Apple M1 Microarchitecture Research by Dougall Johnson

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

SQDMLAL2 (by element, 4S)

Test 1: uops

Code:

  sqdmlal2 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)030b1e3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op fp/simd (7e)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst neon or fp (9a)a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303722006125482510001000100039831330183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
1004303723006125482510001000100039831330183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
1004303722006125482510001000100039831330183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
10043037230126125482510001000100039831330183037303724153289510001000300030373037111001100000073116112630100030843038303830383038
1004303723006125482510001000100039831330183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
1004303723036125482510001000100039831330183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
1004303723006125482510001000100039831330183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
1004303722006125482510001000100039831330183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
1004303722006125482510001000100039831330183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
1004303723006125482510001000100039831330183037303724153289510001000300030373037111001100000073116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  sqdmlal2 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)030b3a3f4e51inst 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)9fa0branch mispredict (cb)cdcfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500612954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000710121622296340100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000710121622296340100001003003830038300383003830038
1020430037225002322954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000710121622296340100001003003830038300383003830038
102043003722500612954825101001001000010310000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000710121622296340100001003003830038300383003830038
1020430037225001472954825101001001000010010000500427731330018300373003728265328745102512001000020030000300373003711102011009910010010000100000712121622296340100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000712121622296340100001003003830038300383003830038
102043003722400612954825101001001000010010000500427867030018300373003728265328758101002001000020030000300373003711102011009910010010000100000710131622296340100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000710121622296340100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000710121622296340100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000712121622296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)031e1f3f4e51inst 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)9fa6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500103295482510010101000010100005042773130300180300373003728287328767100102010323203000030037300371110021109101010000100536403162229630010000103003830038300383003830038
10024300372250074295482510010101000010100005042773130300180300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
10024300372240061295482510010101000010100005042773131300180300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
10024300372250061295482510010101000010100005042773131300180300373003728287328767101592010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
10024300372250084295482510010101000010100005042773130300180300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
10024300372250061295482510010101000810100005042773131300180300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
10024300372250061295482510010101000010100005042773131300180300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
10024300372250061295482510010101000010100005042773131300180300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
10024300372250061295482510010101000010100005042773130300180300373003728287728767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
10024300372250061295482510010101000010100005042773130300180300373003728287328767100102010000203000030037300371110021109101010000100006402162329630010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  sqdmlal2 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)03080b191e1f3f4e51inst 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)9fa1a8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500000612954825101001001000010010000500427731330018030037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003008530038300383003830038
102043003722500000822954825101001001000010010000500427731330018030085300842826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
102043003722500060662954825101001001000010010000500427731330018030037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
1020430037225000007262954825101001001000010010000500427731330018030037300372826532874510100200100002003000030037300371110201100991001001000010000307101161129634100001003003830038300383003830038
1020430037225000002512954825101001001000010010000500427731330018030037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
1020430037225000001032954825101001001000010010149500427731330018030037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300853008530038
102043003722500000612954825101001001000010010000500427731330018030037300372826532874510100200104882043000030180300371110201100991001001000010000007101161129634100001003003830038300383003830038
102043003722400000612954825101001001000010010000500427731330018030037300372826532874510100200100002003000030037300371110201100991001001000010000907101161129634100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731330018030037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731330018030037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038

