Firestorm: ADDHN2 (vector, 2D) measurements

Code:

  addhn2 v0.4s, v1.2d, v2.2d

Initialization

  movi v0.16b, 1
  movi v1.16b, 2
  movi v2.16b, 3

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 1.000

Issues: 1.000

Integer unit issues: 0.000

Load/store unit issues: 0.000

SIMD/FP unit issues: 1.000

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

retire uop (01)	cycle (02)	03	18	1e	3f	4e	51	schedule uop (52)	schedule simd uop (54)	dispatch simd uop (57)	ldst uops in schedulers (5b)	60	69	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map simd uop (7e)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst simd alu (9a)	l1d cache writeback (a8)	ac	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	f5	f6	f7	f8	fd
1004	3037	23	0	0	61	2548	25	1000	1000	1000	398313	0	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	61	2548	25	1000	1000	1000	398313	0	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	0	0	61	2548	25	1000	1000	1000	398313	0	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	61	2548	25	1000	1000	1000	398313	0	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	0	0	61	2548	25	1000	1000	1000	398313	0	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	3	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	61	2548	25	1000	1000	1000	398313	0	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	61	2548	25	1000	1000	1000	398313	0	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	61	2548	25	1000	1000	1000	398313	0	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	61	2548	25	1000	1000	1000	398313	0	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	0	0	61	2548	25	1000	1000	1000	398313	0	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038

Test 2: Latency 1->1

Code:

  addhn2 v0.4s, v1.2d, v2.2d

Initialization

  movi v0.16b, 1
  movi v1.16b, 2
  movi v2.16b, 3

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

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

retire uop (01)	cycle (02)	03	mmu table walk data (08)	1e	1f	3a	3f	4e	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	60	69	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	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)	inst simd alu (9a)	9f	l1d cache writeback (a8)	a9	ac	c2	cf	d0	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10204	30037	225	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	710	0	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	710	0	2	16	2	2	29634	10000	100	30228	30038	30038	30038	30038
10204	30037	225	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	2	1	10201	100	99	100	100	10000	100	0	0	0	0	710	0	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	710	0	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	0	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	4	0	0	0	736	0	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	1	0	0	0	82	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10251	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	1	0	0	0	710	0	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	103	29548	25	10100	100	10000	100	10000	500	4277313	0	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	1	0	3	0	710	0	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	0	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	1	0	0	0	710	0	2	16	2	3	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	0	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	710	0	2	16	3	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	0	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	710	0	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

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

retire uop (01)	cycle (02)	03	1e	3f	4e	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	69	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	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)	inst simd alu (9a)	9f	l1d cache writeback (a8)	ac	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10024	30037	225	0	61	29548	25	10010	10	10000	10	10000	50	4277313	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	640	4	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	61	29548	25	10010	10	10000	10	10000	50	4277313	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	1	0	640	2	16	2	3	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	61	29548	25	10010	10	10000	10	10000	50	4277313	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	1	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	61	29548	25	10010	10	10000	10	10000	50	4277313	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	61	29548	25	10010	10	10000	10	10000	50	4277313	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	640	2	16	2	3	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	61	29548	25	10010	10	10000	10	10000	50	4277313	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	640	2	16	2	3	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	224	29548	25	10010	10	10000	10	10000	50	4277313	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	640	2	16	2	3	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	726	29548	25	10010	10	10000	10	10000	50	4277313	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	640	3	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	61	29548	25	10018	10	10000	10	10000	50	4277313	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	1011	29548	25	10010	10	10000	10	10000	50	4277313	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	640	2	16	3	2	29630	10000	10	30038	30038	30038	30038	30038

Test 3: Latency 1->2

Code:

  addhn2 v0.4s, v0.2d, v1.2d

Initialization

  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

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

retire uop (01)	cycle (02)	03	1e	1f	3f	4e	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	60	69	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	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)	inst simd alu (9a)	9f	ld unit uop (a6)	l1d cache writeback (a8)	ac	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? int output thing (e9)	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10204	30037	225	0	0	1503	29548	25	10100	100	10000	100	10000	500	4277313	0	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	982	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	2853	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	974	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	1132	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	1234	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	977	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	972	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	1002	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	1039	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

