Apple M1 Microarchitecture Research by Dougall Johnson

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

SMLSL2 (by element, 4S)

Test 1: uops

Code:

  smlsl2 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
10043037236125482510001000100039831313018303730372415328951000100030003037303711100110001073116112630100030383038303830383038
10043037236125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037236125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372210725482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037236125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037228225482510001000100039831303018303730372415328951000100030003037303711100110001073116112630100030383038303830383038
10043037236125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037236125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037236125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037228225482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  smlsl2 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)9fa0a1a6a8a9acc2c5branch mispredict (cb)cdcfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500000016129548251010010010000100100005004277313300183003730037282727287401010020010008200300243003730037111020110099100100100001000000000111717001600296460100001003003830038300383003830038
102043003722500000006129548251010010010000100100005004277313300183003730037282727287411010020010008200300243003730037111020110099100100100001000000000111718001600296960100001003003830038300383003830038
102043003722500000006129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000000710121622296340100001003003830038300383003830038
102043003722500000006129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000001000000710121622296340100001003003830038300383003830038
102043003722500000006129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000000710121622296340100001003003830038300383003830038
1020430037225000000061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000000008471485242988510100001003032430371303603037230322
102043032422710679241760451029512162101681241005612410894522428681230234303223037128273372887411165210114842283348030372303738110201100991001001000010042204200030000869123322298868100001003032430370303733013330361
102043032422711779366160459629484184101561131005612311043615428545530126303683032228291392886511168222111642063349530372303708110201100991001001000010002010191032000868127223298948100001003037330372303683018030369
102043037422700000006129548251010010010007100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000000710121622296340100001003003830085300383003830038
102043003722500000006129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000000710121622296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

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)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)9fa0a8acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037224006129548251001010100001010000504277313030018030037300372828703287671001020100002030000300373003711100211091010100001000300640516322963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018030037300372828703287671001020100002030000300373003711100211091010100001000000640316232963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313130018030037300372828703287671001020100002030000300373003711100211091010100001000000640316322963010000103003830038300383003830038
10024300372250072629548251001010100001010000504277313030018030037300372828703287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
10024300372250015629548251001010100001010000504277313030018030037300372828703287671001020100002030000300373003711100211091010100001000000640216232963010000103003830038300383003830038
10024300372240053629548251001010100001010000504277313130018030037300372828703287671001020100002030000300373003711100211091010100001000000640216432963010000103003830038300383003830038
10024300372240015629548251001010100001010000504277313130018030037300372828703287671001020100002030000300373003711100211091010100001000000640216332963010000103003830038300383003830038
100243003722518031329548251001010100001010000504277313030018030037300372828703287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018030037300372828703287671001020100002030000300373003711100211091010100001000000640216332963010000103003830038300383003830038
1002430037224006129548251001010100001010000504277313030018030037300372828703287671001020100002030000300373003711100211091010100001000000640316332963010000103003830083300383003830038

Test 3: Latency 1->2

Code:

  smlsl2 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)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)9fa1a8a9acc2cfd5d6ddinst fetch restart (de)e0ec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225126129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
1020430037225306129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000100071011611296340100001003003830038300383003830038
1020430037225276129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
1020430037225186129548251010010010000100100005004277313300183003730037282653288161010020010000200300003003730037111020110099100100100001000000071011622296340100001003003830038300383003830038
1020430037225426129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
1020430037225216129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
1020430037225336129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
1020430037225308929548251010010010000100100005004277313300183003730037282653288161010020010000200300003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
1020430037225276129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038

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)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)9fa8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037224061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000640216122963010000103003830038300853003830038
1002430037225061295482510010101000710100005042773133001830037300372828732876710010221000020300003003730037111002110910101000010100640216222963010000103003830038300383003830038
100243003722542661295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372251561295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372254261295482510010101000010100005042773133001830037300372828732882310010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372254561295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372251261295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  smlsl2 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)03081e1f3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225018006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372240006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722501506129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100007321161129634100001003003830038300383003830038
10204300372240306129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722505106129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038

