Apple M1 Microarchitecture Research by Dougall Johnson

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

UMLAL2 (vector, 2D)

Test 1: uops

Code:

  umlal2 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)03081e3f4e51inst 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
10043037220010325482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037230015625482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
1004303722006125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037220010325482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037220010325482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
1004303723006125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
1004303723006125482510001000100039831303054303730372415328951000100030003037303711100110000073116112630100030383038303830383038
1004303723006125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
1004303723006125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
1004303723006125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  umlal2 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)031e3a3f4e51inst 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)9fa8a9accdcfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250015629548251010010010000100100005004277313030018300373003728265328745101002001000020030000300843003711102011009910010010000100000071212163229634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313030018300373003728284328745101002001000020030000300373003711102011009910010010000100000071012162229634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000071012162329634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004278171030018300373003728265328745101002001000020030000300373003711102011009910010010000100000071012163229634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100100071012162329634100001003003830038300383003830038
1020430037224006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000071012162229634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000071012162229634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000071012162229634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000071212162229634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000071012162229634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0307080a18191e1f3a3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000000061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000006404163229630010000103003830038300383003830038
10024300372250000000061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000006402162329630010000103003830038300383003830038
10024300372250000000061295122510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000006403162329630010000103003830038300383003830038
10024300372240000000061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000006403162329630010000103003830038300383003830038
10024300372250000000061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000006403163329630010000103003830038300383003830038
10024300372250000000061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000020006402163229630010000103003830038300383003830038
10024300372240000000061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000306403163329630010000103003830038300383003830038
10024300372250000000061295302510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000006402163329630010000103003830038300383003830038
10024300372250000000061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000006403163329630010000103003830038300383003830038
10024300372250000000061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000006403163329630010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  umlal2 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)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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773130300183003730037282653287611010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b1e1f3f4e51inst 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)9fa8a9acc2c5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000822954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000006402162229630010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000006402162229630010000103003830038300383003830038
100243003722500001032954825100101010000101000050427812513001830037300372828732876710010201000020300003003730037111002110910101000010000006402162229630010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313030018300373003728287262876710010201000020300003003730037111002110910101000010000006402162229630010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000006402162229630010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000006402162229630010000103003830038300383003830038
10024300372240000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000006402162229630010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000006402162229630010000103003830038300383003830038
10024300372240000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000006402162229630010000103003830038300383003830038
10024300802250000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000006402162229630010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  umlal2 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)03080b18191e1f3f4e51inst 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)9fa0a1a8acc5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000000710116112963400100001003003830038300383003830038
1020430037225000000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000000710116112963400100001003003830038300383003830038
1020430037225000000612954825101001001000810010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000000710116112963400100001003003830038300383003830038
1020430037224000000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000000710116112963400100001003003830038300383003830038
1020430037225000000612954825101001001000010010000500427731303001830037300372826532874510100200100002003054030037300371110201100991001001000010000030710116112963400100001003003830038300383003830038
1020430037225000000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000000710116112963400100001003003830038300383003830038
1020430037224000000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000000710116112963400100001003003830038300383003830038
1020430037224000000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000000710116112963402100001003003830038300383003830038
1020430037225000000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000000710116112963400100001003003830038300383003830038
1020430037224000000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000000710116112963400100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0308091e3f4e51inst 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)9fa0a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000640316222963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
10024300372250006129548251001710100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
10024300372240106129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
10024300372240006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  umlal2 v0.2d, v8.4s, v9.4s
  movi v1.16b, 0
  umlal2 v1.2d, v8.4s, v9.4s
  movi v2.16b, 0
  umlal2 v2.2d, v8.4s, v9.4s
  movi v3.16b, 0
  umlal2 v3.2d, v8.4s, v9.4s
  movi v4.16b, 0
  umlal2 v4.2d, v8.4s, v9.4s
  movi v5.16b, 0
  umlal2 v5.2d, v8.4s, v9.4s
  movi v6.16b, 0
  umlal2 v6.2d, v8.4s, v9.4s
  movi v7.16b, 0
  umlal2 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)030818191e3a3f51inst 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)9fa1a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602042010015100000392580100100800001008000050064000011200452006420064322801002008000020024000020064200641116020110099100100160000100001210112216222006101600001002006520065200652006520065
160204200641500000039258010010080000100800005006400000020045200642006432280100200800002002400002006420064111602011009910010016000010000310113316422006101600001002006520065200652006520065
160204200641500010039258010010080000100800005006400000120045200642006432280100200800002002400002006420064111602011009910010016000010000010114416332006101600001002006520065200652006520065
160204200641500000039258010010080000100800005006400000020045200642006432280100200800002002400002006420064111602011009910010016000010000010113216332006101600001002006520065200652006520065
160204200641510000039258010010080314100800005006400000120045200642006432280100200800002002400002006420064111602011009910010016000010020010113316332006101600001002006520065200652006520065
160204200641500000039258010010080314100800005006400000120045200642006432280100200800002002400002006420064111602011009910010016000010000010112316222030101600001002006520065200652006520065
160204200641500000039258010010080000100800005006400000120045200642006432280100200800002002400002006420064111602011009910010016000010000010112216222006101600001002006520065200652006520065
160204200641511000081258010010080000100800005006400000020045200642006432280100200800002002400002006420064111602011009910010016000010000310112216222006101600001002006520065200652006520065
160204200641500000039258010010080000100800005006400000020069200642006432280100200800002002400002006420064111602011009910010016000010000010113316322038301600001002006520065200652034420065
16020420064150000006025801001008000010080000500640000012004520064200643438010020080000200240000200642006411160201100991001001600001000027510114216232006101600001002006520065200652006520065

