Apple M1 Microarchitecture Research by Dougall Johnson

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

SQRDMLSH (vector, 2S)

Test 1: uops

Code:

  sqrdmlsh v0.2s, v1.2s, v2.2s
  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)03080b18191e1f3f4e51inst 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)a0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037230000006125482510001000100039831303018303730372415328951000100030003037303711100110000000000073116112630100030383038303830383038
10043037230000006125482510001000100039831303018303730372415328951000100030003037303711100110000000000073116112630100030383038303830383038
100430372300000017725482510001000100039831303018303730372415328951000100030003037303711100110000000000073116112630100030383038303830383038
100430372300000014525482510001000100039831303018303730372415328951000100030003037303711100110002000000073116112630100030383038303830383038
10043037230000006525482510001000100039831303018303730372415328951000100030003037303711100110000000000073116112630100030383038303830383038
10043037230000006125482510001000100039831303018303730372415328951000100030003037303711100110000000000073116112630100030383038303830383038
1004303722000011406125482510001000100039831303018303730372415328951000100030003037303711100110000000003073116112630100030383038303830383038
10043037230000006125482510001000100039831303018303730372415328951000100030003037303711100110000000000073116112630100030383038303830383038
10043037230000006125482510001000100039831303018303730372415328951000100030003037303711100110000000000073116112630100030383038303830383038
10043037220000006125482510001000100039831303018303730372415328951000100030003037303711100110000000000073116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  sqrdmlsh v0.2s, v1.2s, v2.2s
  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)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)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)9fa8acc2branch mispredict (cb)cfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225006129548251010010010000100101485004277313003001830037300372826532874510100214100002003000030037300371110201100991001001000010000007100216222963400100001003003830038300383003830038
1020430037224006129548441010010010000100100005004277313103001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101216222963400100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313003001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101216222963400100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313003001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101216222963400100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313003001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101316222963400100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313003001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101216222963400100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313003001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101216232963400100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313003001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101216222963400100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313003001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101216222963400100001003003830038300383003830038
1020430037225016129548251010010010000100100005004277313003001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101216222963400100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03191e3a3f4e51inst 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)9fa0a1a6a8a9acc2c5branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372240011702954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000000010640816882963010000103003830038300383003830038
10024300372250001672954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000000000640716782963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000000000640616782963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000000000640816882963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000000000640916762963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000000000640716782963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000000000640716672963010000103003830038300383003830038
1002430037224000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000000000640817772963010000103003830038300383003830038
1002430037224000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000500000640816872963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000000000640716682963010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  sqrdmlsh v0.2s, v0.2s, v1.2s
  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)0307080b18191e1f3a3f4e51inst 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)9fa1a8a9acc5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430420228001751068704061295482510100100100001001014950042773131301620303723013328282292883811641216108282323248730324303248110201100991001001000010021016923084239631298860100001003008130038300383003830038
1020430037225000051442640626029484205102011141006413110894740428681203048603069330037282656287401010020010008200300243003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
102043003722500000000612954825101001001000010010000500427731303001803003730037282653287451010020010000200300003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
102043003722500000000612954825101001001000010010000500427731303001803003730037282653287451010020010000200300003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
1020430037225000000006129548251010012510000125100005004277313030018030037300372826532874510100200100002003000030037300371110201100991001001000010000000710116112963425100001003003830038300383003830038
102043003722500000000612954825101001001000010010000500427731303001803003730037282653287451010020010000200300003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
1020430037225000000006129548251010010010000100100005004277313030018030037300372826532874510100200100002003000030037300371110201100991001001000010000000710116332963425100001003003830038300383003830038
102043003722500000000612954825101001001000010010000626427731303001803003730037282653287451010020010000200300003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
102043003722500000000612954825101001001000010010000500427731303001803003730037282653287451010020010000200300003003730037111020110099100100100001000000071011611296340100001003008630038300853003830038
102043003722500000000612954825101001001000010010000500427731303001803003730037282653287451010020010000200300003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b1e3f4e51inst 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)9fa6a8accdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225023715129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000006403163329630010000103003830038300383003830038
1002430037224006129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001031006403163329630010000103003830038300383003830038
10024300372250126129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000006403163329630010000103003830038300383003830038
10024300372250540112029548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000006403163329630010000103003830038300383003830038
100243003722502461295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010003006403163329630010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000006403163329630010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000006403163329630010000103003830038300383003830038
10024300372250034629548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000006403163329630010000103003830038300383003830038
10024300372250072629548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000006403163329630010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000006403163329666210000103003830038300383003830133

