Apple M1 Microarchitecture Research by Dougall Johnson

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

SMLSL (by element, 4S)

Test 1: uops

Code:

  smlsl v0.4s, v1.4h, v2.h[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)0318191e3f4e51inst 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
10043037220006125482510001000100039831313018303730372415328951000100030003037303711100110000073116312698100030383038303830383038
10043037230006125482510001000100039831303018303730372415328951000100030003037303711100110002073116112630100030383038303830383038
10043037220006125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037220006125482510001000100039831313018303730372415328951000100030003037303711100110000373116112630100030383038303830383038
10043037220006125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037230006125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037220006125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037230006125482510001000100039831303018303730372415328951000100030003037303711100110001073116112630100030383038303830383038
10043037220006125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037230006125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  smlsl v0.4s, v1.4h, v2.h[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)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)9fa0a1a6a8a9acc2branch mispredict (cb)cfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000000066295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000050300710021622296340100001003003830038300383003830038
10204300372250000000061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000010000710021622296340100001003003830038300383003830038
10204300372240000090082295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000030000710021623296340100001003003830038300383003830038
10204300372250000000061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000000710021622296340100001003003830082300383003830038
10204300372250000000061295482510100100100001041000052242773133001830037300372826532874510100204100002003000030037300371110201100991001001000010000000000710131622296340100001003003830038300383003830038
10204300372250000000061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000000710121622296340100001003003830038300383003830038
10204300372250000000094295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000000710121622296340100001003003830038300383003830038
10204300372250000000061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000000710121622296340100001003003830038300383003830038
10204300372250000000061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000000000710121622296340100001003003830038300383003830038
10204300372250000000061295482510100100100001001000050042773133001830037300852826532874510100200100002003000030037300371110201100991001001000010000000000710121622296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0308090b1e3f4e51inst 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)9fa8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
10024300372251110612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010030640316332963010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010100640316332963010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000103200640316332963010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313130018300373003728287242876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  smlsl v0.4s, v0.4h, v1.h[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)0308191e1f3f4e51inst 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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038
102043003722400001187295094510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773130300183003730037282653287451010020010000200305043008530037111020110099100100100001000000007101161129634100001003003830038300383003830038
10204300372250300321295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038
1020430037225000061295484410100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038
10204300372250012061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000007101161129634100001003003830218300383003830038
1020430037225000061295482510100100100001001000050042773131300183003730084282656287451010020010000200300003003730037111020110099100100100001004000007101161129634100001003003830038300383003830038

