Apple M1 Microarchitecture Research by Dougall Johnson

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

MLS (by element, 2S)

Test 1: uops

Code:

  mls v0.2s, v1.2s, v2.s[1]
  movi v0.16b, 1
  movi v1.16b, 2
  movi v2.16b, 3

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 1.000

Issues: 1.000

Integer unit issues: 0.000

Load/store unit issues: 0.000

SIMD/FP unit issues: 1.000

retire (01)cycle (02)031e3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372306125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
1004303723156125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372206125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
1004303723073725482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372206125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  mls v0.2s, v1.2s, v2.s[1]
  movi v0.16b, 1
  movi v1.16b, 2
  movi v2.16b, 3

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03041e1f3a3f4e51inst 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)9fa8a9acc2cfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250001662954825101001001000010010000500427731313001830037300372826503287451010020010000200300003003730037111020110099100100100001002000713141655296340100001003003830038300383003830038
102043003722510017829548251010010010000100100005004277313030018300373003728265032874510100200100002003000030037300371110201100991001001000010000150713151655296340100001003003830038300383003830038
10204300372251001782954825101001001000010010000500427731303001830037300372826503287451010020010000200300003003730037111020110099100100100001001000713151654296340100001003003830038300383003830038
10204300372251001782954825101001001000010010000500427731313001830037300372826503287451010020010000200300003003730037111020110099100100100001002000713141655296340100001003003830038300383003830230
10204300372251001782954825101001001000010010000500427731303001830037300372826503287451010020010000200300003003730037111020110099100100100001001000713141664296340100001003003830038300383003830038
10204300372251001782954825101001001000010010000500427731313001830037300372826503287451010020010000200300003008430037111020110099100100100001001000713151635296340100001003003830038300383003830038
102043003722510017829548251010010010000100100005004277313130018300373003728265032874510100200100002003000030037300371110201100991001001000010031030712151656296340100001003003830038300383003830038
10204300372251003782954825101001001000010010000500427731303001830037300372826503287451010020010000200300003003730037111020110099100100100001002000713151655296340100001003003830038300383003830038
10204300372251001782954825101001001000010010000500427731303001830037300372826503287451010020010000200300003003730037111020110099100100100001001000713151655296340100001003003830038300383003830180
102043003722510017432954825101001001000010010000500427731313001830037300372826503287451010020010000200300003003730037111020110099100100100001000000713151665296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03083f4e51inst 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)9fa8cdcfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722506629548251001010100001010000504277313003001830037300372828732876710010201000020300003003730037111002110910101000010006400216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313103001830037300372828732876710010201000020300003003730037111002110910101000010006400216322963010000103003830038300383003830038
100243003722406129548251001010100001010000504277313003001830037300372828732876710010201000020300003003730037111002110910101000010006400216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313103001830037300372828732876710010201000020300003003730037111002110910101000010006400216222963010000103003830038300383003830038
100243003722406129548251001010100001010000504277313103001830037300372828732876710010201000020300003003730037111002110910101000010006400316422963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313003001830037300372828732876710010201000020300003003730037111002110910101000010006400316222963010000103003830038300383003830038
100243003722406129548251001010100001010000504277313103001830037300372828732876710010201000020300003003730037111002110910101000010006400216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313103001830037300372828732876710010201000020300003003730037111002110910101000010006400216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313003001830037300372828732876710010201000020300003003730037111002110910101000010006400216222963010000103003830038300383003830038
100243003722506129548441001010100001010000504277313103001830037300372828732876710010201000020300003003730037111002110910101000010006400216322963010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  mls v0.2s, v0.2s, v1.s[1]
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030818191e3a3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa6a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000150612954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
1020430037225000007962954825101001001000010010000500427731330018300373003728290328745101002001000020030000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
1020430037224000001682954825101001001000010010000500427731330018300373003728265328745107262001000020030000300373003711102011009910010010000100010007101161129634100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
1020430037225000001032954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100002907101161129742100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
102043003722400000612954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000047101161129634100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100310007101161129634100001003003830038300383003830038
102043003722500000612954825101001001000010010000500428209930018300373003728265328745101002001000020030000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b183a3f4e51inst 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)9fa1a6a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722501061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000640516542963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000640516452963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000001640516542963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000640416342963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000640449552963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373007911100211091010100001000000640516552963010000103003830038300383003830038
1002430037225000726295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000640516542963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000640516552963010000103003830038300383003830038
100243003722400061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000640416452963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000640516552963010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  mls v0.2s, v1.2s, v0.s[1]
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)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)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)9fa0a1a6a8a9acc2c5branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000042006129548251010010010000100100005004277313030018030037300372826532874510100200100002003000030037300371110201100991001001000010000000000071021622296340100001003003830038300383003830038
102043003722400000006129548251010010010000100100005004277313030018030037300372826532874510100200100002003000030037300371110201100991001001000010000000000071021622296340100001003003830038300383003830038
102043003722500000008929548251010010010000100100005004277313030018030037300372826532874510100200100002003000030037300371110201100991001001000010000000000071021622296340100001003003830038300383003830038
102043003722500000006129548251010010010000100100005004277313030018030037300372826532874510100200100002003000030037300371110201100991001001000010000000000071021622296340100001003003830038300383003830038
102043003722500000006129548251010010010000100100005004277313130018030037300372826532874510100200100002003000030037300371110201100991001001000010000000000071021622296340100001003003830038300383003830038
102043003722500000006129548251010010010000100100005004277313030018030037300372826532874510100200100002003000030037300371110201100991001001000010000000000071021622296340100001003003830038300383003830038
102043003722400000006129548251010010010000100100005004277313030018030037300372826532874510100200100002003000030037300371110201100991001001000010000000000071021622296340100001003003830038300383003830038
10204300372250000420010329548251010010010000100100005004277313130018030037300372826572874510100200100002003000030037300371110201100991001001000010000000000071021622296340100001003003830038300383003830038
1020430037225000000053629548251010010010000100100005004277313030018030037300372826532874510100200100002003000030037300371110201100991001001000010000000000171021622296341100001003003830038300383003830038
102043003722400000006129548251010010010000100100005004277313030018030037300372826532874510100200100002003000030037300371110201100991001001000010000000000071021622296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)031e1f3f4e51inst 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)9facc5cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037224006129548251001010100001010000504277313130018030037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018030037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313130018030037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313130018030037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
10024300372250010629548251001010100001010000504277313030018030037300372828732876710010201000020300003003730037111002110910101000010010640316332963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313130018030037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313130018030037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313130018030037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018030037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
1002430037224006129548251001010100001010000504277313130018030037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  mls v0.2s, v8.2s, v9.s[1]
  movi v1.16b, 0
  mls v1.2s, v8.2s, v9.s[1]
  movi v2.16b, 0
  mls v2.2s, v8.2s, v9.s[1]
  movi v3.16b, 0
  mls v3.2s, v8.2s, v9.s[1]
  movi v4.16b, 0
  mls v4.2s, v8.2s, v9.s[1]
  movi v5.16b, 0
  mls v5.2s, v8.2s, v9.s[1]
  movi v6.16b, 0
  mls v6.2s, v8.2s, v9.s[1]
  movi v7.16b, 0
  mls v7.2s, v8.2s, v9.s[1]
  movi v8.16b, 9
  movi v9.16b, 10

