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

ST2 (single, B)

Test 1: uops

Code:

  st2 { v0.b, v1.b }[1], [x6]
  nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop ; nop
  mov x0, 0

(no loop instructions)

1000 unrolls and 1 iteration

Retires (minus 60 nops): 2.000

Issues: 2.000

Integer unit issues: 0.001

Load/store unit issues: 1.000

SIMD/FP unit issues: 1.000

retire uop (01)cycle (02)schedule uop (52)schedule int uop (53)schedule simd uop (54)schedule ldst uop (55)dispatch simd uop (57)dispatch ldst uop (58)simd uops in schedulers (5a)ldst uops in schedulers (5b)dispatch uop (78)map ldst uop (7d)map simd uop (7e)map ldst uop inputs (80)map simd uop inputs (81)? int output thing (e9)? ldst retires (ed)? simd retires (ee)
62006295862005110021002100210008751400020001000100020002000110001000
62004301702001110001000100010008751400020001000100020002000110001000
62004293332001110001000100010008751400020001000100020002000110001000
62004293742001110001000100010008751400020001000100020002000110001000
62004293612001110001000100010008751400020001000100020002000110001000
62004293342001110001000100010008751400020001000100020002000110001000
62004293102001110001000100010008751400020001000100020002000110001000
62004293392001110001000100010008751400020001000100020002000110001000
62004293092001110001000100010008751400020001000100020002000110001000
62004293082001110001000100010008751400020001000100020002000110001000

Test 2: throughput

Count: 8

Code:

  st2 { v0.b, v1.b }[1], [x6]
  st2 { v0.b, v1.b }[1], [x6]
  st2 { v0.b, v1.b }[1], [x6]
  st2 { v0.b, v1.b }[1], [x6]
  st2 { v0.b, v1.b }[1], [x6]
  st2 { v0.b, v1.b }[1], [x6]
  st2 { v0.b, v1.b }[1], [x6]
  st2 { v0.b, v1.b }[1], [x6]
  mov x7, x6
  mov x8, x6
  mov x9, x6
  mov x10, x6
  mov x11, x6
  mov x12, x6
  mov x13, x6

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 1.0006

retire uop (01)cycle (02)schedule uop (52)schedule int uop (53)schedule simd uop (54)schedule ldst uop (55)dispatch int uop (56)dispatch simd uop (57)dispatch ldst uop (58)int uops in schedulers (59)simd uops in schedulers (5a)ldst uops in schedulers (5b)dispatch uop (78)map int uop (7c)map ldst uop (7d)map simd uop (7e)map int uop inputs (7f)map ldst uop inputs (80)map simd uop inputs (81)? int output thing (e9)? ldst retires (ed)? simd retires (ee)? int retires (ef)
16020680151160155101800368001810080038800013001359994320026160107200800068000620016001216001218000080000100
16020480045160105101800048000010080006800013001360066320026160107200800068000620016001216001218000080000100
16020480045160105101800048000010080006800013001360066320026160107200800068000620016001216001218000080000100
16020580103160153101800348001810080036800013001360192320026160107200800068000620016001216001218000080000100
16020480045160105101800048000010080006800013001360066320026160107200800068000620016001216001218000080000100
16020480045160105101800048000010080006800013001360066320026160107200800068000620016001216001218000080000100
16020480045160105101800048000010080006800013001360066320026160107200800068000620016001216001218000080000100
16020480045160105101800048000010080006800013001360066320026160107200800068000620016001216001218000080000100
16020480045160105101800048000010080006800013001360066320026160107200800068000620016001216001218000080000100
16020480045160105101800048000010080006800013001360066320026160107200800068000620016001216001218000080000100

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 1.0005

retire uop (01)cycle (02)schedule uop (52)schedule int uop (53)schedule simd uop (54)schedule ldst uop (55)dispatch int uop (56)dispatch simd uop (57)dispatch ldst uop (58)int uops in schedulers (59)simd uops in schedulers (5a)ldst uops in schedulers (5b)dispatch uop (78)map int uop (7c)map ldst uop (7d)map simd uop (7e)map int uop inputs (7f)map ldst uop inputs (80)map simd uop inputs (81)? int output thing (e9)? ldst retires (ed)? simd retires (ee)? int retires (ef)
16002680144160065118003680018108003880001301360030320026160017208000680006201600001600001800008000010
16002480038160011118000080000108000080001301359940320026160017208000680006201600001600001800008000010
16002480038160011118000080000108000080000301359937320000160010208000080000201600001600001800008000010
16002480038160015118000480000108000680000301359937320000160010208000080000201600001600001800008000010
16002480038160011118000080000108000080031301360263320146160077208003680036201600001600001800008000010
16002480038160011118000080000108000080000301359937320000160010208000080000201600001600001800008000010
16002480038160011118000080000108000080000301359937320000160010208000080000201600001600001800008000010
16002480038160011118000080000108000080000301359937320000160010208000080000201600001600001800008000010
16002480038160011118000080000108000080000301359937320000160010208000080000201600001600001800008000010
16002480038160011118000080000108000080000301359937320000160010208000080000201600001600001800008000010