Apple Microarchitecture Research by Dougall Johnson

M1/A14 P-core (Firestorm): Overview | Base Instructions | SIMD and FP Instructions
M1/A14 E-core (Icestorm):  Overview | Base Instructions | SIMD and FP Instructions

MOVI (vector, 4S, zero)

Test 1: uops

Code:

  movi v0.4s, #0

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 1.000

Issues: 0.000

Integer unit issues: 0.001

Load/store unit issues: 0.000

SIMD/FP unit issues: 0.000

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

retire uop (01)	cycle (02)	schedule uop (52)	schedule int uop (53)	? int output thing (e9)	? simd retires (ee)
1004	557	1	1	1	1000
1004	286	1	1	1	1000
1004	275	1	1	1	1000
1004	275	1	1	1	1000
1004	275	1	1	1	1000
1004	275	1	1	1	1000
1004	275	1	1	1	1000
1004	275	1	1	1	1000
1004	275	1	1	1	1000
1004	275	1	1	1	1000

Test 2: throughput

Count: 8

Code:

  movi v0.4s, #0
  movi v1.4s, #0
  movi v2.4s, #0
  movi v3.4s, #0
  movi v4.4s, #0
  movi v5.4s, #0
  movi v6.4s, #0
  movi v7.4s, #0

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2511

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

retire uop (01)	cycle (02)	schedule uop (52)	schedule int uop (53)	dispatch int uop (56)	int uops in schedulers (59)	dispatch uop (78)	map int uop (7c)	map int uop inputs (7f)	? int output thing (e9)	? simd retires (ee)	? int retires (ef)
80204	20318	101	101	100	300	100	200	200	1	80000	100
80204	20096	101	101	100	300	100	200	200	1	80000	100
80204	20086	101	101	100	300	100	200	200	1	80000	100
80204	20086	101	101	100	300	100	200	200	1	80000	100
80205	20120	101	101	100	300	100	200	200	1	80000	100
80204	20086	101	101	100	300	100	200	200	1	80000	100
80205	20125	101	101	100	300	100	200	200	1	80000	100
80204	20086	101	101	100	300	100	200	200	1	80000	100
80204	20086	101	101	100	300	100	200	200	1	80000	100
80204	20086	101	101	100	300	100	200	200	1	80000	100

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2507

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

retire uop (01)	cycle (02)	schedule uop (52)	schedule int uop (53)	dispatch int uop (56)	int uops in schedulers (59)	dispatch uop (78)	map int uop (7c)	map int uop inputs (7f)	? int output thing (e9)	? simd retires (ee)	? int retires (ef)
80024	22009	21	21	20	69	20	20	20	11	80000	10
80024	20170	21	21	20	65	20	20	20	11	80000	10
80024	20058	21	21	20	65	20	20	20	11	80000	10
80024	20058	21	21	20	65	20	20	20	11	80000	10
80024	20058	21	21	20	65	20	20	20	11	80000	10
80024	20067	21	21	20	65	20	20	20	11	80000	10
80024	20058	21	21	20	65	20	20	20	11	80000	10
80024	20058	21	21	20	65	20	20	20	11	80000	10
80024	20058	21	21	20	65	20	20	20	11	80000	10
80024	20058	21	21	20	65	20	20	20	11	80000	10