Apple M1 Microarchitecture Research by Dougall Johnson

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

RADDHN2 (8H)

Test 1: uops

Code:

  raddhn2 v0.16b, v1.8h, v2.8h
  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)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)a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303722061254825100010001000398313130183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
100430372314761254825100010001000398313030183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
10043037220103254825100010001000398313030183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
1004303723061254825100010001000398313030183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
10043037230736254825100010001000398313030183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
1004303722061254825100010001000398313030183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
1004303723061254825100010001000398313030183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
1004303723061254825100010001000398313030183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
1004303722061254825100010001000398313130183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
1004303723061254825100010001000398313030183037303724153289510001000300030373037111001100000073116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  raddhn2 v0.16b, v1.8h, v2.8h
  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)03080b1e3a3f4e51inst 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)9facc5branch mispredict (cb)cdcfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000612954825101001001000010010000500427731303001803003730037282727287401010020010008200300243003730037111020110099100100100001000111717001600296470100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731313001803003730037282727287411010020010008200300243003730037111020110099100100100001000111718001600296470100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731313001803003730037282653287451010020010000200300003003730037111020110099100100100001000000710121622296340100001003003830086300383003830038
10204300372250000612954825101001001000010010000500427731313001803003730037282653287451010020010000200300003003730037111020110099100100100001000000710121622296340100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731313001803003730037282653287451010020010000200300003003730037111020110099100100100001000000710121622296340100001003003830038300383003830038
102043003722500001562954825101001001000010010000500427731313001803003730037282653287451010020010000200300003003730037111020110099100100100001000000777126923296341100001003008630038300853003830038
102043003722510004412954825101001001000010010000500427731303001803003730037282653287451010020010000200300003003730037111020110099100100100001000000710121622296340100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731313001803003730037282653287451010020010000200300003003730037111020110099100100100001000000710121622296340100001003003830038300383003830038
102043003722500007262954825101001001000010010000500427731313001803003730037282653287451010020010000200300003003730037111020110099100100100001000000710121622296340100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731313001803003730037282653287451010020010000200300003003730037111020110099100100100001000000710121622296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b18191e1f3f4e51inst 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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500000061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000000006404163529630010000103003830038300383003830038
100243003722500000061295482510010101000010100006142786703001830037300372828732876710010201000020300003003730037111002110910101000010000000006402163229630010000103003830038300383003830038
100243003722500000061295482510017101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000000006403162229630010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000010006402162229630010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000000006402163229630010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000000006402162229630010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  raddhn2 v0.16b, v0.8h, v1.8h
  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)03191e3f4e51inst 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)6061696d6edispatch 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)9fa8cfd0d2d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372240014529548251010010010000100100005004277313053001830037300372826532874510100200100002003000030037300371110201100991001001000010007105141622296340100001003003830038300383003830038
1020430037224006129548251010010010000100100005004277313053001830037300372826532874510100200100002003000030037300371110201100991001001000010007100021622296340100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313053001830037300372826532874510100200100002003000030037300371110201100991001001000010007100021622296340100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313053001830037300372826532874510100200100002003000030037300371110201100991001001000010007105121622296340100001003003830085300383003830038
1020430037225006129548251010010010000100100005004277313103001830037300372826532874510100200100002003000030037300371110201100991001001000010007105121622296340100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313103001830037300372826532874510100200100002003000030037300371110201100991001001000010007100021622296340100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313103001830037300372826532874510100200100002003000030037300371110201100991001001000010007100021622296340100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313053001830037300372826532874510100200100002003000030037300371110201100991001001000010007105121622296340100001003003830038300863003830038
10204300372250012429548251010010010000100100005004277313053001830037300372826532874510100200100002003000030037300371110201100991001001000010007100021622296340100001003003830038300383003830038
102043003722500208129539251010010010000100100005004277313103001830037300372826532874510100200100002003000030037300371110201100991001001000010007100021722296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030818191e1f3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372250000061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372250000061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372250000061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372250000061295482510010101000010100005042773130300183003730037282873287671001020100002030000300843003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372250000061295482510010101000010100005042773130300183003730037282873287671001020100002030516300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372250000061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372250000061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372250000061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372250000061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000006402162229630010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  raddhn2 v0.16b, v1.8h, v0.8h
  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)0318191e3a3f4e51inst 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)9fa6a8acc2c5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300842250001766295302510121100100081261000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000100071011611296340100001003003830038300383003830085
1020430037224000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000032071011611296340100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
1020430037224000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
1020430037224000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
10204300372250000251295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0307080a191e1f3a3f4e51inst 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
100243003722410100026829548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100064411165102963010000103003830038300383003830038
100243003722510100026829548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100064451611102963010000103003830038300383003830038
1002430037225101000225829548251001010100001010000504277313030065300373003728287328767100102010000203000030037300371110021109101010000100064410165112963010000103003830038300383003830038
10024300372251010002258295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000644131610102963010000103003830038300383003830038
10024300372251010002543295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000644101610102963010000103003830038300383003830038
1002430037225101000268295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000644111610102969710000103003830038300383003830038
10024300372251010002543295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000644111610102963010000103003830038300383003830038
1002430037225101000268295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000644101610102963010000103003830038300383003830038
100243003722510100026829548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100064411166102963010000103003830038300383003830038
1002430037225101000268295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000644101610102963010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  raddhn2 v0.16b, v8.8h, v9.8h
  movi v1.16b, 0
  raddhn2 v1.16b, v8.8h, v9.8h
  movi v2.16b, 0
  raddhn2 v2.16b, v8.8h, v9.8h
  movi v3.16b, 0
  raddhn2 v3.16b, v8.8h, v9.8h
  movi v4.16b, 0
  raddhn2 v4.16b, v8.8h, v9.8h
  movi v5.16b, 0
  raddhn2 v5.16b, v8.8h, v9.8h
  movi v6.16b, 0
  raddhn2 v6.16b, v8.8h, v9.8h
  movi v7.16b, 0
  raddhn2 v7.16b, v8.8h, v9.8h
  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)03070a18191e1f3a3f51inst 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)9fa0a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16020420089150000000039258010010080000100800005006400002004520064200643228010020080000200240000200642006411160201100991001001600001000000010111116112006101600001002006520065200652006520065
160204200641501000000392580100100800001008000050064000020045200642006432280100200800002002400002006420064111602011009910010016000010000000101143163320061251600001002006520065200652006520065
160204200641500000000209258010010080000100801045786400002004520064200643228010020080000200240000200642006411160201100991001001600001000000010111116112006101600001002006520065200652006520065
16020520064150000000039258010010080000100800005006400002004520064200643228010020080000200240000200642006411160201100991001001600001000000010111116112006101600001002006520065200652006520065
16020420064150100000039258010010080000100800005006400002004520064200643228010020080000200240000200642006411160201100991001001600001000000010111116112006101600001002006520065200652006520065
16020420064150000000039258010010080000100800005006400002004520064200643228010020080000200240000200642006411160201100991001001600001000000010111116112006101600001002006520065200652006520065
16020420064150000000039258010010080000100800005006400002004520064200643228010020080000200240000200642006411160201100991001001600001000000010111116112006101600001002006520065200652006520065
160204200641500000000102258010011780000100800005006400002004520064200643228010020080000200240000200642006411160201100991001001600001000000010111116112006101600001002006520065200652006520065
160204200641501000000374258010010080000100800005006400002004520064200643228010020080000200240000200642006411160201100991001001600001000000010111116112006101600001002006520065200652006520065
16020420064150000000039258010010080000100800005006400002004520064200643228010020080000200240000200642006411160201100991001001600001000000010111116112006101600001002006520065200652006520065

