Apple M1 Microarchitecture Research by Dougall Johnson

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

FMLS (by element, 8H)

Test 1: uops

Code:

  fmls v0.8h, v1.8h, 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)a8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10044037300613407251000100010005319080401840374037325833895100010003000403740371110011000073116113473100040384038403840384038
1004403730129613407251000100010005319080401840374037325933895100010003000403740371110011000073116113473100040384038403840384038
1004403730843833407251000100010005319080401840374037325833895100010003000403740371110011000073116113473100040384038403840384038
1004403730996134072510001000100053190804018403740373258338951000100030004037403711100110001073116113473100040384038403840384038
100440373033613407251000100010005319080401840374037325833895100010003000403740371110011000073116113473100040384038403840384038
10044037300613407251000100010005319080401840374037325833895100010003000403740371110011000073116113473100040384038403840384038
10044037300613407251000100010005319080401840374037325833895100010003000403740371110011000073116113473100040384038403840384038
10044037300613407251000100010005319080401840374037325833895100010003000403740371110011000473116113473100040384038403840384038
10044037310613407251000100010005319080401840374037325833895100010003000403740371110011000073116113473100040384038403840384038
10044037310613407251000100010005319080401840374037325833895100010003000403740371110011000073116113473100040384038403840384038

Test 2: Latency 1->1

Code:

  fmls v0.8h, v1.8h, 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)033a3f4e51inst 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)9fa8acc5branch mispredict (cb)cdcfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020440037300061394072510100100100001001000050057069080400184003740037381157387401010020010008200300244003740037111020110099100100100001000611171700160039489100001004003840038400384003840038
102044003729906139407251010010010000100100005005706908040018400374003738115738740101002001017420030024400374003711102011009910010010000100017111171700160039490100001004003840038400384003840038
1020440037300061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000000071012162239479100001004003840038400384003840038
10204400373000613940725101001001000010010000500570690804001840037400373810833874510100200100002003000040037400371110201100991001001000010001200071012162239479100001004003840038400384003840038
10204400373000613940725101001001000010010000500570690814001840037400373810833874510100200100002003000040037400371110201100991001001000010003000071012162239479100001004003840038400384003840038
102044003730006139407251010010010000100100005005706908040018400374003738108338745101002001000020030000400374003711102011009910010010000100014700071012162239479100001004003840038400384003840038
102044003729906139407251010010010000100100005005706908040018400374003738108338745101002001000020030000400374003711102011009910010010000100112900071012162239479100001004003840038400384003840038
102044008130006139407251010010010000100100005005706908040018400374003738108338745101002001000020030000400374003711102011009910010010000100013200071012162239479100001004003840038400384003840038
10204400373000613940725101001001000010010000500570690804001840037400373810833874510100200100002003000040037400371110201100991001001000010001500071012162239479100001004003840038400384003840038
102044003730006139407251010010010000100100005005706908040018400374003738108338745101002001000020030000400374003711102011009910010010000100012600071012162239479100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)031e1f3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024400372990061394072510010101000010100005057069084001840037400373813033876710010201000020300004003740037111002110910101000010443640216233947310000104003840038400384003840038
10024400373000061394072510010101000010100005057069084001840037400373813033876710010201000020300004003740037111002110910101000010440640216223947310000104003840038400384003840038
10024400372990061394074110010101000010100005057069084001840037400373813033876710010201000020300004003740037111002110910101000010453640216223947310000104003840038400384003840038
10024400372990061394072510010101000010100005057069084001840037400373813033876710010201000020300004003740037111002110910101000010069640216223947310000104003840038400384003840038
100244003730000613940725100101010000101000050570690840018400374003738130338767100102010000203000040037400371110021109101010000105014403640216223947310000104003840038400384003840085
1002440037299008239407251001010100001010000505706908400184003740037381303387671001020100002030000400374003711100211091010100001079640216223947310000104003840038400384003840038
10024400372993061394072510010101000010100005057069084001840037400373813033876710010201000020300004003740037111002110910101000010712640316223947310000104003840038400384003840038
1002440037300006139407251001010100001010000505706908400184003740037381303387671001020100002030000400374003711100211091010100001069640216223947310000104003840038400384003840038
10024400373000090394072510010101000010100005057069084001840037400373813033876710010201000020300004003740037111002110910101000010533662216223954510000104013240133400864003840038
1002440037300105920894339407251001010100001010000505706908400184003740037381303387671001020100002030000400374003711100211091010100001023640216223947310000104003840038400384003840038

