Firestorm: SQRSHRN (4S) measurements

Code:

  sqrshrn v0.4h, v0.4s, #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	09	l2 tlb miss data (0b)	18	19	1e	1f	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 tlb access (a0)	l1d tlb miss (a1)	ld unit uop (a6)	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	22	0	0	0	0	0	0	61	2547	25	1000	1000	1000	398160	3018	3037	3037	2414	3	2895	1000	1000	1000	3037	3037	1	1	1001	1000	0	0	0	0	0	73	1	16	1	1	2629	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	0	0	0	0	61	2547	25	1000	1000	1000	398160	3018	3037	3037	2414	3	2895	1000	1000	1000	3037	3037	1	1	1001	1000	0	0	0	0	0	73	1	16	1	1	2629	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	0	0	0	0	61	2547	25	1000	1000	1000	398160	3018	3037	3037	2414	3	2895	1000	1000	1000	3037	3037	1	1	1001	1000	0	0	0	0	0	73	1	16	1	1	2629	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	0	0	0	0	103	2547	25	1000	1000	1000	398160	3018	3037	3037	2413	3	2895	1000	1000	1000	3037	3037	1	1	1001	1000	0	0	0	0	0	73	1	16	2	2	2629	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	0	0	0	0	61	2547	25	1000	1000	1000	398160	3018	3037	3037	2414	3	2895	1000	1000	1000	3037	3037	1	1	1001	1000	0	0	0	0	0	73	1	16	2	2	2629	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	0	0	0	0	61	2547	25	1000	1000	1000	398160	3018	3037	3037	2414	3	2895	1150	1000	1000	3037	3037	1	1	1001	1000	0	0	0	0	0	73	1	16	1	1	2629	1000	3038	3038	3038	3038	3038
1004	3037	22	0	0	0	0	0	0	61	2547	25	1000	1000	1000	398160	3018	3037	3037	2414	3	2895	1000	1000	1000	3037	3037	1	1	1001	1000	0	0	0	0	0	73	1	16	1	1	2629	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	0	0	0	0	61	2547	25	1000	1000	1000	398160	3018	3037	3037	2414	3	2895	1000	1000	1000	3037	3037	1	1	1001	1000	0	0	0	0	0	73	1	16	1	1	2629	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	0	0	12	0	61	2547	25	1000	1000	1000	398160	3018	3037	3037	2414	3	2895	1000	1000	1000	3037	3037	1	1	1001	1000	0	0	0	0	0	73	1	16	1	1	2629	1000	3038	3038	3038	3038	3038
1004	3037	23	0	0	0	0	0	0	61	2547	25	1000	1000	1000	398160	3018	3037	3037	2414	3	2895	1000	1000	1000	3037	3037	1	1	1001	1000	0	0	0	0	0	94	1	16	1	1	2629	1000	3038	3038	3038	3038	3038

Test 2: Latency 1->2

Code:

  sqrshrn v0.4h, v0.4s, #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): 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 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)	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
10204	30037	233	0	0	0	0	0	0	0	0	0	61	29547	43	10100	100	10008	123	10000	500	4277160	0	30018	0	30037	30037	28264	3	28745	10100	200	10000	200	10000	30037	30037	1	1	10201	100	99	100	100	10000	100	2	0	0	0	0	0	0	710	1	16	1	1	29633	0	10000	100	30038	30038	31497	30038	30372
10204	30467	244	2	0	0	1	12	11	1191	176	0	138	29547	25	10100	100	10000	100	10000	500	4277160	0	30018	0	30037	30037	28264	3	28739	10116	200	10000	200	10000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	2	0	6	0	710	1	16	1	1	29633	0	10000	100	30038	30038	30038	30038	30038
10204	30037	241	0	0	1	0	0	0	0	0	0	61	29547	25	10100	100	10000	100	10000	500	4277160	0	30018	0	30037	30037	28264	3	28745	10100	200	10000	200	10000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	0	710	1	16	1	1	29633	0	10000	100	30134	30182	30038	30038	30038
10204	30037	241	0	0	0	0	0	0	0	0	0	61	29547	25	10125	125	10000	125	10000	626	4277160	0	30018	0	30037	30037	28264	3	28745	10100	200	10000	200	10000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	0	710	1	16	1	1	29669	0	10000	100	30038	30038	30038	30038	30038
10204	30037	241	0	0	0	0	0	0	117	0	1	61	29547	25	10100	100	10000	100	10000	500	4277160	0	30054	0	30037	30037	28264	3	28745	10100	200	10000	200	10000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	0	710	1	16	1	1	29633	0	10000	100	30038	30038	30038	30038	30038
10204	30037	233	0	0	0	0	0	0	0	0	0	61	29547	25	10100	100	10000	100	10000	500	4277160	0	30018	0	30037	30037	28264	3	28745	10100	200	10000	200	10000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	0	710	1	16	1	1	29633	0	10000	100	30038	30038	30038	30038	30038
10204	30037	232	0	0	0	0	0	0	0	0	0	61	29547	25	10100	100	10000	100	10000	500	4277160	0	30018	0	30037	30037	28264	3	28745	10100	200	10000	200	10000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	0	0	710	1	25	1	1	29633	0	10000	100	30038	30038	30038	30038	30038
10204	30037	233	0	0	0	0	0	0	144	0	0	61	29547	25	10100	100	10000	100	10000	500	4277160	1	30018	0	30037	30085	28264	3	28763	10100	200	10000	200	10000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	1	0	0	0	710	2	16	1	1	29703	6	10000	100	30038	30038	30038	30038	30038
10204	30037	233	0	0	1	0	0	0	0	0	0	61	29547	25	10100	125	10000	125	10000	500	4278512	0	30774	0	30852	31172	28271	3	28745	10100	200	10493	258	13809	30037	30085	1	1	10201	100	99	100	100	10000	100	0	0	0	0	2	5751	0	712	1	17	1	1	29633	0	10000	100	30085	30086	30038	30038	30038
10204	30037	233	0	1	0	0	0	0	12	0	0	61	29547	25	10100	125	10008	100	10000	500	4277160	0	30846	0	30086	30037	28264	3	28796	10100	200	10000	200	10000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	2858	2	710	1	16	1	1	29633	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	09	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)	st unit uop (a7)	l1d cache writeback (a8)	ac	c2	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10024	30037	224	0	0	0	0	0	61	29547	25	10010	10	10000	10	10000	50	4277160	1	30018	30037	30037	28286	3	28767	10611	20	10000	20	10000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	0	640	2	16	2	2	29629	10000	10	30038	30038	30038	30038	30273
10024	30037	225	0	0	0	21	0	103	29547	25	10010	10	10007	10	10000	50	4277160	1	30018	30037	30037	28286	3	28767	10010	20	10000	20	10000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	3	0	640	2	16	2	2	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	0	61	29547	80	10010	10	10000	10	10000	50	4277160	1	30018	30037	30037	28286	3	28767	10010	22	10000	20	10000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	3	4	640	2	16	2	2	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	48	0	61	29547	25	10010	10	10000	10	10000	50	4277160	1	30018	30037	30037	28286	3	28767	10010	20	10000	20	10000	30037	30179	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	12	0	640	2	16	2	2	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	0	61	29547	25	10010	10	10000	10	10000	50	4277160	1	30018	30037	30037	28286	3	28767	10010	20	10000	20	10000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	0	640	3	16	2	2	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	0	61	29547	25	10010	10	10000	10	10000	50	4277160	1	30018	30037	30037	28286	3	28767	10010	20	10000	20	10000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	0	0	640	2	16	2	2	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	0	61	29529	25	10010	10	10000	10	10000	50	4277160	1	30018	30037	30037	28286	3	28767	10010	20	10000	20	10000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	3	0	640	2	16	2	2	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	1	0	0	0	61	29547	25	10010	10	10000	10	10000	50	4277160	1	30018	30037	30037	28286	3	28767	10010	20	10000	20	10000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	126	0	640	2	16	2	2	29629	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	0	726	29547	25	10010	10	10000	10	10000	50	4277160	1	30018	30037	30037	28286	3	28767	10010	20	10000	20	10000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	90	0	640	2	16	2	2	29629	10000	10	30038	30038	30086	30038	30038
10024	30037	224	0	0	0	0	0	61	29547	25	10010	10	10000	10	10000	50	4277160	1	30018	30037	30037	28286	3	28767	10010	20	10000	20	10000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	0	18	0	640	2	16	2	2	29629	10000	10	30038	30038	30038	30038	30038

