Apple M1 Microarchitecture Research by Dougall Johnson

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

FMLS (vector, 2S)

Test 1: uops

Code:

  fmls v0.2s, v1.2s, v2.2s
  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)03191e3f4e51inst 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)accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100440373000613407251000100010005319080401840374037325833895100010003000403740371110011000073116113473100040384038403840384038
100440373000823407251000100010005319080401840374037325833895100010003000403740371110011000073116113473100040384038403840384038
100440373000613407251000100010005319080401840374037325833895100010003000403740371110011000073116113473100040384038403840384038
100440373000613407251000100010005319080401840374037325833895100010003000403740371110011000673116223473100040384038403840384038
100440373000613407251000100010005319080401840374037325833895100010003000403740371110011000073116113473100040384038403840384038
100440373000613407251000100010005319080401840374037325833895100010003000403740371110011000073116213473100040384038403840384038
100440373000613407251000100010005319080401840374037325833895100010003000403740371110011000073116113473100040384038403840384038
100440373000613407251000100010005319080401840374037325833895100010003000403740371110011000073116223473100040384038403840384038
100440373000613407251000100010005319080401840374037325833895100010003000403740371110011000073116223473100040384038403840384038
100440373100613407251000100010005319080401840374037325833895100010003000403740371110011000073116113473100040384038403840384038

Test 2: Latency 1->1

Code:

  fmls v0.2s, v1.2s, v2.2s
  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)031e3a3f4e51inst 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)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)9fa8accfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020440037299006139407251010010010000100100005005706908400184003740037381083387451010020010000200300004003740037111020110099100100100001000071012162239479100001004003840038400384003840038
10204400373000010339407251010010010000100100005005706908400184003740037381083387451010020010000200300004003740037111020110099100100100001000071012162239479100001004003840038400384003840038
1020440037300006139407251010010010000100100005885706908400184003740037381083387451010020010000200300004003740037111020110099100100100001000071012162239479100001004003840038400384003840038
1020440037300016139407251010010010000100100005005706908400184003740037381083387451010020010000200300004003740037111020110099100100100001000071012162239479100001004003840038400384003840038
1020440037299016139407251010010010000100100005005706908400184003740037381083387451010020010000200300004003740037111020110099100100100001000371012162239479100001004003840038400384003840038
1020440084301006139407251010010010000100100005005706908400184003740037381083387451010020010000200300004003740037111020110099100100100001000071012162239479100001004003840038400384003840038
1020440037300006139407251010010010000100100005005706908400184003740037381083387451010020010000200300004003740037111020110099100100100001000671012162339479100001004003840038400384003840038
1020440037300006139407251010010010000100100005005706908400184003740037381083387451010020010000200300004003740037111020110099100100100001000071013162239479100001004003840038400384003840038
10204400373000010339407251010010010000100100005005706908400184003740037381083387451010020010000200300004003740037111020110099100100100001000071012162239479100001004003840038400384003840038
1020440037300006139407251010010010000100100005005706908400184003740037381083387451010020010000200300004003740037111020110099100100100001000071012162239479100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)031e3f4e51inst 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)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)9fa7a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024400373000613940725100101010000101000050570690840018400374003738130338767100102010000203000040037400371110021109101010000100303640316223947310000104003840038400384003840038
10024400373000613940725100101010000101000050570690840018400374003738130338767100102010000203000040037400371110021109101010000100000640216223947310000104003840038400384003840038
10024400372990613940725100101010000101000050570690840018400374003738130338767100102010000203000040037400371110021109101010000100000640216223947310000104003840038400384003840038
1002440037300120613940725100101010000101000060570690840018400374003738130338767100102010000203000040037400371110021109101010000100000640216223947310000104003840038400384003840038
10024400373000613940725100101010000101000050570690840018400374003738130338767100102010000203000040037400371110021109101010000100000640216223947310000104003840038400384003840038
10024400843000613940725100101010000101000050570690840018400374003738130338767100102010000203000040037400371110021109101010000100140640316223947310000104008640038400384003840038
10024400373000613940725100101010000101000050570690840018400374003738130338767100102010000203000040037400371110021109101010000100000640216223947310000104003840038400384003840038
10024400373000613940725100101010000101000050570690840018400374003738130338767100102010000203000040037400371110021109101010000100000640216223947310000104003840038400384003840038
10024400373000613940725100101010000101000050570690840018400374003738130338767100102010000203000040037400371110021109101010000100000640216223947310000104003840038400384003840038
10024400373000613940725100101010000101000050570690840018400374003738130338767100102010000203000040037400371110021109101010000100000640216223947310000104003840038400384003840038

