Apple M1 Microarchitecture Research by Dougall Johnson

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

SQDMLAL (scalar, S)

Test 1: uops

Code:

  sqdmlal s0, h1, h2
  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)0304191e3a3f4e51inst 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)a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303723000178254825100010001000398313130183037303724153289510001000300030373037111001100000075616662630100030383038303830383038
100430372210132178254825100010001000398313030183037303724153289510001000300030373037111001100000075616662630100030383038303830383038
10043037231001322254825100010001000398313130183037303724153289510001000300030373037111001100000096616662630100030383038303830383038
1004303723100178254825100010001000398313030183037303724153289510001000300030373037111001100000075616662630100030383038303830383038
1004303722100178254825100010001000398313130183037303724153289510001000300030373037111001100000075616662630100030383038303830383038
10043037221001173254825100010001000398313130183037303724153289510001000300030373037111001100000075616662630100030383038303830383038
1004303722100178254825100010001000398313030183037303724153289510001000300030373037111001100000075616662630100030383038303830383038
1004303722100178254825100010001000398313030183037303724153291410001000300030373037111001100002075616772630100030383038303830383038
10043037221001173254825100010001000398313030183037303724153289510001000300030373037111001100000075616662630100030383038303830383038
1004303723100178254825100010001000398313130183037303724153289510001000300030373037111001100010075716672630100030383038303830383038

Test 2: Latency 1->1

Code:

  sqdmlal s0, h1, h2
  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)0304080b18191e1f3a3f4e51inst 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)9fa0a1a6a8a9acc2cfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000710021622296340100001003003830038300383003830038
10204300372240000000061295392510112100100001001000050042773130300183003730037282653287451010020010000200305013003730037111020110099100100100001000000000710021622296340100001003003830038300383003830038
10204300372250000000061295482510100100100001001000050042773130300183003730086282653287451010020010000200300003003730037111020110099100100100001000000000710021622296340100001003003830038300383003830038
10204300372250000000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000779021623296340100001003003830038300383003830038
102043008422501000000103295482510100100100001001000050042773130301263003730037282653287451010020010000200300003003730037111020110099100100100001002000028330710021622296340100001003003830038300383003830038
10204300372250000000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000710021623296340100001003003830038300383003830038
10204300372240000000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000710021622296340100001003003830038300383003830038
10204300372250000000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000710021622297030100001003003830038300383003830038
10204300372250000000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000710021632296340100001003003830038300383003830038
10204300372250000000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000710121632296340100001003003830038300383003830038

1000 unrolls and 10 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)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)9fa0a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500000061295482510010101000010100005042773130300183003730037282870328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773131300183003730037282870328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722500000089295482510010101000010100005042773131300183003730037282870328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773131300183008530084282870328767100102010000203000030037300371110021109101010000100000640316222963010000103003830038300383003830038
100243003722400000061295482510010101000010100005042773131300183003730037282870328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773130300183003730037282870328767100102010000203000030037300371110021109101010000100000640316222963010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773130300183003730037282870328767100102010000203000030037300371110021109101010000100003640216222963010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773130300183003730037282870328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773130300183003730037282870328767100102010172203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
10024300372250000006129548251001010100001010000504277313130018300373003728287032876710010201000020300003003730037111002110910101000010000105640216222963010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  sqdmlal s0, h0, h1
  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)03181e3f4e51inst 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)9fa0a1a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
1020430037225003462954825101001001000010010000500427731303001830037300372826532874510100204101662003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
102043003722500612954883101001001000010010000500427731303001830037300372827832874510100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100221011363071011611296340100001003003830038300383003830038
102043003722400612953925101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
102043003722410612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000000271011611296340100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0308090b181e1f3f4e51inst 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)9fa1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000006129548251001010100001010149504277313130018300373008428292328767100102010000203000030037300371110021109101010000100000006403163329630010000103003830038300383003830038
10024300372250001006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000006403163329630010000103003830038300383003830038
10024300792240000006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000006403163329630010000103003830038300383003830038
100243003722500009010329548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000006403163329630010000103003830038300383003830038
100243003722500000072629548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000006403163329630010000103003830038300383003830038
10024300372250000006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100060006403163329630010000103003830038300383003830038
10024300852250000006129548251001010100241010000504277313130018300373003728287328767101632010000203000030037300371110021109101010000100230006403164429630010000103003830226300383003830038
100243003722500100010329548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000006403163329630010000103003830038300383003830038
10024300372240000008229548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000006403163329630010000103003830038300383003830038
10024300372250001006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000006403163329630010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  sqdmlal s0, h1, h0
  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)03070a18191e1f3a3f4e51inst 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)9fa1a6a7a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722511000006129548251010010010000100100005004277313030018300373003728272062874010100200100082003002430037300371110201100991001001000010000000001117171161129651100001003003830038300383003830038
1020430037225110000061295482510100100100001001000050042773130300183003730037282720628740101002001000820030024300373003711102011009910010010000100000003901117181161129651100001003003830085300383003830038
102043003722511000006129548251010010010000100100005004277313030018300373003728272072874010100200100082003002430037300371110201100991001001000010000000001117171161129650100001003003830038300383003830038
102043003722511000006129548251010010010000100100005004277313030054300373003728272062874110100200100082003002430037300371110201100991001001000010000000001117181161129651100001003003830038300383003830038
102043003722511000006129548251010010010000100100005004277313030018300373003728265032874510100200100002003000030037300371110201100991001001000010000000000007102162229634100001003003830038300383003830038
102043003722500000008229548251010010010000100100005004277313030018300373003728265032874510100200100002003000030037300371110201100991001001000010000000300007102162229634100001003003830038300383003830038
102043003722400000006129548251010010010000100100005004277313030018300373003728265032874510100200100002003000030037300371110201100991001001000010000000000007102162229704100001003003830038300383003830038
102043003722500000008229548251010010010000100100005004277313030018300373003728265032874510100200100002003000030037300371110201100991001001000010000000000007102162229634100001003003830038300383003830038
102043003722400000006129548251010010010000100100005004277313030018300373003728265072874510100200100002003000030037300371110201100991001001000010000000000007102162229634100001003003830038300383003830038
102043003722400000006129548251010010010000100100005004277313030018300373003728265032874510100200100002003000030037300371110201100991001001000010000000000007102162229634100001003003830038300383003830038