Test 3: Latency 1->2

Code:

  fmls v0.8h, v0.8h, 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)03090b1e3f4e51inst 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)9fa0a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204400373000006139407251010010010000100100005005706908400184003740037381083387451010020010000200300004003740037111020110099100100100001000000007101161139479100001004003840038400384003840038
10204400373000006139407251010010010000100100005005706908400184003740037381083387451010020010000200300004003740037111020110099100100100001000010307101161139479100001004003840085400864008640038
10204400372990006139407251010010010000100100005005706908400184003740037381083387451010020010000200300004003740037111020110099100100100001000000007101161139479100001004003840038400384003840038
10204400373000006139407251010010010000100100005005706908400184003740037381083387451010020010000200300004003740037111020110099100100100001000000007101161139479100001004003840038400384003840038
10204400373000006139407251010010010000100101475005706908400184003740037381083387451010020010000200300004003740037111020110099100100100001000000007101161139479100001004003840038400384003840038
10204400373000006139407251010010010000100100005005706908400184003740037381083387451010020010000200300004003740037111020110099100100100001000040007101161139479100001004003840038400384003840038
10204400373000006139407251010010010000100100005005706908400184003740037381083387451010020010000200300004003740037111020110099100100100001000210007101161139479100001004003840038400384003840038
10204400372990006139407251010010010000100100005005706908400184003740037381083387451010020010000200300004003740037111020110099100100100001000010007101161139479100001004003840038400384003840038
10204400372990006139407251010010010000100100005005706908400184003740037381083387451010020010000200300004003740037111020110099100100100001000020007101161139479100001004003840038400384003840038
1020440037300001210339407251010010010000100100005005706908400184003740037381083387451010020010000200300004003740037111020110099100100100001007200357627101161139479100001004008640038400854013140038

1000 unrolls and 10 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)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)9fa0a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100244003729900147394072510010101000010100005057069081400184003740037381303387671001020100002030000400374003711100211091010100001000006402162239473010000104003840038400384003840038
100244003730000124394072510010101000010100005057069081400184003740037381303387671001020100002030000400374003711100221091010100001000006402162239473010000104003840038400384003840038
10024400372990061394072510010101000010100005057069081400184003740037381303387671001020100002030000400374003711100211091010100001000006402162239473010000104003840038400384003840038
100244003730000115394072510010101000010100005057069080400184003740037381303387671001020100002030000400374003711100211091010100001000006402162239473010000104003840038400384003840038
100244003729900290394072510010101000010100005057069081400184003740037381303387671001020100002030000400374003711100211091010100001000706402162239548010000104003840038400384003840038
100244003729900453394072510010101000010100005057069081400184003740037381303387671001020100002030000400374003711100211091010100001000006402162239473010000104003840038400384003840038
100244003730000212394072510010101000010100005057069081400184003740037381303387671001020100002030000400374003711100211091010100001000006402162239473010000104003840038400384003840038
10024400373000102149394072510010101000010100005057069080400184003740037381303387671001020100002030000400374003711100211091010100001000006402162239473010000104003840038400384003840038
100244003730000456394072510010101000010100005057069080400184003740037381303387671001020100002030000400374003711100211091010100001000006402162239473010000104003840038400384003840038
100244003730000421394072510010101000010100005057069080400184003740037381303387671001020100002030000400374003711100211091010100001000006402162239473010000104003840038400384003840038

