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, post-index, D)

Test 1: uops

Code:

  st2 { v0.d, v1.d }[1], [x6], x8
  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
  mov x8, 0

(no loop instructions)

1000 unrolls and 1 iteration

Retires (minus 60 nops): 2.000

Issues: 3.000

Integer unit issues: 1.001

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 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 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)
6200629963300710031002100210021002100030008751400030001000100030002000100110001000
6200429456300110011000100010001000100030008751400030001000100030002000100110001000
6200429336300110011000100010001000100030008751400030001000100030002000100110001000
6200429337300110011000100010001000100030008751400030001000100030002000100110001000
6200429359300110011000100010001000100030008751400030001000100030002000100110001000
6200429361300110011000100010001000100030008751400030001000100030002000100110001000
6200429359300110011000100010001000100030008751400030001000100030002000100110001000
6200429362300110011000100010001000100030008751400030001000100030002000100110001000
6200429335300110011000100010001000100030008751400030001000100030002000100110001000
6200429338300110011000100010001000100030008751400030001000100030002000100110001000

Test 2: throughput

Count: 8

Code:

  st2 { v0.d, v1.d }[1], [x6], x8
  st2 { v0.d, v1.d }[1], [x6], x8
  st2 { v0.d, v1.d }[1], [x6], x8
  st2 { v0.d, v1.d }[1], [x6], x8
  st2 { v0.d, v1.d }[1], [x6], x8
  st2 { v0.d, v1.d }[1], [x6], x8
  st2 { v0.d, v1.d }[1], [x6], x8
  st2 { v0.d, v1.d }[1], [x6], x8
  mov x7, x6
  mov x8, x6
  mov x9, x6
  mov x10, x6
  mov x11, x6
  mov x12, x6
  mov x13, x6
  mov x8, 0

(fused SUBS/B.cc loop)

100 unrolls and 100 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)
1602068015524018680132800368001880138800388000268043613600583200262401142008000680006200240027160018800018000080000100
16020580097240184801318003580018801378003780004123297013599063200382401222008000980009200240024160016800018000080000100
16020480039240107801018000680000801088000880003116028113599653200342401192008000880008200240024160016800018000080000100
16020480039240107801018000680000801088000880003116028113599653200342401192008000880008200240024160016800018000080000100
16020480039240107801018000680000801088000880003116028113599653200342401192008000880008200240024160016800018000080000100
16020480039240107801018000680000801088000880003116028113599653200342401192008000880008200240024160016800018000080000100
16020480039240107801018000680000801088000880003116028113599653200342401192008000880008200240024160016800018000080000100
16020480039240107801018000680000801088000880003116028113599653200342401192008000880008200240018160012800058000080000100
16020580105240185801318003680018801388003880003116028113599653200342401192008000880008200240024160016800018000080000100
16020480039240107801018000680000801088000880003116028113599653200342401192008000880008200240024160016800018000080000100

1000 unrolls and 10 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)
16002680147240093800418003480018800468003680004100491013601293200382400322080009800092024002116001480001800008000010
1600248004524001180011800008000080010800008000068015913600523200002400102080000800002024000016000080001800008000010
1600248004524001180011800008000080010800008000068015913600523200002400102080000800002024000016000080001800008000010
1600248004524001180011800008000080010800008000068015913600523200002400102080000800002024000016000080001800008000010
1600248004524001180011800008000080010800008000068015913600523200002400102080000800002024000016000080001800008000010
1600248004524001180011800008000080010800008002668027813602213201122400922280027800272024000016000080001800008000010
1600248004524001180011800008000080010800008000068015913600523200002400102080000800002024000016000080001800008000010
1600248004524001180011800008000080010800008000068015913600523200002400102080000800002024000016000080001800008000010
1600248004524001180011800008000080010800008000068015913600523200002400102080000800002024000016000080001800008000010
1600248004524001180011800008000080010800008000068015913600523200002400102080000800002024000016000080001800008000010