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, 4H)

Test 1: uops

Code:

  fmls v0.4h, 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)03191e3f4e51inst 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
1004403731006134072510001000100053190804018403740373258338951000100030004037403711100110001073116113473100040384038403840384038
1004403730006134072510001000100053190814018403740373258338951000100030004037403711100110000073116113473100040384038403840384038
1004403730006134072510001000100053190814018403740373258338951000100030004037403711100110000073116113473100040384038403840384038
1004403730006134072510001000100053190804018403740373258338951000100030004037403711100110000073116113473100040384038403840384038
1004403730006134072510001000100053190804018403740373258338951000100030004037403711100110000073116113473100040384038403840384038
1004403730006134072510001000100053190804018403740373258338951000100030004037403711100110000073116113473100040384038403840384038
10044037300186134072510001000100053190804018403740373258338951000100030004037403711100110007073116113473100040384038403840384038
10044037300156134072510001000100053190804018403740373258338951000100030004037403711100110000073116113473100040384038403840384038
1004403730008234072510001000100053190804018403740373258338951000100030004037403711100110000073116113473100040384038403840384038
10044037300061340725100010001000531908040184037403732583389510001000300040374037111001100014073116113473100040384038403840384038

Test 2: Latency 1->1

Code:

  fmls v0.4h, 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): 4.0037

retire (01)cycle (02)031e3a3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)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)9fa8accfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204400373000061394072510100100100001001000050057069084001804003740037381083387451010020010000200300004003740037111020110099100100100001000071002162239479100001004003840038400384003840038
10204400373000061394072510100100100001001000050057069084001804003740037381083387451025220010000200300004003740037111020110099100100100001000071002162239479100001004003840038400384003840038
10204400373000061394072510100100100001001000050057069084001804003740037381083387451010020010000200300004003740037111020110099100100100001000071012162239479100001004003840038400384003840038
10204400372990061394072510100100100001001000050057069084001804003740037381083387451010020010000200300004003740037111020110099100100100001000071012162239479100001004003840038400384003840038
102044003730000613940725101001001000010010000500570690840018040037400373810833874510100200100002003000040037400371110201100991001001000010002771012162239479100001004003840038400384003840038
10204400373000061394072510100100100001001000050057069084001804003740037381083387451010020010000200300004003740037111020110099100100100001000071012162239479100001004003840038400384003840038
10204400373000061394072510100100100001001000050057069084001804003740037381083387451010020010000200300004003740037111020110099100100100001000071012162239479100001004003840038400384003840038
10204400373000061394072510100100100001001000050057069084001804003740037381083387451010020010000200300004003740037111020110099100100100001000071212162339479100001004003840038400384003840038
10204400372990061394072510100100100001001000050057069084001804003740037381083387451010020010000200300004003740037111020110099100100100001000071012162239479100001004003840038400384003840038
10204400373000061394072510100100100001001000050057069084001804003740037381083387451010020010000200300004003740037111020110099100100100001000071013162239479100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)03181e3f4e51inst 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)9fa8a9accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002440037299006139407251001010100001010000505706908140018400374003738130338767100102010000203000040037400371110021109101010000100000640316443947310000104003840038400384003840038
1002440037300006139407251001010100001010000505706908040018400374003738130338767100102010000203000040037400371110021109101010000100000640316343947310000104003840038400384003840038
1002440037300006139407251001010100001010000505706908040053400374003738130338767100102010000203000040037400371110021109101010000100000640416443947310000104003840038400384003840038
10024400373000072639407251001010100001010000505706908040018400374003738130338767100102010000203000040037400371110021109101010000100000640316343947310000104003840038400384003840038
1002440037300006139407251001010100001010000505706908140018400374003738130338767100102010000203051640037400371110021109101010000100000640416443947310000104003840038400384003840038
1002440037300006139407251001010100001010000505706908140018400374003738130338767100102010000203000040037400371110021109101010000100000640316443947310000104003840038400384003840038
1002440037300008239407251001010100001010000505706908140018400374003738130338767100102010000203000040037400371110021109101010000100000640416443954710000104003840038400384003840038
10024400373000072639407251001010100001010000505706908040018400374003738130338767100102010000203000040037400371110021109101010000100000640316333947310000104003840038400384003840038
1002440037300006139407251001010100001010000505706908140018400374003738130338767100102010000203000040037400371110021109101010000100000640416533947310000104003840038400384003840038
1002440037300006139407251001010100001010000505706908040018400374003738130338767100102010000203000040037400371110021109101010000100000640316343947310000104003840038400384003840038

