Firestorm: SDOT (vector, 8B) measurements

Code:

  sdot v0.2s, v1.8b, v2.8b

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)	l1d cache writeback (a8)	ac	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	f5	f6	f7	f8	fd
1004	3037	23	0	82	2548	25	1000	1000	1000	398313	1	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	73	2	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	126	2548	25	1000	1000	1000	398313	1	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	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	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	21	61	2548	25	1000	1000	1000	398313	1	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	2	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	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	0	82	2548	25	1000	1000	1000	398313	1	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	61	2548	25	1000	1000	1000	398313	1	3018	3037	3037	2415	3	2895	1000	1168	3000	3037	3037	1	1	1001	1000	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	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	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	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	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038

Test 2: Latency 1->1

Code:

  sdot v0.2s, v1.8b, v2.8b

Initialization

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

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

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

retire uop (01)	cycle (02)	03	mmu table walk data (08)	l2 tlb miss data (0b)	18	1e	1f	3a	3f	4e	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	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 tlb miss (a1)	ld unit uop (a6)	st unit uop (a7)	l1d cache writeback (a8)	a9	ac	branch cond mispred nonspec (c5)	cf	d0	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10204	30037	225	0	0	0	18	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	1	0	0	0	710	0	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	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	0	0	710	0	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	226	0	1	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	3	0	3	0	710	1	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	30018	30037	30086	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	2	0	0	7	0	0	0	712	1	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	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	0	0	710	1	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	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	1	0	0	0	710	1	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	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	0	0	710	1	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	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	1	0	0	0	710	1	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	0	61	29548	25	10136	100	10000	100	10000	522	4277313	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	2	0	0	0	710	1	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	1	61	29548	25	10100	100	10000	100	10000	500	4277313	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	1	0	0	0	710	1	2	16	2	2	29634	10000	100	30038	30038	30038	30038	30038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

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

retire uop (01)	cycle (02)	03	1e	3f	4e	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	69	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)	l1d cache writeback (a8)	ac	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10024	30037	225	0	61	29548	25	10010	10	10000	10	10000	50	4277313	30018	0	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	640	3	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	61	29548	25	10010	10	10000	10	10000	50	4277313	30018	0	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	2	3	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	61	29548	25	10010	10	10000	10	10000	50	4277313	30018	0	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	61	29548	25	10010	10	10000	10	10000	50	4277313	30018	0	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	640	3	16	3	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	61	29548	25	10010	10	10000	10	10000	50	4277313	30018	0	30037	30037	28292	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	1	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	346	29548	25	10010	10	10000	10	10000	50	4277313	30018	0	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	32	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	726	29548	25	10010	10	10000	10	10000	50	4277313	30018	0	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	640	2	16	2	3	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	726	29548	25	10010	10	10000	10	10000	50	4277313	30018	0	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	4	0	640	2	16	3	2	29695	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	61	29548	25	10010	10	10000	10	10000	50	4277313	30018	0	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	726	29548	25	10010	10	10008	10	10000	50	4277313	30018	0	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	3	3	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038

Test 3: Latency 1->2

Code:

  sdot v0.2s, v0.8b, v1.8b

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	09	l2 tlb miss data (0b)	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	ld unit uop (a6)	l1d cache writeback (a8)	a9	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
10204	30037	225	0	0	0	0	12	166	29548	25	10151	103	10000	107	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	9	2	2808	0	0	710	1	16	2	1	29634	17	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30084	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	225	0	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	5	0	0	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	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	50	0	12	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	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	0	0	0	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	61	29512	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	224	0	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	0	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	0	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	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	0	0	0	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	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	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	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)	ac	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	eb	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10024	30037	225	0	459	29548	25	10010	10	10000	10	10000	50	4277313	0	30018	0	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	640	3	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	224	0	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	0	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	61	29548	25	10010	10	10000	10	10000	50	4277313	0	30018	0	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	9	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	103	29548	25	10010	10	10000	10	10000	50	4277313	1	30054	0	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	0	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	149	29548	25	10010	10	10000	10	10000	50	4277313	0	30018	3	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	224	0	61	29548	25	10010	10	10000	10	10000	50	4277313	0	30018	0	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	1	6	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	0	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	212	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	0	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	61	29548	25	10010	10	10000	10	10000	50	4277313	0	30018	0	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038

