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, 4H)

Test 1: uops

Code:

  mls 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)030b1e3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)696d6edispatch 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)a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372300251254825100010001000398313301830373037241532895100010003000303730371110011000001873116112630100030383038303830383038
1004303723006125482510001000100039831330183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
1004303723006125482510001000100039831330183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
100430372301086125482510001000100039831330183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
100430372302558225482510001000100039831330183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
1004303723006125482510001000100039831330183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
10043037230015625482510001000100039831330183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
1004303723006125482510001000100039831330183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
1004303722006125482510001000100039831330183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
10043037230126125482510001000100039831330183037303724153289510001000300030373037111001100000073116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  mls 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)03191e3a3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)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)9fa0a8acc2c5branch mispredict (cb)cdcfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000107295482510100100100001001000050042773131300180300373003728272628741101002021000820030024300373003711102011009910010010000100000011171700161029646100001003003830038300383003830038
1020430037225001316295482510100100100001001000050042773130300180300373008428272728740101002001000820030024300373003711102011009910010010000100000011171700160029647100001003003830038300383003830038
1020430037225001258295482510100100100001001000050042773130300180300373003728272728740101002001000820030024300373003711102011009910010010000100000000071012162229634100001003003830038300383003830038
1020430037224000404295482510100100100001001000050042773130300180300373003728265328745101002001000020030000300373003711102011009910010010000100000000071012162229634100001003003830038300383003830038
1020430037224001191295482510100100100001001000050042773130300180300373003728265328745101002001000020030000300373003711102011009910010010000100060000071212162229634100001003003830038300383003830086
1020430037225000535295482510100100100001001000050042773130300180300373003728265328745101002001000020030000300373003711102011009910010010000100000000071012162229634100001003003830038300383003830038
102043003722500184295482510100100100001001000050042773130300183300373003728265328745101002001000020030000300373003711102011009910010010000100000000071012162229634100001003003830038300383003830038
1020430037225000103295482510100100100001001000050042773130300180300373003728265328745101002001000020030000300373003711102011009910010010000100000000071012162229634100001003003830038300383003830038
10204300372250121296295482510100100100001001000050042773130300180300373003728265328745101002001000020030000300373003711102011009910010010000100000000071012162229634100001003003830038300383003830038
1020430037225001454295482510100100100001001000050042773130300180300373003728265328745102522021000020030000300373003711102011009910010010000100205571200071012162229634100001003003830038300383003830038

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)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)9fa0a1a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000000012429548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000006403162229630010000103003830179300853003830038
1002430037225000000018729548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000006692162229630010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000006402163229630010000103003830038300383003830038
1002430037225000000025229548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
1002430037225000000015629548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
1002430037225000000072629548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
100243003722500000008429548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000006402162229630010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  mls 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)030b18191e1f3f4e51inst 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)9fa0a1a6a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500000187295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
102043003722400000256295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000071011611296340100001003003830180300853013330038
10204300372250000061295482510100100100001001014850042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
102043003722511015610461295392510100100100001001000050042773131300183003730037282653287451010020010000200300003008430037311020110099100100100001000000002071011611296340100001003003830038300383003830038
10204300372240003122081528295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000071011611296340100001003003830038300863003830038
102043003722500000559295482510100100100001001000050042773131300183003730037282653287621010020010000200300003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
10204300372250000061295302510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001002001090071022512296342100001003013330179300863003830038

