Apple M1 Microarchitecture Research by Dougall Johnson

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

FMLAL (vector, 4S)

Test 1: uops

Code:

  fmlal v0.4s, v1.4h, v2.4h
  movi v0.16b, 1
  movi v1.16b, 2
  movi v2.16b, 3

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 1.000

Issues: 1.000

Integer unit issues: 0.000

Load/store unit issues: 0.000

SIMD/FP unit issues: 1.000

retire (01)cycle (02)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)a6a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10044037300613407251000100010005319081401840374037325833895100010003000403740371110011000000073116113473100040384038403840384038
10044037309613407251000100010005319081401840374037325833895100010003000403740371110021000000073116113473100040384038403840384038
10044037306613407251000100010005319081401840374037325833895100010003000403740371110011000000373116113473100040384038403840384038
10044037300613407251000100010005319081401840374037325833895100010003000403740371110011000000073116113473100040384038403840384038
10044037300613407251000100010005319081401840374037325833895100010003000403740371110011000002373116113473100040384038403840384038
10044037300613407251000100010005319081401840374037325833895100010003000403740371110011000000073116113473100040384038403840384038
10044037300613407251000100010005319081401840374037325833895100010003000403740371110011000000073116113473100040384038403840384038
10044037310613407251000100010005319081401840374037325833895100010003000403740371110011000000373116113473100040384038403840384038
10044037300613407251000100010005319081401840374037325833895100010003000403740371110011000000073116113473100040384038403840384038
10044037300613407251000100010005319081401840374037325833895100010003000403740371110011000000073116113473100040384038403840384038

Test 2: Latency 1->1

Code:

  fmlal v0.4s, v1.4h, v2.4h
  movi v0.16b, 1
  movi v1.16b, 2
  movi v2.16b, 3

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)030b1e3a3f4e51inst 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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102044003730000061394072510100100100001001000050057080461400184003740037381083387451010020010000200300004003740037111020110099100100100001000071002162239479100001004003840038400384003840038
102044003730000061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000071012162239479100001004003840038400384003840038
102044003730000061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000071012162239479100001004003840038400384003840038
102044003730000061393892510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000071012162239479100001004003840038400384003840038
102044003729900061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000071012162239479100001004003840038400384003840038
102044003730000061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000071012162239479100001004003840038400384003840038
102044003730000061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000071013162239479100001004003840038400384003840038
102044003730000061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000071012162239479100001004003840038400384003840038
102044003730000061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000071012162239479100001004003840038400384003840038
1020440037300000103394072510100100100001001000050057069081400184003740037381083387451010020010000200300004003740037111020110099100100100001000071013162239479100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)030708090a0b18191e1f3a3f4e51inst 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)9fa1a6a7a9acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024400373001001000001633940725100101010000101000050570690814001804003740037381303387671001020100002030000400374003711100211091010100001000000000642716683947310000104003840038400384003840038
10024400373001001000001633940725100101010000101000050570690814001804003740037381303387671001020100002030000400374003711100211091010100001000000000642916883947310000104003840038400384003840038
10024400372991001000001633940725100101010000101000050570690804001804003740037381303387671001020100002030000400374003711100211091010100001000000000642716683947310000104003840038400384003840038
100244003730010010000016339407251001010100001010000505706908140018040037400373813033876710010201000020300004003740037111002110910101000010000000006421016863947310000104003840038400384003840038
10024400373001001000002633940725100101010000101000050570690814001804003740037381303387671001020100002030000400374003711100211091010100001000000000642716873947310000104003840038400384003840038
100244003730010010000016339407251001010100001010000505706908140018040037400373813033876710010201000020300004003740037111002110910101000010000000006421116883947310000104003840038400384003840038
100244003729910011000016339407251001010100001010000505706908140018040037400373813033876710010201000020300004003740037111002110910101000010000000006428161093947310000104003840038400384003840038
1002440037300100100000264394072510010101000010100005057069081400180400374003738130338767100102010000203000040037400371110021109101010000100000010064210161093947310000104003840038400384003840038
100244003730010010000016339407251001010100001010000505706908040018040037400373813033876710010201000020300004003740037111002110910101000010000000006448169103947310000104003840038400384003840038
1002440037300100100000163394072510010101000010100005057069080400180400374003738130338767100102010000203000040037400371110021109101010000100000000064210161093947310000104003840038400384003840038