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)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)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
16020420089151039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100001011431644200611600001002006520065200652006520065
16020420064151039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100001011541644200611600001002006520065200652006520065
16020420064150939258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100001011341655200611600001002006520065200652006520065
16020420064150039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100101011441644200611600001002006520065200652006520065
16020420064151039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100001011451635200611600001002006520065200652006520065
16020420064150039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100001011551654200611600001002006520065200652006520065
16020420064150081258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100091011451654200611600001002006520065200652006520065
16020420064151039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100001011441653200611600001002006520065200652006520065
16020420064150039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100001011441654200611600001002006520065200652006520065
16020420064150060258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100001011551655200611600001002006520065200652006520065

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03181e3f51inst 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)5f6061696d6e74scheduler 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)9fa8acc2cfd0d2icache miss (d3)itlb miss (d4)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1600242006315100131258001212800001280000626400001102002720046200460322800122080000202400002005020046111600211091010160000100001002784103242115520043215160000102004720047200472004720047
160024200461500045258001212800001280000626400001152002720046200460322800122080000202400002005020046111600211091010160000100001002984103202115520043215160000102004720047200472004720047
160024200461500045258001212800001280000626400001152002720046200460322800122080000202400002004620046111600211091010160000100001002784104202224420043215160000102004720047200472004720047
160024200461500045258001212800001280000626400001152002720046200460322800122080000202400002004620046111600211091010160000100001002784103202114420043215160000102004720047200472004720047
160024200461500045258001212800001280000626400001152002720046200460322800122080000202400002004620046111600211091010160000100001002784104202113420043215160000102004720047200472004720047
160024200461500045258001212800001280000626400001152002720046200460322800122080000202400002005020050111600211091010160000100001002884104202114320043215160000102004720047200472004720047
1600242004615100512580012128000012800006264000001520031200502005003228001220800002024000020046200462116002110910101600001000010031115205242225420047230160000102005120051200472005120051
1600242005015000129258001212800001280000626400001152002720046200460322800122080000202400002005020050111600211091010160000100001002784104202113320043215160000102004720047200472004720047
1600242004615000512580012128000012800006264000011520031200502005003228001220800002024000020046200461116002110910101600001000010030115105244225420047230160000102005120051200512005120051
160024200461500945258001212800001280000626400001152003120050200460322800122080000202400002004620050111600211091010160000100001002684105202115320043215160000102005120051200512005120051

