Firestorm: LSR (register, 32-bit) measurements

Code:

  lsr w0, w0, w1

Initialization

  mov x0, 1
  mov x1, 2

(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	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)	cf	d0	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? int output thing (e9)	? int retires (ef)	f5	f6	f7	f8	fd
1004	1035	7	0	61	862	25	1000	1000	1000	16916	1	1035	1035	728	3	868	1000	1000	2000	1035	41	1	1	1001	1000	0	73	0	2	41	2	2	937	1000	1000	1036	1036	1036	1036	1036
1004	1035	8	0	61	862	25	1000	1000	1000	16916	1	1035	1035	728	3	868	1000	1000	2000	1035	41	1	1	1001	1000	0	73	0	2	41	2	2	937	1000	1000	1036	1036	1036	1036	1036
1004	1035	7	0	61	862	25	1000	1000	1000	16916	1	1035	1035	728	3	868	1000	1000	2000	1035	41	1	1	1001	1000	0	73	0	2	41	2	2	937	1000	1000	1036	1036	1036	1036	1036
1004	1035	8	0	107	862	25	1000	1000	1000	16916	1	1035	1035	728	3	868	1000	1000	2000	1035	41	1	1	1001	1000	0	73	0	2	41	2	3	937	1000	1000	1036	1036	1036	1036	1036
1004	1035	7	0	61	862	25	1000	1000	1000	16916	1	1035	1035	728	3	868	1000	1000	2000	1035	41	1	1	1001	1000	0	73	0	2	41	2	2	937	1000	1000	1036	1036	1036	1036	1036
1004	1035	7	0	61	862	25	1000	1000	1000	16916	1	1035	1035	728	3	868	1000	1000	2000	1035	41	1	1	1001	1000	0	73	0	2	41	2	2	937	1000	1000	1036	1036	1036	1036	1036
1004	1035	8	0	61	862	25	1000	1000	1000	16916	1	1035	1035	728	3	868	1000	1000	2000	1035	41	1	1	1001	1000	0	73	0	2	41	2	3	937	1000	1000	1036	1036	1036	1036	1036
1004	1035	8	0	61	862	25	1000	1000	1000	16916	1	1035	1035	728	3	868	1000	1000	2000	1035	41	1	1	1001	1000	0	73	0	2	41	2	2	937	1000	1000	1036	1036	1036	1036	1036
1004	1035	7	0	61	862	25	1000	1000	1000	16916	1	1035	1035	728	3	868	1000	1000	2000	1035	41	1	1	1001	1000	0	73	0	2	41	2	2	937	1000	1000	1036	1036	1036	1036	1036
1004	1035	8	0	61	862	25	1000	1000	1000	16916	1	1035	1035	728	3	868	1000	1000	2000	1035	41	1	1	1001	1000	0	73	0	2	41	2	2	937	1000	1000	1036	1036	1036	1036	1036

Test 2: Latency 1->2

Code:

  lsr w0, w0, w1

Initialization

  mov x0, 1
  mov x1, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 1.0035

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

retire uop (01)	cycle (02)	03	1e	1f	3a	3f	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)	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	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? int output thing (e9)	? int retires (ef)	f5	f6	f7	f8	fd
10204	10035	75	0	0	0	61	9877	25	10100	10100	10100	88664	49	6955	10035	10035	8580	0	3	8722	10100	10200	20200	10035	41	1	1	10201	100	99	100	10100	100	0	0	710	1	37	1	1	9941	10000	10100	10036	10036	10036	10036	10036
10204	10035	75	0	0	0	61	9877	25	10100	10100	10434	90658	49	6955	10035	10035	8580	0	3	8722	10100	10200	20200	10035	41	1	1	10201	100	99	100	10100	100	0	12	710	1	37	1	1	9941	10000	10100	10036	10036	10036	10036	10036
10204	10035	75	0	0	0	61	9877	25	10100	10100	10100	88664	49	6955	10035	10035	8580	0	3	8722	10100	10200	20200	10035	41	1	1	10201	100	99	100	10100	100	0	0	710	1	37	1	1	9941	10000	10100	10036	10036	10036	10036	10036
10204	10035	76	0	0	0	61	9877	25	10100	10100	10100	88664	49	6955	10035	10035	8580	0	3	8722	10100	10200	20200	10035	41	1	1	10201	100	99	100	10100	100	0	0	710	1	37	1	1	9941	10000	10100	10036	10036	10036	10036	10036
10204	10035	75	0	0	0	61	9877	25	10100	10100	10100	88664	49	6955	10035	10035	8580	0	3	8722	10100	10200	20200	10035	41	1	1	10201	100	99	100	10100	100	0	0	710	1	37	1	1	9941	10000	10100	10036	10036	10036	10036	10036
10204	10035	75	0	0	0	61	9877	25	10100	10100	10100	88664	49	6955	10035	10035	8580	0	3	8722	10100	10200	20200	10035	41	1	1	10201	100	99	100	10100	100	0	0	710	1	37	1	1	9941	10000	10100	10036	10036	10036	10036	10036
10204	10035	75	0	0	0	61	9877	25	10100	10100	10100	88664	49	6955	10082	10082	8580	0	3	8722	10100	10200	20200	10035	41	1	1	10201	100	99	100	10100	100	0	24	710	1	37	1	1	9941	10000	10100	10036	10036	10036	10036	10036
10204	10035	76	0	0	0	61	9877	25	10100	10100	10100	88664	49	6955	10035	10035	8580	0	3	8722	10100	10200	20200	10035	41	1	1	10201	100	99	100	10100	100	0	0	710	1	37	1	1	9941	10000	10100	10036	10036	10036	10036	10036
10204	10035	75	0	0	0	61	9877	25	10100	10100	10100	88664	49	6955	10035	10035	8580	7	3	8722	10100	10200	20200	10035	41	1	1	10201	100	99	100	10100	100	0	0	710	1	37	1	1	9941	10000	10100	10036	10036	10036	10036	10036
10204	10035	75	0	0	0	61	9877	25	10100	10100	10100	88664	49	6955	10035	10035	8580	0	3	8722	10100	10200	20200	10035	41	1	1	10201	100	99	100	10100	100	0	0	710	1	37	1	1	9941	10000	10100	10036	10036	10036	10036	10036

