Apple M1 Microarchitecture Research by Dougall Johnson

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

MLA (by element, 4H)

Test 1: uops

Code:

  mla v0.4h, v1.4h, v2.h[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
100430372206125482510001000100039831313018303730372415328951000100030003037303711100110000073216222630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100030003037303711100110000073216222630100030383038303830383038
100430372208425482510001000100039831313018303730372415328951000100030003037303711100110000073216222630100030383038303830383038
100430372406125482510001000100039831313018303730372415328951000100030003037303711100110000073216222630100030383038303830383038
100430372208225482510001000100039831313018303730372415328951000100030003037303711100110000373216222630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100030003037303711100110000094268222630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100030003037303711100110000073216222630100030383038303830383038
100430372206125482510001000100039831303018303730372415328951000100030003037303711100110000073216222630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100030003037303711100110000073216222630100030383038303830383038
100430372206125482510001000100039831303018303730372415328951000100030003037303711100110000073216222630100030383038303830383038

Test 2: Latency 1->1

Code:

  mla v0.4h, v1.4h, v2.h[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)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)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)cfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722400822954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000071004162229634100001003003830038300383003830038
102043003723200612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000071012162229634100001003003830038300383003830038
1020430037225001912954825101001001000010210298527427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000071012162229634100001003003830038300383003830038
102043003722500822954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000071212162329634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000071012162329634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010006071212162229634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000071012162229634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010002535071012162229634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000071012162229634100001003008530038300383003830038
102043003722500612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000071012162229634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0307080b18191e1f3f4e51inst 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)9fa0a1a6a8a9acc2branch mispredict (cb)cfd5d6daddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500000001522954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100000000064031602229630010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100000000064021602229630010000103003830038300383003830038
100243003722500000001032954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100000000064021602329630010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100000000064021602229630010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100000000064021602229630010000103003830038300383003830038
10024300372250100000612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100000000064021602229630010000103003830038300383003830038
100243003722500000007262954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100000000064021602229630010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100000000064021602229630010000103003830038300383003830038
100243003722500000007262954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100000000064021602229630210000103003830038300383003830038
100243003722500000007262954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100000000064021612229630010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  mla v0.4h, v0.4h, v1.h[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)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)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)9fa6a8acc2cfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372240076729539251010010010000100100005004277313130018030037300372826503287451010020010000200300003003730037111020110099100100100001002000710012511296340100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313030018030037300372826503287451010020010000200300003003730037111020110099100100100001000000710011611296340100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313130018030037300372826503287451010020010000200300003003730037111020110099100100100001000000741111611296340100001003003830038300383003830038
102043003722512016629548251010010010000100100005004277313030018030037300372826503287451010020010000200300003003730037111020110099100100100001000100710011611296340100001003003830038300383003830038
1020430037225001580295484610100100100001001000050042773131300180300373003728265012287821010020210000204300003008430037111020110099100100100001000030710011611296340100001003003830038300383003830038
10204300372251206129548251010010010000100100005004277313130018030037300372826503287451010020010000200300003003730037111020110099100100100001000000710011611296340100001003003830038300383003830038
10204300372251206129548251010010010000100100005004277313130018030037300372826503287451010020010000200300003003730037111020110099100100100001000000710011611296340100001003003830038300383003830038
1020430037225006129548251010010010000126100005004277313130018030037300372826503287451010020010000200300003008530037111020110099100100100001000000710011612296340100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313030018030037300372826503287451010020010000200300003003730037111020110099100100100001000000710011611296340100001003003830038300383003830038
102043003722501086129548251010010010000100100005004277313130018030037300372826503287451010020210000200300003003730037111020110099100100100001000000710011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03081e3f4e51inst 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)9fa0a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001001200640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100010640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216272963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100003640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216232963010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  mla v0.4h, v1.4h, v0.h[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)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)9fa0a1a6a7a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000087001702954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000000000071021622296340100001003003830038300383003830038
10204300372250000000612954825101001001000011910000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000000000071021622296340100001003003830038300383003830038
10204300372250000000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000000000071021622296340100001003003830038300383003830038
10204300372240000000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000000000071021622296340100001003003830038300383003830038
10204300372250000000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000000000071021622296340100001003003830038300383003830038
10204300372250000000612954825101001001000010010000500427731313001830037300372826532874510100200100002103000030037300371110201100991001001000010000000000071021622296340100001003003830038300383003830038
10204300372251000000612954825101001001000010010000500428274113001830037300372826532874510100200100002003000030037300371110201100991001001000010000000000071021622296340100001003003830038300383003830038
10204300372250000000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000000000071021622296340100001003003830038300383003830038
10204300372250000000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110202100991001001000010000000000071021622297020100001003003830038300383003830038
10204300372250000000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030229300371110201100991001001000010000000000071021622296340100001003003830038300383003830038

