Apple M1 Microarchitecture Research by Dougall Johnson

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

FMLA (vector, 8H)

Test 1: uops

Code:

  fmla 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)03191e3f4e51inst 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)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004403730006134072510001000100053190840184037403732583389510001000300040374037111001100073116113473100040384038403840384038
1004403730006134072510001000100053190840184037403732583389510001000300040374037111001100073116113473100040384038403840384038
1004403730006134072510001000100053190840184037403732583389510001000300040374037111001100073116113473100040384038403840384038
1004403730006134072510001000100053190840184037403732583389510001000300040374037111001100073116113473100040384038403840384038
100440373011986134072510001000100053190840184037403732583389510001000300040374037111001100073116113473100040384038403840384038
1004403730006134072510001000100053190840184037403732583389510001000300040374037111001100073116113473100040384038403840384038
1004403730006134072510001000100053190840184037403732583389510001000300040374037111001100073116113473100040384038403840384038
1004403730036134072510001000100053190840184037403732583389510001000300040374037111001100073116113473100040384038403840384038
1004403730006134072510001000100053190840184037403732583389510001000300040374037111001100073116113473100040384038403840384038
1004403730006134072510001000100053190840184037403732583389510001000300040374037111001100073116113473100040384038403840384038

Test 2: Latency 1->1

Code:

  fmla 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): 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)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)9fa6a8acc5cdcfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204400373000061394072510100100100001001000050057069081400184003740037381083387451010020010000200300004003740037111020110099100100100001000000071002162239479100001004003840038400384003840038
10204400372990061394072510100100100001001000050057069081400184003740037381089387451010020410000200300004003740037111020110099100100100001000200071012162239479100001004003840038400384003840038
10204400373000061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000000071012163239479100001004003840038400384003840038
10204400373000061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000000071012162239479100001004003840038400384003840038
10204400372990161394072510100100100001001000050057069081400184003740037381083387451010020010000200300004003740037111020110099100100100001000000071012162239479100001004003840038400384003840038
10204400372990061394072510100100100001001000050057069081400184003740037381083387451010020010000200300004003740037111020110099100100100001000000071212162239479100001004003840038400384003840038
102044003729900536394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000000071213162239479100001004003840038400384003840038
10204400373000061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000000071012163239479100001004003840038400384003840038
10204400373000061394072510100100100001001000050057069081400184003740037381083387451010020010000200300004008540037111020110099100100100001000000071012163239479100001004003840038400384003840038
10204400373000061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000000071013162239479100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)03181e1f3f4e51inst 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)9fa0a6a7a8acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100244003730000061394072510010101000010100005057069080400180400374003738130338767100102010000203000040037400371110021109101010000100000000640416333947310000104003840038400384003840038
100244003730000061394072510010101000010100005057069080400180400374003738130338767100102010000203000040037400371110021109101010000100000301640316333947310000104003840038400384003840038
100244003730000061394072510010101000010100005057069080400180400374003738130338767100102010000203000040037400371110021109101010000100000000640316333947310000104003840038400384003840038
100244003730000061394072510010101000010100005057069080400180400374003738130338767100102010000203000040037400371110021109101010000100000000640316333947310000104003840038400384003840038
100244003729900061394072510010101000010100005057069080400183400374003738130338767100102010000203000040037400371110021109101010000100000000640316333947310000104003840038400384003840038
100244003729900061394072510010101000010100005057069080400180400374003738130338767100102010000203000040037400371110021109101010000100000000640316333947310000104003840085400384003840038
100244003731700061394072510010101000010100005057069080400180400374003738130338767100102010000203000040037400371110021109101010000100000000640416333947310000104003840038400384003840038
100244003730000061394072510010101000010100005057069080400180400374003738130338767100102010000203000040037400371110021109101010000100000000640316333947310000104003840038400384003840038
100244003730000061394072510010101000010100005057069080400180400374003738130338767100102010000203000040037400371110021109101010000100000000668316333947310000104003840038400384003840038
100244003730000061394072510010101000010100005057069080400180400374003738130338767100102010161203000040037400371110021109101010000100000000640316333947310000104003840038400384003840038

