Apple M1 Microarchitecture Research by Dougall Johnson

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

SQDMLSL2 (by element, 4S)

Test 1: uops

Code:

  sqdmlsl2 v0.4s, v1.8h, v2.h[1]
  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)033f4e51inst 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
10043037226125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037236125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037236125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037236125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037236125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037226125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037236125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037236125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037226125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037226125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  sqdmlsl2 v0.4s, v1.8h, v2.h[1]
  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): 3.0037

retire (01)cycle (02)03080b18191e1f3a3f4e51inst 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)9fa1a6a8accfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500000007129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000710131622296340100001003003830038300383003830038
102043003722500000006129548251010010010000100100005334277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000710121622296340100001003003830038300383003830038
102043003722500000006129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000710121622296340100001003008230038300383003830038
102043003722500000006129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000710121622296340100001003003830038300383003830038
102043003722500000006129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000710121622296340100001003003830038300383003830038
102043003722500000006129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000710121632296340100001003003830038300383003830038
1020430037225000012006129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000033710121622296340100001003003830038300383003830038
102043003722500000006129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000710121622296340100001003003830038300383003830038
102043003722500000006129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000710121622296340100001003003830038300383003830038
102043003722500000006129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000710121622296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)031e1f3f4e51inst 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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225006129548101100101010000101000050427731303001830037300372828732876710010201000020300003003730083211002110910101000010500640416342963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010200640316332963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010200640316332963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640316362966810000103003830038300383003830038
10024300372250598612954825100101010000101000050427731303001830037300372828732876710161201016320300003003730037111002110910101000010200640316332963010000103003830038300383003830038
100243003723300612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
100243003722400612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010200640316332963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010100640316332963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010100640316332963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  sqdmlsl2 v0.4s, v0.8h, v1.h[1]
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0318191e1f3f4e51inst 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)9fa1a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000239295482510100100100001001000050042773131300180300373003728265328745101002001000020030000300373003711102011009910010010000100211141371011611296340100001003003830038300383003830038
1020430037225002406129548251010010010000100100005004277313130018030037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
1020430037225000049229548251010010010000100100005004277313030018030037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
102043003722500608429548251010010010000100100005004277313130018030037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
1020430037224001506129548251010010010000100100005004277313130018030037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
1020430037225000012429548251010010010000100100005004277313130018030037300372826532874510100200100002003000030037300373110201100991001001000010000071011611296340100001003003830038300383003830181
1020430085225000010729548251010010010000100100005004277313130018030037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313130018030037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
102043003722500010818929548251010010010000100100005004277313130018030037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
10204300372250000191295482510100100100001001000050042773131300180300373003728265328745101002001000020030000300373003711102011009910010010000100051071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