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)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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372258229548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100640316222963010000103003830038300383003830038
100243003722547229548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100640216222963010000103008630121300863018030038
100243003722516629548251001010100001010000504277313030018300843003728287328767100102010000203000030037300371110021109101010000100640216222963010000103003830038300383003830038
100243003722518729548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100640216222963010000103003830038300383003830038
100243003722578929548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100640216222963010000103003830038300383003830038
10024300372256129548251001911100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100640216222963010000103003830038300383003830038
100243003722516629548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100640216222963010000103003830038300383003830038
10024300372258229548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000103640216222963010000103003830038300383003830038
100243003722410329548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100640216222963010000103003830038300383003830038
100243003722521029548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100640216222963010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  smlsl v0.4s, v1.4h, v0.h[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)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)9fa8acc5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250010529548251010010010000100100005004277313130018300373003728265032874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
10204300372250014529548251010010010000100100005004277313030018300373003728265032874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
10204300372250012429548251010010010000100100005004277313030018300373003728265032874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
10204300372250014529548251010010010000100100005004277313130018300373003728265032874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
10204300372250012429548251010010010000100100005004277313130018300373003728265032874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
10205300372250012429548251010010010000100100005004277313030018300373003728265332874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
1020430037225008229548251010010010000100100005004277313030018300373003728265032874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
10204300372250016829548251010010010000100100005004277313030018300373003728265032874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
10204300372240010329548251010010010000100100005004277313030018300373003728265032874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
10204300372250016629548251010010010000100100005004277313030018300373003728265032874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b191e3a3f4e51inst 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)9fa0a6a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250002662954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000006441216121229630010000103003830038300383003830038
1002430037225000217802954825100101010000101000050427731313001830037300372828732876710010201016220305043008430085211002110910101000010000406671116111129630010000103008630038300383003830038
100243003722500026629530451001911100081010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000064491613929630010000103003830038300383003830038
10024300372250002108295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000644111661129630010000103003830038300383003830038
10024300372250002662954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000006441116111229630010000103003830080300383003830038
1002430037225000266295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000644111612729630010000103003830038300383003830038
10024300372250002261295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000644616111129630010000103003830038300383003830038
10024300372250002662954825100211010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000006446169929630010000103003830038300383003830038
1002430037225000266295482510019101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000644111661129630010000103003830038300383003830038
10024300372250002662954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000006441316121229630010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  smlsl v0.4s, v8.4h, v9.h[1]
  movi v1.16b, 0
  smlsl v1.4s, v8.4h, v9.h[1]
  movi v2.16b, 0
  smlsl v2.4s, v8.4h, v9.h[1]
  movi v3.16b, 0
  smlsl v3.4s, v8.4h, v9.h[1]
  movi v4.16b, 0
  smlsl v4.4s, v8.4h, v9.h[1]
  movi v5.16b, 0
  smlsl v5.4s, v8.4h, v9.h[1]
  movi v6.16b, 0
  smlsl v6.4s, v8.4h, v9.h[1]
  movi v7.16b, 0
  smlsl v7.4s, v8.4h, v9.h[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)0318191e3f51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602042006515000081258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100001011131611200611600001002006520132200652006520065
1602042006415100081258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
1602042006415000039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
1602042006415000039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
16020420064151000463258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
1602042006415000039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
16020420064150001239258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
1602042006415000039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
1602042006415000039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
16020420064150000771258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065

1000 unrolls and 10 iterations

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

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)5f60696b6d6escheduler 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)e0? int output thing (e9)eaec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1600242007415004527800121280000128000062640000112003202005120051322800122080000202400002005120051111600211091010160000100010029311122521159202352201160000102005220052200522005220052
16002420051150045278001212800001280000626400001120032020051200513228001220800002024000020051200511116002110910101600001000100323111025211106202432201160000102005220052200522005220052
1600242005115001082780012128000012800006264000011200320200512005132280012208000020240000200512005111160021109101016000010001003231152521159202082201160000102005220052200522005220052
16002420060150015427800121280000128000062640000112003202005120051322800122080000202400002005120051111600211091010160000100010028311102521169202262201160000102005220052200522005220052
160024200511500458880012128000012800006264000011200320200512005132280012208000020240000200512005111160021109101016000010001002831192521199202182201160000102005220052200522005220052
1600242005115006827800121280000128000062640000112003202005120051322800122080000202400002005120051111600211091010160000100010032311102521159202112201160000102005220052200522005220052
1600242005115003932780012128000012800006264000011200320200512005132280012208000020240000200512005111160021109101016000010101003231153421195202042201160000102005220052200522005220052
160024200511500452980012128000012800006264000011200320200512005132280012208000020240000200512005111160021109101016000010001002831152521159202042201160000102005220052200522005220052
1600242005115003652780012128000012800006264000011200320200512005132280012208000020240000200512005111160021109101016000010001002831162521159202072201160000102005220052200522005220052
1600242005115001087680012128000012800006264000011200320200512005132280012208000020240000200512005111160021109101016000010001003231172521159202062201160000102005220052200522005220052

