Firestorm: UMLSL (by element, 2D) measurements

Code:

  umlsl v0.2d, v1.2s, v2.s[1]

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	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)	ac	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	f5	f6	f7	f8	fd
1004	3037	23	0	61	2548	25	1000	1000	1000	398313	0	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	63	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	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	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	0	61	2548	25	1000	1000	1000	398313	1	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	61	2548	25	1000	1000	1000	398313	1	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	61	2548	25	1000	1000	1000	398313	1	3018	3037	3037	2415	3	2900	1000	1000	3000	3037	3037	1	1	1001	1000	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	61	2548	25	1000	1000	1000	398313	1	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	61	2548	25	1000	1000	1000	398313	1	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	0	61	2548	25	1000	1000	1000	398313	0	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	12	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	61	2548	25	1000	1000	1000	398313	1	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	61	2548	25	1000	1000	1000	398313	1	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038

Test 2: Latency 1->1

Code:

  umlsl v0.2d, v1.2s, v2.s[1]

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	50	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	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	0	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	17	15	710	1	2	16	2	2	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	61	29548	0	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	180	710	1	2	16	2	3	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	61	29548	0	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	120	710	1	2	16	2	3	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	1	61	29548	0	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	147	710	1	2	16	2	2	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	61	29548	0	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	3	710	1	2	16	2	2	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	61	29548	0	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	105	710	1	2	16	2	2	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	61	29548	0	25	10100	100	10000	100	10464	500	4277313	0	30018	30084	30132	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	111	710	1	2	16	2	3	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	61	29548	0	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	3	710	1	2	16	2	2	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	61	29548	0	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	99	710	1	2	16	2	2	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	224	0	0	61	29548	0	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	168	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 miss (a1)	l1d cache writeback (a8)	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	224	0	0	61	29548	25	10010	10	10000	10	10000	50	4281384	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	21	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	0	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	1	18	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	233	0	0	355	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	39	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	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	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	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	117	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	4278670	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	27	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	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	33	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	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	21	0	640	2	16	2	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	111	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	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	126	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038

Test 3: Latency 1->2

Code:

  umlsl v0.2d, v0.2s, v1.s[1]

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	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 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	225	0	0	30	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	36	0	0	710	1	16	1	1	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	52	0	0	710	1	16	1	1	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	52	0	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	61	29548	25	10100	100	10024	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	59	0	0	710	1	16	1	1	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	3	710	1	16	1	1	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	6	710	1	16	1	1	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	41	0	0	710	1	16	1	1	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	38	0	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	61	29548	25	10100	100	10032	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	3	0	0	710	1	16	1	1	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	39	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)	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)	a9	ac	c2	branch mispred nonspec (cb)	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	232	0	12	145	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	2	0	0	0	1	640	3	16	3	3	29630	0	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	3	0	0	0	0	640	3	16	3	3	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	61	29548	25	10010	13	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	4	0	3	0	0	640	3	16	3	3	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	3717	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	38	0	0	0	0	640	3	16	3	3	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	224	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	3	0	3	0	0	640	3	16	3	3	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	49	0	0	0	0	640	3	16	3	3	29630	0	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	39	0	0	0	0	640	3	16	3	3	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	61	29548	25	10010	12	10000	11	10000	50	4277313	1	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	2	1	10021	10	9	10	10	10000	10	0	31	0	0	0	0	640	3	16	3	3	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	2798	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	30037	30037	28287	3	28786	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	0	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	32	0	0	0	0	640	3	16	3	3	29630	0	10000	10	30038	30038	30038	30038	30038

Test 4: Latency 1->3

Code:

  umlsl v0.2d, v1.2s, v0.s[1]

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)	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	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 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	225	0	0	6079	29548	44	10134	100	10000	119	10000	500	4277313	1	30018	0	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	2	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	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	0	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	61	29548	25	10100	100	10000	100	10000	500	4277797	1	30018	0	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	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	0	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	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	0	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	3589	29548	86	10100	100	10000	100	10000	500	4277313	1	30018	0	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	2	0	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	0	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	1	0	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	0	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	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	0	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	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	0	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	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	ld unit uop (a6)	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	1	1	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	644	12	16	10	10	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	1	1	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	1	0	644	10	16	10	10	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	1	1	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	1	0	644	5	16	10	8	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	1	1	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	1	0	644	10	16	10	10	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	1	1	0	0	2	68	29548	25	10010	10	10000	13	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	1	0	644	10	16	9	5	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	1	1	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	2	0	644	7	16	10	10	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	1	1	0	0	2	68	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	1	0	644	10	16	10	10	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	1	1	0	0	2	68	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	1	0	644	10	16	10	10	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	1	1	0	0	2	89	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	1	0	644	10	16	10	10	29630	10000	10	30038	30038	30038	30086	30038
10024	30037	225	1	1	0	0	2	68	29548	25	10010	12	10000	10	10000	50	4277313	1	30018	30037	30037	28296	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	3	666	10	16	10	10	29630	10000	10	30038	30038	30038	30038	30038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  umlsl v0.2d, v8.2s, v9.s[1]
  movi v1.16b, 0
  umlsl v1.2d, v8.2s, v9.s[1]
  movi v2.16b, 0
  umlsl v2.2d, v8.2s, v9.s[1]
  movi v3.16b, 0
  umlsl v3.2d, v8.2s, v9.s[1]
  movi v4.16b, 0
  umlsl v4.2d, v8.2s, v9.s[1]
  movi v5.16b, 0
  umlsl v5.2d, v8.2s, v9.s[1]
  movi v6.16b, 0
  umlsl v6.2d, v8.2s, v9.s[1]
  movi v7.16b, 0
  umlsl v7.2d, v8.2s, v9.s[1]

