Apple M1 Microarchitecture Research by Dougall Johnson

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

UMLSL2 (vector, 2D)

Test 1: uops

Code:

  umlsl2 v0.2d, 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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037230612548251000100010003983133018303730372415328951000100030003037303711100110000073216222630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100030003037303711100110000073216222630100030383038303830383038
100430372301242548251000100010003983133018303730372415328951000100030003037303711100110000073216222630100030383038303830383038
1004303723102612548251000100010003983133018303730372415328951000100030003037303711100110000073216222630100030383038303830383038
10043037220822548251000100010003983133018303730372415328951000100030003037303711100110000073216222630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100030003037303711100110000073216222630100030383038303830383038
10043037220612548251000100010003983133018303730372415328951000100030003037303711100110000073216222630100030383038303830383038
100430372212612548251000100010003983133018303730372415328951000100030003037303711100110000073216222630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100030003037303711100110000073216222630100030383038303830383038
100430372302272548251000100010003983133018303730372415328951000100030003037303711100110000073216222630100030383038303830383038

Test 2: Latency 1->1

Code:

  umlsl2 v0.2d, 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)03080b18191e1f3a3f4e51inst 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)9fa0a1a8a9accfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000000710121622296340100001003003830038300383003830038
10204300372250000000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000000710121622296340100001003003830038300383003830038
10204300372250000000612954825101001001000010010000500427731313001830226300372826532874510100200100002003000030037300371110201100991001001000010000000710131622296340100001003003830038300383003830038
10204300372240000000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000000710131622296340100001003003830038300383003830038
10204300372250000001612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000000710121622296340100001003003830038300853003830038
102043003722500002700612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000000710121622296340100001003003830038300383003830038
10204300372250000000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000000710121622296340100001003003830038300383003830038
102043003722500000001032954825101001001000010010000500427731303001830037300372827232874510100200100002003000030037300371110201100991001001000010000000710121632296340100001003003830038300383003830038
10204300372250000001612953063101221061001610510149533427867003005430085300842826982876310251208103352063099630131301323110201100991001001000010000002820733122422296863100001003013330135301333013430085
102043008522601212341920766295031641016512010048110108946104285455030270303573013128292312887411017224111592263295830358303237110201100991001001000010020121933885513127242985011100001003037030371303753036930401

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03181e1f3f4e51inst 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)9fa0a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225054061295482510010101000010100005042773131300180300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773131300180300373003728297328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
1002430037225015061295482510010101000010100005042773131300180300373003728287328767100102010000203000030037300371110021109101010000100000640216232963010000103003830038300383003830038
100243003722406061295482510010101000010100005042773131300180300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
1002430037225042061295482510010101000010100005042773131300180300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773131300180300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
1002430037225012061295482510010101000010100005042773131300180300373003728314328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
1002430037225024061295482510010101000010100005042773131300180300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773131300180300373003728287328767100102010000203000030037300371110021109101010000100000640216322963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773131300180300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  umlsl2 v0.2d, 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)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)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)9fa1a6a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250005706129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000071011611297060100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313300183003730037282653287451010020010664200300003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
1020430037224000006129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
10204300372250008406129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000371011611296340100001003003830038300383003830038
10204300372250000072629548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
102043003722500093526129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000071011611296340100001003003830038300383008430038
1020430037225000006129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000000071011611296340100001003003830038300383008630038
102043003722500051019129548251010010010000126100005004277313300543003730037282653287451010020010165204300003003730037211020110099100100100001000000071011611296340100001003008530086300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b181e1f3f4e51inst 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)9fa1a6a8accdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500090612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000006402162229630010000103003830038300383003830038
1002430037225000300612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010001834306402162229630010000103003830038300383003830038
10024300372250003901032954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000006402162229630210000103003830038300383003830038
1002430037225000270612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000006402322229630010000103003830038300383003830038
1002430037225000150612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000006402162229630010000103003830038300383003830038
10024300372250002404412954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000006402162229630010000103003830038300383003830038
1002430037225000002512954825100101010000101000050427731303001830037301792828732876710010201000020300003003730037111002110910101000010001006402162229630010000103003830038300383003830038
10024300372250001201032954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000006402162229630010000103003830038300383003830038
1002430037225000330612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000006402162229630010000103003830038300383003830038
1002430037225000240612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000006402162229630010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  umlsl2 v0.2d, 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)03081e3f4e51inst 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)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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250061295482510100100100001001000050042773133001803003730037282650328745101002001000020030000300373003711102011009910010010000100007103161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773133001803003730037282650328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773133001803003730037282650328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773133001833003730037282650328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773133001803003730037282650328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773133001803003730037282650328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773133001803003730037282650328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773133001803003730037282650328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372240061295482510100100100001001000050042773133001803003730037282650328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773133001803003730037282650328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038

