Firestorm: USHR (vector, 2S) measurements

Code:

  ushr v0.2s, v0.2s, #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	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	2037	15	0	61	1686	25	1000	1000	1000	264521	2018	2037	2037	1571	3	1895	1000	1000	1000	2037	2037	1	1	1001	1000	1	0	73	1	16	1	1	1786	1000	2038	2038	2038	2038	2038
1004	2037	15	0	61	1686	25	1000	1000	1000	264521	2018	2037	2037	1571	3	1895	1000	1000	1000	2037	2037	1	1	1001	1000	14	0	73	1	16	1	1	1786	1000	2038	2038	2038	2038	2038
1004	2037	15	0	61	1686	25	1000	1000	1000	264521	2018	2037	2037	1571	3	1895	1000	1000	1000	2037	2037	1	1	1001	1000	1	3	73	1	16	1	1	1786	1000	2038	2038	2038	2038	2038
1004	2037	16	0	61	1686	25	1000	1000	1000	264521	2018	2037	2037	1571	3	1895	1000	1000	1000	2037	2037	1	1	1001	1000	0	0	73	1	16	1	1	1786	1000	2038	2038	2038	2038	2038
1004	2037	16	0	61	1686	25	1000	1000	1000	264521	2018	2037	2037	1571	3	1895	1000	1000	1000	2037	2037	1	1	1001	1000	0	0	73	1	16	1	1	1786	1000	2038	2038	2038	2038	2038
1004	2037	16	0	61	1686	25	1000	1000	1000	264521	2018	2037	2037	1571	3	1895	1000	1000	1000	2037	2037	1	1	1001	1000	0	0	73	1	16	1	1	1786	1000	2038	2038	2038	2038	2038
1004	2037	16	12	104	1686	25	1000	1000	1000	264521	2018	2037	2037	1571	3	1895	1000	1000	1000	2037	2037	1	1	1001	1000	0	3	73	1	16	1	1	1786	1000	2038	2038	2038	2038	2038
1004	2037	16	0	103	1686	25	1000	1000	1000	264521	2018	2037	2037	1571	3	1895	1000	1000	1000	2037	2037	1	1	1001	1000	1	0	73	1	16	1	1	1786	1000	2038	2038	2038	2038	2038
1004	2037	16	0	82	1686	25	1000	1000	1000	264521	2018	2037	2037	1571	8	1914	1000	1000	1000	2037	2037	1	1	1001	1000	0	0	73	1	16	1	1	1786	1000	2038	2038	2038	2038	2038
1004	2037	16	0	61	1686	25	1000	1000	1000	264521	2018	2037	2037	1571	3	1895	1000	1000	1000	2037	2037	1	1	1001	1000	0	0	73	1	16	1	1	1786	1000	2038	2038	2038	2038	2038

Test 2: Latency 1->2

Code:

  ushr v0.2s, v0.2s, #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)	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
10204	20037	155	12	61	19686	25	10100	100	10000	100	10000	500	2847521	1	20018	20037	20037	18421	3	18766	10100	200	10000	200	10000	20037	20037	1	1	10201	100	99	100	100	10000	100	0	710	1	16	1	1	19791	10000	100	20038	20038	20038	20038	20038
10204	20037	156	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	710	1	16	1	1	19791	10000	100	20038	20038	20038	20038	20038
10204	20037	155	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	710	1	16	1	1	19791	10000	100	20038	20038	20038	20038	20038
10204	20037	156	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	710	1	16	1	1	19791	10000	100	20038	20038	20038	20038	20038
10204	20037	155	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	710	1	16	1	1	19791	10000	100	20038	20038	20038	20038	20038
10204	20037	155	0	61	19675	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	710	1	16	1	1	19791	10000	100	20038	20038	20038	20038	20038
10204	20037	155	0	536	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	1	710	1	16	1	1	19791	10000	100	20038	20038	20038	20038	20038
10204	20037	155	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	710	1	16	1	1	19791	10000	100	20038	20038	20038	20038	20038
10204	20037	155	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	710	1	16	1	1	19791	10000	100	20038	20038	20038	20038	20038
10204	20037	155	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	46	710	1	16	1	1	19791	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	branch cond mispred nonspec (c5)	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	? int output thing (e9)	eb	? 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	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	0	640	2	16	2	2	19786	0	0	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	2	0	0	640	2	16	2	2	19786	0	0	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	0	640	2	16	2	2	19786	0	0	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	0	640	2	16	2	2	19786	0	0	10000	10	20038	20038	20038	20038	20038
10024	20037	150	0	0	408	19684	44	10023	12	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	12	0	640	2	24	2	2	19786	0	0	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	44	3	0	640	2	16	2	2	19786	0	0	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	1	3	0	640	2	16	2	2	19786	0	0	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	20	6	0	640	2	16	2	2	19786	0	0	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	1	6	0	640	2	16	2	2	19786	0	0	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	0	640	2	24	2	2	19786	0	0	10000	10	20038	20038	20038	20038	20038