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	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	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 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
160204	20065	151	39	25	80100	100	80000	100	80000	500	640000	0	20045	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	0	160000	100	20065	20065	20065	20065	20065
160204	20064	150	39	25	80100	100	80000	100	80000	500	640000	0	20045	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	0	160000	100	20065	20065	20065	20065	20065
160204	20064	151	39	66	80100	100	80000	100	80000	500	640000	0	20045	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	0	160000	100	20065	20065	20065	20065	20065
160204	20064	150	39	25	80100	100	80000	100	80000	500	640000	0	20045	20064	20064	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	1	0	0	10111	1	16	1	1	20061	0	160000	100	20065	20065	20065	20065	20065
160204	20064	150	39	25	80100	100	80000	100	80000	500	640000	0	20045	20064	20064	3	49	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	0	160000	100	20065	20065	20065	20065	20065
160204	20064	150	39	25	80100	100	80000	100	80000	500	640000	0	20045	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	0	160000	100	20065	20065	20065	20065	20065
160204	20064	150	39	25	80100	100	80000	100	80000	500	640000	0	20045	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	0	160000	100	20065	20065	20065	20065	20065
160204	20064	150	39	25	80100	100	80000	100	80000	500	640000	0	20045	20064	20064	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	1	0	0	10111	1	16	1	1	20061	0	160000	100	20065	20065	20065	20065	20065
160204	20064	156	39	25	80100	100	80000	100	80000	500	640000	0	20045	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	0	160000	100	20065	20065	20065	20065	20065
160204	20064	150	39	25	80100	100	80000	100	80000	500	640000	0	20045	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	0	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	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 cache writeback (a8)	a9	ac	cd	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	20086	151	0	51	27	80012	12	80000	12	80000	62	640000	1	1	20032	20051	20060	3	22	80012	20	80000	20	240000	20051	20051	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10030	3	1	1	6	25	2	1	1	7	16	20057	2	40	1	160000	10	20052	20257	20052	20052	20052
160024	20060	151	0	45	27	80012	12	80000	12	80000	62	640000	0	1	20032	20051	20051	3	22	80012	20	80000	20	240000	20051	20051	1	1	160021	10	9	10	10	160000	10	2	0	3	0	10030	3	1	1	6	25	2	1	1	16	16	20048	2	20	1	160000	10	20052	20232	20061	20052	20052
160024	20051	150	0	51	27	80012	12	80000	12	80000	62	640000	1	1	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	10030	3	1	1	16	34	4	2	2	16	5	20048	2	20	1	160000	10	20052	20225	20052	20052	20052
160024	20051	150	0	45	27	80012	12	80000	12	80000	62	640000	1	1	20032	20051	20051	3	22	80012	20	80000	20	240000	20060	20051	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10037	3	1	1	17	25	2	1	1	12	6	20048	2	40	1	160000	10	20052	20233	20052	20052	20052
160024	20051	151	0	45	27	80012	12	80000	12	80000	62	640000	0	1	20041	20051	20060	3	22	80012	20	80000	20	240000	20051	20051	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10033	3	1	1	6	25	2	1	1	16	6	20048	2	20	1	160000	10	20052	20223	20052	20052	20052
160024	20051	150	0	45	27	80012	12	80000	12	80000	62	640000	1	1	20032	20051	20060	3	22	80012	20	80140	20	240000	20051	20051	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10040	3	1	1	6	25	2	1	1	6	16	20048	2	20	1	160000	10	20052	20259	20052	20061	20052
160024	20060	150	0	51	186	80012	12	80000	12	80000	62	640000	1	1	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	10040	3	1	1	16	25	2	1	1	16	6	20048	2	20	1	160000	10	20052	20200	20052	20052	20052
160024	20051	150	0	45	27	80012	12	80000	12	80000	62	640000	1	1	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	10040	3	1	1	6	25	2	1	1	16	6	20048	2	20	1	160000	10	20052	20202	20052	20052	20052
160024	20051	150	0	45	27	80012	12	80000	12	80000	62	640000	1	1	20032	20051	20051	3	22	80012	20	80000	20	240000	20051	20051	1	1	160021	10	9	10	10	160000	10	48	0	0	0	10040	3	1	1	16	25	2	1	1	17	7	20048	2	20	1	160000	10	20052	20176	20052	20052	20052
160024	20051	151	0	45	27	80012	12	80000	12	80000	62	640000	1	1	20041	20060	20060	3	22	80012	20	80000	20	240000	20051	20051	1	1	160021	10	9	10	10	160000	10	0	0	0	0	10040	3	1	1	16	25	2	1	1	16	16	20048	2	20	1	160000	10	20052	20204	20052	20052	20052

