Apple M1 Microarchitecture Research by Dougall Johnson

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

SHA256SU1

Test 1: uops

Code:

  sha256su1 v0.4s, v1.4s, v2.4s
  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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372300611901251000100010001045003018303730372739328951000100030003037303711100110000073116112920100030383038303830383038
100430372300611901251000100010001045003018303730372739328951000100030003037303711100110000073116112920100030383038303830383038
100430372200821901251000100010001045003054303730372739328951000100030003037303711100110000073116112920100030383038303830383038
100430372200611901251000100010001045003018303730372739328951000100030003037303711100110000073116112920100030383038303830383038
100430372300611901251000100010001045003018303730372739328951000100030003037303711100110000073116112920100030383038303830383038
100430372300611901251000100010001045003018303730372739328951000100030003037303711100110001073116112920100030383038303830383038
100430372200611901251000100010001045003018303730372739328951000100030003037303711100110000073116112920100030383038303830383038
100430372200611901251000100010001045003018303730372739328951000100030003037303711100110000073116112920100030383038303830383038
100430372200611901251000100010001045003018303730372739328951000100030003037303711100110000073116112920100030383038303830383038
100430372200611901251000100010001045003018303730372739328951000100030003037303711100110000073116112920100030383038303830383038

Test 2: Latency 1->1

Code:

  sha256su1 v0.4s, v1.4s, v2.4s
  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)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)9fa8a9accfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500611990125101001001000010010000500106750013001830037300372858932874510100200100002003000030037300371110201100991001001000010000071003162229920100001003003830038300383003830038
102043003722500611990125101001001000010010000500106750013001830037300372858932874510100200100002003000030037300371110201100991001001000010000071002162229920100001003003830038300383003830038
102043003722500611990125101001001000010010000500106750003001830037300372858932874510100200100002003000030037300371110201100991001001000010000071012162229920100001003003830038300383003830038
1020430037225005361990125101001001000010010000500106750003001830037300372858932874510100200100002003000030037300371110201100991001001000010000071012162229920100001003003830038300383003830038
1020430037225004411990125101001001000010010000500106750003001830037300372858932874510100200100002003000030037300371110201100991001001000010000071012162229920100001003003830038300383003830038
102043003722500611990125101001001000010010000500106750013001830037300372858932874510100200100002003000030037300371110201100991001001000010000071012162229920100001003003830038300383003830038
102043003722400611990125101001001000010010000500106750003001830037300372858932874510100200100002003000030037300371110201100991001001000010000071012162329920100001003003830038300383003830038
102043003722400611990125101001001000010010000500106750003001830037300372858932874510100200100002003000030037300371110201100991001001000010000071012162229920100001003003830038300383003830038
1020430037225007261990125101001001000010010000500106750003001830037300372858932874510100200100002003000030037300371110201100991001001000010000071012162229920100001003003830038300383003830038
1020430037225003461990125101001001000010010000500106750003001830037300372858932874510100200100002003000030037300371110201100991001001000010010071012162229920100001003003830038300383003830038

