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

CLREX

Test 1: uops

Code:

  clrex
  mov x0, 0

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 1.000

Issues: 1.000

Integer unit issues: 0.001

Load/store unit issues: 1.000

SIMD/FP unit issues: 0.000

retire uop (01)cycle (02)schedule uop (52)schedule int uop (53)schedule ldst uop (55)dispatch ldst uop (58)simd uops in schedulers (5a)dispatch uop (78)map ldst uop (7d)? int output thing (e9)? ldst retires (ed)
100449561001110001000867771000100011000
100449561001110001000867771000100011000
100449561001110001000867771000100011000
100449561001110001000867771000100011000
100449561001110001000867771000100011000
100449561001110001000867771000100011000
100449561001110001000867771000100011000
100449561001110001000867771000100011000
100449561001110001000867771000100011000
100449561001110001000867771000100011000

Test 2: throughput

Code:

  clrex
  add x6, x6, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 4.9956

retire uop (01)cycle (02)schedule uop (52)schedule int uop (53)schedule ldst uop (55)dispatch int uop (56)dispatch ldst uop (58)int uops in schedulers (59)simd uops in schedulers (5a)dispatch uop (78)map int uop (7c)map ldst uop (7d)map int uop inputs (7f)? int output thing (e9)? ldst retires (ed)? int retires (ef)
202044995620102101021000010101100003571488777720101102031000310203100021000010100
202044995620101101011000010100100003571088777720100102021000210202100011000010100
202044995620101101011000010100100003571088777720100102021000210202100011000010100
202044995620101101011000010100100003571088777720100102021000210202100011000010100
202044995620101101011000010100100003571088777720100102021000210202100011000010100
202044995620101101011000010100100003571088777720100102021000210202100011000010100
202044995620101101011000010100100003571088777720100102021000210202100011000010100
202044995620101101011000010100100003571088777720100102021000210202100011000010100
202044995620101101011000010100100003571088777720100102021000210202100011000010100
202044995620101101011000010100100003571088777720100102021000210202100011000010100

1000 unrolls and 10 iterations

Result (median cycles for code): 4.9956

retire uop (01)cycle (02)schedule uop (52)schedule int uop (53)schedule ldst uop (55)dispatch int uop (56)dispatch ldst uop (58)int uops in schedulers (59)simd uops in schedulers (5a)dispatch uop (78)map int uop (7c)map ldst uop (7d)map int uop inputs (7f)? int output thing (e9)? ldst retires (ed)? int retires (ef)
200244995620012100121000010011100003548588777720010100201000010020100011000010010
200244995620011100111000010010100003548588777720010100201000010020100011000010010
200244995620011100111000010010100003548588777720010100201000010020100011000010010
200244995620011100111000010010100003548588777720010100201000010052100291000010010
200244995620011100111000010010100003548588777720010100201000010020100011000010010
200244995620011100111000010010100003548588777720010100201000010020100011000010010
200244995620011100111000010010100003548588777720010100201000010020100011000010010
200244995620011100111000010010100003548588777720010100201000010020100011000010010
200244995620011100111000010010100003548588777720010100201000010020100011000010010
200244995620011100111000010010100003548588777720010100201000010020100011000010010

Test 3: throughput

Code:

  clrex
  mov x7, 8

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 4.9956

retire uop (01)cycle (02)schedule uop (52)schedule int uop (53)schedule ldst uop (55)dispatch int uop (56)dispatch ldst uop (58)int uops in schedulers (59)simd uops in schedulers (5a)dispatch uop (78)map int uop (7c)map ldst uop (7d)map int uop inputs (7f)? int output thing (e9)? ldst retires (ed)? int retires (ef)
10204499561010110110000100100003008877771010020010004200110000100
10205499121010610310003102100003008877771010020010004200110000100
10204499561010110110000100100003008877771010020010004200110000100
10204499561010110110000100100003008877771010020010004200110000100
10204499561010110110000100100003008877771010020010004200110000100
10204499561010110110000100100003008877771010020010004200110000100
10204499561010110110000100100003008877771010020010004200110000100
10204499561010110110000100100003008877771010020010004200110000100
10204499561010110110000100100003008877771010020010004200110000100
10204499561010110110000100100003008877771010020010004200110000100

1000 unrolls and 10 iterations

Result (median cycles for code): 4.9956

retire uop (01)cycle (02)schedule uop (52)schedule int uop (53)schedule ldst uop (55)dispatch int uop (56)dispatch ldst uop (58)int uops in schedulers (59)simd uops in schedulers (5a)dispatch uop (78)map int uop (7c)map ldst uop (7d)map int uop inputs (7f)? int output thing (e9)? ldst retires (ed)? int retires (ef)
10024499561001111100001010000308877771001020100042011000010
10024499561001111100001010000308877771001020100002011000010
10024499561001111100001010000308877771001020100002011000010
10024499561001111100001010000308877771001020100002011000010
10024499561001111100001010000308877771001020100002011000010
10024499561001111100001010021308866041003120100342011000010
10024499561001111100001010000308877771001020100002011000010
10024499561001111100001010000308877771001020100002011000010
10024499561001111100001010000308877771001020100002011000010
10024499561001111100001010000308877771001020100042011000010