Apple M1 Microarchitecture Research by Dougall Johnson

Firestorm: Overview | Base Instructions | SIMD and FP Instructions
Icestorm:  Overview | Base Instructions | SIMD and FP Instructions

FMLAL (vector, 2S)

Test 1: uops

Code:

  fmlal v0.2s, v1.2h, v2.2h
  movi v0.16b, 1
  movi v1.16b, 2
  movi v2.16b, 3

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 1.000

Issues: 1.000

Integer unit issues: 0.000

Load/store unit issues: 0.000

SIMD/FP unit issues: 1.000

retire (01)cycle (02)031e3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op fp/simd (7e)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst neon or fp (9a)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100440373006134072510001000100053190804018403740373258338951000100030004037403711100110000073116113473100040384038403840384038
100440373006134072510001000100053190814018403740373258338951000100030004037403711100110000073116123473100040384038403840384038
100440373006134072510001000100053190814018403740373258338951000100030004037403711100110000073116113473100040384038403840384038
100440373006134072510001000100053190804018403740373258338951000100030004037403711100110000073116113473100040384038403840384038
100440373006134072510001000100053190804018403740373258338951000100030004037403711100110000073116113473100040384038403840384038
1004403730061340725100010001000531908140184037403732583389510001000300040374037111001100011073116113473100040384038403840384038
1004403730061340725100010001000531908040184037403732583389510001000300040374037111001100018073116113473100040384038403840384038
1004403730061340725100010001000531908140184037403732583389510001000300040374037111001100003673116113473100040384038403840384038
100440373006134072510001000100053190814018403740373258338951000100030004037403711100110000073116113473100040384038403840384038
100440373006134072510001000100053190804018403740373258338951000100030004037403711100110000073116113473100040384038403840384038

Test 2: Latency 1->1

Code:

  fmlal v0.2s, v1.2h, v2.2h
  movi v0.16b, 1
  movi v1.16b, 2
  movi v2.16b, 3

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)03080b191e3a3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8acc2cfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020440168300000001683940725101001001000010010000500570690814001840037400373810833874510100200100002003000040037400371110201100991001001000010000071012162239479100001004003840038400384003840038
102044003730000002613940725101001001000010010000500570690814001840037400373810833874510100200100002003000040037400371110201100991001001000010000071012162239479100001004003840038400384003840038
1020440037300000002313940725101001001000010010000500570690814001840037400373810833874510100200100002003000040037400371110201100991001001000010013071012162239479100001004003840038400384003840038
1020440037300000002123940725101001001000010010000500570690814001840037400373810833874510100200100002003000040037400371110201100991001001000010000071012162339479100001004003840038400384003840038
1020440037300000390613940725101001001000010010000500570690814001840037400373810833874510100200100002003000040037400371110201100991001001000010000071012162239479100001004003840038400384003840038
102044003730000051017153940725101001001000010010000500570690804001840037400373810833874510100200100002003000040037400371110201100991001001000010000071012162239479100001004003840038400384003840038
1020440037299003003213940725101001001000010010000500570690814001840037400373810833874510100200100002003000040037400371110201100991001001000010000071012162239479100001004003840038400384003840038
1020440037300000001453940725101001001000010010000500570690814001840037400373810833874510100200100002003000040037400371110201100991001001000010000071012162239479100001004003840038400384003840038
1020440037300000002123940725101001001000010010000500570690814001840037400373810833874510100200104932003000040037400371110201100991001001000010000071012162239479100001004003840038400384003840038
10204400372990000010403940725101001001000010010000500570690814001840037400373810833874510100200100002003000040037400371110201100991001001000010000071012163239479100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)03081e3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa0a1a6a7a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002440037300003173940725100101010000101000050570690804001840037400373813033876710010201000020300004003740037111002110910101000010000000640416323947310000104003840038400384003840038
100244003730000613940725100101010000101000050570690804001840037400373813033876710010201000020300004003740037111002110910101000010000000640316343947310000104003840038400384003840038
100244003730000613940725100101010000101000050570690814001840037400373813033876710010201000020300004003740037111002110910101000010000000640316333947310000104003840038400384003840038
100244003729900613940725100101010000101000050570690814001840037400373813033876710010201000020300004003740037111002110910101000010000000640316343947310000104003840038400384003840038
100244003729900613940725100101010000101000050570690814001840037400373813033876710010201000020300004003740037111002110910101000010000000640316333947310000104003840038400384003840038
100244003730000613940725100101010000101000050570690814001840037400373813033876710010201000020300004003740037111002110910101000010000000640316433947310000104003840038400384003840038
100244003730000613940725100101010000101000050570690814001840037400373813033876710010201000020300004003740037111002110910101000010000000640316333947310000104003840038400384003840038
100244003730000613940725100101010000101000050570690814001840037400373813033876710010201000020300004003740037111002110910101000010000000640416333947310000104003840038400384003840038
100244003730000613940725100101010000101000050570690814001840037400373813033876710010201000020300004003740037111002110910101000010000000640316333947310000104003840038400384003840038
100244003730000613940725100101010000101000050570690804001840037400373813033876710010201000020300004003740037111002110910101000010000010640316333947310000104003840038400384003840038