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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500061295482510010101000010100005042786701300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500661295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372250005555295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225000103295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722400061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  sqdmlal2 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)031e1f3f4e51inst 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
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500147295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500166295482510100100100001001000050042773130300183003730037282693287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372240061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001005307101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)033f4e51inst 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038
10024300372251032954825100101010000101000050427731303001830037300372828732876710158201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038
1002430037225612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038
1002430037225612954825100101010000101000050427731303001830037300372830732876710010201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038
1002430037224612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010406692162229630010000103003830038300383003830038
1002430037225612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038
1002430037225612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038
10024300372251032954825100101210000101000050427731303001830037300372828732876710160201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038
10024300372251032954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038
1002430037225822954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  sqdmlal2 v0.4s, v8.8h, v9.h[1]
  movi v1.16b, 0
  sqdmlal2 v1.4s, v8.8h, v9.h[1]
  movi v2.16b, 0
  sqdmlal2 v2.4s, v8.8h, v9.h[1]
  movi v3.16b, 0
  sqdmlal2 v3.4s, v8.8h, v9.h[1]
  movi v4.16b, 0
  sqdmlal2 v4.4s, v8.8h, v9.h[1]
  movi v5.16b, 0
  sqdmlal2 v5.4s, v8.8h, v9.h[1]
  movi v6.16b, 0
  sqdmlal2 v6.4s, v8.8h, v9.h[1]
  movi v7.16b, 0
  sqdmlal2 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)0308090b18191e1f3f51inst 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)60696d6escheduler 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)9fa1a8acc2cfd5d6dbddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602042008815000000001042580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000000101111160112006101600001002006520065200652006520065
16020420064150000000039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100001980210224118002220327221600001002047020416202822046620471
16020420467154101555403521074185806461238031912380521638644200120347204622047240130806442028052320024156920387203076116020110099100100160000100212445010231218403120392221600001002046820305205222055120227
1602042022615301045660264832580100100800001008000050064000012011120064200643228010020080000200240000200642006411160201100991001001600001000130101111160112006101600001002006520065200652006520065
160204200641500000000392580100100800001008000050064000002004520064200643228010020080000200240000200642006411160201100991001001600001000000101111160112006101600001002006520065200652006520065
1602042006415000000001482580100100800001008000050064000002004520064200643228010020080000200240000201682006421160201100991001001600001000000101111160112006101600001002006520065200652006520065
1602042006415000000001482580100100800001008000050064000002004520064200643228010020080000200240000200642006411160201100991001001600001000100101111160112006101600001002006520065200652006520065
160204200641500000000392580100100800001008000050064000002004520064200643228010020080000200240000200642006411160201100991001001600001000000101111160112006101600001002006520065200652006520065
160204200641500000000392580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000000101111160112006101600001002006520065200652006520065
160204200641500000000392580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000000101111160112006101600001002006520065200652006520065

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030918191e1f3f51inst 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)9fa8accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160024200791500000068258001212800001280000626400001152002702004620046322800122080000202400002004620046111600211091010160000100010032821112021169520043215160000102004720047200472004720047
160024200461500000011025800121280000128000062640000115200270200462004632280012208000020240000200462004611160021109101016000010001003282192021156520043215160000102004720047200472004720047
16002420046150100006625800121280000128000062640000115200270200462004632280012208000020240000200462004611160021109101016000010001002882142021135320043215160000102004720047200472004720047
16002420046150000004525800121280000128000062640000115200270200462004632280012208000020240000200462004611160021109101016000010001002882132021149520043215160000102036720047200472004720047
16002420046150000004525800121280000128000062640000115200270200462004632280012208000020240000200462004611160021109101016000010001003282152021144520043215160000102004720047200472004720047
16002420046150000004525800121280000128000062640000115200270200462004632280012208000020240000200462004611160021109101016000010001003282152021135320043215160000102004720047200472004720047
16002420046150000004525800121280000128000062640000115200270200462004632280012208000020240000200462004611160021109101016000010001002882192021125420043215160000102004720047200472004720047
16002420046150000004525800121280000128000062640000115200270200462004632280012208000020240000200462004611160021109101016000010001003282172021154520043215160000102004720047200472004720047
16002420046150000004525800121280000128000062640000115200270200462004632280012208000020240000200462004611160021109101016000010001002682132021179520043215160000102004720047200472004720047
16002420046150000008725800121280000128000062640000115200270200462004632280012208000020240000200462004611160021109101016000010001003482142021134920043215160000102004720047200472004720047