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)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)9fa0a1a6a7a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500000000061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000006404162229630010000103003830038300383003830038
1002430037225000000150061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
1002430037225000000150061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
1002430037225000000150061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
1002430037224000000120061295482510010101000010100005042773130300183003730037282873288411001020100002030000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
1002430037225000000270061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
1002430037225000000180061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
1002430037225000000390061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
1002430037225000000180061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372250000002400612954825100101010000101000050427731303001830037300372828721287671001020100002030000300373003711100211091010100001000000006402162229630010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  smlsl2 v0.4s, v8.8h, v9.h[1]
  movi v1.16b, 0
  smlsl2 v1.4s, v8.8h, v9.h[1]
  movi v2.16b, 0
  smlsl2 v2.4s, v8.8h, v9.h[1]
  movi v3.16b, 0
  smlsl2 v3.4s, v8.8h, v9.h[1]
  movi v4.16b, 0
  smlsl2 v4.4s, v8.8h, v9.h[1]
  movi v5.16b, 0
  smlsl2 v5.4s, v8.8h, v9.h[1]
  movi v6.16b, 0
  smlsl2 v6.4s, v8.8h, v9.h[1]
  movi v7.16b, 0
  smlsl2 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)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)9fa0a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160204200881501239258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100000010111116112006101600001002006520065200652006520065
160204200641501539258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100000010111116112006101600001002006520065200652006520065
16020420064151039258010010080000100800005006400001200452006420224322801002008000020024000020064200641116020110099100100160000100000010111116112006101600001002016820306200652015820065
16020420064150039258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100000010111116112006101600001002006520065200652006520065
16020420064150039258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100000010111116112006101600001002006520065200652006520065
16020420064150039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100000010111116112006101600001002006520065200652006520065
16020420064151039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100000010111116112006101600001002006520065200652006520065
16020420064150039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100000010111116112006101600001002006520065200652006520065
16020420064150039258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100000010111116112006101600001002006520065200652006520065
160204200641500963258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100000010111116112006101600001002006520065200652006520065

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03041e3a3f51inst 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)5f6061696b6d6escheduler 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)9fa8accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16002420071150090452580012128000012800006264000011520029020052200523228001220800002024000020048200521116002110910101600001000100468112922111261720045216160000102004920049200492004920049
16002420048150001742580012128000012800006264000011020029020048200483658001220800002024000020048200481116002110910101600001000100473112622111212520045216160000102004920049200492004920049
16002420048150061742580012128000012800006264000011520029020050200483228001220800002024000020048200481116002110910101600001010100443412122121162520049216160000102004920049200492004920049
16002420052150100742580012128000012800006264000000020029020052200483228001220800002024000020048200481116002110910101600001000100398412122111251520045216160000102004920049200492004920049
160024200481511017425800121280000128000062640000100200290200522004832280012208000020240000200482004811160021109101016000010001004811112522311272720045216160000102004920049200492004920049
16002420052150100452580012128000012800006264000010520029020048200483228001220800002024000020048200481116002110910101600001000100478411722312271620045216160000102004920049200492004920049
160024200481500181742580012128000012800006264000010520029020048200483228001220800002024000020048200481116002110910101600001000100433412322111261620045216160000102004920049200492004920049
16002420048150130452580012128000012800006264000010520029020052200483228001220800002024000020048200481116002110910101600001000100468512422111282120045231160000102004920049200492004920049
160024200481501330742580012128000012800006264000011520029020048200523228001220800002024000020048200481116002110910101600001000100478112622111172620045216160000102004920049200492004920049
160024200481501150742580012128000012800006264000010520029020052200483228001220800002024000020048200481116002110910101600001000100493112722111252620045216160000102004920049200492004920049