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)9fa8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722400612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100000640416452963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100000640716542963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100000640416542963010000103003830038300383003830038
100243003722400612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100000640616542963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100000640416552963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100000640716552963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100000640516552963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100000640616552963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100000640516452963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100000640616542963010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  mla v0.4h, v8.4h, v9.h[1]
  movi v1.16b, 0
  mla v1.4h, v8.4h, v9.h[1]
  movi v2.16b, 0
  mla v2.4h, v8.4h, v9.h[1]
  movi v3.16b, 0
  mla v3.4h, v8.4h, v9.h[1]
  movi v4.16b, 0
  mla v4.4h, v8.4h, v9.h[1]
  movi v5.16b, 0
  mla v5.4h, v8.4h, v9.h[1]
  movi v6.16b, 0
  mla v6.4h, v8.4h, v9.h[1]
  movi v7.16b, 0
  mla v7.4h, v8.4h, v9.h[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)03191e3f51inst 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
160204200881510039258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100001011121611200611600001002006520065200652006520065
160204200641500039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100001011131611200611600001002006520065200652006520065
160204200641510039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100001011121611200611600001002006520065200652006520065
160204200641500039258010010080000100800005006400000202182006420064322801002008000020024000020064200641116020110099100100160000100001011131611200611600001002006520065200652006520065
160204200641500039258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100101011121611200611600001002006520065200652006520065
160204200641500039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100001011121611200611600001002006520065200652006520065
160204200641500039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100001011121611200611600001002006520065200652006520065
160204200641500039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
160204200641510039258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100001011121611200611600001002006520065200652006520065
160204200641500062258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100001011121611200611600001002006520065200652006520065

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2507

retire (01)cycle (02)030407090a3a3f51inst 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)5f60696d6e74scheduler 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)9fcfd0d2icache miss (d3)itlb miss (d4)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1600242008715001001581278001212800001280000626400001120034200622005303228001220800002024000020053200531116002110910101600001010050311141271112425200502211160000102005420054200542005420054
1600242005315111111106278001212800001280000626400001120034200532005303228001220800002024000020053200531116002110910101600001010044311128271112124200502212160000102005420054200542005420063
1600242005315011111112278001212800001280000626400001120034200532005303228001220800002024000020053200531116002110910101600001010049311129271112727200502211160000102005420054200542005420054
1600242005315011111169278001212800001280000626400001120034200532005303228001220800002024000020053200531116002110910101600001010050321125271112126200502211160000102005420054200542005420054
1600242005315010111106278001212800001280000626400001120034200532005303228022120800002024000020053200531116002110910101600001010045321127271112025200502211160000102005420054200542005420054
1600242005315010111190278001212800001280000626400001120034200532005303228001220800002024000020053200531116002110910101600001010040321123271112126200502211160000102012420054200542005420054
160024200531500001094278001212800001280000626400001120034200532005303228001220800002024000020053200531116002110910101600001010045311124271111627200502211160000102005420054200542005420054
1600242005315011101169278001212800001280000626400001120034200532005303228001220800002024000020053200531116002110910101600001010049321123271112516200502211160000102005420054200542005420054
16002420053150101001062780012128000012800006264000011200342005320053032280012208000020240000200532005311160021109101016000010100503211151591112616200502211160000102005420054200542005420054
1600242005315010110106278001212800001280000626400001120034200532005303228001220800002024000020053200531116002110910101600001010050321123271112426200502211160000102005420054200542005420054