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)9fa8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225014519901251001010100001010000501067500030018300373003728611328767100102010000203000030037300371110021109101010000100640217222992010000103003830038300383003830038
100243003722506119901251001010100001010000501067500030018300373003728611328767100102010000203000030037300371110021109101010000100640216232992010000103003830038300383003830038
100243003722506119901251001010100001010000501067500030018300373003728611328767100102010000203000030037300371110021109101010000100640316222992010000103003830038300383003830038
100243003722506119901251001010100001010000501067500030018300373003728611328767100102010000203000030037300371110021109101010000100640216222992010000103003830038300383003830038
100243003722506119901251001010100001010000501067500030018300373003728611328767100102010000203000030037300371110021109101010000100640216222992010000103003830038300383003830038
100243003722506119901251001010100001010000501067500030018300373003728611328767100102010000203000030037300371110021109101010000100640216222992010000103003830038300383003830038
100243003722506119901251001010100001010000501067500030018300373003728611328767100102010000203000030037300371110021109101010000100640216222992010000103003830038300383003830038
100243003722406119901251001010100001010000501067500030018300373003728611328767100102010000203000030037300371110021109101010000100640216222992010000103003830038300383003830038
100243003722406119901251001010100001010000501067500030018300373003728611328767100102010000203000030037300371110021109101010000100640216322992010000103003830038300383003830038
100243003722506119901251001010100001010000501067500030018300373003728611328767100102010000203000030037300371110021109101010000100640216222992010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  sha256su1 v0.4s, v0.4s, v1.4s
  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)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)9fa8cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250006119901251010010010000100100005001067500130018300373003728589328745101002001000020030000300373003711102011009910010010000100071011611299200100001003003830038300383003830038
10204300372250006119901251010010010000100100005001067500130018300373003728589328745101002001000020030000300373003711102011009910010010000100071011611299200100001003003830038300383003830038
10204300372250006119901251010010010000100100005001067500130018300373003728589328745101002001000020030000300373003711102011009910010010000100071011611299200100001003003830038300383003830038
1020430037225005286119901251010010010000100100005001067500130018300373003728589328745101002001000020030000300373003711102011009910010010000100071011611299200100001003003830038300383003830038
10204300372250006119901251010010010000100100005001067500130018300373003728589328745101002001000020030000300373003711102011009910010010000100071011611299200100001003003830038300383003830038
10204300372240006119901251010010010000100100005001067500130018300373003728589328745101002001000020030000300373003711102011009910010010000100071011611299200100001003003830038300383003830038
10204300372250006119901251010010010000100100005001067500130018300373003728589328745101002001000020030000300373003711102011009910010010000100071011611299200100001003003830038300383003830038
10204300372250006119901251010010010000100100005001067500130018300373003728589328745101002001000020030000300373003711102011009910010010000100171011611299200100001003003830038300383003830038
10204300372250006119901251010010010000100100005001067500130018300373003728589328745101002001000020030000300373003711102011009910010010000100071011611299200100001003003830038300383003830038
10204300372250006119901251010010010000100100005001067500030018300373003728589328745101002001000020030000300373003711102011009910010010000100071011611299200100001003003830038300383003830038

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)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)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037224246044119901251001010100001010000501067500300183003730037286113287671001020100002030000300373003711100211091010100001020640416442992010000103003830038300383003830038
1002430037225606119901251001010100001010000501067500300183003730037286113287671001020100002030000300373003711100211091010100001000640516552992010000103003830038300383003830038
1002430037225158872619901251001010100001010000501067500300183003730037286113287671001020100002030000300373008411100211091010100001000640616452992010000103003830038300383003830038
1002430037225606119901251001010100001010000501067500300183003730037286113287671001020100002030000300373003711100211091010100001000640616562992010000103003830038300383003830038
10024300372253015619901251001010100001010000501067500300183003730037286113287671001020100002030000300373003711100211091010100001000640516652992010000103003830038300383003830038
1002430037225608219901251001010100001010000501067500300183003730037286113287671001020100002030000300373003711100211091010100001000640616662998910000103003830038300383003830038
10024300372256053619901251001010100001010000501067500300183003730037286113287671001020100002030000300373003711100211091010100001000640516652992010000103003830038300383003830038
10024300372251506119901251001010100001010000501067500300183003730037286113287671001020100002030000300373003711100211091010100001000640616652992010000103003830038300383003830038
1002430037225606119901251001010100001010000501067500300183003730037286113287671001020100002030000300373003711100211091010100001000640616642992010000103003830038300383003830038
10024300372256008219901251001010100001010000501067500300183003730037286113287671001020100002030000300373003711100211091010100001000640516662992010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  sha256su1 v0.4s, v1.4s, v0.4s
  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)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)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)9fa1a6a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000072619901251010010010000100100005001067500130018300373003728589328745101002001000020030000300373003711102011009910010010000100000007101161129920100001003003830038300383003830038
1020430037225000083919901251010010010000100100005001067500030018300373003728589328745101002001000020030000300373003711102011009910010010000100000007101161129920100001003003830038300383003830038
10204300372250018034619901251010010010000100100005001067500030018300373003728589328745101002001000020030000300373003711102011009910010010000100000007101161129920100001003003830038300383003830038
102043003722400006119901251010010010000100100005001067500130018300373003728589328745101002001000020030000300373003711102011009910010010000100000007101161129920100001003003830038300383003830038
10204300372250412074719901251010010010000100100005001067500030018300373003728589328745101002001000020030000300373008411102011009910010010000100000007101161129920100001003003830038300383003830038
1020430037225000063119901251010010010000100100005001067500030018300373003728589328745101002001000020030000300373003711102011009910010010000100000007101161129920100001003003830038300383003830038
102043003722500006119901251010010010000100100005001067500130018300373003728589328745101002001000020030000300373003711102011009910010010000100000007101161129920100001003008430038300383003830038
102043003722500006119901251010010010000100100005001067500030018300373003728589328745101002001000020030000300373003711102011009910010010000100000007101161129920100001003003830038300383003830038
102043003722500006119901251010010010000100100005001067500030018300373003728589328745101002001000020030000300373003711102011009910010010000100000007101161129920100001003003830038300383003830038
1020430037225302706119901251010010010000100100005001067500030018300373003728589328745101002001000020030000300373003711102011009910010010000100000007101161129920100001003003830038300383003830038