Test 4: Latency 1->3

Code:

  sdot v0.2s, v1.8b, v0.8b

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	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 tlb miss (a1)	ld unit uop (a6)	l1d cache writeback (a8)	ac	c2	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
10204	30037	225	0	0	0	103	29548	25	10100	100	10000	100	10000	500	4277313	1	30054	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	0	710	2	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	229	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	0	710	1	16	1	2	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	1	0	0	0	710	1	16	1	2	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	61	29548	44	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	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	224	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	6	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	30000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	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	l2 tlb miss data (0b)	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)	ac	c2	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	225	0	0	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	640	6	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	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	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	224	0	0	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	30037	30181	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	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	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	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	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	640	2	16	2	2	29630	10000	10	30038	30081	30038	30038	30038
10024	30037	225	0	0	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	640	3	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	224	0	0	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	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	24	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	640	2	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	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	640	3	16	2	2	29630	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	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	640	3	16	2	2	29630	10000	10	30038	30038	30038	30038	30038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  sdot v0.2s, v8.8b, v9.8b
  movi v1.16b, 0
  sdot v1.2s, v8.8b, v9.8b
  movi v2.16b, 0
  sdot v2.2s, v8.8b, v9.8b
  movi v3.16b, 0
  sdot v3.2s, v8.8b, v9.8b
  movi v4.16b, 0
  sdot v4.2s, v8.8b, v9.8b
  movi v5.16b, 0
  sdot v5.2s, v8.8b, v9.8b
  movi v6.16b, 0
  sdot v6.2s, v8.8b, v9.8b
  movi v7.16b, 0
  sdot v7.2s, v8.8b, v9.8b

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	l1i tlb fill (04)	mmu table walk data (08)	18	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	69	6d	6e	rob full (74)	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
160204	20091	150	1	0	0	0	39	25	80100	100	80000	100	80000	500	640000	1	20045	20064	20064	0	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	0	0	10111	3	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	0	264	60	25	80100	100	80000	100	80000	500	640000	1	20045	20064	20064	0	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	0	0	10111	2	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	151	0	0	0	0	39	25	80100	100	80000	100	80000	500	640000	1	20045	20064	20064	0	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	0	3	10111	2	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	151	0	0	0	0	39	25	80100	100	80000	100	80000	500	640000	1	20045	20064	20064	0	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	0	0	10111	2	16	1	1	20061	160000	100	20065	20065	20065	20133	20065
160204	20064	150	0	0	0	0	39	25	80100	100	80000	100	80000	500	640000	1	20045	20064	20064	0	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	2	0	10111	2	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	0	0	39	25	80100	100	80000	100	80000	500	640000	1	20045	20064	20064	0	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	44	0	0	10111	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	151	0	0	0	0	39	25	80100	100	80000	100	80000	500	640000	1	20045	20064	20064	0	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	0	0	10111	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	0	0	39	25	80100	100	80000	100	80000	500	640000	1	20045	20064	20064	0	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	0	0	10111	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	151	0	0	0	294	88	25	80100	104	80104	100	80000	500	640000	1	20045	20064	20064	0	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	0	0	10111	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	0	0	0	39	25	80100	100	80000	100	80000	500	640000	1	20045	20064	20064	0	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	0	0	10111	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20131