1000 unrolls and 10 iterations

Result (median cycles for code): 1.0035

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

retire uop (01)	cycle (02)	03	18	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)	ac	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? int output thing (e9)	? int retires (ef)	f5	f6	f7	f8	fd
10024	10035	75	1	3	61	9863	25	10010	10010	10010	88784	0	49	6955	10035	10035	8602	3	8740	10010	10020	20020	10035	41	1	1	10021	10	9	10	10010	10	0	0	640	3	41	3	3	9940	10000	10010	10036	10036	10036	10036	10036
10024	10035	75	0	15	61	9863	25	10010	10010	10010	88784	0	49	6955	10035	10035	8602	3	8740	10010	10020	20020	10035	41	1	1	10021	10	9	10	10010	10	0	0	640	3	41	3	3	9940	10000	10010	10036	10036	10036	10036	10036
10024	10035	75	0	15	61	9863	25	10010	10010	10010	88784	0	49	6955	10035	10035	8602	3	8740	10012	10020	20020	10035	41	1	1	10021	10	9	10	10010	10	0	0	640	3	41	3	3	9940	10000	10010	10036	10036	10036	10036	10036
10024	10035	75	0	0	178	9863	25	10010	10010	10010	88784	0	49	6955	10035	10035	8602	3	8740	10010	10020	20020	10035	41	1	1	10021	10	9	10	10010	10	0	0	640	3	41	3	3	9940	10000	10010	10036	10036	10036	10036	10036
10024	10035	75	0	132	536	9863	25	10010	10010	10010	88784	0	49	6955	10035	10035	8602	3	8740	10010	10020	20020	10035	41	1	1	10021	10	9	10	10010	10	0	0	640	3	41	3	3	9940	10000	10010	10036	10036	10081	10036	10036
10024	10035	75	0	0	61	9863	25	10010	10010	10010	88784	0	49	6955	10035	10035	8602	3	8740	10010	10020	20020	10035	41	1	1	10021	10	9	10	10010	10	0	0	640	3	41	3	3	9940	10000	10010	10036	10036	10036	10036	10036
10024	10035	75	0	0	213	9863	25	10010	10010	10010	88784	0	49	6955	10035	10035	8602	3	8740	10010	10020	20020	10035	41	1	1	10021	10	9	10	10010	10	0	0	640	3	41	3	2	9940	10000	10010	10036	10036	10036	10036	10036
10024	10035	75	0	18	61	9863	25	10010	10010	10010	88784	0	49	6955	10035	10035	8602	3	8742	10012	10020	20020	10035	41	1	1	10021	10	9	10	10010	10	0	0	640	3	41	3	3	9940	10000	10010	10036	10036	10036	10036	10036
10024	10035	75	0	0	61	9863	25	10010	10010	10010	88784	0	49	6955	10035	10035	8602	3	8740	10010	10020	20020	10035	41	1	1	10021	10	9	10	10010	10	0	0	640	3	41	3	3	9940	10000	10010	10036	10036	10036	10036	10036
10024	10035	75	0	0	441	9863	25	10010	10010	10010	88784	0	49	6955	10035	10035	8602	3	8740	10010	10020	20020	10035	41	1	1	10021	10	9	10	10010	10	0	0	640	3	41	3	3	9940	10000	10010	10036	10036	10036	10036	10036

Test 3: Latency 1->3

Code:

  lsr w0, w1, w0

Initialization

  mov x0, 1
  mov x1, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 1.0035

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)	18	19	1e	1f	3a	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)	l1d cache writeback (a8)	a9	ac	c2	branch cond mispred nonspec (c5)	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? int output thing (e9)	? int retires (ef)	f5	f6	f7	f8	fd
10204	10035	75	0	0	0	0	0	0	0	61	9877	25	10100	10100	10100	88664	0	49	6955	10035	10035	8580	3	8722	10100	10200	20200	10035	41	1	1	10201	100	99	100	10100	100	0	0	0	0	0	0	0	0	710	1	37	1	1	9941	10000	10100	10036	10036	10036	10036	10036
10204	10035	75	0	0	0	0	0	0	0	61	9877	25	10100	10100	10100	88664	0	49	6955	10035	10035	8580	3	8722	10100	10200	20200	10035	41	1	1	10201	100	99	100	10100	100	0	0	0	0	0	0	0	0	710	1	37	1	1	9941	10000	10100	10036	10036	10036	10036	10036
10204	10035	75	0	0	0	0	0	0	0	61	9877	25	10100	10100	10100	88664	0	49	6955	10035	10035	8580	3	8722	10100	10200	20200	10035	41	1	1	10201	100	99	100	10100	100	0	0	0	0	0	3	0	0	710	1	37	1	1	9976	10000	10100	10036	10036	10036	10036	10036
10204	10035	75	0	0	0	0	0	0	0	61	9877	25	10100	10100	10100	88664	0	49	6955	10035	10035	8580	3	8722	10100	10200	20200	10035	41	1	1	10201	100	99	100	10100	100	0	0	0	27	0	0	0	0	710	1	37	1	1	9941	10000	10100	10036	10036	10036	10036	10036
10204	10035	75	0	0	0	0	0	0	0	61	9877	25	10100	10100	10100	88664	0	49	6955	10035	10035	8580	3	8722	10100	10200	20200	10035	41	1	1	10201	100	99	100	10100	100	0	0	0	0	0	3	0	0	710	1	37	1	1	9941	10000	10100	10036	10036	10036	10036	10036
10204	10035	75	0	0	0	0	0	0	0	61	9877	25	10100	10100	10100	88664	0	49	6955	10035	10035	8580	3	8722	10100	10200	20200	10035	41	1	1	10201	100	99	100	10100	100	0	0	0	0	0	3	0	0	710	1	37	1	1	9941	10000	10100	10036	10036	10036	10036	10036
10204	10035	75	0	0	0	0	0	0	0	61	9877	25	10100	10100	10100	88664	0	49	6955	10035	10035	8580	3	8722	10100	10200	20200	10035	41	1	1	10201	100	99	100	10100	100	0	0	0	4	0	0	0	0	710	1	37	1	1	9941	10000	10100	10036	10036	10036	10036	10036
10204	10035	75	0	0	0	0	0	0	0	61	9877	25	10100	10100	10100	88664	0	49	6955	10035	10035	8580	3	8722	10100	10200	20200	10035	41	1	1	10201	100	99	100	10100	100	0	0	0	5	0	0	0	0	710	1	37	1	1	9941	10000	10100	10036	10036	10036	10036	10036
10204	10035	75	0	0	0	0	0	0	0	61	9877	25	10100	10100	10100	88664	0	49	6955	10035	10035	8580	3	8722	10100	10200	20200	10035	41	1	1	10201	100	99	100	10100	100	0	0	0	0	0	0	0	0	710	1	37	1	1	9941	10000	10100	10036	10036	10036	10036	10036
10204	10035	75	0	0	0	0	0	0	0	61	9877	25	10100	10100	10100	88664	0	49	6955	10035	10035	8580	3	8722	10100	10200	20200	10035	41	1	1	10201	100	99	100	10100	100	0	0	0	0	0	3	0	0	710	1	37	1	1	9941	10000	10100	10036	10036	10036	10036	10036

