Apple M1 Microarchitecture Research by Dougall Johnson

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

SQDMLAL (by element, D)

Test 1: uops

Code:

  sqdmlal d0, s1, v2.s[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)031e3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)696d6edispatch 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)a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372306125482510001000100039831330183085307324153289510001000300030373037111001100000073116112630100030383038303830383038
1004303726126125482510001000100039831330183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
100430372308425482510001000100039831330183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
100430372308425482510001000100039831330183037303724193289510001000300030373037111001100000073116112630100030383038303830383038
100430372306125482510001000100039831330183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
100430372306125482510001000100039831330183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
100430372306125482510001000100039831330183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
100430372308425482510001000100039831330183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
100430372308425482510001000100039831330183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
100430372306125482510001000100039831330183037303724153289510001000300030373037111001100000073116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  sqdmlal d0, s1, v2.s[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)030818191e1f3a3f4e51inst 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)9fa6a8accfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500090015629548251011710010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000710031622296340100001003003830038300383003830038
10204300372250000006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000710021622296340100001003003830038300383003830038
10204300372250000006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000710031622296340100001003003830038300383003830038
1020430037225000001135129530861013310610032106105965224281384030162301803016928275328745101002001000020030000300373003711102011009910010010000100000712021622296340100001003003830038300383003830038
102043003722500000053629548251010010010000100100005004277313030018300373003728265328745102522001000020030000300373003711102011009910010010000100000710121622296340100001003003830038300383003830038
102043003722500000063129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000710121622296340100001003003830038300383003830038
102043003722500000025129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000710121622296340100001003003830038300383003830038
10204300372250000006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000710121622296340100001003003830038300383003830038
10204300372250000006129548251010010010007100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000710121622296340100001003003830038300383003830038
10204300372250000006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000710121622296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

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)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)9fa6a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500012429548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003721100211091010100001001000640216322963010000103008530038300383003830038
10024300372250006129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
10024300372250006129548251001010100001110000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000000640216232963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001001000640216222963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000030640216222963010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  sqdmlal d0, s0, v1.s[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)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)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)9fa0a1a6a8a9acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500961295482510100100100001001000050042773130300183008430037282727287411010020010008200300243003730037111020110099100100100001000000001117170160029647100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773131300183003730037282727287411010020010008200300243003730037111020110099100100100001000000001117170160029647100001003003830038300383003830038
1020430037225000612954825101001001000010010000500427731303001830182302152826512287801010021210665212304953003730037511020110099100100100001000000000007101161129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000007101161129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000007101161129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000007101161129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000007101161129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000007101161129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000007101161129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