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

retire uop (01)	cycle (02)	03	18	1e	1f	3a	3f	4e	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	60	69	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	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)	inst simd alu (9a)	9f	l1d cache writeback (a8)	ac	branch mispred nonspec (cb)	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10024	30037	225	0	0	0	1	518	29548	25	10010	10	10000	10	10000	50	4277313	0	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	1	897	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	30037	30037	28287	3	28767	10010	22	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	660	2	16	3	3	29630	10000	10	30038	30086	30038	30038	30038
10024	30037	225	3	0	88	1	483	29548	25	10010	10	10000	10	10000	50	4277313	0	30018	30037	30037	28287	3	28767	10010	20	10000	20	30978	30084	30037	1	1	10021	10	9	10	10	10000	10	1	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	12	0	1	1033	29548	25	10010	10	10000	10	10000	50	4277313	0	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	1	900	29548	25	10010	10	10000	10	10000	50	4277313	1	30126	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	1	254	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	224	0	0	0	1	61	29548	25	10010	10	10000	10	10000	50	4277313	0	30018	30037	30084	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	1	103	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	224	0	0	0	1	84	29548	25	10010	10	10000	10	10000	50	4277313	0	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	1	166	29548	25	10010	10	10000	10	10000	50	4277313	0	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	87	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038

Test 4: Latency 1->3

Code:

  addhn2 v0.4s, v1.2d, v0.2d

Initialization

  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

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

retire uop (01)	cycle (02)	03	18	19	1e	3f	4e	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	69	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	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)	inst simd alu (9a)	9f	l1d tlb access (a0)	ld unit uop (a6)	ac	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10204	30037	224	0	0	0	332	29548	25	10100	100	10000	100	10000	500	4277313	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	149	29548	25	10100	100	10000	100	10000	500	4277313	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	191	29548	25	10100	100	10000	100	10000	500	4277313	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	224	0	0	0	948	29548	25	10100	100	10000	100	10000	500	4277313	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	2	0	710	1	16	0	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	2674	29548	25	10100	100	10000	100	10000	500	4278670	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	147	29548	25	10100	100	10000	100	10000	500	4277313	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	710	1	16	1	1	29691	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	149	29548	25	10100	100	10000	100	10000	500	4277313	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	170	29548	25	10100	100	10000	100	10000	500	4277313	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30083
10204	30037	225	0	0	0	321	29548	25	10100	100	10000	100	10000	500	4277313	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	103	29548	25	10100	100	10000	100	10000	500	4277313	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

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

retire uop (01)	cycle (02)	03	19	1e	3f	4e	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	69	6b	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	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)	inst simd alu (9a)	9f	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	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10024	30037	225	0	0	61	29548	44	10010	10	10000	10	10149	50	4278670	30018	0	30037	30225	28287	10	28786	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	2	2	53	2	5611	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30180	225	2	12	103	29548	102	10020	10	10000	10	10000	50	4277313	30018	0	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	3	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	30018	0	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	1	0	0	2	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	224	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	30018	0	30037	30084	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	30018	0	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	1	0	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	224	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	30018	0	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	1	0	0	0	668	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30226
10024	30037	225	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	30018	0	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	1	0	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	30018	0	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	1	0	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	224	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	30018	0	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	35	0	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	30018	0	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	55	0	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  addhn2 v0.4s, v8.2d, v9.2d
  movi v1.16b, 0
  addhn2 v1.4s, v8.2d, v9.2d
  movi v2.16b, 0
  addhn2 v2.4s, v8.2d, v9.2d
  movi v3.16b, 0
  addhn2 v3.4s, v8.2d, v9.2d
  movi v4.16b, 0
  addhn2 v4.4s, v8.2d, v9.2d
  movi v5.16b, 0
  addhn2 v5.4s, v8.2d, v9.2d
  movi v6.16b, 0
  addhn2 v6.4s, v8.2d, v9.2d
  movi v7.16b, 0
  addhn2 v7.4s, v8.2d, v9.2d