Test 6: throughput

Count: 12

Code:

  smlsl2 v0.4s, v12.8h, v13.h[1]
  smlsl2 v1.4s, v12.8h, v13.h[1]
  smlsl2 v2.4s, v12.8h, v13.h[1]
  smlsl2 v3.4s, v12.8h, v13.h[1]
  smlsl2 v4.4s, v12.8h, v13.h[1]
  smlsl2 v5.4s, v12.8h, v13.h[1]
  smlsl2 v6.4s, v12.8h, v13.h[1]
  smlsl2 v7.4s, v12.8h, v13.h[1]
  smlsl2 v8.4s, v12.8h, v13.h[1]
  smlsl2 v9.4s, v12.8h, v13.h[1]
  smlsl2 v10.4s, v12.8h, v13.h[1]
  smlsl2 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)03071e373f4e51inst 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)9fa8acc5branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1202043014722500041025120100100120000100120000500439952430020317483003914973314997120100200120000200360000317483003911120201100991001001200001000000761061622300361200001003004031749300403004330040
120204300392250604102512010010012000010012000050096000031729317483003914973316706120100200120000200360000300403003911120201100991001001200001000000761021622300361200001003174930040317493004030041
1202043092223200186102512011810012000110012000050096000030020300393174816653316706120100200120000200360000317483003911120201100991001001200001000000761021622300361200001003174930040317493004031749
120204317482250004167132512011810012000110012000050096000030021300393004014973314997120100200120000200360000300393004011120201100991001001200001000000761021622317451200001003004031749300403174930040
1202043003923800042025120100100120000100120000500439952430020300393174816653314998120100200120000200360000317483003911120201100991001001200001000000761021622300361200001003174930040317493004030040
120204300392380014167132512011810012000010012000050096000030020317483003914973314997120100200120000200360000300393174811120201100991001001200001000000761021622317451200001003004031749317393004030040
1202043003923800041671325120118100120018100120000500439952430020300393174816653314997120100200120000200360000300393004211120201100991001001200001000000761021622300361200001003174930040317493004030040
12020430039225001761025120100100120000100120000500439952430020300393174816653316706120100200120000200360000317483003911120201100991001001200001000000761021622300361200001003174930040317493004031749
1202043174822500041025120100100120000100120000500428362230020300393092214973316706120100200120000200360000317483003911120201100991001001200001004000761021622300361200001003078330040300403004030040
1202043003922500018667132512011810012001810012012050096000030065300403003914973314997120100200120000200360000300393004011120201100991001001200001000000761021622300371200001003174930040300433004130040

1000 unrolls and 10 iterations

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

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)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)9fa1a8c2cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
120024300392310460251200101012000010120000509600001130020300413003914996315019120010201200002036000030039309221112002110910101200001000075223111916211121230036206120000103004030923300403004030040
120024300392250460251200101012000010120000509600001130022300393003914996315019120010201200002036000030039300391112002110910101200001000075223111316211813300362022120000103004030040300403004030040
12002430039225046025120010101200001012000050960000213002030039300391499631501912001020120000203600003003930039111200211091010120000100007522311131621113930036206120000103004030040300403004030040
12002430039225046025120010101200001012000050960000213002030039300391499631501912001020120000203600003003930039111200211091010120000100007522311121621181430036206120000103004030040309233004030042
120024300392250460251200101012000010120000509600002130020300393003914996315019120010201200002036000030039300391112002110910101200001000075223111216211141330036206120000103004030040300403004030040
12002430039225046025120010101200001012000050990000213002030039300391499631590212001020120000203600003003930039111200211091010120000100007522311141621113930036206120000103004030040300403004030040
1200243003922504602512002710120000101200005096000021300203004130039149963150191200102012000020360000300393003911120021109101012000010000752431191621191430036206120000103004030040300403004030040
120024300392250460251200101012000010120000509600002130020300393003914996315019120010201200002036000030039300391112002110910101200001000075223111416211131330036206120000103004030040300403004030040
120024300392250460251200101012000010120000509600002130021300393003914996315019120010201200002036000030039300391112002110910101200001000075223111516211131430086206120000103004030040300403004030040
120024300392250460251200101012000010120000509600002130020300393003914996315019120010201200002036000030039300391112002110910101200001000075223111416211121230036206120000103004030040300403004030040