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

NEGS (register, lsr, 32-bit)

Test 1: uops

Code:

  negs w0, w0, lsr #17
  mov x0, 1
  mov x1, 2

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 1.000

Issues: 2.000

Integer unit issues: 2.001

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)
100420302001200110005226510001000100020011000
100420302001200110005226510001000100020011000
100420302001200110005226510001000100020011000
100420302001200110005226510001000100020011000
100420302001200110005226510001000100020011000
100420302001200110005226510001000100020011000
100420302001200110005226510001000100020011000
100420302001200110005226510001000100020011000
100420302001200110005226510001000100020011000
100420302001200110005226510001000100020011000

Test 2: Latency 1->2

Code:

  negs w0, w0, lsr #17
  mov x0, 1
  mov x1, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 2.0030

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)
10204200302010120101101045290011010410206102062000110100
10204200302010120101101045294231013810248102082000110100
10204200302010120101101045290871010410208102082000110100
10204200302010120101101045290871010410208102082000110100
10204200302010120101101045290871010410208102082000110100
10204200302010120101101045290871010410208102082000110100
10204200302010120101101045290871010410208102082000110100
10204200302010120101101045290871010410208102082000110100
10204200302010120101101045290871010410208102082000110100
10204200302010120101101045290871010410208102082000110100

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0030

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)
10024200302002120021100255292491002010020100202001110010
10024200302002120021100205292491002010020100202001110010
10024200302002120021100205292491002010020100202001110010
10024200302002120021100205292491002010020100722002510010
10024200302002120021100205292491002010020100202001110010
10024200302002120021100205292491002010020100202001110010
10024200302002120021100205292491002010020100202001110010
10024200302002120021100205292491002010020100202001110010
10024200302002120021100205292491002010020100202001110010
10024200302002120021100205292491002010020100202001110010

Test 3: Latency 3->2

Chain cycles: 1

Code:

  negs w0, w1, lsr #17
  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): 2.0030

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)
20204300303010130101201067892892010620212202123000120100
20204300303010130101201057893692010520212202123000120100
20204300303010130101201057893692010520212202123000120100
20205300603011730117201447893692010520212202123000120100
20204300303010130101201057893692010520212202123000120100
20204300303010130101201057893692010520212202123000120100
20204300303010130101201057893692010520212202563001520100
20204300303010130101201067892892010520212202123000120100
20204300303010130101201057893692010520212202123000120100
20204300303010130101201057893692010520212202123000120100

1000 unrolls and 10 iterations

Result (median cycles for code, minus 1 chain cycle): 2.0030

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)
20024300303001130011200157894382001020020200203000120010
20024300303001130011200107894382001020020200203000120010
20024300303001130011200107894382001020020200203000120010
20024300303001130011200107894382001020020200203000120010
20024300303001130011200107897902005120076200203000120010
20024300643001130011200157894382001020020200613002220010
20024300303001130011200107894382001020020201043004320010
20024300303001130011200107894382001020020200203000120010
20024300303001130011200107897892005320073200203000120010
20024300303001130011200107894382001020020200203000120010

Test 4: throughput

Count: 8

Code:

  negs w0, w8, lsr #17
  negs w1, w8, lsr #17
  negs w2, w8, lsr #17
  negs w3, w8, lsr #17
  negs w4, w8, lsr #17
  negs w5, w8, lsr #17
  negs w6, w8, lsr #17
  negs w7, w8, lsr #17
  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): 0.6675

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)
802045341816011616011600801220109993780123802248022416001480100
802045340416011416011400801230110007680123802248022416001480100
802045340416011416011400801230110007680123802248022416001480100
802045340416011416011400801230110007680123802248022416001480100
802045340416011416011400801230110007680123802248022416001480100
802045340416011416011400801230110007680123802248022416001480100
802045340416011416011400801230110424180164802648022416001480100
802045340416011416011400801230110007680123802248022416001480100
802045340416011416011400801230110007680123802248022416001480100
802045340416011416011400801230111647380160802608022416001480100

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.6671

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)
800245338016004216004280048110473480048800488002016001180010
800245337116002116002180020110773280020800208008816007780010
800245338516002116002180020110773280020800208002016001180010
800245337116002116002180020110773280020800208002016001180010
800245337116002116002180020110773280020800208002016001180010
800245337116002116002180020110773280020800208002016001180010
800245337116002116002180020110773280020800208002016001180010
800245337116002116002180020110773280020800208002016001180010
800245337116002116002180020110773280020800208002016001180010
800245337116002116002180020110773280020800208002016001180010