Test 3: Latency 1->2

Code:

  fmlal v0.2s, v0.2h, v1.2h
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)030a0b1e3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)72scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020440037300000823940725101001001000010010000500570690814001840037400373810803387451010020010000200300004003740037111020110099100100100001000007102162239479100001004003840038400384003840038
1020440037300000613940725101001001000010010000500570690814001840037400373810803387451010020010000200300004003740037111020110099100100100001000007102162239479100001004003840038400384003840038
1020440037300000613940725101001001000010010296616570690814005340037400373810803387451010020010000200300004003740037111020110099100100100001000007102162239479100001004003840038400384003840038
1020440037300000613940725101001001000010010000500570690814001840037400373810803387451010020010000200300004003740037111020110099100100100001000007102162239479100001004003840038400384003840038
1020440037300000613940725101001001000010010000500570690814001840037400373810803387451010020010000200300004003740037111020110099100100100001000007102162239479100001004003840038400384003840038
1020440037300000843940725101001001000010010000500570690804001840037400373810803387451010020010000200300004003740037111020110099100100100001000007102162239479100001004003840038400384003840038
1020440037299000613940725101001001000010010000500570690804001840037400373810803387451010020010000200300004003740037111020110099100100100001000007102162239479100001004003840038400384003840038
1020440037301000613940725101001001000010010000500570690804001840037400373810803387451010020010000200300004003740037211020110099100100100001000007102162239479100001004003840038400384003840038
10204400373000006139407251010010010000100100005005706908140018400374003738108033874510100200100002003000040037400371110201100991001001000010001807102162239479100001004003840038400384003840038
1020440037299000613940725101001001000010010000500570690814001840037400373810803387451010020010000200300004003740037111020110099100100100001000007102162239479100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)0318191e1f3a3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)696d6edispatch stall (70)72scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024400372990000061394072510010101000010100005057069084001840037400373813003387671001020100002030000400374003711100211091010100001000640216223947310000104003840038400384003840038
10024400373000000061394072510010101000010100005057069084001840037400373813003387671001020100002030000400374003711100211091010100001000640216223947310000104003840038400384003840038
10024400372990000061394072510010101000010100005057069084001840037400373813003387671001020100002030000400374003711100211091010100001000640216223947310000104003840038400384003840038
10024400373000000061394072510017101000010100005057069084001840037400373813003387671001020100002030000400374003711100211091010100001000640216223947310000104003840038400384003840038
100244003730000150061394072510010101000010100005057069084001840037400373813003387671001020100002030000400374003711100211091010100001000640216223947310000104003840038400384003840038
10024400373000000061394072510010101000010100005057069084001840037400373813003387671001020100002030000400374003711100211091010100001060640216223947310000104003840038400384003840038
10024400373000000061394072510010101000010100005057069084001840037400373813003387671001020100002030000400374003711100211091010100001000640216223947310000104003840038400384003840038
10024400372990000061394072510010101000010100005057069084001840037400373813003387671001020100002030000400374003711100211091010100001000640216223947310000104003840038400384003840038
10024400373000000061394072510010101000010100005057069084001840037400853813003387671001020100002030000400374003711100211091010100001000640216223947310000104003840038400384003840038
10024400373000000061394072510010101000010100005057069084001840037400373813003387671001020100002030000400374003711100211091010100001000640216223947310000104003840038400384003840038

