Firestorm: SUBHN2 (vector, 4S) measurements

Code:

  subhn2 v0.8h, v1.4s, v2.4s

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	mmu table walk data (08)	l2 tlb miss data (0b)	18	19	1e	1f	3a	3f	4e	51	schedule uop (52)	schedule simd uop (54)	dispatch simd uop (57)	ldst uops in schedulers (5b)	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 tlb access (a0)	l1d tlb miss (a1)	ld unit uop (a6)	l1d cache writeback (a8)	a9	ac	c2	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	f5	f6	f7	f8	fd
1004	3037	23	0	0	0	0	0	0	0	61	2548	25	1000	1000	1000	398313	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	0	0	0	0	0	73	2	16	1	1	2702	1000	3038	3038	3038	3038	3038
1004	3037	22	0	0	0	0	0	0	0	61	2548	25	1000	1000	1000	398313	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	0	0	0	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	0	0	0	0	0	0	0	61	2548	25	1000	1000	1000	398313	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	0	0	0	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	0	0	0	0	0	61	2548	25	1000	1000	1000	398313	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	0	0	0	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	0	0	0	0	0	61	2548	25	1000	1000	1000	398313	3018	3037	3037	2415	3	2895	1000	1000	3000	3084	3037	1	1	1001	1000	0	0	0	0	0	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	0	0	0	0	0	0	0	61	2548	25	1000	1000	1000	398313	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	0	0	0	6	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	0	0	0	0	0	61	2548	25	1000	1000	1000	398313	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	0	0	0	3	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	0	0	0	0	0	0	0	61	2548	25	1000	1000	1000	398313	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	0	0	0	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	0	0	0	0	0	61	2548	25	1000	1000	1000	398313	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	0	0	0	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	0	0	36	0	0	61	2548	25	1000	1000	1000	398313	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	0	0	0	3	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038

Test 2: Latency 1->1

Code:

  subhn2 v0.8h, v1.4s, v2.4s

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	1e	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)	cf	d0	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	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	710	0	2	16	2	2	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	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	710	0	2	16	2	2	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	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	710	1	2	16	2	2	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	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	710	1	2	16	2	2	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	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	37	710	1	2	16	2	2	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	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	710	1	2	16	2	2	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	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	710	1	2	16	2	2	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	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	710	1	2	16	2	2	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	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	710	1	2	16	2	2	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	224	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	710	1	2	16	2	2	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	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	l1d tlb access (a0)	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	241	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	0	30018	30037	30037	28287	3	28788	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	640	9	16	4	3	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	61	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	0	0	0	640	3	16	3	3	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	61	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	0	0	0	640	3	16	3	4	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	61	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	0	0	0	640	3	16	3	4	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	224	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30054	30037	30037	28287	3	28767	10010	20	10000	20	30000	30083	30037	2	1	10021	10	9	10	10	10000	10	0	0	0	0	2870	0	640	3	16	3	4	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	0	30018	30037	30037	28287	3	28767	10010	20	10000	20	30516	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	640	3	16	3	4	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	61	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	0	0	0	640	4	16	4	3	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	61	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	0	0	0	640	3	16	5	3	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	61	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	0	0	0	640	3	16	5	3	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	224	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	0	30090	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	0	0	728	3	16	3	3	29630	10000	10	30038	30038	30038	30038	30038

Test 3: Latency 1->2

Code:

  subhn2 v0.8h, v0.4s, v1.4s

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	l1i tlb fill (04)	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)	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 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
10204	30037	225	1	0	134	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	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	726	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	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	504	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	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	155	29548	49	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	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	812	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	10000	100	30038	30038	30038	30038	30038
10204	30037	224	0	0	726	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	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	124	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	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	124	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	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	246	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	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	166	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	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	mmu table walk instruction (07)	l2 tlb miss instruction (0a)	18	19	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 cond mispred nonspec (c5)	cd	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
10024	30037	225	1	1	0	0	219	0	2	68	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	0	644	15	16	10	10	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	1	1	0	0	3	0	2	68	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	3	0	0	644	10	16	5	10	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	1	1	0	0	0	0	2	68	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	0	644	10	16	10	8	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	1	1	0	0	3	0	2	68	29548	25	10010	10	10000	10	10000	50	4277313	0	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30082	1	1	10021	10	9	10	10	10000	10	0	0	0	0	644	10	16	10	10	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	241	1	1	0	0	21	0	2	68	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	0	644	11	16	10	10	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	1	1	0	0	18	0	2	68	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	0	644	10	16	10	10	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	1	1	0	0	144	0	2	68	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	1	644	8	16	10	10	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	1	1	0	0	42	0	2	68	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	0	644	10	16	10	10	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	1	1	0	0	0	0	2	4835	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	0	644	10	16	10	10	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	1	1	0	0	30	0	2	68	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	0	644	5	16	10	10	29630	0	10000	10	30038	30038	30038	30038	30038

Test 4: Latency 1->3

Code:

  subhn2 v0.8h, v1.4s, v0.4s

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	mmu table walk data (08)	09	l2 tlb miss instruction (0a)	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)	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)	a9	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	273	0	0	0	0	0	0	440	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	26	0	0	710	3	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	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	59	0	0	710	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	232	0	0	0	0	0	0	363	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	48	710	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	245	0	0	1	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	1	0	0	710	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	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	6	0	15	710	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	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	1	0	3	710	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	0	61	29548	25	10100	104	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	1	0	3	710	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	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	3	0	3	710	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	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	2	0	3	710	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	224	0	0	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	1	0	3	710	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	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)	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 cond mispred nonspec (c5)	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
10024	30037	225	0	27	99	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	642	4	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	33	61	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	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	12	61	29548	25	10010	10	10000	10	10000	50	4277313	0	30018	30037	30037	28287	3	28767	10012	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	1	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	12	61	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	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	61	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	2	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	57	61	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	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	303	61	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	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	18	61	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	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	3	61	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	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	61	29548	25	10010	10	10000	10	10000	60	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	0	10000	10	30038	30038	30038	30038	30038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  subhn2 v0.8h, v8.4s, v9.4s
  movi v1.16b, 0
  subhn2 v1.8h, v8.4s, v9.4s
  movi v2.16b, 0
  subhn2 v2.8h, v8.4s, v9.4s
  movi v3.16b, 0
  subhn2 v3.8h, v8.4s, v9.4s
  movi v4.16b, 0
  subhn2 v4.8h, v8.4s, v9.4s
  movi v5.16b, 0
  subhn2 v5.8h, v8.4s, v9.4s
  movi v6.16b, 0
  subhn2 v6.8h, v8.4s, v9.4s
  movi v7.16b, 0
  subhn2 v7.8h, v8.4s, v9.4s

