Apple M1 Microarchitecture Research by Dougall Johnson

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

SMLAL2 (by element, 2D)

Test 1: uops

Code:

  smlal2 v0.2d, v1.4s, 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)a0a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303723061254825100010001000398313130183037303724153289510001000300030373037111001100022073116112630100030383038303830383038
1004303722061254825100010001000398313030183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
1004303723061254825100010001000398313030183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
1004303722061254825100010001000398313030183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
1004303723061254825100010001000398313130183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
10043037221261254825100010001000398313130183037303724153289510001000300030373037111001100000073116112630100030383038303830383086
1004303722082254825100010001000398313030183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
1004303723061254825100010001000398313130183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
1004303723061254825100010001000398313130183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
1004303723061254825100010001000398313130183037303724153289510001000300030373037111001100000073116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  smlal2 v0.2d, v1.4s, 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)0318191e3a3f4e51inst 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)9fa8acc2branch mispredict (cb)cfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000612954825101001001000010010000500427731303001830037300372826503287451010020010000200300003003730037111020110099100100100001000000710121622296346100001003003830038300383003830038
10204300372250000822954825101001001000010010000500427731303001830037300372826503287451010020010000200300003003730037111020110099100100100001000000710121622296340100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731313001830037300372826503287451010020010000200300003003730037111020110099100100100001000000710121622296700100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731303001830037300372826573287451010020010000200300003003730037111020110099100100100001000000710131622296340100001003003830038300383003830038
1020430037232000067262954825101001001000010010000500427731313001830037300372826503287451010020010000200300003003730037111020110099100100100001000000712121622296340100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731303001830037300372826503287451010020010000200300003003730037111020110099100100100001000000710121622296340100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731303001830037300372826503287451010020010000200300003003730037111020110099100100100001000000710121622296340100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731303001830037300372826503287451010020410000200300003008430037111020110099100100100001000000710131622296340100001003003830038300383003830038
1020430037225004920612954825101001001000010010000500427731303001830037300372826503287451010020010000200300003003730037111020110099100100100001000000710121622296340100001003003830038300383003830038
102043003722500005272954825101001001000010010000500427731303001830037300372826503287451010020010000200300003003730037111020110099100100100001000000710121622296340100001003003830038300383003830038

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)9fa1a8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250612954825100101010000101000050427731303001803003730037282873287671001020100002030000300373003711100211091010100001000640316332963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001803003730037282873287671001020100002030000300373003711100211091010100001000640316442963010000103003830038300383003830038
1002430037225552612954825100101010000101000050427731303001803003730037282873287671001020100002030000300373003711100211091010100001000640316332963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001803003730037282873287671001020100002030000300373003711100211091010100001000640316332963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001803003730037282873287671001020100002030000300373003711100211091010100001000640416332963010000103003830038300383003830038
1002430037225300612954825100101010000101000050427731303001803003730037282873287671001020100002030000300373003711100211091010100001000640316332963010000103003830038300383003830038
10024300372259612954825100101010000101000050427731303001803003730037282873287671045920100002030000300373003711100211091010100001000640316332963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001803003730037282873287671001020100002030000300373003711100221091010100001000640316332963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001803003730037282873287671001020100002030000300373003711100211091010100001000640316332963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001803003730037282873287671001020100002030000300373003711100211091010100001000640316332963010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  smlal2 v0.2d, v0.4s, 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)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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372258769029548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100007102162229634100001003003830038300383003830038
10204300372253072629548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100007102162229634100001003003830038300383003830038
1020430037225306129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100007102162229634100001003003830038300383003830038
10204300372253696129548251010010010000100100005004277735130018300373003728265328745101002001000020030000300373003711102011009910010010000100007102162229634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100007102162229634100001003003830038300383003830038
1020430037225276129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100007102162229634100001003003830038300383003830038
1020430037225216129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100007102162229634100001003003830038300383003830038
1020430037225336129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100007102162229634100001003003830038300383003830038
10204300372252715629548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100007102162229634100001003003830038300383003830038
1020430037225396129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100007102162229634100001003003830038300383003830038