1000 unrolls and 10 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)9fa0a1a6a7a8a9acc2c5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500004206119901251001010100001010000501067500030018300373003728611328767100102010000203017430037300371110021109101010000100000000006402162229920010000103003830038300383003830038
10024300372250000906119901251001010100001010000501067500030018300373003728611328767100102010115203017130084300374110021109101010000103421047975207407726930063210000103003830038300383003830038
10024300372250000006119901251001010100001010000501067500030018300373003728611328767100102010000203000030037300371110021109101010000100000000006402162229920010000103003830038300383003830038
10024300372240000006119901251001010100001010000501067500030018300373003728611328767100102010000203000030037300371110021109101010000100000000006402162229920010000103003830038300383003830038
10024300372250000006119901251001010100001010000501067500030018300373003728611328767100102010000203000030037300371110021109101010000100000100006402162229920010000103003830038300383003830038
10024300372250000006119901251001010100001010000501067500030018300373003728611328767100102010000203020430037300371110021109101010000100000000006402162229920010000103003830038300383003830038
10024300372250000006119901251001010100001010000501067500030018300373003728611328767100102010000203000030037300371110021109101010000100000000006402162229920010000103003830038300383003830038
10024300372250000006119901251001010100001010000501067500030018300373003728611328767100102010000203000030037300371110021109101010000100000000006402162229920010000103003830038300383003830038
10024300372250000006119901251001010100001010000501067500030018300373003728611328767100102010000203000030037300371110021109101010000100000000006402162229920010000103003830038300383003830038
10024300372250000006119901251001010100001010000501067500030018300373003728611328767100102010000203000030037300371110021109101010000100000000006402162229920010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  sha256su1 v0.4s, v8.4s, v9.4s
  movi v1.16b, 0
  sha256su1 v1.4s, v8.4s, v9.4s
  movi v2.16b, 0
  sha256su1 v2.4s, v8.4s, v9.4s
  movi v3.16b, 0
  sha256su1 v3.4s, v8.4s, v9.4s
  movi v4.16b, 0
  sha256su1 v4.4s, v8.4s, v9.4s
  movi v5.16b, 0
  sha256su1 v5.4s, v8.4s, v9.4s
  movi v6.16b, 0
  sha256su1 v6.4s, v8.4s, v9.4s
  movi v7.16b, 0
  sha256su1 v7.4s, v8.4s, v9.4s
  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): 1.0005