1000 unrolls and 10 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)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)9fa6a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000061295482510010101000010100005042773130301263003730037283043287671001020100002030000300373003711100211091010100001000090640216222963010000103003830038300383003830038
1002430037224000061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
1002430037225000061295482510010121000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
100243003722503396061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  sqdmlal s0, h8, h9
  movi v1.16b, 0
  sqdmlal s1, h8, h9
  movi v2.16b, 0
  sqdmlal s2, h8, h9
  movi v3.16b, 0
  sqdmlal s3, h8, h9
  movi v4.16b, 0
  sqdmlal s4, h8, h9
  movi v5.16b, 0
  sqdmlal s5, h8, h9
  movi v6.16b, 0
  sqdmlal s6, h8, h9
  movi v7.16b, 0
  sqdmlal s7, h8, h9
  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)030b1e3f51inst 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)9fa6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160204200891500026425801001008000010080000500640000120045200642006432280100200800002002400002006420064111602011009910010016000010020100010111116112006101600001002006520065200652006520065
160204200641500303925801001008000010080000500640000120045200642006432280100200800002002400002006420064111602011009910010016000010000000010111116112006101600001002006520065200652006520065
160204200641500638125801001008000010080000500640000120045200642006432280100200800002002400002006420064111602011009910010016000010000000010111116112006101600001002006520065200652006520065
16020420064150003925801001008000010080000500640000120045200642006432280124200800002002400002006420064111602011009910010016000010000000010111116112006101600001002006520065201362006520065
16020420064151003925801001008000010080000500640000120045200642006432280100200800002002400002006420064111602011009910010016000010000000010111116112006101600001002006520065200652006520065
16020420064151003925801001008000010080000500640000120045200642006432280100200800002002400002006420064111602011009910010016000010000000010111116112006101600001002006520065200652006520065
16020420064150003925801001008000010080000500640000120045200642006432280100200800002002400002006420064111602011009910010016000010000000010111116112006101600001002006520065200652006520065
160204200641500039258010010080000100800005006400001200452006420064402280100200800002002400002006420064111602011009910010016000010000000010111116112006101600001002006520065200652006520065
16020420064151003925801001008000010080000500640000120045200642006432280100200800002002400002006420064111602011009910010016000010000000010111116112006101600001002006520065200652006520065
16020420064150003925801001008000010080000500640000120045200642006432280100200800002002400002006420064111602011009910010016000010000000010111116112006101600001002006520065200652006520065

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0304070a18191e3a3f51inst 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)itlb miss (d4)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16002420074150000000045278001212800001280000626400001102003202005120051322800122080000202400002006220062111600211091010160000100010068622143363223326200592412160000102006320063200632006320063
160024200621501110000212298001212800001280000626400000102004302006220062322800122080000202400002006220062111600211091010160000100010064622135363223418200592412160000102006320063200632006320063
16002420062150100000045278001212800001280000626400001102003202005120051322800122080000202400002006220062111600211091010160000100010067622134363223433200592412160000102006320063200632006320063
16002420062150100000186298001212800001280000626400000102004302006220062322800122080000202400002006220062111600211091010160000100010067622138363223736200592412160000102006320063200632006320063
16002420062150122000198298001212800001280000626400000102004302006220062322800122080000202400002006220062111600211091010160000100010049622133363223720200592412160000102006320063200632006320063
16002420062150122000198298001212800001280000626400000102004302006220062322800122080000202400002006220062111600211091010160000100010073622122363223621200592412160000102006320063200632006320063
160024200621501110000172298001212800001280000626400000102004302006220062322800122080000202400002013020062111600211091010160000100010069622136363223533200592412160000102006320063200632006320063
16002420062150132000092298001212800001280000626400000102004302006220062322800122080000202400002006220062111600211091010160000100010059622119363223231200592412160000102006320063200632006320063
16002420062150133000098298001212800001280000626400000102004302006220062322800122080000202400002006220062111600211091010160000100010066622116363223421200592412160000102006320063200632006320063
160024200621501210001660298001212800001280000626400000102010802006220062322800122080000202400002006220062111600211091010160000100010069622136363223727200592412160000102006320052200522005220052

