Firestorm: UQRSHL (vector, 4S) measurements

Code:

  uqrshl v0.4s, v0.4s, v1.4s

Initialization

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

(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)	1e	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	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	f5	f6	f7	f8	fd
1004	3037	23	0	0	61	2548	25	1000	1000	1000	398313	3018	3037	3037	2415	3	2895	1000	1000	2000	3037	3037	1	1	1001	1000	0	0	73	2	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	61	2548	25	1000	1000	1000	398313	3018	3037	3037	2415	3	2895	1000	1000	2000	3037	3037	1	1	1001	1000	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	0	0	251	2548	25	1000	1000	1000	398313	3018	3037	3037	2415	3	2895	1000	1000	2000	3037	3037	1	1	1001	1000	0	6	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	61	2548	25	1000	1000	1000	398313	3018	3037	3037	2415	3	2895	1000	1000	2000	3037	3037	1	1	1001	1000	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	0	0	61	2548	25	1000	1000	1000	398313	3018	3037	3037	2415	3	2895	1000	1000	2000	3037	3037	1	1	1001	1000	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	0	0	61	2548	25	1000	1000	1000	398313	3018	3037	3037	2415	3	2895	1000	1000	2000	3037	3037	1	1	1001	1000	6	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	61	2548	25	1000	1000	1000	398313	3018	3037	3037	2415	3	2895	1000	1000	2000	3037	3037	1	1	1001	1000	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	61	2548	25	1000	1000	1000	398313	3018	3037	3037	2415	3	2895	1000	1000	2000	3037	3037	1	1	1001	1000	0	0	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	22	0	0	199	2548	25	1000	1000	1000	398313	3018	3037	3037	2415	3	2895	1000	1000	2000	3037	3037	1	1	1001	1000	0	27	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	61	2548	25	1000	1000	1000	398313	3018	3037	3037	2415	3	2895	1000	1000	2000	3037	3037	1	1	1001	1000	0	21	73	1	16	1	1	2630	1000	3038	3038	3038	3038	3038

Test 2: Latency 1->2

Code:

  uqrshl v0.4s, v0.4s, v1.4s

Initialization

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

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

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

retire uop (01)	cycle (02)	03	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	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10204	30037	224	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	1	3	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	1	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	224	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	6	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	20000	30037	30037	4	1	10201	100	99	100	100	10000	100	0	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

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

retire uop (01)	cycle (02)	03	mmu table walk data (08)	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	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	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	0	61	29548	25	10010	10	10000	10	10000	50	4277313	0	30018	30037	30037	28287	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	1	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	0	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	30037	30037	28287	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	1	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	0	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	30037	30037	28287	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	1	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	0	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	30037	30037	28287	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	33	0	0	0	767	4	65	3	4	29881	3	10000	10	30360	30372	30325	30320	30324
10024	30359	227	1	1	6	7	924	264	1	4514	29485	162	10073	14	10056	12	10894	60	4285455	0	30270	30369	30365	28295	30	28900	11055	24	11186	22	22282	30366	30368	9	1	10021	10	9	10	10	10000	10	6	0	2	2	0	2	21323	0	788	6	85	3	3	29942	2	10000	10	30367	30369	30369	30371	30368
10024	30508	227	0	0	0	0	0	0	0	103	29548	84	10069	13	10048	16	11043	77	4286742	0	30306	30370	30369	28312	33	28899	11058	20	10491	22	22294	30370	30369	8	1	10021	10	9	10	10	10000	10	2	0	0	0	31	2	20913	2	788	2	85	5	5	29884	3	10000	10	30501	30273	30415	30467	30454
10024	30417	228	0	0	8	9	1068	704	1	5912	29467	180	10081	11	10072	16	11192	66	4288299	0	30342	30451	30177	28315	35	28936	11654	22	11307	24	22278	30463	30414	10	1	10021	10	9	10	10	10000	10	2	2	0	0	21	2	32490	2	917	6	113	2	5	29812	4	10000	10	30561	30466	30562	30595	30412
10024	30544	235	0	0	0	0	3	0	0	61	29548	25	10010	10	10008	12	10298	83	4285455	1	30306	30083	30463	28303	13	28937	10908	26	10325	26	23276	30037	30369	4	1	10021	10	9	10	10	10000	10	0	0	0	0	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	0	82	29548	25	10010	10	10000	10	10000	50	4277313	0	30018	30037	30084	28287	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	0	0	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	232	0	0	0	0	0	0	0	82	29548	25	10010	10	10000	10	10000	50	4277313	0	30018	30037	30037	28287	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	1	0	0	0	640	2	16	2	2	29630	0	10000	10	30038	30038	30038	30038	30038

Test 3: Latency 1->3

Code:

  uqrshl v0.4s, v1.4s, v0.4s

Initialization

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

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

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

retire uop (01)	cycle (02)	03	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 cache writeback (a8)	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10204	30037	225	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	224	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	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	202	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	224	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	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	12	0	61	29548	25	10100	100	10000	100	10000	500	4277313	1	30018	30037	30037	28265	3	28745	10100	200	10000	200	20000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	710	1	16	1	1	29634	10000	100	30038	30038	30038	30038	30038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

