Apple M1 Microarchitecture Research by Dougall Johnson

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

MLS (vector, 4S)

Test 1: uops

Code:

  mls 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)031e3f4e51inst 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)a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372206125482510001000100039831330183037303724153289510001000300030373037111001100000073216112630100030383038303830383038
100430372306125482510001000100039831330183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
100430372306125482510001000100039831330183037303724153289510001000300030373037111001100000073116112630100030383038303830383085
100430372206125482510001000100039831330183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
100430372206125482510001000100039831330183037303724153289510001000300030373037111001100001073116112630100030383038303830383038
100430372206125482510001000100039831330183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
100430372306125482510001000100039831330183037303724153289510001000300030373037111001100000373116112630100030383038303830383038
100430372306125482510001000100039831330183037303724153289510001000300030373037111001100001073116112630100030383038303830383038
1004303723010525482510001000100039831330183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
100430372206125482510001000100039831330183037303724153289510001000300030373037111001100000073116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  mls 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)03191e3a3f4e51inst 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)9fa0a8accfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000142529548251010010010000100100005004277313030018030037300372826532874510100200100002003000030037300371110201100991001001000010000371013162229634100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313130018030037300372826582874510100202101652003000030037300371110201100991001001000010000286371012162229634100001003003830038300383003830038
10204300372250906129548251010010010000104101495004278594030018030085300372826932874510100200100002003000030037300371110201100991001001000010000071012162229634100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313030018030037300372826532874510100200100002003000030037300371110201100991001001000010000071012162229634100001003003830038300383003830038
102043003722500072629548251010010010000100100005004277313130018030037300372826532874510100200100002003000030037300371110201100991001001000010000071213162329634100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313030018030037300372826582874510100204100002003000030037300371110201100991001001000010002073212163229670100001003003830038300383003830038
10204300372250016129548251010010010000100100005004277313030018030037300372826532874510100200100002003000030037300371110201100991001001000010001371012163229634100001003003830038300383003830038
102043003722403010329548251010010010000100100005004277313030018030037300372826532874510100200100002003000030037300371110201100991001001000010000071012162229634100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313030018030037300372826532874510100200100002003000030182300371110201100991001001000010000371012162229634100001003003830038300383003830038
10204300372240006129548251010010010000100100005004277313030018030037300372826532874510100200100002003000030037300371110201100991001001000010000071012162229634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0308090b181e3f4e51inst 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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216232963010000103003830038300383003830038
100243003722500000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037224000006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000103130640216232963010000103003830038300383003830038
100243003722401100612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640316222963010000103003830038300383003830038
100243003722500000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010002640216222963010000103003830038300383003830038
100243003722500000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216232963010000103003830038300383003830038
100243003722500000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  mls 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)030e1e3f4e51inst 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)9fc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
10204300372250361295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
1020430037225150726295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
10204300372250076295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03041e3f4e51inst 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430084225107912954825100101010000101000050427731313001830037300372829232876710010201016820304893003730037111002110910101000010106405162229630010000103003830038300383003830038
1002430037225001032954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038
100243003722500612954825100101010000101000050427731303001830079300372828732876710010201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038
1002430037225001032954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038
100243003722500612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038
100243003722500612954825100101010000101000050427731303001830037300372828732876710610201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038
100243003722500612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038
10024300372250225612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038
100243003722500612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038
1002430037225033612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  mls 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)03080b191e1f3f4e51inst 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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250003300612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
10204300372250002670612954825101001001000010010000500427731303001830037300372826532881310100200101802003000030037300371110201100991001001000010000271011611296340100001003003830038300383003830038
10204300372250003360612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
10204300372250002880612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
10204300372240003810612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
10204300372250003330612954825101001001000010010000500427731313001830037300372826532874510561200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
102043003722400000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
10204300372250003570612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
10204300372250003000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03091e3f4e51inst 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)9fa8cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722523936129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000640316332963010000103003830038300383003830038
100243003722503156129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000640316332963010000103003830038300383003830038
100243003722503306129548251001010100001010000504277313300183003730037282873287671001022100002030000300373003711100211091010100001000640316342963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000640316332963010000103003830038300383003830038
100243003722503516129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000640316332963010000103003830038300383003830038
100243003722403456129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000640316332963010000103003830038300833003830038
100243003722403426129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000640316332963010000103003830038300383003830038
100243003722503096129548251001010100001010000504277313300183003730037282873288231001020100002030000300373003711100211091010100001000640316332963010000103003830038300383003830038
100243003722502706129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000640316332963010000103003830038300383003830038
100243003722503246129548251001010100001210000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000640316332963010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  mls v0.4s, v8.4s, v9.4s
  movi v1.16b, 0
  mls v1.4s, v8.4s, v9.4s
  movi v2.16b, 0
  mls v2.4s, v8.4s, v9.4s
  movi v3.16b, 0
  mls v3.4s, v8.4s, v9.4s
  movi v4.16b, 0
  mls v4.4s, v8.4s, v9.4s
  movi v5.16b, 0
  mls v5.4s, v8.4s, v9.4s
  movi v6.16b, 0
  mls v6.4s, v8.4s, v9.4s
  movi v7.16b, 0
  mls 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): 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)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)9facc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16020420065150039258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
16020420064150039258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
1602042006415018339258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
16020420064150939258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
1602042006415031239258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
1602042006415030339258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
16020420064150039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
16020420064150039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
1602042006415048639258010010080000100800005006400000200452006420064343801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
16020420064151039258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2507