Test 3: Latency 1->2

Code:

  fmlal v0.4s, v0.4h, v1.4h
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)030708091e1f3a3f4e51inst 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)9fa0a6a8a9accdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102044003730000000019353940725101251001000010010000500570690814001840037400373810833874510100211100002003000040037400371110201100991001001000010000000071011621394790100001004003840038400384003840038
1020440037300100000115394072510150100100001251000050057069081400184003740037381083387451010020010000200300004022740037111020110099100100100001004000213071011611394790100001004003840038400864008640038
10204400372990000001033940725101291231000612510000500570690814001840037400373811163874510100200100002003000040169400371110201100991001001000010000009071011688394790100001004003840038400384003840038
10204400373000000021473938925101001001000012510000500570690814001840037400373810833874510100200100002003000040037400371110201100991001001000010000000071011611394790100001004023140038400384003840038
1020440037299000000613940725101001001000012510000500570690804001840037400373810833874510100200100002003000040037400371110201100991001001000010000000071031681394790100001004003840038400384018040038
1020440037300000000613940725101001001000012510000500570690814001840037400373810833874510100200100002003000040037400371110201100991001001000010000000071411611394790100001004003840038400384003840038
1020440037300000000613940725101001001000012510000500570690804001840037400373810833874510100200100002003000040037400371110201100991001001000010000003071041611394790100001004003840038400384003840038
10204400373000000006139407251010010010000125100005005706908040018400374003738108338745101002001000020030000400374003711102011009910010010000100001010864071011611394790100001004003840038400384003840038
1020440037300000000613940725101001001000010010000500570690804001840037400373810833874510100200100002003000040037400371110201100991001001000010000000071011611394790100001004003840038400384003840038
1020440037300000300613940725101001001000012310000500570690814001840037400373810833874510100200100002003000040037400371110201100991001001000010002300071011611394790100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)030918191e3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8a9accdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100244003730000007263940725100101010000101000050570690804001840037400373813033876710010201000020300004003740037111002110910101000010006906402162239473010000104003840038400384003840038
10024400373000000823940725100101010000101000050570690804001840037400373813083876710010201000020300004003740037111002110910101000010008116402162239473010000104003840038400384003840038
100244003730000015613940725100101210000101000050570690804001840037400373813033876710010201000020300004003740037111002110910101000010008106402162239473010000104003840038400384003840038
1002440037300000061394072510010101000010100005057069080400184003740037381303387671001020100002030000400374003711100211091010100001000006402162239473010000104003840038400384003840038
1002440037300000061394072510010101000011101485057069080400184003740226381303387671001020100002030000400374003711100211091010100001000606402162239473010000104012040085400384003840038
100244003730000009623940725100101010000101000050570690804001840037400373813033876710010201000020309664008540037111002110910101000010005706402162239473010000104003840038400384003840038
10024400373000000613940725100101010000101000050570690804001840037400373813033876710010201000020300004003740037111002110910101000010007806402162239473010000104003840038400384003840038
100244003729900002513940725100101010000101000050570690804001840037400373813033882510010201000020300004003740037111002110910101000010208106402162239473010000104003840038400384003840038
10024400373000000613940725100101010000101000050570690804001840037400373813033876710010201000020300004003740037111002110910101000010005706402162239473010000104003840038400384003840038
100244003730000006139407431001010100001010000505706908040018400374003738130203876710010201000020300004003740037111002110910101000010007206402162239473010000104003840038400384003840038

