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

SUBS (sxtx, 64-bit)

Test 1: uops

Code:

  subs x0, x0, x1, sxtx
  mov x0, 1
  mov x1, 2

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 1.000

Issues: 1.000

Integer unit issues: 1.001

Load/store unit issues: 0.000

SIMD/FP unit issues: 0.000

retire uop (01)cycle (02)schedule uop (52)schedule int uop (53)dispatch int uop (56)int uops in schedulers (59)dispatch uop (78)map int uop (7c)map int uop inputs (7f)? int output thing (e9)? int retires (ef)
100410301001100110002504310001000200010011000
100410301001100110002504310001000200010011000
100410301001100110002504310001000200010011000
100410301001100110002504310001000200010011000
100410301001100110002504310001000200010011000
100410301001100110002504310001000200010011000
100410301001100110002504310001000200010011000
100410301001100110002504310001000200010011000
100410301001100110002504310001000200010011000
100410301001100110002504310001000200010011000

Test 2: Latency 1->2

Code:

  subs x0, x0, x1, sxtx
  mov x0, 1
  mov x1, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 1.0030

retire uop (01)cycle (02)schedule uop (52)schedule int uop (53)dispatch int uop (56)int uops in schedulers (59)dispatch uop (78)map int uop (7c)map int uop inputs (7f)? int output thing (e9)? int retires (ef)
10204100301010110101101082516411010610206202201000110100
10204100301010110101101082517741010810208202161000110100
10204100301010110101101082517741010810208202161000110100
10204100301010110101101082517741010810208202161000110100
10204100301010110101101082517741010810208202161000110100
10204100301010110101101082517741010810208202161000110100
10204100301010110101101082517741010810208202161000110100
10204100301010110101101082517741010810208202161000110100
10204100301010110101101082517741010810208202161000110100
10204100301010110101101082517741010810208202161000110100

1000 unrolls and 10 iterations

Result (median cycles for code): 1.0030

retire uop (01)cycle (02)schedule uop (52)schedule int uop (53)dispatch int uop (56)int uops in schedulers (59)dispatch uop (78)map int uop (7c)map int uop inputs (7f)? int output thing (e9)? int retires (ef)
10024100301002110021100282532011002810028200201001110010
10024100301002110021100202531611002010020200201001110010
10024100301002110021100202531611002010020200201001110010
10024100301002110021100202531611002010020200201001110010
10024100301002110021100202531611002010020200201001110010
10024100301002110021100202531611002010020200201001110010
10024100301002110021100202531611002010020200201001110010
10024100301002110021100202531611002010020200201001110010
10024100301002110021100202531611002010020200201001110010
10024100301002110021100202531611002010020200201001110010

Test 3: Latency 1->3

Code:

  subs x0, x1, x0, sxtx
  mov x0, 1
  mov x1, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 1.0030

retire uop (01)cycle (02)schedule uop (52)schedule int uop (53)dispatch int uop (56)int uops in schedulers (59)dispatch uop (78)map int uop (7c)map int uop inputs (7f)? int output thing (e9)? int retires (ef)
10204100301010110101101072515201010610206202161000110100
10204100301010110101101082517741010810208202161000110100
10204100301010110101101082517741010810208202161000110100
10204100301010110101101082517741010810208202161000110100
10204100301010110101101082517741010810208202161000110100
10204100301010110101101082517741010810208202161000110100
10204100301010110101101082517741010810208202161000110100
10204100301010110101101082517741010810208202161000110100
10204100301010110101101082517741010810208202161000110100
10204100301010110101101082517741010810208202161000110100

1000 unrolls and 10 iterations

Result (median cycles for code): 1.0030

retire uop (01)cycle (02)schedule uop (52)schedule int uop (53)dispatch int uop (56)int uops in schedulers (59)dispatch uop (78)map int uop (7c)map int uop inputs (7f)? int output thing (e9)? int retires (ef)
10024100301002110021100292532921002810030200201001110010
10024100301002110021100202531611002010020200201001110010
10024100301002110021100202531611002010020200201001110010
10024100301002110021100202531611002010020200201001110010
10024100301002110021100202531611002010020200201001110010
10024100301002110021100202531611002010020200201001110010
10024100301002110021100202531611002010020200201001110010
10024100301002110021100202531611002010020200201001110010
10024100301002110021100202531611002010020200201001110010
10024100301002110021100202531611002010020200201001110010

Test 4: Latency 4->2

Chain cycles: 1

Code:

  subs x0, x1, x2, sxtx
  cset x1, cc
  mov x0, 1
  mov x1, 2
  mov x2, 3
  mov x3, 4
  mov x4, 5

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code, minus 1 chain cycle): 1.0030

retire uop (01)cycle (02)schedule uop (52)schedule int uop (53)dispatch int uop (56)int uops in schedulers (59)dispatch uop (78)map int uop (7c)map int uop inputs (7f)? int output thing (e9)? int retires (ef)
20204200302010120101201085192342010820216302212000120100
20204200302010120101201085195482010820216302242000120100
20204200302010120101201085195482010820216302242000120100
20204200302010120101201085195482010820216302242000120100
20204200302010120101201085195482010820216302242000120100
20204200302010120101201085195482010820216302242000120100
20204200302010120101201085195482010820216302242000120100
20204200302010120101201085195482010820216302242000120100
20204200302010120101201085195482010820216302242000120100
20204200302010120101201085195482010820216302242000120100