Test 4: Latency 1->3

Code:

  fmlal v0.2s, v1.2h, v0.2h
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)0308090b18191e1f3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa0a1a6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020440037299000000061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000000071011611394790100001004003840038400384003840038
1020440037300000000061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000000071011611394790100001004003840038400384003840038
1020440037300000000061394072510100100100001001000050057069080400184003740037381163387451010020010000200300004003740037111020110099100100100001000000071011611394790100001004003840038400384003840038
1020440037299000000061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000000071011611394790100001004003840038400384003840038
1020440037299000000061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000000071011611394790100001004003840038400384003840038
1020540037300000000061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000000071011611394790100001004003840038400384003840038
1020440037300000000061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000000074111611394790100001004003840038400384003840038
1020440037300000000061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000000073911611394790100001004003840085400384003840038
1020440037300000000061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000000071011611394790100001004003840038400384003840038
1020440037300000000061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000000071011611394790100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)0308090b18191e1f3a3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696b6d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa0a1a6a8a9acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002440037300000000008239407251001010100001010000505706908040018040037400373813033876710010201000020300004003740037111002110910101000010000000026402162239473010000104003840038400384003840038
100244003729900000216006139407251001010100001010000505706908040018040037400373813033876710010201000020300004003740037111002110910101000010000000006402162239473010000104003840038400384003840038
100244003729900000447006139407251001010100001010000505706908040018040037400373813033876710010201000020300004003740037111002110910101000010000000006402162239473010000104003840038400384003840038
100244003730000000261006139407251001010100001010000505706908040018040037400373813033876710010201000020300004003740037111002110910101000010000000006402162239473010000104003840038400384003840038
100244003730000000231006139407251001010100001010000505706908040018040037400373813033876710010201000020300004003740037111002110910101000010000000006402162239473010000104003840038400384003840038
100244003730000000435006139407251001010100001010000505706908040018040037400373813033876710010201000020300004003740037111002110910101000010000000006402162239473010000104003840038400384003840038
10024400373000000015006139407251001010100001010000505706908040018040037400373813033876710010201000020300004003740037111002110910101000010000000006402162239473010000104003840038400384003840038
100244003729900000282006139407251001010100001010000505706908040018040037400373813033876710010201000020300004003740037111002110910101000010000000006402162239473010000104003840038400384003840038
100244003730000000342006139407251001010100001010000505706908040018040037400373813033876710010201000020300004003740037111002110910101000010000000006402162239473010000104003840038400384003840038
100244003730000000000695739326200100621810048121133265570830404001804008540037381303387671001020101612030000400374003741100211091010100001002300322352083131054439885510000104051340508405104055740509

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  fmlal v0.2s, v8.2h, v9.2h
  movi v1.16b, 0
  fmlal v1.2s, v8.2h, v9.2h
  movi v2.16b, 0
  fmlal v2.2s, v8.2h, v9.2h
  movi v3.16b, 0
  fmlal v3.2s, v8.2h, v9.2h
  movi v4.16b, 0
  fmlal v4.2s, v8.2h, v9.2h
  movi v5.16b, 0
  fmlal v5.2s, v8.2h, v9.2h
  movi v6.16b, 0
  fmlal v6.2s, v8.2h, v9.2h
  movi v7.16b, 0
  fmlal v7.2s, v8.2h, v9.2h
  movi v8.16b, 9
  movi v9.16b, 10

