Firestorm: UQXTN (S) measurements

Code:

  uqxtn h0, s0

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	1e	3f	4e	51	schedule uop (52)	schedule simd uop (54)	dispatch simd uop (57)	ldst uops in schedulers (5b)	60	69	6d	6e	map stall dispatch (70)	map rewind (75)	map stall (76)	dispatch uop (78)	map simd uop (7e)	map simd uop inputs (81)	82	83	flush restart other nonspec (84)	85	inst all (8c)	inst simd alu (9a)	l1d cache writeback (a8)	ac	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	f5	f6	f7	f8	fd
1004	3037	22	0	61	2547	25	1000	1000	1000	398160	0	3018	3037	3037	2415	3	2895	1000	1000	1000	3037	3037	1	1	1001	1000	0	3	73	1	16	1	1	2629	1000	3038	3038	3038	3038	3038
1004	3037	22	0	61	2547	25	1000	1000	1000	398160	0	3018	3037	3037	2414	3	2895	1000	1000	1000	3037	3037	1	1	1001	1000	0	0	73	1	16	1	1	2629	1000	3038	3038	3038	3038	3038
1004	3037	23	0	82	2547	25	1000	1000	1000	398160	0	3018	3037	3037	2414	3	2895	1000	1000	1000	3037	3037	1	1	1001	1000	0	0	73	1	16	1	1	2629	1000	3038	3038	3038	3038	3038
1004	3037	23	0	61	2547	25	1000	1000	1000	398160	0	3018	3037	3037	2414	3	2895	1000	1000	1000	3037	3037	1	1	1001	1000	0	0	73	1	16	1	1	2629	1000	3038	3038	3038	3038	3038
1004	3037	23	0	312	2547	25	1000	1000	1000	398160	0	3018	3037	3037	2414	3	2895	1000	1000	1000	3037	3037	1	1	1001	1000	0	0	73	1	16	1	1	2629	1000	3038	3038	3038	3038	3038
1004	3037	23	0	61	2547	25	1000	1000	1000	398160	0	3018	3037	3037	2414	3	2895	1000	1000	1000	3037	3037	1	1	1001	1000	0	0	73	1	16	1	1	2629	1000	3038	3038	3038	3038	3038
1004	3037	23	0	61	2547	25	1000	1000	1000	398160	0	3018	3037	3037	2414	3	2895	1000	1000	1000	3037	3037	1	1	1001	1000	0	0	73	1	16	1	1	2629	1000	3038	3038	3038	3038	3038
1004	3037	22	0	390	2547	25	1000	1000	1000	398160	0	3018	3037	3037	2414	3	2895	1000	1000	1000	3037	3037	1	1	1001	1000	0	0	73	1	16	1	1	2629	1000	3038	3038	3038	3038	3038
1004	3037	23	0	61	2547	25	1000	1000	1000	398160	0	3018	3037	3037	2414	3	2895	1000	1000	1000	3037	3037	1	1	1001	1000	6	0	73	1	16	1	1	2629	1000	3038	3038	3038	3038	3038
1004	3037	23	0	61	2547	25	1000	1000	1000	398160	0	3018	3037	3037	2414	3	2895	1000	1000	1000	3037	3037	1	1	1001	1000	0	0	73	1	16	1	1	2629	1000	3038	3038	3038	3038	3038

Test 2: Latency 1->2

Code:

  uqxtn h0, s0

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)	09	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	st unit uop (a7)	l1d cache writeback (a8)	a9	ac	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	0	0	0	0	0	189	29547	25	10100	100	10000	100	10000	500	4277160	0	30018	30181	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	710	1	16	1	1	29633	0	10000	100	30038	30038	30038	30038	30038
10204	30084	226	0	0	0	0	0	69	0	1455	29547	25	10100	100	10000	100	10000	500	4277160	0	30018	30037	30037	28264	3	28745	10100	200	10000	200	10000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	5	0	0	0	710	1	16	1	1	29633	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	0	0	61	29547	86	10100	110	10000	103	10000	500	4277160	0	30018	30037	30037	28264	3	28745	10100	200	10000	200	10000	30037	30037	1	1	10201	100	99	100	100	10000	100	1	2	0	0	0	710	1	16	1	1	29633	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	0	0	61	29547	80	10100	100	10000	100	10000	500	4277160	0	30018	30037	30037	28264	3	28745	10100	200	10000	200	10000	30037	30037	5	1	10201	100	99	100	100	10000	100	0	0	0	0	0	710	1	16	1	1	29633	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	0	0	61	29547	25	10100	100	10000	100	10000	500	4277160	0	30018	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	710	1	16	4	2	29633	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	0	0	103	29547	25	10100	100	10000	100	10000	500	4277160	0	30018	30037	30037	28264	3	28745	10100	200	10000	200	10000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	1	0	0	0	710	1	16	1	1	29633	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	0	0	61	29547	25	10100	100	10000	100	10000	500	4277160	1	30018	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	710	1	16	1	1	29633	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	0	0	103	29547	100	10100	100	10000	100	10000	500	4277160	0	30018	30037	30037	28264	3	28745	10100	200	10000	200	10000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	3	0	0	0	710	1	16	1	1	29633	0	10000	100	30038	30038	30038	30038	30038
10204	30037	225	0	0	0	0	0	0	0	61	29547	25	10100	100	10000	100	10000	500	4277160	0	30018	30037	30037	28264	3	28745	10100	200	10000	200	10000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	1	0	0	0	710	1	16	1	1	29633	0	10000	100	30038	30038	30038	30038	30038
10204	30037	224	0	0	0	0	0	0	0	61	29547	25	10100	100	10000	100	10000	500	4277160	0	30018	30037	30131	28264	3	28745	10100	200	10000	200	10000	30037	30037	1	1	10201	100	99	100	100	10000	100	0	0	0	0	0	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	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)	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)	st unit uop (a7)	l1d cache writeback (a8)	a9	ac	c2	branch mispred nonspec (cb)	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	0	0	0	0	0	61	29547	25	10010	10	10000	10	10000	50	4277160	30018	30037	30037	28286	0	26	28767	10010	20	10000	20	10000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	3	0	9	0	0	0	640	2	16	2	2	29629	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	0	0	61	29547	25	10010	10	10000	10	10000	50	4277160	30018	30037	30037	28286	0	3	28767	10010	20	10000	20	10000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	3	0	0	0	640	2	16	2	2	29629	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	0	0	61	29547	25	10010	10	10000	10	10000	50	4277160	30018	30037	30037	28286	0	3	28767	10010	20	10000	20	10000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	5	0	0	0	0	0	640	2	16	2	2	29629	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	0	0	61	29547	25	10010	10	10000	10	10000	50	4277160	30018	30037	30037	28286	0	3	28767	10010	20	10000	20	10000	30037	30037	1	1	10021	10	9	10	10	10000	10	0	0	0	0	15	0	0	0	640	2	16	4	3	29901	1	10000	10	30413	30416	30170	30417	30416
10024	30418	228	1	1	9	8	399	792	5180	29547	25	10010	10	10000	10	10000	50	4278512	30018	30037	30037	28312	0	42	28915	11364	24	11141	20	11306	30177	30037	1	1	10021	10	9	10	10	10000	10	0	0	45	2	24813	0	0	0	640	2	16	2	2	29629	0	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	0	0	3905	29484	177	10079	16	10056	14	11050	67	4285272	30306	30464	30179	28317	0	34	28917	11063	22	11303	24	10652	30413	30418	9	1	10021	10	9	10	10	10000	10	2	1	39	0	22318	2	1	0	857	7	72	2	3	29878	3	10000	10	30038	30038	30038	30038	30038
10024	30037	225	0	0	0	0	0	0	5834	29475	174	10079	15	10056	14	11350	60	4289328	30306	30458	30415	28298	0	44	28916	11367	24	11354	24	11310	30461	30272	9	1	10021	10	9	10	10	10000	10	0	0	2	0	13605	4	0	0	849	3	97	3	5	29919	3	10000	10	30372	30453	30274	30514	30464
10024	30320	228	1	0	9	3	807	880	61	29547	25	10010	10	10000	10	10000	50	4278512	30342	30417	30321	28313	0	10	28915	11214	24	11017	20	10972	30319	30368	6	1	10021	10	9	10	10	10000	10	0	0	1	0	0	2	0	0	829	2	72	3	2	29834	2	10000	10	30419	30414	30274	30465	30464
10024	30321	228	1	0	10	5	0	0	61	29547	25	10010	10	10008	12	10000	50	4277160	30270	30319	30367	28318	0	17	28916	10915	20	10325	20	11144	30178	30416	6	1	10021	10	9	10	10	10000	10	0	0	2	0	0	0	0	0	640	4	73	4	3	29736	2	10000	10	30466	30180	30463	30180	30180
10024	30452	227	0	0	0	0	0	0	61	29547	25	10026	12	10064	13	10750	81	4281216	30198	30370	30180	28315	0	11	28954	10614	20	10989	20	10978	30227	30509	8	1	10021	10	9	10	10	10000	10	0	0	1	0	0	0	0	0	640	2	16	2	2	29629	0	10000	10	30038	30038	30038	30038	30038