Test 4: Latency 1->3

Code:

  fmlal v0.4s, v1.4h, v0.4h
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)03191e3f4e51inst 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)9fa0a8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102044003730000613940725101001001000010010000500570690840018400374003738108338745101002001000020030000400374003711102011009910010010000100050607101161139479100001004003840038400384003840038
10204400373000061394072510100100100001001000050057069084001840037400843810833874510100200100002003000040037400371110201100991001001000010000307101161139479100001004003840038400384003840038
1020440037300018613940725101001001000010010000500570690840018400374003738108338745101002001000020030000400374003711102011009910010010000100007207101161139479100001004003840038400384003840038
102044003730009613940725101001001000010010000500570690840018400374003738108338745101002001000020030000400374003711102011009910010010000100054907101161139479100001004003840038400384003840038
102044003730000613940725101001001000010010000500570690840018400374003738108338745101002001000020030000400374003711102011009910010010000100053307101161139479100001004003840038400384003840038
102044022930000613940725101221061000010010000500570690840018400374003738108338745101002001000020030000400374003711102011009910010010000100055007101161139479100001004003840038400384003840038
1020440037300004803940725101001001000010010000500570690840018400374003738108338745101002001000020030000400374003711102011009910010010000100050307101161139479100001004003840038400384003840038
1020440037300001563940725101001001000010010000500570690840018400374003738108338745101002001000020030000400374003711102011009910010010000100050307101161139479100001004003840038400384003840038
102044003731006613940725101001001000010010000500570690840018400374003738108338745101002001000020030000400374003711102011009910010010000100053307101161139479100001004003840038400384003840038
102044003730000613940725101001001000010010000500570690840018400374003738108338745101002001000020030000400374003711102011009910010010000100055307101161139479100001004003840038400384003840038

1000 unrolls and 10 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)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
1002440037300000006139407251001010100001010000505706908040018400374003738155338767100102010178203000040037400371110021109101010000101006402162239473010000104003840038400384003840229
1002440084300000006139407451001010100001010000505706908040018400374003738130338767100102010000203000040037400371110021109101010000100006402162239473010000104003840038400384003840038
1002440037300000006139407251001010100001010000505706908040018400374003738130338767100102010000203000040037400371110021109101010000101006402162239473010000104003840038400384003840038
1002440037299000006139407251001010100001010000505706908040018400374003738130338767100102010000203000040037400371110021109101010000101006402162239473010000104003840038400384003840038
1002440037300000006139407251001010100001010000505706908040018400374003738130338767100102010000203000040037400371110021109101010000101006402162239473010000104003840038400384003840038
1002440037310000006139407251001010100001010000505706908040018400374003738130338767100102010000203000040037400371110021109101010000100006402162239473010000104003840038400384003840225
1002440037300000006139407251001010100001010000505706908040018400374003738130338767100102010000203000040037400371110021109101010000102006402162239473010000104003840038400384003840038
1002440037299000006139407251001010100001010000505706908040018400374003738130338767100102010000203000040037400371110021109101010000101006402162239473010000104003840038400384003840038
1002440037300000006139407251001010100001010000505706908040018400374003738130338767100102010000203000040037400371110021109101010000101006402162239473010000104003840038400384003840038
1002440037300000006139407251001010100001010000505706908040018400374003738130338767100102010000203000040037400371110021109101010000101006402162239473010000104003840038400384003840038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  fmlal v0.4s, v8.4h, v9.4h
  movi v1.16b, 0
  fmlal v1.4s, v8.4h, v9.4h
  movi v2.16b, 0
  fmlal v2.4s, v8.4h, v9.4h
  movi v3.16b, 0
  fmlal v3.4s, v8.4h, v9.4h
  movi v4.16b, 0
  fmlal v4.4s, v8.4h, v9.4h
  movi v5.16b, 0
  fmlal v5.4s, v8.4h, v9.4h
  movi v6.16b, 0
  fmlal v6.4s, v8.4h, v9.4h
  movi v7.16b, 0
  fmlal v7.4s, v8.4h, v9.4h
  movi v8.16b, 9
  movi v9.16b, 10

