Firestorm: UABAL (vector, 2D) measurements

Code:

  uabal v0.2d, v1.2s, v2.2s

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	l2 tlb miss data (0b)	18	1e	3a	3f	4e	51	schedule uop (52)	schedule simd uop (54)	dispatch simd uop (57)	ldst uops in schedulers (5b)	69	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map simd uop (7e)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst simd alu (9a)	l1d cache writeback (a8)	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	2	107	2548	25	1000	1000	1000	398313	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	0	75	5	16	6	6	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	0	0	0	1	84	2548	25	1000	1000	1000	398313	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	0	75	6	16	6	6	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	0	1	82	2548	25	1000	1000	1000	398313	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	2730	0	75	5	16	6	6	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	0	1	102	2548	25	1000	1000	1000	398313	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	6	0	75	6	16	5	5	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	0	0	0	1	164	2548	25	1000	1000	1000	398313	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	0	75	6	16	6	6	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	0	0	0	2	61	2548	25	1000	1000	1000	398313	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	1	0	0	75	5	16	6	6	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	0	0	0	1	84	2548	25	1000	1000	1000	398313	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	1	0	0	75	6	16	5	5	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	0	0	0	1	84	2548	25	1000	1000	1000	398313	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	0	75	6	16	7	7	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	0	1	82	2548	25	1000	1000	1000	398313	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	0	0	0	75	6	16	6	6	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	0	1	107	2548	25	1000	1000	1000	398313	3018	3037	3037	2415	3	2895	1000	1000	3000	3037	3037	1	1	1001	1000	1	0	0	75	6	16	6	6	2630	1000	3038	3038	3038	3038	3038

Test 2: Latency 1->1

Code:

  uabal v0.2d, v1.2s, v2.2s

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 instruction (07)	mmu table walk data (08)	09	l2 tlb miss instruction (0a)	l2 tlb miss data (0b)	18	19	1e	1f	3a	3f	4e	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	60	69	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)	a9	ac	c2	branch cond mispred nonspec (c5)	branch mispred nonspec (cb)	cd	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	1	0	0	1	0	0	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	0	30018	0	30037	30037	28272	6	28740	10100	200	10008	200	30540	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	0	0	1	1	1	766	0	2	16	1	1	29649	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	1	0	0	1	0	0	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	0	30037	30037	28272	6	28741	10100	200	10008	200	30024	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	3	0	1	1	1	720	0	1	16	1	1	29649	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	1	0	0	1	0	0	0	0	0	0	82	29548	25	10100	100	10000	100	10000	500	4277313	0	30018	0	30037	30037	28272	7	28740	10100	200	10008	200	30024	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	0	0	1	1	1	717	0	1	16	1	1	29648	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	1	0	0	1	0	0	0	0	0	0	61	29548	25	10100	100	10000	100	10000	511	4277313	0	30018	0	30037	30037	28272	6	28741	10100	200	10008	200	30024	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	0	0	1	1	1	717	0	1	16	1	1	29648	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	1	0	0	1	0	0	0	0	0	0	1426	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	0	30037	30037	28272	6	28741	10100	200	10008	200	30024	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	1	0	0	0	0	0	0	710	1	3	16	3	3	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	0	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	0	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	0	0	0	0	0	0	0	0	712	1	3	16	3	3	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	0	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	0	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	0	0	0	0	0	0	0	0	712	1	3	16	3	3	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	0	0	0	0	0	86	29548	25	10100	104	10000	100	10000	500	4277313	0	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	0	0	0	0	0	0	0	0	710	1	3	16	3	3	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	0	0	0	0	0	61	29548	25	10112	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	0	0	0	0	0	0	0	0	710	1	3	16	3	4	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	0	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	0	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	0	0	0	0	0	0	0	0	710	1	3	16	3	3	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	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d cache writeback (a8)	a9	ac	c2	cd	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? int output thing (e9)	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10024	30037	225	0	251	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	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	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	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	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	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	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	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	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	233	0	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	640	2	16	2	3	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	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	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	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	536	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	640	2	16	3	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	441	29548	25	10010	10	10000	10	10000	50	4277313	0	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038

