Apple M1 Microarchitecture Research by Dougall Johnson

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

FMLSL (by element, 4S)

Test 1: uops

Code:

  fmlsl v0.4s, v1.4h, v2.h[1]
  movi v0.16b, 1
  movi v1.16b, 2
  movi v2.16b, 3

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 1.000

Issues: 1.000

Integer unit issues: 0.000

Load/store unit issues: 0.000

SIMD/FP unit issues: 1.000

retire (01)cycle (02)031e3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op fp/simd (7e)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst neon or fp (9a)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004403730366134072510001000100053190814018403740373258338951000100030004037403711100110000073116113473100040384038403840384038
100440373006134072510001000100053190804018403740373258338951000100030004037403711100110000073116113473100040384038403840384038
100440373006134072510001000100053190804018403740373258338951000100030004037403711100110000373116113473100040384038403840384038
1004403730014734072510001000100053190804018403740373258338951000100030004037403711100110000073116113473100040384038403840384038
100440373006134072510001000100053190804018403740373258338951000100030004037403711100110000073116113473100040384038403840384038
100440373008234072510001000100053190804018403740373258338951000100030004037403711100110000073116113473100040384038403840384038
100440373106134072510001000100053190804018403740373258338951000100030004037403711100110000073116113473100040384038403840384038
100440373006134072510001000100053190804018403740373258338951000100030004037403711100110000373116113473100040384038403840384038
100440373006134072510001000100053190804018403740373258338951000100030004037403711100110000073116113473100040384038403840384038
100440373066134072510001000100053190814018403740373258338951000100030004037403711100110000373116113473100040384038403840384038

Test 2: Latency 1->1

Code:

  fmlsl v0.4s, v1.4h, v2.h[1]
  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)0308191e3f4e51inst 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)9fa1a6a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204400372990006139407251010010010000100100005005706908040123400374003738108338745101002001000020030000400374003711102011009910010010000100000007103163339479100001004003840038400384003840038
102044003729900216139407251010010010000100100005005706908040018400374003738108338745101002001000020030000400374003711102011009910010010000100000007103163339479100001004003840038400384003840038
102044003729910061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740084311020110099100100100001000000637104163339479100001004003840038400384003840038
1020440037300000613940725101001001000010010000500570690804001840037400373810833874510100200100002003000040037400371110201100991001001000010000101087103163339479100001004003840038400384003840038
1020440037300000613940725101001001000010010000500570690804001840037400373810833874510100200100002003000040037400371110201100991001001000010000002167103164339479100001004003840038400384003840038
1020440037300000613940725101001001000010010000500570690804001840037400373810833874510100200100002003000040037400371110201100991001001000010000002197103163439479100001004003840038400384003840038
1020440037299000613940725101001001000010010000500570690804001840037400373810833874510100200100002003000040037400371110201100991001001000010000002137123163439479100001004003840038400384003840038
10204400373000006139407251010010010000100100005005706908040018400374003738108338745101002001000020030000400374003711102011009910010010000100000007103163339479100001004003840038400384003840038
10204400373000006139407251010010010000100100005005706908040018400374003738108338745101002001000020030000400374003711102011009910010010000100000007103163339479100001004003840038400384003840038
10204400372990006139407251010010010000100100005005706908040018400374003738108338745101002001000020030000400374003711102011009910010010000100000007103163339479100001004003840038400384003840038