Test 3: throughput

Count: 8

Code:

  uqxtn h0, s8
  uqxtn h1, s8
  uqxtn h2, s8
  uqxtn h3, s8
  uqxtn h4, s8
  uqxtn h5, s8
  uqxtn h6, s8
  uqxtn h7, s8

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	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)	st unit uop (a7)	l1d cache writeback (a8)	ac	branch cond mispred nonspec (c5)	branch mispred nonspec (cb)	cd	cf	d5	map dispatch bubble (d6)	fetch restart (de)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
80204	20058	150	0	30	25	80108	100	80008	100	80020	500	640132	1	20020	20039	20039	9977	6	9990	80120	200	80032	200	80142	20039	20039	1	1	80201	100	99	100	100	80000	100	0	0	0	0	1	1	1	5118	0	16	0	20036	80000	100	20040	20040	20040	20040	20040
80204	20039	150	0	30	25	80108	100	80008	100	80020	500	640132	1	20020	20039	20039	9977	6	9990	80120	200	80032	200	80032	20039	20039	1	1	80201	100	99	100	100	80000	100	0	0	0	0	1	1	1	5118	0	16	0	20036	80000	100	20040	20040	20040	20040	20040
80204	20039	150	0	30	25	80108	100	80008	100	80020	500	640132	1	20020	20039	20039	9977	6	9990	80120	200	80032	200	80032	20039	20039	1	1	80201	100	99	100	100	80000	100	0	0	0	0	1	1	1	5118	0	16	0	20036	80000	100	20040	20040	20040	20040	20040
80204	20039	150	0	30	25	80108	100	80008	100	80020	500	640132	1	20020	20039	20039	9977	6	9990	80120	200	80032	200	80032	20039	20039	1	1	80201	100	99	100	100	80000	100	0	0	1	0	1	1	1	5118	0	16	0	20036	80000	100	20040	20040	20040	20040	20040
80204	20039	150	0	30	25	80108	100	80008	100	80020	500	640132	0	20020	20039	20039	9977	6	9990	80120	200	80032	200	80032	20039	20039	1	1	80201	100	99	100	100	80000	100	0	0	1	3	1	1	1	5118	0	16	0	20036	80000	100	20040	20040	20040	20040	20040
80204	20039	150	0	30	25	80108	100	80008	100	80020	500	640132	0	20020	20039	20039	9977	6	9990	80120	200	80032	200	80032	20039	20039	1	1	80201	100	99	100	100	80000	100	0	0	0	0	1	1	1	5118	0	16	0	20036	80000	100	20040	20040	20040	20040	20040
80204	20039	150	0	30	25	80108	100	80008	100	80020	500	640132	1	20020	20039	20039	9977	6	9990	80120	200	80032	200	80032	20039	20039	1	1	80201	100	99	100	100	80000	100	0	0	0	0	1	1	1	5118	0	16	0	20036	80000	100	20040	20040	20040	20040	20040
80204	20039	150	0	30	25	80108	100	80008	100	80020	500	640132	1	20020	20039	20039	9977	6	9990	80120	200	80032	200	80032	20039	20039	1	1	80201	100	99	100	100	80000	100	0	0	0	0	1	1	1	5118	0	16	0	20036	80000	100	20040	20040	20040	20040	20040
80204	20039	150	0	30	25	80108	100	80008	100	80020	500	640132	1	20020	20039	20039	9977	6	9990	80120	200	80032	200	80032	20039	20039	1	1	80201	100	99	100	100	80000	100	0	0	0	0	1	1	1	5118	0	16	0	20036	80000	100	20040	20040	20040	20040	20040