Test 3: Latency 1->2

Code:

  uabal v0.2d, v0.2s, v1.2s

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	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	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	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
10204	30037	225	0	0	1999	29548	25	10100	100	10000	100	10000	500	4277313	0	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	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	224	0	0	978	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	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	972	29548	25	10100	100	10000	100	10000	500	4277313	0	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	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	0	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	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	82	29548	25	10100	100	10000	100	10000	500	4277313	0	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	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	208	29548	25	10100	100	10000	100	10000	500	4277313	0	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	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	224	0	0	1676	29548	25	10100	100	10000	100	10000	500	4277313	0	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	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	241	0	0	1267	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	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	224	0	0	1337	29548	25	10100	100	10000	100	10000	500	4277313	0	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	0	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	1061	29548	25	10100	100	10000	100	10000	500	4277313	0	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	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)	69	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d cache writeback (a8)	ac	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? int output thing (e9)	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10024	30037	225	0	300	29548	25	10010	10	10000	10	10000	50	4277313	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	1200	29548	25	10010	10	10000	10	10000	50	4277313	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	1118	29548	25	10010	10	10000	10	10000	50	4277313	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	683	29548	25	10010	10	10000	10	10000	50	4277313	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	6	1026	29548	25	10010	10	10000	10	10000	50	4277313	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	1129	29548	25	10010	10	10000	10	10000	50	4277313	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	61	29548	64	10022	10	10008	14	10149	50	4277313	30018	30133	30085	28296	12	28785	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	640	2	16	2	2	29702	3	10000	10	30038	30038	30038	30038	30085
10024	30037	225	0	1339	29548	25	10010	11	10008	10	10000	50	4277313	30054	30085	30083	28292	8	28786	10161	20	10000	20	30000	30037	30085	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	6	61	29548	25	10010	10	10000	10	10000	50	4277313	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	224	0	1175	29548	25	10010	10	10000	10	10000	50	4277313	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038

Test 4: Latency 1->3

Code:

  uabal v0.2d, v1.2s, v0.2s

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)	l2 tlb miss data (0b)	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 tlb access (a0)	l1d tlb miss (a1)	l1d cache writeback (a8)	a9	ac	c2	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	0	0	231	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	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	18	0	0	710	1	16	1	1	29634	0	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	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	0	710	1	16	1	1	29634	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	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	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	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	0	0	0	61	29548	25	10110	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	0	710	1	16	1	1	29634	0	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	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	1	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	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	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28293	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	0	9	0	251	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	mmu table walk data (08)	l2 tlb miss data (0b)	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 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	? int output thing (e9)	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10024	30037	225	0	0	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	0	0	0	724	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	0	0	61	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	0	0	0	0	12	0	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	12	0	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	30037	30228	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	0	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	0	0	61	29548	25	10010	10	10000	10	10000	61	4277313	1	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	0	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	224	0	0	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	0	0	0	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	224	0	0	0	0	0	0	726	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	2	0	0	0	0	0	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	1	0	0	0	0	536	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	30037	30037	28287	3	28767	10010	20	10000	20	30000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	9	0	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	9	0	726	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	30037	30037	28291	3	28767	10010	20	10000	20	30000	30037	30037	2	1	10021	10	9	10	10	10000	10	0	0	0	1	0	27905	0	834	3	97	3	3	29992	4	10000	10	30513	30558	30549	30548	30510
10024	30558	229	0	0	9	11	1329	880	5944	29458	239	10102	24	10088	23	11418	93	4290883	1	30414	30402	30543	28325	51	28973	11502	20	11806	24	35388	30559	30462	13	1	10021	10	9	10	10	10000	10	4	2	2	4	2	27835	0	859	3	104	2	4	30055	2	10000	10	30508	30558	30464	30461	30512
10024	30557	228	1	0	8	9	1188	528	5346	29476	200	10090	15	10064	10	11341	81	4288169	0	30342	30467	30415	28319	36	28917	11206	22	11316	22	33933	30462	30459	4	1	10021	10	9	10	10	10000	10	0	0	2	1	2	25145	0	850	5	121	4	3	30061	5	10000	10	30461	30556	30556	30510	30543

Test 5: throughput

Count: 8

Code:

