	85	1	1	20021	10	9	10	20010	10010	1	0	0	1270	1	33	1	1	29959	30000	20010	30036	30036	30036	30036	30036
20024	30035	225	0	0	61	10000	29891	25	30010	30010	20010	1956289	0	49	26955	30035	30035	27391	3	27498	20010	20020	20020	30035	85	1	1	20021	10	9	10	20010	10010	0	0	0	1270	1	33	1	1	29959	30000	20010	30036	30036	30036	30036	30036
20024	30035	225	0	0	61	10000	29891	25	30010	30010	20010	1956289	0	49	26955	30035	30035	27391	3	27498	20010	20020	20020	30035	85	1	1	20021	10	9	10	20010	10010	0	0	0	1270	1	33	1	1	29959	30000	20010	30036	30036	30036	30036	30036
20024	30035	225	0	0	61	10000	29891	25	30010	30010	20010	1956289	1	49	26955	30035	30035	27391	3	27498	20010	20020	20020	30035	85	1	1	20021	10	9	10	20010	10010	0	0	0	1270	1	33	1	1	29959	30000	20010	30036	30036	30036	30036	30036
20024	30035	225	0	0	61	10000	29891	25	30010	30010	20010	1956289	0	49	26955	30035	30035	27391	3	27498	20010	20020	20020	30035	85	1	1	20021	10	9	10	20010	10010	0	0	0	1270	1	33	1	1	29959	30000	20010	30036	30036	30036	30036	30036
20024	30035	225	0	0	61	10000	29891	25	30010	30010	20010	1956289	1	49	26955	30035	30035	27391	3	27498	20010	20020	20020	30035	85	1	1	20021	10	9	10	20010	10010	0	0	0	1270	1	33	1	1	29959	30000	20010	30036	30036	30036	30036	30036

Test 4: throughput

Count: 8

Code:

  negs w0, w8, asr #17
  negs w1, w8, asr #17
  negs w2, w8, asr #17
  negs w3, w8, asr #17
  negs w4, w8, asr #17
  negs w5, w8, asr #17
  negs w6, w8, asr #17
  negs w7, w8, asr #17

Initialization

  mov x8, 9
  mov x9, 10
  mov x10, 11

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.6676

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

retire uop (01)	cycle (02)	03	mmu table walk data (08)	18	19	1e	3f	4c	4d	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)	flags prf full (73)	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)	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)	? int retires (ef)	f5	f6	f7	f8	fd
80204	53507	400	0	0	0	0	2105	80013	48791	29	160137	160137	80176	3441890	49	50333	53414	53414	43345	2909	8	43355	80176	80288	80288	53414	39	1	1	80201	100	99	100	80100	100	0	0	0	0	0	0	1	1	1	5123	0	16	0	0	53411	160037	80100	53415	53415	53415	53415	53415
80204	53414	400	0	0	0	0	2258	80013	48791	29	160137	160137	80176	3441890	49	50334	53414	53414	43345	2909	8	43355	80176	80288	80288	53414	39	1	1	80201	100	99	100	80100	100	0	0	0	0	0	0	1	1	1	5124	0	16	0	0	53411	160037	80100	53415	53415	53415	53415	53415
80204	53414	400	0	0	0	0	1925	80013	48791	29	160137	160137	80176	3441890	49	50334	53414	53414	43345	2909	8	43355	80176	80288	80288	53414	39	1	1	80201	100	99	100	80100	100	0	0	0	0	0	0	1	1	1	5124	0	16	0	0	53411	160037	80100	53415	53415	53415	53415	53415
80204	53413	400	0	0	0	0	2029	80013	48791	29	160137	160137	80176	3441890	49	50334	53414	53414	43345	2909	8	43355	80176	80288	80288	53414	39	1	1	80201	100	99	100	80100	100	0	0	0	0	0	0	1	1	1	5124	0	16	0	0	53411	160037	80100	53415	53415	53415	53415	53415
80204	53414	400	0	0	0	0	2170	80013	48791	25	160100	160100	80100	3440005	49	50330	53410	53410	43298	2909	3	43360	80100	80200	80200	53410	39	1	1	80201	100	99	100	80100	100	0	0	0	0	0	0	0	0	0	5110	1	24	1	1	53390	160000	80100	53411	53411	53411	53411	53411
80204	53410	400	0	0	0	0	2158	80000	48741	25	160100	160100	80100	3440005	49	50330	53410	53410	43298	2909	3	43360	80100	80200	80200	53410	39	1	1	80201	100	99	100	80100	100	0	0	0	0	0	0	0	0	0	5110	1	24	1	1	53390	160000	80100	53411	53411	53411	53411	53411
80204	53410	400	0	0	0	0	208	80000	48741	25	160100	160100	80100	3440005	49	50330	53410	53410	43298	2909	3	43360	80100	80200	80200	53410	39	1	1	80201	100	99	100	80100	100	0	0	0	0	0	0	0	0	0	5110	1	24	1	1	53390	160000	80100	53411	53411	53411	53411	53411
80204	53410	400	0	0	0	0	250	80000	48741	25	160100	160100	80100	3440005	49	50330	53410	53410	43298	3024	3	43360	80100	80418	80200	53467	39	1	1	80201	100	99	100	80100	100	0	0	0	0	0	0	0	0	0	5110	1	24	1	1	53390	160000	80100	53411	53411	53411	53411	53411
80204	53410	400	0	0	0	0	2161	80000	48741	25	160100	160100	80100	3440005	49	50330	53410	53410	43298	3024	3	43360	80100	80200	80200	53410	39	1	1	80201	100	99	100	80100	100	0	0	0	0	0	0	0	0	0	5110	1	24	1	1	53390	160000	80100	53411	53411	53411	53411	53411
80204	53410	400	0	0	0	0	2064	80000	48741	25	160100	160100	80100	3440005	49	50330	53410	53410	43298	3024	3	43360	80273	80200	80200	53410	39	1	1	80201	100	99	100	80100	100	0	0	0	0	0	0	0	0	0	5110	1	24	1	1	53390	160000	80100	53411	53411	53411	53411	53411