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)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)9fa8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722506129548251001010100001010000504277313130018030037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313030018030037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103013330038300383003830038
1002430037225096429548251001010100001010000504277313130018030037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313130018030037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313130018030037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313130018030037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722406129548251001010100001010000504277313130018030037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038301793003830038
100243003722506129548251001010100001210000504277313130018030037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722507529548251001010100001010000504277313130018030037300372828732876710010201000020300003003730037111002110910101000010000640216232963010000103003830038300383003830038
100243003722406129548251001010100001010000504277313130018030037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  sqdmlsl2 v0.4s, v1.8h, v0.h[1]
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0318191e3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000212295482510100100100001001000050042773130300183003730037282650328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300183003730037282650328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300183003730037282650328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722500061295484410100100100001001000050042773130300183003730037282650328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300183003730037282650328745101002001000020030000300373003711102011009910010010000100007101161229634100001003003830038300383003830038
102043003722400661295482510100100100001001000050042773130300183003730037282650328745101002001000020030000300853003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300183003730037282650328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722400061295482510100100100001001000050042773130300183003730037282650328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300183003730037282650328745101002001000020030000300373003711102011009910010010000100007101331129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300183003730037282650328745101002001000020030000300373003711102011009910010010000100037101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0307080a0b18191e1f3a3f4e51inst 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)696b6d6edispatch 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)9fa0a6a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372241010000021102954825100101010000101000050427731330018030037300372828703287671001020100002030000300373003711100211091010100001000000644101651029630010000103003830038300383003830038
100243003722510100000211029548251001010100001010000504277313300180300373003728287032876710010201000020300003003730037111002110910101000010000006441016101029630010000103003830038300383003830038
100243003722410100000219629548251001010100001010000504277313300180300373003728287032876710010201000020300003003730080111002110910101000010000006441016111029630010000103003830038300383003830038
10024300372251010000021752954825100101010000101000050427731330018030037300372828703287671001020100002030000300373003711100211091010100001000000644101610529630010000103003830038300383003830038
10024300372251010000028929548251001010100001010000504277313300180300373003728287032876710010201000020300003003730037111002110910101000010000006441016101129630010000103003830038300383003830038
1002430037225101000002198295482510010101000010100005042773133001803003730037282870328767100102010000203000030037300371110022109101010000100000064481611829630010000103003830038300383003830038
10024300372251010000021312954825100101010000101000050427731330018030037300372828703287671001020100002030000300373003711100211091010100001000000644516111029630010000103003830038300383003830038
100243003722510100000217329548251001010100001010000504277313300180300373003728287032876710010201000020300003003730037111002110910101000010000006441016101029630010000103003830038300383003830038
100243003722510100000230329548251001010100001010000504277313300180300373003728287032876710010201000020300003003730037111002110910101000010000006441016101029630010000103003830038300383003830038
100243003722510100000213129548251001010100001010000504277313300180300373003728287032876710010201000020300003003730037111002110910101000010000006441016101229630010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  sqdmlsl2 v0.4s, v8.8h, v9.h[1]
  movi v1.16b, 0
  sqdmlsl2 v1.4s, v8.8h, v9.h[1]
  movi v2.16b, 0
  sqdmlsl2 v2.4s, v8.8h, v9.h[1]
  movi v3.16b, 0
  sqdmlsl2 v3.4s, v8.8h, v9.h[1]
  movi v4.16b, 0
  sqdmlsl2 v4.4s, v8.8h, v9.h[1]
  movi v5.16b, 0
  sqdmlsl2 v5.4s, v8.8h, v9.h[1]
  movi v6.16b, 0
  sqdmlsl2 v6.4s, v8.8h, v9.h[1]
  movi v7.16b, 0
  sqdmlsl2 v7.4s, v8.8h, v9.h[1]
  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)0307080a191e3f51inst 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)696d6escheduler 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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16020420089150101002925801161008001610080028500640196200452006520065612801282008002820024008420065200651116020110099100100160000100001111011931611200621600001002006620066200662006620066
16020420065150101002925801161008001610080028500640196200452006520065612801282008000020024000020064200641116020110099100100160000100000001011221622200611600001002006520065200652006520065
16020420064150000003925801001008000010080000500640000200452006420064322801002008000020024000020064200641116020110099100100160000100000001011221622200611600001002006520065200652006520065
16020420064150000008125801001008000010080000500640000200452006420064322801002008000020024000020064200641116020110099100100160000100000001011221622200611600001002006520065200652006520065
16020420064150000063925801001008000010080000500640000200452006420064322801002008000020024000020064200641116020110099100100160000100000001011221622200611600001002006520065200652006520065
1602042006415000003123925801001008000010080000500640000200452006420064322801002008000020024000020064200641116020110099100100160000100000001011221622200611600001002006520065200652006520065
16020420064150000003925801001008000010080000500640000200452006420064322801002008000020024000020064200641116020110099100100160000100000001011224922200611600001002006520065200652006520065
16020420064150000003925801001008000010080000500640000200452006420064322801002008000020024000020064200641116020110099100100160000100000001011221622200611600001002006520065200652014620065
16020420144150010103925801001008000010080000500640000200452006420064322801002008000020024000020064200641116020110099100100160000100000001011221622200611600001002006520065200652006520065
160204200641500000041925801001008000010080000500640000200452006420064322801002008000020024000020064200641116020110099100100160000100000001011221622200611600001002006520065200652006520065

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03070a1e1f3a3f51inst 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)5f60696b6d6escheduler 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)9fa8acc5cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16002420079150000009272580012128000012800006264000011200270200462004632280012208000020240000200462004611160021109101016000010000100293116202118820043215160000102004720047200472004720047
1600242004615000000452580012128000012800006264000010200270200462004632280012208000020240000200462004611160021109101016000010000100313119202116920043215160000102004720047200472004720047
1600242004615000000452580012128000012800006264000011200270200462004632280012208000020240000200462004611160021109101016000010000100293119202119920043215160000102004720047200472004720047
1600242004615000000452580012128000012800006264000011200270200462004632280012208000020240000200502005011160021109101016000010000100313229264226920049215160000102005320053200512005120053
1600242005215000000512580012128000012800006264000001200270200502004632280012208000020240000200502005011160021109101016000010000100313226244226920047230160000102005320053200512005120053
1600242005015000000562580012128000012800006264000001200310200502005032280012208000020240000200502005011160021109101016000010001100356229594226920047231160000102005320053200512005120051
1600242005015000000452580012128000012800006264000011200270200462004632280012208000020240000200502005011160021109101016000010053001003031110202116620043215160000102004720047200472004720047
1600242004615000600512580012128000012800006264000000200310200502005032280012208000020240000200502005011160021109101016000010000100293119202119920043215160000102004720047200472004720047
1600242004615000000512580012128000012800006264000011200270200462004632280012208000020240000200462004611160021109101016000010000100293118202115520043215160000102004720047200472004720047
1600242004615000000452580012128000013800006264000010200270200462004632280012208000020240000200462004611160021109101016000010000100293119202119620043215160000102004720047200472004720047

