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

ST1 (single, post-index, D)

Test 1: uops

Code:

  st1 { v0.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)
6200629503300710031002100210021002100030008751400030001000100030001000100110001000
6200429288300110011000100010001000100030008751400030001000100030001000100110001000
6200429301300110011000100010001000100030008751400030001000100030001000100110001000
6200429290300110011000100010001000100030008751400030001000100030001000100110001000
6200429316300110011000100010001000100030008751400030001000100030001000100110001000
6200429280300110011000100010001000100030008751400030001000100030001000100110001000
6200429301300110011000100010001000100030008751400030001000100030001000100110001000
6200429297300110011000100010001000100030008751400030001000100030001000100110001000
6200429290300110011000100010001000100030008751400030001000100030001000100110001000
6200429297300110011000100010001000100030008751400030001000100030001000100110001000

Test 2: throughput

Count: 8

Code:

  st1 { v0.d }[1], [x6], x8
  st1 { v0.d }[1], [x6], x8
  st1 { v0.d }[1], [x6], x8
  st1 { v0.d }[1], [x6], x8
  st1 { v0.d }[1], [x6], x8
  st1 { v0.d }[1], [x6], x8
  st1 { v0.d }[1], [x6], x8
  st1 { v0.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)
1602068015124018380131800348001880136800368000412376071359842320038240122200800098000920024002780009800018000080000100
1602048003924010780101800068000080108800088000311602751359965320034240119200800088000820024002480008800018000080000100
1602058009724018580131800368001880138800388000311602751359965320034240119200800088000820024002480008800018000080000100
1602048003924010780101800068000080108800088000311602751359965320034240119200800088000820024002480008800018000080000100
1602048003924010780101800068000080108800088000311602751359965320034240119200800088000820024002480008800018000080000100
1602048003924010780101800068000080108800088000311602751359965320034240119200800088000820024002480008800018000080000100
1602048003924010780101800068000080108800088000311602751359965320034240119200800088000820024010880036800318000080000100
1602048003924010780101800068000080108800088000311602751359965320034240119200800088000820024002480008800018000080000100
1602048003924010780101800068000080108800088000311602751359965320034240119200800088000820024002480008800018000080000100
1602048003924010780101800068000080108800088000311602751359965320034240119200800088000820024002480008800018000080000100

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)
160026801512400978004280037800188004980039800038801251360034320030240027208000780007202400188000680003800008000010
160024800472400118001180000800008001080000800005202411360088320000240010208000080000202400008000080001800008000010
160025801082400958004180036800188004880038800005202411360088320000240010208000080000202400008000080001800008000010
160024800472400118001180000800008001080000800005202411360088320000240010208000080000202400008000080001800008000010
160024800472400118001180000800008001080000800005202411360088320000240010208000080000202400008000080001800008000010
160024800472400118001180000800008001080000800005202411360088320000240010208000080000202400008000080001800008000010
160024800472400118001180000800008001080000800005202411360088320000240010208000080000202400008000080001800008000010
160024800472400118001180000800008001080000800005202411360088320000240010208000080000202400008000080001800008000010
160024800472400118001180000800008001080000800005202411360088320000240010208000080000202400008000080001800008000010
160025801182400958004180036800188004880038800004452551360106320000240010208000080000202400008000080001800008000010