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, 2D)

Test 1: uops

Code:

  fmls v0.2d, v1.2d, v2.2d
  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)03070a1e3a3f4e51inst 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
100440373100006134072510001000100053330414018403740373258338951000100030004037403711100110000073616663473100040384038403840384038
100440373000006134072510001000100053190814018403740373258338951043100030004037403711100110000073616663473100040384038403840384038
1004403730000086434072510001000100053190814018403740373258338951000100030004037403711100110000073616663473100040384038403840384038
1004403730000010334072510001000100053190814018403740373258338951000100030004037403711100110000073616663473100040384038403840384038
100440373000006134072510001000100053190814018403740373258338951000100034804037403711100110000073616663473100040384038403840384038
100440373000006134072510001000100053190814018403740373258338951000100030004037403711100110000075616553473100040384038403840384038
100440373000006134072510001000100053190814018403740373258338951000100030004037403711100110000073616663473100040384038403840384038
10044037300012023334072510001000100053190814018403740373258338951000100030004037403711100110000073616663473100040384038403840384038
100440373000006134072510001000100053190814018403740373258338951000100030004037403711100110000073616663473100040384038403840384038
100440373000006134072510001000100053190814018403740373258338951000100030004037403711100110000073616663473100040384038403840384038

Test 2: Latency 1->1

Code:

  fmls v0.2d, v1.2d, v2.2d
  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)9fa8accfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102044003730000823940725101001001000010010000500570690804001840037400373810833874510100200100002003000040037402271110201100991001001000010000710172533394790100001004003840038400384003840038
1020440037300007263940725101001001000010010000500570690804003740037400373810833874510100200100002003000040037400371110201100991001001000010000712131633394790100001004003840038400384003840038
102044003730000613940725101001001000010010000500570690804001840037400373810833874510100200100002003000040037400371110201100991001001000010000710131633394790100001004003840038400384003840038
102044003730000613940725101001001000010010000500570690804001840037400373810833874510100200100002003000040037400371110201100991001001000010000712131622394790100001004003840038400384003840038
102044003730000613940725101001001000010010000500570690804001840037400373810833874510100200100002003000040037400371110201100991001001000010000710131633394790100001004003840038400384003840038
102044003730000613940725101001001000010010000500570690804001840037400373810833874510100200100002003000040227400371110201100991001001000010000710141633394790100001004003840038400384003840038
1020440037299007263940725101001001000010010000500570690804001840037400373810833874510100200100002003000040037400371110201100991001001000010000710131633394790100001004003840038400384003840038
102044003730000613940725101001001000010010000500570690804001840037400373810833874510100200100002003000040037400371110201100991001001000010000710131633394790100001004003840038400384003840038
102044003729900613940725101001001000010010000500570690804001840037400373810833874510100200100002003000040037400371110201100991001001000010000710131633394790100001004003840038400384003840038
10204400373000067863940725101001001000010010000500570690804001840037400373810833874510100200100002003000040037400371110201100991001001000010000710131633394790100001004003840038400384003840038

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)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)9fa8a9acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024400373000160539407251001010100001010000505706908040018400374003738130338767100102010000203000040037400371110021109101010000100000640216323947310000104003840038400384003840038
100244003730006139407251001010100001010000505706908040018400374003738130338767100102010000203147940037400371110021109101010000100001640216223947310000104003840038400384003840038
100244003730006139407251001010100001010000505706908040018400374003738130338767100102010000203000040037400371110021109101010000100000640216223947310000104003840038400384003840038
100244003730006139407251001010100001010000505706908140018400374003738130338767100102010000203000040037400371110021109101010000100000640216223947310000104003840038400384003840038
100244003731006139407251001010100001010000505706908040018400374003738130338767100102010000203000040037400371110021109101010000100000640216233947310000104003840038400384003840038
100244003730006139407251001010100001010000505706908040018400374003738130338767100102010000203000040037400371110021109101010000100000640216223947310000104003840038400384003840038
100244003730006139407251001010100001010000505706908040018400374003738130338767100102010000203000040037400371110021109101010000100000661216223947310000104003840038400384003840038
100244003730006139407251001010100001010000505706908140018400374003738130338767100102010000203000040037400371110021109101010000100000640316223947310000104003840038400384003840038
100244003730006139407251001010100001010000505706908040018400374003738130338767100102010000203000040037400371110021109101010000100000640216223947310000104003840038400384003840038
1002440037299072639407251001010100001010000505706908040018400374003738130338767100102010000203000040037400371110021109101010000100000640216223947310000104003840038400384003840038

