Apple M1 Microarchitecture Research by Dougall Johnson

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

SABAL (vector, 4S)

Test 1: uops

Code:

  sabal v0.4s, v1.4h, v2.4h
  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)03181e3f4e51inst 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
1004303723006125482510001000100039831313018303730372415328951000100030003037303711100110002373216222630100030383038303830383038
1004303723006125482510001000100039831303018303730372415328951000100030003037303711100110000073216222630100030383038303830383038
1004303723006125482510001000100039831313018303730372415328951000100030003037303711100110000073216222630100030383038303830383038
1004303722006125482510001000100039831313018303730372415328951000100030003037303711100110000073216222630100030383038303830383038
1004303723006125482510001000100039831313018303730372415328951000100030003037303711100110004073216222630100030383038303830383038
100430372201056125482510001000100039831313018303730372415328951000100030003037303711100110000073216222630100030383038303830383038
1004303723006125482510001000100039831313018303730372415328951000100030003037303711100110000073216222630100030383038303830383038
1004303722006125482510001000100039831313018303730372415328951000100030003037303711100110000073216222630100030383038303830383038
1004303722006125482510001000100039831313018303730372415328951000100030003037303711100110000073216222630100030383038303830383038
1004303723006125482510001000100039831313018303730372415328951000100030003037303711100110000073216222630100030383038303830383038

Test 2: Latency 1->1

Code:

  sabal v0.4s, v1.4h, v2.4h
  movi v0.16b, 1
  movi v1.16b, 2
  movi v2.16b, 3

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b1e3a3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)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)9fa0a1a6a8a9accfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225001890612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071012162229634100001003022930038300383003830038
10204300372250000612954825101001001000010010000500427731313001830037300372826932874510100200100002003000030037300371110201100991001001000010000000071012162229634100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313130018300373003728265192874510100200100002003000030037300371110201100991001001000010000000071012162229634100001003003830038300383003830038
1020430037224000027662954825101001001000010010000500427731313001830085300372826532874510100200100002003000030037300371110201100991001001000010002000071012162229634100001003003830038300383003830038
1020430037225000027542954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071212163229634100001003003830038300383003830038
10204302282250000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000001071012162229634100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071012162229634100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731313001830084300852826532874510100200100002003000030037300371110201100991001001000010000000071012162229634100001003003830038300383003830038
102043003722500001032954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071012162229634100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037302291110201100991001001000010000010071012162529634100001003003830038300383003830038

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)9fa8acc2c5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250612954825100101010000101000050427731303001803003730037282873287671001020100002030000300373003711100211091010100001000006402162229630010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001803003730037282873287671001020100002030000300373003711100211091010100001000006402162229630010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001803003730037282873287671001020100002030000300373003711100211091010100001000006402162229630010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001803003730037282873287671001020100002030000300373003711100211091010100001000006402162229630010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001803003730037282873287671001020100002030000300373003711100211091010100001030006402162229630010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001803003730037282873287671001020100002030000300373003711100211091010100001000006402162229630010000103003830038300383003830038
10024300372250612954825100101010000101000050427731313001803003730037282873287671001020100002030000300373003711100211091010100001000006402162329630010000103003830038300383003830038
10024300372250612954825100101010000101000050427731313001833003730037282873287671001020100002030000300373003711100211091010100001000006402162229630010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001803003730037282873287671001020100002030000300373003711100211091010100001010006402162229630010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001803003730037282873287671001020100002030000300373003711100211091010100001000006402162229630010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  sabal v0.4s, v0.4h, v1.4h
  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)03080b18191e3f4e5051inst 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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000061295480251010010010000100100005004277313130018300373003728265032874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
10204300372250000061295482251010010010000100100005004277313030018300373003728265032874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
10204300372250000061295480251010010010000100100005004277313030018300373003728265032874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
10204300372250000061295480251010010010000100100005004277313030018300373003728265032874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
10204300372260000061295480251010010010000100100005004277313030018300373003728265032874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
10204300372250000061295480251010010010000100100005004277313030018300373003728265032874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
102043003722500001261295480251010010010000100100005004277313030018300373003728265032874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
10204300372250000061295480251010010010000100100005004277313030018300373003728265032874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
10204300372250000061295480251010010010000100100005004277313030065300373003728265032874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
10204300372250000061295480251010010010000100100005004277313030018300373003728265032874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038