Test 4: Latency 1->3

Code:

  fmls v0.8h, v1.8h, 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)031e1f3f4e51inst 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)9fa6a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204400373000021239407251010010010000100100005005706908140018400374003738108338745101002001000020030000400374003711102011009910010010000100001007102161139479100001004003840038400384003840038
10204400373000060439407251010010010000100100005005706908140018400374003738108338745101002001000020030000400374003711102011009910010010000100000007101161139479100001004003840038400384003840038
10204400373000049939407251010010010000100100005005706908040018400374003738108338745101002001000020030000400374003711102011009910010010000100000007101161139479100001004003840038400384003840038
10204400372990014939407251010010010000100100005005706908140018400374003738108338745101002001000020030000400374003711102011009910010010000100000007101161139479100001004003840038400384003840038
1020440037300006139407251010010010000100100005005706908140018400374003738108338745101002001000020030000400374003711102011009910010010000100000307101161139479100001004003840038400384003840038
10204400373000044539407251010010010000100100005005706908140018400374003738108338745101002001000020030000400374003711102011009910010010000100000007351161139479100001004003840038400384003840038
10204400373000032539407251010010010000100100005005706908140018400374003738108338745101002001000020030000400374003711102011009910010010000100000007101161139479100001004003840038400384003840038
10204400843000050439407251010010010000100100005005706908140018400374003738108338745101002001000020030000400374003711102011009910010010000100000007101161139479100001004003840038400384003840038
10204400373006054639407251010010010000100100005005706908140018400374003738108338745101002001017420030000400374003711102011009910010010000100000007101161139479100001004003840038400384003840038
10204400372990052939407251010010010000100100005005706908140018400374003738108338745101002001000020030000400374003711102011009910010010000100000007101161139479100001004003840038400384003840038

1000 unrolls and 10 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)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)9fa1a8acc5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002440037300008543940725100101010000101000050570690814001840037400373813003387671001020100002030000400374003711100211091010100001000006402162239473010000104003840038400384003840038
1002440037300001703940725100101010000101014855570690814001840037400373813003387671001020100002030000400374003711100211091010100001030006402162339475010000104003840038400384003840038
100244003730000613940725100101010000101000050570690814001840037400373813003387671001020100002030000400374003711100211091010100001000006402162239473010000104003840038400384003840038
1002440037300600613940725100101010000101000050570690814001840037400373813003387671001020100002030000400374003711100211091010100001000006402162239475010000104003840038400384003840038
1002440037300007143940725100101010000101000050570690814001840037400373813003387671001020100002030000400374003711100211091010100001000006402162239475010000104003840038400384003840038
1002440037300002283940725100101010000101000050570690814001840037400373813073387671001220100002030000400374003711100211091010100001000006402162239475010000104003840038400384003840038
1002440037299001493940725100101010000101000050570690814001840037400373813003387671001020100002030000400374003711100211091010100001000006402162239526010000104003840038400384003840038
100244003730000613940725100101010000101000050570690814001840037400373813003387671001020100002030000400374003711100211091010100001000006402162239475010000104003840038400384003840038
100244003730000613940725100101010000101000050570690814001840037400373813003387671001020100002030000400374003711100211091010100001000006402162239475010000104003840038400384003840038
100244003730000823940725100101010000101000050570690814001840037400373813003387671001020100002030000400844003711100211091010100001000006402162239475010000104003840038400384003840038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  fmls v0.8h, v8.8h, v9.h[1]
  movi v1.16b, 0
  fmls v1.8h, v8.8h, v9.h[1]
  movi v2.16b, 0
  fmls v2.8h, v8.8h, v9.h[1]
  movi v3.16b, 0
  fmls v3.8h, v8.8h, v9.h[1]
  movi v4.16b, 0
  fmls v4.8h, v8.8h, v9.h[1]
  movi v5.16b, 0
  fmls v5.8h, v8.8h, v9.h[1]
  movi v6.16b, 0
  fmls v6.8h, v8.8h, v9.h[1]
  movi v7.16b, 0
  fmls v7.8h, v8.8h, 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)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)60696b6d6escheduler 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)9fa6a7a8acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160204200911500040025801001008000010080000500640000120046020065200653238010020080000200240000200652006511160201100991001001600001000000001011251622200621600001002006620066200662006620066
16020420065150006325801001008000010080000500640000120046020065200653238010020080000200240000200652006511160201100991001001600001000000001011221622200621600001002006620066200662006620066
160204200651500087425801001008000010080000500640000120046020065200653238010020080000200240000200652006511160201100991001001600001000000001011221622200621600001002006620066200662006620066
16020420065150004025801001008000010080000500640000120046020065200653238010020080000200240000200652006511160201100991001001600001000010001011221622200621600001002006620066200662006620066
160204200651510010325801001008000010080000500640000120046020065200653238010020080000200240000200652006511160201100991001001600001000000001011221622200621600001002006620066200662006620066
160204200651500052125801001008000010080000500640000120046020065200653238010020080000200240000200652006511160201100991001001600001000000001011221622200621600001002006620066200662006620066
16020420065150004025801001008000010080000500640000120046020065200653238010020080000200240000200652006511160201100991001001600001000010001011221622200621600001002006620066200662006620066
16020420065150008225801001008000010080000500640000120046020065200653238010020080000200240000200652006511160201100991001001600001000000001011221622200621600001002006620066200662006620066
16020420065150004025801001008000010080000500640000120046020065200653238010020080000200240000200652006511160201100991001001600001000000001011221622200621600001002006620066200662006620066
160204200651500016825801001008000010080000500640000120046020065200653238010020080000200240000200652006511160201100991001001600001000000001011221622200621600001002006620066200662006620066

