Apple M1 Microarchitecture Research by Dougall Johnson

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

MLS (vector, 16B)

Test 1: uops

Code:

  mls v0.16b, v1.16b, v2.16b
  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)a0a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037230612548251000100010003983131301830373037241532895100010003000303730371110011000000073116112675100030383038303830383038
100430372301512548251000100010003983131301830373037241532895100010003000303730371110011000001073116112630100030383038303830383038
100430372205292548251000100010003983131301830373037241532895100010003000303730371110011000000073116112630100030383038303830383038
10043037230612548251000100010003983131301830373037241532895100010003000303730371110011000000073116112630100030383038303830383038
10043037230612548251000100010003983131301830373037241532895100010003000303730371110011000000073116112630100030383038303830383038
10043037230612548251000100010003983131301830373037241532895100010003000303730371110011000000073116112630100030383038303830383038
100430372304992548251000100010003983131301830373037241532895100010003000303730371110011000000073116112630100030383038303830383038
10043037230612548251000100010003983131301830373037241532895100010003000303730371110011000000073116112630100030383038303830383038
10043037230612548251000100010003983131301830373037241532895100010003000303730371110011000000073116112630100030383038303830383038
10043037220612548251000100010003983131301830373037241532895100010003000303730371110011000000073116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  mls v0.16b, v1.16b, v2.16b
  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)031e1f3a3f4e51inst 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)9fa1a6a8a9acc2cfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043023522500028582954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000103071012162229634100001003003830038300383003830038
1020430037225000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000106071013162229634100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100003609071012162229634100001003003830038300383003830038
102043003722500078929548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100001409071012162229634100001003003830038300383003830084
102043003722500061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000055015071012162329634100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100005206071012162229634100001003003830038300383003830038
1020430181225000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000003271012163229634100001003003830038300383003830038
10204300372251200612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000106071012163229634100001003003830038300383003830038
10204300372240006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100005606071012162229634100001003003830038300383003830038
10204300372250016129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100003909071012162229634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)031e3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)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)9fa8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640316222963010000103003830038300383003830038
100243003722507262954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103018030038300383003830038
1002430037225276092954825100101010000101000061427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722507262954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722507262954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722405362954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103013230038300383003830038
100243003722505082954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722507262954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722505362954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  mls v0.16b, v0.16b, v1.16b
  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)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)9fa0a1a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000000612954825101001001000010010000500427731303001830037300372827262874110100200100082003002430037300371110201100991001001000010000000011171701600296470100001003003830038300383003830038
10204300372250000000612954825101001001000010010000500427731303001830037300372827272874010100200100082003002430037300371110201100991001001000010000000011171701600296470100001003003830038300383003830083
10204300372250000000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000000000071011611296340100001003022930038300383003830038
10204300372250000000612954825101001001000010010000500427828803001830037300372826532874510100200100002003000030037300371110201100991001001000010000000000071011611296340100001003003830038300383003830038
10204300372250000000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000000000071011611296340100001003003830038300383003830038
10204300372250000000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000000000071011611296340100001003003830038300383003830038
102043003722500000006129548251010010010000100100005004277313030018300373003728265252874510100200100002003000030037300371110201100991001001000010000000000071011611296340100001003003830038300383003830038
10204300372250000000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000000000171011611296340100001003003830038300383003830038
10204300372250000000612954825101001001000010410000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000000000071011611296340100001003003830038300383003830038
10204300372250000000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000000000071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03081e1f3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa0a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000000640216222963010000103003830038300383003830038
1002430037224000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000030640216222963010000103003830038300383003830038
1002430037224000822954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000000640216222970210000103003830038300383008530038
1002430037225000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010003000640216222963010000103003830038300383003830038
1002430037225000822954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010001030668216222963010000103003830038300383003830038
10024300372250001032954825100101010000111014950427731303001830037300372828732876710010201000020300003003730037111002110910101000010200030640216222963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000000640216222963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000000640216222963010000103003830038300383003830038
1002430037225060612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010001200640216222963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000000640216222963010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  mls v0.16b, v1.16b, v0.16b
  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)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)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)9fbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
102043003722500612954825101001001000711110149500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
102043003722400612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010007401161129634100001003003830038300383003830038
102043003722400612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
1020430037225001032954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)031e3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)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)9fa0a8a9acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250822954825100101010000101000050427731313001803003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
100243003722501662954825100101010000101000050427731313001803003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
100243003722504952954825100101110000101000050427731313001803003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
100243003722501452954825100101010000101000050427731313001803003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
100243003722501452954825100101010000101000050427731303001803003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
100243003722401452954825100101010000101000050427731303001803003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
10024300372240612954825100101010000101000050427731303001803003730037282873287671001020100002030000300373003711100211091010100001003000640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001803003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
100243003722406782954825100101010000101000050427731303001803003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
100243003722501452954825100101010000101000050427731313001803003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  mls v0.16b, v8.16b, v9.16b
  movi v1.16b, 0
  mls v1.16b, v8.16b, v9.16b
  movi v2.16b, 0
  mls v2.16b, v8.16b, v9.16b
  movi v3.16b, 0
  mls v3.16b, v8.16b, v9.16b
  movi v4.16b, 0
  mls v4.16b, v8.16b, v9.16b
  movi v5.16b, 0
  mls v5.16b, v8.16b, v9.16b
  movi v6.16b, 0
  mls v6.16b, v8.16b, v9.16b
  movi v7.16b, 0
  mls v7.16b, v8.16b, v9.16b
  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)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)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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16020420089150000201258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100001011221622200611600001002006520065200652006520065
1602042006415000060258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100001011221622200611600001002006520065200652006520065
1602042006415000083258010010080000100800005006400000200452006420064322802282008000020024000020064200641116020110099100100160000100001011221622200611600001002006520065200652006520065
1602042006415200039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100001011221622200611600001002006520065200652006520065
16020420064151000125258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100001011221622200611600001002006520065200652006520065
16020420064150000104258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100001011221622200611600001002006520065200652006520065
16020420064150000102258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100001011221622200611600001002006520065200652006520065
16020420064150000103258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100001011221622200611600001002006520065200652006520065
1602042006415000039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100001011221622200611600001002006520065200652006520065
1602042006415100039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100001011221622200611600001002006520065200652006520065

