Apple M1 Microarchitecture Research by Dougall Johnson

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

SABA (vector, 16B)

Test 1: uops

Code:

  saba v0.16b, v1.16b, v2.16b
  movi v0.16b, 1
  movi v1.16b, 2
  movi v2.16b, 3

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 1.000

Issues: 1.000

Integer unit issues: 0.000

Load/store unit issues: 0.000

SIMD/FP unit issues: 1.000

retire (01)cycle (02)031e3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op fp/simd (7e)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst neon or fp (9a)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372306125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831303018303730372415328951000100030003037303711100110000373116112630100030383038303830383038
100430372306125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372206125482510001000100039831313018303730372415328951000100030003037303711100110000373116112630100030383038303830383038
100430372206125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
1004303722325125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372206125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372206125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  saba v0.16b, v1.16b, v2.16b
  movi v0.16b, 1
  movi v1.16b, 2
  movi v2.16b, 3

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)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)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)9fa8accfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225906129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000071002162329634100001003003830038300383003830038
1020430037225606129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000071002162229634100001003003830038300853003830038
10204300372252106129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000071002162229634100001003003830038300383003830038
1020430037225606129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000071002162229634100001003003830038300383003830038
10204300372254206129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000071003162229634100001003003830038300383003830038
1020430037225606129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000071012162229634100001003003830038300383003830038
1020430037225306129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000071012162229634100001003003830038300383003830038
1020430037225616129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000071012162329634100001003003830038300383003830038
1020430037225606129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000071212162229634100001003003830038300383003830038
1020430037225606129537251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000071012162229634100001003003830038300383003830038

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)9fa8acc5cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225216129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640316222963010000103003830038300383003830038
100243003722566129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640316332963010000103003830038300383003830038
100243003722566129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216332963010000103003830038300383003830038
100243003722566129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
1002430037225126129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640316422963010000103003830038300383003830038
1002430037225336129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640416332963010000103003830038300383003830038
1002430037225186129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640316332963010000103003830038300383003830038
100243003722566129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722566129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640316332963010000103003830038300383003830038
100243003722566129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640316322963010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  saba v0.16b, v0.16b, v1.16b
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b18191e1f3f4e51inst 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)9fa8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000007262954825101001001000010010000500427731313001830037300372827272874010100200100082003002430037300371110201100991001001000010000011171701600296470100001003003830038300383003830134
1020430037225011021019661295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000242000710116112963428100001003003830038300383003830038
102043003722500009061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000117000071011611296340100001003003830038300383003830038
1020430037225000000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
10204300372250000120612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
1020430037225101124104822954825101001001000010010000500427731313001830085301292826582874510100202100002003000030037300841110201100991001001000010000000071011611296340100001003003830038300383003830087
1020430037225000000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010010000071011611296340100001003003830038300383003830038
1020430037225000000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010010000071011611296340100001003003830038300383003830038
10204300372250100300103295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000138000071011611296340100001003003830038300383003830038
102043003722400000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000132000071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0318191e3f4e51inst 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)9fa0a6a7a8acc5cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000162006402162229630010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000135006402162229630010000103003830038300383003830038
1002430037224100612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000090006402162229630010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000108006402162229630010000103003830038300383003830038
10024300372250021612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000099006402162229630010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000111006402162229630010000103003830038300383003830038
100243003722400025529548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000111006402162229630010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000102006402162229630010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000117006402162229630010000103003830038300383003830038
100243003722500061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000006402162229630010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  saba v0.16b, v1.16b, v0.16b
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03183f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722401562954825101001001000010010000500427731303001830037300372826532874510100200101802003000030037300371110201100991001001000010009971011611296340100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100013571011611296340100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100011471011611296340100001003003830038300383003830038
102043003722516129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100012671011611296340100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100013871011611296340100001003003830038300383003830038
1020430037225015629548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100012671011611296340100001003003830038300383003830038
1020430037224025129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100012071011611296340100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300853003711102011009910010010000100012671011611296340100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010006371011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03181e1f3f4e51inst 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)9fa1a8c5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225000168295482510010101000010100005042773133001830037300372828732876710158201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225000103295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010001640216222963010000103003830038300383003830038
1002430037225000124295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250001101295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225000124295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225000103295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037224000145295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225000103295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250001076295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  saba v0.16b, v8.16b, v9.16b
  movi v1.16b, 0
  saba v1.16b, v8.16b, v9.16b
  movi v2.16b, 0
  saba v2.16b, v8.16b, v9.16b
  movi v3.16b, 0
  saba v3.16b, v8.16b, v9.16b
  movi v4.16b, 0
  saba v4.16b, v8.16b, v9.16b
  movi v5.16b, 0
  saba v5.16b, v8.16b, v9.16b
  movi v6.16b, 0
  saba v6.16b, v8.16b, v9.16b
  movi v7.16b, 0
  saba v7.16b, v8.16b, v9.16b
  movi v8.16b, 9
  movi v9.16b, 10

