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, H)

Test 1: uops

Code:

  st2 { v0.h, v1.h }[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)
6200629743300710031002100210021002100030008751400030001000100030002000100110001000
6200429342300110011000100010001000100030008751400030001000100030002000100110001000
6200429392300110011000100010001000100030008751400030001000100030002000100110001000
6200429751300110011000100010001000100030008751400030001000100030002000100110001000
6200430129300110011000100010001000100030008751400030001000100030002000100110001000
6200429341300110011000100010001000100030008751400030001000100030002000100110001000
6200429337300110011000100010001000100030008751400030001000100030002000100110001000
6200429372300110011000100010001000100030008751400030001000100030002000100110001000
6200429373300110011000100010001000100130038756400430031001100130002000100110001000
6200429342300110011000100010001000100030008751400030001000100030002000100110001000

Test 2: throughput

Count: 8

Code:

  st2 { v0.h, v1.h }[1], [x6], x8
  st2 { v0.h, v1.h }[1], [x6], x8
  st2 { v0.h, v1.h }[1], [x6], x8
  st2 { v0.h, v1.h }[1], [x6], x8
  st2 { v0.h, v1.h }[1], [x6], x8
  st2 { v0.h, v1.h }[1], [x6], x8
  st2 { v0.h, v1.h }[1], [x6], x8
  st2 { v0.h, v1.h }[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): 1.0006

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)
16020680149240183801318003480018801368003680004121871513599903200382401222008000980009200240027160018800018000080000100
1602048004724010880101800078000080109800098000252049513600943200262401142008000680006200240018160012800038000080000100
1602048004724010780103800048000080106800068000252049513600943200262401142008000680006200240018160012800038000080000100
1602048004724010780103800048000080106800068000252049513600943200262401142008000680006200240018160012800038000080000100
1602048004724010780103800048000080106800068000252049513600943200262401142008000680006200240018160012800038000080000100
1602048004724010780103800048000080106800068000252049513600943200262401142008000680006200240018160012800038000080000100
1602048004724010780103800048000080106800068000252049513600943200262401142008000680006200240018160012800038000080000100
1602048004724010780103800048000080106800068000252049513600943200262401142008000680006200240018160012800038000080000100
1602048004724010780103800048000080106800068000250333213603463200262401142008000680006200240018160012800038000080000100
1602048004724010780103800048000080106800068000252049513600943200262401142008000680006200240018160012800038000080000100

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)
16002680145240095800418003680018800488003880033134187813603553201502401172080037800372024000016000080001800008000010
1600248004524001180011800008000080010800008000068015913600523200002400102080000800002024000016000080001800008000010
1600248004524001180011800008000080010800008000068015913600523200002400102080000800002024000016000080001800008000010
1600248004524001180011800008000080010800008000068015913600523200002400102080000800002024000016000080001800008000010
1600248004524001180011800008000080010800008000068015913600523200002400102080000800002024000016000080001800008000010
1600248004524001180011800008000080010800008000068015913600523200002400102080000800002024000016000080001800008000010
1600248004524001180011800008000080010800008000068015913600523200002400102080000800002024000016000080001800008000010
16002480045240011800118000080000800108000080033127602413604113201542401192080038800382024000016000080001800008000010
1600248004524001180011800008000080010800008000068015913600523200002400102080000800002024000016000080001800008000010
1600248004524001180011800008000080010800008000068015913600523200002400102080000800002024000016000080001800008000010