Apple M1 Microarchitecture Research by Dougall Johnson

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

SMLAL (by element, 2D)

Test 1: uops

Code:

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

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 1.000

Issues: 1.000

Integer unit issues: 0.000

Load/store unit issues: 0.000

SIMD/FP unit issues: 1.000

retire (01)cycle (02)031e3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op fp/simd (7e)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst neon or fp (9a)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303723156125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372308225482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
1004303722246125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372308225482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
1004303723126125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831303018303730372415828951000100030003037303711100110000073116112630100030383038303830383038

Test 2: Latency 1->1

Code:

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

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)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)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)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000612954825101001001000010010000500427731330018300373003728272628741101002001000820030024300373003711102011009910010010000100000001117170160029646100001003003830038300383003830038
1020430037224000612954825101001001000010010000500427731330018300373003728272628741101002001000820030024300373003711102011009910010010000100240001117170160029646100001003003830038300383003830038
10204300372254001472954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000000007102162229634100001003003830038300383003830038
10204300372250004712954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100001000007102162229634100001003003830038300383003830038
10204300372250001472954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000000007102162229634100001003003830038300383003830038
10204300372250007072954865101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000000007102162229634100001003003830038300383003830038
102043003722500010222954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000000007102162229634100001003003830038300383003830038
10204300372250004172954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000000007102162229634100001003003830038300383003830038
10204300372250002232954825101001001000010010000500427731330059300373003728265328745101002001016820430000300373003711102011009910010010000100000000007102162229634100001003003830038300383003830038
10204300372250006312954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000000007102162229634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080a0b18191e1f3a3f4e51inst 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)9fa0a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500000000536295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000006406163329630010000103003830038300383003830038
1002430037225000000002512954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000002406403163329630010000103003830038300383003830038
10024300372250000000061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000006403163329630010000103003830038300383003830038
10024300372250000000061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000006403163329630010000103003830038300383003830038
10024300372250000000061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000006403163329630010000103003830038300383003830038
1002430037225000634115280328929485140100591110048131099150427731303001830037300372828732876710010201000020300003003730037111002110910101000010020141946927885494429882010000103040530418302283032230369
10024303682261115593652824292294851431006614100561111043724282741030306304133045228339372891810457221131126314913041630451911002110910101000010200142249028094804529918110000103046330465304653046630466
1002430416227000000001452954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010222102485008293247429920110000103045730452304683050930467
1002430462228010491065792061295482510010101000010100005042773130300183003730037282873287671001020100002033435300373003711100211091010100001000030006403163329630010000103003830038300383003830038
10024300372250000090019762953682100381210032121059650428274103016230226302242830315288241045720104862030000301313008331100211091010100001000002006406323329749010000103008630084300863013230229

Test 3: Latency 1->2

Code:

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

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)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)9fa6a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071021611296340100001003003830038300383003830038
10204300372250000000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
10204300372240000000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
10204300372240000000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
102043003723300000006832954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
10204300372250000000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
10204300372250000000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
10204300372250000000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
10204300372250000000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
10204300372250000000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071013211296340100001003003830038300383003830038

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)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)9fa0a1a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500612954825100101010000101000050427731303001803003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731303001803003730037282873287671001020100002030000300373003711100211091010100001000000640216322963010000103003830038300383003830083
100243003722400612954825100101010000101000050427731313001803003730037282878287861001020100002030000300373003711100211091010100001000000640216322963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731313001803003730037282873287671001020100002030000300373003711100211091010100001000000640217322963010000103003830038300383003830038
1002430037225001912954825100101010000101000050427731303001803003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731313001803003730037282873287671001020100002030000300373003711100211091010100001000000640216232963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731303001803003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731313001803003730085282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731303001803003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731303001803003730037282873287671001020100002030000300373003711100211091010100001000000640216322963010000103003830038300383003830038

Test 4: Latency 1->3

Code:

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

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)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)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)9fa8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722502646129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730085211020110099100100100001000007101161129634100001003003830038300383003830038
102043003722524306129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000067101161129634100001003003830038300383003830038
102043003722525806129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372254508429548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037224006129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038

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)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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
1002430037225054306129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000101006402162229630010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
1002430037225046806129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

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

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)033f51inst 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)9fa8a9acc5branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16020420078150704258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100106001011111611200611600001002006520065200652006520065
1602042006415139258010010080000100800005006400000200452006420064322801002008013620024000020064200641116020110099100100160000100100101011111611200611600001002006520065200652006520307
1602042006415039258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100100001011111611200611600001002006520065200652006520065
1602042006415039258010010080000100800005006400000200452006420064322801002008000020024000020064200642116020110099100100160000100000001011111611200611600001002006520065200652006520065
1602042006415039258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100000001011111611200611600001002022420065200652006520065
1602042006415039258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100000001011111611200611600001002006520065200652006520065
1602042006415039258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100100001011111611200611600001002006520065200652006520065
1602042006415039258010010080000102800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100000001011111611200611600001002006520065200652006520065
1602042006415039258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100000001011111611200611600001002006520065200652006520065
1602042006415039258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100100001011111611200611600001002006520065200652006520065