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b1e3a3f51inst 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)9fa6a8a9acc5cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16002420065150000115125800121280000128000062640000112002720046200463228001220800002024000020046200461116002110910101600001001000100273113202115520043215160000102004720047200472004720047
160024200461501005125800121280000128000062640000112002720046200463228001220800002024000020046200461116002110910101600001000000100303113202115420043215160000102004720047200472004720047
160024200461500004525800121280000128000062640000112002720046200463228001220800002024000020046200461116002110910101600001000000100263117202117420043215160000102005120047200472004720047
1600242004615000023425800121280000128000062640000112002720046200463228001220800002024000020046200461116002110910101600001000000100303118202117420043215160000102012820047200472004720047
160024200461500004525800121280000128000062640000112002720046200463228001220801042024000020046200461116002110910101600001000001100293115202115820047215160000102004720047200472004720047
1600242004615000015425800121280000128000062640000112002720046200463228001220800002024000020046200461116002110910101600001000000100313125202113520043215160000102004720047200472004720047
160024200461500006625800121280000128000062640000112002720046200463228001220800002024000020046200461116002110910101600001000000100303117202115520043230160000102004720047200472004720047
1600242004615000021525800121280000128000062640000112002720046200463228001220800002024000020046200461116002110910101600001000000100303114204117720043215160000102004720047200472004720047
160024200461500004525800121280000128000062640000112002720046200463228001220800002024000020046200461116002110910101600001000000100283117202117420043215160000102012820047200472004720047
160024200461500004525800121280000128000062640000112002720046200463228001220800002024000020046200461116002110910101600001000000100283117202117920043215160000102004720047200472004720047