Initialization

  movi v8.16b, 9
  movi v9.16b, 10

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2508

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

retire uop (01)	cycle (02)	03	mmu table walk data (08)	09	l2 tlb miss instruction (0a)	3f	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	60	69	6b	6d	6e	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	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)	inst simd alu (9a)	9f	l1d tlb miss (a1)	l1d cache writeback (a8)	ac	branch cond mispred nonspec (c5)	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
160204	20091	150	0	0	0	2844	25	80100	100	80000	100	80000	500	640000	1	20045	0	20064	20064	3	22	80100	200	80000	200	240312	20228	20064	1	1	160201	100	99	100	100	160000	100	0	0	493	0	10112	2	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20155	150	0	0	0	39	25	80100	100	80000	100	80000	500	640000	0	20045	0	20064	20064	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	0	0	0	10116	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	0	39	25	80100	100	80000	100	80000	500	640000	0	20045	0	20064	20064	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	0	0	0	10112	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	0	186	25	80100	100	80000	100	80000	500	640000	1	20045	0	20064	20064	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	0	0	0	10111	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	0	39	25	80100	115	80000	100	80000	500	640000	1	20045	0	20064	20064	3	63	80531	200	80313	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	0	0	0	10111	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	0	39	25	80100	100	80000	100	80000	500	640000	0	20045	0	20064	20064	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	0	3	0	10112	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	0	39	25	80100	100	80000	100	80000	500	640000	0	20045	0	20064	20064	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	0	0	0	10112	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	0	39	25	80100	100	80000	100	80000	500	640000	0	20045	0	20064	20064	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	0	0	0	10112	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	0	62	25	80100	100	80000	100	80000	500	640000	1	20045	0	20064	20064	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	0	0	0	10111	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	151	0	0	0	39	25	80100	100	80000	100	80000	500	640000	0	20045	0	20064	20064	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	1	0	0	0	10112	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2506

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

retire uop (01)	cycle (02)	03	mmu table walk data (08)	1e	3f	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	5f	60	69	6d	6e	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	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)	inst simd alu (9a)	9f	l1d tlb miss (a1)	l1d cache writeback (a8)	a9	c2	cf	d0	d2	l1i cache miss demand (d3)	d5	map dispatch bubble (d6)	d9	da	db	dd	fetch restart (de)	e0	? int output thing (e9)	ea	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
160024	20071	150	0	0	51	25	80012	12	80000	12	80000	62	640000	1	1	20027	20046	20046	3	22	80012	20	80000	20	240000	20046	20046	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10029	3	1	1	8	20	2	1	1	3	4	20043	2	15	160000	10	20047	20047	20047	20047	20047
160024	20046	150	0	0	45	25	80012	12	80000	12	80000	62	640000	1	1	20027	20046	20046	3	22	80012	20	80000	20	240000	20046	20046	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10027	3	1	1	3	20	2	1	1	4	3	20043	2	15	160000	10	20047	20047	20047	20047	20047
160024	20046	150	0	0	45	25	80012	12	80000	12	80000	62	640000	1	1	20027	20046	20046	3	22	80012	20	80000	20	240000	20046	20046	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10027	3	1	1	7	20	2	1	1	3	4	20043	2	15	160000	10	20047	20047	20047	20047	20047
160024	20046	150	0	0	45	25	80012	12	80000	12	80000	62	640000	1	1	20031	20046	20046	3	22	80012	20	80000	20	240000	20046	20046	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10027	3	1	1	3	20	2	1	1	3	4	20043	2	15	160000	10	20047	20051	20047	20047	20047
160024	20046	150	0	0	152	25	80012	12	80000	12	80000	62	640000	1	1	20027	20046	20046	3	22	80012	20	80000	20	240000	20046	20046	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10027	6	1	1	9	20	2	1	1	4	3	20043	2	15	160000	10	20047	20047	20047	20047	20047
160024	20046	150	0	0	45	25	80012	12	80000	12	80000	62	640000	1	1	20027	20046	20046	3	22	80012	20	80000	20	240000	20046	20046	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10029	3	1	1	5	20	2	2	1	4	3	20043	2	15	160000	10	20047	20047	20047	20047	20047
160024	20046	150	0	0	45	25	80012	12	80096	12	80000	62	640000	1	1	20027	20046	20046	3	22	80012	20	80000	20	240000	20046	20046	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10026	3	1	1	8	20	2	1	1	6	6	20043	2	15	160000	10	20047	20047	20047	20047	20047
160024	20046	150	0	0	51	25	80012	12	80000	12	80000	62	640000	1	1	20027	20046	20046	3	22	80012	20	80000	20	240000	20046	20046	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10027	3	1	1	8	20	2	1	1	4	4	20043	2	15	160000	10	20047	20047	20047	20047	20047
160024	20046	150	0	0	192	25	80012	12	80000	12	80000	62	640000	1	1	20027	20046	20046	3	22	80012	20	80000	20	240000	20046	20046	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10030	3	1	1	7	20	2	1	1	3	4	20043	2	15	160000	10	20047	20047	20047	20047	20047
160024	20046	157	0	0	45	25	80012	12	80000	12	80000	62	640000	1	1	20027	20046	20046	3	22	80012	20	80000	20	240000	20046	20046	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10031	3	1	1	8	20	2	1	1	6	4	20043	2	15	160000	10	20047	20047	20047	20047	20047