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

retire uop (01)	cycle (02)	03	mmu table walk instruction (07)	l2 tlb miss instruction (0a)	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)	simd prf full (72)	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	0	6	697	29548	25	10012	12	10008	10	10000	50	4277313	1	30018	30037	30037	28287	0	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	642	3	16	3	3	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	30037	30037	28287	0	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	642	5	16	4	5	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	61	29548	25	10010	10	10007	12	10000	50	4277313	1	30018	30037	30037	28287	0	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	640	3	16	5	4	29632	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	30037	30037	28287	0	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	640	3	16	3	3	29630	0	10000	10	30038	30038	30038	30038	30085
10024	30037	225	0	0	27	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	30037	30037	28287	0	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	10	10	10000	10	2	0	642	3	16	3	3	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	61	29548	25	10012	12	10000	12	10000	50	4277313	1	30018	30037	30037	28287	0	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	640	3	16	3	3	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	61	29548	25	10012	12	10000	12	10000	50	4277313	1	30018	30037	30037	28287	0	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	3	640	3	16	3	3	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	61	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	30037	30037	28287	0	3	28767	10012	20	10000	20	20000	30084	30037	1	1	10021	10	9	10	10	10000	10	0	0	642	5	16	3	3	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	251	29548	25	10012	12	10000	12	10000	50	4277313	1	30018	30037	30037	28287	0	3	28767	10012	20	10000	20	20000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	640	3	16	3	3	29630	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	1	0	0	726	29548	25	10010	10	10000	10	10000	50	4277313	1	30018	30037	30037	28287	0	3	28767	10010	20	10000	20	20000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	640	3	16	3	3	29630	0	10000	10	30038	30038	30038	30038	30038

Test 4: throughput

Count: 8

Code:

  uqrshl v0.4s, v8.4s, v9.4s
  uqrshl v1.4s, v8.4s, v9.4s
  uqrshl v2.4s, v8.4s, v9.4s
  uqrshl v3.4s, v8.4s, v9.4s
  uqrshl v4.4s, v8.4s, v9.4s
  uqrshl v5.4s, v8.4s, v9.4s
  uqrshl v6.4s, v8.4s, v9.4s
  uqrshl v7.4s, v8.4s, v9.4s

Initialization

  movi v8.16b, 9
  movi v9.16b, 10

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2505

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

retire uop (01)	cycle (02)	03	l2 tlb miss data (0b)	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)	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	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
80204	20059	150	0	0	0	41	25	80100	100	80000	100	80000	500	640000	0	20020	20039	20039	9973	3	9997	80100	200	80000	200	160000	20039	20039	1	1	80201	100	99	100	100	80000	100	0	0	0	0	5110	3	16	1	1	20036	0	80000	100	20040	20040	20040	20040	20040
80204	20039	150	0	0	0	41	25	80100	100	80000	100	80000	500	640000	1	20020	20039	20039	9973	3	9997	80100	200	80000	200	160000	20039	20039	1	1	80201	100	99	100	100	80000	100	0	0	0	0	5110	1	16	1	1	20036	0	80000	100	20040	20040	20040	20040	20040
80204	20039	150	0	0	0	729	25	80100	100	80000	100	80000	500	640000	1	20020	20039	20039	9973	3	9997	80100	200	80000	200	160000	20039	20039	1	1	80201	100	99	100	100	80000	100	0	0	0	0	5110	1	16	1	1	20036	0	80000	100	20040	20040	20040	20040	20040
80204	20039	150	0	0	0	83	25	80100	100	80000	100	80000	500	640000	1	20020	20039	20039	9973	3	9997	80100	200	80000	200	160000	20039	20039	1	1	80201	100	99	100	100	80000	100	0	0	0	0	5110	1	16	1	1	20036	0	80000	100	20040	20040	20040	20040	20040
80204	20039	150	0	0	0	106	25	80217	100	80000	100	80000	536	640000	1	20061	20039	20039	9973	3	9997	80100	200	80000	200	160000	20039	20039	1	1	80201	100	99	100	100	80000	100	0	1	0	0	5110	1	16	1	1	20036	0	80000	100	20040	20040	20040	20040	20040
80204	20039	150	0	0	0	546	44	80100	100	80000	108	80000	500	640000	0	20020	20039	20039	9973	3	9997	80100	200	80000	200	160000	20039	20039	1	1	80201	100	99	100	100	80000	100	0	1	0	0	5110	1	16	1	1	20036	0	80000	100	20040	20040	20040	20040	20040
80204	20039	150	0	0	0	41	25	80100	100	80000	100	80000	500	640000	1	20020	20039	20039	9973	3	9997	80100	200	80000	200	160000	20039	20039	1	1	80201	100	99	100	100	80000	100	0	0	0	0	5110	1	16	1	1	20036	0	80000	100	20200	20040	20040	20040	20040
80204	20039	150	0	12	0	41	25	80100	100	80000	100	80000	500	640000	1	20020	20039	20039	9973	3	9997	80100	200	80000	200	160000	20039	20039	1	1	80201	100	99	100	100	80000	100	0	0	0	0	5110	1	16	1	1	20036	0	80000	100	20040	20040	20040	20040	20040
80204	20039	150	0	0	0	41	25	80100	100	80000	100	80000	500	640000	0	20020	20039	20039	9973	3	9997	80100	200	80000	200	160000	20039	20039	1	1	80201	100	99	100	100	80000	100	0	0	0	0	5110	1	16	1	1	20036	0	80000	100	20040	20040	20040	20040	20040
80204	20145	150	0	12	0	41	25	80100	100	80000	100	80000	500	640000	1	20020	20039	20039	9973	3	9997	80100	200	80000	200	160000	20039	20039	1	1	80201	100	99	100	100	80000	100	0	1	0	0	5110	1	16	1	1	20036	24	80000	100	20094	20040	20040	20040	20040

