Apple M1 Microarchitecture Research by Dougall Johnson

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

FCMLA (vector, 2S)

Test 1: uops

Code:

  fcmla v0.2s, v1.2s, v2.2s, #90
  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)6061696d6edispatch 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)a8accfd0d2d5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100440373006134072510001000100053190810401840374037325833895100010003000403740371110011000007300116113473100040384038403840384038
1004403730010334072510001000100053190810401840374037325833895100010003000403740371110011000007300116113473100040384038403840384038
100440373106134072510001000100053190810401840374037325833895100010003000403740371110011000007300116113473100040384038403840384038
100440373006134072510001000100053190810401840374037325833895100010003000403740371110011000007300116113473100040384038403840384038
100440373006134072510001000100053190810401840374037325833895100010003000403740371110011000007300116113473100040384038403840384038
100440373006134072510001000100053190810401840374037325833895100010003000403740371110011000007300116113473100040384038403840384038
100440373006134072510001000100053190810401840374037325833895100010003000403740371110011000007300116113473100040384038403840384038
100440373006134072510001000100053190810401840374037325833895100010003000403740371110011000007300116113473100040384038403840384038
100440373068234072510001000100053190810401840374037325833895100010003000403740371110011000007300116113473100040384038403840384038
100440373006134072510001000100053190810401840854037325833895100010003000403740371110011000007300116113473100040384038403840384038

Test 2: Latency 1->1

Code:

  fcmla v0.2s, v1.2s, v2.2s, #90
  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)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)9fa0a1a6a8acc5branch mispredict (cb)cdcfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102044003730000613940725101001001000010010000500570690840018400374003738115063874110100200100082003002440037400371110201100991001001000010000000111718041600394890100001004003840038400384003840038
102044003730000613940725101001001000010010000500570690840018400374003738115063874010100200100082003002440037400371110201100991001001000010000010111718001600394900100001004003840038400384003840038
1020440037300001563940725101001001000010010000500570690840018400374003738108033874510100200100002003000040037400371110201100991001001000010000000000710121622394790100001004003840038400384003840038
102044003730000613940725101001001000010010000500570690840018400374003738116033874510100200100002003000040037400371110201100991001001000010000000000710121622394790100001004003840038400384003840038
102044003729900613940725101001001000010010000500570690840018400374003738108033874510100200100002003000040037400371110201100991001001000010000000000710121622394790100001004003840038400384003840038
102044003729900613940725101001001000010010000500570690840018400374003738108733874510100200100002003000040037400371110201100991001001000010000000000710121632394790100001004003840038400384003840038
102044003729900613940725101001001000010010000500570690840018400374003738108033874510100200100002003000040037400371110201100991001001000010000000000710121623394790100001004003840038400384003840038
102044003730000613940725101001001000010010000500570690840018400374003738108033874510100200100002003000040037400371110201100991001001000010000000000710121622394790100001004003840038400384003840038
102044003730000613940725101001001000010010000500570690840018400374003738108033874510100200100002003000040037400371110201100991001001000010000000000710121623394790100001004003840038400384003840038
102044003730001613940725101001001000010010000500570690840018400374003738108033874510100200100002003000040037400371110201100991001001000010000000000710121623394790100001004003840038400384003840038

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)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)9fa8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100244003730000061394072510010101000010100005057069080400180400374003738130033876710010201000020300004003740037111002110910101000010000640216223947310000104003840038400384003840038
100244003730000061394072510010101000010100005057069080400180400374003738130033876710010201000020300004003740037111002110910101000010000640216223947310000104003840038400384003840038
100244003729900061394072510010101000010100005057069080400180400374003738130033876710010201000020300004003740037111002110910101000010000640216223947310000104003840038400384003840038
1002440037300000441394072510010101000010100005057069080400180400374003738130033876710010201000020300004003740037111002110910101000010000640216223947310000104003840038400384003840038
100244003730000061394072510010101000010100005057069080400180400374003738130033876710010201000020300004003740037111002110910101000010000640216223947310000104003840038400384003840038
100244003730000061394072510010101000010100005057069080400180400374003738130033876710010201000020300004003740037111002110910101000010000640216223947310000104003840038400384003840038
1002440037300000613940725100101010000101000050570690804001804003740037381300338767100102010000203000040037400371110021109101010000101330640216323947310000104003840038400384003840038
100244003730000061394072510010101000010100005057069080400180400374003738130033876710010201000020300004003740037111002110910101000010000640216223947310000104003840038400384003840038
1002440037300000251394072510010101000010100005057069080400180400374003738130033876710010201000020300004003740037111002110910101000010000640216223947310000104003840038400384003840038
100244003729900061394072510010101000010100005057069080400180400374003738130033876710010201000020300004003740037111002110910101000010000640216223947310000104003840038400384003840038