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)031e3f51inst 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)696d6escheduler 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
16020420089150061258010010080000100800005006400002004620065200653238010020080000200240000200652006511160201100991001001600001000010111216112006201600001002006620066200662006620066
16020420065150082258010010080000100800005006400002004620065200653238010020080000200240000200652006511160201100991001001600001000010111116112006201600001002006620066200662006620066
16020420065150040258010010080000100800005006400002004620065200653238010020080000200240000200652006511160201100991001001600001000010111116112013001600001002006620066200662006620066
16020420065151040258010010080000100800005006400002004620065200653238010020080000200240000200652006511160201100991001001600001000010111116112006201600001002006620066200662006620066
160204200651500126258010010080000100800005006400002004620065200653238010020080000200240000200652006511160201100991001001600001000010111116112006201600001002006620066200662006620066
16020420065150040258010010080000100800005006400002004620065200653238010020080000200240000200652006511160201100991001001600001001010111116112006201600001002006620066200662006620066
16020420065150063258010010080000100800005006400002004620065200653238010020080000200240000200652006511160201100991001001600001000010111116112006201600001002006620066200662006620066
16020420065150040258010010080000100800005006400002004620065200653238010020080000200240000200652006511160201100991001001600001001010111116112006201600001002006620066200662006620066
16020420065150061258010010080000100800005006400002004620065200653238010020080000200240000200652006511160201100991001001600001000010111116112006201600001002006620066200662006620066
16020420065150061258010010080000100800005006400002004620065200653238010020080000200240000200652006511160201100991001001600001000010111116112006201600001002006620066200662006620066

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e3f51inst 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)5f6061696b6d6escheduler 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)9fa8acc5cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1600242005715001152580012128000012800006264000011020028020047200473238001220800002024000020047200471116002110910101600001000010029321102021191320044215160000102004820048200482004820048
1600242004715004625800121280000128000062640000110200280200472004732380012208000020240000200472004711160021109101016000010000100303119202119820044215160000102004820048200482004820048
16002420047150046258001212800001280000626400001102002802004720047323800122080000202400002004720047111600211091010160000100001003331112202119720044215160000102004820048200482004820048
1600242004715004152580012128000012800006264000011020028020047200473238001220800002024000020047200471116002110910101600001000010030311112021161320044215160000102004820048200482004820048
16002420047150069258001212800001280000626400001102002802004720047323800122080000202400002005120047111600211091010160000100001003131162021171020044230160000102004820048200482004820048
160024200471505752258001212800001280000626400001102002802004720047323800122080000202400002004720047111600211091010160000100001003231162021181220044215160000102004820048200482004820048
16002420047150092258001212800001280000626400001102002802004720047323800122080000202400002004720047111600211091010160000101001003231162021171120044215160000102004820048200482004820048
1600242004715001722580012128000012800006264000011020028020047200473238001220800002024000020047200471116002110910101600001020010032311920211131220044215160000102004820048200482004820048
16002420047151046258001212800001280000626400001102002802004720047323800122080000202400002004720047111600211091010160000100001002931192021161220044215160000102004820048200482004820048
16002420047150067258001212800001280000626400001102002802004720047323800122080000202400002004720047111600211091010160000100001003331192021191320044215160000102004820048200482004820048

Test 6: throughput

Count: 12

Code:

  fmlal v0.4s, v12.4h, v13.4h
  fmlal v1.4s, v12.4h, v13.4h
  fmlal v2.4s, v12.4h, v13.4h
  fmlal v3.4s, v12.4h, v13.4h
  fmlal v4.4s, v12.4h, v13.4h
  fmlal v5.4s, v12.4h, v13.4h
  fmlal v6.4s, v12.4h, v13.4h
  fmlal v7.4s, v12.4h, v13.4h
  fmlal v8.4s, v12.4h, v13.4h
  fmlal v9.4s, v12.4h, v13.4h
  fmlal v10.4s, v12.4h, v13.4h
  fmlal v11.4s, v12.4h, v13.4h
  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): 0.3474