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)696d6edispatch 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
1002430037225000298295482510010101000010100005042773133001830037300372828703287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722400061295482510010101000010100005042773133001830037300372828703287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773133001830037300372828703287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225019810861295482510010101000710100005042773133001830037300372828703287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773133001830037300372828703287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773133001830037300372828703287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773133001830037300372828703287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773133001830037300372828703287671001020100002030000300373003711100211091010100001000640316232963010000103003830038300383003830038
1002430037225000187295482510010101000010100005042773133001830037300372828703287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773133001830037300372828703287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  mls 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)0308090b18191e1f3a3f4e51inst 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)696b6d6edispatch 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)9fa0a1a6a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000000001372954825101001001000010010000500427731330018030037300372826503287451010020010000200300003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
102043003722500000000612954825101001001000010010000500427731330018030037300372826503287451010020010000200300003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
102043003722500000000612954825101001001000010010000500427731330018030037300372826503287451010020010000200300003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
102043003722500000000612954825101001001000010010000500427731330018030037300372826503287451010020010000200300003003730037111020110099100100100001000000000071011611296340100001003018130086300383003830038
102043003722500000000612954825101001001000010010000500427731330018030037300372826503287451010020010000200300003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
102043003722500000000612954825101001001000010010000500427731330018030037300372826503287451010020010000200300003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
102043003722500000000612954825101001001000010010000500427731330018030037300372826507287451010020010000200300003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
102043003722500000000612954825101001001000010010000500427731330018030037300372826503287451010020010000200300003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
1020430037225000000002512954825101001001000010010000500427731330018330037300372826503287451010020010000200300003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
102043003722500000000612954825101001001000010010000500427731330018030037300372826503287451010020010000200300003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b1e3f4e51inst 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)9fa0a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722400023229548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000640316222963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216222970210000103003830038300383003830038
10024300372250006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103008530038300383003830038
10024300372250006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313130018300373003728287328767101592010000223000030037300371110021109101010000100000640216322963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
10024300372240006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
10024300372240006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640224222963010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  mls v0.4h, v8.4h, v9.h[1]
  movi v1.16b, 0
  mls v1.4h, v8.4h, v9.h[1]
  movi v2.16b, 0
  mls v2.4h, v8.4h, v9.h[1]
  movi v3.16b, 0
  mls v3.4h, v8.4h, v9.h[1]
  movi v4.16b, 0
  mls v4.4h, v8.4h, v9.h[1]
  movi v5.16b, 0
  mls v5.4h, v8.4h, v9.h[1]
  movi v6.16b, 0
  mls v6.4h, v8.4h, v9.h[1]
  movi v7.16b, 0
  mls 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)031e1f3f51inst 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
1602042008915000123258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100001011221632200611600001002006520065200652006520065
160204200641500081258019610080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100001011211611200611600001002006520065200652006520065
160204200641500039258010010080000100800005006400000200452006420064322801002008000020024000020064200741116020110099100100160000100001011121631200611600001002006520065200652006520065
160204200641500039258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100001011231611200611600001002006520065200652006520065
160204200641500039258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100001011111622200611600001002006520065200652006520065
160204200641500039258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
160204200641500039258010010080000100800005006400001200452006420064322801002008000020024000020064200761116020110099100100160000100001011311632200611600001002006520065200652006520065
160204200641510039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100001011111621200611600001002006520065200652006520065
160204200641500081258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100001011211621200611600001002006520065200652006520065
160204200641500039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100001011311622200611600001002006520065200652006520065

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0318191e3f51inst 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)9fa1a7a8accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16002420087151003045278001212800001280000626400001102003220051202633228001220800002024000020051200511116002110910101600001000001003084132521134200482201160000102005220052200612005220052
16002420051150000452780012128000012800006264000011520032200512027432280012208000020240000200512005111160021109101016000010000010028115142521154200572201160000102005220052200522005220061
160024200511500014145278001212800001280000626400001002003220051202483228001220800002024000020051200511116002110910101600001000001002731122521135200482201160000102005220052200522005220052
16002420051150000452780012128000012800006264000011520032200512021232280012208000020240000200512005111160021109101016000010000010029116132542144200572202160000102005220061200612006120061
16002420060150000562980012128000012800006264000000520032200602021032280012208000020240000200512005111160021109101016000010000010030112233422253200572401160000102005220061200612006120061
16002420051150000512980012128000012800006264000000520032200602023532280012208000020240000200602005111160021109101016000010000010031115253442255200572401160000102006120061200612006120061
1600242006015000051298001212800001280000626400000152004120060202033228001220800002024000020060200601116002110910101600001000001003085152521155200482201160000102006120061200612005220144
160024200511510024452780012128000012800006264000001520041200602020932280012208000020240000200602006011160021109101016000010000010031116243442233200572402160000102006120061200612006120061
16002420060150000452980012128000012800006264000001520032200602018532280012208000020240000200602006011160021109101016000010000010030115243442244200572402160000102006120052200612006120061
16002420051150009512980012128000012800006264000011520041200512019032280012208000020240000200602006011160021109101016000010000010030116253442255200482402160000102006120061200612006120061