Test 3: Latency 1->2

Code:

  fmls v0.2s, v0.2s, v1.2s
  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)031e3f4e51inst 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)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)9fa0a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020440037300061394072510100100100001001000050057069080400180400374003738108033874510100200100002003000040037400371110201100991001001000010000007101161139479100001004003840038400384003840038
1020440037300061394072510100100100001001000050057069080400180400374003738108033874510100200100002003000040037400371110201100991001001000010000007101161139479100001004003840038400384003840038
10204400373000726394072510118100100001001000050057069081400180400374003738108033874510100200100002003000040037400371110201100991001001000010000007101161139479100001004003840038400384003840038
1020440037299061394072510100100100001001000050057069080400180400374003738108033874510100200100002003000040037400371110201100991001001000010000007101161139479100001004003840038400384003840038
1020440037300061394072510100100100001001000050057069080400180400374003738108033874510100200100002003000040037400371110201100991001001000010000037101161139479100001004003840038400384003840038
1020440037300061394072510100100100001001000050057069080400180400374003738108033874510100200100002003000040037400371110201100991001001000010000007101161139479100001004003840038400384003840038
10204400372990156394072510100100100001001000050057069080400180400374003738108033874510260200100002003000040037400371110201100991001001000010000007101161139479100001004003840038400384003840038
10204400372990104394072510100100100001001000050057069080400180400374003738108033874510100200100002003000040037400371110201100991001001000010000007101161139479100001004003840038400384003840038
1020440037300061394072510100100100001001000050057069080400180400374003738108033874510100200100002003000040037400371110201100991001001000010000007101161139479100001004003840038400384003840038
1020440037300061394072510100100100001001000050057069080400180400374003738108033874510100200100002003000040037400371110201100991001001000010000007101161139479100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)030b181e3f4e51inst 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)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)9fa0a1a8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100244003730000036739407251001010100001010000505706908400184003740037381303387671001020100002030000400374003711100211091010100001000000640316333947310000104003840038400384003840038
1002440037300000134139407251001010100001010000505706908400184003740037381303387671001020100002030000400374003711100211091010100001000000640316333947310000104003840038400384003840038
1002440037299000101339407251001010100001010000505706908400184003740037381303387671001020100002030000400374003711100211091010100001000000640316333947310000104003840038400384003840038
1002440037300000114739407251001010100001010000505706908400184003740037381303387671001020100002030000400374003711100211091010100001000000640316333947310000104003840038400384003840038
10024400373000006139407251001010100001010000505706908400184003740037381303387671001020100002030000400374003711100211091010100001000000640316333947310000104003840038400384003840038
100244003729900027339407251001010100001010000505706908400184003740037381303387671001020100002030000400374003711100211091010100001000130640316333947310000104003840038400384003840038
10024400373000016218739407251001010100001010000505706908400184003740037381303387671001020100002030132400834008411100211091010100001022100640316333947310000104003840038400384003840038
1002440037299001523339407251001010100001010000505706908400184003740037381303387671001020100002030000400374003711100211091010100001000000640316333947310000104003840038400384003840038
100244003730002029339407251001010100001010000505706908400184003740037381303387671001020100002030000400374003711100211091010100001000030640316533947310000104003840038400384003840038
1002440037300000175439407251001010100001010000505706908400184003740037381303387671001020100002030000400374003711100211091010100001000000640316333947310000104003840038400754003840038