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2508

retire (01)cycle (02)031e3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6escheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160204200881502314025801001008000010080000500640000120046200652006532380100200800002002400002006520065111602011009910010016000010001011121611200621600001002006620066200662006620066
1602042006515004025801001008000010080000500640000120046200652006532380100200800002002400002006520065111602011009910010016000010001011111611200621600001002006620066200662006620066
1602042006515104025801001008000010080000500640000120046200652006532380100200800002002400002006520065111602011009910010016000010001011111611200621600001002006620066200662006620066
1602042006515004025801001008000010080000500640000120046200652006532380100200800002002400002006520065111602011009910010016000010001011111611200621600001002006620066200662006620066
1602042006515006825801001008000010080000500640000120046200652006532380100200800002002400002006520065111602011009910010016000010001011111611200621600001002006620066200662006620066
1602042006515004025801001008000010080000500640000120046200652006532380100200800002002400002006520065111602011009910010016000010011011111611200621600001002006620066200662006620066
1602042006515104025801001008000010080000500640000120046200652006532380100200800002002400002006520065111602011009910010016000010001011111611200621600001002006620066200662006620066
1602042006515004025801001008000010080000500640000120046200652006532380100200800002002400002006520065111602011009910010016000010001011111611200621600001002006620066200662006620066
16020420065150364025801001008000010080000500640000120046200652006532380100200800002002400002006520065111602011009910010016000010001011111611200621600001002006620066200662006620066
1602042006515004025801001008000010080000500640000120046200652006532380100200800002002400002006520065111602011009910010016000010001011111611200621600001002006620066200662006620066

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2509

retire (01)cycle (02)031e1f3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)5f6061696d6escheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa1a6a8accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0eaec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16002420102150120462780010108000010800005064000011102004020059200593238001020800002024000020059200591116002110910101600001000001002713712252113420056201160000102006020060200602006020060
1600242005915000462780010108000010800005064000011102004020059200593238001020800002024000020059200591116002110910101600001000001002813715252115420056201160000102006020060200602006020060
1600242005915100462780010108000010800005064000011102004020059200593238001020800002024000020059200591116002110910101600001040001002713715252216420056201160000102006020060200602006020060
1600242005915000462780010108000010800005064000011102004020059200593238001020800002024000020059200591116002110910101600001000001002813714252114320056201160000102006020060200602006020060
1600242005915000462780010108000010800005064000011102004920068200683238001020800002024000020068200681116002110910101600001000001002813715252115520056201160000102006020060200602006020060
1600242005915000462780010108000010800005064000011102004920068200683238001020800002024000020068200681116002110910101600001000001002713713252114420056201160000102006020060200602006020060
1600242005915000462780010108000010800005064000011102004920068200683238001020800002024000020068200681116002110910101600001000001003016823344224420065402160000102006920069200692006920069
160024200681501202362780010108000010800005064000011102004020059200593238001020800002024000020059200591116002110910101600001000001002713714252114420056201160000102006020060200602006020060
1600242005915000512780010108000010800005064000011102004020059200593238001020800002024000020059200591116002110910101600001000001002713713252113420056201160000102006020060200602006020060
1600242006815000522980010108000010800005064000001102004920068200683238001020800002024000020068200681116002110910101600001000101003116825344225320065402160000102006920069200692006920069

Test 6: throughput

Count: 12

Code:

  fmlal v0.2s, v12.2h, v13.2h
  fmlal v1.2s, v12.2h, v13.2h
  fmlal v2.2s, v12.2h, v13.2h
  fmlal v3.2s, v12.2h, v13.2h
  fmlal v4.2s, v12.2h, v13.2h
  fmlal v5.2s, v12.2h, v13.2h
  fmlal v6.2s, v12.2h, v13.2h
  fmlal v7.2s, v12.2h, v13.2h
  fmlal v8.2s, v12.2h, v13.2h
  fmlal v9.2s, v12.2h, v13.2h
  fmlal v10.2s, v12.2h, v13.2h
  fmlal v11.2s, v12.2h, v13.2h
  movi v12.16b, 13
  movi v13.16b, 14