Test 6: throughput

Count: 12

Code:

  sqdmlal2 v0.4s, v12.8h, v13.h[1]
  sqdmlal2 v1.4s, v12.8h, v13.h[1]
  sqdmlal2 v2.4s, v12.8h, v13.h[1]
  sqdmlal2 v3.4s, v12.8h, v13.h[1]
  sqdmlal2 v4.4s, v12.8h, v13.h[1]
  sqdmlal2 v5.4s, v12.8h, v13.h[1]
  sqdmlal2 v6.4s, v12.8h, v13.h[1]
  sqdmlal2 v7.4s, v12.8h, v13.h[1]
  sqdmlal2 v8.4s, v12.8h, v13.h[1]
  sqdmlal2 v9.4s, v12.8h, v13.h[1]
  sqdmlal2 v10.4s, v12.8h, v13.h[1]
  sqdmlal2 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)030b1e373f4e51inst 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)9fa6a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1202043004823200357266713251201181001200011001200005004399524130020300393004016653314997120100200120000200360000309223175011120201100991001001200001000000761011611300361200001003004031749300403004130040
120204300392250018610251201001001200001001200005004399524031729317483003914973314997120100200120000200360000300403092211120201100991001001200001000000761011611317451200001003004031749300403174930040
120204300392370011810251201001001200001001200005004399524131729317483003914973316706120100200120000200360000300393003911120201100991001001200001000000761011611300361200001003174930040317493004031749
12020431748225000410251201001001200001001200005004399524130021317483003914973316706120100200120000200360000300393003911120201100991001001200001000000761011611317451200001003004031749300403004130040
1202043003923700041025120100100120000100120000500960000131729317483003914973316706120100200120000200360000300393003911120201100991001001200001000000761011611300361200001003004130040317493004030041
1202043004022500041025120100100120018100120000500960000130020300393004016653316706120100200120000200360000300393003911120201100991001001200001000000761011611300371200001003004030041300403004130040
120204300392250018420251201001001200001001202155004399524131729317483003914973314997120100200120000200360000300393004011120201100991001001200001000000761011611317451200001003004030040300403004030040
1202043003923800041671325120101100120018100120000500960000030020300393174816653314997120100200120000200360000300393003911120201100991001001200001000000761011611317451200001003174930040317493004031749
12020431748225001842025120100100120000100120000500960000130020300393174814973316706120100200120000200360000300393003911120201100991001001200001000000761011611317451200001003174930040300433174930040
12020430039238001610251201001001200001001200005004399524130020300393174816653316706120100200120000200360000300413003911120201100991001001200001000000761011611300361200001003174930040317493004031749

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2503

retire (01)cycle (02)03373a3f51inst 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)9facc5cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1200243003922500462512001010120000101200005096000011530020300393003914996315019120010201200002036000030042300391112002110910101200001000752283161622275302034012120000103004030040300403004030943
12002430039225005279120010101200001012000050960000015300203003930039149963150191200102012000020360000300393004011120021109101012000010017525115271642247300364012120000103004030040300403004030040
12002430039225005225120010101200001012000050960000015300203003930039149963150191200102012000020360000300393003911120021109101012000010007525114241642276300364036120000103004030040300403004030040
1200243003922500522512001010120000101200005096000001530020300393003914996315019120010201200002036000030039300391112002110910101200001000752511424162118630036206120000103004030040300403004030040
12002430039225005225120010101200001012000050960000015300203003930039149963150191200102012000020360000300393003911120021109101012000010007525114251642274300364012120000103004030040300403004030040
1200243003922500522512001010120000101200005096000001530020300393003914996315019120010201200002036000030042300391112002110910101200001000752283151642257300364012120000103004030040300403004030040
120024300392250023625120010101200001012000050960000015300203003930039149963150191200102012000020360000300393003911120021109101012000010007525114271642247300364012120000103004030923300403004030040
1200243003922500462512001010120000101200005046331661153002030039300391499631501912001020120000203600003003930039111200211091010120000100075228314162117730036206120000103004030040300403004030040
12002430039225004625120010101200001012000050960000115300203003930039149963150191200102012000020360000300393004111120021109101012000010007525114271642277300364022120000103004030040300403004030040
1200243003922500522512001010120000101200005096000001530020300393003914996315019120010201200002036000030039300391112002110910101200001000752213314162118430036206120000103004030040300403004030040