Test 6: throughput

Count: 12

Code:

  umlsl v0.2d, v12.2s, v13.s[1]
  umlsl v1.2d, v12.2s, v13.s[1]
  umlsl v2.2d, v12.2s, v13.s[1]
  umlsl v3.2d, v12.2s, v13.s[1]
  umlsl v4.2d, v12.2s, v13.s[1]
  umlsl v5.2d, v12.2s, v13.s[1]
  umlsl v6.2d, v12.2s, v13.s[1]
  umlsl v7.2d, v12.2s, v13.s[1]
  umlsl v8.2d, v12.2s, v13.s[1]
  umlsl v9.2d, v12.2s, v13.s[1]
  umlsl v10.2d, v12.2s, v13.s[1]
  umlsl v11.2d, v12.2s, v13.s[1]

Initialization

  movi v12.16b, 13
  movi v13.16b, 14

(fused SUBS/B.cc loop)

100 unrolls and 100 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	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	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
120204	30058	224	0	70	41	6713	25	120118	100	120018	100	120000	500	960000	0	30020	30039	30039	16653	3	14997	120100	200	120000	200	360000	31748	30039	1	1	120201	100	99	100	100	120000	100	0	0	0	7610	3	16	2	3	31745	120000	100	30040	31749	30040	30041	30040
120204	30041	225	0	1	44	6713	25	120118	100	120001	100	120000	500	960000	0	31729	30040	30039	14973	3	14997	120100	200	120000	200	360000	30039	31748	1	1	120202	100	99	100	100	120000	100	0	0	1	7610	3	16	2	3	30036	120000	100	30040	30040	31749	30040	31749
120204	31748	225	0	0	41	0	25	120100	100	120000	100	120000	500	960000	0	31729	31748	30039	14973	3	14997	120100	200	120000	200	360000	30039	30040	1	1	120201	100	99	100	100	120000	100	0	0	0	7610	3	16	3	3	30036	120000	100	30040	31749	30040	30040	31749
120204	31748	225	0	18	61	6713	25	120118	100	120001	100	120000	500	960000	0	30020	30039	30040	16653	3	16706	120100	200	120000	200	360000	30040	30039	1	1	120201	100	99	100	100	120000	100	0	0	0	7610	2	16	2	3	30036	120000	100	30040	31749	30040	31749	30040
120204	30039	225	0	0	41	6713	25	120101	100	120001	100	120000	500	4283622	0	30020	30039	30040	14973	3	14998	120100	200	120000	200	360000	30039	30039	1	1	120201	100	99	100	100	120000	100	0	0	0	7610	4	16	3	3	30036	120000	100	30040	30043	30040	31749	30041
120204	31748	224	0	1	42	6713	25	120118	100	120000	100	120000	500	960000	0	30020	30039	30039	14973	3	16706	120100	200	120000	200	360000	30039	31748	1	1	120201	100	99	100	100	120000	100	0	0	0	7610	3	16	3	2	31745	120000	100	30040	30041	30040	30041	31749
120204	30040	225	0	18	41	0	25	120100	100	120000	100	120000	500	960000	0	30020	30039	30039	14973	3	16706	120100	200	120000	200	360000	31748	30039	1	1	120201	100	99	100	100	120000	100	0	0	0	7610	3	16	3	2	30037	120000	100	30041	30040	31749	30040	30041
120204	30040	225	0	70	44	0	25	120100	100	120000	100	120000	500	990000	0	30021	31748	30039	14973	3	14997	120100	200	120000	200	360000	30039	30040	1	1	120201	100	99	100	100	120000	100	0	0	0	7610	2	16	2	3	30039	120000	100	30040	31749	30040	30041	30040
120204	30039	238	0	0	251	6713	25	120118	100	120018	100	120000	500	960000	0	30020	31748	30040	16653	3	16706	120100	200	120000	200	360000	31748	30039	1	1	120201	100	99	100	100	120000	100	0	0	0	7610	3	16	3	2	30036	120000	100	30040	30040	31749	30040	31749
120204	30039	238	0	18	41	0	25	120100	100	120001	100	120000	500	960000	0	30020	30039	30040	16653	3	16706	120100	200	120000	200	360000	31748	30039	1	1	120201	100	99	100	100	120000	100	0	0	0	7610	3	16	3	2	30036	120000	100	31749	30040	30041	30040	30041