Test 6: throughput

Count: 12

Code:

  mls v0.2s, v12.2s, v13.s[1]
  mls v1.2s, v12.2s, v13.s[1]
  mls v2.2s, v12.2s, v13.s[1]
  mls v3.2s, v12.2s, v13.s[1]
  mls v4.2s, v12.2s, v13.s[1]
  mls v5.2s, v12.2s, v13.s[1]
  mls v6.2s, v12.2s, v13.s[1]
  mls v7.2s, v12.2s, v13.s[1]
  mls v8.2s, v12.2s, v13.s[1]
  mls v9.2s, v12.2s, v13.s[1]
  mls v10.2s, v12.2s, v13.s[1]
  mls v11.2s, v12.2s, v13.s[1]
  movi v12.16b, 13
  movi v13.16b, 14

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)03191e373f4e51inst 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)9fa6a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1202043003922500041025120152100120000100120000500960000130020300393095114973314997120100200120000200360000300393003911120201100991001001200001000000761011611300361200001003004030923300403004030040
1202043003922500041025120100100120000100120000500960000130020300393003914973314997120100200120000200360000300393003911120201100991001001200001000000761011611300361200001003004030040300403004030040
1202043095122500041025120100100120000100120000500960000130020300393003914973314997120100200120000200360000300393003911120201100991001001200001000003761011611300361200001003004030040300403004030040
1202043003922500041025120100100120000100120000500960000130020300393003914973314997120100200120000200360000300393003911120201100991001001200001000000761011611300361200001003004030040300403004030040
1202043003922500041025120100100120000100120000500960000130020309513003914973314997120100200120000200360000300393003911120201100991001001200001000000761011611300361200001003004030040300403004030952
120204300392250843041025120100100120000100120000500960000130020300393003914973314997120100200120000200360000300393003911120201100991001001200001000000761011611300361200001003004030040300403004030040
1202043003922505070410251201001001200001001200005004286184030020309513003914973314997120100200120000200360000300393003911120201100991001001200001000000761011611300361200001003004030040300403004030040
120204300392250007600251201001001200001001200005004286184030020300393003914973314997120100200120000200360000300393003911120201100991001001200001000000761011611300361200001003004030040309523004030040
1202043003922500041025120100100120052100120000500960000030020300393003914973314997120100200120000200360000300393003911120201100991001001200001000000761011611300361200001003004030040309523004030040
1202043003922500041025120100100120000100120000500960000130020300393003914973314997120100200120000200360000300393003911120201100991001001200001000000761011611300361200001003004030040300403004030040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e373a3f4e51inst 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)9fa8c5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
12002430048228002450251200101012003510120000509600000300203003930039149963150191200102012000020360000300393003911120021109101012000010007524171617830036120000103004030040300403004030040
120024300392250025002512001010120000101200005096000013002030039300901499631501912001020120000203600003003930039111200211091010120000100075241316161430036120000103004030040300403004030040
12002430039225002450251200101012000010120000509600001300203003930039149963150191200102012000020360000300393003921120021109101012000010007524716161930036120000103004030040300403004030040
1200243003922501824502512001010120000101200005096000013002030039300391499631590212001020120000203600003175030039111200211091010120000100075241916171530036120000103004030040300403004030040
120024300392250024502512001010120000101200005096000003002030039300391499631501912001020120000203600003004030039111200211091010120000100075241316141430036120000103004030040300403004030040
12002430039224002450251200101012000010120000509600001300203003930039149963150191200102012000020360000300393003911120021109101012000010007524111681530036120000103004030040300403004030040
120024300392250024502512001010120000101200005096075613002030039300391499631501912001020120000203600003003930039111200211091010120000100075241916151730036120000103004030040300403004030040
120024300392250024502512001010120000101200005096000013002030039300391499631673912001020120000203600003003930039111200211091010120000100075241316161430036120000103004030040300403004030040
120024300392250024502512001010120000101200005096000003002030039300391499631501912001020120000203600003003930039111200211091010120000100075241516131730036120000103004030040300403004030040
120024317502250024502512001010120000101200005096000003002030039300391499631501912001020120000203600003003930039111200211091010120000100075241516131530036120000103004030040300403004030040