Apple M1 Microarchitecture Research by Dougall Johnson

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

SQDMLAL (vector, 4S)

Test 1: uops

Code:

  sqdmlal v0.4s, v1.4h, v2.4h
  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)030b191e3f4e51inst 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
10043037230006125482510001000100039831303018303730372415328951000100030003037303711100110000073216112630100030383038303830383038
10043037230096125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037230006125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037220006125482510001000100039831303018303730372415328951000100030003037303711100110007073116112630100030383038303830383038
10043037220006125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037220006125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037220006125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037220006125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037230066125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037230006125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  sqdmlal v0.4s, v1.4h, v2.4h
  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)030b18191e1f3a3f4e51inst 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)9fa6a8a9accfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010004403710131633296340100001003003830038300383003830038
102043003722400000061295482510100102100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000100710131633296340100001003003830038300383003830038
102043003722400000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000712131633296340100001003003830038300383003830038
102043003722500000161295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000100710131633296340100001003003830038300383003830038
102043003722500000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000203710131633296340100001003003830038301333003830038
102043003722500033011452954825101001001000010010000500427731303001830037300372826932874510100204100002003000030037300371110201100991001001000010001020710131633297060100001003003830038300383003830038
1020430037227000000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010006012710131633296340100001003003830038300383003830038
1020430037225000600842954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010003503712131633296340100001003003830038300383003830038
102043003722500000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000103710131633296340100001003003830038300383003830038
102043003722500000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000710131633296340100001003003830038300383003830038

1000 unrolls and 10 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)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
1002430037225006129548251001010100001010000504277313300180300373003728287328767100102010000203000030037300371110021109101010000102830640416332963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313300180300373003728287328767100102010000203000030037300371110021109101010000103300640316332963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731330018030037300372828732876710010201000020300003003730037111002110910101000010200640316332963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313300180300373003728287328767100102010000203000030037300371110021109101010000105100640316332963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313300180300373003728287328767100102010000203000030037300371110021109101010000104000640316332963010000103003830038300383003830038
1002430037226106129548251001010100001010000504277313300180300843003728287328767100102010000203000030037300371110021109101010000103530640316332963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313300180300373003728287328767100102010000203000030037300371110021109101010000101300640316332963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313300180300373003728287328767100102010000203000030037300371110021109101010000103600640416332963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313300180300373003728287328767100102010000203000030037300371110021109101010000100150640316332963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313300180300373003728287328767100102010000203000030037300371110021109101010000104200640316332963010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  sqdmlal v0.4s, v0.4h, v1.4h
  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)0307080a0b1e3f4e51inst 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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000084295482510100124100001001000050042773131300180300373003728265328745101002001000020030000300373003711102011009910010010000100000007102162229634100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773131300180300373003728265328745101002001000020030000300373003711102011009910010010000100400007102162229634100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773131300180300373003728265328745101002001000020030000300373003711102011009910010010000100100007102162229634100001003003830038300383003830181
10204300372250000061295482510100100100001001000050042773131300180300373003728265328745101002001000020030000300373003711102011009910010010000100000007102162229634100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773130300180300373003728265328745101002001000020030000300373003711102011009910010010000100100007102162229634100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773131300183300373003728265328745101002001000020030000300373003711102011009910010010000100100107102162229634100001003003830038300383003830038
10204300372250101061295482510100100100001001000050042773131300180300373003728265328745101002001000020030000300373003711102011009910010010000100000007102162229634100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773131300180300373003728265328745101002001000020030000300373003711102011009910010010000100100007102162229634100001003003830038300383003830038
10204300842240000061295482510100100100001001000050042773131300180300373003728265328745101002001000020030000300373003711102011009910010010000100000007102162229634100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773131300180300373003728265328745101002001000020030000300373003711102011009910010010000100000007102162229634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0308090b18191e1f3a3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)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)9fa0a1a6a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000030010329548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100005606006404164329630010000103003830038300383003830038
100243003722500000000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000000006404164329630010000103003830038300383003830038
100243003722500000000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000003006404164329630010000103003830038300383003830038
100243003722400000000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000000006403164429630010000103003830038300383003830038
10024300372250000000035829548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100006103006403164429630010000103003830038300383003830038
1002430037225000000006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100006006006402164329630010000103003830038300383003830038
1002430037225000000005062954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000200006403164429630010000103003830038300383003830038
1002430037224000000006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100004106006404164329630010000103003830038300383003830038
100243003722500000000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000000006404163329630010000103003830038300383003830038
100243003722500000000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000000006403163429630010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  sqdmlal v0.4s, v1.4h, v0.4h
  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)03080b1e3f4e51inst 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)9fa8accdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250039612954825101001001000010010000500427731303001830037300372827262874010100200100082003002430037300371110201100991001001000010000071011611296340100001003003830038300383003830038
1020430037225000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
102043003722500342612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
10204300372250066129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100012071011611296340100001003003830038300383003830038
10204300372250039612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383008630038
10204300372250027612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
1020430037225000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
1020430037225000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
1020430037225006612954825101001001000010010000500427867003001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
10204300372250015612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b1e3f4e51inst 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)9fa0a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037224000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010010640216222963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225000612954841100101010000101000050427731313001830037300372828732876710010201000020304833003730037111002110910101000010000640216222963010000103003830038300383003830085
1002430084225010612954825100101010000101000050427731313001830037300372828732876710161201016320300003003730084211002110910101000010450640216222963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225000822954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010003640216222963010000103003830171300383003830038
1002430037225006822954825100101010000101000050427731313001830132300372830032880410010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  sqdmlal v0.4s, v8.4h, v9.4h
  movi v1.16b, 0
  sqdmlal v1.4s, v8.4h, v9.4h
  movi v2.16b, 0
  sqdmlal v2.4s, v8.4h, v9.4h
  movi v3.16b, 0
  sqdmlal v3.4s, v8.4h, v9.4h
  movi v4.16b, 0
  sqdmlal v4.4s, v8.4h, v9.4h
  movi v5.16b, 0
  sqdmlal v5.4s, v8.4h, v9.4h
  movi v6.16b, 0
  sqdmlal v6.4s, v8.4h, v9.4h
  movi v7.16b, 0
  sqdmlal v7.4s, v8.4h, v9.4h
  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)0308090b18191e1f3a3f51inst 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)6061696d6escheduler 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)9fa0a1a6a7a8a9acc2cfd0d2d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602042008915100000000392580100100800001008000050064000015200452006420064322801002008000020024000020064200641116020110099100100160000100000000001011151116112006101600001002006520065200652006520065
1602042006415000000000392580100100800001008000050064000015200452006420064322801002008000020024000020064200641116020110099100100160000100000000001011151116112006101600001002006520065200652006520065
1602042006415000000000392580100100800001008000050064000005200452006420064322801002008000020024000020064200641116020110099100100160000100000000001011150116112006101600001002006520065200652006520065
16020420064150000000002432580100100800001008000050064000005200452006420064322801002008000020024000020064200641116020110099100100160000100000000001011250116112006101600001002006520065200652006520065
1602042006415000000000392580100100800001008000050064091610200452006420064322801002008000020024000020064200641116020110099100100160000100000000001011150116112006101600001002006520065200652006520065
1602042006415100000000392580100100800001008000050064000015200452006420064322801002008000020024000020064200641116020110099100100160000100000000001011100116112006101600001002006520065200652006520065
1602042006415000000000392580100100800001008000050064000015200452006420064322801002008000020024000020064200641116020110099100100160000100000000001011150116112006101600001002006520065200652006520065
1602042006415000000000392580100100800001008000050064000005200452006420064322801002008000020024000020064200641116020110099100100160000100000000001011151316112006101600001002006520065200652006520065
1602042006415000000000392580100100800001008000050064000005200452006420064322801002008000020024000020064200641116020110099100100160000100000000001011150116112006101600001002006520065200652006520065
1602042006415000000000392580100100800001008000050064000000200452006420064322801002008000020024000020064200641116020110099100100160000100000000001011100116112006101600001002006520065200652006520065