80204	20039	150	0	30	25	80108	100	80008	100	80020	500	640132	0	20020	20039	20039	9977	6	9990	80120	200	80032	200	80032	20039	20039	1	1	80201	100	99	100	100	80000	100	0	0	1	9	1	1	1	5118	0	16	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)	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)	ac	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	20020	20039	20039	9996	3	10019	80010	20	80000	20	80000	20039	20039	1	1	80021	10	9	10	10	80000	10	0	4	9	5020	9	16	7	10	20036	80000	10	20040	20040	20040	20040	20040
80024	20039	150	0	40	25	80010	10	80000	10	80000	50	640000	20020	20039	20039	9996	3	10019	80010	20	80000	20	80000	20039	20039	1	1	80021	10	9	10	10	80000	10	0	57	0	5020	10	16	10	7	20036	80000	10	20040	20040	20040	20040	20040
80024	20039	150	0	40	25	80010	10	80000	10	80000	50	640000	20020	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	7	10	20036	80000	10	20040	20040	20040	20040	20040
80024	20039	150	0	40	25	80010	10	80097	10	80000	50	640000	20020	20039	20039	9996	3	10019	80010	20	80107	20	80000	20039	20039	1	1	80021	10	9	10	10	80000	10	0	22	180	5020	8	16	7	10	20036	80000	10	20040	20040	20040	20040	20040
80024	20039	150	0	40	25	80010	10	80000	10	80000	50	640000	20020	20039	20039	9996	3	10019	80010	20	80000	20	80000	20039	20039	1	1	80021	10	9	10	10	80000	10	0	24	0	5020	7	16	10	7	20036	80000	10	20040	20040	20040	20040	20040
80024	20039	150	0	40	25	80010	10	80000	10	80000	50	640000	20020	20039	20039	9996	3	10019	80010	20	80000	20	80000	20039	20039	1	1	80021	10	9	10	10	80000	10	0	1	3	5020	7	16	8	10	20036	80000	10	20040	20040	20040	20040	20040
80024	20039	150	0	40	25	80010	10	80000	10	80000	50	640000	20020	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	7	16	7	10	20036	80000	10	20040	20040	20040	20040	20040
80024	20039	150	0	40	25	80010	10	80000	10	80000	50	640000	20020	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	12	16	12	9	20036	80000	10	20040	20040	20040	20040	20040
80024	20039	150	0	40	25	80010	10	80291	10	80000	50	640000	20020	20039	20039	9996	3	10019	80010	20	80000	20	80000	20039	20039	1	1	80021	10	9	10	10	80000	10	0	26	0	5020	12	16	12	12	20036	80000	10	20040	20040	20040	20040	20040
80024	20039	150	0	40	25	80010	10	80000	10	80000	50	640000	20020	20039	20039	9996	3	10019	80010	20	80000	20	80000	20039	20039	1	1	80021	10	9	10	10	80000	10	0	32	0	5020	10	16	12	12	20036	80000	10	20040	20040	20040	20040	20040

UQXTN (S)

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