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.3474

retire (01)cycle (02)03080b18191e1f373f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8acc5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
120204400393110000003619961251201001001200001001200005005851869041667416914003924932324997120100200120000200360000400394168611120201100991001001200001000007610116114003001200001004168740040416874004041687
120204416863000000003619961251201001001200001001200005005851993041667416864003924932324997120100200120000200360000400394168611120201100991001001200001000017610116114167701200001004004041687400404168740040
1202044168630000000006137966251201031001200031001200005005630640040020400394168626592324997120100200120000200360000400394168611120201100991001001200001000007610116114167701200001004004041687400404169240040
1202044003931200000006137966251201031001200031001200005005788190140020400394168626577324997120100200120000200360000400394168611120201100991001001200001000007610116114169501200001004004041692400404168740040
1202044003931200000036136429251201031001200031001200005005626928141672416864003924932324997120100200120000200360000416914003911120201100991001001200001000007610116114003001200001004168740040416874004041687
12020441686300000000161379662512010310012000310012000050056306400400204003941686265773249971201002001200002003600004003941686111202011009910010012000010011207610116114167701200001004168740040416874004041687
1202044168630000000006135689251201031001200031001200005005851869040020400394003924932324997120100200120000200360000400394168611120201100991001001200001000007610116114169501200001004004040040400404004041692
120204416913000000000619961251201001001200001001200005005630640040020400394168626577326644120100200120000200360000416864003911120201100991001001200001000007610116114003001200001004168740040416874004041687
1202044169130000000002329961251201001001200001001200005005851993040020400394169126577326644120100200120000200360000416864003911120201100991001001200001000007610116114003001200001004004041689400404168740040
1202044003931200000006137966251201011001200031001200005005851869041667416864003924932324997120100200120000200360000400394168611120201100991001001200001000007610116114003001200001004169240040416874004041687

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.3337

retire (01)cycle (02)03181e1f373a3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)6061696b6d6edispatch stall (70)72scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8accfd0d2d5d6daddinst fetch restart (de)e0? int output thing (e9)eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
12002440039300000006199612512001010120000101200005056306401041667040039400392495503250191200102012000020360000400394003911120021109101012000010007520514160554003000120000104004040040400404004040040
120024400392990000061379662512001010120000101200005056306401540020040039400392495503250191200102012000020360000400394003911120021109101012000010007520004160434168300120000104004040040400404004040040
12002440039300000006199612512001010120000101200005056306401540020040039400392495503250191200102012000020360000400394003911120021109101012000010007520504160444168300120000104004040040400404004040040
12002440039299000006199612512001010120000101200005056306401540020040039400392495503250191200102012000020360000400394003911120021109101012000010007520504160344003000120000104004040040400404004040040
12002440039300000006199612512001010120000101200005056306401540020340039400392495503250191200102012000020360000400394003911120021109101012000010007520005160354003000120000104004040089400404169240040
120024416913000000010399612512001010120000101200005056306401040020040039400392660003250191200102012000020360000400394003911120021109101012000010007520533160534003000120000104004040040400404004040040
120024400393000000061402742512001010120000101200005056306401540020040039400392495503250191200102012000020360000400394003911120021109101012000010007520534160444003000120000104004040040400404004040040
12002440039300000006199612512001010120000101200005056306401540020040039400392495503250191200102012000020360000400394003911120021109101012000010007520534160444003000120000104004040040400404004040040
12002440039299000006199612512001010120000101200005058518691040020040039400392495503250191200102012000020360000400394003911120021109101012000010007520533160334003000120000104004040040400404004040040
120024400393000000061996125120010101200001012000050563064015400200400394003924955032501912001020120000203600004003940039111200211091010120000104507520534160444003000120000104004040040400404004040040