Firestorm: LSL (register, 64-bit) measurements

Code:

  lsl x0, x0, x1

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	mmu table walk instruction (07)	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 tlb access (a0)	l1d tlb miss (a1)	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
1004	1035	7	0	0	61	862	25	1000	1000	1000	16916	1	1035	1035	728	3	868	1000	1000	2000	1035	41	1	1	1001	1000	0	0	0	0	0	73	1	41	1	1	937	1000	1000	1036	1036	1036	1036	1036
1004	1035	7	0	0	61	862	25	1000	1000	1000	16916	1	1035	1035	728	3	868	1000	1000	2000	1035	41	1	1	1001	1000	0	0	0	0	0	73	2	39	2	2	936	1000	1000	1036	1036	1036	1036	1036
1004	1035	7	1	0	61	862	25	1000	1000	1000	16916	0	1035	1035	728	3	868	1000	1000	2000	1035	41	1	1	1001	1000	0	0	0	0	0	73	1	41	1	1	937	1000	1000	1036	1036	1036	1036	1036
1004	1035	7	0	0	61	862	25	1000	1000	1000	16916	1	1035	1035	728	3	868	1000	1000	2000	1035	41	1	1	1001	1000	0	0	0	0	0	73	1	41	1	1	937	1000	1000	1036	1036	1036	1036	1036
1004	1035	8	0	0	61	862	25	1000	1000	1000	16916	1	1035	1035	728	3	868	1000	1000	2000	1035	41	1	1	1001	1000	0	0	0	0	0	73	1	41	1	1	937	1000	1000	1036	1036	1036	1036	1036
1004	1035	7	0	0	61	862	25	1000	1000	1000	16916	0	1035	1035	728	3	868	1000	1000	2000	1035	41	1	1	1001	1000	2	0	0	0	0	73	1	41	1	1	937	1000	1000	1036	1036	1036	1036	1036
1004	1035	8	1	0	61	862	25	1000	1000	1000	16916	1	1035	1035	728	3	868	1000	1000	2000	1035	41	1	1	1001	1000	0	0	0	0	0	73	1	41	1	1	937	1000	1000	1036	1036	1036	1036	1036
1004	1035	8	0	0	61	863	25	1000	1000	1000	16916	0	1035	1035	728	3	868	1000	1000	2000	1035	41	1	1	1001	1000	0	0	0	0	0	73	1	41	1	1	937	1000	1000	1036	1036	1036	1036	1036
1004	1035	8	0	0	61	862	25	1000	1000	1000	16916	1	1035	1035	728	3	870	1000	1000	2000	1035	43	1	1	1001	1000	0	0	0	0	0	73	1	41	1	1	937	1000	1000	1036	1036	1036	1036	1036
1004	1035	7	0	0	82	862	25	1000	1000	1000	16916	1	1035	1035	728	3	868	1000	1000	2000	1035	41	1	1	1001	1000	0	0	0	0	0	73	1	41	1	1	937	1000	1000	1036	1036	1036	1036	1036

Test 2: Latency 1->2

Code:

  lsl x0, x0, x1

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 instruction (07)	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)	st unit uop (a7)	l1d cache writeback (a8)	a9	ac	c2	cf	d0	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	1	0	0	0	0	414	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	710	0	2	37	2	2	9941	10000	10100	10036	10036	10036	10036	10036
10204	10035	75	0	0	0	0	0	0	0	0	433	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	710	0	2	37	2	2	9941	10000	10100	10036	10036	10036	10036	10036
10204	10035	75	0	0	0	0	0	138	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	710	0	2	37	2	2	9941	10000	10100	10036	10036	10036	10036	10036
10204	10035	75	0	0	0	0	0	12	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	47	0	0	0	710	0	2	37	2	2	9941	10000	10100	10036	10036	10036	10036	10036
10204	10035	76	0	0	0	0	0	0	0	0	61	9877	25	10100	10100	10100	88664	0	49	6955	10035	10035	8580	3	8736	10100	10377	20200	10035	41	1	1	10201	100	99	100	10100	100	0	0	0	0	0	0	0	710	0	2	37	2	2	9941	10000	10100	10036	10036	10036	10036	10036
10204	10035	75	0	0	0	0	0	39	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	710	0	2	37	2	2	9941	10000	10100	10036	10036	10036	10036	10036
10204	10035	75	0	0	0	0	0	60	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	710	0	2	37	2	2	9941	10000	10100	10036	10036	10036	10036	10036
10204	10035	75	0	0	0	0	0	42	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	710	0	2	37	2	2	9941	10000	10100	10036	10036	10036	10036	10036
10204	10035	75	0	0	0	0	0	63	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	1	0	0	0	710	0	2	37	2	2	9941	10000	10100	10036	10036	10036	10036	10036
10204	10035	75	0	0	0	0	0	0	0	0	61	9877	25	10100	10100	10100	88664	0	49	6955	10035	10081	8580	7	8722	10100	10200	20200	10035	41	1	1	10201	100	99	100	10100	100	0	0	0	0	0	0	0	710	0	2	37	2	2	9941	10000	10100	10036	10081	10036	10082	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	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	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	103	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	640	2	41	2	2	9940	10000	10010	10036	10036	10036	10036	10036
10024	10035	75	320	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	640	2	41	2	2	9940	10000	10010	10036	10036	10036	10036	10036
10024	10035	76	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	640	2	41	2	2	9940	10000	10010	10036	10036	10036	10036	10036
10024	10035	75	61	9863	25	10010	10010	10010	88784	0	49	6955	10035	10035	8602	3	8740	10010	10191	20020	10035	41	1	1	10021	10	9	10	10010	10	0	640	2	41	2	2	9940	10000	10010	10036	10036	10036	10036	10036
10024	10035	75	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	640	2	41	2	2	9940	10000	10010	10036	10036	10036	10036	10036
10024	10035	75	251	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	640	2	41	2	2	9940	10000	10010	10036	10036	10036	10036	10036
10024	10035	75	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	640	2	41	2	2	9940	10000	10010	10036	10036	10036	10036	10036
10024	10035	75	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	640	2	41	2	2	9940	10000	10010	10036	10036	10036	10036	10036
10024	10035	75	61	9863	25	10010	10033	10010	88784	1	49	6955	10035	10035	8602	3	8740	10010	10020	20020	10035	41	1	1	10021	10	9	10	10010	10	0	640	2	41	2	2	9940	10000	10010	10036	10036	10036	10036	10036
10024	10035	75	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	640	2	41	2	2	9940	10000	10010	10036	10036	10036	10036	10036

Test 3: Latency 1->3

Code:

  lsl x0, x1, x0

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	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)	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
10204	10035	75	285	61	9877	25	10100	10100	10100	88664	49	6955	10035	10035	8580	3	8722	10100	10200	20200	10035	41	1	1	10201	100	99	100	10100	100	0	0	0	710	2	37	1	1	9941	10000	10100	10036	10036	10036	10036	10036
10204	10035	75	0	61	9877	25	10100	10100	10100	88664	49	6955	10035	10035	8580	3	8722	10100	10200	20200	10035	41	1	1	10201	100	99	100	10100	100	0	0	0	710	1	37	1	1	9941	10000	10100	10036	10036	10036	10036	10036
10204	10035	75	0	82	9877	25	10100	10100	10100	88664	49	6955	10035	10035	8580	3	8722	10100	10200	20200	10035	41	1	1	10201	100	99	100	10100	100	0	0	0	710	1	37	1	1	9941	10000	10100	10036	10036	10036	10036	10036
10204	10035	75	0	61	9877	25	10100	10100	10100	88664	49	6955	10035	10035	8580	3	8722	10100	10200	20200	10035	41	1	1	10201	100	99	100	10100	100	0	0	0	710	1	37	1	1	9941	10000	10100	10036	10036	10036	10036	10036
10204	10035	75	240	61	9877	25	10100	10100	10100	88664	49	6955	10035	10035	8580	3	8722	10100	10200	20200	10035	41	3	1	10201	100	99	100	10100	100	0	0	0	710	1	37	1	1	9941	10000	10100	10036	10036	10036	10036	10036
10204	10035	76	0	61	9877	25	10100	10100	10100	88664	49	6955	10035	10035	8580	3	8722	10100	10200	20200	10035	41	1	1	10201	100	99	100	10100	100	0	0	3	710	1	37	1	1	9941	10000	10100	10036	10036	10036	10036	10036
10204	10035	75	0	61	9877	25	10100	10100	10100	88664	49	6955	10035	10035	8580	3	8722	10100	10200	20200	10035	41	1	1	10201	100	99	100	10100	100	0	0	0	710	1	37	1	1	9941	10000	10100	10036	10036	10036	10036	10036
10204	10035	75	0	620	9877	25	10100	10100	10100	88664	49	6955	10035	10035	8580	3	8722	10100	10200	20200	10035	41	1	1	10201	100	99	100	10100	100	0	1	0	710	1	37	1	1	9941	10000	10100	10036	10036	10036	10036	10036
10204	10035	75	0	61	9877	25	10100	10100	10100	88664	49	6955	10035	10035	8580	3	8722	10100	10200	20200	10035	41	1	1	10201	100	99	100	10100	100	0	0	0	710	1	37	1	1	9941	10000	10100	10036	10036	10036	10036	10036
10204	10035	75	21	61	9877	25	10100	10100	10100	88664	49	6955	10035	10035	8580	3	8722	10100	10200	20200	10035	41	1	1	10201	100	99	100	10100	100	0	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)	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	0	61	9863	25	10010	10010	10010	88784	49	6955	10035	10035	8602	3	8740	10010	10020	20020	10035	41	1	1	10021	10	9	10	10010	10	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	49	6955	10035	10035	8602	3	8740	10010	10020	20020	10035	41	1	1	10021	10	9	10	10010	10	0	0	640	2	41	2	2	9940	10000	10010	10036	10036	10036	10036	10036
10025	10035	75	0	61	9863	25	10010	10010	10010	88784	49	6955	10035	10035	8602	3	8740	10010	10020	20020	10035	41	1	1	10021	10	9	10	10010	10	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	49	6955	10035	10035	8602	3	8740	10010	10020	20020	10035	41	1	1	10021	10	9	10	10010	10	1	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	49	6955	10035	10035	8602	3	8740	10010	10020	20020	10035	41	1	1	10021	10	9	10	10010	10	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	49	6955	10035	10035	8602	3	8740	10010	10020	20020	10035	41	1	1	10021	10	9	10	10010	10	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	49	6955	10035	10035	8602	3	8740	10010	10020	20020	10035	41	1	1	10021	10	9	10	10010	10	1	0	640	2	41	2	2	9940	10000	10010	10036	10036	10036	10036	10036
10024	10035	75	0	631	9863	25	10010	10010	10010	88784	49	6955	10035	10035	8602	3	8740	10010	10020	20020	10035	41	1	1	10021	10	9	10	10010	10	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	49	6955	10035	10035	8602	3	8740	10010	10020	20020	10081	41	1	1	10021	10	9	10	10010	10	0	3	640	2	41	2	2	9940	10000	10010	10036	10036	10036	10036	10036
10024	10035	75	0	61	9863	25	10010	10010	10010	88784	49	6955	10035	10035	8602	3	8740	10010	10020	20020	10035	41	1	1	10021	10	9	10	10010	10	0	0	640	2	41	2	2	9940	10000	10010	10036	10036	10036	10036	10036

Test 4: throughput

Count: 8

Code:

  lsl x0, x8, x9
  lsl x1, x8, x9
  lsl x2, x8, x9
  lsl x3, x8, x9
  lsl x4, x8, x9
  lsl x5, x8, x9
  lsl x6, x8, x9
  lsl x7, x8, x9

