Apple M1 Microarchitecture Research by Dougall Johnson

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

SQRDMLAH (vector, 8H)

Test 1: uops

Code:

  sqrdmlah v0.8h, v1.8h, v2.8h
  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)031e3f4e5051inst 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)a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037230612548302125100010001000398313130183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
10043037230612548025100010001000398313130183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
1004303723240612548025100010001000398313130183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
10043037230612548025100010001000398313130183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
10043037230612548025100010001000398313130183037303724153289510001000300030373037111001100000096116112630100030383038303830383038
10043037230612548025100010001000398313030183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
10043037230612548025100010001000398313130183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
10043037230612548025100010001000398313130183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
10043037220612548025100010001000398313130183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
10043037239612548025100010001000398313130183037303724153289510001000300030373037111001100000073116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  sqrdmlah v0.8h, v1.8h, v2.8h
  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)030b181e3f4e51inst 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)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)9fa0a6a7a8accfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250006129548251010010010000100100005004277313130018030037300372826503287451010020010000200300003003730037111020110099100100100001000004913871004164329634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300180300373003728265032874510100200100002003000030037300371110201100991001001000010000053071013163329634100001003003830038300383003830038
102043003722501061295482510100100100001001000050042773130300180300373003728265032874510100200100002003000030037300371110201100991001001000010000009071013163329634100001003003830038300383003830038
1020430037225000612954825101001001000010010000500427731303001803003730037282650328745101002001000020030000300373003711102011009910010010000100000017171013163329634100001003003830038300383003830038
1020430037225000612954825101001001000010010000500427731303001803003730037282650328745101002001000020030000300373003711102011009910010010000100000012071013163329634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300180300373003728265032874510100200100002003000030037300371110201100991001001000010000048071013163329634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300180300373003728265032874510100200100002003000030037300371110201100991001001000010000068071013163329634100001003003830038300383003830038
102043003722400072629548251010010010000100100005004277313130018030037300372826503287451010020010000200300003003730037111020110099100100100001000000671013163329634100001003003830038300383003830038
1020430037225000441295482510100100100001001000050042773130300180300373003728265032874510100200100002003000030037300371110201100991001001000010000023371013163329634100001003003830038300383003830038
1020430037225000612954825101001001000010010000500427731313001803003730037282650328745101002001000020030000300373003711102011009910010010000100000011471013163329634100001003003830038300383003830038