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)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)6061696d6escheduler 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)9fa8accfd0d2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160204200891500711258010010080000100800005006400001520045200642006432280100200800002002400002006420064111602011009910010016000010000101115111611200611600001002006520065200652006520065
160204200641500180258010010080000100800005006400001520045200642006432280100200800002002400002006420064111602011009910010016000010000101110011611200611600001002006520065200652006520065
16020420064150039258010010080000106801055006400001020045200642006432280100200800002002400002006420064111602011009910010016000010000101110011611200611600001002006520065200652006520065
160204200641500476258010010080000100800005006400001520045200642006432280100200800002002400002006420064111602011009910010016000010000101115111611200611600001002006520065200652006520065
160204200641500123258010010080000100800005006400001520045200642006432280100200800002002400002006420064111602011009910010016000010010101115011611200611600001002006520065200652006520065
1602042006415101936258010010080000100800005006400001520045200642006432280100200800002002400002006420064111602011009910010016000010000101115111611200611600001002006520065200652006520065
160204200641500229258010010080000100800005006400001520045200642006432280100200800002002400002006420064111602011009910010016000010000101115111611200611600001002006520065200652006520065
160204200641500326258010010080000100800005006400001520045200642006432280100200800002002400002006420064111602011009910010016000010023101115011611200611600001002006520065200652006520065
160204200641506123258010010080000100800005006400001520045200642006432280100200800002002400002006420064111602011009910010016000010000101115111611200611600001002006520065200652006520065
16020420064150039258010010080000100800005006400001520045200642006432280100200800002002400002006420064111602011009910010016000010000101115111611200611600001002006520065200652006520065

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0304191e1f3f51inst 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)9fa8acc5cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16002420070150100015229800121280000128000062640000112003220051200510322800122080000202400002005120051111600211091010160000100001003231112252111012200482201160000102005220052200522005220052
1600242005115000001332780012128000012800006264000011200322005120051032280012208000020240000200512005111160021109101016000010100100353111225211910200482201160000102005220052200522005220052
16002420051150000013327800121280000128000062640000112003220051200510322800122080000202400002005120051111600211091010160000100001003631112253111313200482201160000102005220052200522005220052
16002420051150000015027800121280000128012862640000012003220051200510322800122080000202400002005120051111600211091010160000100001003531110252121311200572201160000102005220052200522006120052
16002420051150000071129800121280000128000062640000112003220051200510322800122080000202400002006220051111600211091010160000100001003532111252111213200482201160000102005220052200522006120052
16002420060150000011229800121280000128000062640000112003220051200510322800122080000202400002005120051111600211091010160000100001003631111254111212200592201160000102005220061200522005220052
16002420051150000017727800121280000128000062640000112003220051200510322800122080000202400002005120051111600211091010160000100001003661110252111113200482201160000102005220052200522006320052
160024200621500000452980012128000012800006264000001200432005120060032280012208000020240000200512005111160021109101016000010000100343211025411109200572201160000102005220063200522005220052
1600242005115000008729800121280000128000062640000112004120060200510322800122080000202400002005120060111600211091010160000100001003632111252111313200572201160000102005220052200522005220061
16002420051151000015827800121280000128000062640000012003220051200510322800122080000202400002005120051111600211091010160000100001003731110252111112200482411160000102005220063200522006120063

