Firestorm: UDOT (vector, 16B) measurements

Code:

  udot v0.4s, v1.16b, v2.16b

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)	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 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	9	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	0	0	0	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	24	0	0	0	0	0	0	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	0	0	0	0	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	24	0	0	0	0	0	0	0	124	2548	25	1000	1000	1000	398313	1	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	24	0	0	0	0	0	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	0	1	0	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	24	0	0	0	0	0	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	0	0	0	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	24	0	0	0	0	0	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	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	0	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	24	0	0	0	0	12	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	0	0	0	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	24	0	0	0	0	0	0	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	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	103	2548	25	1000	1000	1000	398313	1	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

Test 2: Latency 1->1

Code:

  udot v0.4s, v1.16b, v2.16b

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 tlb access (a0)	l1d cache writeback (a8)	ac	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	232	93	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	712	0	4	16	3	3	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	233	27	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	0	4	16	3	3	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	232	27	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	0	3	16	3	3	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	241	0	0	2798	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	3	710	0	3	16	3	3	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	232	174	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	0	3	16	3	3	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	233	12	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	0	3	16	3	3	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	233	24	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	0	3	16	3	3	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	232	15	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	712	0	3	16	3	3	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	233	30	0	103	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	3	710	0	3	16	3	3	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	232	168	0	82	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	710	0	3	16	3	3	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 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	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	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	233	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	640	3	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	233	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	640	2	16	3	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	246	0	0	147	29548	25	10010	10	10007	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	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	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	82	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30130	30037	1	1	10021	10	9	10	10	10000	10	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	0	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	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	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	241	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	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	0	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	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	5	1	10021	10	9	10	10	10000	10	0	640	2	16	2	3	29630	10000	10	30038	30038	30038	30038	30038

Test 3: Latency 1->2

Code:

  udot v0.4s, v0.16b, v1.16b

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	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	branch cond mispred nonspec (c5)	branch mispred nonspec (cb)	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
10204	30037	233	0	0	103	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	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	233	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	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	233	0	33	61	29539	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	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	233	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	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	232	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	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	233	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	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	233	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	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	232	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	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	233	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	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	233	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	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	l1i tlb fill (04)	mmu table walk data (08)	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	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	233	1	0	0	0	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	3	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	232	0	0	0	4	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	0	10000	10	30038	30038	30038	30038	30038
10024	30037	233	0	0	0	0	42	0	61	29548	25	10010	12	10000	12	10000	50	4277313	0	30022	30037	30037	28287	3	28767	10012	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	0	10000	10	30038	30038	30038	30038	30038
10024	30037	233	0	0	0	0	0	0	61	29548	25	10012	12	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	0	10000	10	30038	30038	30038	30038	30038
10024	30037	233	0	0	0	0	0	0	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	0	0	642	4	16	2	2	29632	2	10000	10	30038	30038	30038	30038	30038
10024	30037	233	0	0	0	0	0	0	61	29548	25	10012	12	10000	12	10000	60	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	0	0	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	232	0	0	0	3	12	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	6	0	640	2	16	2	2	29630	2	10000	10	30038	30038	30038	30038	30038
10024	30037	233	0	0	0	0	0	0	61	29548	25	10012	12	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	0	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	233	0	0	0	0	3	0	117	29548	25	10012	12	10000	12	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	0	642	3	16	3	4	29632	2	10000	10	30038	30038	30038	30038	30038
10024	30037	233	0	0	0	0	0	0	722	29548	25	10012	12	10000	12	10000	60	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	0	0	642	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038

Test 4: Latency 1->3

Code:

  udot v0.4s, v1.16b, v0.16b

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	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	l1d tlb miss nonspec (c1)	cf	l1i cache miss demand (d3)	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10204	30037	232	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	710	0	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	233	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	0	0	0	710	0	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	232	0	0	89	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	0	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	233	0	12	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	710	0	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	232	1	0	103	29548	25	10100	100	10000	100	10000	500	4277313	0	30018	30086	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	710	0	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	232	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	141	1	710	0	0	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	233	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	710	0	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	233	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	153	0	710	0	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	233	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	710	0	1	16	1	1	29634	10000	100	30038	30038	30038	30081	30038
10204	30037	232	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	710	0	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 data (08)	09	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 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
10024	30037	232	0	0	0	0	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	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	232	0	0	0	0	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	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	233	0	0	0	0	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	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	233	0	0	0	0	0	726	29548	25	10010	10	10000	10	10000	50	4277313	30018	30037	30084	28287	26	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	232	0	0	0	0	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	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	233	0	0	0	0	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	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	232	0	0	0	0	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	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	232	0	0	0	0	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	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	233	0	1	0	0	0	251	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	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	232	0	0	0	0	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	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038