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)9fc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722506129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100640216222963010000103003830038300383003830038
100243003722406129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100640216222963010000103003830038300383003830038
1002430037225366129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100640216222963010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  sabal v0.4s, v1.4h, v0.4h
  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)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)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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250612954825101001001000010010000659427731303001803003730037282650328745101002001000020030000300373003711102011009910010010000100337101161129634100001003003830038300383003830038
10204300372323612954825101001001000010010000500427731303001803003730037282650328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731303001803003730037282650328745101002001000020030000300373003711102011009910010010000100107101161129634100001003003830038300383003830038
10204300372250612953025101001001000010010000500427731303001803003730037282650328745101002001000020030000300373003711102011009910010010000100207101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731303001803003730037282650328745101002001000020030000300373003711102011009910010010000100907101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731303009003003730037282650328745101002001000020030000300373003711102011009910010010000100707101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313030018030037300372826503287451010020010000200300003003730037111020110099100100100001006007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005164277313030018030037300372826503287451010020010000200300003003730037111020110099100100100001001207101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313030065030037300372826503287451010020010000200300003003730037111020110099100100100001001107101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731303001803003730037282650328745101002001000020030000300373003711102011009910010010000100607101161129634100001003003830038300383003830038

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)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)9fa0a1a8acc2c5branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010002515000640216222963010000103003830038300383003830038
100243003722506129548251001010100001410000504277313300183003730037282873287671001020100002030000300373003711100211091010100001004246000640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000279000640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000415000640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000286000640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000280000640216222963010000103003830038300383003830038
100243003722506129548251001010100001010596504277313300183003730037282873287671001020100002030000300373003711100211091010100001000263000640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100026000640216222963010000103003830038300383003830038
100243003722406129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000296000640216222963010000103003830038300383003830038
100243003722504412954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100029000640216222963010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  sabal v0.4s, v8.4h, v9.4h
  movi v1.16b, 0
  sabal v1.4s, v8.4h, v9.4h
  movi v2.16b, 0
  sabal v2.4s, v8.4h, v9.4h
  movi v3.16b, 0
  sabal v3.4s, v8.4h, v9.4h
  movi v4.16b, 0
  sabal v4.4s, v8.4h, v9.4h
  movi v5.16b, 0
  sabal v5.4s, v8.4h, v9.4h
  movi v6.16b, 0
  sabal v6.4s, v8.4h, v9.4h
  movi v7.16b, 0
  sabal v7.4s, v8.4h, v9.4h
  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)61696d6escheduler 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)9fa8acc5branch mispredict (cb)cdcfd0d2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16020420089150029258011610080016100800285006401960200452006520065612801282008002820024008420065200651116020110099100100160000100330111101190021600200621600001002006620066200662006620066
1602042006515102925801161008001610080028500640196020045200652006561280128200800282002400842006520065111602011009910010016000010000111101200001610200621600001002006520065200652006520065
160204200641500392580100100800001008000050064000002004520064200643228010020080000200240000200642006411160201100991001001600001000102000101110031621200611600001002006520065200652006520065
1602042006415003925801001008000010080000500640000020045200642006432280100200800002002400002006420064111602011009910010016000010010000101120021621200611600001002006520065200652006520065
1602042006415003925801001008000010080000500640000020045200642006432280100200800002002400002006420064111602011009910010016000010000000101110011611200611600001002006520065200652006520065
1602042006415063925801001008000010080000500640000020045200642006432280100200800002002400002006420064111602011009910010016000010000000101120011621200611600001002006520065200652006520065
16020420064150039258010010080000100800005006400000200452006420064322801002008000020024000020064200871116020110099100100160000100330000101110011612200611600001002006520065200652006520065
1602042006415003925801001008000010080000500640000020306200642006432280100200800002002400002006420064111602011009910010016000010000000101120111612200611600001002006520065200652006520065
16020420064150039258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100293000101120011612200611600001002006520065200652006520065
1602042006415003925801001008000010080000500640000020045200642006432280100200800002002400002006420064111602011009910010016000010000000101110011612200611600001002006520065200652006520065

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03071e3f51inst 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)9fa8accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaebec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160024200851500045278001212800001280000626400001102003220051200513228001220800002024000020051200511116002110910101600001010100323119252111282004822001160000102005220212200912005220052
16002420051150004527800121280000128000062640000110200322005120051322800122080000202400002005120051111600211091010160000100010034311112521111112004822001160000102005220207200872005220061
16002420051150004527800121280000128000062640000100200322005120051322800122080000202400002005120051111600211091010160000100010031311925411972004822001160000102005220201200872005220052
1600242005115000452780012128000012800006264000010020032200512005132280012208000020240000200512005111160021109101016000010001003411218252137142004822001160000102005220188200742005220052
16002420051150004527800121280000128000062640000110200322005120060322800122080000202400002005120131111600211091010160000101610032811825221992004822001160000102005220203200872005220052
160024200511500045278001212800001280000626400001052003220051200513228001220800002024000020051200511116002110910101600001000100358211225211992004822001160000102005220171200872005220052
1600242005115000452780012128000012800006264000011520032200512005132280012208000020240000200512005111160021109101016000010001003182112252117920048220298160000102005220052200522005220052
1600242005115000452780012128000012800006264000011520032200512005132280012208000020240000200512005111160021109101016000010066100348211125211111120048220298160000102005220052200522005220052
160024200511500045298001212800001280000626400001152003220051200513228001220800002024000020051200511116002110910101600001020100348211125211111120048220278160000102005220052200522005220052
16002420051150004527800121280000128000062640000115200322005120051322800122080000202400002005120051111600211091010160000100010034821725211101120048220338160000102005220052200522005220052