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)	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	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 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
160204	20089	150	0	0	39	25	80100	100	80000	100	80000	500	640000	0	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	10111	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	39	25	80100	100	80000	100	80000	500	640000	0	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	10111	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	39	25	80100	100	80000	100	80000	500	640000	0	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	10111	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	151	0	0	39	25	80100	100	80000	100	80000	500	640000	0	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	10111	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	15	39	25	80100	100	80000	100	80000	500	640000	0	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	10111	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	39	25	80100	100	80000	100	80000	500	640000	0	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	10111	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	39	25	80100	100	80000	100	80000	500	640000	0	0	20045	0	20064	20064	3	22	80100	200	80000	200	240000	20064	20064	2	1	160201	100	99	100	100	160000	100	0	0	10111	1	58	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	39	25	80100	100	80000	100	80000	500	640000	0	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	10111	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	39	25	80100	100	80000	100	80000	500	640000	0	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	10111	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	39	25	80100	100	80000	100	80000	500	640000	0	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	10111	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)	l2 tlb miss data (0b)	19	1e	1f	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	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 access (a0)	l1d tlb miss (a1)	l1d cache writeback (a8)	ac	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	ec	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
160024	20074	150	0	0	0	0	0	51	27	80012	12	80000	12	80000	62	640000	1	1	5	20032	20051	20051	3	22	80012	20	80000	20	240000	20051	20051	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10028	8	1	1	7	25	2	1	1	5	5	20048	2	20	1	160000	10	20052	20052	20052	20052	20052
160024	20051	150	0	0	0	0	0	45	27	80012	12	80000	12	80000	62	640000	1	1	5	20032	20051	20051	3	22	80012	20	80000	20	240000	20051	20051	1	1	160021	10	9	10	10	160000	10	0	0	0	9	10030	8	1	1	5	25	2	1	1	6	6	20048	2	20	1	160000	10	20052	20052	20052	20052	20052
160024	20132	151	0	0	3	9	176	45	27	80012	14	80521	13	80000	62	640000	1	1	5	20032	20051	20051	3	22	80012	20	80000	20	240000	20051	20051	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10029	8	1	1	6	25	2	1	1	5	7	20048	2	20	1	160000	10	20052	20056	20052	20052	20052
160024	20051	150	0	0	0	0	0	45	27	80012	12	80000	12	80000	62	640000	1	1	5	20032	20051	20051	3	22	80012	20	80000	20	240000	20051	20051	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10028	8	1	1	5	116	2	1	1	5	5	20253	3	20	1	160000	10	20132	20134	20134	20482	20052
160024	20131	150	0	0	0	0	0	45	27	80012	12	80000	12	80000	62	640000	1	1	5	20032	20051	20051	3	22	80012	20	80000	20	240000	20051	20051	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10028	8	1	1	5	25	2	1	1	5	5	20048	2	20	1	160000	10	20052	20052	20052	20052	20052
160024	20051	150	0	0	0	0	0	710	27	80012	12	80000	12	80105	62	640000	1	1	5	20032	20051	20051	3	22	80012	20	80000	20	240000	20051	20051	1	1	160021	10	9	10	10	160000	10	0	0	3	93	10028	8	1	1	7	25	2	1	1	7	5	20048	2	20	1	160000	10	20052	20052	20052	20052	20052
160024	20051	152	0	0	0	0	0	45	27	80012	13	80000	12	80000	62	640000	1	1	5	20032	20051	20051	3	22	80012	20	80000	20	240000	20051	20051	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10029	8	1	1	4	25	2	1	1	5	5	20048	2	20	1	160000	10	20052	20052	20052	20052	20052
160024	20051	150	0	0	0	45	0	45	27	80012	12	80000	12	80000	62	640000	1	1	5	20032	20051	20051	3	22	80012	20	80000	20	240000	20051	20051	1	1	160021	10	9	10	10	160000	10	0	0	2	0	10029	8	1	1	5	25	2	1	1	5	7	20048	2	20	1	160000	10	20052	20052	20052	20052	20052
160024	20051	150	0	0	0	0	0	45	27	80012	12	80000	12	80000	62	640000	1	1	5	20032	20051	20051	3	22	80012	20	80000	20	240000	20051	20051	1	1	160021	10	9	10	10	160000	10	0	0	1	0	10028	8	1	1	7	25	2	1	1	5	6	20048	2	20	1	160000	10	20052	20052	20052	20052	20052
160024	20051	150	0	0	0	0	0	45	27	80012	12	80000	12	80000	62	640000	1	1	5	20032	20051	20051	25	22	80012	20	80000	20	240000	20051	20051	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10029	8	1	1	6	25	2	1	1	7	7	20048	2	20	1	160000	10	20052	20052	20052	20052	20052

Test 6: throughput

Count: 16

Code:

  subhn2 v0.8h, v16.4s, v17.4s
  subhn2 v1.8h, v16.4s, v17.4s
  subhn2 v2.8h, v16.4s, v17.4s
  subhn2 v3.8h, v16.4s, v17.4s
  subhn2 v4.8h, v16.4s, v17.4s
  subhn2 v5.8h, v16.4s, v17.4s
  subhn2 v6.8h, v16.4s, v17.4s
  subhn2 v7.8h, v16.4s, v17.4s
  subhn2 v8.8h, v16.4s, v17.4s
  subhn2 v9.8h, v16.4s, v17.4s
  subhn2 v10.8h, v16.4s, v17.4s
  subhn2 v11.8h, v16.4s, v17.4s
  subhn2 v12.8h, v16.4s, v17.4s
  subhn2 v13.8h, v16.4s, v17.4s
  subhn2 v14.8h, v16.4s, v17.4s
  subhn2 v15.8h, v16.4s, v17.4s