Test 5: throughput

Count: 8

Code:

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

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	l2 tlb miss instruction (0a)	19	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)	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 cache writeback (a8)	ac	branch cond mispred nonspec (c5)	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
160204	20065	155	0	0	0	39	25	80125	125	80000	100	80000	500	640000	0	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	10115	0	3	16	3	3	20061	0	160000	100	20065	20363	20065	20065	20065
160204	20064	155	0	1	0	39	25	80100	100	80000	100	80000	506	640000	0	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	10114	0	4	16	4	4	20061	0	160000	100	20065	20065	20065	20065	20065
160204	20064	155	0	0	0	39	25	80100	100	80000	100	80000	500	640000	0	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	10115	0	6	16	5	4	20061	0	160000	100	20065	20065	20065	20065	20065
160204	20064	155	0	0	0	39	25	80100	100	80000	100	80000	500	640000	0	0	20045	20064	20064	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	1	9	0	10113	0	3	16	4	4	20061	0	160000	100	20065	20065	20065	20065	20065
160204	20064	155	0	0	0	39	25	80100	100	80000	100	80000	500	640000	0	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	10114	0	4	16	5	6	20061	0	160000	100	20065	20065	20065	20065	20065
160204	20064	156	0	0	0	39	25	80100	100	80000	100	80000	500	640000	0	0	20045	20064	20064	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	1	0	0	10115	0	3	16	4	4	20061	0	160000	100	20065	20065	20065	20065	20065
160204	20064	156	0	0	0	39	25	80100	100	80000	100	80000	500	640000	0	0	20045	20064	20064	3	22	80100	200	80000	202	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	0	1	10113	0	4	16	5	3	20061	0	160000	100	20065	20065	20065	20065	20065
160204	20064	155	0	0	0	39	25	80100	100	80000	100	80000	500	640000	1	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	10114	0	4	16	5	3	20061	0	160000	100	20065	20065	20065	20065	20065
160204	20064	156	0	0	0	39	25	80100	100	80000	100	80000	500	640000	1	0	20045	20064	20064	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	9	3	0	10115	0	4	16	4	4	20061	0	160000	100	20065	20065	20065	20065	20065
160204	20064	155	0	0	0	39	25	80100	100	80000	100	80000	500	640000	0	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	10115	0	5	16	5	4	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	mmu table walk instruction (07)	mmu table walk data (08)	l2 tlb miss instruction (0a)	l2 tlb miss data (0b)	18	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	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)	ld unit uop (a6)	l1d cache writeback (a8)	a9	ac	c2	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	20092	155	0	0	0	0	0	0	0	0	51	25	80012	12	80000	12	80000	62	640000	1	1	20027	20046	20046	3	22	80012	20	80000	20	240000	20050	20050	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	3	0	0	10033	6	2	2	10	24	4	2	2	8	4	20047	2	30	0	160000	10	20051	20051	20051	20051	20051
160024	20046	155	0	0	0	0	0	0	12	0	45	25	80012	12	80000	12	80000	62	640000	0	1	20031	20046	20136	3	22	80012	20	80000	20	240000	20046	20046	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	3	0	0	10033	3	1	1	10	24	2	2	1	5	10	20043	2	15	0	160000	10	20047	20051	20047	20051	20047
160024	20046	156	1	0	0	0	0	0	0	0	51	25	80012	12	80000	12	80000	62	640000	0	1	20027	20050	20046	3	22	80012	20	80000	20	240000	20046	20046	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	3	0	0	10030	3	1	2	9	20	4	1	1	4	8	20051	2	16	0	160000	10	20051	20047	20047	20051	20047
160024	20046	155	0	0	0	0	0	0	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	0	105	0	0	10030	3	1	1	4	24	2	1	1	10	4	20246	2	31	0	160000	10	20047	20051	20047	20051	20047
160024	20046	155	0	0	0	0	0	0	0	0	51	25	80012	12	80000	12	80000	62	640000	0	1	20027	20046	20050	3	22	80012	20	80000	20	240000	20046	20047	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	0	0	0	10030	3	1	1	8	20	2	1	1	7	4	20043	2	15	0	160000	10	20047	20047	20047	20047	20047
160024	20046	155	0	0	0	0	0	0	0	0	45	25	80012	12	80000	12	80000	62	640000	1	1	20031	20046	20046	3	22	80012	20	80000	20	240000	20047	20046	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	0	0	0	10034	6	2	2	4	20	2	2	1	11	4	20043	2	15	0	160000	10	20047	20047	20047	20047	20047
160024	20046	155	0	0	0	0	0	0	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	0	9	0	0	10030	3	1	1	4	24	2	1	2	4	7	20043	2	15	0	160000	10	20051	20051	20051	20047	20051
160024	20046	156	1	0	0	0	0	0	0	0	45	25	80012	12	80000	12	80000	62	640000	0	1	20031	20050	20050	3	22	80012	20	80000	20	240000	20046	20046	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	12	0	0	10027	6	2	2	7	20	2	1	1	4	7	20043	2	15	0	160000	10	20051	20051	20051	20047	20051
160024	20046	155	1	0	0	0	0	0	0	0	93	25	80012	12	80000	12	80000	62	640000	0	1	20027	20046	20050	3	22	80012	20	80000	20	240000	20046	20046	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	9	0	0	10027	3	1	1	7	20	2	1	1	5	11	20043	2	15	0	160000	10	20047	20047	20047	20047	20047
160024	20046	156	0	0	0	0	0	0	0	0	45	25	80012	12	80000	12	80000	62	640000	1	1	20031	20050	20046	3	22	80012	20	80000	20	240000	20046	20046	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	9	0	0	10033	3	1	2	4	24	4	1	2	4	8	20047	2	15	0	160000	10	20047	20047	20051	20047	20052