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)9fa6a8a9accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaebec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16002420074150000010927800121280000128000062640000115200332005220052323800122080000202400002005220052211600211091010160000100000100291131193421116162004922001160000102005320053200532005320053
16002420061150015000462780012128000012800006264000011520033200612005232380012208000020240000200612005211160021109101016000010000010039114116252116162004922001160000102005320053200532005320062
16002420052150000046278001212800001280000626400001152003320052200523238001220800002024000020052200521116002110910101600001000001003984116252216162004922001160000102005320053200532005320053
160024200521500750088278001212800001280216626400001152003320052200523238001220800002024000020052200521116002110910101600001000073910039841162521116162004922001160000102005320053200532005320053
160024200521500010804627800121280000128010962640000115200332013520052323800122080000202400002005220052111600211091010160000100000100398416252111662004922001160000102005320053200532005320053
1600242005215010001682780012128000012800006264000011520033200522005232380012208000020240000200522005211160021109101016000010000010040841162521116162004922001160000102005320053200532005320053
160024200521500000462780012128000012800006264000011520033200522005232380012208000020240000200522005211160021109101016000010000010040841162521116162004922001160000102005320053200532005320053
160024200521500540046278001212800001280000626400001152003320052200523238001220800002024000020061200521116002110910101600001000001003984116252116162004922001160000102005320053200532005320053
160024200521500510046278001212800001280000626400001152003320052200523238001220800002024000020052200521116002110910101600001000001003984116252116162004922001160000102005320053200532005320053
16002420052150057004627800121280000128000062640000115200332005220052323800122080000202400002005220052111600211091010160000100000100308416252116162004922001160000102005320053200532005320053