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2505

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

retire uop (01)	cycle (02)	03	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)	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	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
80024	20040	150	0	5	82	25	80010	10	80000	10	80000	50	640000	1	20020	20039	20039	9996	3	10019	80010	20	80000	20	160000	20039	20039	1	1	80021	10	9	10	10	80000	10	0	0	5020	5	16	3	5	20036	80000	10	20040	20040	20040	20040	20040
80024	20039	150	0	0	40	25	80010	10	80000	10	80000	50	640000	1	20020	20039	20039	9996	3	10019	80010	20	80105	20	160000	20100	20039	1	1	80021	10	9	10	10	80000	10	0	0	5020	7	16	5	6	20036	80000	10	20040	20040	20040	20040	20040
80024	20039	150	0	0	126	25	80010	10	80000	10	80000	50	640000	1	20020	20039	20039	9996	3	10019	80010	20	80000	20	160000	20039	20039	1	1	80021	10	9	10	10	80000	10	0	0	5020	5	16	4	5	20036	80000	10	20040	20040	20040	20040	20040
80024	20039	150	0	0	40	25	80010	10	80000	10	80000	50	640000	1	20020	20039	20039	9996	3	10019	80010	20	80000	20	160000	20039	20039	1	1	80021	10	9	10	10	80000	10	0	0	5020	5	16	4	5	20036	80000	10	20040	20040	20040	20040	20040
80024	20039	150	0	0	40	25	80010	10	80000	10	80000	50	640000	1	20020	20039	20039	9996	3	10019	80010	20	80000	20	160000	20039	20039	1	1	80021	10	9	10	10	80000	10	0	0	5020	5	16	7	5	20036	80000	10	20040	20040	20040	20040	20040
80024	20039	150	0	0	40	25	80010	10	80000	10	80000	50	640000	1	20020	20039	20039	9996	3	10019	80010	20	80000	20	160000	20039	20039	1	1	80021	10	9	10	10	80000	10	0	0	5020	4	16	4	5	20036	80000	10	20040	20040	20040	20040	20040
80024	20039	150	0	0	103	25	80010	10	80000	10	80000	50	640000	1	20020	20039	20039	9996	3	10019	80010	20	80000	20	160000	20039	20039	1	1	80021	10	9	10	10	80000	10	0	0	5020	5	16	5	6	20036	80000	10	20040	20040	20040	20040	20040
80024	20039	150	0	0	542	25	80010	10	80000	10	80000	50	640000	1	20020	20039	20039	9996	3	10019	80010	20	80000	20	160000	20039	20039	1	1	80021	10	9	10	10	80000	10	0	0	5020	5	16	5	4	20036	80000	10	20040	20040	20040	20040	20040
80024	20039	150	0	0	40	25	80010	10	80000	10	80000	50	640000	1	20020	20039	20039	9996	3	10019	80010	20	80000	20	160000	20039	20039	1	1	80021	10	9	10	10	80000	10	0	0	5020	5	16	5	4	20036	80000	10	20040	20040	20040	20040	20040
80024	20039	150	0	0	40	25	80010	10	80000	10	80000	50	640000	1	20020	20039	20039	9996	3	10019	80010	20	80000	20	160000	20039	20039	1	1	80021	10	9	10	10	80000	10	0	0	5020	6	16	5	5	20036	80000	10	20040	20040	20040	20040	20040

UQRSHL (vector, 4S)

Test 1: uops

1000 unrolls and 1 iteration

Test 2: Latency 1->2

100 unrolls and 100 iterations

1000 unrolls and 10 iterations

Test 3: Latency 1->3

100 unrolls and 100 iterations

1000 unrolls and 10 iterations

Test 4: throughput

100 unrolls and 100 iterations

1000 unrolls and 10 iterations