Apple M1 Microarchitecture Research by Dougall Johnson

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

SDOT (by element, 16B)

Test 1: uops

Code:

  sdot v0.4s, v1.16b, v2.4b[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)033f4e51inst 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
10043037238225482510001000100039831303018303730372415328951000100030003037303711100110001073116112630100030383038303830383038
10043037236125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372210325482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037236125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372314925482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037236125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372210225482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037226125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037236125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037238225482510001000100039831313018303730372415328951000100030003037303711100110000373116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  sdot v0.4s, v1.16b, v2.4b[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)0308090b18191e1f3a3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)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)9fa1a6a8a9acc2c5cfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000000072629548251010010010000100100005004277313130018030037300372826532874510100200100002003000030037300371110201100991001001000010000005100712121622296340100001003003830038300383003830038
1020430037225000000004412954825101001001000010010000500427731313001803003730037282653287451010020010000200300003003730037111020110099100100100001000000900710121622296340100001003003830038300383003830038
102043003722500004537001262954844101001001000010010000500427731313001803003730037282653287451010020010000200300003003730037111020110099100100100001000030900710121622296340100001003003830038300383003830038
10204300372250000000018929548251010010010000100100005004277313130018030037300372826532874510100200100002003000030037300371110201100991001001000010000201200710121632296340100001003003830038300383003830038
1020430037224000000006129548251010010010000100100005004277313130018030037300372826532874510100200100002003000030037300371110201100991001001000010000520000710121622296340100001003003830038300383003830038
10204300372250000000144129548251010010010000100100005004277313130018030037300372826532874510100200100002003000030037300371110201100991001001000010000480000710121622296340100001003003830038300383003830038
1020430037225000000006312954825101001001000010010000500427731313001803003730037282653287451010020010000200300003003730037111020110099100100100001000048018300710121622296340100001003003830038300383003830038
102043003722500000000251295482510100100100001001000050042773131300180300373003728265328745101002001000020030000300373003711102011009910010010000100005001102800710121622296340100001003003830038300383003830038
1020430037225000000006129548251010010010000100100005004277313130018030037300372826532874510100200100002003000030037300371110201100991001001000010000370000710121622296340100001003003830038300383003830038
10204300372250000000025129548251010010010000100100005004277313130018030037300372826532874510100200100002003000030037300371110201100991001001000010000004500710121622296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b18191e1f3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372240000061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000600306402162229630010000103003830038300383003830038
1002430037225000006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100020006402163229630010000103003830038300383003830038
1002430037225000006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100010006402162229630010000103003830038300383003830038
1002430037225000006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100030306403162229630010000103003830085300863008530038
1002430037225000006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100010006402162229630010000103003830038300383003830038
1002430037225000006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100010006402162229630010000103003830038300383003830038
10024300372250000061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000701206402162329630010000103003830038300383003830038
1002430037225000006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100020006402162229630010000103003830038300383003830038
1002430037225000006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100010306402162229630010000103003830038300383003830038
1002430037225000006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100010006402162229630010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  sdot v0.4s, v0.16b, v1.4b[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)030708090a0b191e3f4e51inst 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)9fa7a8a9acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225100100061295482510100100100001001000050042773130300183003730037282726287401010020010008200300243003730037111020110099100100100001000590121117182161129650100001003003830038300383003830038
10204300372241001000612954825101001001000010010000500427731303001830037300372827272874110100200100082003002430037300371110201100991001001000010003001117171161129650100001003003830038300383003830038
10204300372241001000612954825101001001000010010000500427731303001830037300372827262874110100200100082003002430037300371110201100991001001000010004001117181161129650100001003003830038300383003830038
10204300372251001000612954825101001001000010010000500427731313001830037300372827272874010100200100082003002430037300371110201100991001001000010003001117181161129651100001003003830038300383003830038
1020430037225100100061295482510100100100001001000050042773130300183003730037282726287411010020010008200300243003730037211020110099100100100001000201680007102162229634100001003003830038300383003830038
10204300372250010000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010001000007102162229634100001003003830038300383003830038
10204300372240000000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010002000007102162229634100001003003830038300383003830038
10204300372250000000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010004000007102162229634100001003003830038300383003830038
102043003722500000006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100054030007102162229634100001003003830038300383003830038
102043003722500000006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100010300007102162229634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)033f4e51inst 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)91inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa0a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109010101000010000640216222963010000103003830038300383003830038
10024300372251052954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109010101000010000640216222963010000103003830038300383003830038
1002430037225842954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109010101000010000640216222963010000103008430038300383003830038
10024300372251072954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109010101000010000640216222963010000103003830038300383008630038
10024300372253962954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109010101000010000640216222963010000103003830038300383003830038
1002430037225612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109010101000010000640216262963010000103003830038300383003830038
10024300372254612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109010101000010000640216222963010000103003830038300383003830038
10024300372251692954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109010101000010000640216222963010000103003830038300383003830038
10024300372241472954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109010101000010010640216222963010000103003830038300383003830038
10024300372251492954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109010101000010000640216222963010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  sdot v0.4s, v1.16b, v0.4b[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)03071e3a3f4e51inst 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)9fa8acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722400022829548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000071021611296340100001003003830038300383003830038
10204300372250006129548251010010010000100101485804277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
10204300372250016129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
10204300372250006129548251010010010000100100006264277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
10204300372250016129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
10204300372240006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
10204300372250016129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
10204300372250008229548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038