Test 6: throughput

Count: 16

Code:

  udot v0.4s, v16.16b, v17.16b
  udot v1.4s, v16.16b, v17.16b
  udot v2.4s, v16.16b, v17.16b
  udot v3.4s, v16.16b, v17.16b
  udot v4.4s, v16.16b, v17.16b
  udot v5.4s, v16.16b, v17.16b
  udot v6.4s, v16.16b, v17.16b
  udot v7.4s, v16.16b, v17.16b
  udot v8.4s, v16.16b, v17.16b
  udot v9.4s, v16.16b, v17.16b
  udot v10.4s, v16.16b, v17.16b
  udot v11.4s, v16.16b, v17.16b
  udot v12.4s, v16.16b, v17.16b
  udot v13.4s, v16.16b, v17.16b
  udot v14.4s, v16.16b, v17.16b
  udot v15.4s, v16.16b, v17.16b

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	1f	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)	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 access (a0)	l1d tlb miss (a1)	ld unit uop (a6)	st unit uop (a7)	l1d cache writeback (a8)	ac	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	eb	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
160204	40124	310	0	0	0	0	0	0	0	0	92	25	160101	100	160017	100	160000	500	1280000	40020	0	40048	40039	19973	3	20006	160100	200	160000	200	480000	40039	40039	1	1	160201	100	99	100	100	160000	100	0	0	0	0	0	12	10110	2	16	1	1	40036	0	160000	100	40040	40049	40040	40040	40040
160204	40039	311	0	0	0	0	0	0	0	0	41	25	160117	100	160000	100	160000	500	1280000	40029	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	40036	0	160000	100	40049	40040	40040	40040	40049
160204	40039	310	0	0	0	0	0	0	0	0	421	25	160118	100	160000	100	160000	500	1280000	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	0	0	0	0	10110	1	16	1	1	40036	0	160000	100	40040	40040	40040	40049	40049
160204	40048	311	0	0	0	0	0	0	0	0	41	25	160100	100	160000	100	160000	500	2398999	40029	0	40048	40039	19973	3	19997	160100	200	160000	200	480000	40048	40048	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	40049	40040	40049
160204	40048	311	0	0	0	0	0	0	0	0	1709	25	160117	100	160000	100	160000	500	1280000	40029	0	40048	40048	19973	3	20006	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	40040	40040	40040	40040	40040
160204	40039	310	0	0	0	0	0	0	17	0	706	25	160100	100	160017	100	160000	500	1280000	40029	0	40039	40039	19973	3	19997	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	40036	0	160000	100	40049	40049	40049	40040	40041
160204	40048	310	0	0	0	0	0	0	0	0	92	25	160100	100	160000	100	160000	500	2398999	40020	0	40048	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	40036	0	160000	100	40040	40049	40049	40049	40041
160204	40048	310	0	0	0	0	0	0	0	0	41	25	160100	100	160017	100	160000	500	1319999	40020	0	40039	40048	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	40045	0	160000	100	40040	40041	40040	40040	40040
160204	40039	310	0	0	0	0	12	0	0	0	41	25	160100	100	160000	100	160000	500	1280000	40120	0	40048	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	40036	0	160000	100	40049	40040	40040	40049	40040
160204	40039	311	0	0	0	0	0	0	17	0	940	25	160117	100	160000	100	160000	500	1280000	40029	0	40039	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	40049	40040	40040	40040