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03073f51inst 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)5f6061696b6d6escheduler 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)9fa8acc5cfd0d2icache miss (d3)itlb miss (d4)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16002420052150051258001212800001280000626400000102003102005020046322800122080000202400002004620046111600211091010160000100001003531101920221201920043215160000102004720047200512005120051
16002420046150145258001212800001280000626400001102002702004620046322800122080000202400002005020050111600211091010160000100001003732101724221141420043230160000102005120047200512005120047
160024200501500108258001212800001280000626400001102002732004620046322800122080000202400002005020046111600211091010160000100001003831101720211141420047215160000102004720047200472004720047
16002420046150074258001212800001280000626400001102002702004620046322800122080000202400002004620046111600211091010160000100001003631101920211141020043215160000102004720047200472004720047
1600242004615004525800121280000128000062640000110200270200462004632280012208000020240000200462004611160021109101016000010100100363110122021181220043215160000102004720047200472004720047
1600242004615005125800121280000128000062640000110200270200462004632280012208000020240000200462004611160021109101016000010000100343221132442216720043230160000102005120051200512005120047
160024200461500710258001212800001280000626400001102002702004620046322800122080000202400002004620046111600211091010160000100001003431111520211131020043215160000102004720047200472004720047
16002420046150045258001212800001280000626400001102002702004620046322800122080000202400002004620046111600211091010160000100001003631101120211121320043215160000102004720047200472004720047
16002420046151015225800121280000128000062640000110200270200462004632280012208000020240000200462004611160021109101016000010000100373110142021191220043215160000102004720047200472004720047
1600242004615004525800121280000128000062640000110200270200462004632280012208000020240000200462004611160021109101016000010000100353111152021112920043215160000102004720047200472004720119

Test 6: throughput

Count: 16

Code:

  umlal2 v0.2d, v16.4s, v17.4s
  umlal2 v1.2d, v16.4s, v17.4s
  umlal2 v2.2d, v16.4s, v17.4s
  umlal2 v3.2d, v16.4s, v17.4s
  umlal2 v4.2d, v16.4s, v17.4s
  umlal2 v5.2d, v16.4s, v17.4s
  umlal2 v6.2d, v16.4s, v17.4s
  umlal2 v7.2d, v16.4s, v17.4s
  umlal2 v8.2d, v16.4s, v17.4s
  umlal2 v9.2d, v16.4s, v17.4s
  umlal2 v10.2d, v16.4s, v17.4s
  umlal2 v11.2d, v16.4s, v17.4s
  umlal2 v12.2d, v16.4s, v17.4s
  umlal2 v13.2d, v16.4s, v17.4s
  umlal2 v14.2d, v16.4s, v17.4s
  umlal2 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)0308090b18191e1f373f4e51inst 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)9fa0a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602044007230000000000410251601001001600001001600005001280000140020400394003919973320007160100200160000200480000400394003911160201100991001001600001000000010110216224003601600001004004040040400404004040040
1602044003929900000000410251601001001600001001600005001316001140020400394003919973319997160100200160000200480000400394003911160201100991001001600001000000010110216224003601600001004004040040400404004040040
1602044003930000000000410251601001001600001001600005001280000140020400394003919973319997160100200160000200480000400394003911160201100991001001600001000000010110216224003601600001004004040040400404004040040
1602044003930000000000410251601001001600001001600005001280000140020400394003919973320007160100200160000200480000400394003911160201100991001001600001000000010110216224003601600001004004040040400404004040040
1602044003930000000000410251601001001600001001600005001280000140030400394003919973319997160100200160000200480000400394003911160201100991001001600001000000010110216224003601600001004004040040400404004040040
1602044004830000000000410251601181001600181001600005001280000140020400394003919973319997160100200160000200480000400394003911160201100991001001600001000000010110216224003601600001004004040040400494004040040
1602044003930000000000420251601001001600181001600005001280000140020400394003919973319997160100200160000200480000400394004911160201100991001001600001000000010110216224003601600001004004040041400404004040040
160204400392990000000041050160100100160018100160000500128000014002040039400391997331999716010020016000020048000040040400481116020110099100100160000100002500541031241223240550211600001004070140591406624072940679
1602044064630411110952888057193651431611451211610961221612386332212697140533406764067820150452031016145720016139720048417340672403931111602011009910010016000010020249754103092633240581211600001004056340630403354065740674
160204409733070001114159913200510251601181001600181001600005001280000140030400494004919973319997160100200160000200480000400394003911160201100991001001600001000000010110216224004601600001004004040040400494005040050

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030818191e1f373f4e51inst 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)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)9fa0a1a8a9acc2cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16002440039299000001746025160010101600171016000050128000011400294004840048199963200191600102016000020480000400394003911160021109101016000010000000100223111317211613400450155160000104004940040400494004040049
160024400393000000352175502516001010160017101600005012800001040029400484004819996320028160010201600002048000040039400391116002110910101600001000106010022311151621156400450155160000104004940040400494004940049
160024400483000000005502516002710160000101600005023990271140029400484027919996320019160010201600002048000040039400485116002110910101600001000003010022311916211513400450155160000104004040049400404004940040
160024400393000000017610251600101016000010160000502398999014002040039400481999632001916001020160000204800004004840039111600211091010160000100000001002231161621166400450155160000104004040049400404004940040
160024400483000000017551012516002710160017101600005023990271140200400394004819996320028160010201600002048000040039400391116002110910101600001000000010022311716422664004503010160000104004040049400494004040050
16002440040299000001761025160010101600001016000050239899901400294004840039199963200191600102016000020480000400394003911160021109101016000010000000100223118162111312400450155160000104005040040400494005340049
160024400482990000017550251600271016000010160000501280000114002040048400391999632002816001020160000204800004004840039111600211091010160000100000001002231161621256400360155160000104004940264400494004940049
16002440039300000001755025160391101600171016000050239899911400204003940048199963200191600102016000020480000400484004811160021109101016000010002000100223111316211138400450155160000104004940040400494004940049
160024400483000000017460251600271016001710160000502398999114002040039400481999632002816001020160000204800004003940048111600211091010160000100000001002231171621176400450155160000104004940040400494004940049
1600244003930000000176250251600271016000110160000501280000114002040039400391999632001916001020160000204800004003940048111600211091010160000100000001002231181621195400450155160000104004040049400404004940040