Test 3: throughput

Count: 8

Code:

  sqrshrn v0.4h, v8.4s, #3
  sqrshrn v1.4h, v8.4s, #3
  sqrshrn v2.4h, v8.4s, #3
  sqrshrn v3.4h, v8.4s, #3
  sqrshrn v4.4h, v8.4s, #3
  sqrshrn v5.4h, v8.4s, #3
  sqrshrn v6.4h, v8.4s, #3
  sqrshrn v7.4h, v8.4s, #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)	09	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)	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 tlb miss (a1)	ld unit uop (a6)	l1d cache writeback (a8)	a9	ac	c2	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	20059	150	0	0	0	0	0	0	30	25	80108	100	80008	100	80020	500	640132	0	20020	20039	20039	9977	0	6	9990	80120	200	80032	200	80032	20039	20039	1	1	80201	100	99	100	100	80000	100	0	0	0	0	0	0	1	1	1	5118	1	16	0	0	20036	80000	100	20040	20040	20040	20040	20040
80204	20039	150	0	0	0	0	0	0	30	25	80108	100	80008	100	80126	500	640132	0	20020	20039	20039	9977	0	6	9990	80120	200	80032	200	80032	20039	20039	1	1	80201	100	99	100	100	80000	100	0	0	0	0	0	0	1	1	1	5118	0	16	0	0	20036	80000	100	20040	20040	20040	20040	20040
80204	20039	150	0	0	0	0	0	0	30	25	80108	100	80008	100	80020	500	640132	1	20020	20039	20039	9977	0	6	9990	80120	200	80032	200	80032	20039	20039	1	1	80201	100	99	100	100	80000	100	0	0	0	0	0	0	1	1	1	5118	0	16	0	0	20036	80000	100	20040	20040	20040	20040	20040
80204	20039	150	0	0	0	0	0	0	30	25	80108	100	80008	100	80020	500	640132	0	20020	20039	20039	9977	0	6	9990	80120	200	80032	200	80032	20039	20039	1	1	80201	100	99	100	100	80000	100	0	0	1	0	0	0	1	1	1	5118	0	16	0	0	20036	80000	100	20040	20040	20040	20040	20040
80204	20039	150	0	0	0	0	0	0	30	25	80108	100	80008	100	80020	500	640132	0	20020	20039	20039	9977	0	6	9990	80120	200	80032	200	80032	20039	20039	1	1	80201	100	99	100	100	80000	100	0	0	0	0	0	0	1	1	1	5118	0	16	0	0	20036	80000	100	20040	20040	20040	20040	20040
80204	20039	150	0	0	0	0	0	0	30	25	80108	100	80008	100	80020	500	640132	0	20020	20039	20039	9977	0	6	9990	80120	200	80032	200	80032	20039	20039	1	1	80201	100	99	100	100	80000	100	0	0	0	0	123	0	1	1	1	5118	0	16	0	0	20036	80000	100	20040	20040	20040	20040	20040
80204	20039	150	0	0	0	1	147	0	30	25	80108	100	80008	100	80020	500	640132	0	20020	20039	20039	9977	0	6	9990	80120	200	80032	200	80032	20039	20039	1	1	80201	100	99	100	100	80000	100	0	0	0	0	0	0	1	1	1	5118	0	16	0	0	20036	80000	100	20040	20040	20040	20040	20040
80204	20039	150	0	0	0	0	0	0	30	25	80108	100	80008	100	80020	500	640132	0	20020	20039	20039	9977	0	6	9990	80120	200	80032	200	80032	20039	20039	1	1	80201	100	99	100	100	80000	100	0	0	0	0	0	0	1	1	1	5118	0	16	0	0	20036	80000	100	20040	20040	20040	20040	20040
80204	20039	150	0	0	0	0	0	0	30	25	80108	100	80008	100	80020	500	640132	0	20020	20039	20039	9977	0	6	9990	80120	200	80032	200	80032	20039	20039	1	1	80201	100	99	100	100	80000	100	0	0	0	0	0	0	1	1	1	5118	0	16	0	0	20036	80000	100	20040	20040	20040	20040	20040