Test 3: Latency 1->2

Code:

  fmla 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): 4.0037

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)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)9fa0a6a8acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204400843000000103394072510100100100001001000050057069084001840037400373810833874510100200100002003000040037400372110201100991001001000010000000078711611394790100001004003840038400384008540038
10204400372990016217661393896310133129100061231014850057069084008840130400843810833874510100204103322023000040037400371110201100991001001000010022002071011611394790100001004003840038400384003840038
10204400373000000726394072510100100100001001000050057054684001840037400373810833874510100200100002003000040037400371110201100991001001000010000000071011611394790100001004003840038400384003840038
1020440037300000061394072510100100100001001000050057069084001840037400373810833874510100200100002003000040037400371110201100991001001000010000130071011611394790100001004003840038400384003840038
1020440037299000061394072510100100100001001000050057069084001840037400373810833874510100200100002003000040037400371110201100991001001000010000030071011611394790100001004003840038400384003840038
10204400373000000613940725101001001000010010000500570690840018400374003738108338745101002001016620030000400374003711102011009910010010000100000718500710216113947914100001004003840038401344008540038
1020440085300000061394072510100100100001001000050057069084001840037400373810833874510100200100002003000040037400371110201100991001001000010000000071011611394790100001004003840038400384003840038
10204400373000012061394072510100100100001001000050057069084001840037400373810833874510100200100002003000040037400371110201100991001001000010000000071011611394790100001004003840038400384003840038
1020440037300000061394072510100100100001001000050057069084001840037400373810833874510100200100002003048340037400371110201100991001001000010000000071011621394790100001004003840038400384003840038
1020440037299000061394072510100100100001001000050057069084001840037400373810833874510100200100002003000040037400371110201100991001001000010000000071011611394790100001004003840038400384003840038

1000 unrolls and 10 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)9fa6a8a9acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024400372990454035261394072510010101000010100005057069081400184003740037381303387671001020100002030000400374003711100211091010100001000000640316333947310000104003840038400384003840038
1002440037300000061394072510010101000010100005057069081400184003740037381303387671001020100582030000400374003711100211091010100001000000640316333947310000104003840038400384003840038
1002440037300000061394072510010101000010100005057069081400184003740037381303387671001020100002030000400374003711100211091010100001000000640316333947310000104003840038400384003840038
1002440037300000061394072510010101000010100005057069080400184003740037381303387671001020100002030000400374003711100211091010100001000000640316333947310000104003840038400384003840038
1002440037310000061394072510010101000010100005057069080400184003740037381303387671001020100002030000400374003711100211091010100001000000640316333947310000104003840038400384003840038
1002440037300000061394072510010101000010100005057069080400184003740037381303387671001020100002030000400374003711100211091010100001000000640316333947310000104003840038400384003840038
1002440037300000061394072510010101000010100005057069080400184003740037381303387861001020100002030000400374003711100211091010100001000000640316333947310000104003840038400384003840038
1002440037300000061394072510010101000010100005057069080400184003740037381303387671001020100002030000400374003711100211091010100001000000640316333947310000104003840038400384003840038
1002440037300000061394072510010101000010100005057069080400184003740037381303387671001020100002030000400374003711100211091010100001000000640316333947310000104003840038400384003840038
1002440037299000061394072510010101000010100005057069080400184003740037381303387671001020100002030000400374003711100211091010100001000000640316333947310000104003840038400384003840038

Test 4: Latency 1->3

Code:

  fmla 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): 4.0037

retire (01)cycle (02)0318191e3f4e51inst 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
102044003730000061394072510100100100001001000050057069081400184003740037381083387451010020010000200300004003740037111020110099100100100001000071011611394790100001004003840038400384003840038
102044003730000061394072510100100100001001000050057069081400184003740037381083387451010020010000200300004003740037111020110099100100100001000071011611394790100001004003840038400384003840038
102044003730000061394072510100100100001001000050057069081400184003740037381083387451010020010000200300004003740037111020110099100100100001000071011611394790100001004003840038400384003840038
1020440037299000346394072510100100100001001000050057069081400184003740037381083387451010020010000200300004003740037111020110099100100100001000071011611394790100001004003840038400384003840038
102044003730000061394072510100100100001001000050057069081400184003740037381083387451010020010000200300004003740037111020110099100100100001004071011611394790100001004003840038400384003840038
10204400373000002833940725101001001000010010000500570690814001840037400373810833874510100200100002003000040037400371110201100991001001000010043071011611394790100001004003840038400384003840038
102044003730000061394072510100100100001001000050057069081400184003740037381083387451010020010000200300004003740037111020110099100100100001000071011611394790100001004003840038400384003840038
102044003729900061394072510100100100001001000050057069081400184003740037381083387451010020010000200300004003740037111020110099100100100001000071011611394790100001004003840038400384003840038
102044003730000061394072510100100100001001000050057069081400184003740037381083387451010020010000200300004003740037111020110099100100100001000071011611394790100001004003840038400384003840038
102044003729900061394072510100100100001001000050057069081400184003740037381083387451010020010000200300004003740037111020110099100100100001000071011611394790100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)0307080918191e3a3f4e51inst 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)9fa1a6a8a9acbranch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100244003730000000007263940725100101010000101000050570690840018400374003738130338767100102010000203000040037400371110021109101010000100000000640616333954510000104003840038400384003840038
10024400373000000000613940725100101010000101000050570690840018400374003738130338767100102010000203000040037400371110021109101010000100000000640316333947310000104003840038400384003840038
10024400373000000000613940725100101010000101000050570690840018400374003738130338767100102010000203000040037400371110021109101010000100000000640316333947310000104003840038400384003840038
10024400373000000000613940725100101010000101000050570690840018400374003738130338767100102010000203000040037400761110021109101010000100000000640316333947310000104003840038400384003840038
10024400372990000000613940725100101010000101000050570690840018400374003738130338767100102010000203000040037400371110021109101010000100000000640316333947310000104003840038400384003840038
10024400373000000000613940725100101010000101000050570690840018400374003738130338767100102010000203000040037400371110021109101010000100000000640316333947310000104003840038400384003840038
10024400373000000000613940725100101010000101000050570690840018400374003738130338767100102010000203000040037400371110021109101010000100000000640316333947310000104003840038400384003840038
10024400373000000000613940725100101010000101000050570690840018400374003738130338767100102010000203000040037400371110021109101010000100000000640316333947310000104003840038400384003840038
10024400373000000000613940725100101010000101000050570690840018400374003738130338767100102010000203000040037400371110021109101010000100000000640316333947310000104003840038400384003840038
10024400372990000000613940725100101010000101000050570690840018400374003738130338767100102010000203000040037400371110021109101010000100000000640316333947310000104003840038400384003840038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  fmla v0.8h, v8.8h, v9.8h
  movi v1.16b, 0
  fmla v1.8h, v8.8h, v9.8h
  movi v2.16b, 0
  fmla v2.8h, v8.8h, v9.8h
  movi v3.16b, 0
  fmla v3.8h, v8.8h, v9.8h
  movi v4.16b, 0
  fmla v4.8h, v8.8h, v9.8h
  movi v5.16b, 0
  fmla v5.8h, v8.8h, v9.8h
  movi v6.16b, 0
  fmla v6.8h, v8.8h, v9.8h
  movi v7.16b, 0
  fmla 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)03181e3f51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160204200901500040258010010080000100800005006400000200462006520065323801002008000020024000020065200651116020110099100100160000100001011441644200621600001002006620066200662006620066
1602042006515002740258010010080000100800005006400000200462006520065323801002008000020024000020065200651116020110099100100160000100001011441634200621600001002006620066200662006620066
160204200651500040258010010080000100800005006400000200462006520065323801002008000020024000020065200651116020110099100100160000100001011341644200621600001002006620066200662006620066
1602042006515004840258010010080000100800005006400000200462006520065323801002008000020024000020065200651116020110099100100160000100001011331644200621600001002006620066200662006620066
160204200651500040258010010080000100800005006400000200462006520065323801002008000020024000020065200651116020110099100100160000100001011441634200621600001002006620066200662006620066
160204200651500040258010010080000100800005006400000200462013520065323801002008000020024000020065200651116020110099100100160000100001011441644200621600001002006620066200662006620066
160204200651500040258010010080000100800005006400000200462006520065323801002008000020024000020065200651116020110099100100160000100001011441644200621600001002006620066200662006620066
16020420065150003704258010010080000100800005006400000200462006520065323801002008000020024000020065200651116020110099100100160000100001011441644200621600001002006620066200662006620066
160204200651500040258010010080000100800005006400000200462006520065323801002008000020024000020065200651116020110099100100160000100001011441644200621600001002006620066200662006620066
160204200651500040258010010080000100801405006400000200462006520065323801002008000020024000020065200651116020110099100100160000100001011441644200621600001002006620066200662006620066

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03081e3f51inst 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)9fa8accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16002420070150004625800121280000128000062640000100200282004720047323800122080000202400002004720047111600211091010160000100010026135162021134200442150160000102006920056200522004820048
160024200471500052258001212800001280000626400001110200282004720047323800122080000202400002004720047111600211091010160000100010026137132021144200442150160000102006920052200522004820048
160024200471500046258001212800001280000626400001110200282004720047323800122080000202400002004720047111600211091010160000100010027138242421243200442150160000102005620048200482004820048
16002420047150004625800121280000128000062640000011020028200472004732380012208000020240000200472004711160021109101016000010712910027135142021244200442150160000102006820048200482004820048
160024200471500046258001212800001280000626400001110200282004720047323800122080000202400002005120047111600211091010160000100010027136132021144200442150160000102006020052200482004820052
160024200471560046258001212800001280000626400001110200282004720047323800122080000202400002004720047111600211091010160000109010026136132021144200442150160000102005620052200482004820048
160024200511500052258001212800001280000626400001110200282004720047323800122080000202400002004720047111600211091010160000106010026166142421144200482300160000102006820048200482004820048
160024200471500046258001212800001280000626400001110200282004720047323800122080109202400002004720047111600211091010160000100010027136142021143200442150160000102006020048200482004820130
160024200471511046258001212800001280000626400001110200282004720047323800122080000202400002004720047111600211091010160000100010026136142021134200442150160000102005620048200482004820048
160024200471500046258001212800001280000626400001110200282004720047323800122080000202400002004720047111600211091010160000100010026136142421134200442150160000102005620048200482004820048