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)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)9fa1a6a7a8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000000640216222963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000000640216222963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000000640216222963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000000640216222963010000103003830038300383003830038
1002430037225000336295482510019121000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000000640216222963010000103003830038300383003830038
100243003722511061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000000640216222963010000103003830038300383003830038
100243003722400061295482510010101000010100005042773133001830037300372828732878610010201000020300003003730037111002110910101000010020028450640216222963010000103003830038300383003830038
10024300372250012126295482510010101000010100005042786703001830037300372828732876710010201000020300003003730037111002110910101000010000000640216222969810000103003830038300383003830038
100243003722500061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000000640216222963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100000240640216222963010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  sqdmlal d0, s1, v0.s[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)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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722506129548251010010010000100100005004277313030018300373003728272628740101002001000820030024300373003711102011009910010010000100001117170160029646100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313030018300373003728290728741101002001000820030024300373003711102011009910010010000100001117170160029647100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313030018300373003728272728740101002001000820030024300373003711102011009910010010000100001117180160029647100001003003830038300383003830038
102043003722406129548251010010010000100100005004277313030018300373003728272728740101002001000820030024300373003711102011009910010010000100001117180160029646100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313030018300373003728272628741101002001000820030024300373003711102011009910010010000100001117170160029646100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313030018300373003728272728740101002001000820030024300373003711102011009910010010000100001117170160029647100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313030018300373003728272628741101002001000820030024300373003711102011009910010010000100001117170160029646100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313030018300373003728272628740101002001000820030024300373003711102011009910010010000100001117180160029646100001003003830038300383003830038
102043003722406129548251010010010000100100005004277313030018300373003728272728741101002001000820030024300373003711102011009910010010000100001117170160029647100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313030018300373003728272628741101002001000820030024300373003711102011009910010010000100001117180160029647100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0307080a0b1e1f3a3f4e51inst 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)9fbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722410100026829548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001006441116101029630010000103003830038300383003830038
1002430037225101000268295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010064410168829630010000103003830038300383003830038
100243003722510100027329548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001006441016101129630010000103003830038300383003830038
10024300372251010002682954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100644101610529630010000103003830038300383003830038
10024300372251010002682954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100644101611529630010000103003830038300383003830038
100243003722510100026829548251001010100001010000554277313300183003730037282873287671001020100002030000300373003711100211091010100001006441016111029630010000103003830038300383003830038
100243003722510100026829548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001006441016101029630010000103003830038300383003830038
10024300372251010002682954844100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100644101610829630010000103003830038300383003830038
1002430037225101015026829548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001006441016101029630010000103003830038300383003830038
1002430037225101081026829548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001006441016101029630010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  sqdmlal d0, s8, v9.s[1]
  movi v1.16b, 0
  sqdmlal d1, s8, v9.s[1]
  movi v2.16b, 0
  sqdmlal d2, s8, v9.s[1]
  movi v3.16b, 0
  sqdmlal d3, s8, v9.s[1]
  movi v4.16b, 0
  sqdmlal d4, s8, v9.s[1]
  movi v5.16b, 0
  sqdmlal d5, s8, v9.s[1]
  movi v6.16b, 0
  sqdmlal d6, s8, v9.s[1]
  movi v7.16b, 0
  sqdmlal d7, s8, v9.s[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)0308090b18191e1f3f51inst 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)9fa0a1a6a8a9acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602042007815000000003925801001008000010080000500640000200452006420064322801002008000020024000020064200641116020110099100100160000100000000010111116112006101600001002006520065200652006520065
1602042006415000000303925801001008000010080000500640000200452006420064322801002008000020024000020064200641116020110099100100160000100000000010111116112006101600001002006520065200652006520065
1602042006415000000003925801001008000010080000500640000200452006420064322801002008000020024000020064200641116020110099100100160000100000000010111116112006101600001002006520065200652006520065
16020420064150000000885142580100100800001008000050064000020045200642006432280100200800002002400002006420064111602011009910010016000010000010557010111116112006101600001002006520065200652006520065
1602042006415000000003925801001008000010080000500640000200452006420064322801002008000020024000020064200641116020110099100100160000100000000010111116112006101600001002006520065200652006520065
1602042006415000000003925801001008000010080000500640000200452006420064322801002008000020024000020064200641116020110099100100160000100000000010111116112006101600001002006520065200652006520065
1602042006415000000003925801001008000010080000500640000200452006420064322801002008000020024000020064200641116020110099100100160000100000000010111116112006101600001002006520065200652006520065
1602042006415000000003925801001008000010080000500640000200452006420064322801002008000020024000020064200641116020110099100100160000100000000010111116112006101600001002006520065200652006520155
1602042006415000000003925801001008000010080000500640000200452006420064322801002008000020024000020064200641116020110099100100160000100000000010111116112006101600001002006520065200652006520065
1602042006415000000003925801001008000010080000500640000200452006420064322801002008000020024000020064200641116020110099100100160000100000000010111116112006101600001002006520065200652006520065

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03181e1f3f51inst 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)9fa8accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1600242007915001204525800121280000128000062640000112002720050200463228001220800002024000020046200461116002110910101600001000100446111020211720200432150160000102004720047200472004720047
160024200461500004525800121280000128000062640000112002720050200463228001220800002024000020046200461116002110910101600001000100476119242212010200472150160000102004720051200512005120047
16002420050150024051258001212800001280000626400000120031200462005032280012208000020240000200502004611160021109101016000010001003132220244122020200472300160000102005120051200512005120051
160024200461500315045258001212800001280000626400000120031200462005032280012208000020240000200462004611160021109101016000010001004732120202212020200472300160000102004720051200512004720051
1600242004615001804525800121280000128000062640000112002720050200503228001220800002024000020050200461116002110910101600001000100476222124222209200472150160000102004720051200512005120047
1600242005015001205125800121280000128000062640000112003120046200463228001220800002024000020046200461116002110910101600001000100453127244112020200472300160000102005120051200512004720051
1600242004615001209325800121280000128000062640000012003120050200503228001220800002024000020050200461116002110910101600001000100443222024421920200472300160000102005120047200472005120047
1600242004615001201467380117128000012800006264000001200312004620050322800122080000202400002005020046111600211091010160000100010036622924221720200472300160000102005120051200512005120051
1600242005015003051258001212800001280000626400000120031201282005032280012208010420240000200502005011160021109101016000010001003232220244212110201242300160000102005120133200512005120131
16002420050151145045258001212800001280000626400000120031200462004632280012208000020240000200522005011160021109101016000010131003362220244121018200472150160000102005120047200472005120051