retire (01)cycle (02)0307090a191e3a3f51inst 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)9fa0a6a8accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1600242007415020201506627800121280000128000062640000112003220051200513228001220800002024000020051200511116002110910101600001000001004231117271112020200482201160000102005420054200542005220052
160024200511510000005127800121280000128000062640000112003220051200513228001220800002024000020051200511116002110910101600001000001004231123251111820200482201160000102005220052200522005420054
1600242005315010002704527800121280000128000062640000112003420051200513228001220800002024000020051200511116002110910101600001000001004431123272112118200502211160000102005220052200522005220052
1600242005115010001204527800121280000128000062640884112003220051200513228001220800002024000020053200531116002110910101600001000001004131118252111718200482211160000102005420052200522005220054
1600242005115030201206927800121280000128000062640000112003420051200513228032420800002024000020051200511116002110910101600001000001004431119252111922200502201160000102005420052200522005220054
1600242005315020214290572780012128000012800006264000011200342005120053322800122080000202400002005120053111600211091010160000100004851004031118271111617200502201160000102005220052201432005420052
16002420051150101039005727800121280000128000062640000112003220051200513228001220800002024000020051200511116002110910101600001000001004031120252111516200502211160000102005420054200522005220052
1600242005115020202404527800121280000128000062640000112003420051200513228001220800002024000020051200511116002110910101600001000001004031122271111516200502202160000102005220052200612005220063
160024200511501020005729800121280000128000062640000112004320062200623228001220800002024000020051200511116002110910101600001000001004262216252211616200482402160000102006120052200612005220052
160024200601502000005129800121280000128000062640000012004120051200623228001220800002024000020051200511116002110910101600001000001004432120274221919200482412160000102006320063200612006120052

Test 6: throughput

Count: 16

Code:

  mls v0.4s, v16.4s, v17.4s
  mls v1.4s, v16.4s, v17.4s
  mls v2.4s, v16.4s, v17.4s
  mls v3.4s, v16.4s, v17.4s
  mls v4.4s, v16.4s, v17.4s
  mls v5.4s, v16.4s, v17.4s
  mls v6.4s, v16.4s, v17.4s
  mls v7.4s, v16.4s, v17.4s
  mls v8.4s, v16.4s, v17.4s
  mls v9.4s, v16.4s, v17.4s
  mls v10.4s, v16.4s, v17.4s
  mls v11.4s, v16.4s, v17.4s
  mls v12.4s, v16.4s, v17.4s
  mls v13.4s, v16.4s, v17.4s
  mls v14.4s, v16.4s, v17.4s
  mls 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): 0.2502