Test 3: Latency 1->2

Code:

  fcmla v0.2s, v0.2s, v1.2s, #90
  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)0304191e3f4e51inst 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)9fa8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102044003729910061394072510100100100001001000050057069081400184003740037381083387451010020010000200300004003740037111020110099100100100001000007101161139479100001004003840038400384003840038
1020440037300000631394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000007101161139479100001004003840038400384003840038
102044003729900061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000007101161139479100001004003840038400384003840038
102044003730000061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000007101161139479100001004003840038400384003840038
102044003730000061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000007101161139479100001004003840038400384003840038
102044003730000061394072510100100100001001000050057069080400184003740037381163387451010020010000200300004003740037111020110099100100100001000007101161139479100001004003840038400384003840038
102044003730000061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000007101161139479100001004003840038400384003840038
102044003730000061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000007101161139479100001004003840038400384003840038
102044003730000061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000007101161139479100001004003840038400384003840038
102044003730000061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000007101161139479100001004003840038400384003840038

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)9fa1a6a8acc5cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024400373000000613940725100101010000101000050570690814001840037400373813033876710010201000020300004003740037111002110910101000010000000640216223947310000104003840038400384003840038
100244003730000120613940725100101010000101000050570690814001840037400373813033876710010201000020300004003740037111002110910101000010002000640216223947310000104003840038400384003840038
10024400373000000613940725100101010000101000050570690814001840037400373813033876710010201000020300004003740037111002110910101000010001000640216223947310000104003840038400384003840038
10024400372990000613940725100101010000101000050570690814001840037400373813033876710010201000020300004003740037111002110910101000010000000640216223947310000104003840038400384003840038
10024400373000000613940725100101010000101000050570690814001840037400373813033876710010201000020300004003740037111002110910101000010000000640216223947310000104003840038400384003840038
10024400373000000613940725100101010000101000050570690804001840037400373813033876710010201000020300004003740037111002110910101000010000000640216223947310000104003840038400384003840038
1002440037300001201033940725100101010006101000050570690804005340037401333813033876710010201000020300004003740037111002110910101000010420000640216223947310000104003840038400384003840038
100244003730000001033940725100101010000101000050570690814001840037400373813033876710010201000020300004003740037111002110910101000010000000640216123947310000104003840038400384003840038
10024400373000000613940725100101010000101000050570690814001840037400373813033876710010201000020300004003740037111002110910101000010000000640216223947310000104003840038400384003840038
100244003730000004413940725100101010000101000050570690804001840037400373813033876710010201000020300004003740037111002110910101000010000000640216223947310000104003840038400384003840038

Test 4: Latency 1->3

Code:

  fcmla v0.2s, v1.2s, v0.2s, #90
  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)030b181e3a3f4e51inst 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)9fa0a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020440037300000061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000007101161139479100001004003840038400384003840038
10204400373000000256394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000007101161139479100001004003840038400384003840038
10204400373000000552394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000007101161139479100001004003840038400384003840038
1020440037299000082394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000007101161139479100001004003840038400384003840038
1020440037299000061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000007101161139479100001004003840038400384003840038
1020440037299000061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000007101161139479100001004003840038400384003840038
1020440037300000061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000007101161139479100001004003840038400384003840038
1020440037300000061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000007101161139479100001004003840038400384003840038
1020440037300000061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000007101161139479100001004003840038400384003840038
10204400373000000613940725101001001000010010000500570690804001840037400373810833874510100200100002003000040037400371110201100991001001000010001007101161139479100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)03080b191e1f3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)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)9fa0a6a7a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100244003730000000613940725100101010000101000050570690814001840037400373813033876710010201000020300004003740037111002110910101000010000006402162239473010000104003840038400384003840038
100244003729900000613940725100101010000101000050570690804001840037400373813033876710010201000020300004003740037111002110910101000010000006402162239473010000104003840038400384003840038
100244003730000000613939825100101010000101000050570690804001840037400373813033876710010201000020300004003740037111002110910101000010000006402162239473010000104003840038400384003840038
100244003730000000613940725100101010000101000050570690804001840037400373813033876710010201000020300004003740037111002110910101000010000006402162239473010000104003840038400384003840038
100244003730000000613940725100101010000101000050570690804001840037400373813033876710010201000020300004003740037111002110910101000010000006402162239473010000104003840038400384003840038
100244003730000000613940725100101010000101000050570690814001840037400373813033876710010201000020300004003740037111002110910101000010000006402162239473010000104003840038400384003840038
1002440037300000007263940725100101010000101000050570690814001840037400373813033876710010201000020300004003740037111002110910101000010000006402162239473010000104003840038400384003840038
100244003730000000613940725100101010000101000050570690814001840037400373813033876710010201000020300004003740037111002110910101000010000006402162239473010000104003840038400384003840038
100244003730000000613940725100101010000101000050570690804001840037400373813033876710010201000020300004003740037111002110910101000010000006402162239473010000104003840038400384003840038
100244003730000000613940725100101010000101000050570690804001840037400373813033876710010201000020300004003740037111002110910101000010000006402162239473010000104003840038400384003840038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  fcmla v0.2s, v8.2s, v9.2s, #90
  movi v1.16b, 0
  fcmla v1.2s, v8.2s, v9.2s, #90
  movi v2.16b, 0
  fcmla v2.2s, v8.2s, v9.2s, #90
  movi v3.16b, 0
  fcmla v3.2s, v8.2s, v9.2s, #90
  movi v4.16b, 0
  fcmla v4.2s, v8.2s, v9.2s, #90
  movi v5.16b, 0
  fcmla v5.2s, v8.2s, v9.2s, #90
  movi v6.16b, 0
  fcmla v6.2s, v8.2s, v9.2s, #90
  movi v7.16b, 0
  fcmla v7.2s, v8.2s, v9.2s, #90
  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)0307080a18191e1f3a3f51inst 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)60696d6e74scheduler 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
16020420078150000000002302580100100800001008000050064000012004620065200650323801002008000020024000020065200651116020110099100100160000100000000010112316222006201600001002006620066200662006620066
1602042006515000000000452580100100800001008000050064000012004620065200650323801002008000020024000020065200651116020110099100100160000100000000010112216222006201600001002006620066200662006620066
16020420065150000000004025801001008000010080000500640000120046200652006503238010020280000200240000200652006511160201100991001001600001000000021010112216222006201600001002006620066200662006620066
1602042006515000000000402580100100800001008000056064000012004620065200650323801002008000020024000020065200651116020110099100100160000100000100010112216222006201600001002006620066200662006620066
16020420065151000003000402580100100800001008000050064000012004620065200650323801002008000020024000020065200651116020110099100100160000100000000010112216222006201600001002006620066200662006620066
1602042006515000000000402580100100800001008000050064000002004620065200650323801002008000020024000020065200651116020110099100100160000100000000010112216222006201600001002006620066200662006620066
1602042006515000000000402580100100800001008000050064000012004620065200650323801002008000020024000020065200651116020110099100100160000100000000010112216222006201600001002006620066200662006620066
1602042006515000000000402580100100800001008000050064000012004620065200650323801002008000020024000020065200651116020110099100100160000100000000010112216222006201600001002006620066200662006620066
1602042006515000000000402580100100800001008000050064000012004620065200650323801002008000020024000020150200651116020110099100100160000100000300010112216222006201600001002006620066200662006620066
16020420065150000000004025801001008000010080000500640000020046200652006503238010020080000200240000200652006511160201100991001001600001000003003010112216222006201600001002006620066200662006620066

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e3a3f51inst 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
160024200761500046278001212800001280000626400001102003320052200523238001220800002024000020052200521116002110910101600001000100388111925211149200492401160000102005320053200532005320053
160024200611500046278001212800001280000626400001152003320052200523238001220800002024000020052200521116002110910101600001000100408411534211149200492201160000102005320053200532005320053
16002420052150015827800121280000128000062640000115200332005220052323800122080000202400002006120052111600211091010160000100010039114114252111515200492201160000102005320053200532006220053
1600242005215100462780012128000012800006264000011520033200522005232380012208000020240000200522005211160021109101016000010031003884115252111616200492201160000102005320053200532005320300
1600242005215000462780012128000012800006264000011520033200522005232380012208000020240000200522005211160021109101016000010001003684113252111414200492201160000102005320053200532005320053
1600242005215000462780012128000012800006264000011520033200522005232380012208000020240000200522005211160021109101016000010101003784115252111514200492201160000102005320053200532005320053
160024200521500046278001212800001280000626400001152003320052200523238001220800002024000020052200521116002110910101600001010100408419252111516200492201160000102005320053200532005320053
16002420052150012362780012128000012800006264000011520033200522005232380012208000020240000200522005211160021109101016000010201003785218252211415200492201160000102005320053200532005320053
160024200521500046278001212800001280000626400001152004220052200523238001220800002024000020052200521116002110910101600001000100388411525211159200492401160000102005320053200532005320053
16002420052152004627800121280000128000062640000115200332005220052323800122080000202400002005220146111600211091010160000100010036114113252111313200492201160000102005320053200532005320053