1000 unrolls and 10 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
10024400372990001683940725100101010000101000050570690814001840037400373813033876710010201000020300004003740037111002110910101000010006402162239473010000104003840038400384003840038
10024400373000001283940725100101010000101000050570690804001840037400373813033876710010201000020300004003740037111002110910101000010006402162239473010000104003840038400384003840038
10024400373000001053940725100101010000101000050570690804001840037400373813033876710010201000020300004003740037111002110910101000010006402162239473010000104003840038400384003840038
10024400373000005093940725100101010000101000050570690814001840037400373813033876710010201000020300004003740037111002110910101000010006402162239473010000104003840038400384003840038
10024400373000004203940725100101010000101000050570690814001840037400373813033876710010201000020300004003740037111002110910101000010006402162239473010000104003840038400384003840038
10024400373000001053940725100101010000101000050570690804001840037400373813033876710010201000020300004003740037111002110910101000010006402162239473010000104003840038400384003840038
10024400373000004493940725100101010000101000050570690814001840037400373813033876710010201000020300004003740037111002110910101000010006402162239473010000104003840038400384003840083
10024400373000001033940725100101010000101000050570690814001840037400373813033876710010201000020300004003740037111002110910101000010006402162239473010000104003840038400384003840038
1002440037300000613940725100101010000101000050570690804001840037400373813033876710010201000020300004003740037111002110910101000010006402162239473010000104003840038400384003840038
10024400372990001283940725100101010000101000050570690814001840037400373813033876710010201000020300004003740037111002110910101000010006402162239473010000104003840038400384003840038

Test 3: Latency 1->2

Code:

  fmlsl v0.4s, v0.4h, v1.h[1]
  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)030b1e1f3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204400373000002333940725101001001000010010000500570690804001840037400373810803387451010020010000200300004003740037111020110099100100100001000071021622394790100001004003840038400384003840038
10204400373000001243940725101001001000010010000500570690804001840037400373810803387451010020010000200300004003740037111020110099100100100001000071021622394790100001004003840038400384003840038
1020440037299000613940744101101001000010010000500570690814001840037400373810803387451010020010000200300004003740037111020110099100100100001000071021622394790100001004003840038400384003840038
1020440037299000613940725101001001000010010000500570690814001840037400373810803387451010020010000200300004003740037111020110099100100100001000071021622394790100001004003840038400384003840038
1020440037300000613940725101001001000010010000500570690814001840037400373810803387451010020010000200300004003740037111020110099100100100001000071021622394790100001004003840038400384003840038
10204400373000690613940725101001001000010010000500570690814001840037400373810803387451010020010000200300004003740037111020110099100100100001000071021622394790100001004003840038400384003840038
1020440037299000613940725101001001000010010000500570690814001840037400373810803387451010020010000200300004003740037111020110099100100100001000071021622394790100001004003840038400384003840038
1020440037300000613940725101001001000010010000500570690804001840037400373810803387451010020010000200300004003740037111020110099100100100001000071021622394790100001004003840038400384003840038
10204400372990002333940725101001001000010010000500570690804001840037400373810803387451026320010000200300004003740037111020110099100100100001000071021622394790100001004003840038400384003840038
1020440037300000613940725101001001000010010000500570690804001840037400373810803387451010020010000200300004003740037111020110099100100100001000071021622394790100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)030b191e3f4e51inst 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)9fa8acc5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100244003730000018939407251001010100001010000505706908140018400374003738130338767100102010000203000040037400371110021109101010000100006402162239473010000104003840038400384003840038
100244003730000045239407251001010100001010000505706908140018400374003738130338767100102010000203000040037400371110021109101010000100006402162239473010000104003840038400384003840038
100244003730000021039407251001010100001010000505706908140018400374003738130338767100102010000203000040037400371110021109101010000100006402162239473010000104003840038400384003840038
10024400373000006139407251001010100001010000505706908140018400374003738130338767100102010000203000040037400371110021109101010000100006402162239473010000104003840038400384003840038
10024400373000006139407251001010100001010000505706908140018400374003738130338767100102010000203000040037400371110021109101010000100006402162239473010000104003840038400384003840038
10024400373000006139407251001010100001010000505706908140018400374003738130338767100102010000203000040037400371110021109101010000100006402162239473010000104003840038400384003840038
10024400373000006139407251001010100001010000505706908140018400374003738130338767100102010000203000040037400371110021109101010000100006402162239473010000104003840038400384003840038
10024400373000006139407251001010100001010000505706908140018400374003738130338767100102010000203000040037400371110021109101010000100006402162239473010000104003840038400384003840038
10024400373000006139407251001010100001010000505706908140018400374003738130338767100102010000203000040037400371110021109101010000100006402162239473010000104003840038400384003840038
10024400372990006139407251001010100001010000505706908140018400374003738130338767100102010000203000040037400371110021109101010000100016402162239473010000104003840038400384003840038