retire (01)cycle (02)03070a18191e1f373a3f4e51inst 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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16020440059300110015901724802516010010016000010016000050012800000400200400404003920033320009160100200160000200480000400394003911160201100991001001600001000001011413161612400361600001004004040049400404004040040
1602044003930011000002480251601001001600001001600005001280000040020040039400391997331999816010020016000020048000040039400391116020110099100100160000100000101146161415400371600001004004040040400404004040050
160204400393001100001727902516011710016000010016000050012800000400300400394003919973320007160100200160000200480000400394004811160201100991001001600001000001011415161214400361600001004004040040400404004040040
1602044003930011000002580251601001001600001001600005001280000040021040048400391997331999716010020016000020048000040049400491116020110099100100160000100060101141216813400461600001004005040050400504004040040
16020440039300110060024802516010010016001710016000050023989991400200400394003919973319997160100200160000200480000400494004911160201100991001001600001000001011413161413400361600001004004040040400404004040049
1602044003930011000002480251601001001600001001600005002438865140020040039400491998431999716010020016000020048000040039400481116020110099100100160000100000101141516147400361600001004004040050400404004040040
160204400393001100001248025160100100160001100160000500128000004002004005140039199733199971601002001600002004800004003940039111602011009910010016000010000010114716711400461600001004004040050400504005040040
16020440040300110000024802516011710016000010016000050024388651400200400404003919973319997160100200160000200480000400394003911160201100991001001600001000001011413161316400361600001004005040050400504005040040
16020440049300110000024802516010010016000010016000050012800001400300400394003919973319997160100200160000200480000400394003911160201100991001001600001000001014013161215400361600001004004140040400404004040041
16020440049300110090024802516011810016001810016000050012800001400200400494003919973319997160100200160000200480000400394003911160201100991001001600001000001011415161513400361600001004005040050400504005040040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b18191e1f373f4e51inst 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)9fa0a1a8acc2cdcfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16002440049300000001752025160027101600001016000050128000011540029400484003919989320022160010201600002048000040049400401116002110910101600001000033001002482141642233400360305160000104004940040400404004040040
1600244003930000000055025160027101600171016000050239899901540033400484003919989320012160010201600002048000040039400481116002110910101600001000000010022331416212444004521510160000104059440653405814063940538
160024406063010991203792149189502171604401216106713161276551874846015404964067940584201025420341161139201614372048397540681406341111600211091010160000104204526201023611224118422464048013010160000104061440651405834063140602
1600244061430411011145288014221214233161215141610371116124160175283411540465406184063720097512030916156220161261204841014061040684111160021109101016000010000000100241122416422444004503010160000104004040040400494004940049
16002440048300000001756025160027101600171016000050128000011540030400484003919989320012160010201600002048000040039400481116002110910101600001000000010024113141621135400360305160000104004940040400494004040040
1600244003930000000175502516002710160017101600005023989991154002940039400481998932002116001020160000204800004004840040111600211091010160000100000001002282141622244400450156160000104004940040400404004940040
16002440039300000000520251600111016000010160000501280000015400304003940039199893200121600102016000020480000400484003911160021109101016000010000000100241131416422424004503010160000104004040049400404004940040
16002440048300000001752025160027101600171016000050128000011540029400394004819989320012160010201600002048000040039400481116002110910101600001000000010024832416422444003603010160000104004940040400404004940040
1600244003930000000052102516001010160017101600005012800000154002940048400391998932001216001020160000204800004003940048111600211091010160000100000001002282141621143400360155160000104004940040400494004040040
160024400393000000005202516001010160084101600005012800000154002040048400391998932001216001020160000204800004003940048111600211091010160000100000001002282141621155400450155160000104004940040400494004040040