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

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	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	6b	6d	6e	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d tlb access (a0)	l1d cache writeback (a8)	ac	branch mispred nonspec (cb)	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
160204	20088	150	0	39	25	80100	100	80000	100	80000	500	640000	0	20045	0	20064	20064	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	0	0	0	10111	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	39	25	80100	100	80000	100	80000	500	640000	0	20045	0	20064	20064	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	0	0	0	10111	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	39	25	80100	100	80000	100	80000	500	640000	0	20045	0	20064	20064	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	0	0	0	10111	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	156	0	39	25	80100	100	80000	100	80000	500	640000	0	20045	0	20064	20064	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	0	0	0	10111	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	39	25	80100	100	80000	100	80000	500	640000	0	20045	0	20064	20064	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	0	0	0	10111	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	54	25	80100	100	80000	100	80000	500	640000	1	20045	0	20064	20064	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	0	0	0	10111	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	39	25	80100	100	80000	100	80000	500	640000	0	20045	0	20064	20064	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	0	0	0	10111	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	39	25	80100	100	80000	100	80000	500	640000	0	20045	0	20064	20064	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	0	0	0	10111	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	150	0	39	25	80100	100	80000	100	80000	500	640000	0	20045	0	20064	20064	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	0	0	0	10111	1	16	1	3	20061	160000	100	20065	20065	20065	20065	20065
160204	20064	151	0	81	25	80100	100	80000	100	80000	500	640000	0	20045	0	20064	20064	3	22	80100	200	80000	200	240000	20064	20064	1	1	160201	100	99	100	100	160000	100	0	0	0	0	10111	1	16	1	1	20061	160000	100	20065	20065	20065	20065	20065

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2507

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)	1e	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 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	d0	d2	l1i cache miss demand (d3)	l1i tlb miss demand (d4)	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	20108	151	2	0	0	0	57	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	10041	3	1	28	0	24	25	2	1	1	21	21	20048	2	20	0	1	160000	10	20052	20052	20052	20052	20052
160024	20051	150	2	2	0	0	57	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	10047	3	1	24	0	19	25	2	1	2	22	19	20048	2	40	0	1	160000	10	20052	20061	20052	20052	20052
160024	20051	150	1	1	0	0	51	27	80012	12	80000	12	80000	62	640000	1	1	20032	20051	20051	3	22	80012	20	80000	20	240000	20051	20060	1	1	160021	10	9	10	10	160000	10	0	0	0	10044	3	1	25	0	19	25	2	1	1	18	21	20048	2	20	0	1	160000	10	20052	20052	20052	20052	20052
160024	20051	150	1	1	0	0	57	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	10045	3	1	24	0	20	25	2	1	1	22	18	20048	2	20	0	1	160000	10	20052	20052	20052	20052	20052
160024	20051	150	1	1	0	0	57	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	10043	3	1	23	0	20	34	2	2	2	22	21	20048	2	40	0	2	160000	10	20052	20061	20052	20061	20052
160024	20051	150	1	1	0	0	290	27	80012	12	80000	12	80000	62	640000	1	1	20032	20051	20060	3	22	80012	20	80000	20	240000	20051	20060	1	1	160021	10	9	10	10	160000	10	0	0	0	10044	6	2	23	0	14	34	4	1	2	22	23	20048	2	40	0	2	160000	10	20061	20061	20061	20052	20061
160024	20060	150	1	1	0	0	292	27	80012	12	80000	12	80000	62	640000	0	1	20032	20060	20060	3	22	80012	20	80000	20	240000	20060	20051	1	1	160021	10	9	10	10	160000	10	0	0	0	10044	6	2	20	0	18	34	2	2	2	20	19	20057	2	40	0	2	160000	10	20061	20052	20061	20052	20061
160024	20060	150	1	1	0	0	1108	27	80012	12	80000	12	80000	62	640000	1	1	20041	20060	20051	3	22	80012	20	80000	20	240000	20060	20060	1	1	160021	10	9	10	10	160000	10	0	0	0	10049	3	2	24	0	20	34	4	1	2	21	22	20048	2	20	0	2	160000	10	20061	20061	20061	20061	20052
160024	20051	150	1	1	0	0	51	27	80012	12	80000	12	80000	62	640000	1	1	20032	20051	20051	3	22	80012	20	80000	20	240000	20060	20060	1	1	160021	10	9	10	10	160000	10	3	0	0	10036	3	1	20	0	20	25	2	1	1	18	20	20048	2	20	0	1	160000	10	20052	20052	20052	20052	20052
160024	20060	150	2	2	0	0	51	29	80012	12	80000	12	80000	62	640000	1	1	20041	20051	20060	3	22	80012	20	80000	20	240000	20060	20060	1	1	160021	10	9	10	10	160000	10	0	0	0	10045	6	2	20	0	19	25	4	1	2	21	20	20057	2	20	0	1	160000	10	20061	20052	20061	20061	20052

