Apple M1 Microarchitecture Research by Dougall Johnson

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

FMLS (vector, 4S)

Test 1: uops

Code:

  fmls v0.4s, 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)031e3f4e51inst 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
100440373106134072510001000100053190814018403740373258338951000100030004037403711100110000073116113473100040384038403840384038
100440373006134072510001000100053190814018403740373258338951000100030004037403711100110000073116113473100040384038403840384038
1004403730010334072510001000100053190804018408440373258338951000100030004037403711100110000073116113473100040384038403840384038
1004403730156134072510001000114853190804018403740373258338951000100030004037403711100110000373116113473100040384038403840384038
10044037301261340725100010001000531908040184037403732583389510001000300040374037111001100024673116113473100040384038403840384038
1004403730012434072510001000100053190804018403740373258338951000100030004037403711100110000073116113473100040384038403840384038
1004403730010334072510001000100053190804018403740373258338951000100030004037403711100110001073116113473100040384038403840384038
100440373006134072510001000100053190804018403740373258338951000100030004037403711100110000073116113473100040384038403840384038
1004403730010334072510001000100053190804018403740373258338951000100030004037403711100110000073116113473100040384038403840384038
100440373006134072510001000100053190814018403740373258338951000100030004037403711100110000073116113473100040384038403840384038

Test 2: Latency 1->1

Code:

  fmls v0.4s, 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): 4.0037

retire (01)cycle (02)030818191e1f3a3f4e51inst 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)9fa8acc2branch mispredict (cb)cdcfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020440037300000000613940725101001001000010010000500570690804001840037400373810833874510100200100002003000040037400371110201100991001001000010000000710021622394790100001004003840038400384003840038
1020440037300000000613940725101001001000010010000500570690804001840037400373810833874510100200100002003000040037400371110201100991001001000010000000710021623394790100001004003840038400384003840038
1020440037299000000613940725101001001000010010000500570690804001840037400373810833874510556204100002003000040037400371110201100991001001000010000000712021622394790100001004003840038400384003840038
102044003729900062400613940725101001001000010010000500570690804001840037400373810833874510100200100002003000040037400371110201100991001001000010000000710121620394790100001004003840038400384003840038
102044003730000066600613940725101001001000010010000500570690804001840037400373810833874510100200100002003000040037400371110201100991001001000010000000710121622394790100001004003840038400384003840038
10204400373000000007263940725101001001000010010000500570690804001840037400373810833874510100200100002003000040037400371110201100991001001000010000000710121623394790100001004003840038400384003840038
1020440037299000000663940725101001001000010010000500570690804001840037400373810833874510100200100002003054040037400371110201100991001001000010000000710121622394790100001004003840038400384003840038
1020440037300000000613940725101001001000010010000500570690804001840037400373810833874510100200100002003000040037400371110201100991001001000010000000710131622394750100001004003840038400384003840038
1020440037299000001613940725101001001000010010000500570690804001840037400373810833874510100200100002003000040037400371110201100991001001000010000000710121622394790100001004003840038400384003840038
1020440037300000000613940725101001001000010010000500570690804001840037400373810833874510100200100002003000040037400371110201100991001001000010000000712121622394790100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)03080b18191e1f3a3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024400853000000180017103940725100101010000101000050570690804001840037400373813003387671001020100002030000400374003711100211091010100001000000306402162239473010000104003840038400384003840038
10024400373000000000613940725100101010000101000050570690814001840037400373813003387671001020100002030000400374003711100211091010100001000010306402162239473010000104003840038400384003840038
10024400372990000000613940725100101010000101000050570690804001840132400373813707388431001020100002030000400374003711100211091010100001000010606402162239473010000104003840038400384003840038
10024400373000000000613940725100101010000101000050570690804001840037400373813003387671001020100002030000400374003711100211091010100001000000006402162239473010000104003840038400384003840038
10024400373000000000613940725100101010000101000050570690814001840037400373813003387671001020100002030000400374003711100211091010100001000000006402162239473010000104003840038400384003840038
10024400373000000000613940725100101010000101000050570690814001840037400373813003387671001020100002030000400374003711100211091010100001000000006402162239473010000104003840085400384003840038
100244003729900006000613940725100101010000101000050570690814001840037400373813003387671001020100002030000400374003711100211091010100001000000006402162239473010000104003840038400384003840038
10024400372990000000613940725100101010006101000050570690814001840037400373813003387671001020100002030000400374003711100211091010100001000000006402162239473010000104003840038400384003840038
10024400373000000000613940725100101010000101000050570690804001840037400373813003387671001020100002030000400374003711100211091010100001000000006402162239473010000104003840038400384003840038
10024400373000000000613940725100101010000101000050570690804001840037400373813003387671001020100002030000400374003711100211091010100001000000006402162239473010000104003840076400384003840038

