Apple M1 Microarchitecture Research by Dougall Johnson

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

SMLAL2 (by element, 4S)

Test 1: uops

Code:

  smlal2 v0.4s, v1.8h, 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
10043037230006125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037220006125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037230006125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037220006125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037230006125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037230006125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372200010525482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372300010325482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037230006125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037230006125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  smlal2 v0.4s, v1.8h, 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)03181e1f3a3f4e51inst 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)9fa8acc5branch mispredict (cb)cdcfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500007682954825101001001000010010000500427731303001830037300372827272874110100200100082003002430037300371110201100991001001000010000111717001600296961100001003003830038300383003830038
10204301782241001612954825101001001000010010149500427867003001830084300372826532874510100200100002003000030037300371110201100991001001000010000000710121622296340100001003003830038300383003830038
10204300862250000612954825101001001000010010000500427867003001830037300372826532874510100200100002003000030037300371110201100991001001000010010000710121622296340100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000000710121622296340100001003003830038300383003830038
10204300372240998812412954825101001001000010010149500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000000710121622296340100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731313001830037300372826532876410100200100002003000030037300371110201100991001001000010000000710121622296340100001003003830038300383003830038
102043003722500002322954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000001710121622296340100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000000710121622296340100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000000710131622296340100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000000710121623296340100001003003830038300383003830038

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)9fa6a8a9acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000640216322963010000103003830038300383003830038
1002430037224061295482510010101000010100005042786701300183008430132282873287671001020100002030000300373003711100211091010100001000000640224222963010000103003830038300383003830038
10024300372250950295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000640237222963010000103003830038300383003830038
1002430037224061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
10024300372240156295482510010101000010100005042773130300183003730037282873287671001020101632030000300373008421100211091010100001000000640216222963010000103003830038300383003830038
10024300372250726295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001030000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  smlal2 v0.4s, v0.8h, 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)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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722466129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722406129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102021009910010010000100137101161129634100001003003830038300383003830038
102043003722408229548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038

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)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)9fa0a6a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722506129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000000640316332963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000100640316332963010000103003830038300383003830038
100243003722406129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000000640316332963010000103003830038300383003830038
1002430037224093529548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000000640316332963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000000640316332963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000000640316332963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000000640316332963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000000640316332963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000000640316332963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000000640316332963010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  smlal2 v0.4s, v1.8h, 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)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)9fa8a9acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372330000046162954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010010240071011611296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000060071011611296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
10204300372250000061295482510100100100241001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000090071011611296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000030071011611296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001001030071011611296340100001003003830038300383003830038
1020430037225010007262954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000120071011611296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000060071011611296340100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100001650071011611296340100001003003830038300383003830038