Test 6: throughput

Count: 16

Code:

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

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)	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	cf	d0	d2	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
160204	40076	300	0	0	17	41	0	25	160101	100	160000	100	160000	500	1280000	0	40029	40071	40049	19973	3	19997	160100	200	160000	200	480000	40039	40048	1	1	160201	100	99	100	100	160000	100	0	0	10110	0	0	0	2	64	1	1	40045	160000	100	40049	40040	40049	40040	40040
160204	40039	300	1	0	17	41	0	25	160101	100	160000	100	160000	500	1319998	0	40029	40039	40039	19973	3	19998	160100	200	160000	200	480000	40039	40048	1	1	160201	100	99	100	100	160000	100	0	0	10110	0	0	0	1	16	1	1	40037	160000	100	40049	40050	40040	40040	40040
160204	40048	300	0	9	0	50	0	25	160100	100	160000	100	160000	500	2398999	0	40020	40039	40040	19973	3	19997	160100	200	160000	200	480000	40048	40039	1	1	160201	100	99	100	100	160000	100	0	0	10110	0	0	0	2	16	1	1	40046	160000	100	40041	40049	40041	40050	40040
160204	40048	300	0	0	17	50	25	25	160100	100	160000	100	160000	500	1280000	0	40020	40039	40048	19973	3	19997	160100	200	160000	200	480000	40048	40048	1	1	160201	100	99	100	100	160000	100	0	0	10110	0	0	0	1	16	1	1	40036	160000	100	40040	40040	40049	40040	40049
160204	40039	300	0	0	0	41	0	25	160100	100	160000	100	160000	500	2398999	0	40020	40039	40039	19973	3	19997	160100	200	160000	200	480000	40049	40039	1	1	160201	100	99	100	100	160000	100	0	0	10110	0	0	0	1	16	1	1	40036	160000	100	40040	40049	40040	40049	40074
160204	40039	300	0	0	17	50	0	25	160117	100	160000	100	160000	500	1280000	0	40021	40039	40048	19973	3	19997	160100	200	160000	200	480000	40048	40040	1	1	160201	100	99	100	100	160000	100	0	0	10110	0	0	0	1	16	1	1	40036	160000	100	40041	40040	40049	40041	40049
160204	40039	300	0	0	1	50	0	25	160101	100	160017	100	160000	500	1280000	0	40021	40039	40040	19973	3	20006	160100	200	160000	200	480000	40048	40039	1	1	160201	100	99	100	100	160000	100	0	0	10110	0	0	0	1	16	1	1	40036	160000	100	40049	40040	40049	40040	40040
160204	40048	300	0	0	0	71	0	25	160100	100	160000	100	160000	500	1280000	0	40029	40039	40039	19973	3	19998	160100	200	160000	200	480000	40039	40049	1	1	160201	100	99	100	100	160000	100	0	0	10110	0	0	0	1	16	1	1	40036	160000	100	40041	40049	40041	40040	40040
160204	40049	300	0	0	17	41	0	25	160100	100	160017	100	160000	500	1319998	0	40021	40040	40098	19973	3	19998	160100	200	160000	200	480000	40048	40039	1	1	160201	100	99	100	100	160000	100	0	0	10110	0	0	1	1	16	1	1	40046	160000	100	40040	40049	40040	40049	40040
160204	40039	300	0	0	0	50	0	25	160100	100	160017	100	160000	500	1280000	0	40020	40040	40048	19973	3	20006	160100	200	160000	200	480000	40039	40039	1	1	160201	100	99	100	100	160000	100	0	0	10110	0	0	0	1	16	1	1	40037	160000	100	40040	40049	40040	40049	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	mmu table walk instruction (07)	mmu table walk data (08)	l2 tlb miss instruction (0a)	l2 tlb miss data (0b)	18	19	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)	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 access (a0)	l1d tlb miss (a1)	ld unit uop (a6)	l1d cache writeback (a8)	a9	ac	c2	cf	d0	d2	l1i cache miss demand (d3)	d5	map dispatch bubble (d6)	d9	da	db	dd	fetch restart (de)	e0	? int output thing (e9)	ea	eb	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