Test 6: throughput

Count: 12

Code:

  sqdmlal d0, s12, v13.s[1]
  sqdmlal d1, s12, v13.s[1]
  sqdmlal d2, s12, v13.s[1]
  sqdmlal d3, s12, v13.s[1]
  sqdmlal d4, s12, v13.s[1]
  sqdmlal d5, s12, v13.s[1]
  sqdmlal d6, s12, v13.s[1]
  sqdmlal d7, s12, v13.s[1]
  sqdmlal d8, s12, v13.s[1]
  sqdmlal d9, s12, v13.s[1]
  sqdmlal d10, s12, v13.s[1]
  sqdmlal d11, s12, v13.s[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)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)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)9fa0a1a8a9acc2branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1202043094222500000004102512010010012000010012000050096000030932300393003914973314997120100200120000200360000300393003911120201100991001001200001002120090007610116113094801200001003004030040300403095230040
1202043003922500000004102512010010012000010012000050096000030020300393003914973314997120100200120000200360000300393095111120201100991001001200001000000300007610116113003601200001003004030040300403004030040
1202043003922500000004102512010010012000010012000050096000030020300393003914973314997120100200120000200360000300393003911120201100991001001200001000000780007610116113003601200001003004030040300403004030040
12020430039225000000025902512010010012000010012000050096000030020300393003914973314997120100200120000200360000309513003911120201100991001001200001000000240007610116113003601200001003004030040300403004030040
1202043003923100000007060251201001001200001001200005009600003002030039300391585731590912010020012000020036000030039300391112020110099100100120000100000000007610116113003601200001003004030040300403004030040
1202043003922500000004102512010010012000010012000050042861843002030039300391497331499712010020012000020036000030039300391112020110099100100120000100000030007610126113144601200001003004030040300403095230040
1202043003922500000004102512010010012000010012000050096000030020300393095114973314997120100200120000200360000300393003911120201100991001001200001000000300007610116113003601200001003004030040300403004030088
1202043003922400000004135232512010010012005210012000050096000030020300393003914973314997120100200120000200360000300393003911120201100991001001200001000000300007610116113094801200001003004030040300403004030040
1202043003922500000004104912010010012000010012000050096000030020300393003915857715026120100200120000200360000300393125511120201100991001001200001000000210007610116113003601200001003004030952300403004030040
1202043003922500000004102512010010012000010012000050096000030020300393003914973314997120100200120000200360000300393003911120201100991001001200001000000810007610116113003601200001003004030040300403004030040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0309181e3f51inst 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)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)9fa0a6a8accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1200243005022500052251200101012000010120000509600000130020300393003914996031501912001020120000203600003003930039111200211091010120000100003075226212164215530036155120000103009230051300403004030040
12002430039224000522512001010120000101200005096000011300203003930039149960315019120010201200002036000030039300391112002110910101200001000081752231141621129730036155120000103004030040300403004030040
12002430039225000246251200101012000010120000509600001130020300393003914996031502112001020120000203600003003930039111200211091010120000100006752231273162114430036155120000103004030040300403004030040
1200243003922500667251200101012000010120000509600001130020300393003914996031501912001020120000203600003003930041111200211091010120000100002175223114162114430036155120000103004030040300403004030040
1200243003922500046251200101012000010120000509600001130020300393003914996031501912001020120000203600003003930039111200211091010120000100001275223114162114430036155120000103092330040300403004030040
12002430039225000462512001010120000101200005096000011300213003930039149960315019120010201200002036000030039300391112002110910101200001000014175223113162113430036155120000103004030040309233004030040
1200243004122500046251200101012000010120000509600002130020300393003914996031501912001020120000203600003003930039111200211091010120000100022475223113162114430036155120000103004030040309233004030040
1200243003922500046251200101012000010120000509600001130020300393003914996031501912001020120000203600003003930039111200211091010120000100008175223114162113330036155120000103009430981304103004030040
120024300392250004625120010101200001012000050960000113002030039300391499603150191200102012000020360000300393003911120021109101012000010000975223113162114430036155120000103004030040300403004030040
120024300392241104625120010101200001012000050960000123002030039300391499603150191200102012000020360000300393003911120021109101012000010000075223113162114430036155120000103004030040309233004030040