1000 unrolls and 10 iterations

Result (median cycles for code): 1.0035

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

retire uop (01)	cycle (02)	03	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	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)	? int retires (ef)	f5	f6	f7	f8	fd
10024	10076	75	195	103	9863	25	10010	10010	10010	88784	1	49	6955	10035	10035	8602	3	8740	10010	10020	20020	10035	41	1	1	10021	10	9	10	10010	10	0	0	0	0	640	3	41	2	2	9940	10000	10010	10036	10036	10036	10036	10036
10024	10035	75	0	61	9863	25	10010	10010	10010	90782	1	49	6955	10035	10035	8602	3	8740	10010	10020	20020	10035	41	1	1	10021	10	9	10	10010	10	0	0	0	0	640	2	41	2	2	9940	10000	10010	10036	10036	10036	10036	10036
10024	10035	75	0	61	9863	25	10010	10010	10010	88784	1	49	6955	10035	10035	8602	3	8740	10010	10020	20020	10035	41	1	1	10021	10	9	10	10010	10	0	2	0	0	640	2	41	2	2	9940	10000	10010	10036	10036	10036	10036	10036
10024	10035	75	0	185	9863	25	10010	10010	10010	88784	1	49	6955	10035	10035	8602	3	8740	10010	10020	20020	10035	41	1	1	10021	10	9	10	10010	10	0	0	0	0	640	2	41	2	2	9940	10000	10010	10036	10036	10036	10036	10036
10024	10035	75	6	61	9863	25	10010	10010	10010	88784	1	49	6955	10035	10035	8602	3	8740	10010	10020	20020	10035	41	1	1	10021	10	9	10	10010	10	0	0	0	0	640	2	41	2	2	9940	10000	10010	10036	10036	10036	10036	10036
10024	10035	76	207	61	9863	25	10010	10010	10010	88784	1	49	6955	10035	10035	8602	3	8740	10010	10020	20020	10035	41	1	1	10021	10	9	10	10010	10	0	0	0	0	640	2	41	2	2	9940	10000	10010	10036	10036	10036	10036	10036
10024	10035	75	0	61	9863	25	10010	10010	10010	88784	1	49	6955	10035	10035	8602	3	8740	10010	10020	20020	10035	41	1	1	10021	10	9	10	10010	10	0	0	0	0	640	2	41	2	2	9940	10000	10010	10036	10036	10036	10036	10036
10024	10035	75	0	61	9863	25	10010	10010	10010	88784	1	49	6955	10035	10035	8602	3	8740	10010	10020	20020	10035	41	1	1	10021	10	9	10	10010	10	0	0	0	0	640	2	41	2	2	9940	10000	10010	10036	10036	10036	10036	10036
10024	10035	75	0	61	9863	25	10010	10010	10010	88784	1	49	6955	10035	10035	8602	3	8740	10010	10020	20020	10035	41	1	1	10021	10	9	10	10010	10	0	0	0	0	640	2	41	2	2	9940	10000	10010	10036	10036	10036	10036	10036
10024	10035	75	0	194	9863	25	10010	10010	10010	88784	1	49	6955	10035	10035	8602	3	8740	10010	10020	20020	10035	41	1	1	10021	10	9	10	10010	10	0	0	0	0	640	2	41	2	2	9940	10000	10010	10036	10036	10036	10036	10036