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	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 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
80204	13420	100	27	35	25	80100	80100	80100	400500	49	10306	13386	13386	3323	3	3341	80100	80200	160200	13386	39	1	1	80201	100	99	100	80100	100	4	5110	2	19	1	1	13383	80000	80100	13387	13387	13387	13387	13387
80204	13386	100	6	35	25	80100	80100	80100	400500	49	10306	13386	13386	3323	3	3341	80100	80200	160200	13386	39	1	1	80201	100	99	100	80100	100	0	5110	1	19	1	1	13383	80000	80100	13387	13387	13387	13387	13387
80204	13386	100	0	35	25	80100	80100	80100	400500	49	10306	13386	13386	3323	3	3341	80100	80200	160200	13386	39	1	1	80201	100	99	100	80100	100	0	5110	1	19	1	1	13383	80000	80100	13387	13387	13387	13387	13387
80204	13386	100	6	35	25	80100	80100	80100	400500	49	10306	13386	13386	3323	3	3341	80100	80200	160200	13386	39	1	1	80201	100	99	100	80100	100	0	5110	1	19	1	1	13383	80000	80100	13387	13387	13387	13387	13387
80204	13386	101	6	35	25	80100	80100	80100	400500	49	10306	13386	13386	3323	3	3341	80100	80200	160200	13386	39	1	1	80201	100	99	100	80100	100	0	5110	1	19	1	1	13383	80000	80100	13387	13387	13387	13387	13387
80204	13386	100	0	35	25	80100	80100	80100	400500	49	10306	13386	13386	3323	3	3341	80100	80200	160200	13386	39	1	1	80201	100	99	100	80100	100	0	5110	1	19	1	1	13383	80000	80100	13387	13387	13387	13387	13387
80204	13386	100	12	35	25	80100	80100	80100	400500	49	10306	13386	13386	3323	3	3341	80100	80200	160200	13386	39	1	1	80201	100	99	100	80100	100	0	5110	1	19	1	1	13383	80000	80100	13387	13387	13387	13387	13387
80204	13386	101	6	35	25	80100	80100	80100	400500	49	10306	13386	13386	3323	3	3341	80100	80200	160200	13386	39	1	1	80201	100	99	100	80100	100	0	5110	1	19	1	1	13383	80000	80100	13387	13387	13387	13387	13387
80204	13386	100	6	35	25	80100	80100	80100	400500	49	10306	13386	13386	3323	3	3341	80100	80200	160200	13386	39	1	1	80201	100	99	100	80100	100	0	5110	1	19	1	1	13383	80000	80100	13387	13387	13387	13387	13387
80204	13386	100	6	35	25	80100	80100	80100	400500	49	10306	13386	13386	3323	3	3341	80100	80200	160200	13386	39	1	1	80201	100	99	100	80100	100	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	mmu table walk instruction (07)	l2 tlb miss instruction (0a)	1e	1f	3a	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)	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? int output thing (e9)	? int retires (ef)	f5	f6	f7	f8	fd
80024	13387	100	1	1	0	0	3	42	25	80010	80010	80010	400050	0	49	10291	13371	13371	3330	3	3348	80012	80020	160020	13371	39	1	1	80021	10	9	10	80010	10	0	5030	18	19	19	18	13368	80000	80010	13372	13372	13372	13372	13372
80024	13371	100	1	1	0	0	3	105	25	80010	80010	80010	400050	0	49	10291	13371	13371	3330	3	3348	80010	80020	160020	13371	39	1	1	80021	10	9	10	80010	10	0	5032	16	19	16	16	13368	80000	80010	13372	13372	13372	13372	13372
80024	13371	100	1	1	0	0	3	346	25	80010	80010	80010	400050	0	49	10291	13371	13371	3330	3	3348	80012	80020	160020	13371	39	1	1	80021	10	9	10	80010	10	0	5030	18	19	17	21	13368	80000	80010	13372	13372	13372	13372	13372
80024	13371	100	1	1	0	0	3	42	25	80010	80010	80010	400050	0	49	10291	13371	13371	3330	3	3348	80010	80020	160020	13371	39	1	1	80021	10	9	10	80010	10	0	5032	18	19	18	9	13368	80000	80010	13372	13372	13372	13372	13372
80024	13371	100	1	1	0	0	3	42	25	80010	80010	80010	400050	0	49	10291	13371	13371	3330	3	3348	80010	80020	160020	13371	39	1	1	80021	10	9	10	80010	10	0	5032	15	19	17	15	13368	80000	80010	13372	13372	13372	13372	13372
80024	13371	100	1	1	0	0	3	42	25	80010	80010	80010	400050	1	49	10291	13371	13371	3330	3	3348	80010	80020	160020	13371	39	1	1	80021	10	9	10	80010	10	0	5027	14	19	18	15	13368	80000	80010	13372	13372	13372	13372	13372
80024	13371	100	1	1	0	0	3	42	25	80010	80010	80010	400050	0	49	10291	13371	13371	3330	3	3348	80010	80020	160020	13371	39	1	1	80021	10	9	10	80010	10	0	5029	18	19	11	12	13368	80000	80010	13372	13372	13372	13372	13372
80024	13371	100	1	1	0	0	3	42	25	80010	80010	80010	400050	1	49	10291	13371	13371	3330	3	3348	80010	80020	160020	13371	39	1	1	80021	10	9	10	80010	10	0	5030	15	19	16	9	13368	80000	80010	13372	13372	13372	13372	13372
80024	13371	100	1	1	0	0	3	42	25	80010	80010	80010	400050	0	49	10291	13371	13371	3330	3	3348	80010	80020	160020	13371	39	1	1	80021	10	9	10	80010	10	0	5031	9	19	13	16	13368	80000	80010	13372	13372	13372	13372	13372
80024	13371	100	1	1	0	0	3	42	25	80010	80010	80010	400050	1	49	10291	13371	13371	3330	3	3348	80010	80020	160020	13371	39	1	1	80021	10	9	10	80010	10	0	5030	13	19	13	15	13368	80000	80010	13372	13372	13372	13372	13372

LSL (register, 64-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