80204	20039	150	0	0	0	0	0	0	30	25	80108	100	80008	100	80020	500	640132	0	20020	20039	20039	9977	0	6	9990	80120	200	80032	200	80032	20039	20039	1	1	80201	100	99	100	100	80000	100	0	0	48	0	0	0	1	1	1	5118	0	16	0	0	20036	80000	100	20040	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	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 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 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
80024	20051	150	0	40	25	80010	10	80000	10	80000	50	640000	0	20020	0	20039	20039	9996	3	10019	80010	20	80000	20	80000	20039	20039	1	1	80021	10	9	10	10	80000	10	1	0	0	5020	9	16	9	14	20036	80000	10	20040	20040	20040	20040	20040
80024	20039	150	0	40	25	80010	10	80000	10	80000	50	640000	0	20020	0	20039	20039	9996	3	10019	80010	20	80000	20	80000	20039	20039	1	1	80021	10	9	10	10	80000	10	0	36	0	5020	10	16	11	14	20036	80000	10	20040	20040	20040	20040	20040
80024	20039	150	0	40	25	80010	10	80000	10	80000	50	640000	0	20020	0	20039	20039	9996	3	10019	80010	20	80000	20	80000	20039	20039	1	1	80021	10	9	10	10	80000	10	0	0	0	5020	16	16	15	11	20036	80000	10	20040	20040	20040	20040	20040
80024	20039	150	0	40	25	80010	10	80000	10	80000	50	640000	0	20020	0	20039	20039	9996	3	10019	80010	20	80000	20	80000	20039	20039	1	1	80021	10	9	10	10	80000	10	0	81	0	5020	14	16	15	15	20036	80000	10	20040	20040	20040	20040	20040
80024	20039	150	0	40	25	80010	10	80000	10	80000	50	640000	0	20020	0	20039	20039	9996	3	10019	80010	20	80000	20	80000	20039	20039	1	1	80021	10	9	10	10	80000	10	0	0	0	5020	13	16	13	16	20036	80000	10	20040	20090	20090	20040	20091
80024	20039	150	0	2721	25	80010	10	80000	10	80000	50	640000	0	20020	0	20039	20039	9996	3	10019	80010	20	80000	20	80000	20039	20039	2	1	80021	10	9	10	10	80000	10	0	0	0	5020	15	16	13	13	20036	80000	10	20040	20040	20040	20040	20040
80024	20039	150	0	40	25	80010	10	80000	10	80000	50	640000	1	20020	0	20039	20039	9996	3	10019	80010	20	80000	20	80000	20039	20039	1	1	80021	10	9	10	10	80000	10	0	0	0	5020	11	16	13	16	20036	80000	10	20040	20040	20091	20040	20040
80024	20039	150	0	40	25	80010	10	80000	10	80000	50	640000	1	20020	0	20039	20039	9996	3	10019	80010	20	80000	20	80000	20039	20039	1	1	80021	10	9	10	10	80000	10	0	0	0	5020	10	16	16	16	20036	80000	10	20040	20040	20040	20040	20040
80024	20039	150	0	705	25	80010	10	80000	10	80000	50	640000	0	20020	0	20039	20039	9996	3	10019	80010	20	80000	20	80000	20039	20039	1	1	80021	10	9	10	10	80000	10	0	0	0	5020	14	16	11	15	20036	80000	10	20040	20040	20040	20040	20040
80024	20039	150	0	40	25	80010	10	80000	10	80000	50	640000	0	20020	0	20039	20039	9996	3	10019	80010	20	80000	20	80000	20039	20039	1	1	80021	10	9	10	10	80000	10	0	0	0	5020	15	16	15	12	20036	80000	10	20040	20040	20040	20040	20040

SQRSHRN (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: throughput

100 unrolls and 100 iterations

1000 unrolls and 10 iterations