Test 3: Latency 1->2

Code:

  fmls v0.2d, v0.2d, v1.2d
  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)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)9fa1a8acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204400373000613940725101001001000010010000500570690814001804003740037381083387451010020010000200300004003740037111020110099100100100001000000071021611394790100001004003840038400384003840038
10204400373000613940725101001001000010010000500570690814001804003740037381083387451010020010000200300004003740037111020110099100100100001000000071011611394790100001004003840038400384003840038
102044003729912613940725101001001000010010000500570690814001804003740037381083387451010020010000200319564003740037111020110099100100100001000035600071011611394790100001004003840038400384003840038
10204400373000613940725101001001000010010000500570690814001804003740037381083387451010020010000200300004003740037111020110099100100100001000000071011611394790100001004003840038400384003840038
10204400373000613940725101001001000010010000500570690814001804003740037381083387451010020010000200300004003740037111020110099100100100001000000071011611394790100001004003840038400384003840038
10204400373000613940725101001001000010010000500570690814001804003740037381083387451010020010000200300004003740037111020110099100100100001000000071011611394790100001004003840038400384003840038
102044003729901333940725101001001000010010000500570690814001804003740037381083387451010020010000200300004003740037111020110099100100100001000000071011611394790100001004003840071400384003840038
10204400373000613940725101001001000010010000500570690814001804003740037381083387451010020010000200300004003740037111020110099100100100001000000071011611394790100001004003840038400384003840038
10204400373000613940725101001001000010010000500570690814001804003740037381083387451010020010000200300004003740037111020110099100100100001000000071011611394790100001004003840038400384003840038
102044003730067263940725101001001000010010000500570690814001804003740037381083387451026320010000200300004003740037111020110099100100100001002100071011611394790100001004003840038400384003840038

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)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)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100244003730006139407251001010100001010000505706908140018040037400373813033876710010201000020300004003740037111002110910101000010006402162239473010000104003840038400384003840038
1002440037299053639407251001010100001010000505706908140018040037400373813033876710010201000020300004003740037111002110910101000010006402162239473010000104003840038400384003840038
100244003730006139407251001010100001010000505706908040018040037400373813033876710010201000020300004003740037111002110910101000010006402162239473010000104003840038400384003840038
100244003730066139407251001010100001010000505706908040018040037400373813033876710010201000020300004003740037111002110910101000010006402162239473010000104003840038400384003840038
100244003729906139407251001010100001010000505706908040018040037400373813033876710010201000020300004003740037111002110910101000010006402162239473010000104003840038400384003840038
10024400373000292939407251001010100001010000505706908040018040037400373813033876710010201000020305164003740037111002110910101000010006402162239473010000104003840038400384003840038
100244003730006139407251001010100001010000505706908040018040037400373813033876710010201000020300004003740037111002110910101000010006402162239473010000104003840038400384003840038
1002440037300306139407251001010100001010000505706908040018040037400373813033876710010201000020300004003740037111002110910101000010006402162239473010000104003840038400384008540038
100244003730006139407251001010100001010000505706908040018040037400373813033876710010201000020300004003740037111002110910101000010006402162239473010000104003840038400384003840038
100244003730006139407251001010100001010000505706908040018040037400373813033876710010201000020300004003740037111002110910101000010006402162239547010000104003840038400384003840038