Test 6: throughput

Count: 16

Code:

  addhn2 v0.4s, v16.2d, v17.2d
  addhn2 v1.4s, v16.2d, v17.2d
  addhn2 v2.4s, v16.2d, v17.2d
  addhn2 v3.4s, v16.2d, v17.2d
  addhn2 v4.4s, v16.2d, v17.2d
  addhn2 v5.4s, v16.2d, v17.2d
  addhn2 v6.4s, v16.2d, v17.2d
  addhn2 v7.4s, v16.2d, v17.2d
  addhn2 v8.4s, v16.2d, v17.2d
  addhn2 v9.4s, v16.2d, v17.2d
  addhn2 v10.4s, v16.2d, v17.2d
  addhn2 v11.4s, v16.2d, v17.2d
  addhn2 v12.4s, v16.2d, v17.2d
  addhn2 v13.4s, v16.2d, v17.2d
  addhn2 v14.4s, v16.2d, v17.2d
  addhn2 v15.4s, v16.2d, v17.2d

Initialization

  movi v16.16b, 17
  movi v17.16b, 18

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2502

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	37	3f	4e	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	5f	60	69	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	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)	inst simd alu (9a)	9f	l1d tlb access (a0)	l1d cache writeback (a8)	ac	c2	branch mispred nonspec (cb)	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
160204	40075	300	0	0	0	0	0	0	41	0	25	160101	100	160001	100	160000	500	2398999	0	1	40020	40048	40039	19973	3	19997	160100	200	160000	200	480000	40040	40049	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	10110	2	16	1	1	40036	160000	100	40049	40050	40040	40040	40040
160204	40048	299	0	0	0	3	0	0	42	0	25	160100	100	160017	100	160000	500	1280000	0	1	40021	40039	40071	19973	3	19998	160100	200	160142	200	480000	40048	40039	1	1	160201	100	99	100	100	160000	100	0	0	0	2	0	10144	1	16	1	1	40046	160000	100	40040	40491	40225	40194	40050
160204	40048	300	1	1	3	3	0	1	507	0	65	160596	110	160255	110	160000	500	1280000	0	1	40020	40048	40040	19973	3	20006	160100	200	160000	200	480000	40039	40040	1	1	160201	100	99	100	100	160000	100	0	1	0	0	0	10110	1	16	1	1	40036	160000	100	40040	40041	40041	40040	40040
160204	40039	300	0	0	0	0	0	0	41	0	25	160100	100	160001	100	160000	500	1280000	0	1	40021	40039	40048	19973	3	19997	160100	200	160000	200	480000	40039	40039	1	1	160201	100	99	100	100	160000	100	0	6	0	0	0	10110	1	16	1	1	40036	160000	100	40041	40050	40040	40049	40040
160204	40048	300	0	0	0	0	0	17	41	0	25	160101	100	160017	100	160000	500	1280000	0	1	40029	40040	40039	19973	3	20006	160100	200	160000	200	480000	40039	40040	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	10110	1	16	1	1	40036	160000	100	40041	40040	40041	40049	40049
160204	40039	300	0	0	0	0	0	0	42	0	25	160117	100	160017	100	160000	500	1319999	0	1	40020	40039	40071	19973	3	19998	160100	200	160000	200	480000	40039	40071	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	10110	1	16	1	1	40037	160000	100	40040	40040	40041	40050	40041
160204	40039	300	0	0	0	0	0	0	50	0	25	160117	100	160017	100	160000	500	1280000	0	1	40021	40040	40039	19973	3	19997	160100	200	160000	200	480000	40040	40040	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	10110	1	16	1	1	40045	160000	100	40040	40040	40040	40040	40050
160204	40039	299	0	0	0	0	0	1	42	0	25	160117	100	160000	100	160000	500	1280000	0	1	40030	40049	40048	19973	3	20006	160100	200	160000	200	480000	40048	40040	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	10110	1	16	1	1	40050	160000	100	40040	40040	40040	40041	40050
160204	40040	300	0	0	0	0	0	0	93	0	25	160101	100	160000	100	160000	500	2398999	0	1	40020	40039	40039	19973	3	20007	160100	200	160000	200	480000	40071	40039	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	10110	1	16	1	1	40036	160000	100	40040	40072	40040	40040	40049
160204	40039	300	0	0	0	0	0	17	50	0	25	160100	100	160000	100	160000	500	1319998	0	1	40021	40040	40040	19973	3	19998	160100	200	160000	200	480000	40048	40039	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	10110	1	16	1	1	40036	160000	100	40040	40050	40049	40049	40041