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	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)	60	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	ld unit uop (a6)	l1d cache writeback (a8)	ac	c2	branch mispred nonspec (cb)	cd	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	ec	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
160204	40061	300	0	0	0	17	41	0	25	160100	100	160000	100	160000	500	2398999	1	40020	0	40048	40039	19973	3	20007	160100	200	160000	200	480000	40048	40039	1	1	160201	100	99	100	100	160000	100	0	1	66	0	0	0	10110	1	16	1	1	40036	0	160000	100	40040	40049	40086	40040	40049
160204	40039	300	0	0	0	17	41	0	25	160117	100	160000	100	160000	500	2398999	0	40020	0	40039	40039	19973	3	19997	160100	200	160000	200	480000	40039	40039	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	0	10110	1	16	1	1	40045	0	160000	100	40049	40040	40040	40040	40040
160204	40039	300	0	0	0	17	41	0	25	160100	100	160000	100	160000	500	1280000	0	40029	0	40039	40048	19973	3	20006	160100	200	160000	200	480000	40048	40039	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	0	10110	1	16	1	1	40045	0	160000	100	40040	40040	40040	40040	40040
160204	40048	300	0	0	0	0	41	0	25	160117	100	160000	100	160000	500	1756047	0	40029	0	40048	40048	19973	3	20006	160100	200	160000	200	480000	40039	40039	1	1	160201	100	99	100	100	160000	100	2	1	228	0	0	0	10110	1	16	1	1	40036	0	160000	100	40040	40040	40040	40040	40040
160204	40052	300	0	0	0	0	146	0	25	160100	100	160000	100	160000	500	1280000	0	40020	0	40039	40039	19973	3	19997	160100	200	160000	200	480000	40048	40048	1	1	160201	100	99	100	100	160000	100	0	0	132	0	0	0	10110	1	16	1	1	40036	0	160000	100	40049	40040	40040	40040	40049
160204	40039	300	0	0	0	0	231	0	25	160117	100	160000	100	160000	500	1280000	0	40029	0	40048	40048	19973	3	20006	160100	200	160000	200	480000	40039	40048	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	0	10110	1	16	1	1	40036	0	160000	100	40040	40049	40040	40040	40040
160204	40039	300	0	0	0	0	50	0	25	160118	100	160000	100	160000	500	1280000	1	40020	0	40049	40039	19973	3	19997	160100	200	160000	200	480000	40039	40048	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	0	10110	1	16	1	1	40036	0	160000	100	40040	40040	40040	40040	40040
160204	40052	300	0	0	0	0	41	0	25	160100	100	160000	100	160000	500	1280000	1	40020	0	40048	40048	19973	3	20007	160100	200	160000	200	480000	40039	40075	1	1	160201	100	99	100	100	160000	100	0	0	213	0	0	0	10110	1	16	1	1	40036	0	160000	100	40049	40040	40049	40049	40040
160204	40039	300	0	0	0	0	41	0	25	160100	100	160000	100	160000	500	1280000	1	40029	0	40039	40048	19973	3	19997	160100	200	160000	200	480000	40039	40039	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	0	10110	1	16	1	1	40036	0	160000	100	40050	40049	40040	40040	40049
160204	40039	300	0	0	0	0	41	0	25	160117	100	160000	100	160000	500	1280000	0	40029	0	40039	40048	19973	3	19997	160100	200	160000	200	480000	40039	40039	1	1	160201	100	99	100	100	160000	100	0	0	9	0	0	0	10110	1	16	1	1	40036	0	160000	100	40040	40050	40049	40040	40049