Test 4: Latency 1->3

Code:

  fmls v0.2d, v1.2d, v0.2d
  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)03081e3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)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)9fa6a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102044003730000726394072510100100100001001000050057069084001840037400373810833874510719200100002003000040037400371110201100991001001000010000007101161139479100001004003840038400384003840038
10204400373000600220394072510100100100001001000050057069084001840037400373810833874510100200100002003000040037400371110201100991001001000010000007101161139479100001004003840038400384003840038
1020440037300072361394072510100100100001001000050057069084001840037400373810833874510100200100002003000040037400371110201100991001001000010000007101161139479100001004003840038400384003840038
1020440037300066961394072510100100100001001000050057069084001840037400373810833874510100200100002003000040037400371110201100991001001000010000007101161139479100001004003840038400384003840038
10204400373000061394072510100100100001001000050057069084001840037400373810833874510100200100002003000040037400371110201100991001001000010000007101161139479100001004003840038400384003840038
10204400372990061394072510100100100001001000050057069084001840037400373810833874510100200100002003000040037400371110201100991001001000010000007101161139479100001004003840038400384003840038
10204400373000061394072510100100100001001000050057069084001840037400373810833874510100200100002003000040037400371110201100991001001000010000007101161139479100001004003840038400384003840038
10204400373001061394072510100100100001001000050057069084001840037400373810833874510100200100002003000040037400371110201100991001001000010000007101161139479100001004018140038400854003840038
10204400373000061394074510133100100001061044450057069084001840037400373810833874510100200100002003000040037400371110201100991001001000010000007101161139479100001004003840038400384003840038
10204400372990061394072510100100100001001000050057069084001840037400373810833874510100200100002003000040037400371110201100991001001000010000007101161139479100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)0308181e1f3f4e51inst 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)9fa0a1a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100244003730000006139407102100101010000101000050570690804001804003740037381303387671001020100002030000400374003711100211091010100001000000640216223947310000104003840038400384003840038
10024400373000000613940725100101010000101000050570690814001804003740037381303387671001020100002030000400374003711100211091010100001000000640216223947310000104003840038400384003840038
10024400373000000613940725100101010000101000050570690814001804003740037381303387671001020100002030000400374003711100211091010100001000030640216223947310000104003840038400384003840038
10024400373000021901793938925100101010000101000050570690804001804003740037381303387671060520100002030000400374003711100211091010100001000002640216223947310000104003840038400384003840038
10024400372990025801033940725100101010000101000050570690814001804003740037381303387671001020100002031938400374003711100211091010100001000000640216223947310000104003840038400384003840038
10024400372990029402313940725100101010000101000050570690814001804022740037381303387671001020100002030000400374003711100211091010100001000000640216223947310000104003840038400384003840038
100244003730000660823940725100101010000101000050570690814015804003740037381303387671001020100002030000400374003711100211091010100001000000640216223947310000104003840038400384003840038
1002440037300002700613940725100101010000101000050570690814001804003740037381303388441001020100002030000400374003711100211091010100001000000640216223947310000104003840038400384003840038
1002440037300003000613940725100101010000101000050570690804001804003740037381303387671001020100002030000400374003711100211091010100001000000640216223947310000104003840038400384003840038
100244003730000390613940725100101010000101000050570690804001804003740037381303387671001020100002030000400374003711100211091010100001000000640216223947310000104003840038400384003840038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  fmls v0.2d, v8.2d, v9.2d
  movi v1.16b, 0
  fmls v1.2d, v8.2d, v9.2d
  movi v2.16b, 0
  fmls v2.2d, v8.2d, v9.2d
  movi v3.16b, 0
  fmls v3.2d, v8.2d, v9.2d
  movi v4.16b, 0
  fmls v4.2d, v8.2d, v9.2d
  movi v5.16b, 0
  fmls v5.2d, v8.2d, v9.2d
  movi v6.16b, 0
  fmls v6.2d, v8.2d, v9.2d
  movi v7.16b, 0
  fmls v7.2d, v8.2d, v9.2d
  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)031e1f3a3f51inst 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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602042006515100040258010010080000100800005006400000120046200652006503238010020080000200240000200652006511160201100991001001600001000001011111611200621600001002006620066200662006620066
1602042006515000040258010010080000100800005006400000020046200652006503238010020080000200240000200652006511160201100991001001600001000001011111611200621600001002006620066200662006620066
1602042006515000040258010010080000100800005006400000120046200652006503238010020080000200240000200652006511160201100991001001600001000001011111611200621600001002006620066200662006620066
1602042006515000040258010010080000100801075006400000020046200652006503238010020080000200240000200652006511160201100991001001600001000001011111611200621600001002006620066200662006620066
16020420065150390082258010010080000100800005006400000120046200652006503238010020080000202240000200652006511160201100991001001600001000001011111611200621600001002006620066200662006620066
1602042015015100040258010010080000100800005006434560120046200652006503238010020080000200240000200652006511160201100991001001600001000001011111611200621600001002006620066200662006620066
1602042006515000040258010010080000100800005006400000020046200652006503238010020080000200240000200652006511160201100991001001600001000001011111611200621600001002006620066200662006620066
1602042006515000040258010010080000100800005006400000120046200652006503238010020080000200240000200652006511160201100991001001600001000001011111611200621600001002006620066200662006620066
1602042006515000040258010010080000100800005006400000120046200652006503238010020080000200240000200652006511160201100991001001600001000001011111614200621600001002006620066200662006620066
1602042006515000040258010010080000100800005006400000120046200652006503238010020080000200240000200652006511160201100991001001600001000001011111611200621600001002006620066200662006620066