Test 4: Latency 1->3

Code:

  fmls v0.2s, v1.2s, v0.2s
  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)03080b1e3f4e51inst 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)9fa8a9accdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204400373000001218394072510100100100001001000050057069084001840037400373810803387451010020010000200300004003740037111020110099100100100001000000710116113947927100001004003840038400384003840038
1020440037299000116039407251010010010000100100005005706908400184003740037381080338745101002001000020030000400374003711102011009910010010000100103071011611394790100001004003840038400384003840038
1020440037299000129939407251010010010000100100005005706908400184003740037381080338745101002001000020030000400374003711102011009910010010000100000071011611394790100001004003840038400384003840038
102044003730000036239407251010010010000100100005005706908400184003740037381080338745101002001000020030000400374003711102011009910010010000100000071011611394790100001004003840038400384003840038
102044003729900062239407251010010010000100101475005706908400184003740037381080338745101002001000020030000400374003711102011009910010010000100000071011611394790100001004003840038400384003840038
1020440037299000119539407251010010010000100100005005706908400184003740037381080338745101002001000020030000400374003711102011009910010010000100000071011611394790100001004003840038400384003840038
102044003730000051339407251010010010000100100005005706908400184003740037381080338745101002001000020030000400374003711102011009910010010000100000071011611394790100001004003840038400384003840038
1020440037300000129039407251010010010000100100005005706908400184003740037381080338745101002001000020030000400374003711102011009910010010000100000071011611394790100001004003840038400384003840038
1020440037300000206639407251010010010000100100005005706908400184003740037381080338745101002001000020030000400374003711102011009910010010000100000071011611394790100001004003840038400384003840038
1020440037300000124639407251010010010000100100005005706908400184003740037381080338745101002001000020030000400374003711102011009910010010000100000071011611394790100001004003840038400384003840038

1000 unrolls and 10 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)696d6edispatch 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)9fa0a1a6a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024400373000000000939394072510010101000010100005057069084001840037400373813033876710010201000020300004003740037111002110910101000010000000640216223947310000104003840038400384003840038
10024400372990000000681394072510010101000010100005057069084001840037400373813033876710010201000020300004003740037111002110910101000010000000640216223947310000104003840038400384003840038
10024400373000000000932394072510010101000010100005057069084001840037400373813033876710010201000020300004003740037111002110910101000010000000640216223947310000104003840038400384003840038
1002440037300000001410945394072510010101000010100005057069084001840037400373813033876710010201000020300004003740037111002110910101000010000000640216223947310000104003840038400384003840038
10024400373000000000831394072510010101000010100005057069084001840037400373813033876710010201000020300004003740037111002110910101000010000000640216223947310000104003840038400384003840038
10024400373000000000712394072510010101000010100005057069084001840037400373813033876710010201000020300004003740037111002110910101000010000000640216223947310000104003840038400384003840038
10024400372990000000893394072510010101000010100005057069084001840037400373813033876710010201000020300004003740037111002110910101000010000000640216223947310000104003840038400384003840038
10024400373000000000210394072510010101000010100005057069084001840037400373813033876710010201000020300004003740037111002110910101000010000000640216223947310000104003840038400384003840038
10024400372990000000314394072510010101000010100005057069084001840037400373813033876710010201000020300004003740037111002110910101000010000000640216233947310000104003840038400384003840038
10024400373000000000145394072510010101000010100005057069084001840037400373813033876710010201000020300004003740084111002110910101000010000000640216223947310000104003840038400384003840038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  fmls v0.2s, v8.2s, v9.2s
  movi v1.16b, 0
  fmls v1.2s, v8.2s, v9.2s
  movi v2.16b, 0
  fmls v2.2s, v8.2s, v9.2s
  movi v3.16b, 0
  fmls v3.2s, v8.2s, v9.2s
  movi v4.16b, 0
  fmls v4.2s, v8.2s, v9.2s
  movi v5.16b, 0
  fmls v5.2s, v8.2s, v9.2s
  movi v6.16b, 0
  fmls v6.2s, v8.2s, v9.2s
  movi v7.16b, 0
  fmls v7.2s, v8.2s, v9.2s
  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)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)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)9fa8a9acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16020420065150004025801001008000010080000500640000120046200652006532380100200800002002400002006520065111602011009910010016000010000001011421645200621600001002006620066200662006620066
16020420065150008625801001008000010080000500640000120046200652006532380100200800002002400002006520065111602011009910010016000010000001011441635200621600001002006620066200662006620066
160204200651500070525801001008000010080000500640000120046200652006532380100200800002002400002006520065111602011009910010016000010010001011451645200621600001002006620066200662006620066
160204200651500014725801001008000010080000500640000120046200652006532380100200800002002400002006520065111602011009910010016000010000001011441654200621600001002006620066200662006620066
160204200651501210812825801001008000010080000500640000120046200652006532380100200800002002400002006520065111602011009910010016000010000001011451655200621600001002006620066200662006620066
160204200651500014925801001008000010080000500640000120046200652006532380100200800002002400002006520065111602011009910010016000010000001011551655200621600001002006620066200662006620066
160204200651500032525801001008000010080000500640000120046200652006532380100200800002002400002006520065111602011009910010016000010000001011441643200621600001002006620066200662006620066
160204200651500028225801001008000010080000500640000120046200652006532380100200800002002400002006520065111602011009910010016000010000001011441644200621600001002006620066200662006620066
160204200651510010525801001008000010080000500640000120046200652006532380100200800002002400002006520065111602011009910010016000010010001011551654200621600001002006620066200662006620066
16020420065151004025801001008000010080000500640000120046200652006532380100200800002002400002006520065111602011009910010016000010000001011451645200621600001002006620066200662006620066