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)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)9fa0a8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
120204416853000072640274251201031001200031001200005005630640041667416864003927359324997120100200120000200360000416914003911120201100991001001200001000000761031631416831200001004169240040400404004040040
1202044169131200849961251201001001200001001200005005630640041667416864003924932324997120100200120000200360000416864169111120201100991001001200001000000761021632416771200001004168740040400404169241692
12020441686299006135689251201031001200031001200005005630640141672400394169126582326649120100200120000200360000416914003911120201100991001001200001000000761031623416771200001004168740040416874169241687
12020441686300036135689251201011001200011001200005005851869140020400394169126577326644120100200120000200360000400394169111120201100991001001200001000000761021633416771200001004168740040416874004041687
1202044169129903619961251201001001200001001200005005851869140020400394003924932324997120100200120000200360000400394168611120201100991001001200001000000761021623400301200001004004041687400404168940040
12020440039312008235689251201011001200011001200005005851993041672416864003924932324997120100200120000200360000400394003911120201100991001001200001002000761031633416831200001004004041687400404168740040
1202044003930093949961251201001001200001001200005005851869141667416864003924932324997120100200120000200360000400394003911120201100991001001200001000000761031633400301200001004169240040416924004040040
1202044003930703619961251201031001200011001200005005851869141672416864003924932324997120100200120000200360000416914168611120201100991001001200001000000761031633416771200001004004040040400404168740040
1202044003931203619961251201001001200001001200005005630640040020400394003924932324997120100200120000200360000416864003911120201100991001001200001000000761031623416831200001004168740040416924004041687
1202044168630003669961251201001001200001001200005005851993041667416864003924932324997120100200120000200360000400394168611120201100991001001200001000000761031625416771200001004004040040400404004040040

1000 unrolls and 10 iterations

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

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)5f60696b6d6edispatch 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)9fa0a8a9acc2cfd0d2icache miss (d3)itlb miss (d4)d5d6d9dadbddinst fetch restart (de)e0eaebec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
120024400393000006799612512001010120000101200005058518691040020040039400392495503250191200102012000020360000400394003911120021109101012000010000007522311211516111139400301694120000104004040040400404004040040
1200244003930000067996125120010101200001012000050563064011400200400394003927382032501912001020120000203600004003940039111200211091010120000100000075223112111161121411400301595120000104004040040400404004040040
120024400393000006799612512001010120000101200005056306401040020040039400392495503250191200102012000020360000400394003911120021109101012000010000007522311209162111514400301697120000104004040040400404004040040
1200244003930000167996125120010101200001012000050596638610400200400394003924955032745012001020120000203600004003940039111200211091010120000100000075243112016162112014400301694120000104004040040400404004040040
1200244003930000073996125120010101200001012000050563064010400200400394003924955032501912001020120000203600004003940039111200211091010120000100000075223114114162111313400301595120000104004040040400404004040040
1200244003930000067996125120010101200001012000050563064011400200400394003926600032501912001020120000203600004003940039111200211091010120000100000075223115013162211115400301595120000104004040040400404004040040
120024400393000004706996125120010101200001012000050563064000400200400394003924955032501912001020120000203600004003940039111200211091010120000100000075223116010161111313400301694120000104004040040400404004040040
12002440039300000679961251200101012000010120000505630640114002004003940039249550325019120010201200002036000040039400391112002110910101200001001000752231141101611214144003015174120000104004040040400404004040040
12002440039300000733568925120010101200001012000050563064011400200400394003924955032501912001020120000203600004003940039111200211091010120000100000075223113010162111613400301694120000104004040040400404004040040
12002440039300000732996125120010101200001012000050563064010400200400394003924955032501912001020120000203600004003940039111200211091010120000100003075223111011162111213416781594120000104004040040400404004040040