Test 3: throughput

Count: 8

Code:

  ushr v0.2s, v8.2s, #3
  ushr v1.2s, v8.2s, #3
  ushr v2.2s, v8.2s, #3
  ushr v3.2s, v8.2s, #3
  ushr v4.2s, v8.2s, #3
  ushr v5.2s, v8.2s, #3
  ushr v6.2s, v8.2s, #3
  ushr v7.2s, v8.2s, #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)	0f	18	19	1e	1f	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	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)	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	20060	155	0	0	0	0	0	0	0	29	25	80108	100	80008	100	80020	500	640132	0	20019	0	20038	20038	9977	6	9989	80120	200	80032	200	80032	20038	20038	1	1	80201	100	99	100	100	80000	100	0	0	0	0	0	1	1	1	5118	0	16	0	0	20035	80000	100	20039	20039	20039	20039	20039
80204	20038	155	0	0	0	0	0	0	0	29	25	80108	100	80008	100	80020	500	640132	0	20019	0	20038	20038	9977	6	9989	80120	200	80032	200	80032	20038	20038	1	1	80201	100	99	100	100	80000	100	0	0	0	0	0	1	1	1	5118	0	16	0	0	20035	80000	100	20039	20039	20039	20039	20039
80204	20038	156	0	0	0	0	0	0	0	29	25	80108	100	80008	100	80020	500	640132	0	20019	0	20038	20038	9977	6	9989	80120	200	80032	200	80032	20038	20038	1	1	80201	100	99	100	100	80000	100	0	0	0	3	0	1	1	1	5118	0	16	0	0	20035	80000	100	20039	20039	20039	20039	20039
80204	20038	155	0	0	0	0	0	0	0	29	25	80108	100	80008	100	80020	500	640132	0	20019	0	20038	20038	9977	6	9989	80120	200	80032	200	80032	20038	20038	1	1	80201	100	99	100	100	80000	100	0	0	0	0	0	1	1	1	5118	0	16	0	0	20035	80000	100	20039	20039	20039	20039	20039
80204	20038	155	0	0	0	0	0	0	0	29	25	80108	100	80008	100	80020	500	640132	0	20019	0	20038	20038	9977	6	9989	80120	200	80032	200	80032	20038	20038	1	1	80201	100	99	100	100	80000	100	0	0	0	0	0	1	1	1	5118	0	16	0	0	20035	80000	100	20039	20039	20039	20039	20039
80204	20038	155	0	0	0	0	0	0	0	29	25	80108	100	80008	100	80020	500	640132	0	20019	0	20038	20038	9977	6	9989	80120	200	80032	200	80032	20038	20038	1	1	80201	100	99	100	100	80000	100	0	0	0	0	0	1	1	1	5118	0	16	0	0	20035	80000	100	20039	20039	20039	20039	20039
80204	20038	155	0	5	0	0	0	0	0	29	25	80108	100	80008	100	80020	500	640132	0	20019	0	20087	20038	9977	14	9989	80512	200	80032	200	80032	20038	20038	1	1	80201	100	99	100	100	80000	100	0	0	0	0	0	1	1	1	5118	0	16	0	0	20035	80000	100	20039	20039	20039	20039	20039
80204	20038	155	0	0	0	0	0	0	0	29	25	80108	100	80008	100	80020	500	640132	0	20019	0	20038	20038	9977	6	9989	80120	200	80032	200	80032	20038	20038	1	1	80201	100	99	100	100	80000	100	0	0	0	0	0	1	1	1	5118	0	29	0	0	20035	80000	100	20039	20039	20039	20039	20039
80204	20038	155	1	0	0	0	264	88	0	29	92	80204	102	80104	100	80222	500	641720	0	20081	0	20100	20102	9995	12	10013	80226	200	80135	200	80135	20103	20092	3	1	80201	100	99	100	100	80000	100	4	0	0	0	1040	1	1	1	5136	0	16	0	0	20333	80000	100	20152	20145	20136	20102	20102