Test 6: throughput

Count: 16

Code:

  fmla v0.8h, v16.8h, v17.8h
  fmla v1.8h, v16.8h, v17.8h
  fmla v2.8h, v16.8h, v17.8h
  fmla v3.8h, v16.8h, v17.8h
  fmla v4.8h, v16.8h, v17.8h
  fmla v5.8h, v16.8h, v17.8h
  fmla v6.8h, v16.8h, v17.8h
  fmla v7.8h, v16.8h, v17.8h
  fmla v8.8h, v16.8h, v17.8h
  fmla v9.8h, v16.8h, v17.8h
  fmla v10.8h, v16.8h, v17.8h
  fmla v11.8h, v16.8h, v17.8h
  fmla v12.8h, v16.8h, v17.8h
  fmla v13.8h, v16.8h, v17.8h
  fmla v14.8h, v16.8h, v17.8h
  fmla 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)031e1f373f4e51inst 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)9fa8a9acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602044014930300604202516010010016006010016000050057179390400214004041227199733211881601002001600002004800004004040040111602011009910010016000010020001011021621400371600001004004140041400414122840041
160204400403090004202516010010016003510016000050012800000400214122740040199733199981601002001600002004800004004040040111602011009910010016000010010001011031612400371600001004004141228400414004140041
1602044004030000544202516016010016000010016000050012800001400214004041227199733199981601002001600002004800004122740040111602011009910010016000010020301011031621412241600001004004140041412284004141228
16020440040300017604206016010010116003710016010650012800001400214004041227199733199981601002001600002004800004004040040111602011009910010016000010010001011021621400371600001004004141228400414004140041
1602044004030800010246142516010010016006010016000050012800000400214231741227199733199981601002001600002004800004004040040111602011009910010016000010030001011011611412241600001004233640041412284004141228
160204412273000004202516016010016000010016000050057179390400214122740040211323199981601002001600002004800004004041227111602011009910010016000010010001011021611400371600001004004140041412284004141228
160204400403000004202516010010016000010016000050057179390412084004040040211323222751601002001600002004800004004040040111602011009910010016000010010001011011622400371600001004004141228400414004140041
160204400403000006102516010010016006010016000050012800001400214122740040199733199981601002001600002004800004004040040111602011009910010016000010040001011011612400371600001004004140041400414004141228
1602044004030000051702516010010016000010016000050057179391412084004041227199733199981601002001600002004800004004040040111602011009910010016000010000001011011632423141600001004004141220412054122840041
160204400403099006102516016010016000010016000050057179390400214004041227199733211851601002001600002004800004122740040111602011009910010016000010000001011011611400371600001004004141228400414004140041

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2577

retire (01)cycle (02)030b1e373a3f4e51inst 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)9fa8accdcfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160024404263000060263994614251600101016006010160000505717939114002141227400402115432120716001020160000204800004004341227111600211091010160000100001002232221164228194122403010160000104122840041400414004140041
16002441227300006021141461425160070101600601016000050571793901412004122741227199963212071600102016000020480000400404004311160021109101016000010000100223111916211199412240155160000104004141228400414004140041
16002440040309000201094614251600701016006010160000505717939114002141227412272115432120716001020160000204800004122740040111600211091010160000100001002231119162111020412240157160000104122840041400414122841228
1600244004030000602088461425160070101600001016000050571793911400214122740040211543211851600102016000020480000400404004011160021109101016000010000100223111916211197412240155160000104122841228412284122841228
16002441227308006020680251600101016006010160000501280000114002141227412271999632120716001020160000204800004004041227111600211091010160000100901002431119162112019400371157160000104004141228412284004141228
16002440040300006023880251600101016006010160000501280000114002140040400402115432002016001020160000204800004004041227111600211091010160000100001002231119162111919412240155160000104122841228400414004140041
1600244122730900022704614251600701016006010160000505717939114120841227412272115432002016001020160000204800004122741227111600211091010160000100001002231119162111619412240157160000104122841228423184004441228
16002441227309006022904614251600701016006010160000505717939114002140040400402115432002016001020160000204800004122740091111600211091010160000100001002231119162211919400400157160000104122841228400414004141228
160024412273080060225570251600111016000010160000505717939114120840040412272115432112216001020160000204800004122741227111600211091010160000100001002431119164111919412240155160000104122841228423184122841228
1600244122730900602417646142516001010160060101600005012800001141208412274122719996320020160010201600002048000040040400401116002110910101600001000110022311916211199400370157160000104004141228412284122841228