Test 4: Latency 1->3

Code:

  fmlsl v0.4s, v1.4h, v0.h[1]
  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)030818191e1f3f4e51inst 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)9fa0a1a6a8a9acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102044003730000000393394072510100100100001001000050057069084001804003740037381083387451010020010000200300004003740037111020110099100100100001000003000071021611394790100001004003840038400384003840038
10204400373000000061394072510100100100001001000050057069084001804003740037381083387451010020010000200300004003740037111020110099100100100001000000000071011611394790100001004003840038400384003840038
10204400372990000061394072510100100100001001000050057069084001804003740037381083387451010020010000200300004003740037111020110099100100100001000000000071011611394790100001004003840038400384003840038
10204400372990000061394072510100100100001001000050057069084001804003740037381083387451010020010000200300004003740037111020110099100100100001000000000071011611394790100001004003840038400384003840038
10204400373000000061394072510100100100001001000050057069084001804003740037381083387451010020010000200300004003740037111020110099100100100001000000000071011612395830100001004003840038400384003840038
102044003730000000153394072510100100100001001000050057069084001804003740037381083387451010020010000200300004003740037111020110099100100100001000000000071011611394790100001004003840038400384003840038
10204400373000000061394072510100100100001001000050057069084001804003740037381083387451010020010000200300004003740037111020110099100100100001000000000071011611395530100001004003840038400384003840038
10204400373000000061394074410100100100001001000050057069084001804003740037381083387451010020010000200300004003740037111020110099100100100001000000000071011611394790100001004003840038400384003840038
10204400373000000061394072510100100100001001000050057069084001804003740037381083387451010020010000200300004003740037111020110099100100100001000000000071011611394790100001004003840038400384003840038
10204400372990000061394072510100100100001001000050057069084001804003740037381083387451010020010000200300004003740037111020110099100100100001000000000071011611394790100001004003840038400384003840038

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)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)9fa8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100244003729901703940725100101010000101000050570690814001804003740037381300338767100102010000203000040037400371110021109101010000100006402162339473010000104003840038400384003840038
100244003730001563940725100101010000101000050570690814001804003740037381300338767100102010000203000040037400371110021109101010000100006402162439473010000104003840038400384003840038
100244003730001213940725100101010000101000050570690814001804003740037381300338767100102010000203000040037400371110021109101010000100006402172439473010000104003840038400384003840038
10024400373009613940725100101010000101000050570690814001804003740037381300338767100102010000203000040037400371110021109101010000100006402162439473010000104003840038400384003840038
10024400373000613940725100101010000101000050570690814001804003740037381300338767100102010000203000040037400371110021109101010000100006402162439473010000104003840038400384003840038
10024400373000613940725100101010000101000050570690814001804003740037381300338767100102010000203000040037400371110021109101010000101206402162339473010000104003840038400384003840038
10024400373000663940725100101010000101000050570690814001804003740037381300338767100102010000203000040037400371110021109101010000100006402162339473010000104003840038400384003840038
10024400373000613940725100101010000101000050570690814001804003740037381300338767100102010000203000040037400371110021109101010000100006402162339473010000104003840038400384003840038
10024400373000613940725100101010000101000050570690814001804003740037381300338767100102010000203000040037400371110021109101010000100006402162439473010000104003840038400384003840038
10024400373000613940725100101010000101000050570690814001804003740037381300338767100102010000203000040037400371110021109101010000100006402162439473010000104003840038400384003840038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  fmlsl v0.4s, v8.4h, v9.h[1]
  movi v1.16b, 0
  fmlsl v1.4s, v8.4h, v9.h[1]
  movi v2.16b, 0
  fmlsl v2.4s, v8.4h, v9.h[1]
  movi v3.16b, 0
  fmlsl v3.4s, v8.4h, v9.h[1]
  movi v4.16b, 0
  fmlsl v4.4s, v8.4h, v9.h[1]
  movi v5.16b, 0
  fmlsl v5.4s, v8.4h, v9.h[1]
  movi v6.16b, 0
  fmlsl v6.4s, v8.4h, v9.h[1]
  movi v7.16b, 0
  fmlsl v7.4s, v8.4h, v9.h[1]
  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)031e1f3f51inst 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)9fa0a8accfd5d6d9ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160204200891500014525801001008000010080000500640000020046200652006532380100200800002002400002006520065111602011009910010016000010000010111216011200621600001002006620066200662006620066
16020420065150004025801001008000010080000500640000020046200652006532380100200800002002400002006520065111602011009910010016000010000010111116011200621600001002006620066200662006620066
1602042006515012108402580100100800001008000050064000002004620065200653238010020080000200240000200652006511160201100991001001600001000011110111116011200621600001002006620066200662006620066
160204200651510064625801001008000010080000500640000020046200652006532380100200800002002400002006520065111602011009910010016000010000010111116011200621600001002006620066200662006620066
16020420065150006376801001008000010080000500640000020046200652006532380100200800002002400002006520065111602011009910010016000010000010111116011200621600001002006620066200662006620066
16020420065150006125801001008000010080000500640000020046200652006532380100200800002002400002006520065111602011009910010016000010000010111116011200621600001002006620066200662006620066
16020420065151004025801001008000010080000500640000020046200652006532380100200800002002400002006520065111602011009910010016000010000010111116011200621600001002006620066200662006620066
16020420065150004025801001008000010080000500640000020046200652006532380100200800002002400002006520065111602011009910010016000010000010111116011200621600001002006620066200662006620066
16020420065150004025801001008000010080000500640000020046200652006532380100200800002002400002006520065111602011009910010016000010000010111116011200621600001002006620066200662006620066
16020420065150004025801001008000010080000500640000020046200652006532380100200800002002400002006520065111602011009910010016000010000010111116011200621600001002006620066200662006620066