Test 6: throughput

Count: 12

Code:

  sqdmlsl2 v0.4s, v12.8h, v13.h[1]
  sqdmlsl2 v1.4s, v12.8h, v13.h[1]
  sqdmlsl2 v2.4s, v12.8h, v13.h[1]
  sqdmlsl2 v3.4s, v12.8h, v13.h[1]
  sqdmlsl2 v4.4s, v12.8h, v13.h[1]
  sqdmlsl2 v5.4s, v12.8h, v13.h[1]
  sqdmlsl2 v6.4s, v12.8h, v13.h[1]
  sqdmlsl2 v7.4s, v12.8h, v13.h[1]
  sqdmlsl2 v8.4s, v12.8h, v13.h[1]
  sqdmlsl2 v9.4s, v12.8h, v13.h[1]
  sqdmlsl2 v10.4s, v12.8h, v13.h[1]
  sqdmlsl2 v11.4s, v12.8h, v13.h[1]
  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): 0.2503

retire (01)cycle (02)03070b18191e1f373a3f4e51inst 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)9fa1a6a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1202043006022500001560170231025120118100120000100120000500960000130020300393003914973314997120100200120000200360000300393003911120201100991001001200001000000076101161130919251200001003004031749300403004030040
12020430039225000000004102512010010012000110012000062699000003002030039300391582831670612010020012000020036000030039300411112020110099100100120000100000007610116113003601200001003004030041300403004030040
120204300392370000001041025120100100120000100120000500960000130020300413003914973316706120100200120000200360000300393174811120201100991001001200001000000076101161130036251200001003004031738300403004031738
12020431737225000000004102512010110012001810012000050096000013002030922300391665331670612010020012000020036000030040300391112020110099100100120000100000007610116513003601200001003004030040300403004030041
1202043003922500223213241124802512010012012015411412011361397425513023331559300391497310150221202222001202102003609483015430266211202011009910010012000010000094507635232113008601200001003004030040300403004030170
120204301062280011132104008337136712010010012008410012000050096000003002030039300391665314150271203252001200002003600003003930040111202011009910010012000010000047027610116113174501200001003004030040317493004431749
120204317482250000000113740177121017125120734123121039626184950403086130429311871581945152621210622041209502003621783092730723811202011009910010012000010022136802773851034530656281200001003049930801309073051031060
120204304792266110101065616930181101951210891241208971241215176322180790131168314143071615682501551312117820212106720236278731017305561111202011009910010012000010020051034784321293330454221200001003086531411324603072730514
12020430876230000015018010302512010010012000010012000050096000013172930040300391497331590012010020012000020036000030039300391112020110099100100120000100000007610517113003701200001003004030923300403092330040
120204300392250000000042302512010010012000010012000050099000013002030039317481497331670612010020012000020036000030039317481112020110099100100120000100000007610116113003601200001003174930040300403004031749

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2503

retire (01)cycle (02)03181e373f51inst 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)9fa1a8accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
12002430048225024046251200101012000010120000509600001130020300393003914996315019120010201200002036000030039300391112002110910101200001000075246111816212106300360155120000103004030923300403004030040
120024300392380604625120010101200001012000050960000113002030951300411499631501912001020120000203600003003930039111200211091010120000100007522311416211128300360305120000103004030040300403004030040
120024300392250420462512001010120000101200005096000011300203003930039149963150191200102012000020360000300393003911120021109101012000010000752231141621186300360155120000103004030040309233004030040
12002430039225060522512013410120000101200005096000011300203003930039149963150191200102012000020360000300393003911120021109101012000010000752231161621165300360155120000103004030040300403004030040
120024300392250004625120010101200001012000050960000113002030039300421499631501912001020120000203600003174830039111200211091010120000100007522311416211104300360155120000103004030040300403004030040
120024300392250604625120010101200001012000050960000013002030039300391499631590212001020120000203600003003930039111200211091010120000100007522311101621164300360155120000103004030040300403004030040
1200243003922506046251200101012000010120000509600001130020300393003916676315019120010201200002036000030039317481112002110910101200001000075226211016211410300360155120000103004030040300403004030040
1200243003922403904625120045101200001012000050960000113002030039300391499631501912001020120000203600003003930039111200211091010120000100007522311101621164300360155120000103004030040300403004030040
1200243174822508404625120010101200001012000050960000113002030039317501499631501912001020120000203600003003930922111200211091010120000100007522311416211410300360155120000103004030040300403004030040
12002430039225030462512001010120000101200005096000011300203003930040149963150191200102012000020360000300393003911120021109101012000010000752461141621146300360155120000103004030040300403004030040