Test 6: throughput

Count: 16

Code:

  sabal v0.4s, v16.4h, v17.4h
  sabal v1.4s, v16.4h, v17.4h
  sabal v2.4s, v16.4h, v17.4h
  sabal v3.4s, v16.4h, v17.4h
  sabal v4.4s, v16.4h, v17.4h
  sabal v5.4s, v16.4h, v17.4h
  sabal v6.4s, v16.4h, v17.4h
  sabal v7.4s, v16.4h, v17.4h
  sabal v8.4s, v16.4h, v17.4h
  sabal v9.4s, v16.4h, v17.4h
  sabal v10.4s, v16.4h, v17.4h
  sabal v11.4s, v16.4h, v17.4h
  sabal v12.4s, v16.4h, v17.4h
  sabal v13.4s, v16.4h, v17.4h
  sabal v14.4s, v16.4h, v17.4h
  sabal v15.4s, v16.4h, v17.4h
  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)031e373f51inst 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)9fa0a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602044005930001741251601001001600001001600005001280000140020400484003919973320006160100200160000200480312401304004811160201100991001001600001000001011031622400361600001004004040040400494004040040
1602044003930000113251601001001600001001600005002398999140020400394003919973320006160100200160000200480000400484003911160201100991001001600001001001011021622400361600001004004040040400494004940040
160204400393000041251601171001600001001600005001280000140029400394003919973319997160100200160000200480000400394003911160201100991001001600001000001011021622400361600001004004040040400404004040040
160204400393000041251601171001600171001600005001280000140030400394003919973319997160100200160000200480000400394003911160201100991001001600001000001011021622400371600001004004940040400404004040052
1602044004830001772251601001001600171001600005002398999140020400394003919973319997160100200160000200480000400394003911160201100991001001600001000001011021622400361600001004004040040400404004140049
1602044003929900727251601001001600171001600005001280000140029400484004819973320006160100200160000200480000400394004911160201100991001001600001000031011021622400361600001004004040040400404004940049
1602044003930000622516010010016001710016000050012800000400204003940039199732619997160100200160000200480000400394003911160201100991001001600001000001011021622400451600001004004040049400404004040040
1602044003929901741251601001001600001001600005002398999040029400394003919973320006160100200160000200480000400484003911160201100991001001600001000001011021622400361600001004004040040400414004940040
160204400483000041251602291001600001061600005002398999040029400394003919973319997160100200160000200480000400394003911160201100991001001600001000001011021622400451600001004004940040400404004040040
160204400483000051251601171001600001001600005001280000040020400484003919973319997160100200160000200480000400484003911160201100991001001600001000001011021622400451600001004004040040400494004040049

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03070a1e373a3f51inst 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)9fa8accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160024400752990001701532516002710160017101600005012800000154002940039400481999632002816001020160000204800004004840039111600211091010160000100010022831291621126254004504118160000104004040049400494004940040
16002440039300100170141425160027101600171016000050239899901540030400404003919996320019160010201600002048000040039400401116002110910101600001000100241142291632214274004504118160000104004940040400494004940040
16002440039300000009625160010101600001016000050239899901540029400394004819996320019160010201600002048000040048400481116002110910101600001000100241142261632215274004506118160000104004940049400404004940049
160024400392991101708425160010101600001016000050239899911540029400484003919996320028160010201600002048000040039400481116002110910101600001000100261142281632222284004504118160000104004040049400404004940049
160024400482991100012032516002710160000101600005012800000154002940039400481999632002816001020160000204800004004840048111600211091010160000103310026831241632225254003624113160000104010140049400404004940134
1600244003930010017166925160010101600001016000050128000001540029401344004819996320028160010201600002048038440292400481116002110910101600001000100261142261632221254003604118160000104004940049400404004940049
160024400493001112170150825160027101600171016000050128000001540029400484003919996320028160010201600002048000040048400481116002110910101600001000100261142231632227134004506127160000104004940040400494004040040
16002440048300100171126525160010101600001016000050239899901540029400394004819996320019160010201600002048000040048400481116002110910101600001003100241142131632233154009224113160000104004040049400404004940040
16002440048300000170118825160010101600001016000050239899901540029400484004819996320019160010201600002048000040039400481116002110910101600001000100261152291632227254003604118160000104004940040400494004040049
16002440048300110170125225160027101600001016000050239899901540020400394004819996320028160010201600002048000040039400481116002110910101600001003100261152291632227314003604118160000104004940040400494004940040