160024	40057	300	0	0	0	0	0	0	12	0	0	46	25	160010	10	160000	10	160000	50	1280000	1	1	0	40029	40039	40048	19996	3	20028	160010	20	160000	20	480000	40039	40048	1	1	160021	10	9	10	10	160000	10	0	0	2	0	4	0	0	10022	8	5	1	34	16	2	1	1	13	10	40036	0	20	6	160000	10	40040	40049	40040	40040	40040
160024	40048	299	0	0	0	0	0	0	0	0	17	55	25	160027	10	160000	10	160000	50	1280000	1	1	5	40020	40039	40048	19996	3	20028	160010	20	160000	20	480000	40039	40048	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	0	0	10022	8	5	1	13	16	2	1	1	19	14	40045	0	20	9	160000	10	40049	40040	40049	40040	40049
160024	40048	300	0	0	0	0	0	0	0	0	0	46	25	160027	10	160000	10	160000	50	2398999	1	1	5	40020	40039	40048	19996	3	20019	160010	20	160000	20	480000	40048	40048	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	0	0	10022	8	5	1	13	16	4	1	1	12	13	40045	0	20	6	160000	10	40040	40049	40040	40050	40040
160024	40048	300	0	0	0	0	0	0	0	0	0	46	25	160027	10	160017	10	160000	50	1280000	1	1	5	40020	40039	40048	19996	3	20028	160010	20	160000	20	480000	40048	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	0	0	10024	8	5	1	12	16	2	1	1	19	14	40036	0	40	9	160000	10	40049	40040	40049	40040	40049
160024	40048	299	0	0	0	0	0	0	0	0	0	542	25	160010	10	160000	10	160000	50	1280000	0	1	5	40020	40039	40048	19996	3	20019	160010	20	160000	20	480000	40048	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	1	0	6	0	10022	8	5	1	12	16	2	1	1	14	9	40088	1	20	6	160000	10	40040	40049	40040	40049	40049
160024	40048	300	0	0	0	0	0	0	0	0	0	55	25	160010	10	160000	10	160000	50	1280000	1	1	5	40020	40039	40039	19996	3	20028	160010	20	160000	20	480000	40048	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	1	0	0	0	10022	8	5	1	9	16	2	1	1	8	12	40045	0	20	6	160000	10	40049	40040	40049	40040	40040
160024	40039	300	0	0	0	0	0	0	0	0	0	46	25	160010	10	160000	10	160000	50	2398999	1	1	5	40029	40039	40048	19996	3	20019	160010	20	160000	20	480000	40039	40048	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	0	2	10022	8	5	1	10	16	2	1	1	10	12	40036	0	20	9	160000	10	40040	40040	40049	40040	40040
160024	40039	300	0	0	0	0	0	0	36	0	51	55	25	160027	10	160017	10	160000	50	1280000	1	1	5	40020	40090	40039	19996	3	20019	160010	20	160000	20	480000	40039	40048	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	0	0	10022	8	5	1	14	16	2	1	1	12	9	40045	0	20	6	160000	10	40049	40040	40049	40040	40040
160024	40039	300	0	0	0	0	0	0	0	0	0	55	25	160027	10	160000	10	160000	50	2398999	1	1	5	40020	40039	40039	19996	3	20028	160010	20	160000	20	480000	40048	40039	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	0	0	10022	8	5	1	13	16	2	1	1	9	17	40036	0	20	6	160000	10	40049	40040	40040	40049	40049
160024	40048	300	0	0	0	0	0	0	0	0	17	55	25	160027	10	160017	10	160000	50	1280000	1	1	5	40020	40039	40039	19996	3	20019	160010	20	160000	20	480000	40039	40049	1	1	160021	10	9	10	10	160000	10	0	0	0	0	0	0	0	10022	8	5	1	12	16	2	1	1	12	8	40036	0	20	9	160000	10	40040	40040	40040	40049	40040

UABAL (vector, 2D)

Test 1: uops

1000 unrolls and 1 iteration

Test 2: Latency 1->1

100 unrolls and 100 iterations

1000 unrolls and 10 iterations

Test 3: Latency 1->2

100 unrolls and 100 iterations

1000 unrolls and 10 iterations

Test 4: Latency 1->3

100 unrolls and 100 iterations

1000 unrolls and 10 iterations

Test 5: throughput

100 unrolls and 100 iterations

1000 unrolls and 10 iterations

Test 6: throughput

100 unrolls and 100 iterations

1000 unrolls and 10 iterations