Test 3: Latency 1->2

Code:

  fmls v0.4s, 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): 4.0037

retire (01)cycle (02)0308191e1f3f4e51inst 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)9fa1a6a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020440037300000061394072510100100100001001000050057069084001840037400373811563874110100200100082003002440037400371110201100991001001000010000001117180160039489100001004003840038400384003840038
1020440037300000061394072510100100100001001000050057069084001840037400373811573874110100200100082003002440037400371110201100991001001000010000001117180160039489100001004003840038400384003840038
1020440037300000061394072510100100100001001000050057069084001840037400373810833874510100200100002003000040037400371110201100991001001000010000000007101161139479100001004003840038400384003840038
1020440037299009061394072510100100100001001000050057069084001840037400373810833874510100200100002003000040037400371110201100991001001000010000100007101161139479100001004003840038400384003840038
102044003730000005877394072510100100100001001000050057069084001840037400373810833874510100200100002003000040037400371110201100991001001000010000000007101161139479100001004003840038400384003840038
1020440037300034217661394072510100100100001001000050057069084001840037400373810833874510100200100002003000040037400371110201100991001001000010000000007101161139479100001004003840038400384003840038
102044003730000006139407251010010010000100100005005706908400184003740037381083387451010020010000200300004003740037111020110099100100100001000001500007101161139479100001004003840038400384003840038
1020440037300000061394072510100100100001001000050057069084001840037400373810833874510100200100002003000040037400371110201100991001001000010000000007101161139479100001004003840038400384003840038
1020440037300000061394072510100100100001001000050057069084001840037400373810833874510100200100002003000040037400371110201100991001001000010000000007101161139479100001004003840038400384003840038
1020440037300009061394072510100100100001001000050057069084001840037400373810833874510100200100002003000040037400371110201100991001001000010000000007101161139479100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

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)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)9fa8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024400373000613940725100101010000101000050570690804001840037400373813003387671001020100002030000400374003711100211091010100001062640216223947310000104003840038400384003840038
10024400373000913940725100101010000101000050570690814001840037400373813002538767100102010000203000040037400371110021109101010000100640216223947310000104003840038400384003840038
1002440037300061394072510010101000010100005057069080400184003740037381300338767100102010000203000040037400371110021109101010000100640216223947310000104003840038400384003840038
1002440037299061394072510010101000010100005057069081400184003740037381300338767100102010000203000040037400371110021109101010000100640216223947310000104003840038400384003840038
1002440037300061394072510010101000010100005057069081400184003740037381300338767100102010000203000040037400371110021109101010000100640216223947310000104003840038400384003840038
1002440037300061394072510010101000010100005057069081400184003740037381300338767100102010000203000040037400371110021109101010000100640216223947310000104003840038400384003840038
1002440085300084394072510010101000010100005057069080400184003740037381300338767100102010000203000040037400371110021109101010000100640216223947310000104003840038400384003840038
1002440037300061394072510010101000010100005057069081400184003740037381300338767100102010000203000040037400371110021109101010000100640216223947310000104003840038400384003840038
10024400373000171394072510010101000010100005057069081400184003740037381300338767100102010000203000040037400371110021109101010000100640216223947310000104003840038400384003840038
1002440037299061394072510010101000010100005057069081400184003740037381300338767100102010000203000040037400371110021109101010000100640216223947310000104003840038400384003840038