Test 4: Latency 1->3

Code:

  sqrdmlsh v0.2s, v1.2s, v0.2s
  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)0308090b18191e1f3a3f404e51inst 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)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000000006102954825101001001000011510149500427731330018300373003728272728741101002001000820030024300373003711102011009910010010000100000000011171801600296470100001003003830038300383003830038
10204300372240000015006102954825101001001000010010000500427731330018300843003728272728740101002001000820030024300373003711102011009910010010000100000000011171801600296470100001003003830038300383003830038
1020430037225000000006102954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000000000071011611296340100001003003830038300383003830038
1020430037225000000006102954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000000000071011611296340100001003003830038300383003830038
1020430037225000000006102954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000000000071011611296340100001003003830038300383003830038
1020430037225000000006102954825101001001000010010000522427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000000000071011611296340100001003003830038300383003830038
1020430037225000000006102954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000000000071011611296340100001003003830038300383003830038
1020430037225000000006102954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000000000071011611296340100001003003830038300383003830038
1020430037225000009006102954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000000000071011611296340100001003003830038300383003830038
1020430037225000000006102954825101001001000010010000500427731330065300373003728265328745101002001000020030000300373003711102011009910010010000100000000000071011611296340100001003003830038300383003830038

1000 unrolls and 10 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)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)9fa1a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010010006403163329630010000103003830038300383003830038
10024300372250000000662954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000006403163329630010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000006403163329630010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000006403163329630010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731303001830037300372829232876710010201000020300003003730037111002110910101000010000006403163329630010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010010006403163329630010000103003830038300383003830038
10024300372240000000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000006403163329630010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000006403163329630010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010070006403163329630010000103003830038300383003830038
10024300372250000000612954844100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000006403163329630010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  sqrdmlsh v0.2s, v8.2s, v9.2s
  movi v1.16b, 0
  sqrdmlsh v1.2s, v8.2s, v9.2s
  movi v2.16b, 0
  sqrdmlsh v2.2s, v8.2s, v9.2s
  movi v3.16b, 0
  sqrdmlsh v3.2s, v8.2s, v9.2s
  movi v4.16b, 0
  sqrdmlsh v4.2s, v8.2s, v9.2s
  movi v5.16b, 0
  sqrdmlsh v5.2s, v8.2s, v9.2s
  movi v6.16b, 0
  sqrdmlsh v6.2s, v8.2s, v9.2s
  movi v7.16b, 0
  sqrdmlsh v7.2s, v8.2s, v9.2s
  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)030708090a0b18191e1f3f51inst 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)9fa0a6a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602042009115000000000039258010010080000100800005006400002004520064200643228010020080000200240000200642006411160201100991001001600001000000010111116112006101600001002006520065200652006520065
1602042006415000000000039258010010080000100800005006400002004520064200643228010020080000200240000200642006411160201100991001001600001000011488010111116112006101600001002006520065200652006520065
1602042006415001000000039258012510080000100800005006400002004520064200643228010020080000200240000200642006411160201100991001001600001000000010111116112006101600001002006520065200652006520065
1602042006415000000000039258010010080097100800005006400002004520064200643228010020080000200240000200642006411160201100991001001600001000000010111116112006101600001002006520065200652006520065
1602042006415100000000039258010010080000100800005006400002004520064200643228010020080000200240000200642006411160201100991001001600001000000010111116112006101600001002006520065200652006520065
1602042006415000000000038258010010080000100800005006400002004520064200643228010020080000200240000200642006411160201100991001001600001000000010111116112006101600001002006520065200652006520065
16020420064150000000000324258010010080000100800005006400002004520064200643228012420080000200240000200642006411160201100991001001600001000000010161116112006101600001002006520065200652006520065
1602042006415000000000039258010010080000100800005006400002004520064200643228012520080000200240000200642006411160201100991001001600001000020010111116212013001600001002006520065200652006520065
1602042006415000000000039258010010080000100800005006400002004520064200643228010020080000200240000200642006411160201100991001001600001000030010111116112006101600001002006520065200652006520065
1602042006415000000000039258010010080000100800005006400002004520064200643228010020080000200240000200642006411160201100991001001600001000020010111116112006101600001002006520065200652006520065

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080b18191e1f3f51inst 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)5f6061696d6escheduler 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)9fa1a6a7a8a9acc2cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1600242005715000000015925800121280000128000062640000110200272004620046322800122080000202400002005020050111600211091010160000100000000100273117202113420043230160000102012720047200512004720047
1600242004615000000028725800121280000128000062640000010200312005020050322800122080000202400002005020050111600211091010160000100206000100283227204113420043230160000102013220051200472004720047
160024200461500000005125800121280000128000062640000010200312005020046322800122080000202400002004620050111600211091010160000100000000100323113202113420043215160000102005120051200512005120051
160024200501500000005125800121280000128000062640000000200312005020050322800122080000202409422005020050111600211091010160000100000060100306226244226620047230160000102005120051200512005120051
1600242005015000000051258001212800001280000626400000102003120050200503228001220800002024000020050200501116002110910101600001000016000100376224244224320047230160000102005120051200512005120051
160024200501500000005125800121280000128000062640000010200312005020050322800122080000202400002005020050111600211091010160000100000000100326226244223420047230160000102005120051200512005120051
160024200501500000005125800121280000128000062640000010200312005020050322800122080000202400002005020050111600211091010160000100000000100306223244224620047230160000102005120051200512005120051
160024200501500000005125800121280000128000062640000010200312005020050322800122080000202400002005020050111600211091010160000100000000100306224244227720047230160000102005120051200512005120051
160024200501510000005125800121280105128000062640000010200312005020050322801172080000202400002005020050111600211091010160000100002000100266218202116420043215160000102004720047200472004720047
160024200461500000004525804311280000128000062640000110200312004620046322800122080000202400002004620046111600211091010160000100000000100276223242114420043215160000102004720047200512004720051