Test 6: throughput

Count: 12

Code:

  mla v0.4h, v12.4h, v13.h[1]
  mla v1.4h, v12.4h, v13.h[1]
  mla v2.4h, v12.4h, v13.h[1]
  mla v3.4h, v12.4h, v13.h[1]
  mla v4.4h, v12.4h, v13.h[1]
  mla v5.4h, v12.4h, v13.h[1]
  mla v6.4h, v12.4h, v13.h[1]
  mla v7.4h, v12.4h, v13.h[1]
  mla v8.4h, v12.4h, v13.h[1]
  mla v9.4h, v12.4h, v13.h[1]
  mla v10.4h, v12.4h, v13.h[1]
  mla v11.4h, v12.4h, v13.h[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)031e1f373f4e51inst 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)9fa1a6a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1202043003922500141671325120118100120018100120000500960000304203174830039166533149971201002001200002003600003004230039111202011009910010012000010000000761021611300361200001003004031749300403174931763
12020430039224001842025120100100120000100120000500990000317293004030039149733149971201002001200002003600003003930039111202011009910010012000010000000761011611300361200001003174930040317493004031749
12020431748224001861025120100107120000100120000500990000300213174830039149733149971201002001200002003600003003931748111202011009910010012000010020000761011611317451200001003004031749300403174930040
12020430039225000706671325120118100120018100120000500960000300203003930040166533167081201002001200002003600003174830039111202011009910010012000010000000761011611309191200001003174930040317493004031749
12020431748225001420251201001001200001001200005004399524317293174830039149733167061201002001200002003600003003930040111202011009910010012000010000000761011611317451200001003004030041300403004130040
120204300392250018610251201001001200001001200005004399524317293010430039149733149971203122001200002003600003174830039111202011009910010012000010000000761011611300361200001003004030040300403004030040
12020430039225001842025120100100120000100120000500990000317293174830039149733149971201002001200002003600003174830039111202011009910010012000010000000761011611317451200001003004031749300403004130923
12020430039238001841025120118100120018100120000500960000300203003930040166533149971201002001200002003600003003930093111202011009910010012000010000000761011611300361200001003009530040300403004030040
12020430039225001861671325120118100120018100120000500960000300203003931748166533149991201002001200002003600003003930040111202011009910010012000010000000761011611300361200001003004130040317493004031749
1202043003922500041671325120118100120018100120000500960000300203003931748149733149971201002001200002003600003003931748111202011009910010012000010000000761011611300361200001003174930040317493004031749

1000 unrolls and 10 iterations

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

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)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)9fa8accfd0d2icache miss (d3)d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
120024300392250040025120010101200001012000050960000003173131750300391499631501912001020120000203600003003930040111200211091010120000100075200004165830036120000103004030040300403004030040
120024300392250040025120011101200011012000050960000003002030039300401667731501912001020120000203600003003931750111200211091010120000100075205305167730036120000103004130040300403004030040
1200243003923800400251200101012000010120000504394061003173130040300391499631501912001020120000203600003003930040111200211091010120000100075200005167730036120000103004030040300403004030040
120024300392240040025120010101200001012000050960000003173131750300391499631501912001020120000203600003092230039111200211091010120000103075200005165430036120000103175130040300413004030040
120024300392250061025120010101200001012000050960000003173130039300391499631501912001020120000203600003003930039111200211091010120000100075200007168730036120000103004030040300403004030041
120024300402250140671825120045101200351012000050960000003002030039300391499631501912001020120000203600003003930039111200211091010120000100075200009167530036120000103004030040300403004030040
120024300392250040025120011101200001012000050990000003002030040300391499631501912001020120000203600003003930040111200211091010120000100075200005167530036120000103004030043300403175130040
120024300392250061025120010101200351012000050960000003002030039300391499631501912001020120000203600003003930039111200211091010120000100075200005167730037120000103004031751300403099830040
120024300392370041025120010101200001012000050960000003002130040300391499631501912001020120000203600003003930040111200211091010120000100075200307165730036120000103004130040300403004030040
120024300392250040025120011101200011012000050960000003002030039300391499631501912001020120000203600003003930039111200211091010120000100075200005165430036120000103004130040300403004030040