1000 unrolls and 10 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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500002401612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000002906403162229630010000103003830038300383003830038
10024300372240000000612954825100101010000101000050427731313001830037300372828732876710159201000020300003003730037111002110910101000010000120006402162229630010000103003830038300383003830038
10024300372250000000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
1002430037225000024001562954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
100243003722500001500612954825100101010000101000050427731303001830037300372828732876710010201000020300003008030037111002110910101000010000000006402162229630010000103003830038300383003830038
100243003722500003300612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
100243003722400001500612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
100243003722500001500612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
100243003722500001500612954825100101010000101000050427731303001830037300372828732876710010201000020300003013030085111002110910101000010000000006402162229630010000103003830038300383003830038
1002430037225000018006129548251001010100001010000504277313030018300373003728287172876710010201000020300003003730037111002110910101000010000000006402162229630010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  smlal2 v0.4s, v8.8h, v9.h[1]
  movi v1.16b, 0
  smlal2 v1.4s, v8.8h, v9.h[1]
  movi v2.16b, 0
  smlal2 v2.4s, v8.8h, v9.h[1]
  movi v3.16b, 0
  smlal2 v3.4s, v8.8h, v9.h[1]
  movi v4.16b, 0
  smlal2 v4.4s, v8.8h, v9.h[1]
  movi v5.16b, 0
  smlal2 v5.4s, v8.8h, v9.h[1]
  movi v6.16b, 0
  smlal2 v6.4s, v8.8h, v9.h[1]
  movi v7.16b, 0
  smlal2 v7.4s, v8.8h, 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)03041e3a3f51inst 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)9fa0a8a9acc2cfd5d6daddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16020420089150000102258010010080000100800005006400000120045200642006432280100200800002002400002006420064111602011009910010016000010000000101122160222006101600001002006520065200652006520065
160204200641500001022580100100800001008000050064000000200452006420064102280100200800002002400002006420064111602011009910010016000010001000101122160222006101600001002006520065200652006520065
1602042006415000062258010010080000100800005006400000020045200642006432280100200800002002400002006420064111602011009910010016000010001202101122160222006101600001002006520065200652006520065
16020420064150000127258010010080000100800005006400000020045200642012132280100200800002002400002006420064111602011009910010016000010000000101122160222006101600001002006520065200652006520065
1602042006415000039258010010080000100800005006400000120045200642006432280100200800002002400002006420064111602011009910010016000010000000101122160222006101600001002006520065200652006520065
1602042006415000039258010010080000100800005006400000020045200642006432280100200800002002400002006420064111602011009910010016000010000000101122160222006101600001002006520065200652006520065
1602042006415000039258012410080000100800005006400000020045200642006432280100200800002002400002006420064111602011009910010016000010000000101122160222006101600001002006520065200652006520065
1602042006415000139258010010080000100800005006400000020045200642006432280100200800002002400002006420064111602011009910010016000010000000101122160222006101600001002006520065200652006520065
1602042006415000039258010010080000100800005006400000020045200642006432280100200800002002400002006420064111602011009910010016000010000000101122160222006101600001002006520065200652006520065
1602042006415000039258010010080000100800005006400000020045200642006432280100200800002002400002006420064111602011009910010016000010000000101122160222006101600001002006520065200652006520065

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03181e1f3f51inst 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)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16002420077150000108258001212800001280000626400000120031020050200503228001220800002024000020046200461116002110910101600001000100353111521211121320047230160000102005120051200512005120051
16002420050150000129258001212800001280000626400001120027020046200463228001220800002024000020046200461116002110910101600001009610038311820211131420113215160000102004720047200472004720047
1600242004615000045258001212800001280000626400001120027020046200463228001220800002024000020046200461116002110910101600001000100353121420211151020043215160000102004720047200512004720047
1600242004615000051258001212800001280000626400000120031020050200503228001220800002024000020050200461116002110910101600001000100373111220211111220043215160000102005120047200472004720047
1600242004615000045258001212800001280000626400001120027020046200463228001220800002024000020046200461116002110910101600001000100333111420211131120043215160000102004720047200472004720047
1600242004615000045258001212800001280000626400001120027020046200463228001220800002024000020046200461116002110910101600001040100333111520211121420043215160000102004720047200472004720047
16002420046150000659258001212800001280000626400001120027320046200463228001220800002024000020046200461116002110910101600001003100353111420211111220043215160000102004720047200472004720047
16002420046150000560258001212800001280000626400001120027020046200463228001220800002024000020046200461116002110910101600001000100363111220211101220043215160000102004720047200472004720047
1600242004615000045258001212800001280000626400001120027020046200463228001220800002024000020046200461116002110910101600001000100353111220211121220043215160000102004720047200472004720047
160024200461500004525800121280000128000062640000112002702004620046322800122080000202400002004620046111600211091010160000100010037311122021181020043215160000102004720047200472004720047