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2502

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	37	3a	3f	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	5f	60	61	69	6b	6d	6e	map stall dispatch (70)	simd prf full (72)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	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)	inst simd alu (9a)	9f	l1d tlb access (a0)	ld unit uop (a6)	ac	cd	cf	d0	d2	l1i cache miss demand (d3)	d5	map dispatch bubble (d6)	d9	da	db	dd	fetch restart (de)	e0	ea	eb	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
160024	40048	300	0	0	0	1	2	722	25	160027	10	160017	10	160000	50	1280000	1	1	5	40021	0	40039	40048	19989	0	3	20012	160010	20	160000	20	480000	40039	40040	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10026	8	2	1	21	16	2	1	1	18	11	40045	20	9	160000	10	40040	40049	40040	40041	40040
160024	40039	300	0	0	0	0	2	48	25	160027	10	160000	10	160000	50	1280000	1	1	5	40021	0	40039	40048	19989	0	3	20021	160010	20	160000	20	480000	40049	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10026	11	3	1	17	16	2	1	1	19	17	40036	40	9	160000	10	40041	40049	40040	40049	40040
160024	40039	300	0	0	0	0	2	56	25	160010	10	160000	10	160000	50	1319999	1	1	0	40020	0	40039	40048	19989	0	3	20021	160010	20	160000	20	480000	40039	40149	1	1	160021	10	9	10	10	160000	10	2	0	3	0	10026	8	2	1	19	16	2	1	1	19	18	40045	20	9	160000	10	40040	40049	40040	40049	40049
160024	40048	300	0	0	0	0	2	48	25	160010	10	160000	10	160000	50	2398999	1	1	0	40029	0	40039	40039	19989	7	3	20012	160010	20	160000	20	480000	40039	40048	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10026	8	2	1	19	16	2	1	1	16	20	40036	20	8	160000	10	40040	40040	40040	40049	40049
160024	40048	300	0	0	0	17	2	47	25	160010	10	160000	10	160000	50	1280000	1	1	5	40020	0	40040	40039	19989	0	3	20021	160010	20	160000	20	480000	40039	40040	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10026	8	2	1	18	16	4	2	1	17	13	40036	20	7	160000	10	40040	40049	40040	40041	40040
160024	40039	299	0	0	0	17	2	712	25	160010	10	160017	10	160000	50	2398999	1	1	5	40021	0	40048	40039	19989	0	3	20013	160010	20	160000	20	480000	40048	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10026	8	1	1	18	16	2	1	1	19	18	40045	20	9	160000	10	40041	40040	40050	40040	40040
160024	40048	300	0	0	0	17	2	56	25	160027	10	160017	10	160000	50	2398999	1	1	5	40029	0	40048	40039	19989	0	3	20012	160010	20	160000	20	480000	40039	40040	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10026	8	1	1	21	16	4	1	1	16	17	40045	20	9	160000	10	40040	40040	40040	40049	40049
160024	40039	300	0	0	0	17	2	47	25	160010	10	160017	10	160000	50	2398999	1	1	5	40020	0	40040	40048	19989	0	3	20012	160010	20	160000	20	480000	40039	40048	1	1	160021	10	9	10	10	160000	10	7	0	0	0	10026	8	2	1	18	16	2	1	1	18	19	40036	20	9	160000	10	40040	40049	40040	40040	40049
160024	40039	300	0	0	0	1	2	56	25	160010	10	160001	10	160000	50	2398999	1	1	5	40021	0	40048	40039	19989	0	3	20012	160010	20	160000	20	480000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10026	3	2	1	19	16	2	1	1	19	18	40045	20	9	160000	10	40049	40049	40049	40040	40050
160024	40039	300	0	0	0	0	2	56	25	160027	10	160017	10	160000	50	1280000	1	1	5	40020	0	40039	40040	19989	0	3	20022	160010	20	160000	20	480000	40049	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10026	8	2	1	19	16	2	1	1	18	20	40036	20	7	160000	10	40040	40049	40040	40049	40049

ADDHN2 (vector, 2D)

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: Latency 1->3

100 unrolls and 100 iterations

1000 unrolls and 10 iterations

Test 5: throughput

100 unrolls and 100 iterations

1000 unrolls and 10 iterations

Test 6: throughput

100 unrolls and 100 iterations

1000 unrolls and 10 iterations