1000 unrolls and 10 iterations

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

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)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
16002420089150045278001212800001280000626400001120032203132006432280012208000020240000200512005111160021109101016000010001003131192521199200482201160000102005220052200522005220052
16002420060150045278001212800001280000626400001120032202872006432280012208000020240000200602006011160021109101016000010001003131142521148200482201160000102005220052200522005220052
16002420051150645278001212800001280000626400001120032203782006432280012208000020240000200512005111160021109101016000010001003131152521148200482201160000102005220052200522005220052
16002420051150045278001212801051380000626400001120032202672006432280012208000020240000200512005111160021109101016000010001002731182521184200482201160000102005220052200522005220052
160024200511501545278001212800001280000626400001120032202662007332280012208000020240000200512005111160021109101016000010001002831182521184200482201160000102005220052200522005220052
16002420051151045278001212800001280000626400001120032203362006432280012208000020240000200512005111160021109101016000010001002931182521188200482201160000102005220052200522005220052
160024200511502145278001212800001280000626400001120032202412006432280012208000020240000200512005111160021109101016000010001002831142521158200482201160000102005220052200522005220052
16002420051150645278001212800001280000626400001120032202252006432280012208000020240000200512005111160021109101016000010001003131192521195200482201160000102005220052200522005220052
16002420051150045278001212800001280000626400001120032202472006432280012208000020240000200512005111160021109101016000010001003131192521148200482201160000102005220052200522005220052
1600242005115045045278001212800001280000626400001120032202232006432280012208000020240000200512005111160021109101016000010001002831182521195200482201160000102005220052200522005220052