1000 unrolls and 10 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)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)9fa1a8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000640616222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
10024300372241206129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722551006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000640216232966610000103003830038300383003830038
1002430037225006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373008528287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
10024300372253306129548251001012100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
10024300372253006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
1002430037225306129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103008630038300383003830038
10024300372253906129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  smlal2 v0.2d, v1.4s, 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)0318191e1f3f4e51inst 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)9fa6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500330612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000071021622296340100001003003830038300383003830038
102043003722500240612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000071021622296340100001003003830038300383003830038
1020430037225001506129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100010710216222963424100001003003830038300383003830038
102043003722500240612954825101001001000010010000500427731303001830086300372826572876210100200101662023000030037300371110201100991001001000010000071021622296340100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000071021622296340100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000071021622296340100001003003830038300383003830038
1020430037225002707262954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000071021622296340100001003003830038300383003830038
1020430037225002402512954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010020071021622296340100001003003830085300873003830085
10204300372252130303462954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000071021622296340100001003003830038300383003830038
102043003722500270612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010001071021622296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03090b1e3f4e51inst 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)9fa8acc5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372252066156295482510010101000010100005042773131300180300373003728287328767100102010000203000030037300371110021109101010000100006407162229630010000103003830038300383003830038
100243003722500061295482510010101000010100005042773130300180300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
10024300372250024232295482510010101000010100005042773131300180300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
1002430037225003361295482510010101000010100005042773131300180300373003728287328767100102010000203000030037300371110021109101010000100306402162229630010000103003830038300383003830038
100243003722500061295482510010101000010100005042773130300183300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
100243003722500361295482510010101000010100005042773131300180300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
10024300372250027943295482510010101000010100005042773131300180300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
1002430037225002161295482510010101000010100005042773131300180300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
100243003722500061295482510010101000010100005042773131300180300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
1002430037225003661295482510010101000010100005042773131300180300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  smlal2 v0.2d, v8.4s, v9.s[1]
  movi v1.16b, 0
  smlal2 v1.2d, v8.4s, v9.s[1]
  movi v2.16b, 0
  smlal2 v2.2d, v8.4s, v9.s[1]
  movi v3.16b, 0
  smlal2 v3.2d, v8.4s, v9.s[1]
  movi v4.16b, 0
  smlal2 v4.2d, v8.4s, v9.s[1]
  movi v5.16b, 0
  smlal2 v5.2d, v8.4s, v9.s[1]
  movi v6.16b, 0
  smlal2 v6.2d, v8.4s, v9.s[1]
  movi v7.16b, 0
  smlal2 v7.2d, v8.4s, 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)030b1e3f51inst 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)60696d6e74scheduler 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)e0ec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160204200651510123925801001008000010080000500640000020045200642006403228010020080000200240000200642006411160201100991001001600001000010111116112006101600001002006520065200652006520065
16020420064150003925801001008000010080000500640000120045200642006403228010020080000200240000200642006411160201100991001001600001000010111116112006101600001002006520065200652006520065
16020420064150003925801001008000010080000500640000020045200642006403228010020080000200240000200642006411160201100991001001600001000010111116112006101600001002006520065200652006520065
16020420064151093925801001008000010080000500640000120045200642006403228010020080000200240000200642030711160201100991001001600001000010111116112006101600001002006520065200652006520065
16020420064150003925801001008000010080000500640000020045200642006403228010020080000200240000200642006411160201100991001001600001000310111116112006101600001002006520065200652006520065
160204200641510873925801001008000010080000500640000120045200642006403228010020080000200240000200642006411160201100991001001600001000010111116112006101600001002006520065200652006520065
16020420064150003925801001008000010080000500640000120045200642006403228010020080000200240000200642006411160201100991001001600001000010111116112006101600001002006520065200652006520065
16020420064150006025801001008000010080000500640000120045200642006403228010020080000200240000200642006411160201100991001001600001000010111116112006101600001002006520065200652006520065
160204200641500070425801001008000010080000500640000120045200642006403228010020080000200240627200642006411160201100991001001600001000010111116112006101600001002006520065200652006520065
16020420064150003925801001008000010080000500640000020045200642006403228010020080000200240000200642006411160201100991001001600001000010111116112006101600001002006520065200652006520065

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)5f60696d6escheduler 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)9fa8c2cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1600242007815001242525800121280000128000062640000112002720046200463228001220800002024000020046200461116002110910101600001000100283119202114720043215160000102004720047200472004720047
1600242004615002456025800121280000128000062640000112002720046200463228001220800002024000020050200461116002110910101600001000100303114202114720043215160000102004720047200472004720047
16002420046150004525800121280000128000062640000112002720046200463228001220800002024000020046202911116002110910101600001000100296115202113720043215160000102004720047200472004720047
16002420046150004525800121280000128000062640000112002720046200463228001220800002024000020046200461116002110910101600001000100303119202114920043215160000102004720047200472004720047
16002420046150004525800121280000128000062640000112002720046200463228001220800002024000020046200461116002110910101600001000100293117202116420047215160000102004720047200472004720047
16002420046150004525800121280000128000062640000012002720050200463228001220800002024000020050200461116002110910101600001000100283117202116420043215160000102004720047200472004720047
16002420046150004525800121280000128000062640000112002720046200463228001220800002024000020046200461116002110910101600001000100273115202216920043215160000102004720047200472004720047
160024200461500754525800121280000128000062640000112002720050200463228001220800002024000020046200461116002110910101600001000100273116202116720043215160000102004720047200472004720047
16002420046150034525800121280000128000062640000112002720046200463228001220800002024000020046200461116002110910101600001000100293125202115420043215160000102004720047200472004720047
16002420046150004525800121280000128000062640000112002720046200463228001220800002024000020046200461116002110910101600001000100283113202118920043215160000102004720047200472004720047