Test 4: Latency 1->3

Code:

  fmls v0.4s, 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): 4.0037

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)9fa8acbranch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102044003729906139407251010010010000100100005005706908140018400374003738108338745101002001000020030000400374003711102011009910010010000100000071011611394790100001004003840038400384003840038
102044003730006139407251010010010000100100005005706908140018400374003738108338745101002001000020030000400374003711102011009910010010000100000071011611394790100001004003840038400384003840038
102044003730006139407251010010010000100100005005706908040018400374003738108338745101002001000020030000400374003711102011009910010010000100000071011611394790100001004003840038400384003840038
102044003730006139407251010010010000100100005005706908040018400374003738108338745101002001000020030000400374003711102011009910010010000100000071011611394790100001004003840038400384003840038
102044003730006139407251010010010000100100005005706908040018400374003738108338745101002001000020030000400374003711102011009910010010000100000071011611394790100001004003840038400384003840038
102044003730006139407251010010010000100100005005706908040018400374003738108338745101002001000020030000400374003711102011009910010010000100000071011611394790100001004003840038400384003840038
102044003730006139407251010010010000100100005005706908040018400374003738108338745101002001000020030000400374003711102011009910010010000100000171011611394790100001004003840038400384003840038
102044003730006139407251010010010000100100005005706908040018400374003738108338745101002001000020030000400374003711102011009910010010000100000071011611394790100001004003840038400384003840038
102044003730006139407251010010010000100100005005706908140018400374003738108338745101002001000020030000400374003711102011009910010010000100000071011611394790100001004003840038400384003840038
102044003729906139407251010010010000100100005005706908140018400374003738108338745101002001000020030000400374003711102011009910010010000100000071011611394790100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)03070b18191e1f3f4e51inst 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)9fa0a6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002440037300000000613940725100101210000101000050570690804001804003740037381303387671001020100002030000400374003711100211091010100001000036402162239473010000104003840038400384003840038
100244003730000000061394072510010101000010100006057069080400180400374003738130338767100102010000203000040037400371110021109101010000100001266402162239473010000104003840038400384003840038
100244003730000000013039407251001010100001010000505706908040018040037400373813033876710010201000020300004003740070111002110910101000010000336402162239473010000104003840038400384008540038
10024400372991000006139407251001010100001010000505706908040018040037400373813033876710010201000020300004003740037111002110910101000010000306402162239473010000104003840038400384003840038
10024400853000000006139407251001010100001010000505706908040018040037400373813033876710157201000020300004003740037111002110910101000010001156402162239545010000104003840038400384003840038
10024400373000000006139407251001010100001010000505706908040018040037400373813033876710010201000020300004003740037111002110910101000010000276402162239473010000104003840038400384003840038
10024400372990000006139407251001010100001010000505706908040018040037400373813033876710010201000020300004003740037111002110910101000010000216402166639475010000104003840038400384003840038
10024400373000000006139407251001010100001010000505706908040018040037400373813033876710010201000020300004003740037111002110910101000010000276402162239473010000104003840038400384003840038
10024400373000000006139407251001010100001010000505706908040018040037400373813033876710010201000020300004003740037111002110910101000010000246402162239473010000104003840038400384003840038
1002440037300000000613940725100101010000101000050570690804001804003740037381303387671001020100002030000400374003711100211091010100001000006402162239473010000104003840038400384003840038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  fmls v0.4s, v8.4s, v9.4s
  movi v1.16b, 0
  fmls v1.4s, v8.4s, v9.4s
  movi v2.16b, 0
  fmls v2.4s, v8.4s, v9.4s
  movi v3.16b, 0
  fmls v3.4s, v8.4s, v9.4s
  movi v4.16b, 0
  fmls v4.4s, v8.4s, v9.4s
  movi v5.16b, 0
  fmls v5.4s, v8.4s, v9.4s
  movi v6.16b, 0
  fmls v6.4s, v8.4s, v9.4s
  movi v7.16b, 0
  fmls v7.4s, 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)031e3f51inst 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)6061696b6d6escheduler 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)91inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8accfd0d2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16020420077151040258010010080000100800005006400000520046020065200653238010020080000200240000200652006511160201100990100100160000100024101125031622200621600001002006620066200662006620066
1602042006515004025801001008000010080000500640000102004602006520065323801002008000020024000020065200651116020110099010010016000010003101120121622200621600001002006620066200662006620066
1602042006515004025801001008000010080000500640000052004602006520065323801002008000020024000020065200651116020110099010010016000010000101120121622200621600001002006620066200662006620066
1602042006515004025801001008000010080000500640000102004602006520065323801002008000020024000020065200651116020110099010010016000010070101125021622200621600001002006620066200662006620066
1602042006515004025801001008000010080000500640000002004602006520065323801002008000020024000020065200651116020110099010010016000010000101125021622200621600001002006620066200662006620066
1602042006515004025801001008000010080000500640000102004602006520065323801002008000020024000020065200651116020110099010010016000010000101120021622200621600001002006620066200662006620066
1602042006515004025801001008000010080000500640000002004602006520065323801002008000020024000020065200651116020110099010010016000010000101120121622200621600001002006620066200662006620066
1602042006515004025801001008000010080000500640000102004602006520065323801002008000020024000020065200651116020110099010010016000010000101125021622200621600001002006620066200662006620066
16020420065150032525801001008000010080000500640000102004602006520065323801002008000020024000020065200651116020110099010010016000010040101120021622200621600001002006620066200662006620066
1602042006515004025801001008000010080000500640000052004602006520065323801002008000020024000020065200651116020110099010010016000010000101120021622200621600001002006620066200662006620066