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)	18	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)	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	ld unit uop (a6)	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	20081	156	0	0	0	0	45	27	80012	12	80000	12	80000	62	640000	1	1	5	20233	20051	20051	3	22	80012	20	80000	20	240000	20051	20051	1	1	160021	10	9	10	10	160000	10	0	0	0	10030	8	6	1	20	25	2	1	1	17	6	20048	2	20	1	160000	10	20052	20052	20052	20052	20052
160024	20051	150	0	0	0	0	45	27	80012	12	80000	12	80000	62	640000	0	1	5	20241	20051	20051	3	22	80012	20	80000	20	240000	20051	20051	1	1	160021	10	9	10	10	160000	10	0	0	0	10040	3	1	1	6	26	2	2	1	6	16	20048	2	20	1	160000	10	20052	20052	20052	20052	20052
160024	20051	151	0	0	0	39	1114	27	80012	12	80000	12	80000	62	640000	1	1	0	20248	20051	20051	3	22	80012	20	80000	20	240000	20051	20051	1	1	160021	10	9	10	10	160000	10	0	0	0	10040	8	6	1	16	25	2	1	1	16	6	20048	2	20	2	160000	10	20052	20052	20052	20052	20052
160024	20051	150	0	0	0	0	45	27	80012	12	80000	12	80104	62	640000	1	1	5	20210	20051	20051	3	22	80012	20	80000	20	240000	20051	20051	1	1	160021	10	9	10	10	160000	10	0	0	0	10065	8	6	1	16	25	2	2	1	16	16	20048	2	20	1	160000	10	20052	20052	20052	20052	20052
160024	20051	150	0	1	0	12	45	27	80012	12	80000	12	80000	62	640000	1	1	5	20197	20051	20051	3	22	80012	20	80000	20	240000	20051	20051	1	1	160021	10	9	10	10	160000	10	0	0	0	10040	8	6	1	6	34	2	1	1	16	6	20048	2	20	1	160000	10	20052	20052	20052	20052	20052
160024	20051	150	0	0	0	0	45	27	80012	12	80000	12	80000	62	640000	1	1	5	20190	20051	20051	3	22	80012	20	80000	20	240000	20051	20051	1	1	160021	10	9	10	10	160000	10	0	0	0	10030	8	6	1	16	25	2	1	1	7	17	20048	2	20	1	160000	10	20052	20052	20052	20052	20052
160024	20051	150	0	0	0	6	51	27	80012	12	80000	12	80000	62	640000	1	1	5	20206	20051	20060	3	22	80012	20	80000	20	240000	20051	20060	1	1	160021	10	9	10	10	160000	10	0	0	0	10033	8	5	1	16	34	2	1	1	16	6	20048	2	20	1	160000	10	20052	20052	20052	20052	20052
160024	20132	150	0	0	0	54	45	27	80012	12	80000	12	80000	62	640000	1	1	5	20215	20060	20051	3	22	80012	20	80000	20	240000	20051	20060	1	1	160021	10	9	10	10	160000	10	0	0	0	10040	8	5	1	16	25	2	1	1	16	16	20048	2	20	1	160000	10	20052	20052	20052	20061	20052
160024	20051	150	0	0	0	0	45	27	80012	12	80000	12	80000	62	640000	1	1	5	20204	20051	20051	3	22	80012	20	80000	20	240000	20051	20051	1	1	160021	10	9	10	10	160000	10	0	0	0	10040	8	5	1	16	25	2	1	2	16	6	20048	2	20	2	160000	10	20052	20061	20061	20052	20052
160024	20051	150	0	0	0	9	45	29	80012	12	80000	12	80000	62	640000	1	1	5	20220	20051	20051	3	22	80012	20	80000	20	240000	20051	20051	1	1	160021	10	9	10	10	160000	10	0	0	0	10043	11	5	1	16	25	4	1	1	16	16	20057	2	20	1	160000	10	20052	20052	20061	20052	20052

Test 6: throughput

Count: 16

Code:

  sdot v0.2s, v16.8b, v17.8b
  sdot v1.2s, v16.8b, v17.8b
  sdot v2.2s, v16.8b, v17.8b
  sdot v3.2s, v16.8b, v17.8b
  sdot v4.2s, v16.8b, v17.8b
  sdot v5.2s, v16.8b, v17.8b
  sdot v6.2s, v16.8b, v17.8b
  sdot v7.2s, v16.8b, v17.8b
  sdot v8.2s, v16.8b, v17.8b
  sdot v9.2s, v16.8b, v17.8b
  sdot v10.2s, v16.8b, v17.8b
  sdot v11.2s, v16.8b, v17.8b
  sdot v12.2s, v16.8b, v17.8b
  sdot v13.2s, v16.8b, v17.8b
  sdot v14.2s, v16.8b, v17.8b
  sdot v15.2s, v16.8b, v17.8b

