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

EOR (register, 64-bit)

Test 1: uops

Code:

  eor x0, x0, x1
  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)schedule simd uop (54)schedule ldst uop (55)dispatch int uop (56)dispatch simd uop (57)int uops in schedulers (59)dispatch uop (78)map int uop (7c)map int uop inputs (7f)? int output thing (e9)? int retires (ef)
100410301001100100100002560310001000200010011000
100410301001100100100002560310001000200010011000
100410301001100100100002560310001000200010011000
100410301001100100100002560310001000200010011000
100410301001100100100002560310001000200010011000
100410301001100100100002560310001000200010011000
100410301001100100100002560310001000200010011000
100410301001100100100002560310001000200010011000
100410301001100100100002560310001000200010011000
100410301001100100100002560310001000200010011000

Test 2: Latency 1->2

Code:

  eor x0, x0, x1
  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)
10204100301010110101101072594161010710214202241000110100
10204100301010110101101072594351010710214202241000110100
10204100301010110101101072595391010710212202241000110100
10204100301010110101101072595391010710212202241000110100
10204100301010110101101072595391010710212202241000110100
10204100301010110101101072595391010710212202241000110100
10204100301010110101101072595391010710212202241000110100
10204100301010110101101072595391010710212202241000110100
10204100301010110101101072595391010710212202241000110100
10204100301010110101101072595391010710212202241000110100

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)
10024100301002110021100302596281002810036200201001110010
10024100301002110021100202595911002010020200201001110010
10024100301002110021100202595911002010020200201001110010
10024100301002110021100202595911002010020200201001110010
10025100601003510035100682595911002010020200201001110010
10024100301002110021100202595911002010020200201001110010
10024100301002110021100202595911002010020200201001110010
10024100301002110021100202595911002010020200201001110010
10024100301002110021100202595911002010020200201001110010
10024100301002110021100202595911002010020200201001110010

Test 3: Latency 1->3

Code:

  eor x0, x1, x0
  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)
10204100301010110101101082593291010710214202281000110100
10204100301010110101101072595391010710212202241000110100
10204100301010110101101072595391010710212202241000110100
10204100301010110101101072595391010710212202241000110100
10204100301010110101101072595391010710212202241000110100
10204100301010110101101072595391010710212202241000110100
10204100301010110101101072595391010710212202241000110100
10204100301010110101101072595391010710212202241000110100
10204100301010110101101072595391010710212202241000110100
10204100301010110101101072595391010710212202241000110100

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)
10024100301002110021100282594741002010020200201001110010
10024100301002110021100202595911002010020200201001110010
10024100301002110021100202595911002010020200201001110010
10024100301002110021100202595911002010020200201001110010
10024100301002110021100202595911002010020200201001110010
10024100301002110021100202595911002010020200201001110010
10024100301002110021100202595911002010020200201001110010
10024100301002110021100202595911002010020200201001110010
10024100301002110021100202595911002010020200201001110010
10024100301002110021100202595911002010020200201001110010

Test 4: throughput

Count: 8

Code:

  eor x0, x8, x9
  eor x1, x8, x9
  eor x2, x8, x9
  eor x3, x8, x9
  eor x4, x8, x9
  eor x5, x8, x9
  eor x6, x8, x9
  eor x7, x8, x9
  mov x8, 9
  mov x9, 10

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.3342

retire uop (01)cycle (02)schedule uop (52)schedule int uop (53)schedule ldst uop (55)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)
8020426841801158011508012024036080120802221602428001480100
8020426739801158011508012024036080120802241602488001580100
8020426737801158011508012024036080120802241602488001580100
8020426737801158011508012024036080120802241602488001580100
8020426737801158011508012024036080120802241602488001580100
8020426737801158011508012024036080120802241602488001580100
8020426737801158011508012024036080120802241602488001580100
8020426737801158011508012024036080120802241602488001580100
8020426737801158011508012024036080120802241602488001580100
8020426737801158011508012024036080120802241602488001580100

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.3340

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)
800242787380039800398004427740480020800201600208001180010
800252683980082800828009826673680020800201600208001180010
800242671780021800218002028273880020800201600208001180010
800242671780021800218002028273880020800201600208001180010
800242671780021800218002028273880020800201600208001180010
800242671780021800218002028273880020800201600208001180010
800242671780021800218002028273880020800201600208001180010
800242671780021800218002028273880020800201600208001180010
800242671780021800218002026921280095800991600208001180010
800242671780021800218002027215480044800461600728002780010