80204	20092	156	1	0	2	2	132	112	1	567	25	80108	100	80008	100	80215	500	640132	0	20019	0	20038	20038	9977	11	10015	80224	200	80137	200	80135	20090	20038	1	1	80201	100	99	100	100	80000	100	0	0	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	l1i tlb fill (04)	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)	5f	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	cd	cf	d5	map dispatch bubble (d6)	dd	fetch restart (de)	e0	ea	? simd retires (ee)	? int retires (ef)	f5	f6	f7	f8	fd
80024	20051	155	1	0	367	25	80010	10	80000	10	80000	50	640000	0	0	20019	20038	20038	9996	7	3	10018	80010	20	80000	20	80000	20038	20038	1	1	80021	10	9	10	10	80000	10	0	0	0	5020	28	16	28	26	20035	0	80000	10	20039	20039	20039	20039	20039
80024	20038	155	0	0	39	25	80010	10	80000	10	80000	50	640000	0	0	20019	20038	20038	9996	0	3	10018	80010	20	80000	20	80000	20038	20038	1	1	80021	10	9	10	10	80000	10	0	0	0	5020	26	16	29	27	20035	0	80000	10	20039	20039	20039	20039	20039
80024	20038	155	0	0	39	25	80010	10	80000	10	80000	50	640000	0	0	20019	20038	20038	9996	0	3	10018	80010	20	80000	20	80000	20038	20038	1	1	80021	10	9	10	10	80000	10	1	0	0	5020	26	16	27	27	20035	0	80000	10	20039	20039	20039	20039	20039
80024	20038	155	0	0	39	25	80010	10	80000	10	80000	50	640000	0	0	20019	20038	20038	9996	0	3	10018	80010	20	80000	20	80000	20038	20038	1	1	80021	10	9	10	10	80000	10	0	0	0	5020	29	16	28	31	20035	0	80000	10	20039	20039	20039	20039	20039
80024	20038	155	0	0	49	25	80010	10	80000	10	80000	50	640000	0	0	20019	20038	20038	9996	0	3	10018	80010	20	80000	20	80000	20038	20038	1	1	80021	10	9	10	10	80000	10	0	0	0	5020	29	16	15	27	20035	0	80000	10	20039	20039	20039	20039	20039
80024	20038	156	0	12	39	25	80010	10	80000	10	80000	50	640000	0	0	20019	20038	20038	9996	0	3	10018	80010	20	80000	20	80000	20038	20038	1	1	80021	10	9	10	10	80000	10	0	0	0	5020	19	16	26	20	20035	0	80000	10	20039	20039	20039	20039	20039
80024	20038	156	0	0	659	25	80010	10	80000	10	80000	50	640000	0	0	20019	20038	20038	9996	0	3	10018	80010	20	80000	20	80000	20038	20038	1	1	80021	10	9	10	10	80000	10	0	0	0	5020	13	16	26	20	20035	0	80000	10	20039	20039	20039	20039	20039
80024	20038	155	0	0	39	25	80010	10	80000	10	80000	50	640000	0	0	20019	20038	20038	9996	0	3	10018	80010	20	80000	20	80000	20038	20038	1	1	80021	10	9	10	10	80000	10	0	0	0	5020	28	16	20	27	20035	0	80000	10	20039	20039	20039	20039	20039
80024	20038	155	0	0	39	25	80010	10	80000	10	80000	50	640000	0	0	20019	20038	20038	9996	0	3	10018	80010	20	80000	20	80000	20038	20038	1	1	80021	10	9	10	10	80000	10	0	0	0	5020	27	16	15	28	20035	0	80000	10	20039	20039	20039	20039	20039
80024	20038	155	0	0	39	25	80010	10	80000	10	80000	50	640000	0	0	20019	20038	20038	9996	0	3	10018	80010	20	80000	20	80000	20038	20038	1	1	80021	10	9	10	10	80000	10	0	0	0	5020	13	16	28	14	20035	0	80000	10	20039	20039	20039	20039	20039

USHR (vector, 2S)

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