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	1e	1f	37	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 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	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
160204	40059	300	0	0	0	534	25	160117	100	160001	100	160000	500	2399082	1	40021	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	10110	1	16	1	1	40045	0	160000	100	40049	40041	40040	40040	40041
160204	40039	300	0	0	17	41	25	160101	100	160001	100	160000	500	2398999	1	40021	40049	40039	19973	3	19997	160100	200	160000	200	480000	40049	40049	1	1	160201	100	99	100	100	160000	100	0	0	0	0	10110	1	16	1	1	40036	0	160000	100	40050	40050	40041	40050	40050
160204	40040	300	39	0	1	50	25	160100	100	160017	100	160000	500	1319999	1	40020	40039	40049	19973	3	19997	160100	200	160000	200	480000	40048	40039	1	1	160201	100	99	100	100	160000	100	0	0	0	0	10110	1	16	1	1	40036	0	160000	100	40049	40041	40040	40040	40040
160204	40039	299	0	0	1	50	25	160100	100	160001	100	160000	500	2398999	1	40020	40049	40039	19973	3	19997	160100	200	160000	200	480000	40040	40039	1	1	160201	100	99	100	100	160000	100	0	0	0	0	10110	1	16	1	1	40045	0	160000	100	40049	40040	40041	40041	40049
160204	40039	300	0	0	17	64	25	160100	100	160017	100	160000	500	1811471	1	40020	40040	40049	19973	3	19997	160100	200	160000	200	480000	40039	40040	1	1	160201	100	99	100	100	160000	100	0	0	0	0	10110	1	16	1	1	40037	0	160000	100	40040	40041	40049	40040	40049
160204	40039	300	0	0	18	42	25	160117	100	160000	100	160000	500	1319997	0	40020	40039	40039	19973	3	20006	160100	200	160000	200	480000	40039	40048	1	1	160201	100	99	100	100	160000	100	0	0	0	0	10110	1	16	1	1	40037	0	160000	100	40049	40049	40049	40049	40040
160204	40040	299	0	0	1	42	25	160100	100	160000	100	160000	500	2398999	0	40033	40040	40048	19983	3	19997	160100	200	160000	200	480000	40039	40040	1	1	160201	100	99	100	100	160000	100	0	0	0	0	10110	1	16	1	1	40037	0	160000	100	40041	40041	40050	40050	40049
160204	40048	299	0	0	0	41	25	160101	100	160000	100	160000	500	2398999	1	40030	40048	40039	19973	3	19997	160100	200	160000	200	480000	40048	40039	1	1	160201	100	99	100	100	160000	100	0	0	0	0	10110	1	16	1	1	40045	0	160000	100	40041	40050	40050	40050	40050
160204	40040	299	0	0	0	41	25	160100	100	160000	100	160000	500	1280000	1	40021	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	10110	1	16	1	1	40046	0	160000	100	40049	40040	40041	40049	40040
160204	40048	300	0	0	18	51	25	160101	100	160018	100	160000	500	1280000	0	40029	40048	40039	19973	3	19998	160100	200	160000	200	480000	40040	40048	1	1	160201	100	99	100	100	160000	100	0	0	0	0	10110	1	16	1	1	40036	0	160000	100	40049	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	l2 tlb miss data (0b)	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 cache writeback (a8)	ac	branch cond mispred nonspec (c5)	cf	d0	d2	l1i cache miss demand (d3)	d5	map dispatch bubble (d6)	d9	da	db	dd	fetch restart (de)	e0	ea	eb	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
160024	40039	300	0	0	0	17	55	0	25	160028	10	160018	10	160000	50	1280000	1	1	0	40020	40039	40039	19996	3	20028	160010	20	160000	20	480000	40039	40071	1	1	160021	10	9	10	10	160000	10	0	0	1	10022	3	1	1	42	16	2	1	1	14	14	40036	20	7	160000	10	40040	40049	40040	40040	40049
160024	40049	300	0	0	132	0	46	0	25	160010	10	160000	10	160000	50	1280000	1	1	5	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	8	5	1	10	16	2	1	1	12	14	40037	20	6	160000	10	40040	40040	40040	40040	40040
160024	40039	300	0	0	0	0	46	0	25	160010	10	160000	10	160000	50	1280000	1	1	5	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	8	5	1	13	16	2	1	1	14	14	40036	20	6	160000	10	40049	40040	40040	40040	40049
160024	40048	299	0	0	0	0	46	0	25	160010	10	160000	10	160000	50	1280000	1	1	5	40029	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	8	5	1	11	16	2	1	1	13	19	40036	20	6	160000	10	40040	40040	40040	40040	40040
160024	40039	300	0	0	0	0	46	0	25	160010	10	160000	10	160000	50	1280000	1	1	5	40029	40039	40039	19996	3	20019	160010	20	160000	20	480000	40071	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	10022	8	2	1	14	16	2	1	1	11	13	40036	20	6	160000	10	40040	40040	40040	40040	40040
160024	40039	300	0	15	0	0	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	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	10022	8	5	1	17	16	2	1	1	19	14	40036	20	7	160000	10	40040	40040	40040	40049	40040
160024	40049	300	1	0	0	0	46	0	25	160071	10	160000	10	160000	50	1280000	1	1	5	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	8	5	1	12	16	2	1	1	18	12	40036	20	6	160000	10	40040	40040	40040	40040	40040
160024	40039	300	0	0	0	0	46	0	25	160010	10	160000	10	160000	50	1280000	1	1	5	40021	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	8	5	1	13	16	2	1	1	13	19	40036	20	6	160000	10	40040	40040	40040	40040	40040
160024	40039	300	0	0	0	0	46	0	25	160010	10	160000	10	160000	50	1280000	1	1	5	40030	40039	40039	19996	3	20028	160010	20	160000	20	480000	40048	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	10022	8	5	1	14	16	2	1	1	13	19	40068	20	6	160000	10	40040	40040	40040	40040	40040
160024	40039	299	0	0	0	0	46	0	25	160010	10	160000	10	160000	50	1280000	1	1	5	40029	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	8	5	1	13	16	2	1	1	17	13	40045	20	6	160000	10	40040	40040	40040	40040	40040

SDOT (vector, 8B)

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