Firestorm: SQSHL (immediate, vector, 16B) measurements

Code:

  sqshl v0.16b, v0.16b, #3

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	3f	4e	51	schedule uop (52)	schedule simd uop (54)	dispatch simd uop (57)	ldst uops in schedulers (5b)	60	61	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	d0	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	f5	f6	f7	f8	fd
1004	2037	15	82	1686	25	1000	1000	1000	264521	0	0	2018	2037	2037	1571	3	1895	1000	1000	1000	2037	2037	1	1	1001	1000	0	0	73	0	1	16	1	1	1786	1000	2038	2038	2038	2038	2038
1004	2037	15	61	1686	25	1000	1000	1000	264521	0	0	2018	2037	2037	1571	3	1895	1000	1000	1000	2037	2037	1	1	1001	1000	0	0	73	0	1	16	1	1	1786	1000	2038	2038	2038	2038	2038
1004	2037	15	61	1686	25	1000	1000	1000	264521	0	0	2018	2037	2037	1571	3	1895	1000	1000	1000	2037	2037	1	1	1001	1000	0	0	73	0	1	16	1	1	1786	1000	2038	2038	2038	2038	2038
1004	2037	15	61	1686	25	1000	1000	1000	264521	1	0	2018	2037	2037	1571	3	1895	1000	1000	1000	2037	2037	1	1	1001	1000	0	0	73	0	1	16	1	1	1786	1000	2038	2038	2038	2038	2038
1004	2037	15	103	1686	25	1000	1000	1000	264521	0	0	2018	2037	2037	1571	3	1895	1000	1000	1000	2037	2037	1	1	1001	1000	0	0	73	0	1	16	1	1	1786	1000	2038	2038	2038	2038	2038
1004	2037	15	61	1686	25	1000	1000	1000	264521	0	0	2018	2037	2037	1571	3	1895	1000	1000	1000	2037	2037	1	1	1001	1000	0	0	73	0	1	16	1	1	1786	1000	2038	2038	2038	2038	2038
1004	2037	15	61	1686	25	1000	1000	1000	264521	0	5	2018	2037	2037	1571	3	1895	1000	1000	1000	2037	2037	1	1	1001	1000	0	0	73	0	1	16	1	1	1786	1000	2038	2038	2038	2038	2038
1004	2037	15	61	1686	25	1000	1000	1000	264521	0	0	2018	2037	2037	1571	3	1895	1000	1000	1000	2037	2037	1	1	1001	1000	0	0	73	0	1	16	1	1	1786	1000	2038	2038	2038	2038	2038
1004	2037	16	61	1686	25	1000	1000	1000	264521	0	5	2018	2037	2037	1571	3	1895	1000	1000	1000	2037	2037	1	1	1001	1000	0	0	73	0	1	16	1	1	1786	1000	2038	2038	2038	2038	2038
1004	2037	16	61	1686	25	1000	1000	1000	264521	0	0	2018	2037	2037	1571	3	1895	1000	1000	1000	2037	2037	1	1	1001	1000	0	0	73	0	1	16	1	1	1786	1000	2038	2038	2038	2038	2038

Test 2: Latency 1->2

Code:

  sqshl v0.16b, v0.16b, #3

Initialization

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

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 2.0037

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	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	20037	150	189	61	19686	25	10100	100	10000	100	10000	500	2847521	1	20018	20037	20037	18421	3	18745	10100	200	10000	200	10000	20037	20037	1	1	10201	100	99	100	100	10000	100	0	0	0	710	2	16	1	1	19791	0	10000	100	20038	20038	20038	20038	20038
10204	20037	150	0	61	19686	25	10100	100	10000	100	10000	500	2847521	1	20018	20037	20037	18421	3	18745	10100	200	10000	208	10000	20037	20037	1	1	10201	100	99	100	100	10000	100	0	0	0	710	1	16	1	1	19791	0	10000	100	20038	20038	20038	20038	20038
10204	20037	150	0	61	19686	25	10100	100	10000	100	10000	500	2847521	0	20018	20037	20037	18421	3	18745	10100	200	10000	200	10000	20037	20037	1	1	10201	100	99	100	100	10000	100	0	0	0	710	1	16	1	1	19791	0	10000	100	20038	20038	20038	20038	20038
10204	20037	150	21	61	19686	25	10100	100	10000	100	10000	500	2847521	1	20018	20037	20037	18421	3	18745	10100	200	10000	200	10000	20037	20037	1	1	10201	100	99	100	100	10000	100	0	0	0	710	1	16	1	1	19791	0	10000	100	20038	20038	20038	20038	20038
10204	20037	150	0	61	19686	25	10100	100	10000	100	10000	500	2847521	1	20018	20037	20037	18421	3	18745	10100	200	10000	204	10000	20037	20037	1	1	10201	100	99	100	100	10000	100	0	0	0	710	1	16	1	1	19791	0	10000	100	20038	20038	20038	20038	20038
10204	20037	150	411	61	19686	25	10100	100	10000	100	10000	500	2847521	1	20018	20037	20037	18421	3	18745	10100	200	10000	200	10000	20037	20037	1	1	10201	100	99	100	100	10000	100	0	0	0	710	1	16	1	1	19791	0	10000	100	20038	20038	20038	20038	20038
10204	20037	150	447	61	19686	25	10100	100	10000	100	10000	500	2847521	1	20018	20037	20037	18421	3	18745	10740	200	10000	200	10000	20037	20037	1	1	10201	100	99	100	100	10000	100	0	0	0	710	1	16	2	1	19791	0	10000	100	20038	20038	20038	20038	20038
10204	20037	150	0	61	19686	25	10100	100	10000	100	10000	500	2847521	1	20018	20037	20037	18421	3	18745	10100	200	10000	200	10000	20037	20037	1	1	10201	100	99	100	100	10000	100	0	0	0	710	1	16	1	1	19791	0	10000	100	20038	20038	20038	20038	20038
10204	20037	150	18	89	19686	25	10100	100	10000	100	10000	500	2847521	1	20018	20037	20037	18421	3	18745	10100	200	10000	200	10000	20037	20037	1	1	10201	100	99	100	100	10000	100	0	0	0	710	1	16	1	1	19791	0	10000	100	20038	20038	20038	20038	20038
10204	20037	150	0	61	19686	25	10100	100	10000	100	10000	500	2847521	1	20018	20037	20037	18421	3	18745	10100	200	10000	200	10000	20037	20037	1	1	10201	100	99	100	100	10000	100	0	0	0	710	1	16	1	1	19791	0	10000	100	20038	20038	20038	20038	20038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

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

retire uop (01)	cycle (02)	03	mmu table walk data (08)	1e	3f	4e	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	60	69	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map int uop (7c)	map simd uop (7e)	map int uop inputs (7f)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst branch (8d)	inst branch taken (90)	inst branch cond (94)	inst int alu (97)	inst simd alu (9a)	9f	l1d cache writeback (a8)	ac	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10024	20037	150	0	0	61	19686	25	10010	10	10000	10	10000	50	2847521	0	20018	20037	20037	18443	3	18767	10010	20	10000	20	10000	20037	20037	1	1	10021	10	9	10	10	10000	10	0	0	640	5	16	6	5	19786	10000	10	20038	20038	20038	20038	20038
10024	20037	156	0	0	1268	19686	25	10010	10	10000	10	10000	50	2847521	0	20018	20037	20037	18443	3	18767	10010	20	10000	20	10000	20037	20037	1	1	10021	10	9	10	10	10000	10	0	0	640	7	16	7	6	19786	10000	10	20038	20038	20038	20038	20038
10024	20037	150	0	0	61	19686	25	10010	10	10000	10	10000	50	2847521	0	20018	20037	20225	18443	3	18767	10010	20	10000	20	10000	20037	20037	1	1	10021	10	9	10	10	10000	10	1	3	640	7	16	6	7	19786	10000	10	20038	20038	20038	20038	20038
10024	20037	150	0	0	61	19686	25	10010	10	10000	10	10000	50	2847521	1	20018	20037	20037	18443	3	18767	10010	20	10000	20	10000	20037	20037	1	1	10021	10	9	10	10	10000	10	0	0	640	6	16	6	6	19786	10000	10	20038	20038	20038	20038	20038
10024	20037	150	0	0	61	19686	25	10010	10	10000	10	10000	50	2847521	0	20018	20037	20037	18443	3	18767	10010	20	10000	20	10000	20037	20037	1	1	10021	10	9	10	10	10000	10	0	0	640	7	16	6	7	19786	10000	10	20038	20038	20038	20038	20038
10024	20037	150	0	0	61	19686	25	10010	10	10000	10	10000	50	2847521	0	20018	20037	20071	18443	3	18767	10010	20	10000	24	10000	20037	20037	1	1	10021	10	9	10	10	10000	10	0	0	640	6	16	6	6	19786	10000	10	20038	20038	20038	20038	20038
10024	20037	150	0	0	536	19686	25	10010	10	10000	10	10000	50	2847521	0	20018	20037	20037	18443	3	18767	10010	20	10000	20	10000	20037	20037	1	1	10021	10	9	10	10	10000	10	0	3	640	7	16	6	6	19786	10000	10	20038	20038	20038	20038	20038
10024	20037	150	0	0	224	19686	25	10010	10	10000	10	10000	50	2847521	0	20018	20037	20037	18443	3	18767	10010	20	10000	20	10000	20037	20037	1	1	10021	10	9	10	10	10000	10	0	0	640	6	16	6	6	19786	10000	10	20038	20038	20038	20038	20038
10024	20037	150	0	0	61	19686	25	10010	10	10000	10	10000	50	2847521	1	20018	20037	20037	18443	3	18767	10010	20	10000	20	10000	20037	20037	1	1	10021	10	9	10	10	10000	10	0	0	640	6	16	6	6	19786	10000	10	20038	20038	20038	20038	20038
10024	20037	150	0	0	61	19686	25	10010	10	10000	10	10000	50	2847521	1	20018	20037	20037	18443	3	18767	10010	20	10000	20	10000	20037	20037	1	1	10021	10	9	10	10	10000	10	0	0	640	7	16	6	5	19786	10000	10	20038	20038	20038	20038	20038