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03070a191e3a3f51inst 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)9fa8acbranch mispredict (cb)cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160024201001502300085227800121280000128000062640000110200332005220052323800122080000202400002006120052111600211091010160000100001003381124252111715200492201160000102005320062200622006220062
160024200521501000083727800121280000128000062640000015200422006120061323800122080000202400002006120052111600211091010160000100001003783215344111416200582201160000102006220053200532005320053
16002420052150100004629800121280000128000062640000115200332005220061323800122080000202400002005220052111600211091010160000100001003784116252111615200492201160000102005320053200532005320062
16002420052150010004627800121280000128000062640000115200332005220052323800122080000202400002005220052111600211091010160000100011003985110252111616200492201160000102005320053200532005320053
1600242005215011000118627800121280000128000062640000115200332005220052323800122080000202400002005220052111600211091010160000100001003885117254211017200582201160000102005320053200532006220062
1600242006115012001109627800121280000128000062640000115200332005220052323800122080000202400002005220052111600211091010160000100001003385116252111515200492201160000102005320053200532005320053
1600242005215011000153627800121280000128000062640000015200422005220052323800122080000202400002005220052111600211091010160000100001003785110252111015200492201160000102005320062200532005320053
16002420052150100004627800121280000128000062640000115200332005220052323800122080000202400002005220052111600211091010160000100001004085116252111617200492201160000102005320053200532005320053
1600242005215021000984278001212800001280000626400001152003320052200523238001220800002024000020052200521116002110910101600001021001003886115252211617200582201160000102005320053200532005320053
16002420052150100004627800121280000128000062640000115200332005220052323800122080000202400002005220052111600211091010160000100001003885113252111610200492201160000102005320053200532005320053

Test 6: throughput

Count: 16

Code:

  fmls v0.4s, v16.4s, v17.4s
  fmls v1.4s, v16.4s, v17.4s
  fmls v2.4s, v16.4s, v17.4s
  fmls v3.4s, v16.4s, v17.4s
  fmls v4.4s, v16.4s, v17.4s
  fmls v5.4s, v16.4s, v17.4s
  fmls v6.4s, v16.4s, v17.4s
  fmls v7.4s, v16.4s, v17.4s
  fmls v8.4s, v16.4s, v17.4s
  fmls v9.4s, v16.4s, v17.4s
  fmls v10.4s, v16.4s, v17.4s
  fmls v11.4s, v16.4s, v17.4s
  fmls v12.4s, v16.4s, v17.4s
  fmls v13.4s, v16.4s, v17.4s
  fmls v14.4s, v16.4s, v17.4s
  fmls v15.4s, 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): 0.2503