Test 6: throughput

Count: 12

Code:

  smlal2 v0.2d, v12.4s, v13.s[1]
  smlal2 v1.2d, v12.4s, v13.s[1]
  smlal2 v2.2d, v12.4s, v13.s[1]
  smlal2 v3.2d, v12.4s, v13.s[1]
  smlal2 v4.2d, v12.4s, v13.s[1]
  smlal2 v5.2d, v12.4s, v13.s[1]
  smlal2 v6.2d, v12.4s, v13.s[1]
  smlal2 v7.2d, v12.4s, v13.s[1]
  smlal2 v8.2d, v12.4s, v13.s[1]
  smlal2 v9.2d, v12.4s, v13.s[1]
  smlal2 v10.2d, v12.4s, v13.s[1]
  smlal2 v11.2d, v12.4s, 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)03080b18191e1f373a3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1202043029622500000000125025120100100120000100120000500428618403002003003930039151283149971201002001200002003600003095130039111202011009910010012000010000000007610116163003601200001003004030040300403004030040
120204300392250100570004102512010010012000010012010450096000013002003003930039149733149971201002001200002003600003003930039111202011009910010012000010000000007610116143003601200001003004030040300403004030040
12020430039232000000520105025120100100120000100120000500428618403002003003930039149733149971201002001200002003600003003930039111202011009910010012000010000000007610116123003601200001003004030040300403004030040
1202043003923100002100014602512010010012000010012000050096000013093203003930039150093149971201002001200002003600003003930039111202011009910010012000010000004907610116133003601200001003004030040300403004030040
1202043003922500000020104025120100100120000100120000500428618403002003003930039149733149971201002001200002003600003003930039111202011009910010012000010000000007610116143003601200001003004030952300403004030040
12020430039231002000104102512010010012000010012000050096000003002003003930039149733156361201002001200002003600003003930039111202011009910010012000010000000007610116143003601200001003004030040300403004030040
12020430039225000000004102512010010012000010012000050096000013002003003930039149733149971201002001200002003600003003930039111202011009910010012000010000000007610116123094801200001003004030040309523004030040
12020430039225000030008335232512010010012000010012000050096000003002003003930039149733159091201002001200002003600003003930039111202011009910010012000010000000007610116143003601200001003004030040300403004030040
12020430039225000000001710251201001001200001001200005004286184030932030039300391497331499712010020012000020036000030039300391112020110099100100120000100000000076101161103003601200001003004030040300403004030040
12020430039225000000004102512010010012000010012000050096000013002033003930039149737149971201002001200002003600003003930039111202011009910010012000010000000007610116123003601200001003004030040300403004030040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080a0b18191e373f4e51inst 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)5f60696d6edispatch 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)9fa8a9acc2cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
120024300392250000000460251200101012000010120000509600001130020300393003914989315012120010201200002036000030039300391112002110910101200001000180752231151621155300360209120000103004030040300403004030040
1200243092222500000008802512004610120036101200005042839151130020300393003914989315012120010201200002036000030039300391112002110910101200001000240752231161621166300360209120000103092330040300403004030040
1200243101022500000005202512001010120000101200005096000001300203003930039149893150121200102012000020360000300393003911120021109101012000010003007524321416422543003602015120000103004030040300403004030040
1200243003922400000018736713251200101012000010120000509600000130020300393003914989315012120010201200002036000030039300391112002110910101200001000270752461251641245300360409120000103004030040300403004030040
120024300392250000000460251200281012000010120000509600001130020300393003914989315012120010201200002036000030039300391112002110910101200001000007524322616422663003604015120000103004030040300403174930040
1200243003922500000005202512001010120000101200005096000001300203003930039149893150121200102012000020360000300393003911120021109101012000010009007524622516222663003604015120000103004030040300403004030040
120024300412250000000520251200101012000010120000509600000130020310103101014989315012120010201200002036000030039309221112002110910101200001000750752461141621245300360409120000103004030040300403004030040
12002430039225000000052025120011101200001012000050960000013002030039300391498931501212001020120000203600003003930039111200211091010120000100010507522621416412553003604015120000103004030923300403004030040
120024300392250000000520251200101012000010120000509600001130903300393174814989315012120010201200002036000030039300391112002110910101200001000960752462251622254300360409120000103004030040300403004030040
120024300392250000000520251200101012000010120000504283622013002030039300391498931501212001020120000203600003003930039111200211091010120000100000752231151621155300360209120000103004030040300403174930040