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2503

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

retire uop (01)	cycle (02)	03	mmu table walk data (08)	09	l2 tlb miss data (0b)	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	61	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 miss (a1)	l1d cache writeback (a8)	a9	ac	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	eb	ec	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
160024	40048	310	0	0	0	0	60	17	67	0	251	161524	15	160528	14	161835	60	2193680	1	1	5	40029	40048	40039	19996	3	20019	160010	20	160000	20	480000	40048	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10022	8	4	1	19	16	2	1	1	20	22	40068	0	15	5	0	160000	10	40040	40049	40072	40049	40040
160024	40048	300	0	0	0	0	0	0	46	0	25	160010	10	160017	10	160000	50	5387188	1	1	5	40021	40039	40048	19996	3	20019	160010	20	160000	20	480000	40049	40048	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10022	8	4	1	19	16	2	1	1	20	22	40036	0	15	5	0	160000	10	40040	40040	40049	40049	40049
160024	40048	300	0	0	0	0	0	17	56	0	25	160027	10	160000	10	160000	50	1280000	1	1	5	40029	40039	40319	19996	3	20051	160010	20	160000	20	480000	40071	40039	3	1	160021	10	9	10	10	160000	10	0	0	0	0	10022	8	4	1	19	16	2	1	1	19	21	40045	0	15	5	0	160000	10	40040	40049	40040	40049	40040
160024	40039	300	0	0	0	0	12	0	46	0	48	160010	10	160017	12	160000	50	1280000	1	1	5	40067	40039	40172	19996	3	20106	160010	20	160000	20	480000	40048	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10022	8	4	1	19	16	2	1	1	10	23	40036	0	15	5	0	160000	10	40040	40049	40040	40049	40040
160024	40071	300	0	0	0	0	0	61	46	0	25	160010	10	160000	10	160000	50	1280000	1	1	5	40020	40039	40048	19996	3	20019	160010	20	160000	20	480000	40039	40048	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10022	8	4	1	8	16	2	1	1	19	9	40136	0	15	5	0	160000	10	40049	40040	40049	40157	40049
160024	40049	300	0	0	0	0	0	17	67	0	25	160010	10	160017	10	160000	50	5387188	1	1	5	40020	40048	40039	19996	3	20075	160118	20	160000	20	480000	40071	40048	1	1	160021	10	9	10	10	160000	10	2	1	4	4498	10022	8	4	1	8	284	2	1	1	19	9	40045	0	15	5	0	160000	10	40040	40040	40040	40050	40040
160024	40039	300	0	0	0	0	0	17	46	0	25	160010	10	160000	10	160000	50	2398999	1	1	5	40020	40039	40039	19996	3	20019	160010	20	160000	20	480000	40048	40048	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10022	8	4	1	19	16	2	1	1	8	21	40160	0	15	5	0	160000	10	40227	40267	40132	40041	40040
160024	40039	300	1	1	1	1	21	36	94	0	83	160338	12	160169	10	160000	50	1280000	1	1	5	40029	40184	40092	20005	11	20106	160010	20	160107	20	480297	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10022	8	4	1	9	16	1	1	1	19	21	40068	0	15	5	0	160000	10	40049	40040	40049	40040	40049
160024	40048	300	0	0	0	0	0	17	97	25	25	160011	10	160001	10	160000	50	2398999	1	1	5	40029	40039	40048	19996	3	20066	160010	20	160210	20	484086	40966	40397	1	1	160021	10	9	10	10	160000	10	2	0	2	0	10022	8	4	1	19	29	2	1	1	16	21	40142	0	15	5	0	160000	10	40072	40049	40040	40049	40040
160024	40039	300	0	0	0	0	0	17	55	0	25	160027	10	160017	10	160000	50	1280000	1	1	5	40052	40039	40039	19996	3	20028	160010	20	160000	20	480000	40048	40039	1	1	160021	10	9	10	10	160000	10	0	1	0	0	10022	8	4	1	8	16	2	1	1	19	9	40036	0	15	5	0	160000	10	40049	40072	40040	40040	40049

SUBHN2 (vector, 4S)

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