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.6673

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	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)	flags prf full (73)	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	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? int output thing (e9)	? int retires (ef)	f5	f6	f7	f8	fd
80024	53385	400	0	0	0	0	0	3	464	80000	47946	25	160010	160010	80010	3438130	1	49	50300	53380	53380	43290	2936	3	43352	80010	80020	80020	53380	39	1	1	80021	10	9	10	80010	10	0	0	0	0	5040	18	24	11	13	53360	160000	80010	53381	53381	53381	53381	53381
80024	53380	399	0	0	0	0	0	1	61	80000	47946	25	160010	160010	80010	3438130	1	49	50300	53380	53380	43290	3251	3	43352	80010	80020	80020	53380	39	1	1	80021	10	9	10	80010	10	0	0	0	0	5020	7	24	11	14	53360	160000	80010	53381	53381	53381	53381	53381
80024	53380	400	0	0	0	0	0	1	103	80000	47946	25	160010	160010	80010	3438130	0	49	50300	53380	53380	43290	2936	3	43352	80010	80020	80020	53380	39	1	1	80021	10	9	10	80010	10	0	0	0	0	5020	12	24	9	13	53360	160000	80010	53381	53381	53381	53381	53381
80024	53380	400	0	0	0	0	0	1	210	80000	47946	25	160010	160010	80010	3438130	0	49	50300	53380	53380	43290	2936	3	43352	80010	80020	80224	53380	39	1	1	80021	10	9	10	80010	10	0	0	0	0	5020	14	24	13	13	53360	160000	80010	53381	53381	53381	53381	53381
80024	53380	399	0	0	0	0	0	1	233	80000	47946	25	160010	160010	80010	3438130	0	49	50300	53380	53380	43290	3251	3	43352	80010	80020	80020	53380	39	1	1	80021	10	9	10	80010	10	0	0	0	0	5020	12	24	11	11	53360	160000	80010	53381	53381	53381	53381	53381
80024	53380	400	0	0	0	0	0	1	124	80000	47946	25	160010	160010	80010	3438130	1	49	50300	53380	53380	43290	2749	3	43352	80010	80020	80020	53380	39	1	1	80021	10	9	10	80010	10	0	0	0	0	5020	12	24	14	14	53360	160000	80010	53381	53381	53381	53381	53381
80024	53380	400	0	0	0	0	0	1	460	80000	47946	25	160010	160010	80010	3438130	0	49	50300	53380	53380	43290	3251	3	43352	80010	80020	80020	53380	39	1	1	80021	10	9	10	80010	10	0	0	0	0	5020	13	24	7	12	53360	160000	80010	53381	53381	53381	53381	53381
80024	53380	399	0	0	0	0	0	1	124	80000	47946	25	160010	160010	80010	3438130	0	49	50300	53380	53380	43290	2936	3	43352	80010	80020	80020	53380	39	1	1	80021	10	9	10	80010	10	0	0	0	0	5020	9	24	12	12	53360	160000	80010	53381	53381	53381	53381	53381
80024	53380	399	0	0	0	0	0	1	166	80000	47946	25	160010	160010	80010	3438130	0	49	50300	53380	53380	43290	2936	3	43352	80010	80020	80020	53380	39	1	1	80021	10	9	10	80010	10	0	0	0	0	5020	11	24	14	12	53360	160000	80010	53381	53381	53381	53381	53381
80024	53380	399	0	0	0	0	6	1	103	80000	47946	25	160010	160010	80010	3438130	0	49	50300	53380	53380	43290	3251	3	43352	80010	80020	80020	53380	39	1	1	80021	10	9	10	80010	10	0	0	0	0	5020	11	24	13	11	53360	160000	80010	53381	53381	53381	53381	53381

NEGS (register, asr, 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 3->2

100 unrolls and 100 iterations

1000 unrolls and 10 iterations

Test 4: throughput

100 unrolls and 100 iterations

1000 unrolls and 10 iterations