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, asr, 32-bit)

Test 1: uops

Code:

  negs w0, w0, asr #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, asr #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)
10204200302010120101101045289931010410206102082000110100
10204200302010120101101045290871010410208102082000110100
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)
10024200302002120021100255292151002510030100202001110010
10024200302002120021100205292491002010020100202001110010
10024200302002120021100205292491002010020100202001110010
10024200302002120021100205292491002010020100202001110010
10024200302002120021100205292491002010020100202001110010
10024200302002120021100205292491002010020100202001110010
10024200302002120021100205292491002010020100202001110010
10024200302002120021100205292491002010020100202001110010
10024200302002120021100205292491002010020100202001110010
10024200302002120021100205292491002010020100202001110010

Test 3: Latency 3->2

Chain cycles: 1

Code:

  negs w0, w1, asr #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)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)
202043003030101301010201067893112010520212202103000120100
20682327823058930422167204087893692010520212202123000120100
202043003030101301010201057897112014320256202123000120100
202043003030101301010201057893692010520212202123000120100
202043003030101301010201057893692010520212202123000120100
202043003030101301010201057893692010520212202123000120100
202043003030101301010201057893692010520212202123000120100
202043003030101301010201057893692010520212202103000120100
202043003030101301010201057893692010520212202123000120100
202043003030101301010201057893692010520212202123000120100

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)
20024300303001130011200157913392016820201200203000120010
20024300303001130011200107894382001020020200203000120010
20025300603002530025200517894382001020020200203000120010
20024300303001130011200107894382001020020200203000120010
20024300303001130011200107894382001020020200203000120010
20024302173008330083201317894382001020020200203000120010
20024300303001130011200107894382001020020200203000120010
20024300303001130011200107894382001020020200203000120010
20024300303001130011200107894382001020020200203000120010
20024300303001130011200107894382001020020200203000120010

Test 4: throughput

Count: 8

Code:

  negs w0, w8, asr #17
  negs w1, w8, asr #17
  negs w2, w8, asr #17
  negs w3, w8, asr #17
  negs w4, w8, asr #17
  negs w5, w8, asr #17
  negs w6, w8, asr #17
  negs w7, w8, asr #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)dispatch int uop (56)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)? int output thing (e9)? int retires (ef)
80204534171601161601168012201099575008012380224008022416001480100
80204534041601141601148012301100424008016180262008022416001480100
80204534041601141601148012301100076008012380224008022416001480100
80204534041601141601148012301100076008012380224008022416001480100
80204534041601141601148012301100076008012380224008022416001480100
80204534041601141601148012301100076008012380224008022416001480100
80204534041601141601148012301100076008012380224008022416001480100
80204534041601141601148012301100076008012380224008022416001480100
80204534041601141601148012301100076008012380224008022416001480100
80204534041601141601148012301100076008012380224008022416001480100

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)map ldst uop inputs (80)map simd uop inputs (81)? int output thing (e9)? ldst retires (ed)? simd retires (ee)? int retires (ef)
8002453416160042160042800481107564800208002080020001600110080010
8002453371160021160021800201107732800208002080020001600110080010
8002453371160021160021800201107732800208002080020001600110080010
8002453371160021160021800201107732800208002080020001600110080010
8002453371160021160021800201107732800208002080020001600110080010
8002453371160021160021800201107732800208002080020001600110080010
8002453371160021160021800201107732800208002080084001600740080010
8002453371160021160021800201107732800208002080020001600110080010
8002453371160021160021800201107732800208002080020001600110080010
8002453371160021160021800201107732800208002080020001600110080010