Test 6: throughput

Count: 16

Code:

  sqdmlal s0, h16, h17
  sqdmlal s1, h16, h17
  sqdmlal s2, h16, h17
  sqdmlal s3, h16, h17
  sqdmlal s4, h16, h17
  sqdmlal s5, h16, h17
  sqdmlal s6, h16, h17
  sqdmlal s7, h16, h17
  sqdmlal s8, h16, h17
  sqdmlal s9, h16, h17
  sqdmlal s10, h16, h17
  sqdmlal s11, h16, h17
  sqdmlal s12, h16, h17
  sqdmlal s13, h16, h17
  sqdmlal s14, h16, h17
  sqdmlal s15, h16, h17
  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)0304080b18191e1f373a3f51inst 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)9fa0a6a8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160204400603000000000172552516011710016001710016000050012800000400294003940048199733199971601002001600002004800004003940048111602011009910010016000010000014101011412161512400361600001004004940040400504004140040
1602044003930000000001724625160117100160000100160000500128000004002040039400391997332000616010020016000020048000040048400391116020110099100100160000100000001011414161414400451600001004004040049400524004040040
1602044003930000000000246251601171001600171001600005001280000040029400484003919973319997160100200160000200480000400394004811160201100991001001600001000001860101148161315400361600001004005040049400414004040041
160204400403000000000172552516011710016000010016000050012800001400204003940048199733200061601002001600002004800004004840039111602011009910010016000010000019801011414161314400361600001004004040049400494004940049
160204400493000000000172552516010010016000010016000050012800001400204003940039199733199971601002001600002004800004003940048111602011009910010016000010000015601011414161514400451600001004004140049400404004040040
16020440049300000000002462516010010016000010016000050012800001400204003940048199733199971601002001600002004800004004840039111602011009910010016000010000016501011415161413400361600001004004940040400404004040040
16020440039299000000018246251601011001600001001600005002438865140020400394003919973319997160100200160000200480000400394004811160201100991001001600001000001950101141416148400361600001004004940040400404004040040
160204400392990000000172562516010010016000010016000050012800001400204003940039199733200061601002001600002004800004004940039111602011009910010016000010000021301011412161413400361600001004004040049400404004040040
1602044004030000000000255251601171001600001001600005001280000140020400394004819973319997160100200160000200480000400484003911160201100991001001600001000002010101141416147400361600001004004940040400494004040049
160204400493000000000172552516011710016000010016000050012800001400204003940108199733200381601002001600002004800004004840039111602011009910010016000010000014401011414161314400451600001004004040040400494004040040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030409181e373a3f51inst 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)5f60696b6d6edispatch 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)9fa0a8accfd0d2icache miss (d3)itlb miss (d4)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160024401073001100015225160010101600001016000050128000011400200400394003919996320028160010201600002048000040039400391116002110910101600001000010023341149161112229400360315160000104004040040400404004040040
160024400713001100014625160010101600001016000050128000011400200400394003919996320019160010201600002048000040039400391116002110910101600001000010024341127161112727400360165160000104004040040400404004040040
16002440055300110000952516001010160000101600005023989991140020040039400391999632001916001020160000204800004003940039111600211091010160000100024910024341126161111726400360165160000104004040040400404004040040
160024400613001100015225160010101600001016000050243886511400200400394003919996320019160010201600002048000040039400391116002110910101600001000010024341126161111526400460165160000104004040040400404004040040
1600244006430011000076625160010101600001016000050128000011400200400394004919996320019160010201600002048000040039400491116002110910101600001000010022341026161111625400360166160000104004040040400404004040040
16002440060300110001101251600101016000010160000501280000114003004003940039199963200191600102016000020480000400394003911160021109101016000010000100243411261631126264003601610160000104004040040400404004040040
1600244005530011000110125160010101600001016000050128000011400200400394003919996320019160010201600002048000040049400391116002110910101600001000010024341120161112616400360165160000104004040040400404004040040
1600244005530011000110125160010101600001016000050128078811400200400394004219996320019160010201600002048000040049400491116002110910101600001000010023341125161111626400460165160000104004040040400404004040040
16002440065300110018117425160010101600001016000050128000011400200400394003919996320019160010201600002048000040039400391116002110910101600001000010025341127161112627400360165160000104004040040400404004040040
1600244006030011000120625160028101600001016000050239899911400200400394003919996320019160010201600002048000040039400391116002110910101600001000010023341126161112732400460166160000104004040040400404004040040