Test 6: throughput

Count: 16

Code:

  sqrdmlsh v0.2s, v16.2s, v17.2s
  sqrdmlsh v1.2s, v16.2s, v17.2s
  sqrdmlsh v2.2s, v16.2s, v17.2s
  sqrdmlsh v3.2s, v16.2s, v17.2s
  sqrdmlsh v4.2s, v16.2s, v17.2s
  sqrdmlsh v5.2s, v16.2s, v17.2s
  sqrdmlsh v6.2s, v16.2s, v17.2s
  sqrdmlsh v7.2s, v16.2s, v17.2s
  sqrdmlsh v8.2s, v16.2s, v17.2s
  sqrdmlsh v9.2s, v16.2s, v17.2s
  sqrdmlsh v10.2s, v16.2s, v17.2s
  sqrdmlsh v11.2s, v16.2s, v17.2s
  sqrdmlsh v12.2s, v16.2s, v17.2s
  sqrdmlsh v13.2s, v16.2s, v17.2s
  sqrdmlsh v14.2s, v16.2s, v17.2s
  sqrdmlsh v15.2s, v16.2s, v17.2s
  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)030b18191e1f373f4e51inst 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)9fa0a1a6a8acc2c5branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602044008730000000041025160100100160000100160000500239899900400204003940039199733199971601002001600002004800004003940039111602011009910010016000010000000000101101161140045061600001004004040041400404004940040
1602044003930000000041025160100100160000100160000500243886501400204003940039199733199971601002001600002004800004003940039111602011009910010016000010000000000101101161140036071600001004004140052400404004040040
1602044003930000000050025160100100160000100160000500239899900400204003940039199733199971601002001600002004800004004840039111602011009910010016000010000000000101101161140036001600001004004040040400404004040040
160204400393000000017362025160100100160017100160000500239908201400204003940039199733199971601002001600002004800004003940039111602011009910010016000010000000000101101161140036001600001004004040049400404004040040
1602044003930000000041025160100100160000100160000500128000001400204003940039199733199971601002001600002004800004003940039111602011009910010016000010000000000101101161140037001600001004004940040400404004940049
16020440039300000000450025160100100160000100160000500128000001400204003940039199733199971601002001600002004800004003940049111602011009910010016000010000000000101101161140036001600001004004040049400404004040040
1602044003929900000062025160100100160000100160000500128000001400204004040049199733199971601002001600002004800004003940039111602011009910010016000010000000000101101161140037001600001004004040040400404004040050
16020440048300000001741025160100100160018100160000500128000001400204003940048199733199971601002001600002004800004003940048111602011009910010016000010000000000101101161140036001600001004004040049400404004040040
16020440049300000001750025160117100160000100160000500128000001400204003940039199733199971601002001600002004800004003940039111602011009910010016000010000000000101101161140036001600001004004940040400404004140050
16020440039300000001741025160100100160000100160000500128000001400294003940039199733199971601002001600002004800004004840048111602011009910010016000010000000001101101161140036001600001004004040040400404004040040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e373f4e51inst 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)5f6061696b6d6edispatch 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)9fa1a8a9acc5branch mispredict (cb)cdcfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1600244005130000711025160010101600001016000050243886511040029040039400391999632002016001020160000204800004003940049111600211091010160000100000000100223216162114440036206160000104004040040400494004040050
160024400393000046025160010101600001016000050131999811040020040039400391999632002816001020160000204800004003940089111600211091010160000100006000100223113162117640036206160000104004040072400404004040040
160024400393000046025160010101600171016000050128000011040020040039400391999632001916001020160000204800004003940039111600211091010160000100000000100223116162114740045206160000104004040041400494004040040
160024400483000146025160010101600001016000050128000011040020040039400391999632001916001020160000204800004003940039111600211091010160000100200000100223114162116740036206160000104004040049400404004040049
160024400483000046025160010101600001016000050128000011040020040039400391999632001916001020160000204800004003940039111600211091010160000100003000100223114162114440045206160000104004040040400404004040040
160024400392990067025160010101600001016000050128000011040020040039400712000232001916001020160000204800004003940039111600211091010160000100000000100223116162114340045206160000104007240041400414005040040
160024400393000062025160027101600001016000050239899911040029040039400481999632001916001020160000204800004003940039111600211091010160000100000000100243117162114440036206160000104004040040400404004040040
1600244003930006167025160010101600171016000050128000011040020040039400481999632002816001020160000204800004004840039111600211091010160000100000000100223116162117640036206160000104004940254400494004040040
16002440039300017462525160010101600001016000050128000011040052040039400391999632002816001020160000204800004003940039111600211091010160000100000020100223116162114440036206160000104004040040400494004040040
160024400492990046025160010101600171016000050239899901040020340048400391999632002816001020160000204800004003940040111600211091010160000100000000100223113164126840036209160000104004040040400494004040040