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)9fa0a6a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010030006402162229630010000103003830038300383003830038
10024300372250612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000006402162229630010000103003830082300383003830038
10024300372250612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000006402162229630010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000006402162229630010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000006402162229630010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000006402162229630010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000006402162229630010000103003830038300383003830038
10024300372250612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000006402162229630010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000006402162229630010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000006402162229630010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  umlsl2 v0.2d, v8.4s, v9.4s
  movi v1.16b, 0
  umlsl2 v1.2d, v8.4s, v9.4s
  movi v2.16b, 0
  umlsl2 v2.2d, v8.4s, v9.4s
  movi v3.16b, 0
  umlsl2 v3.2d, v8.4s, v9.4s
  movi v4.16b, 0
  umlsl2 v4.2d, v8.4s, v9.4s
  movi v5.16b, 0
  umlsl2 v5.2d, v8.4s, v9.4s
  movi v6.16b, 0
  umlsl2 v6.2d, v8.4s, v9.4s
  movi v7.16b, 0
  umlsl2 v7.2d, 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)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)696d6escheduler 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
16020420089150000392580100100800001008000050064000020045200642006432280100200800002002400002006420064111602011009910010016000010003010111516112006101600001002006520065200652006520065
1602042006415100070425801001008000010080000500640000200452006420064322801002008000020024000020064200641116020110099100100160000100420010111116112006101600001002006520065200652006520065
160204200641500003925801001008000010080000500640000200452006420064322801002008000020024000020064200641116020110099100100160000100380010111116112006101600001002006520065200652006520065
16020420064150000392580100100800001008000065464000020045200642006432280100200800002002400002006420064111602011009910010016000010000010111116112006101600001002006520065200652006520065
1602042006415000039258010010080000100800005006400002004520064200643228010020080000200240000200642006411160201100991001001600001001612010111116112006101600001002006520065200652006520065
160204200641500003925801001008000010080000500640000200452006420064322801002008000020024000020064200641116020110099100100160000100180010111116112006101600001002006520065200652006520065
16020420064150000392580100100800001008000050064000020045200642006432280100200800002002400002006420064111602011009910010016000010000010111116112006101600001002006520065200652006520065
1602042006415000039258010010080000100800005006400002004520064200643228010020080000200240000200642006411160201100991001001600001000129010111116112006101600001002006520065200652006520065
16020420064150000392580100100800001008000062664000020045200642006432280100200800002002400002006420064111602011009910010016000010000010111116112006101600001002006520065200652006520065
16020420064151000392580100100800001008000050064000020045200642006432280100200800002002400002006420064111602011009910010016000010000010111116112006101600001002006520065200652006520065

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)5f6061696d6escheduler 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
1600242007415005127800121280000128000062640000005200322005120051322800122080000202400002005120051111600211091010160000101731002731162521166200482201160000102005220052200522005220065
160024200511500452780012128000012800006264000011520032200512005132280012208000020240000200512005111160021109101016000010001002681142521143200482201160000102005220052200522005220087
1600242005115001502780012128000012800006264000010020032200512005132280012208000020240000200512005111160021109101016000010001002781142521166200482201160000102005220052200522005220065
160024200511500452780012128000012800006264000010520032200512005132280012208000020240000200512005111160021109101016000010131002982162521134200482201160000102005220052200522005220065
160024200511500452780012128000012800006264000010020032200512005132280012208000020240000200512005111160021109101016000010001002781142521176200482201160000102005220052200522005220065
160024200511500452780012128000012800006264000010020032200512005132280012208000020240000200512005111160021109101016000010001002681132521176200482201160000102005220052200522005220065
160024200511500452780012128000012800006264000010020032200512005132280012208000020240000200512005111160021109101016000010301003032142521144200482201160000102005220052200522005220065
1600242005115002352780012128000012800006264000010020032200512005132280012208000020240000200512005111160021109101016000010001002981142521176200482201160000102005220052200522005220087
160024200511500452780012128000012800006264000010020032200512005132280012208000020240000200512005111160021109101016000010001002632162521143200482201160000102005220052200522005220065
160024200511500452780012128000012800006264000011520032200512005132280012208000020240000200512005111160021109101016000010001002981132521176200482201160000102005220052200522005220087