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2506

retire (01)cycle (02)0318191e1f3f51inst 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)5f60696d6escheduler 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)9fa8accdcfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16002420053150000090258001212800001280000626400001120028200472004732380012208000020240000200472004711160021109101016000010000100303119202116720044215160000102004820048200482004820048
160024200471500000134258001212800001280000626400001120028200472004732380012208000020240000200472004711160021109101016000010200100303117202117420044215160000102004820048200482004820048
160024200471500000174258001212800001280000626400001120028200472004732380012208000020240000200472004711160021109101016000010000100303114202114720044215160000102004820048200482004820048
16002420047150000067258001212800001280000626400001120028200472004732380012208000020240000200472004711160021109101016000010000100273117202116420044215160000102004820048200482004820048
16002420047150009046258001212800001280000506400001120028200472004732380012208000020240000200472004711160021109101016000010000100303117202117620044215160000102004820048200482004820048
1600242004715000013246258001212800001280000626400001120028200472004732380012208000020240000200472004711160021109101016000010000100273116202117420044215160000102004820048200482004820048
160024200471500000136258001212800001280000626400001120028200472004732380012208000020240000200472004711160021109101016000010000100303117202114720044215160000102004820048200482004820048
160024200471510000134258001212800001280000626400001120028200472004732380012208000020240000200472004711160021109101016000010000100273115202117520044215160000102004820048200482004820048
16002420047150000046258001212800001280000626400001120028200472004732380012208000020240000200472004711160021109101016000010000100303117202117420112215160000102004820048200482004820048
16002420047150000046258001212800001280000626400001120028200472004732380012208000020240000200472004711160021109101016000010000100303117202114720044215160000102004820048200482004820048

Test 6: throughput

Count: 16

Code:

  fmls v0.2s, v16.2s, v17.2s
  fmls v1.2s, v16.2s, v17.2s
  fmls v2.2s, v16.2s, v17.2s
  fmls v3.2s, v16.2s, v17.2s
  fmls v4.2s, v16.2s, v17.2s
  fmls v5.2s, v16.2s, v17.2s
  fmls v6.2s, v16.2s, v17.2s
  fmls v7.2s, v16.2s, v17.2s
  fmls v8.2s, v16.2s, v17.2s
  fmls v9.2s, v16.2s, v17.2s
  fmls v10.2s, v16.2s, v17.2s
  fmls v11.2s, v16.2s, v17.2s
  fmls v12.2s, v16.2s, v17.2s
  fmls v13.2s, v16.2s, v17.2s
  fmls v14.2s, v16.2s, v17.2s
  fmls v15.2s, v16.2s, v17.2s
  movi v16.16b, 17
  movi v17.16b, 18