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)9fa8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225248012954844100101010008101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010100640216222963010000103003830038300383003830085
10024300372250612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010030640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010090640216232963010000103003830038300383008530038
10024300372259612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010030640216232963010000103003830038300383003830038
10024300372240612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010055130640216322963010000103003830038300383003830038
10024300372250822954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010030640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000105260640216222963010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  sqrdmlah v0.8h, v0.8h, v1.8h
  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)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)9fa0a1a6a8a9acbranch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
102043003722501061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
102043003722400061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830087
102043003722400061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b1e3f4e51inst 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)9fa1a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372240061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000006403164429630010000103003830038300383003830038
10024300372250061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000006404164429630010000103003830038300383003830038
10024300372250061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000006403164329630010000103003830038300383003830038
10024300372250061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000006403163429630010000103003830038300383003830038
100243003722500612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010056036404164329630010000103003830038300383003830038
100243003722500612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037211002110910101000010046066404164329630010000103003830038300383003830038
100243003722500612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010024006403164429630010000103003830038300383003830038
10024300372250061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001003206404163429630010000103003830038300383003830038
10024300372250061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000006404163429630010000103003830038300383003830038
1002430037225012612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010036006404164429630010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  sqrdmlah v0.8h, v1.8h, v0.8h
  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)60696b6d6edispatch 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)9fa0a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250961295482510100100100001001000050042773130300180300373003728265032874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
10204300862250061295482510100100100001001000050042773130300180300373003728265032874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300540300373003728265032874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300180300373003728265032874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300180300373003728265032874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300180300373003728265032874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383008530038
10204300372250061295482510100100100001001000050042773130300180300373003728265032874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300180300373003728265032874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300180300373003728265032874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183300373003728265032874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b181e1f3f4e51inst 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)9fa1a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500008929548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100006403162229630010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100183966402162229630010000103003830038300383003830038
1002430037225001292205229548251001013100161010000504277313030018300853017928301328825100102010000203000030037301321110021109101010000100027556402412229630110000103003830038300383003830085
100243013022610006129548251001010100001210000504277313130342304643046428316328767109052210000203000030037300371110021109101010000104006402162229630010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100136402162229630010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  sqrdmlah v0.8h, v8.8h, v9.8h
  movi v1.16b, 0
  sqrdmlah v1.8h, v8.8h, v9.8h
  movi v2.16b, 0
  sqrdmlah v2.8h, v8.8h, v9.8h
  movi v3.16b, 0
  sqrdmlah v3.8h, v8.8h, v9.8h
  movi v4.16b, 0
  sqrdmlah v4.8h, v8.8h, v9.8h
  movi v5.16b, 0
  sqrdmlah v5.8h, v8.8h, v9.8h
  movi v6.16b, 0
  sqrdmlah v6.8h, v8.8h, v9.8h
  movi v7.16b, 0
  sqrdmlah v7.8h, v8.8h, v9.8h
  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)9facc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160204200891500003925801001008000010080000500640000200452006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065201342006520065
160204200641500003925801001008000010080000500640000200452006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
160204200641500003925801001008000010080000500640000200452006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
160204200641501003925801001008000010080000500640000200452006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
1602042006415100060925801001008000010080000500640000200452006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
160204200641500003925801001008000010080000500640000200452006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
160204200641510003925801001008000010080000500640000200452006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
160204200641500003925801001008000010080000500640000200452006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
1602042006415000031625801001008000010080000500640000200452006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065
1602042006415000031225801001008000010080000500640000200452006420064322801002008000020024000020064200641116020110099100100160000100001011111611200611600001002006520065200652006520065

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e1f3f51inst 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)9fa0a1a8a9accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16002420086150903212580012128000012800006264000011520027200462004632280012208000020240000200462004611160021109101016000010000001003082111202115820043247160000102004720047200472004720047
160024200461500022225800121280000128000062640000115200272004620046322800122080000202400002004620046111600211091010160000100000010033821520211101020043232160000102004720047200472004720047
1600242004615000271258001212800001280000626400001152002720046200463228001220800002024000020046200461116002110910101600001000000100328219202117720043232160000102004720047200472004720047
1600242004615000251258001212800001280000626400001152002720046200463228001220800002024000020046200461116002110910101600001000000100288319202217520043247160000102005120051200512005120051
16002420050150002382580012128000012800006264000011520027200462004632280012208000020240000200462004611160021109101016000010000031003382110202119720043232160000102004720047200472004720047
1600242004615000212258001212800001280000626400001152002720046200463228001220800002024000020046200461116002110910101600001000000100338216202119920043232160000102004720047200472004720047
1600242004615000210258001212800001280000626400001152002720046200463228001220800002024000020046200461116002110910101600001000000100298217202117520043232160000102004720047200472004720047
160024200461501620223258001212800001280000626400001152002720046200463228001220800002024000020046200461116002110910101600001000000100328219202116720043232160000102004720047200472004720047
16002420046150001932580012128000012800006264000011520027200462004632280012208000020240000200462004611160021109101016000010000001003182172021161020043232160000102004720047200472004720047
16002420046150002162580012128000012800006264000011520027200462004632280012208000020240000200462004611160021109101016000010000001003382172021171020043232160000102004720047200472004720047