retire (01)cycle (02)0308090b1e1f373a3f4e51inst 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)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)9fa0a6a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16020440578317000004305634489251601001001600801001600005005707497400214004042312222140322285160100200160000200480000400414004111160201100991001001600001000000010110216224003901600001004121040041400414232640041
16020440040300000003409130251601011001600001001600005005745006400234004042327211150321167160100200160000200480000400404004011160201100991001001600001000000010110216224003901600001004121041210412104121040043
1602044004231700000003448988251601681001600001001600005001280000411904004041190221980319998160100200160000200480000400404231211160201100991001001600001000000010110216224003701600001004121041210412104121040041
1602044004030000000004088988251601341001600191001600005005707386411904232741204199730321162160100200160000200480000400404004011160201100991001001600001000000010110216224232401600001004229542299400414231342295
1602044229431700000115244695251601341001600001001600005005864245400214232541209210950321167160100200160000200480000412094120911160201100991001001600001000000010110216224003701600001004004341205412064004140043
1602044004030000000004245752516014010016006110016000050057057744002140040400402024035320000160100200160000200480000423154120911160201100991001001600001000000610110216234120601600001004121041210412104004141210
1602044004231700000001874695251601401001601411001600006295865526408634126941205211090321239160100200160000200480000400424004011160201100991001001600001000000010143216224232201600001004232641210400414231940041
16020442335300000006803360251601801001600341001600005005707386411904004240040199730321167160100200160000200480000400424004011160201100991001001600001000000010110216224003701600001004231540041423264121041205
1602044120531700000003450251601681001600001001600005005707497400214004042298222050321239160100200160000200480000400424004211160201100991001001600001000000010110216224003701600001004004141191400434128240041
1602044119830000000001260251601341001600681001600005005865526411854004241204199730319998160100200160000200480000400434229611160201100991001001600001000000010110216224003901600001004004140041423264121041206

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2592

retire (01)cycle (02)030a1e373f4e51inst 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)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)9fa8a9accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0eaebec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1600244004930000804060251600901016007010160000501319999015400214044340040222373332002316001020160000204800004232742327111600211091010160000100001002282131622358423241570160000104232842328400414232842328
16002440040316000218895525160090101600801016000050128000011542308423274004019996032230716001020160000204800004120542285111600211091010160000100001002283161621163400371550160000104232840041423284232840041
160024400403160002368863251600101016000010160000501280000115423084229442327222373332230716001020160000204800004004042327111600211091010160000100001002285161621164423241560160000104232840041423284004142328
1600244232730000802008955251600901016008010160000505868895115423084004042327222373332230716001020160000204800004004042327111600211091010160000100001002285151622155423321550160000104232840041423284004142328
160024423273170001970251600901016000010160000501280000115423084004042327222373332230716001020160000204800004004042327111600211091010160000100001002285141621147423241550160000104004142315423284004140041
160024400403170004740251600901016000010160000501280000115400214232742327222373332002016001020160000204800004232742327111600211091010160000100001002285151621155400371550160000104004142328400414232842328
160024423273000002658955251600101016000010160000505868895115400214232740040222373332002016001020160000204800004004042327111600211091010160000100001002285131621153423241560160000104232840041423284228640041
16002442327317000216025160090101600801016000050128000011542295423274004019996032002016001020160000204800004004042327111600211091010160000100001002285171621178423241550160000104232842328423284232842328
160024423272990001778955251600101016000010160000505868895115400214232740040222373332230716001020160000204800004232742327111600211091010160000100001002285161621174400371550160000104232842000400414232840041
160024423273170001108955251600101016000010160000505868895115400214228540040199963332002016001020160000204800004232740040111600211091010160000100001002285171621174400371560160000104004142328400414232842328