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2502

retire (01)cycle (02)0308191e373f4e51inst 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)9fa0a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602044042730000004202516010010016000010016000050012800001400214004040040199733199981601002001600002004800004004040040111602011009910010016000010000001011021611400371600001004004140041400414004141228
1602044004029900004202516010010016000010016000050012800001400214004040040199733199981601002001600002004800004119041205111602011009910010016000010000001011011611400371600001004122840041400414004140041
16020440040300000070702516010010016000010016012450012800001400214004040040199733199981601002001600002004800004004041190111602011009910010016000010000001011011611400371600001004004140044423194004140041
16020440040309000604202516012210016000010016000050012800000400224004141227210953199981601002001600002004800004004041227111602011009910010016000010000001011011611400371600001004004141191412064119141228
1602044004030900014202516016010016002210016000050012800000412084004140040210953200011601002001600002004800004004040040111602011009910010016000010000001011011611412241600001004004141228400414004140041
1602044004030000004202516010010016000010016000050012800000412084004041227199733199981601002001600002004800004004040040111602011009910010016000010000001011011611400371600001004004140041400414004140041
1602044004030000004202516010010016000010016000050012800000400214119041205199733211481601002001600002004800004120440040111602011009910010016000010000001011011611400371600001004004141191412064004141228
1602044004030000006144852516012210016002210016000050057179391400214004341190199733199981601002001600002004800004119041205111602011009910010016000010000001011011611412021600001004004141191412064004141191
1602044004030000004202516010010016006010016000050057179391400214004040040199733211631601002001600002004800004004041227111602011009910010016000010000001011011611400371600001004004140041412284004140041
16020440040308000051746142516010010016000010016000050012800001400214004040040199733199981601002001600002004800004004040040111602011009910010016000010000001011011611412241600001004004141191400444004140041

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2502

retire (01)cycle (02)031e373f4e51inst 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)5f60696d6edispatch 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)9fa1a6a8acc2cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1600244004931600470251600101016000010160000501280000114002140040422941999632226116001020160000204800004229440040111600211091010160000100000010022311201621120740037208160000104004140041400414004142295
160024400403090063788962516001010160000101600005012800001141226400404004019996222122516001020160000204800004004042294111600211091010160000100000010026621161622219940037408160000104004140041400414004140041
160024400403000225302516001010160000101600005012800000142275400404124521173321225160010201600002048000040040400401116002110910101600001000000100246221916221202240039408160000104004140041400414004140041
16002440040300005302516001010160035101600005012800001142275422944124519996320020160010201600002048000040040422941116002110910101600001000000100246121916412922400374023160000104004141246422954004142295
16002440040309453355302516001010160000101600005012800000142277400404004019996320020160010201600002048000042294400401116002110910101600001000000100246221916422922423154016160000104004140041400414124640042
160024400403000073025160010101600351016000050128000001400214004040040199963200201600102016000020480000400404124511160021109101016000010000001002462219164222023400374016160000104004140041400414004140041
1600244004031700534695251600101016000010160000501280000014002140040400401999632002016001020160000204800004004040040111600211091010160000100000010024622816422199400374016160000104004141246400414004142295
160024400913004380718025160010101600351016000050572107311400214004040040199963222981600102016000020480000422944004011160021109101016000010000001002261181641119940037407160000104004140041422824229740041
160024400403000067889625160010101600001016000050128000011400214004040040199963222981600102016000020480000400404004011160021109101016000010000001002231181621119940037208160000104004142295400414004140041
16002440040317053470251600631016005310160000501280000114002140040423181999632002016001020160000204800004004040040111600211091010160000100000010022312191622120840037207160000104004140041400424004140041