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, H)

Test 1: uops

Code:

  st1 { v0.h }[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)
62006295442005110021002100210008751400020001000100020001000110001000
62004293292001110001000100010008751400020001000100020001000110001000
62004293442001110001000100010008751400020001000100020001000110001000
62004293522001110001000100010008751400020001000100020001000110001000
62004293382001110001000100010008751400020001000100020001000110001000
62004293482001110001000100010008751400020001000100020001000110001000
62004293362001110001000100010008751400020001000100020001000110001000
62004293372001110001000100010008751400020001000100020001000110001000
62004293362001110001000100010008751400020001000100020001000110001000
62004293362001110001000100010008751400020001000100020001000110001000

Test 2: throughput

Count: 8

Code:

  st1 { v0.h }[1], [x6]
  st1 { v0.h }[1], [x6]
  st1 { v0.h }[1], [x6]
  st1 { v0.h }[1], [x6]
  st1 { v0.h }[1], [x6]
  st1 { v0.h }[1], [x6]
  st1 { v0.h }[1], [x6]
  st1 { v0.h }[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)
1602068015516015610180037800181008003980001300136003032002616010720080006800062001600128000618000080000100
1602048004716010510180004800001008000680001300136010232002616010720080006800062001600128000618000080000100
1602048004716010510180004800001008000680001300136010232002616010720080006800062001600128000618000080000100
1602048004716010510180004800001008000680031300136043332014616016720080036800362001600128000618000080000100
1602048004716010510180004800001008000680001300135990432002616010720080006800062001600128000618000080000100
1602048004716010510180004800001008000680001300136010232002616010720080006800062001600128000618000080000100
1602048004716010510180004800001008000680001300136010232002616010720080006800062001600128000618000080000100
1602048005616010510180004800001008000680001300136012032002616010720080006800062001600128000618000080000100
1602048004716010510180004800001008000680001300136010232002616010720080006800062001600128000618000080000100
1602048004716010510180004800001008000680001300136010232002616010720080006800062001600128000618000080000100

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)
1600268014916006511800368001810800388000130136006632002616001720800068000620160012800061800008000010
1600248004716001111800008000010800008000030136009932000016001020800008000020160000800001800008000010
1600248004716001111800008000010800008000030136009932000016001020800008000020160012800061800008000010
1600248004716001111800008000010800008000030136009932000016001020800008000020160000800001800008000010
1600248004716001111800008000010800008000030136009932000016001020800008000020160000800001800008000010
1600248004716001111800008000010800008000030136009932000016001020800008000020160000800001800008000010
1600248004716001111800008000010800008000030136009932000016001020800008000020160000800001800008000010
1600248004716001111800008000010800008000030136009932000016001020800008000020160000800001800008000010
1600248004716001111800008000010800008000030136009932000016001020800008000020160000800001800008000010
1600248004716001111800008000010800008000030136009932000016001020800008000020160072800361800008000010