Test 6: throughput

Count: 16

Code:

  mls v0.16b, v16.16b, v17.16b
  mls v1.16b, v16.16b, v17.16b
  mls v2.16b, v16.16b, v17.16b
  mls v3.16b, v16.16b, v17.16b
  mls v4.16b, v16.16b, v17.16b
  mls v5.16b, v16.16b, v17.16b
  mls v6.16b, v16.16b, v17.16b
  mls v7.16b, v16.16b, v17.16b
  mls v8.16b, v16.16b, v17.16b
  mls v9.16b, v16.16b, v17.16b
  mls v10.16b, v16.16b, v17.16b
  mls v11.16b, v16.16b, v17.16b
  mls v12.16b, v16.16b, v17.16b
  mls v13.16b, v16.16b, v17.16b
  mls v14.16b, v16.16b, v17.16b
  mls v15.16b, v16.16b, v17.16b
  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)03070a181e373a3f51inst 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)9fa8branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160204400692991100025725160117100160000100160000500128000004002040039400481997331999716010020016000020048000040039400481116020110099100100160000100001011411161413400361600001004004940040400494004040040
1602044003930011000271325160100100160000100160000500239899914002940039400481997331999716010020016000020048000040039400491116020110099100100160000100001011413161314400361600001004005040049400404004940049
160204400483001100025725160100100160000100160000500239899904002040039400481997332000616010020016000020048000040048400391116020110099100100160000100001011413161412400361600001004004040049400404004940049
160204400492991100025725160100100160000100160000500239899904002040039400481997332000616010020016000020048000040039400481116020110099100100160000100001011414161412400361600001004004040049400404004940040
1602044003930011001724825160100100160000100160000500128000004002040039400481997332000616010020016000020048000040048400391116020110099100100160000100001011413161312400361600001004004940040400504004040040
160204400392991100024825160100100160000100160000500239899904002940039400481997331999716010020016000020048000040039400481116020110099100100160000100001011412161412400361600001004004040049400404004940040
160204400393001100025725160100100160000100160000500128000004002940048400391997331999716010020016000020048000040039400391116020110099100100160000100001011412161412400361600001004004040049400404004940049
160204400393001100172482516011710016001710016000050023989990400294004840039199733200061601002001600002004800004003940048111602011009910010016000010000101141216716400361600001004005040040400494004040049
160204400483001100024825160100100160000100160000500131999804002040039400481997332000616010020016000020048000040039400481116020110099100100160000100001011415161311400361600001004004940040400494004040049
160204400483001100025825160100100160000100160000500239899904002940048400391997331999716010020016000020048000040048400391116020110099100100160000100001011411161014400451600001004004940040400494004040049

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03181e373f4e51inst 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)5f6061696d6edispatch 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)9fa8a9accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16002440048300065106702516001010160000101600005012800001154002040039400391999632001916001020160000204800004003940071111600211091010160000101031002284161621137400460155160000104004040040400404004040143
1600244009330006004602516001010160000101600006012800001154002040039400391999632001916001020160000204800004003940039111600211091010160000100001002284131621154400360155160000104004040040400494004040040
16002440039300027046025160010101600611016000050128000001540020400394004019996320029160010201600002048000040049400491116002110910101600001000010022851516222374003601510160000104004940040400404005040050
16002440039299030046025160010101600171016000050128000001540020400394007119996320019160010201600002048000040039400391116002110910101600001000010024852316422374003603010160000104004040040400404004040040
1600244003930006046025160071101600001016000050128000011540052400394004919996320019160010201600002048000040039400712116002110910101600001000010022851516422574003603010160000104004040040400404009040049
16002440039300060460251600271016001810160000502399027015400204003940039199963200191600122016000020480000400394003911160021109101016000010000100221142516422574003603010160000104004040049400404004140040
160024400713000151752025160028101600001016000050128000001540020400394003919996320028160010201600002048000040039400711116002110910101600001000010022115231641297400362305160000104004040049400404004040040
160024400393000531615202516001010160000101600005012800000154002040049400391999632001916001020160000204800004003940048111600211091010160000100001002284151621157400680155160000104004040040400404004040040
160024400393000121773025160010101600001016000050128000001540020400394007119996320019160010201600002048000040039400391116002110910101600001000010024115251622255400360305160000104004040050400404004040040
16002440039300060223025160030101600001016000050128000011540020400404004919996320019160010201600002048000040039400391116002110910101600001000310022842516222374003603010160000104004040072400404004040040