Test 6: throughput

Count: 12

Code:

  smlsl v0.4s, v12.4h, v13.h[1]
  smlsl v1.4s, v12.4h, v13.h[1]
  smlsl v2.4s, v12.4h, v13.h[1]
  smlsl v3.4s, v12.4h, v13.h[1]
  smlsl v4.4s, v12.4h, v13.h[1]
  smlsl v5.4s, v12.4h, v13.h[1]
  smlsl v6.4s, v12.4h, v13.h[1]
  smlsl v7.4s, v12.4h, v13.h[1]
  smlsl v8.4s, v12.4h, v13.h[1]
  smlsl v9.4s, v12.4h, v13.h[1]
  smlsl v10.4s, v12.4h, v13.h[1]
  smlsl v11.4s, v12.4h, v13.h[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)031e373f4e51inst 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)9fa8branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1202043174822503561671325120100100120000100120000500960000130020031748300391497331499712010020012000020036000030039317481112020110099100100120000100007610216113003601200001003174930040317493004031749
1202043004022500880251201001001200001001200005004399524130903030039317481665331595512010020012000020036000030039317481112020110099100100120000100007682116113174501200001003004031749300403174930040
12020430039238002316713251201181001200181001200005004399524131729031748300391497331670612010020012000020036000031748300391112020110099100100120000100007610116113174501200001003004031749300403004030040
120204300392250042671325120118100120018100120000500990000131729031748300391497331499712010020012000020036000030039300401112020110099100100120000100007610116113174501200001003174930040300403004031749
120204317482250141671325120118100120018100120000500960000030020030039300401497331596812010020012000020036000030039317481112020110099100100120000100007610116113174501200001003004030040300413004030041
120204317482250061025120100100120000100120000500990000130021031748300391497331596812010020012000020036000030039317481112020110099100100120000100007610116113003701200001003174930040300413004031749
120204317482250041025120100116120000100120000500960000130020030039300401665331596812010020012000020036000030040300391112020110099100100120000100007610116113003601200001003004030041300403004030041
120204317482250041671325120100100120018100120000500960000130020030039300421497331499712010020012000020036000031748300391112020110099100100120000100007610116113003601200001003004030041300403004130040
120204300392380041671325120118100120018100120000500960000130020030039300401497331499712010020012000020036000030039317481112020110099100100120000100007610116113174501200001003174930040317493004030041
120204300402253041671325120101100120018100120000500960000031729030040300391497331499712010020012000020036000030039317481112020110099100100120000100007610116113003601200001003004031749300403174930040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0308191e373f4e51inst 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)6061696d6edispatch 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)9fa6a7a8accfd2d5d6dbddinst fetch restart (de)e0? int output thing (e9)eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
12002430338229000110302512001010120000101200005043995240030020300393003914996031501912001020120000203600003003930039111200211091010120000100000752002160543003600120000103004030040309233004030041
120024309222250000101902512001110120001101200005043940610030020300403003914996031501912001020120000203600003003930040111200211091010120000100000752006160353003600120000103004030040300403004030040
12002430040238000090302512001010120000101200005042834000030020300393003914996031501912003420120000203600003003930039111200211091010120000100010752004160283003600120000103004030923300403174930923
120024300392250000400251200101012000010120000509600000030020300393003914996031501912001020120000203600003003930039111200211091010120000100000752003160533003600120000103004030923300413175130040
120024309222250000400251200101012000010120000509600000030020300393003914996031501912001020120000203600003003930039111200211091010120000100000752004160493003600120000103092330040300403092330040
120024309222250000400251200101012000010120000509600000030020300393003914996031501912001020120000203600003003930039111200211091010120000100000752003160443003600120000103004030040300403004030041
1200243003922500004002512001010120000101200005096000000317313003930039149960315019120010201200002036000030039300391112002110910101200001000007520071601043003600120000103004130041317513004030040
120024300392250000400251200101012000010120000509600000031731309223004015850031501912001020120000203600003092230039111200211091010120000100000752006160343003900120000103004030040300413004030041
120024300392250000400251200101012000010120000509600000030020300393003914996031501912001020120000203600003003930039111200211091010120000100000752003160453003600120000103004130041300413004031749
1200243175022500017050251200101012000010120000509900000030903309223003914996031501912001020120000203600003003930922111200211091010120000100000752004160453003600120000103004030040300403004030040