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	l1i tlb fill (04)	mmu table walk instruction (07)	mmu table walk data (08)	l2 tlb miss data (0b)	18	19	1e	1f	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)	ac	c2	cf	d0	d2	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
120024	30042	238	0	0	0	0	0	0	9	0	0	41	0	25	120027	10	120000	10	120000	50	4283400	0	1	0	30021	30997	30040	14996	3	15019	120010	20	120000	20	360000	30039	30039	1	1	120021	10	9	10	10	120000	10	0	0	0	0	7520	0	0	23	16	19	18	30036	0	120000	10	30040	30040	30040	30040	30040
120024	30039	225	0	0	0	0	0	0	0	0	0	40	0	25	120010	10	120000	10	120000	50	960000	0	1	5	30020	30039	30039	14996	3	15019	120010	20	120000	20	360000	30039	30039	1	1	120021	10	9	10	10	120000	10	0	0	0	0	7520	0	3	15	16	16	15	30036	0	120000	10	30040	30040	30040	30040	30040
120024	30039	224	0	0	0	0	0	0	0	0	0	61	0	25	120010	10	120000	10	120000	50	960000	0	0	5	30020	30039	30039	14996	3	15019	120010	20	120000	20	360000	30039	30039	1	1	120021	10	9	10	10	120000	10	0	0	0	0	7520	5	3	16	16	16	17	30036	0	120000	10	30040	30040	30040	30040	30040
120024	30039	225	0	0	0	0	0	0	0	0	0	40	847	25	120010	10	120000	10	120000	50	960000	0	0	5	30020	30039	30039	14996	3	15019	120010	20	120107	20	360000	30039	30039	1	1	120021	10	9	10	10	120000	10	0	0	0	0	7520	5	3	16	16	14	14	30036	0	120000	10	30040	30040	30040	31749	30040
120024	30039	231	0	0	0	0	0	0	0	0	0	40	0	25	120010	10	120000	10	120000	50	960000	0	1	5	30020	30039	30039	14996	3	15019	120010	20	120000	20	360000	30040	30040	1	1	120021	10	9	10	10	120000	10	0	0	0	0	7520	5	3	16	16	14	14	30037	0	120000	10	30040	30040	30040	30040	30041
120024	30039	225	0	0	0	0	0	0	0	0	0	61	0	25	120010	10	120017	10	120000	50	960000	0	1	5	30020	30039	30039	14996	3	16728	120010	20	120000	20	360000	30039	30039	1	1	120021	10	9	10	10	120000	10	0	0	0	0	7520	0	3	15	16	17	17	30036	0	120000	10	30040	30040	30040	30040	30040
120024	30039	225	0	0	0	0	0	0	0	0	0	40	0	25	120011	10	120000	10	120000	50	960000	0	1	5	30020	30039	30039	16677	3	15020	120010	20	120000	20	360000	30039	30039	1	1	120021	10	9	10	10	120000	10	0	0	0	0	7520	5	3	15	16	16	16	30036	0	120000	10	30040	32567	30040	30041	30041
120024	30039	231	0	0	0	0	0	0	0	0	0	40	0	25	120011	10	120000	10	120000	50	990000	0	1	5	30020	30039	30040	14996	3	15020	120010	20	120000	20	360000	30922	30039	1	1	120021	10	9	10	10	120000	10	0	0	0	0	7520	5	3	16	16	16	11	30036	0	120000	10	31749	30040	30040	30040	30041
120024	30039	225	0	0	0	0	0	0	0	0	0	40	0	25	120010	10	120001	10	120000	50	990000	0	1	5	30020	30093	32569	14996	3	15019	120010	20	120000	20	360000	30039	30951	1	1	120021	10	9	10	10	120000	10	0	0	0	0	7520	5	3	15	16	11	18	30036	0	120000	10	30042	30923	30041	30040	30043
120024	30039	225	0	0	0	0	0	0	0	0	1	41	0	25	120027	10	120000	10	120000	50	960000	0	1	5	30020	30922	30039	14996	3	15019	120010	20	120000	20	360000	30040	30040	1	1	120021	10	9	10	10	120000	10	0	0	0	0	7520	5	3	17	16	15	17	30036	0	120000	10	30040	30040	30040	30040	30041

UMLSL (by element, 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