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03191e1f3a3f51inst 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)9fa0a8acc2branch mispredict (cb)cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1600242007115000004625800121280000128000062640000115200282004720047323800122080000202400002004720047111600211091010160000100000010033811152023449920044215160000102004820048200482005220048
16002420047150000046258001212800001280000626400001152002820047200473238001220800002024000020047200471116002110910101600001000000100318521520230412620044215160000102004820048200482004820048
1600242004715000004625800121280000128000062640000115200322004720047323800122080000202400002004720047111600211091010160000100200010030851620229451520044215160000102004820048200482004820048
160024200471510000462580012128000012800006264000011520032200472004732380012208000020240000200512004711160021109101016000010000001003811511320234471320044215160000102004820048200482004820048
160024200471500000462580012128000012800006264000011520028200472004732380012208000020240000200472004711160021109101016000010000001003885192022647920044215160000102004820048200482004820048
1600242004715000004625800121280000128000062640000115200282004720047323800122080000202400002004720047111600211091010160000100000010027851520225291220048230160000102005220052200522005220052
16002420051150000046258001212800001280000626400001152002820047200473238001220800002024000020047200471116002110910101600001000020100371162724429451220044315160000102012920129200482015320048
160024200511500156104047425800121280000128000062640000015201202018120145323800122080000202400002005120051111600211091010160000100000010031116262442526920048230160000102005220052200522005220052
16002420051150000046258001212800001280000626400001152002820047200473238001220800002024000020047200471116002110910101600001000000100341162424425241220044215160000102004820048200482004820048
16002420047150090046258001212800001280000626400001152002820047200473238001220800002024000020047200471116002110910101600001000000100298511420219461420044215160000102004820048200482004820048

Test 6: throughput

Count: 12

Code:

  fmlsl v0.4s, v12.4h, v13.h[1]
  fmlsl v1.4s, v12.4h, v13.h[1]
  fmlsl v2.4s, v12.4h, v13.h[1]
  fmlsl v3.4s, v12.4h, v13.h[1]
  fmlsl v4.4s, v12.4h, v13.h[1]
  fmlsl v5.4s, v12.4h, v13.h[1]
  fmlsl v6.4s, v12.4h, v13.h[1]
  fmlsl v7.4s, v12.4h, v13.h[1]
  fmlsl v8.4s, v12.4h, v13.h[1]
  fmlsl v9.4s, v12.4h, v13.h[1]
  fmlsl v10.4s, v12.4h, v13.h[1]
  fmlsl v11.4s, v12.4h, v13.h[1]
  movi v12.16b, 13
  movi v13.16b, 14