Test 4: throughput

Count: 8

Code:

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

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): 0.1673

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

retire uop (01)	cycle (02)	03	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	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? int output thing (e9)	? int retires (ef)	f5	f6	f7	f8	fd
80204	13404	101	0	0	35	25	80100	80100	80100	400500	1	49	10306	13386	13386	3323	3	3341	80100	80200	160200	13386	39	1	1	80201	100	99	100	80100	100	0	0	5110	3	19	1	1	13383	80000	80100	13387	13387	13387	13387	13387
80204	13386	100	0	0	35	25	80100	80100	80100	400500	0	49	10306	13386	13386	3323	3	3341	80100	80200	160200	13386	39	1	1	80201	100	99	100	80100	100	0	0	5110	1	19	1	1	13383	80000	80100	13387	13387	13387	13387	13387
80204	13386	100	0	0	35	25	80100	80100	80100	400500	1	49	10306	13386	13386	3323	3	3341	80100	80200	160200	13386	39	1	1	80201	100	99	100	80100	100	0	0	5110	1	19	1	1	13383	80000	80100	13387	13387	13387	13387	13387
80204	13386	100	0	0	35	25	80100	80100	80100	400500	0	49	10306	13386	13386	3323	3	3341	80100	80200	160200	13386	39	1	1	80201	100	99	100	80100	100	0	6	5110	1	19	1	1	13383	80000	80100	13387	13387	13387	13387	13387
80204	13386	100	0	0	35	25	80100	80100	80100	400500	0	49	10306	13386	13386	3323	3	3341	80100	80200	160200	13386	39	1	1	80201	100	99	100	80100	100	0	0	5110	1	19	1	1	13383	80000	80100	13387	13387	13387	13387	13387
80204	13386	100	0	0	35	25	80100	80100	80100	400500	1	49	10306	13386	13386	3323	3	3341	80100	80200	160200	13386	39	1	1	80201	100	99	100	80100	100	1	0	5110	1	19	1	1	13383	80000	80100	13387	13387	13387	13387	13387
80204	13386	100	0	0	35	25	80100	80100	80100	400500	1	49	10306	13386	13386	3323	3	3341	80100	80200	160200	13386	39	1	1	80201	100	99	100	80100	100	1	0	5110	1	19	1	1	13383	80000	80100	13387	13387	13387	13387	13387
80204	13386	100	0	0	35	25	80100	80100	80100	400500	0	49	10306	13386	13386	3323	3	3341	80100	80200	160200	13386	39	1	1	80201	100	99	100	80100	100	0	0	5110	1	19	1	1	13383	80000	80100	13387	13387	13387	13387	13387
80204	13386	101	0	0	35	25	80100	80100	80100	400500	0	49	10306	13386	13386	3323	3	3341	80100	80200	160200	13386	39	1	1	80201	100	99	100	80100	100	0	3	5110	1	19	1	1	13383	80000	80100	13387	13387	13387	13387	13387
80204	13386	101	0	0	35	25	80100	80100	80100	400500	0	49	10306	13386	13386	3323	3	3341	80100	80200	160200	13386	39	1	1	80201	100	99	100	80100	100	7	0	5110	1	19	1	1	13383	80000	80100	13387	13387	13387	13387	13387