Test 3: throughput

Count: 8

Code:

  sqshl v0.16b, v8.16b, #3
  sqshl v1.16b, v8.16b, #3
  sqshl v2.16b, v8.16b, #3
  sqshl v3.16b, v8.16b, #3
  sqshl v4.16b, v8.16b, #3
  sqshl v5.16b, v8.16b, #3
  sqshl v6.16b, v8.16b, #3
  sqshl v7.16b, v8.16b, #3

Initialization

  movi v8.16b, 9

(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	mmu table walk data (08)	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 tlb miss (a1)	l1d cache writeback (a8)	ac	branch cond mispred nonspec (c5)	branch mispred nonspec (cb)	cd	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
80204	20048	150	0	15	0	29	25	80108	100	80008	100	80020	500	640132	0	20019	20038	20038	9977	6	9989	80223	200	80032	200	80032	20038	20038	1	1	80201	100	99	100	100	80000	100	0	0	0	1	1	1	5118	0	16	0	0	20035	80000	100	20039	20039	20039	20039	20039
80204	20038	150	0	0	0	71	25	80108	100	80008	100	80020	500	640132	0	20019	20038	20038	9977	6	9989	80120	200	80032	200	80032	20038	20038	1	1	80201	100	99	100	100	80000	100	2	0	0	1	1	1	5118	0	16	0	0	20035	80000	100	20039	20039	20039	20039	20039
80204	20038	150	0	0	0	29	25	80108	100	80008	100	80020	500	640952	0	20061	20038	20038	9977	6	9989	80120	200	80032	200	80032	20190	20038	1	1	80201	100	99	100	100	80000	100	0	0	0	1	1	1	5118	0	16	0	0	20035	80000	100	20039	20039	20039	20039	20039
80204	20038	150	0	168	0	29	25	80108	100	80008	100	80020	500	640132	0	20019	20250	20038	9977	6	9989	80120	200	80032	200	80032	20038	20038	1	1	80201	100	99	100	100	80000	100	0	0	0	1	1	1	5118	0	16	0	0	20035	80000	100	20039	20039	20039	20039	20039
80204	20038	150	0	0	0	29	25	80108	100	80008	100	80020	500	640132	0	20019	20038	20038	9977	6	9989	80120	200	80032	200	80032	20038	20048	1	1	80201	100	99	100	100	80000	100	0	0	0	1	1	1	5118	0	16	0	0	20035	80000	100	20039	20039	20039	20039	20039
80204	20038	150	0	0	0	3569	25	80108	100	80008	100	80020	500	640132	0	20019	20038	20038	9977	6	9989	80120	200	80032	200	80032	20038	20038	1	1	80201	100	99	100	100	80000	100	0	0	0	1	1	1	5118	0	16	0	0	20035	80000	100	20039	20039	20039	20039	20039
80204	20038	150	0	0	0	29	25	80108	100	80008	100	80020	500	640132	0	20019	20038	20038	9977	6	9989	80120	200	80032	200	80032	20038	20038	1	1	80201	100	99	100	100	80000	100	0	0	0	1	1	1	5118	0	16	0	0	20035	80000	100	20039	20039	20039	20039	20039
80204	20038	150	0	39	0	71	25	80108	100	80008	100	80020	500	640132	0	20019	20038	20038	9977	6	9989	80120	200	80032	200	80032	20038	20038	1	1	80201	100	99	100	100	80000	100	0	0	0	1	1	1	5118	0	16	0	0	20035	80000	100	20039	20039	20039	20039	20039
80204	20038	150	0	0	0	71	25	80108	100	80008	100	80020	500	640132	0	20019	20038	20038	9977	6	9989	80120	200	80032	200	80032	20038	20038	1	1	80201	100	99	100	100	80000	100	0	0	0	1	1	1	5118	0	16	0	0	20035	80000	100	20039	20039	20039	20039	20039
80204	20038	150	0	12	0	29	25	80108	100	80008	100	80020	500	640132	0	20019	20038	20038	9977	6	9989	80120	200	80032	200	80032	20038	20038	1	1	80201	100	99	100	100	80000	100	0	0	0	1	1	1	5118	0	16	0	0	20035	80000	100	20039	20039	20039	20039	20039