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0304070a0b191e1f3a3f51inst 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)9fa8a9acc2cfd0d2icache miss (d3)itlb miss (d4)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160024200781560010012001682780012128000012800006264000001020045200622005132280012208000020240000200512005111160021109101016000010100010042831032252122126200482201160000102006320052200522005220052
1600242005115500300180115429800121280000128000062640000015200432006220062322800122080000202400002006220063111600211091010160000100000100551162030363222429200592412160000102006320063200632005220063
1600242006215601200000353329800121280000128000062640000115200432006220062322800122080000202400002006220062111600211091010160000100000100541162030363221631200592412160000102006320063200632006320063
1600242006215502200000692980012128000012800006264000011520043200622006232280012208000020240000200622005111160021109101016000010000010040851022252112817200482201160000102005220052200522005220052
16002420051153021000005727800121280000128000062640000115200322005120051322800122080000202400002005120051111600211091010160000100000100541161030362221729200482201160000102006320052200632005220052
1600242005115302300000632980012128000012800006264000011520032200512005132280012208000020240000200512005111160021109101016000010000010045851022252112922200482201160000102005220063200522005220052
1600242005115301200000572780012128000012800006264000011520032200512005132280012208000020240000200512005111160021109101016000010000010052851030252112930200482201160000102005220063200522005220052
1600242145316300000000452580012128000012800006264000011020027200462004632280012208000020240000200462004611160021109101016000010000010052311029202112329200432150160000102004720047200472004720047
1600242004615002000000572580012128000012800006264000011020027200462004632280012208000020240000202912004611160021109101016000010003010054311029202111729200432150160000102004720126200472004720049
1600242013515002200000572580012128000012800006264000011020027200462004632280012208000020240000200462004611160021109101016000010100210052311029202112229201103150160000102004720047200472004720047

Test 6: throughput

Count: 12

Code:

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

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)030b1e1f373a3f4e51inst 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)9faccfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
12020431429234000011253489251201001001200531001200005009900001300203094330039149733149971201002001200002003600003003930039111202011009910010012000010007610116113091901200001003004030040309443004030923
12020430039225000111690251201001001200531001200005009600000300203004230039158503150001201002001200002003600003092230039111202011009910010012000010007610116113003601200001003004030040309233004030040
1202043094322500001640251201011001200001001200005009900000300203004230039158503159011201002001200002003600003004230039111202011009910010012000010007610116113003801200001003092330040300403004330040
120204300422250001132202512010010012000010012000050096000003002330039300391497320149971201002001200002003600003004230039111202011009910010012000010007610116113003601200001003004030043300403004030040
12020430039225000011470471201001001200001001200005009600000300203003930039149733149971201002001200002003600003003930922111202011009910010012000010007610116113003901200001003004030040309443004030041
12020430039225000016402512010010012000010012000050096000003002030039300421497325167081201002001200002003600003003930042111202011009910010012000010007610116113003601200001003004030040309443004030043
12020430039224000016402512015310012000010012000050042834000300203094330039158503150001201002001200002003600003004230039111202011009910010012000010007610116113003601200001003004330040300403094430040
1202043175023700011620251201001001200001001200005009600000300203003930039149733149971201002001200002003600003003930039111202011009910010012000010007610116113003601200001003004030040300433004030040
1202043003922500001640251201011001200001001200005009900000300203003930042149733149971201002001200002003600003003930039111202011009910010012000010007610116113003651200001003004030944300403004030040
12020430039232000011640251201531001200001001200005009900000300203094330039149733150001201002001200002003600003094330039111202011009910010012000010007610116113091901200001003004030043317503004030923

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03081e373a3f4e51inst 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)5f6061696b6d6edispatch 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)9fa8a9accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1200243004022505118162160251200101012000010120000509600001153002003003930039149963150191200102012000020360000300393003911120021109101012000010000752283115162112020300360206120000103004030040300403004030040
1200243003922500081760251200101012000010120000509600001153002003003930039149963150191200102012000020360000300393003911120021109101012000010000752283120162112120300360206120000103004030040300403004030040
120024300392250007670251200101012000010120000509600001153002003003930039149963150191200102012000020360000300393003911120021109101012000010000752283114162111913300362206120000103004030040300403004030040
1200243003922500207460251200101012000010120000509600001153002003003930039149963150191200102012000020360000300393003911120021109101012000010000752283119162112020300360206120000103004030040300403004030040
1200243003922500071340251200101012000010120000509600001153002003003930039149963150191200102012000020360000300393003911120021109101012000010000752283118162111819300360206120000103004030040300403004030040
120024300392250007690251200101012000010120000509600001153002003003930039149963150191200102012000020360000300393003911120021109101012000010000752283115162111819300360206120000103004030040300403004030040
1200243003922500083630251200101012000010120000509600001153002003003930039149963150191200102012000020360000300393003911120021109101012000010000752283118162111918300360206120000103004030040300403004030040
120024300392250006690251200101012000010120000509600001153002003003930039149963150191200102012000020360000309223003911120021109101012000010000752283120162111919300363206120000103004030040300403004030040
1200243003922500081550251200101012000010120000509600001153002003003930039149963150191200102012000020360000300393003911120021109101012000010000752283119162111919300360206120000103004030040300403004030040
1200243003922500061990251200101012000010120000509600001153002003003930039149963150191200102012000020360000300393003911120021109101012000010000752283118162111820300360206120000103004030040300403004030040