Test 6: throughput

Count: 12

Code:

  smlal2 v0.4s, v12.8h, v13.h[1]
  smlal2 v1.4s, v12.8h, v13.h[1]
  smlal2 v2.4s, v12.8h, v13.h[1]
  smlal2 v3.4s, v12.8h, v13.h[1]
  smlal2 v4.4s, v12.8h, v13.h[1]
  smlal2 v5.4s, v12.8h, v13.h[1]
  smlal2 v6.4s, v12.8h, v13.h[1]
  smlal2 v7.4s, v12.8h, v13.h[1]
  smlal2 v8.4s, v12.8h, v13.h[1]
  smlal2 v9.4s, v12.8h, v13.h[1]
  smlal2 v10.4s, v12.8h, v13.h[1]
  smlal2 v11.4s, v12.8h, 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)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)9fa0a1a8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
12020430157230006102512010010012000010012000050099000003002030039300391497303149971201002001200002003600003003931739111202011009910010012000010000000761011611300361200001003004030040300403004030040
12020430039225004102512010010012000010012000050096000003002030039300391497303149971201002001200002003600003003931736111202011009910010012000010000000761011611300361200001003004030041300403004030040
12020430039225014102512010010012000010012000050096000003002030039300391497303149971201002001200002003600003003930922111202011009910010012000010000000761011611300361200001003004030040300403004030042
12020430039225014102512010010012000010012000050096000013002030039300391497303149971201002001200002003600003003931736111202011009910010012000010000000761011611300361200001003004030040300413004030040
12020430039225004102512010010012000010012000050096000003002030039300391497303149971201002001200002003600003256230039111202011009910010012000010000000761011611300361200001003004030040300403004030040
12020430039225004202512010010012000110012000050096000003002030039300391497303149971201002001200002003600003173630039111202011009910010012000010000000761011611300361200001003004030040300403004030041
12020430039224004102512010010012000010012000050096000003002130039300391497303149971201002001200002003600003003931736111202011009910010012000010000000761011611300361200001003004030040300403004030040
12020430039238004102512010010012000010012000050096000003002030039300391497303149971201002001200002003600003003930039111202011009910010012000010000000761011611300361200001003004030040300403004030040
12020430039225004102512010010012000010012000050099000003002130039300391497303149971201002001200002003600003003931753111202011009910010012000010000000761011611300361200001003004130040300403173730040
12020430040225004102512010010012000010012000050096000003175630039300391497303149971201002001200002003600003003930039111202011009910010012000010000000761011611300361200001003004030040300403004030041

1000 unrolls and 10 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)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)9fa6a7a8a9acc2cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1200243004022503546025120010101200001012000050960000115300203003930039149963150191200102012000020360000300393004111120021109101012000010000000752283161631155300360155120000103004030040300403004030040
1200243003922500460251200101012000010120000509600001153002030039300391499631501912001020120000203600003003930039111200211091010120000100010000752283161671167300360155120000103004030040300403004030040
120024300392250046025120010101200001012000050960000115300203003930039149963150191200102012000020360000300393004211120021109101012000010000000752283161671185300360155120000103004030040300403004030040
120024300392250046025120010101200001012000050960000115300203003930039149963150191200102012000020360000300393003911120021109101012000010000000752283161631157300360155120000103004030040300403004030040
120024300392240046025120010101200001012000050960000115300203003930039149963150191200102012000020360000300393003911120021109101012000010000000752283161631189300360155120000103004030040300403004030040
120024300392250046025120010101200001012000050960000115300203003930039149963150191200102012000020360000300393004011120021109101012000010000000752283171671167300360155120000103004030040300403004030040
120024300392250046025120010101200001012000050960000115300203003930039149963150191200102012000020360000300393004111120021109101012000010000000752283171671166300360155120000103004030040300403004030040
120024300392250046025120010101200001012000050960000105300203003930039149963150191200102012000020360000300393003911120021109101012000010000000752283171661165300360155120000103004030040309233004030040
120024300392250046025120010101200001012000050960000115300203003930039149963150191200102012000020360000300393174311120021109101012000010000000752283171651176300360155120000103004030040300403004030040
120024300392250046025120010101200001012000050960000115300203003930039149963150191200102012000020360000300393004011120021109101012000010000000752283151631168300360155120000103004030923300403004030040