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03071e1f3f51inst 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)9fa6a8cdcfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1600242005015020052258001212800001280000626400001120032200532005332380012208000020240000200532005311160021109101016000010000100286116243226620048231160000102005220052200482005420054
1600242005315000081258001212800001280000626400002120028200472004732380012208000020240000200472004711160021109101016000010000100293118202118820044215160000102004820048200482004820048
16002420047150012046258001212800001280000626400002120028200472004732380012208000020240000200472004711160021109101016000010000100283115202116720044215160000102004820048200482004820048
1600242004715000046258001212800001280000626400002120028200472004732380012208000020240000200472004711160021109101016000010000100283115202115520044215160000102004820048200482004820048
1600242004715000046258001212800001280000626400002120028200472004732380012208000020240000200472004711160021109101016000010000100303115202116520044215160000102004820048200482004820048
1600242004715000046258001212800001280000626400000120028200532004732380012208000020240000200532005311160021109101016000010000100303116202115620044215160000102004820048200482004820048
1600242004715000046258001212800001280000626400001120028200472004732380012208000020240000200472004711160021109101016000010000100336225244225620048230160000102004820048200482004820048
1600242004715100088258001212800001280000626400001120028200472004732380012208000020240000200472004711160021109101016000010000100293225263228520048231160000102005220052200522005220052
16002420053150000236258001212800001280000626400001120028200472004732380012208000020240000200472004711160021109101016000010010100293115202117820044215160000102004820048200482004820048
1600242004715100052258001212800001280000626400001120028200472004732380012208000020240000200472004711160021109101016000010010100313125244225620050230160000102005420052200542005420052