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.3337

retire (01)cycle (02)03373f4e51inst 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)9fa8accdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
120204416863000619961251201001001200001001200005005630640040020400394003924932324997120100200120000200360000400394003911120201100991001001200001000007610216224003001200001004004040040400404004040040
120204400393000619961251201001001200001001200005005630640040020400394003924932324997120100200120000200360000400394003911120201100991001001200001000007610216224003001200001004004040040400404004040040
120204400393000899961251201001001200001001200005005630640140020400394169124932324997120100200120000200360000400394003911120201100991001001200001000007610216224003001200001004004040040400404004040040
12020440039300045849961251201001001200001001200005005851993040020400394003924932324997120100200120000200360000400394003911120201100991001001200001000007610216224003001200001004168940040400404004040040
120204400392990619961251201001001200001001200005005630640040020424704003924932324997120100200120000200360000400394003911120201100991001001200001000007610216224168301200001004004040040400404004040040
120204400393000619961251201001001200001001200005005630640040020400394003924932324997120100200120000200360000400394003911120201100991001001200001000007610216224003001200001004004040040400404004040040
120204400393000619961251201001001200001001200005005630640040020400394003924932324997120100200120000200360000400394003911120201100991001001200001000007610216224003001200001004004040040400404004040040
120204400393000619961251201001001200001001200005005630640040020400394003924932324997120100200120000200360000400394003911120201100991001001200001000307610216224003001200001004004040040400404004040040
120204400393000619961251201001001200001001200005005630640040020400394003924932324997120100200120000200360000400394003911120201100991001001200001000007610216224003001200001004004040040400404004040040
120204400392990619961251201001001200001001200005005630640140020400394003924932324997120100200120000200360000400394247011120201100991001001200001000007610216224003001200001004004040040400404004040040

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.3337

retire (01)cycle (02)0318191e1f373f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)5f6061696d6edispatch stall (70)72scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa0a6a7a8acc2cdcfd0d2d5d6d9ddinst fetch restart (de)e0? int output thing (e9)ec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
120024411063000000061996125120010101200001012000050563064001040020400394003924955032501912001020120000203600004003940039111200211091010120000100000000752050231601294003000120000104004040040400404004040040
120024400393000000061996125120010101200001012000050563064001540020400394003924955032501912001020120000203600004168640039111200211091010120000100000000752053151607114003000120000104004040040400404004040040
120024400393000000061996125120010101200001012000050563064001540020400394003924955032667112001020120000203600004003940039111200211091010120000100000000752053121609184003000120000104004040040400404004040040
120024400393000000061996125120010101200001012000050563064001540020400394003924955032501912001020120000203600004003940039111200211091010120000100000000752053816012124003000120000104004040040400404004040040
120024400393000000061996125120010101200001012000055563064001540020400394003924955032501912001020120000203600004003940039111200211091010120000100000000752054143509124003000120000104004040040400404004040040
1200244003930000000619961251200101012000010120000505630640015400204003940039249550325019120010201200002036000040039400391112002110910101200001020000407756541388211154150930120000104170841590417734163441875
120024413883081011804968523202552222712087712120795141219196057585490154043441611416112559807726114121979201222072036600341807410701011200211091010120000102210723300775654128808124131720120000104183941185415454114941383
120024413853101111133244061153235432521207991312085513121179555729109115400204003940039249550325019120010201200002036000040039400391112002110910101200001000000007520541116014144003000120000104004040040400404004040040
120024400393000000061996125120010101200001012000050562694201540020400394003924955032501912001020120000203600004003940039111200211091010120000100000000752054916013134003000120000104004040040400404004040040
1200244003929900000829961251200101012000010120000505630640015400204003940039249550325019120010201200002036000040039400391112002110910101200001000000007520541316011194003000120000104004040040400404004040040