Test 6: throughput

Count: 16

Code:

  sqrdmlah v0.8h, v16.8h, v17.8h
  sqrdmlah v1.8h, v16.8h, v17.8h
  sqrdmlah v2.8h, v16.8h, v17.8h
  sqrdmlah v3.8h, v16.8h, v17.8h
  sqrdmlah v4.8h, v16.8h, v17.8h
  sqrdmlah v5.8h, v16.8h, v17.8h
  sqrdmlah v6.8h, v16.8h, v17.8h
  sqrdmlah v7.8h, v16.8h, v17.8h
  sqrdmlah v8.8h, v16.8h, v17.8h
  sqrdmlah v9.8h, v16.8h, v17.8h
  sqrdmlah v10.8h, v16.8h, v17.8h
  sqrdmlah v11.8h, v16.8h, v17.8h
  sqrdmlah v12.8h, v16.8h, v17.8h
  sqrdmlah v13.8h, v16.8h, v17.8h
  sqrdmlah v14.8h, v16.8h, v17.8h
  sqrdmlah v15.8h, v16.8h, v17.8h
  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)03080b18191e1f373f4e51inst 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)9fa0a1a6a7a8acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602044005830000000017410251601001001600001001600005001280000140029400394004819973320006160100200160000200480000400394004811160201100991001001600001000000000010110116114003601600001004004040049400404004040049
1602044003930000000004102516011710016001710016000050012800001400294003940039199733200061601002001600002004800004003940039111602011009910010016000010000000150010110416114003601600001004004940040400404004940040
1602044003930000002100510251601001001600001001600005001280000140020400394003919973320006160100200160000200480000400494003911160201100991001001600001000000000010110116124003701600001004004940040400404009040040
160204400393000000000410251601171001600001001600005001280000140020400394003919973320006160100200160000200480000400394004811160201100991001001600001000000000010110316114003601600001004004040049400494004040040
160204400403000000000410251601171001600001001600005001280000140020400484003919973319997160100200160000200480000400394003911160201100991001001600001000000000010127216114003601600001004004040040400404004040049
160204400393000000000410251601001001600001001600005001280000140020400394004819973320006160100200160000200480000400394003911160201100991001001600001000000000010110116114004501600001004004040040400414004040040
160204400392990000000500251601171001600001001600005001280000140020400404004819973319997160100200160000200480000400394003911160201100991001001600001000000000010110116114003601600001004004040040400404004040040
160204400393000000000500251601001001600001001600005001280000140020400394003919973319997160100200160000200480000400484004811160201100991001001600001000000000010110116114003601600001004004040040400404004040040
1602044003930000000017410251601001001600171001600005001280000140020400394003919973319997160100200160000200480000400484004811160201100991001001600001000000000010110316114003601600001004004040040400404004940049
160204400393000000000410251601001001600001001600005002398999140020400394004819973319997160100200160000200480318400484003911160201100991001001600001000000000010110116234003601600001004004940049400404004040040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03071e1f373a3f4e51inst 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)9fa8accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16002440075300024000460251600111016000010160000501280000114002040039400391999632001916001020160000204800004003940039111600211091010160000100010022842261642277400453011160000104004940040400494004940049
16002440048300081000730251600101016000010160000505387188014005240040400481999632002816001020160000204800004003940071111600211091010160000100010024931171642179400363010160000104007240040400404004040040
1600244003930000000462525160010101600001016000050128000001400524003940039199963200191600102016000020480000400394003911160021109101016000010001002275116162116540046155160000104007240040400404004040040
16002440049300000004625251600711016000010160000501280000014002040039400391999632001916001020160000204800004003940039111600211091010160000100010022812161632267400363010160000104004040040400404004040040
1600244003929900017055025160010101600001016000050128000001400524003940039199963200191600102016000020480000400394003911160021109101016000010001002281116162117740068155160000104004040040400404007240040
160024400393000000046025160027101600001016000050128000011400204003940071200023200511600102016000020480000400484004811160021109101016000010001002272218164225640036155160000104004040040400404004040040
16002440071299000170610251600101016000010160000501280000114002040039400711999632001916001020160000204800004003940071111600211091010160000100010022722181621015640036155160000104007240040400724004040040
1600244003930000000460251600711016006110160000501280000114002040039400392000232001916001020160000204800004004840048111600211091010160000100010024811291642257400363010160000104004940040400494004040040
1600244003930010000520251600101016000010160000501280000114002940039400391999632001916001020160000204800004003940048111600211091010160000100010024811191642165400681510160000104004040040400494004940049
160024400393000000046025160010101600001016000050128000001400204003940039199963200191600102016000020480000400484003911160021109101016000010001002275218162225640036155160000104004040072400404007240040