Test 3: Latency 1->2

Code:

  fmls v0.4h, 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): 4.0037

retire (01)cycle (02)0318191e1f3f4e51inst 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)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204400373000000613940725101001001000010010000500570690804001840037400373810833874510100200100002003000040037400371110201100991001001000010000007101161139479100001004003840038400384003840038
10204400372990000613940725101001001000010010000500570690804001840037400373810833874510100200100002003000040037400371110201100991001001000010000207101163139549100001004003840086401324013240133
1020440085300220011883940725101001001001211610148522570830414005340037400373811233878210100200100002003000040037400372110201100991001001000010010007101162139479100001004003840038400384003840038
1020440037300402401033940725101001001000010010000500570690804001840037400373810833874510100200100002003000040037400371110201100991001001000010000007101161139479100001004003840038400384003840038
102044003730000270823940725101001001000010010000500570690804001840037400373810833874510100200100002003000040037400371110201100991001001000010000007101161139479100001004003840038400384003840038
102044003730000156881243940725101001001000010010000500570690804001840037400373810833874510100200100002003000040037400841110201100991001001000010000007101161139479100001004003840038400384003840038
10204400373000000613940725101001001000010010000500570690804001840037400373810833874510100200100002003000040037400371110201100991001001000010000007101161139479100001004003840038400384003840038
102044003730000007263940725101001001000010010000500570690804001840037400373810833874510100200100002003000040037400371110201100991001001000010000007101161139479100001004003840038400384003840038
10204400373000000613940725101001001000010010000500570690804001840037400373810833874510100200100002003000040037400371110201100991001001000010000007101161139479100001004003840038400384003840038
10204400373000000613940725101001001000010010000500570690814001840037400373810833874510100200100002003000040037400371110201100991001001000010000007101161139479100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)03181e3f4e51inst 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)9fa8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100244003730000912394072510010101000010100005057069080400184003740037381303387671001020100002030000400374003711100211091010100001000006404164339473010000104003840038400384003840038
10024400372990061394072510010101000010100005057069080400184003740037381303387671001020100002030000400374003711100211091010100001000006403163439473010000104003840038400384003840038
10025400373000061394072510010101000010100005057069080400184003740037381303387671001020100002230000400374003711100211091010100001000006404164439473010000104003840038400384003840038
10024400373000061394072510010101000010100005057069081400184003740037381303387671001020100002030000400374003711100211091010100001010006404164339473010000104003840038400384003840038
10024400372990061394072510010101000010100005057069081400184003740037381303387671001020100002030000400374003711100211091010100001000006404164439473010000104003840038400384003840038
10024400373000061394072510010101000010100005057069081400184003740037381303387671001020100002030000400374003711100211091010100001000006404164339473010000104003840038400384003840038
10024400373000061394072510010101000010100005057069081400184003740037381303387671001020100002030000400374003711100211091010100001000006404164439473010000104003840038400384003840038
10024400373000061394072510010101000010100005057069081400184003740037381303387671001020100002030486401324003711100211091010100001000006404163439473010000104003840038400384003840038
10024400373000061394072510010101000010100005057069081400184003740037381303387671001020100002030000400374003711100211091010100001000006404163439473010000104003840038400384003840038
10024400373000061394072510010101000010100005057069081400184003740037381303387671001020100002030000400374003711100211091010100001000006404164439473010000104003840038400384003840038