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03070a0b181e1f3a3f51inst 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)9fa7a9accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160024200661510000150045258001212800001280000626400000120027200462005232280012208000020240000200462004611160021109101016000010000100533113420211292920043215160000102004720047200472004720047
16002420046150120000057258001212800001280000626400000120027200462004632280012208000020240000200462004611160021109101016000010000100576212926322182820049231160000102005320053200532005320053
160024200521502300210051258001212800001280000626400001120027200462004632280012208000020240000200462004611160021109101016000010000100516112920211323020043215160000102005320053200472004720047
16002420052150220000057258001212800001280000626400001120033200462004632280012208000020240000200462004611160021109101016000010000100406111826211301820043215160000102005320047200472004720047
16002420046150220000057258001212800001280000626400001120027200522004632280012208000020240000200522005211160021109101016000010000100566223126322212520043215160000102004720047200472004720047
16002420052150220000157258001212800001280000626400000120027200462004632280012208000020240000200522005211160021109101016000010000100546223126211282720043215160000102005320053200532004720053
16002420046150110000057258001212800001280000626400001120031200462005232280012208000020240000200462005211160021109101016000010000100563122920222293020049231160000102004720047200472004720053
16002420052150120000057258001212800001280000626400000120027200462004632280012208000020240000200522004611160021109101016000010000100526222820212192920043215160000102005320047200472004720053
16002420052150220000057258001212800001280000626400001120027200522004632280012208000020240000200522004611160021109101016000010000100526122920221322920049215160000102005320047200472005320047
16002420046150220000163258001212800001280000626400001120027200462004632280012208000020240000200462005211160021109101016000010000100533112626322222620049215160000102005320047200532004720047