1000 unrolls and 10 iterations

Result (median cycles for code, minus 1 chain cycle): 1.0030

retire uop (01)cycle (02)schedule uop (52)schedule int uop (53)dispatch int uop (56)int uops in schedulers (59)dispatch uop (78)map int uop (7c)map int uop inputs (7f)? int output thing (e9)? int retires (ef)
20024200302001120011200185194952001820036300382000120010
20024200302001120011200105195982001020020300202000120010
20024200302001120011200105195982001020020300202000120010
20024200302001120011200105195982001020020300202000120010
20024200302001120011200105195982001020020300202000120010
20024200302001120011200105195982001020020300202000120010
20024200302001120011200105195982001020020300202000120010
20024200302001120011200105195982001020020300202000120010
20024200302001120011200105195982001020020300202000120010
20024200302001120011200105195982001020020300202000120010

Test 5: Latency 4->3

Chain cycles: 1

Code:

  subs x0, x1, x2, sxtx
  cset x2, cc
  mov x0, 1
  mov x1, 2
  mov x2, 3
  mov x3, 4
  mov x4, 5

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code, minus 1 chain cycle): 1.0030

retire uop (01)cycle (02)schedule uop (52)schedule int uop (53)dispatch int uop (56)int uops in schedulers (59)dispatch uop (78)map int uop (7c)map int uop inputs (7f)? int output thing (e9)? int retires (ef)
20204200302010120101201085196012014720260302242000120100
20204200302010120101201085195482010820216302242000120100
20204200302010120101201085195482010820216302242000120100
20204200302010120101201085195482010820216302242000120100
20204200302010120101201085195482010820216302242000120100
20204200302010120101201085195482010820216302242000120100
20204200302010120101201085195482010820216302242000120100
20204200302010120101201085195482010820216302242000120100
20204200302010120101201085195482010820216302242000120100
20204200302010120101201085195482010820216302902001520100

1000 unrolls and 10 iterations

Result (median cycles for code, minus 1 chain cycle): 1.0030

retire uop (01)cycle (02)schedule uop (52)schedule int uop (53)dispatch int uop (56)int uops in schedulers (59)dispatch uop (78)map int uop (7c)map int uop inputs (7f)map ldst uop inputs (80)? int output thing (e9)? ldst retires (ed)? simd retires (ee)? int retires (ef)
20024200302001120011200185194102001820036300200200010020010
20024200302001120011200105195982001020020300200200010020010
20024200302001120011200105195982001020020300200200010020010
20024200302001120011200105195982001020020300200200010020010
20024200302001120011200105195982001020020300200200010020010
20024200302001120011200105195982001020020300200200010020010
20024200302001120011200105195982001020020301160200150020010
20024200302001120011200105195982001020020300200200010020010
20024200302001120011200105195982001020020300200200010020010
200242003020011200112001051959820010200203068948320309285120412

Test 6: throughput

Count: 8

Code:

  subs x0, x8, x9, sxtx
  subs x1, x8, x9, sxtx
  subs x2, x8, x9, sxtx
  subs x3, x8, x9, sxtx
  subs x4, x8, x9, sxtx
  subs x5, x8, x9, sxtx
  subs x6, x8, x9, sxtx
  subs x7, x8, x9, sxtx
  mov x8, 9
  mov x9, 10
  mov x10, 11

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.5010

retire uop (01)cycle (02)schedule uop (52)schedule int uop (53)dispatch int uop (56)int uops in schedulers (59)dispatch uop (78)map int uop (7c)map int uop inputs (7f)? int output thing (e9)? int retires (ef)
802044011080112801128011524034580115802161602288001180100
802044008180112801128011524034580115802161602328001280100
802044008180112801128011524034580115802161602328001280100
802044008180112801128011524034580115802161602328001280100
802044008180112801128011524034580115802161602328001280100
802044008180112801128011524034580115802161602328001280100
802044008180112801128011524034580115802161602328001280100
802044008180112801128011524034580115802161602328001280100
802044008180112801128011524034580115802161602328001280100
802044008180112801128011524034580115802161602328001280100

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.5004

retire uop (01)cycle (02)schedule uop (52)schedule int uop (53)dispatch int uop (56)int uops in schedulers (59)dispatch uop (78)map int uop (7c)map int uop inputs (7f)? int output thing (e9)? int retires (ef)
800244011080032800328003524006780020800201600208001180010
800244004180021800218002024006580020800201600208001180010
800244003080021800218002024006580020800201600208001180010
800244003080021800218002024020980068800681600208001180010
800244003080021800218002024006580020800201600208001180010
800244003080021800218002024006580020800201600208001180010
800244003080021800218002024006580020800201600208001180010
800244003080021800218002024006580020800201600208001180010
800244003080021800218002024006580020800201600208001180010
800244003080021800218002024006580020800201601248005380010