Test 4: Latency 1->3

Code:

  fmls v0.4h, 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): 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)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020440037299061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000071011611394790100001004003840038400384003840038
10204400373000613940725101001001000010010000500570690804001840037400373810820387451010020010000200300004003740037111020110099100100100001000071011611394790100001004003840038400384003840038
1020440037300061394072510100100100001001000050057069081400184003740037381083387451010020010000200300004003740037111020110099100100100001000071011611394790100001004003840038400384003840038
1020440037300061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000071011611394790100001004003840038400384003840038
1020440037300061394072510100100100001001000050057069081400184003740037381083387451010020010000200300004003740037111020110099100100100001000071011611394790100001004003840038400384003840038
1020440037299061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000071011611394790100001004003840038400384003840038
1020440037299061394072510100100100001001000050057069081400184003740037381083387451010020010000200300004003740037111020110099100100100001000071011611394790100001004003840038400384003840038
1020440037300061394072510100100100001001000056657069081400184003740037381083387451010020010000200300004003740037111020110099100100100001000071011611394790100001004003840038400384003840038
10204400372990145394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000071011611394790100001004003840038400384003840038
1020440037300061394072510100100100001001000050057069081400184003740037381083387451010020010000200300004003740037111020110099100100100001000071011611394790100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

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)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)9fa1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024400373000006139407251001010100001010000505706908040018400374003738130033876710010201000020300004003740037111002110910101000010000640216223947310000104003840038400384003840083
10024400372990006139407251001010100001010000505706908040018400374003738130033876710010201000020300004003740037111002110910101000010000640216223947310000104003840038400384003840038
10024400373000106139407251001010100001010000605706908040018400374003738130033876710010201000020300004003740037111002110910101000010000640216223947310000104003840038400384003840038
100244003730000053639407251001010100001010000505706908140018400374003738130033876710010201000020300004003740037111002110910101000010000640216223947310000104003840038400384003840038
10024400373000006139407251001010100001010000505706908140018400374003738130033876710010201000020300004003740037111002110910101000010000640216223947310000104003840038400384003840038
10024400373000006139407251001010100001010000505706908140018400374003738130033876710010201000020300004003740037111002110910101000010000640216223947310000104003840038400384003840038
10024400373000006139407251001010100001010000505706908040018400374003738130033876710010201000020300004003740037111002110910101000010000640216223947310000104003840038400384003840038
10024400373000106139407251001010100001010148505706908140018400374003738130033876710010201000020300004003740037111002110910101000010000640216223947310000104003840038400384003840038
10024400373000006139407251001010100001010000505706908040018400374003738130033876710010201000020300004003740037111002110910101000010000640216223947310000104003840038400384003840038
10024400372990006139407251001010100001010000505706908040018400374003738130033876710010201000020300004003740037111002110910101000010000640216223947310000104003840038400384003840038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  fmls v0.4h, v8.4h, v9.4h
  movi v1.16b, 0
  fmls v1.4h, v8.4h, v9.4h
  movi v2.16b, 0
  fmls v2.4h, v8.4h, v9.4h
  movi v3.16b, 0
  fmls v3.4h, v8.4h, v9.4h
  movi v4.16b, 0
  fmls v4.4h, v8.4h, v9.4h
  movi v5.16b, 0
  fmls v5.4h, v8.4h, v9.4h
  movi v6.16b, 0
  fmls v6.4h, v8.4h, v9.4h
  movi v7.16b, 0
  fmls v7.4h, 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)030b181e3f51inst 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)5f60696d6e74scheduler 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)9fa0a6a8a9accfd2d5d6d9daddinst fetch restart (de)e0ec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602042007815000040258010010080000100800005006400000020046200652006503238010020080000200240000200652006511160201100991001001600001000000010114031620442006201600001002006620066200662006620066
1602042006515100040258010010080000100800005006400000020046200652006503238010020080000200240000200652006511160201100991001001600001000000010115051600452006701600001002006620066200662007120066
1602042006515000040258010010080000100800005006400000020046200652006503238010020080000200240000200652006511160201100991001001600001000000010114051602442006201600001002006620066200662006620066
16020420065151000515258010010080000100800005006400000020046200652006503238010020080000200240000200652006511160201100991001001600001002000010115041600452006201600001002006620066200662006620066
1602042006515000052258010010080000100800005006400000020046200652006503238010020080000200240000200652006511160201100991001001600001000010610115051600542006201600001002006620066200662006620066
1602042006515000640258010010080000100800005006400000020046200652006503238010020080000200240000200652006511160201100991001001600001000000010115051600452006201600001002006620066200662006620066
1602042006515000040258010010080000100800005006400000020046200652006503238010020080000200240000200652006511160201100991001001600001000000010114031600452006201600001002006620066200662006620066
1602042006515000040258010010080000100800005006400000020046200652006503238010020080000200240000200652006511160201100991001001600001000000010114051600352006201600001002006620066200662006620066
1602042006515000040258010010080000100800005006400000020046200652006503238010020080000200240000200652006511160201100991001001600001000000010115041600542006201600001002006620066200662006620066
1602042006515000040258010010080000100800005006400000020046200652006503238010020080000200240000200652006511160201100991001001600001000000010114051600452006201600001002006620066200662006620066