Test 6: throughput

Count: 16

Code:

  sqdmlal v0.4s, v16.4h, v17.4h
  sqdmlal v1.4s, v16.4h, v17.4h
  sqdmlal v2.4s, v16.4h, v17.4h
  sqdmlal v3.4s, v16.4h, v17.4h
  sqdmlal v4.4s, v16.4h, v17.4h
  sqdmlal v5.4s, v16.4h, v17.4h
  sqdmlal v6.4s, v16.4h, v17.4h
  sqdmlal v7.4s, v16.4h, v17.4h
  sqdmlal v8.4s, v16.4h, v17.4h
  sqdmlal v9.4s, v16.4h, v17.4h
  sqdmlal v10.4s, v16.4h, v17.4h
  sqdmlal v11.4s, v16.4h, v17.4h
  sqdmlal v12.4s, v16.4h, v17.4h
  sqdmlal v13.4s, v16.4h, v17.4h
  sqdmlal v14.4s, v16.4h, v17.4h
  sqdmlal v15.4s, v16.4h, v17.4h
  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)03181e373f51inst 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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160204400583000005025160100100160017100160000500128000000400214003940039199730319997160100200160000200480000400494003911160201100991001001600001000000010110216224003601600001004004940049400404004040049
1602044003930000050251601001001600171001600005001280000004002040048400391997303200061601002001600002004805074004840048111602011009910010016000010001500010110216224003601600001004004040040400494004940040
1602044003930000174125160100100160000100160000500239899900400204003940039199730320006160100200160000200480000400394003911160201100991001001600001000000010110216224004501600001004004940040400404004940040
1602044004830000041251601001001600171001600005001280000004002940039400391997303200061601002001600002004800004004840048111602011009910010016000010044000010110216224003601600001004010040040400404004940040
160204400483000004125160100100160000100160000500128000000400204004840039199730319997160100200160000200480000400484003911160201100991001001600001000000010110216224004501600001004004940049400404004040040
160204400393000005025160117100160000100160000500128000000400204003940039199730319997160100200160000200480000400484004811160201100991001001600001000000010110216224004501600001004004040040400494004940040
1602044004930000041425160100100160017100160000500239899900400204003940039199737319997160100200160000200480000400394003911160201100991001001600001000000010110216224004501600001004004940049400404004040040
1602044003930000174125160117100160018100160000500239899900400294003940039199730320006160100200160000200480000400394003911160201100991001001600001000000010110216224003601600001004004940049400494004940040
1602044003930000175025160117100160000100160000500128000000400294004840048199730319997160100200160000200480000400394004811160201100991001001600001000000010110216224003601600001004004040049400404004040040
16020440039300001719025160100100160000100160000500239899900400204003940048199730319997160100200160000200480000400394003911160201100991001001600001000000010110216224003601600001004004940040400404004940049

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030708090b1e1f373f51inst 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)5f60696b6d6edispatch 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)9fa6a8acc5cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160024400493000000001746251600101016000010160000501280000214002004003940049199960320028160010201600002048000040039400391116002110910101600001000001002431122164221984003603010160000104004040040400404004040040
160024400393001000000622516002710160000101600005012800000140020040039400391999603200291600102016000020480000400394003911160021109101016000010000010024622161642220204003601510160000104004040040400404004040040
1600244004830000000017522516001010160000101600005024388650140020040048400481999603200191600102016000020480000400394003911160021109101016000010000010024622161642210204003603012160000104004040040400404004040040
160024400492991000000522516002710160018101600005012800000140020040039400391999603200191600102016000020480000400394003911160021109101016000010000010024622191642220204003603010160000104004040050400404004040041
16002440048300011000061251600101016000010160000501280000014002004003940039199960320019160010201600002048000040049400391116002110910101600001000001002462219164229204003603010160000104005040050400404004040040
160024400392991000000622251600101016000010160000501280000114002004003940039199960320019160010201600002048000040039400391116002110910101600001000001002462291642210204003603010160000104004040040400404004040050
16002440039300100000035325160010101600001016000050239899901400290400394003919996032001916001020160000204800004003940039111600211091010160000100000100246229164227194003603010160000104004040040400404004040040
160024400392990000000522516001010160000101600005012800000140029040039400491999603200191600102016000020480000400394003911160021109101016000010000010060622191662221214003603010160000104004040040400404004040040
16002440039300000000052251600101016000010160000501320000014002004003940049199960320019160010201600002048000040049400391116002110910101600001000001002462219164221994003603010160000104004140040400404004040040
160024400393000000000522516001010160000101600005012800001140020040039400391999603200191600102016000020480000400394003911160021109101016000010000010024622191642210204003603010160000104004040040400404004040040