Test 6: throughput

Count: 16

Code:

  saba v0.16b, v16.16b, v17.16b
  saba v1.16b, v16.16b, v17.16b
  saba v2.16b, v16.16b, v17.16b
  saba v3.16b, v16.16b, v17.16b
  saba v4.16b, v16.16b, v17.16b
  saba v5.16b, v16.16b, v17.16b
  saba v6.16b, v16.16b, v17.16b
  saba v7.16b, v16.16b, v17.16b
  saba v8.16b, v16.16b, v17.16b
  saba v9.16b, v16.16b, v17.16b
  saba v10.16b, v16.16b, v17.16b
  saba v11.16b, v16.16b, v17.16b
  saba v12.16b, v16.16b, v17.16b
  saba v13.16b, v16.16b, v17.16b
  saba v14.16b, v16.16b, v17.16b
  saba v15.16b, v16.16b, v17.16b
  movi v16.16b, 17
  movi v17.16b, 18

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)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)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)9fa8accfd5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16020440049300541721525160100100160000100160000500128000040020400394003919973319997160100200160000200480000400394003911160201100991001001600001000010110116114003601600001004004040040400404004040040
160204400393000174125160100100160000100160000500128000040020400394003919973319997160100200160000200480000400394003911160201100991001001600001000010110116114003601600001004004040049400404004940040
160204400393000177325160100100160000100160000500128000040020400394003919973320006160100200160000200480000400394003911160201100991001001600001000010110116114003601600001004004040040400404004040040
160204400393000175025160100100160000100160000500128000040020400394003919973319997160100200160000200480000400394003911160201100991001001600001004010110116114003601600001004004040049400404004040040
160204400483000176225160100100160000100160000500128000040020400394003919973319997160100200160000200480000400394003911160201100991001001600001000010110116114003601600001004004040040400404004040049
160204400393000174125160100100160000100160000500128000040020400394003919973319997160100200160000200480000400394003911160201100991001001600001001010110116114003601600001004004040040400404004940040
16020440039300004125160100100160000100160000500239899940020400394003919973319997160100200160000200480000400484003911160201100991001001600001000010110116114003601600001004004040040400404004040049
16020440039299014225160100100160000100160000500128000040020400484003919973319997160100200160000200480000400394003911160201100991001001600001000010110116114003601600001004004040040400404004040040
16020440039300004125160100100160000100160000500239905540020400394003919973319997160100200160000200480000400394003911160201100991001001600001000010110116114004601600001004004040049400404004940040
1602044003930001758225160100100160000100160000500128000040020400484003919973319997160100200160000200480000400394003911160201100991001001600001000010110116114003601600001004004940040400404004040040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03041e373f51inst 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)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16002440049299002071825160010101600001016000050239899911040020400394004819996320028160010201600002048000040039400391116002110910101600001000100228113516221141440036206160000104004940040400494004040049
1600244004830000175550160027101600171016000050128000011540029400394004819996320028160010201600002048000040048400481116002110910101600001000100228411416211141440045206160000104004040049400404004940040
1600244004830000174625160027101600001016000050239899911540020400394004819996320028160010201600002048000040048400391116002110910101600001000100228411216211141140036206160000104004040049400494004940040
16002440048299001746251600271016001710160000501280000115400294003940048199963200191600102016000020480000400484004811160021109101016000010001002284120162111412400454018160000104004940049400404004940040
1600244003930000175525160027101600171016000050239899911540029400484003919996320019160010201600002048000040039400481116002110910101600001000100228121916421121840045209160000104004940049400404004940040
160024400483000017193251600271116012710160000502398999115400204003940048199963200281600102016000020480000400484004811160021109101016000010001002411521316412131340036409160000104004940049400404004940049
160024400393000011612516002710160017101600005012800000154002940048400391999632001916001020160000204800004003940048111600211091010160000101010024115213164221113400454018160000104004040049400404004940040
16002440048300002462516001010160000101600005023989991154002040039400481999632005016001020160000204800004003940048111600211091010160000100010024115214164221113400456012160000104004040049400404004940040
1600244004830000171702516001010160000101600005023989990154002940039400481999632001916001020160000204800004004840039111600211091010160000100010024115211164221311400364018160000104004040049400404004940049
160024400393000017522516001010160017101600005012800000154002940039400481999632002816001020160000204800004003940048111600211091010160000100010046116214164221713400456018160000104004940040400494004040049