Test 6: throughput

Count: 12

Code:

  mls v0.4h, v12.4h, v13.h[1]
  mls v1.4h, v12.4h, v13.h[1]
  mls v2.4h, v12.4h, v13.h[1]
  mls v3.4h, v12.4h, v13.h[1]
  mls v4.4h, v12.4h, v13.h[1]
  mls v5.4h, v12.4h, v13.h[1]
  mls v6.4h, v12.4h, v13.h[1]
  mls v7.4h, v12.4h, v13.h[1]
  mls v8.4h, v12.4h, v13.h[1]
  mls v9.4h, v12.4h, v13.h[1]
  mls v10.4h, v12.4h, v13.h[1]
  mls 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)0308191e1f373f4e51inst 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)9fa0a1a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
12020430060225000005206704251201001001200171001200005009600001300203003930039149733159011201002001200002003600003092230039111202011009910010012000010000007610116113003601200001003004030040300433004030043
1202043003922500000410251201001001200001001200005009600001300203003930039149733150001201002001200002003600003004230039111202011009910010012000010000007610116113094001200001003004030040300403004030040
1202043003922400001410251201001001200001001200005009600001300233019930039149733149971201002001200002003600003003930039111202011009910010012000010000007610238113003701200001003004030043300403004330040
120204300392240000111443489251201001001200011001200005009600001300203094330039158503149971201002001200002003600003092230039111202011009910010012000010000007610116113003901200001003004030040300403004030040
1202043003922500601410251201001001200011001200005009900001300203003930039149733149971201002001200002003600003003930039111202011009910010012000010000007610116113003601200001003004030043300403004030040
1202043003922500600410251201011001200011001200005009600001300203003930039149733149971201002001200002003600003094330039111202011009910010012000010000007610116113003601200001003004030040300403004330040
1202043004222500000410251201011001200001001200005009600001300203094330039149733149971201002001200002003600003003930039111202011009910010012000010000007610116113094001200001003004030040300403004330040
1202043003922500000412900251201001001200171001200005009900001300203014631750149733149971201002001200002003600003003930039111202011009910010012000010000037610116113003691200001003004030043300403004030043
1202043003923100000620251201001001200001001200005009600001309033003930943149733150001201002001200002003600003003930039111202011009910010012000010000007610116113003601200001003004030040300433004030040
1202043003922400600410251201011001200011001200005009600001300203003930039149733159011201002001200002003600003003930039111202011009910010012000010000007610116113094001200001003004030944300403004030944

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030a1e373f4e51inst 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)9fa8acbranch mispredict (cb)cdcfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
12002430050225200460251200101012000010120000509600006153002030039300391499631501912001020120000203600003003930039111200211091010120000100000752411314272113330036206120000103004030040300403004030040
12002430039225000460251200101012000010120000509600005153002030039300391499631501912001020120000203600003003930039111200211091010120000100000752282121621133300364013120000103175130040300403004030040
1200243003922500046025120010101200001012000050960000515300203003930039149963150191200102012000020360000300393003911120021109101012000010000075228213162113230036206120000103004030040300403004030040
1200243003922400046025120010101200001012000050960000715300203003930039149963150191200102012000020360000300393003911120021109101012000010000075228212162112430036206120000103004030040309233175130040
12002430039225000732025120010101200001012000050960000715300203003930039149963150191200102012000020360000300393003911120021109101012000010030075248212162113430037206120000103004030040300403092330040
12002430039225000460251200101012001810120000504394061515309033003930039149963150191200102012000020360000300393003911120021109101012000010000075248213162113230036206120000103004030040300423004130040
1200243003922400146025120010101200011012000050990000715300203003930039149963150191200102012000020360000300393003911120021109101012000010000075228243164223230036206120000103004030040300403004030040
1200243092222500046025120010101200001012000050960000615300203003930039149963150201200102012000020360000300393003911120021109101012000010000075228213162113230036206120000103004030040300403004030040
120024300392250909220251200101012000010120000504283915615306763003930039149963150191200102012000020360000300393003911120021109101012000010000075228213162113330036206120000103004030040300403004030040
1200243003922500046025120010101200001012000050960000715300203003930039149963150191200102012000020360000300393003911120021109101012000010000075228213162113330036206120000103004030040300403004030040