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)9fa1acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722501242954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640416552963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640516462963010000103003830038300383003830038
10024300372250842954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640616652963010000103003830038300383003830038
10024300372250662954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640616652963010000103003830085300383003830038
100243003722505712954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640516662963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640616652963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010030640616652963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640516662963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640616642963010000103008530038300383003830038
10024300372250612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640616652963010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  sdot v0.4s, v8.16b, v9.4b[1]
  movi v1.16b, 0
  sdot v1.4s, v8.16b, v9.4b[1]
  movi v2.16b, 0
  sdot v2.4s, v8.16b, v9.4b[1]
  movi v3.16b, 0
  sdot v3.4s, v8.16b, v9.4b[1]
  movi v4.16b, 0
  sdot v4.4s, v8.16b, v9.4b[1]
  movi v5.16b, 0
  sdot v5.4s, v8.16b, v9.4b[1]
  movi v6.16b, 0
  sdot v6.4s, v8.16b, v9.4b[1]
  movi v7.16b, 0
  sdot v7.4s, v8.16b, v9.4b[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)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)60696b6d6escheduler 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)9fa1accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602042006515004632580100100800001008000050064000002004502006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
160204200641500392580100100800001008000050064000012004502006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
160204200641500392580100100800001008000050064000002004502006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
160204200641500392580100100800001008000050064000002004502006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
160204200641500392580100100800001008000050064000002004502006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002017020065201672006520065
160204200641500392580100100800001008000050064000012004502006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
160204200641510392580100100800001008000050064000012004502006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
1602042006415131442580100100800001008000050064000012004502006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
160204200641500392580100100800001008000050064000012004502006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
160204200641500392580100100800001008000050064000002004502006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0307080b191e1f3f51inst 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)9fa0a6a8acc2cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160024200851500000006627800121280000128000062640000112004120060200600322800122080000202400002006020051111600211091010160000100000010028311152521158200482202160000102005220052200522005220052
16002420051150100101081512980012128000012800006264000011200322005120051032280012208000020240000200512005111160021109101016000010000001002831182521178200482402160000102005220052200522005220052
16002420060150000000512780012128000012800006264000001200322006020060032280012208013420240000200602005111160021109101016000010000001003462282542185200572401160000102006120052200522005220061
16002420060150000000452980012128000012800006264000001200322006020051032280012208000020240000200602006011160021109101016000010000001003132183441158200482201160000102005220052200522005220052
16002420051150000000452780012128000012800006264000011200322005120051032280012208000020240000200512005111160021109101016000010000001002831152521185200482201160000102005220052200522005220052
16002420051150000000452780012128000012800006264000011200322005120051032280012208000020240000200512005111160021109101016000010000001003131182521187200482201160000102005220052200522005220052
160024200511500001004527800121280000128000062640000112003220051200510322800122080000202400002005120051111600211091010160000100000010031311725211118200482201160000102005220052200522005220052
160024200511500000004527800121280000128000062640000112003220051200600322800122080000202400002005120051111600211091010160000100000010031311625211108200482201160000102005220052200522005220052
1600242005115000000010242780012128000012800006264000011200322005120051032280012208000020240000200512005111160021109101016000010000001003131182521185200482201160000102005220052200522005220052
16002420051150000000111927800121280000128000062640000112003220051200510322800122080000202400002005120051111600211091010160000100000010031311525211108200482201160000102005220052200522005220052