Test 6: throughput

Count: 16

Code:

  umlsl2 v0.2d, v16.4s, v17.4s
  umlsl2 v1.2d, v16.4s, v17.4s
  umlsl2 v2.2d, v16.4s, v17.4s
  umlsl2 v3.2d, v16.4s, v17.4s
  umlsl2 v4.2d, v16.4s, v17.4s
  umlsl2 v5.2d, v16.4s, v17.4s
  umlsl2 v6.2d, v16.4s, v17.4s
  umlsl2 v7.2d, v16.4s, v17.4s
  umlsl2 v8.2d, v16.4s, v17.4s
  umlsl2 v9.2d, v16.4s, v17.4s
  umlsl2 v10.2d, v16.4s, v17.4s
  umlsl2 v11.2d, v16.4s, v17.4s
  umlsl2 v12.2d, v16.4s, v17.4s
  umlsl2 v13.2d, v16.4s, v17.4s
  umlsl2 v14.2d, v16.4s, v17.4s
  umlsl2 v15.2d, 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)0308090b18191e1f373a3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696b6d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602044007530000000001705400251601001001600171001600006051280000140020040039400711997332002916010020016000020048000040049400481116020110099100100160000100000000010110216114003701600001004004940040400404004940040
16020440039300000000000410251601611001600001001600005001280000040020040039400391997331999816010020016000020048000040040400391116020110099100100160000100000000010110116114004501600001004004040040400404004140041
16020440039300000000000420251601171001600171001600005002398999040020040039400481997331999816010020016000020048000040040400391116020110099100100160000100000000010110116114003601600001004004040050400404005040049
160204400493000000000170410251601171001600011001600005002399027140020040048400391997332000616010020016000020048000040039400401116020110099100100160000100000000010110116114004601600001004004040050400494004940040
1602044003930000000000050252516011710016001710016000050012800001400300400404004019973319998160100200160000200480000400394003911160201100991001001600001000000000101101161140096161600001004004040040400404004140040
160204400393000000000003260251601011001600011001600005001280000040030040039400481997331999716010020016000020048000040039400491116020110099100100160000100000000010110116114003601600001004004940049400404005040040
16020440039300000000010410251601001001600001001600005003157562040020040039400481997332000616010020016000020048000040049400391116020110099100100160000100000000010110116114003601600001004005040040400494004040040
16020440039300000000000500251601001001600001001600005002399027140021040039400481997331999716010020016000020048000040039400481116020110099100100160000100000000010110116114003701600001004004040041400404004140049
160204400393000000000170410251601171001600011001600005001280000140020040039400391997331999816010020016000020048000040049400481116020110099100100160000100000000010110116114003701600001004004040041400404004940040
16020440048300000000000420251601171001600011001600005002399027140020040040400481997331999816010020016000020048000040040400391116020110099100100160000100000000010110116114004601600001004004140040400414004040041

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030708090a0b18191e1f373f4e51inst 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)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)9fa1a6a8a9accdcfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16002440067300000000000055025160029101600001016000050131999911400204003940048199960320019160010201600002048000040048400711116002110910101600001000620601002431141621186400450209160000104004940072400404004040041
160024400393000000000240062025160016101600001016000050239899901400294003940071199960320028160010201600002048000040039400481116002110910101600001000610311002231181621146400360206160000104004940040400494004040040
1600244004830000000000017522525160070101600001016000050128000011400524003940048199960320028160010201600002048000040039400711116002110910101600001000640601002231161621146400460206160000104004140050400404004040049
16002440039300000000000052025160013101600171016000050128000011400204003940048199960320051160010201600002048000040039400481116002110910101600001000560601002232191621199400360206160000104004040049400404004940041
1600244004930000000000017560501600131016001710160413501280000114002940048401031999603200191600102016000020480000400394004811160021109101016000010005203010022311816211464004502018160000104005040040400494004940040
16002440039300000000000046025160029101600001016000050128000011400204003940048199960320028160010201600002048000040039400391116002110910101600001000001501002431261622164400360209160000104004040072400404004040040
16002440071300000000000171780251600151016001710160000501280000114002040039400391999603200191600102016000020480000400484003911160021109101016000010005201201002231191621185400450206160000104004940040400404004940040
160024400393000000000006146025160012101600001016000050128000011400524003940049199960320019160010201600002048000040071400391116002110910101600001000700601002231141621146400360209160000104004040072400404004040053
1600244004830000000000017582525160036101600001016000050128000011400214003940048199960320019160010201600002048000040039400481116002110910101600001000620601002231181621185400450208160000104004040049400404004940041
16002440039300000000000067025160013101600001016035750128000001400294004840039199960320028160010201600002048000040039400481116002110910101600001000520301002231161621178400360206160000104007240040400404004940041