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2508

retire (01)cycle (02)0308191e1f3a3f51inst 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)9fa1a8a9accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16002420076151000004627800121280000128000062640000112003320052200523238001220800002024000020052200521116002110910101600001000001002731182521143200492201160000102005320053200532005320053
1600242005215000312004627800121280000128000062640000112003320052200523238001220800002024000020052200521116002110910101600001000001002731242521134200492201160000102005320053200532005320053
16002420052151000004627800121280000128000062640000212003320052200523238001220800002024000020052200521116002110910101600001000001002631142521144200492201160000102005320053200532005320053
16002420052150000004627800121280000128000062640000112003320052200523238001220800002024000020052200521116002110910101600001000001002631142521144200492201160000102005320053200532005320053
16002420052150009004627800121280000128000062640000212003320052200523238001220800002024000020061200521116002110910101600001000001003031142521144200492401160000102005320053200532005320062
16002420061150000004627800121280000128000062640000112003320061200523238001220800002024000020052200521116002110910101600001000001002631233441134200492201160000102005320062200622005320062
160024200521500000052278001212800001280000626400001120033200522006132380012208000020240000200522005211160021109101016000010021001002731242521143200492201160000102006220053200532005320053
16002420052150000004627800121280000128000062640000012004220052200523238001220800002024000020052200611116002110910101600001000001002731132541144200492201160000102006220053200532005320053
1600242005215000378008027800121280000128000062640000112003320052200523238001220800002024000020052200521116002110910101600001000001002632142542134200582401160000102005320062200532005320053
16002420052150000004629800121280000128000062640000112003320052200523238001220800002024000020052200521116002110910101600001000031002761142541234200492202160000102005320053200532005320053

Test 6: throughput

Count: 16

Code:

  fmls v0.4h, v16.4h, v17.4h
  fmls v1.4h, v16.4h, v17.4h
  fmls v2.4h, v16.4h, v17.4h
  fmls v3.4h, v16.4h, v17.4h
  fmls v4.4h, v16.4h, v17.4h
  fmls v5.4h, v16.4h, v17.4h
  fmls v6.4h, v16.4h, v17.4h
  fmls v7.4h, v16.4h, v17.4h
  fmls v8.4h, v16.4h, v17.4h
  fmls v9.4h, v16.4h, v17.4h
  fmls v10.4h, v16.4h, v17.4h
  fmls v11.4h, v16.4h, v17.4h
  fmls v12.4h, v16.4h, v17.4h
  fmls v13.4h, v16.4h, v17.4h
  fmls v14.4h, v16.4h, v17.4h
  fmls v15.4h, 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)03080918191e373a3f4e51inst 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)9fa6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602044050130610000004202516010010016000010016000050058688951400210400404004021151031999816010020016000020048000040040400401116020110099100100160000100002011011011611400371600001004124641246400414004140041
1602044232730800000004202516010010016000010016000050012800001422990400404231822222032117716010020016000020048000042318400401116020110099100100160000100001441011011611423151600001004004142319400414004140041
1602044004031600000006102516013510016000010016000050012800000400210412454004019973032120316010020016000020048000041245400401116020110099100100160000100001531011011611400371600001004004140041400414004141246
1602044004030000000530924025160100100160000100160000500585605704230804232740040199733531999816010020016000020048000042318400401116020110099100100160000100001501011011611400371600001004004140041400414004141246
160204400403000000080061025160100100160070100160000500128000004002104004040040211510319998160100200160000200480000400404004011160201100991001001600001000001011011611400371600001004231940041400414004140041
160204400433170000000658970251601001001600531001600005001280000040021040040400401997303199981601002001600002004800004231840040111602011009910010016000010000241011011611400371600001004004140041400414004140041
1602044228530000000004202516014310016004310016000050012800000400210400404004019973031999816010020016000020048000040040423181116020110099100100160000100001621011011611400371600001004004142319400414004140041
16020442309300000003604202516010010016000010016000050012800000400210400414231819973031999816010020016000020048000042318400401116020110099100100160000100001441011011611400371600001004124641246412464004140041
160204400403090000053053689702516015310016000010016000050058560570400210400404004019973031999816010020016000020048000040040412451116020110099100100160000100001891011011611400371600001004004140041400414004141246
1602044229531700000004289702516015310016000010016000050012800000412260422964004019973031999816010020016000020048000040040400401116020110099100100160000100001561011011611400371600001004004140041400414004140041

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030407080a18191e1f373a3f4e51inst 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)9fa0a1a6a8a9acc2cdcfd0d2icache miss (d3)itlb miss (d4)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaebec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160024400403071000000000470251600101016000010160000505868333014120741226412261999603222981600102016000020480000412264122611160021109101016000010000000001002664212116222263440037031118160000104004140043400414122741227
16002440040317100000005301134025160063101600531016000050128000011400214004042318222440320020160010201600002048000040040400401116002110910101600001000000000100256421331632233354003701559160000104004140041423194004140043
16002440040300100000000053025160010101600001016000050128000011400214004042318222440320020160010201600002048000040040423181116002110910101600001000000000100233111331621117344003701559160000104004142319400414004140041
1600244004231610000000530712025160010101600001016000050572804711412004004040040199960322298160010201600002048000040040400401116002110910101600001000000000100233111341621133344231501574160000104004142319400414231942319
160024423183001000000000678863251600551016005310160000505868333114002142318400401999603200201600102016000020480000400404231811160021109101016000010000000001002331113216211343442315015611160000104004142319400414004140041
1600244004030010000000004789702516001010160000101600005013199991140021400404004019996032002016001020160000204800004004042318111600211091010160000100000000110026642134163122533400370312217160000104063742319400414004140041
16002440040300100000005315902516001010160053101600005012800001140021400404231822244032002016001020160000204800004122641226111600211091010160000100000000010026642133163223235400370311111160000104004142319400414004140041
16002440040300100000005317302516001010160053101600005057280471142266423184004019996032229816001020160000204800004122641226111600211091010160000100000000010025642134163221832400370311112160000104004140042412204121841227
16002440040300100000000067025160010101600001016000050586833311400214004042318199960320020160010201600002048000040040423181116002110910101600001000000000100233111181621133324003701564160000104004140041400414123041227
160024412263001000000000470251600101016000010160000501280000114120742318400401999603200201600102016000020480000400404231811160021109101016000010000000001002331113516211173342315031111160000104231940041400414004140041