retire (01)cycle (02)030818191e1f3f51inst 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)9fa8accdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602048003959900000502580100100800001008000050064000008002080039800395996435999780100200800002002400008003980039111602011009910010016000010000010110116118003501600001008004080040800408004080040
1602048003960000000502580100100800001008000050064000018002080039800395996435999780100200800002002400008003980039111602011009910010016000010000010110116118003501600001008004080040800408004080040
1602048003959900000502580100100800001008000050064000008002080039800395996435999780100200800002002400008003980039111602011009910010016000010000010110116118003501600001008004080040800408004080040
1602048003959900000502580100100800001008000050064000008002080039800395996435999780100200800002002400008003980039111602011009910010016000010000010110116118003501600001008004080040800408004080040
1602048003960000000502580100100800001008000050064000008002080039800395996435999780100200800002002400008003980039111602011009910010016000010000010110116118003501600001008004080040800408004080040
1602048003960000000502580100100800001008000050064000008002080039800395996435999780148200800002002400008003980039111602011009910010016000010000010110116118003501600001008004080040800408004080040
1602048003960000000502580100100800001008000050064000008002080039800395996435999780100200800002002400008003980039111602011009910010016000010000010110116118003501600001008004080040800408004080040
16020480039599000007152580100100800001008000050064000008002080039800395996435999780100200800002002400008003980039111602011009910010016000010000010110116118003501600001008004080040800408004080040
1602048003959900000502580100100800001008000050064000008002080039800395996435999780100200800002002400008003980039111602011009910010016000010000010110116118003501600001008004080040800408004080040
1602048003959900000502580100100800001008000050064000008002080039800395996435999780100200800002002400008003980039111602011009910010016000010000010110116118003501600001008004080040800408004080040

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 1.0005

retire (01)cycle (02)0308090a0b1e3f51inst 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)9fa1a6a8acbranch mispredict (cb)cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16002480039599000005625800101080000108000050640000018002080039800395998636001980010208000020240000800398003911160021109101016000010000001002231114162111068003502013160000108004080040800408004080040
1600248003959900000562580010108000010800005064000011800208003980039599863600198001020800002024000080039800391116002110910101600001000000100223116162111098003502013160000108004080040800408004080040
160024800395990000056258001010800001080000506400000180020800398003959986360019800102080000202400008003980039111600211091010160000100000010022611121622114780035040117160000108004080040800408004080040
160024800395990000056258001010800001080000506400002180020800398003959986360019800102080000202400008003980039111600211091010160000100000010022622916221488003502026160000108004080040800408004080040
160024800395990000056258001010800001080000506400001180020800398003959986360019800102080000202400008003980039111600211091010160000100000010022321616221888003504013160000108004080040800408004080040
160024800396000000056258001010800001080000506400000180020800398003959986360019800102080000202400008003980039111600221091010160000100000010022311816211958003502013160000108004080040800408004080040
16002480039599000005625800101080000108000050640000218002080039800395998636001980010208000020240000800398003911160021109101016000010000001002231110162115148003502013160000108004080040800408004080040
160024800396000000056258001010800001080000506400001180020800398003959986360019800102080036202404388003980039111600211091010160000100000010022311516211968003502013160000108004080040800408004080040
1600248003959900000562580010108000010800005064000011800208003980039599863600198001020800002024000080039800391116002110910101600001000000100223114162111468003502013160000108004080040800408004080040
16002480039600000002462580010108000010800005064000011800208003980039599863600198001020800002024000080039800391116002110910101600001000000100223111116211958003502013160000108004080040800408004080040

Test 6: throughput

Count: 16

Code:

  sha256su1 v0.4s, v16.4s, v17.4s
  sha256su1 v1.4s, v16.4s, v17.4s
  sha256su1 v2.4s, v16.4s, v17.4s
  sha256su1 v3.4s, v16.4s, v17.4s
  sha256su1 v4.4s, v16.4s, v17.4s
  sha256su1 v5.4s, v16.4s, v17.4s
  sha256su1 v6.4s, v16.4s, v17.4s
  sha256su1 v7.4s, v16.4s, v17.4s
  sha256su1 v8.4s, v16.4s, v17.4s
  sha256su1 v9.4s, v16.4s, v17.4s
  sha256su1 v10.4s, v16.4s, v17.4s
  sha256su1 v11.4s, v16.4s, v17.4s
  sha256su1 v12.4s, v16.4s, v17.4s
  sha256su1 v13.4s, v16.4s, v17.4s
  sha256su1 v14.4s, v16.4s, v17.4s
  sha256su1 v15.4s, v16.4s, v17.4s
  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): 1.0002