Test 6: throughput

Count: 16

Code:

  fcmla v0.2s, v16.2s, v17.2s, #90
  fcmla v1.2s, v16.2s, v17.2s, #90
  fcmla v2.2s, v16.2s, v17.2s, #90
  fcmla v3.2s, v16.2s, v17.2s, #90
  fcmla v4.2s, v16.2s, v17.2s, #90
  fcmla v5.2s, v16.2s, v17.2s, #90
  fcmla v6.2s, v16.2s, v17.2s, #90
  fcmla v7.2s, v16.2s, v17.2s, #90
  fcmla v8.2s, v16.2s, v17.2s, #90
  fcmla v9.2s, v16.2s, v17.2s, #90
  fcmla v10.2s, v16.2s, v17.2s, #90
  fcmla v11.2s, v16.2s, v17.2s, #90
  fcmla v12.2s, v16.2s, v17.2s, #90
  fcmla v13.2s, v16.2s, v17.2s, #90
  fcmla v14.2s, v16.2s, v17.2s, #90
  fcmla v15.2s, v16.2s, v17.2s, #90
  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)03080b1e373f4e51inst 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)6061696b6d6edispatch 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)9fa0a1a8accfd0d2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16020441598317000061884425160100100160000100160000500502220905411710411904120519973322243160100200160000200480000412054119011160201100991001001600001000020101105111611400371600001004120640044411914004440041
16020441190316000045025160100100160022100160000500128000005400240412054231819973319998160100200160000200480000412054119011160201100991001001600001000000101100011611400371600001004119140044400414004140041
160204400402990004361454125160122100160000100160000500570577410411860400404004019973321148160100200160000200480000411904004311160201100991001001600001000000101105111611400401600001004004140041400414004140041
160204400403000002242448525160100100160000100160000500128000015400210412054004021095321148160100200160000200480000400404004011160201100991001001600001000000101105111611412021600001004119141206423194004141206
16020441205300000042454125160101100160000100160000500131322310400210400404004022185319998160100200160000200480000412054119011160201100991001001600001000000101105111611412021600001004119141206411914004141191
16020440040309000061025160143100160043100160000500571526110400210400404004019973319998160100200160000200480000411904004311160201100991001001600001001013101105111611411871600001004004140041411914004441191
16020441190300000161025160100100160000100160000500131999910411860400404004019973321163160100200160000200480000400404004011160201100991001001600001000000101100011611400371600001004004140041411914120641191
160204411903080002242025160100100160043100160000500128000005411710400404004019973319998160100200160000200480000400434004011160201100991001001600001000000101105111611400371600001004004140041411914228240041
1602044004030000022709454125160100100160000100160000500128000010411710411904004319973319998160100200160000200480000400404004011160201100991001001600001000000101100011611400401600001004120641191412064119140041
160204400432991002243025160101116160000100160000500571526105411710411904004321111321163160100200160000200480000400404004011160201100991001001600001000000101100011611411871600001004120641191412064119141206

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03081e373f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)5f6061696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa0a8acc2c5cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1600244004930000186702516001010160000101600005012800001154002140040400402117332002016001020160000204800004004040040111600211091010160000100000010022811416422334003703010160000104004140521422824004141246
160024400402990001158970251600101016000012160000505868333015400214231840040211463200201602272016000020480318402184004011160021109101016000010000201002284121621123400370155160000104004140041400414004140041
16002440040300000670251600101016000010160000501280000115400214004040040199963200201600102016000020480000412194121911160021109101016000010000001002284121622133400370155160000104004140041400414004141246
160024400403000035470251600101016000010160000501280000215412264004040040199963200201600102016000020480000400404004011160021109101016000010000001002284131621132407940157160000104004140041400414004141246
16002440040300100470251600101016014110160000505721073115400214232740040199963200201600102016000020480000400404009111160021109101016000010020001002284141621123400370155160000104004140041400414124640041
160024400403000053670251600451016005310160000501280000115400214004042318222123222981600102016000020480000400404121911160021109101016000010000001002284121621124400370155160000104004140041422974004140041
16002440040309000478970251600101016000010160000501280000115400214121941219222443200201600102016000020480000423184004011160021109101016000010000001002284121621133400370156160000104004140041400414004140041
16002440040309000470251600101016000010160000505721073115412264124540040199963200201600102016000020480000400404228111160021109101016000010000001002284141621132423150305160000104004142319400414231942319
160024400403170004746952516001010160035101600005012800001154002140040400402117332002016001020160000204800004004040040111600211091010160000100000010022115121621123400370156160000104004140041400414124640041
160024400402990035670251600101016000010160000501280000115400214004040040199963200201600102016000020480000400404004011160021109101016000010000001002284121621123412160155160000104004140041400414231940041