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	09	18	19	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	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	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	40070	311	0	0	0	9	0	0	46	25	160028	10	160000	10	160000	50	1280000	0	1	40020	40048	40048	19996	3	20019	160010	20	160000	20	480000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	10022	3	1	1	17	16	2	1	1	17	16	40036	0	15	5	0	160000	10	40040	40040	40040	40040	40040
160024	40039	310	0	0	0	0	0	0	55	25	160010	10	160000	10	160000	50	2398999	1	1	40020	40049	40039	19996	3	20029	160010	20	160000	20	480000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	10022	3	1	1	18	16	2	2	1	19	20	40045	0	16	5	0	160000	10	40040	40040	40040	40040	40040
160024	40039	310	0	0	1	0	0	0	52	25	160010	10	160000	10	160000	50	1280000	1	1	40020	40039	40039	19996	3	20019	160010	20	160000	20	480000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	10022	3	1	1	19	16	2	1	1	12	16	40036	0	15	5	0	160000	10	40040	40040	40040	40040	40040
160024	40039	310	0	0	0	0	0	0	46	25	160010	10	160000	10	160000	50	1280000	1	1	40029	40049	40039	19996	3	20019	160010	20	160000	20	480000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	10024	3	1	1	17	16	2	2	2	19	19	40036	0	15	5	0	160000	10	40040	40040	40040	40040	40040
160024	40039	310	0	0	0	9	0	0	55	25	160010	10	160000	10	160000	50	1280000	1	1	40020	40048	40048	19996	3	20019	160010	20	160000	20	480000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	10022	3	1	1	19	16	2	1	1	19	19	40036	0	15	10	0	160000	10	40040	40040	40040	40040	40040
160024	40039	310	0	0	0	0	0	0	46	25	160010	10	160000	10	160000	50	1280000	1	1	40020	40039	40039	19996	3	20029	160010	20	160000	20	480000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	10022	3	1	1	17	16	4	1	1	19	17	40036	0	30	5	0	160000	10	40049	40040	40040	40040	40040
160024	40039	311	0	0	0	0	0	0	67	25	160010	10	160000	10	160000	50	2398999	1	1	40021	40049	40039	19996	3	20029	160010	20	160000	20	480000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	10022	3	1	2	15	16	2	1	1	17	15	40046	0	15	10	0	160000	10	40040	40040	40050	40050	40040
160024	40039	310	0	1	0	0	0	0	46	25	160010	10	160000	10	160000	50	1280000	1	1	40020	40039	40039	19996	3	20019	160010	20	160000	20	480000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	10022	6	2	2	18	16	2	1	1	18	17	40036	0	15	5	0	160000	10	40040	40040	40040	40041	40040
160024	40039	310	0	0	0	12	0	0	46	25	160010	10	160000	10	160000	50	1280000	1	1	40020	40039	40049	19996	3	20019	160010	20	160000	20	480000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	10022	3	1	1	17	16	2	1	1	13	19	40036	0	15	6	0	160000	10	40040	40040	40040	40040	40040
160024	40039	310	0	0	0	0	0	0	47	25	160010	10	160000	10	160000	50	1280000	1	1	40020	40039	40039	19996	3	20019	160010	20	160000	20	480000	40039	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	10022	3	1	1	15	16	2	1	1	19	13	40036	0	15	5	0	160000	10	40049	40040	40040	40040	40049

UDOT (vector, 16B)

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