retire (01)cycle (02)03080b18191e1f3f51inst 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)9fa0a1a6a8a9acc2c5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602041602371199100000922516010010016000010016000050012800000160020160039160039139964031399971601002001600002004800001600391600391116020110099100100160000100000262600010110616851600357160000100160040160040160040160040160040
16020416023611990000005025160100100160096100160000500128000001601721600391600391399640313999716022120016000020048000016003916003911160201100991001001600001000000000010168616661600350160000100160040160040160040160040160040
160204160039119900000018025160206102160000100160000500128081201600201600391600391399640313999716010020016000020048000016003916003941160201100991001001600001002000000010110616561600350160000100160040160040160237160040160040
16020416003911980000009225160100100160000100160000500128000001600201600391602351399640313999716010020016000020048000016003916003921160201100991001001600001000000000010110516551600350160000100160139160040160040160040160040
16020416003911990000005025160100100160000100160000500128000001600201600391600391399640313999716010020016000020048000016003916003951160201100991001001600001000000000010110616651600350160000100160040160040160040160040160040
160204160039119800000050251601001001600001001600005001280000016002016003916003913996403139997160100200160000200480447160039160039111602011009910010016000010000000300101106161051600359160000100160040160040160040160239160040
160204160039119910000071525160100100160000100160000500128000001600201600391600391399640314014316010020016000020048000016003916008911160201100991001001600001000000090010110516661600350160000100160040160040160040160040160040
16020416003911990000123525025160100100160000100160000525128000001600201600391600391399640313999716010020016000020048000016003916003911160201100991001001600001000001000010110516441600350160000100160040160040160040160040160040
16020416003911991000123525025160100100160000100160000500128000001600201600391600391399640313999716010020016000020048000016023916003911160201100991001001600001000003000010167516651600350160000100160040160040160040160040160040
1602041600391199000058205025160100100160000100160000620128000001600201600391600391399640313999716010020016000020048014416003916003951160201100991001001600001000000000010110516581600350160000100160040160040160040160040160040

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 1.0002

retire (01)cycle (02)03181e3f51inst 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)5f60696b6d6edispatch 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)9fa6a7a8a9acc5cdcfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)dfe0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1600241600391199005625160010101600001016000050128000011160020016003916003913998603140019160010201600002048000016003916003911160021109101016000010000000010025312916211653160034151316000010160040160040160040160040160040
160024160039119800562516001010160000101600005012800001116002001600391600391399860314001916001020160000204800001600391600391116002110910101600001000001770010025311516211933160034151316000010160040160040160040160040160040
16002416003911990056251600101016000010160000501280000111600200160039160039139986031400191600102016000020480000160039160039111600211091010160000100000375001002531151621110103160034151316000010160040160040160040160040160040
16002416003911990066572516001010160000101600005012800001116002001600391600391399860314001916001020160000204800001600391600391116002110910101600001000003480010025322516211353160147151316000010160040160040160040160040160040
1600241602851200305625160010101600001016000050128000001160020016003916003913998603140019160010201600002048000016003916003911160021109101016000010200232320010025311416211933160034151316000010160040160040160040160040160040
1600241600391199007212516001010160000101600005012800001116002001600391600391399860314001916001020160000204800001600391600391116002110910101600001000402130010025311416211893160034151316000010160040160040160040160040160040
160024160039119800772516001010160000101600005012800001116002001600391600391399860314001916001020160000204800001600391600391116002110910101600001020101740010025311316211393160034151316000010160040160040160040160040160040
1600241600391199007422516001010160000101600005012800001116002001600391600391399860314001916001020160000204800001600391600391116002110910101600001000002460010046322416211533160034151316000010160040160040160040160040160040
1600241600391199072622516001011160024101600006012800001116002001600391600391399860314001916001020160040204800001600391602141116002110910101600001002102490010025311316211393160034151316000010160040160040160040160040160040
1600241600391201007725160010101600001016000050128000011160020016003916003913998603140019160010201600002048000016003916003911160021109101016000010000090010027321916221393160034301316000010160040160040160040160040160087