Test 6: throughput

Count: 16

Code:

  fmls v0.2d, v16.2d, v17.2d
  fmls v1.2d, v16.2d, v17.2d
  fmls v2.2d, v16.2d, v17.2d
  fmls v3.2d, v16.2d, v17.2d
  fmls v4.2d, v16.2d, v17.2d
  fmls v5.2d, v16.2d, v17.2d
  fmls v6.2d, v16.2d, v17.2d
  fmls v7.2d, v16.2d, v17.2d
  fmls v8.2d, v16.2d, v17.2d
  fmls v9.2d, v16.2d, v17.2d
  fmls v10.2d, v16.2d, v17.2d
  fmls v11.2d, v16.2d, v17.2d
  fmls v12.2d, v16.2d, v17.2d
  fmls v13.2d, v16.2d, v17.2d
  fmls v14.2d, v16.2d, v17.2d
  fmls v15.2d, v16.2d, v17.2d
  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)031e373f4e51inst 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)9fa6a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16020440158300004202516013510016000010016000050048117110412264004040040199730322252160100200160000200480000400404231811160201100991001001600001000016201011021611422911600001004124640041400414004141246
16020440043300120424695251601351001600351001600005001280000040021412454124519973031999816010020016000020048000042294400401116020110099100100160000100005701011011611400371600001004119140041422864120642295
160204412303090042889625160100100160000100160000500128000014227541245412451997303199981601002001600002004800004004040040111602011009910010016000010000001011011611412421600001004004140041400414004142282
160204400403000061025160100100160000100160000500128000004002140040400401997303211881601002001600002004800004004041245111602011009910010016000010000001011011611412421600001004004142295400424004140041
160204400403000064889625160100100160035100160000500128000014002140040400401997303199981601002001600002004800004004040040111602011009910010016000010000001011011611400371600001004004142319400414231940041
16020440040308459356102516010010016000010016000050012800000400214004040040199730319998160100200160000200480000412454124511160201100991001001600001000021001011011611400371600001004004140041422954004142295
160204400403000042025160100100160000100160000500128000004002140040400402115103199981601002001600002004800004124540040111602011009910010016000010000001011011611400371600001004231940041423194004140041
160204400403000061025160153100160053100160000500128000004002140040400401997303199981601002001600002004800004004040040111602011009910010016000010000001011011611400371600001004004142295412464004140041
16020440040299035234025160100100160000100160000500128000004122641245400401997303212031601002001600002004800004004040040111602011009910010016000010000001011011611423151600001004004142319400414231940041
16020441202300007070251601001001600001001600005005868333140021400404009019973032227616010020016000020048000040040423181116020110099100100160000100009601011011611400371600001004004142295412464004141246

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e373f4e51inst 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)9fa0a6a8acbranch mispredict (cb)cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16002440093309005108025160010101600001016000050128000011400214119040040199963211701600102016000020480000400404004011160021109101016000010000001002231125162112221400370208160000104004140041411914004140041
160024400613000047025160010101600001016000050128000010400214004040040199963200201600102016000020480000400404004011160021109101016000010000001002231120162112120400370208160000104004140041400414004140041
16002440077300005602516001010160000101600005012800001040021400404004019996320020160010201600002048000040040400401116002110910101600001000018001002431117162112117400370408160000104004140044412284122840041
16002440043299004702516001110160022101600005057152611040021400404004021118320020160010201600002048000040040400401116002110910101600001000017101002262119164111323400370208160000104004140041400414004140041
160024400433000047025160010101600011016000050128000011400214004040040199963200201600102016000020480000400404004011160021109101016000010000001002231117162122016400370208160000104004140041400414004140041
160024400412990053025160010101600001016000050128000001400244004040040199963200201600102016000020480000400404004011160021109101016000010000001002262113162112220400370208160000104004140041400414004140041
160024412093080047025160010101600001016000050181622601400214004040040199963200201600102016000020480000411904004011160021109101016000010020216010022612191621122184003702016160000104004140041400414004140041
160024412093000047025160010101600001016000050128000010400214004040040199963200231600102016000020480000400404004011160021109101016000010000001002431222164111922400370408160000104004140041400414004140041
1600244120929900530251600101016000010160000501280000114002140040400401999632002016001020160000204800004004040040111600211091010160000100000110022321201641116194003702016160000104004140041400414004140041
1600244120929900470251600101016000010160000505715261104002140040400401999632002016001020160000204800004004040040111600211091010160000100007201002231221162212223400370208160000104004140041400414004140041