Test 6: throughput

Count: 16

Code:

  raddhn2 v0.16b, v16.8h, v17.8h
  raddhn2 v1.16b, v16.8h, v17.8h
  raddhn2 v2.16b, v16.8h, v17.8h
  raddhn2 v3.16b, v16.8h, v17.8h
  raddhn2 v4.16b, v16.8h, v17.8h
  raddhn2 v5.16b, v16.8h, v17.8h
  raddhn2 v6.16b, v16.8h, v17.8h
  raddhn2 v7.16b, v16.8h, v17.8h
  raddhn2 v8.16b, v16.8h, v17.8h
  raddhn2 v9.16b, v16.8h, v17.8h
  raddhn2 v10.16b, v16.8h, v17.8h
  raddhn2 v11.16b, v16.8h, v17.8h
  raddhn2 v12.16b, v16.8h, v17.8h
  raddhn2 v13.16b, v16.8h, v17.8h
  raddhn2 v14.16b, v16.8h, v17.8h
  raddhn2 v15.16b, v16.8h, v17.8h
  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)0318191e373f4e51inst 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)9fa1a8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602044006030000378174102516016110016006110016000050023989991400214003940048199733199981601002001600002004800004003940039111602011009910010016000010000001011011611400451600001004004940040400494004040040
160204400393000024050025160117100160000100160000500239902704002040040400491997331999716010020016000020048000040039400491116020110099100100160000100011801011011611400361600001004004040040400404004040040
16020440039300005704102516011810016000010016000050024388650400204003940039199733199971601002001600002004800004004940039111602011009910010016000010000001011011611400461600001004004040040400414004140041
160204400393000030174102516011710016000010016000050012800000400204006640049199733199971601002001600002004800004003940049111602011009910010016000010000001011011611400461600001004005040041400404005040040
16020440039300004214102516010010016000010016000050013200000400204003940039199733199971601002001600002004800004004940048111602011009910010016000010000001011011611400361600001004004040050400494004040040
160204400393000051174102516011710016000010016000050023990270400524004940039199733199971601002001600002004800004003940040111602011009910010016000010000001011011611400361600001004005040040400494004040040
16020440039300003004102516010010016000010016000050023989990400204003940039199733200291601002001600002004800004004940039111602011009910010016000010000001011011611400361600001004005040050400404004040049
160204400393000057174102516010010016000010016000050012800000400204003940040199733200291601002001600002004800004003940049111602011009910010016000010000001011011611400451600001004004040040400494004040040
16020440039299002404102516010010016001710016000050012800000400304004940039199733199971601002001600002004800004003940039111602011009910010016000010000001011011611400361600001004004040050400404007240040
16020440039300003604102516011710016001710016000050012800000400204005340048199733199971601002001600002004800004003940049111602011009910010016000010000001011011611400451600001004004040040400414004040040

1000 unrolls and 10 iterations

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

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)9fa1a8acc2c5cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16002440048300001746251600101016000010160000501280000114003240039400391999632001916001020160000204800004003940039111600211091010160000100000010022311141621135400360156160000104004040040400414004940040
160024400392990004625160027101600181016000050243886511400214003940039199963200191600102016000020480000400394003911160021109101016000010000001002231131621135400360155160000104004040040400404004040049
160024400393000005525160010101600001016000050128000011400334003940048199963200191600102016000020480000400404003911160021109101016000010000001002462271621195400360155160000104004040040400404004940040
160024400403000014625160010101600181016000050128000011400334003940039199963200191600102016000020480000400394003911160021109101016000010000001002231151621193400360155160000104004040040400404004040040
1600244003930000175225160010101600001016000050128000011400214003940049199963200191600102016000020480000400394003911160021109101016000010000001002231131621139400360155160000104004040040400504005040040
1600244003930011514625160010101600001016000050128000011400214003940048199963200191600102016000020480000400394004911160021109101016000010000001002231131621135400360155160000104004040040400404004040040
160024400492990005225160010101600001016000050128000011400214003940039199963200191600102016000020480000400394003911160021109101016000010000001002231191621193400360156160000104005040040400404004040040
1600244004930000023725160010101600171016000050128000011400334003940039199963200191600102016000020480000400494003911160021109101016000010000001002231131621135400360156160000104004140049400404004040040
1600244003930000046251600101016008910160000501320000114003340039400401999632001916001020160000204800004003940039111600211091010160000100000010022311516211534004503010160000104004040040400404004040040
160024400393000004625160010101600001016000050128000001400204003940039199963200191600102016000020480000400394003911160021109101016000010000001002231131621193400360155160000104004040040400404004040040