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	mmu table walk data (08)	l2 tlb miss data (0b)	18	19	1e	1f	3f	51	schedule uop (52)	schedule int uop (53)	schedule simd uop (54)	dispatch int uop (56)	dispatch simd uop (57)	int uops in schedulers (59)	ldst uops in schedulers (5b)	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	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
80024	20048	150	0	0	0	0	297	0	39	25	80010	10	80000	10	80000	50	640000	0	20019	20038	20038	9989	3	10011	80010	20	80000	20	80000	20038	20038	1	1	80021	10	9	10	10	80000	10	0	0	0	0	0	0	0	5020	1	16	1	1	20035	80000	10	20039	20039	20039	20039	20039
80024	20038	150	0	0	0	0	0	0	39	25	80010	10	80000	10	80000	50	640000	0	20019	20038	20038	9989	3	10011	80010	20	80000	20	80000	20038	20038	1	1	80021	10	9	10	10	80000	10	0	0	0	0	0	0	0	5020	1	16	1	1	20035	80000	10	20039	20039	20039	20039	20039
80024	20038	150	0	0	0	0	543	0	39	25	80010	10	80000	10	80000	50	640000	0	20019	20038	20038	9989	3	10011	80010	20	80000	20	80132	20038	20038	1	1	80021	10	9	10	10	80000	10	0	0	0	0	0	0	0	5020	1	26	1	1	20035	80000	10	20039	20039	20039	20039	20039
80024	20038	150	0	0	0	0	0	0	514	25	80010	10	80000	10	80000	50	640000	0	20019	20038	20038	9989	3	10011	80010	20	80000	20	80000	20038	20038	1	1	80021	10	9	10	10	80000	10	0	0	0	0	0	0	0	5020	3	54	6	6	20226	80000	10	20291	20241	20296	20295	20238
80024	20287	152	0	0	6	5	660	440	876	124	80477	10	80465	10	80197	50	643848	0	20213	20241	20339	10031	24	10118	80495	20	80387	20	80488	20291	20091	6	1	80021	10	9	10	10	80000	10	2	2	2	1	0	2348	0	5107	2	70	3	2	20235	80000	10	20039	20039	20039	20039	20039
80024	20038	150	0	0	0	0	0	0	39	25	80010	10	80000	10	80000	50	640000	0	20019	20038	20038	9989	3	10011	80010	20	80000	20	80000	20038	20038	1	1	80021	10	9	10	10	80000	10	0	0	0	0	0	0	0	5020	1	16	1	1	20035	80000	10	20039	20039	20039	20039	20091
80024	20038	150	0	0	0	0	45	0	91	25	80010	10	80000	10	80000	50	640000	0	20019	20038	20038	9989	3	10011	80010	20	80000	20	80000	20038	20038	1	1	80021	10	9	10	10	80000	10	0	0	0	0	0	2343	0	5020	1	16	1	1	20035	80000	10	20039	20039	20039	20039	20039
80024	20038	150	0	0	0	0	0	0	144	64	80197	10	80279	10	80098	50	640772	0	20135	20291	20281	10024	20	10146	80313	20	80489	20	80585	20333	20377	8	1	80021	10	9	10	10	80000	10	0	2	2	1	0	3753	4	5038	1	102	5	1	20350	80000	10	20291	20444	20389	20440	20439
80024	20438	153	0	0	8	8	1056	616	1494	159	80761	10	80660	10	80776	50	646144	0	20333	20436	20346	10050	42	10229	80789	20	80000	20	80000	20038	20038	1	1	80021	10	9	10	10	80000	10	0	0	0	1	2	3510	0	5020	1	16	1	1	20073	80000	10	20039	20292	20400	20337	20392
80024	20244	152	1	0	7	7	1026	440	1308	81	80850	10	80839	10	80780	50	646952	0	20332	20440	20493	10057	31	10253	80888	22	80681	20	80775	20480	20443	10	1	80021	10	9	10	10	80000	10	0	4	0	0	0	3733	2	5177	3	74	3	2	20345	80000	10	20039	20039	20039	20039	20039

SQSHL (immediate, vector, 16B)

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: throughput

100 unrolls and 100 iterations

1000 unrolls and 10 iterations