Test 6: throughput

Count: 16

Code:

  sdot v0.4s, v16.16b, v17.4b[1]
  sdot v1.4s, v16.16b, v17.4b[1]
  sdot v2.4s, v16.16b, v17.4b[1]
  sdot v3.4s, v16.16b, v17.4b[1]
  sdot v4.4s, v16.16b, v17.4b[1]
  sdot v5.4s, v16.16b, v17.4b[1]
  sdot v6.4s, v16.16b, v17.4b[1]
  sdot v7.4s, v16.16b, v17.4b[1]
  sdot v8.4s, v16.16b, v17.4b[1]
  sdot v9.4s, v16.16b, v17.4b[1]
  sdot v10.4s, v16.16b, v17.4b[1]
  sdot v11.4s, v16.16b, v17.4b[1]
  sdot v12.4s, v16.16b, v17.4b[1]
  sdot v13.4s, v16.16b, v17.4b[1]
  sdot v14.4s, v16.16b, v17.4b[1]
  sdot v15.4s, v16.16b, v17.4b[1]
  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)696b6d6edispatch 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)9fa0a8a9acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602044004929996050251601001001600001001600005001280000400200400394003919973319997160100200160000200480000400394004811160201100991001001600001000000001011081649400451600001004004040049400404004040050
1602044004030001750251601001001600171001600005002148048400200400394003919973319997160100200160000200480000400484003911160201100991001001600001000000001011091699400361600001004004040040400404004040049
160204400903000041251601001001600001001600005001280000400200400394003919973320006160100200160000200480000400394003911160201100991001001600001000000001011091649400361600001004004040040400494004040040
1602044003930015041251601001001600001001600005001280000400200400394003919973320007160100200160000200480000400494003911160201100991001001600001000000001011091648400361600001004004040041400524004940040
160204400393000050251601001001600001001600005001280000400200400394004819973320007160100200160000200480000400394009041160201100991001001600001000000001011091698400361600001004004040040400404004040040
16020440039300004125160100100160000100160000500128000040029340039400841997332000616010020016000020048000040039400391116020110099100100160000100000000101109161010400361600001004004040049400404004040040
160204400483000041251601001001600001001600005002398999400200400484003919973319997160100200160000200480000400394003911160201100991001001600001000600001011061699400361600001004004940040400504004040040
160204400392990069251601001001600171001600005002398999400200400394003919973319997160100200160000200480000400394003911160201100991001001600001000000001011041699400361600001004004940040400404004040040
160204400392990041251601801001600011001600005001280000400200400394003919973319997160100200160000200480000400484003911160201100991001001600001000000001011041649400361600001004004040049400404004040049
160204400392990041251601001001600001001600005001280000400200400394003919973319997160100200160000200480000400394003911160201100991001001600001000000001011031694400361600001004004040049400404004040040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03070a373a3f51inst 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
1600244005830011025325160028101600001016000050128000001540020400394003919996320032160010201600002048000040049400391116002110910101600001000100268212316211191940036207160000104004040040400404004040049
1600244004030011025925160010101600011016000050128000001540020400394003919996320032160010201600002048000040039400391116002110910101600001000100268411916211182040046206160000104004040040400404004040040
160024400392991102532516001010160000101600005012800001104002040049400391999632002016001020160000204800004003940039111600211091010160000100470100268212116211192040036209160000104005040040400404004040040
1600244003930011025325160010101600001016000050128000011540020400394003919996320032160010201600002048000040039400391116002110910101600001000100268311916211182040036206160000104004040040400404004040050
1600244003930011025325160010101600001016000050128000011540020400394003919996320028160010201600002048000040039400391116002110910101600001000100268212116211212240036206160000104004140049400404004040040
1600244004830011025325160010101600181016000050128000011540020400394003919996320032160010201600002048000040039400391116002110910101600001000100288311716211181640036206160000104004040040400404004040040
1600244004930011025325160010101600001016000050128000011540020400484004819996320032160010201600002048000040039400391116002110910101600001000100268211616411161840036206160000104004040040400404004140040
16002440039300111725325160010101600001016000050128000011540020400394004919996320016160010201601052048000040039400391116002110910101600001000100268211816211182040036206160000104004040040400404004040040
16002440039299111727425160010101600001016014850128000011540020400394003919996320032160010201600002048000040039400391116002110910101600001000100268312116211192140036206160000104004040040400404004040050
16002440039300111825325160010101600001016000050128000011540020400394003919996320020160010201600002048000040039400391116002110910101600001000100268311916211191940036207160000104004040040400404004040040