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.1671

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	61	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	c3	cf	d0	d2	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? int output thing (e9)	? int retires (ef)	f5	f6	f7	f8	fd
80024	13376	100	0	35	25	80010	80010	80010	400050	1	5	49	10291	13371	13373	3330	0	3	3348	80010	80020	160020	13371	39	1	1	80021	10	9	10	80010	10	0	0	0	5022	5	3	5	19	5	5	13368	80000	80010	13372	13372	13372	13372	13372
80024	13371	100	0	35	25	80010	80010	80010	400050	1	5	49	10291	13371	13371	3330	0	3	3348	80010	80020	160020	13371	39	1	1	80021	10	9	10	80010	10	0	0	0	5021	5	3	4	19	5	5	13368	80000	80010	13372	13372	13372	13372	13372
80024	13371	100	6	35	25	80010	80010	80010	400050	1	5	49	10291	13371	13371	3330	0	3	3348	80010	80020	160020	13371	39	1	1	80021	10	9	10	80010	10	0	0	0	5021	5	3	6	19	6	6	13368	80000	80010	13372	13372	13372	13372	13372
80024	13371	100	0	35	25	80010	80010	80010	400050	1	5	49	10291	13371	13371	3330	0	3	3348	80010	80020	160020	13371	39	1	1	80021	10	9	10	80010	10	0	0	0	5022	5	3	5	19	6	6	13368	80000	80010	13372	13372	13372	13372	13372
80024	13371	100	0	35	25	80010	80010	80010	400050	1	5	49	10291	13371	13371	3330	0	3	3348	80010	80020	160020	13371	39	1	1	80021	10	9	10	80010	10	0	0	0	5021	5	4	6	19	5	5	13368	80000	80010	13372	13372	13372	13372	13372
80024	13371	100	0	35	25	80010	80010	80010	400050	0	5	49	10291	13371	13373	3330	0	3	3348	80010	80020	160020	13371	39	1	1	80021	10	9	10	80010	10	0	0	0	5021	5	4	5	19	6	5	13368	80000	80010	13372	13372	13372	13372	13372
80024	13371	100	0	35	25	80010	80010	80010	400050	1	0	49	10291	13371	13371	3330	0	3	3348	80010	80020	160020	13371	39	1	1	80021	10	9	10	80010	10	0	0	0	5021	0	0	5	19	5	4	13368	80000	80010	13372	13372	13372	13372	13372
80024	13371	100	252	35	25	80010	80010	80010	400050	1	0	49	10291	13371	13371	3330	0	3	3348	80010	80020	160020	13371	39	1	1	80021	10	9	10	80010	10	0	0	0	5022	5	0	5	19	5	6	13368	80000	80010	13372	13372	13372	13372	13372
80024	13371	100	0	35	25	80010	80010	80010	400050	1	0	49	10291	13371	13371	3330	0	3	3348	80010	80020	160020	13371	39	1	1	80021	10	9	10	80010	10	0	0	0	5021	5	0	6	19	6	4	13368	80000	80010	13372	13372	13372	13372	13372
80024	13371	100	0	35	25	80010	80010	80010	400050	0	5	49	10291	13371	13371	3330	0	3	3348	80010	80020	160020	13371	39	1	1	80021	10	9	10	80010	10	0	0	0	5022	5	4	6	19	5	5	13368	80000	80010	13372	13372	13372	13372	13372

LSR (register, 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