Test 6: throughput

Count: 12

Code:

  fmls v0.8h, v12.8h, v13.h[1]
  fmls v1.8h, v12.8h, v13.h[1]
  fmls v2.8h, v12.8h, v13.h[1]
  fmls v3.8h, v12.8h, v13.h[1]
  fmls v4.8h, v12.8h, v13.h[1]
  fmls v5.8h, v12.8h, v13.h[1]
  fmls v6.8h, v12.8h, v13.h[1]
  fmls v7.8h, v12.8h, v13.h[1]
  fmls v8.8h, v12.8h, v13.h[1]
  fmls v9.8h, v12.8h, v13.h[1]
  fmls v10.8h, v12.8h, v13.h[1]
  fmls v11.8h, v12.8h, 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)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)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)9fa0a1a6a7a8acc5cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1202044003930015016140274251201001001200011001200005005630640400204003941687265823249971201002001200002003600004003940039111202011009910010012000010000000000761011611416821200001004168940040400404168940040
120204400393121800619961251201541001200021001200005005630640416694003940039265903249971201002001200002003600004003940039111202011009910010012000010000000000761011611400301200001004168840040400404168940040
120204400393000026136348251201001001200001001200005005630640400204003941688249323249971201002001200002003600004168740039111202011009910010012000010000008000761011611424611200001004004040040400404004040040
12020440039312159001459961251201011001200001001200005005630640400204003940039265843249971201002001200002003600004003941688111202011009910010012000010000000000761011611400301200001004004040040400404168940040
1202044168830015006136348251201001001200011001200005005630640416684003940039265913249971201002001200002003600004003941688111202011009910010012000010000000000761011611416821200001004168940040400404168940040
120204400393124200619961251201001001200031001200005005630640400204003941688265663249971201002001200002003600004003940039111202011009910010012000010000000000761011611416791200001004168740040400404168940040
1202044168829933602619961251201011001200001001200005005630640400204003940039265913266451201002001200002003600004168840039111202011009910010012000010000000000761011611400301200001004004041689400404004041689
12020440039300351006136348251201001001200021001200005005856942400204003941688265933249971201002001200002003600004003941687111202011009910010012000010000000000761011611416791200001004168940040400404004040040
12020441687299279001569961251201011001200001001200005005848392400204003940039265843249971201002001200002003600004168740039111202011009910010012000010000000000761011611400301200001004004040040416894004041688
12020440039300423520619961251201011001200001001200005005630640400204003940039249323266461201002001200002003600004168840039111202011009910010012000010000000000761011611400301200001004168940040400404168940040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030818191e1f373a3f4e51inst 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)9fa0a1a6a8acc5cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaebec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1200244169930000000006799612512001010120000101200005056306401140020400394003924955325019120010201200002036000040039400391112002110910101200001000000075223117162117540030020105120000104004040040400404004040040
1200244003930000000009099612512001010120000101200005056306401141376400394003924955325019120010201200002036000040039400391112002110910101200001000000075223118162117540030020105120000104004040040416884168740040
1200244169130000000006799612512001010120000101200005056306401140020400394003924955325019120010201200002036000040039400391112002110910101200001020000075223116162116540030020105120000104004040040400404004040040
1200244003930000000006799612512001010120000101200005056306401140020400394003924955325019120010201200002036000040039400391112002110910101200001000000075223116162115640030020105120000104169241692400404004040040
1200244169130000000006799612512001010120000101200005056306401140020400394003924955325019120010201200002036000040039400391112002110910101200001000000075223116162116541692020105120000104004040040400404004040040
1200244003930000000006799612512001010120000101200005056306401140020400394003924955325019120010201200002036000040039400391112002110910101200001000000075223115162115540030020105120000104004040040400404004040040
1200244003929900000006799612512001010120000101200005056306401140020400394003924955325019120010201200002036000040039400391112002110910101200001000000075223116162118740030020105120000104004040040400404004040040
1200244003930000060006799612512001010120000101200005056306401140020400394003924955325019120010201200002036000040039400391112002110910101200001000000075223118162115940030020105120000104004040040400404004040040
1200244003930000000006799612512001010120000101200005056306401140020400394003924955325019120010201200002036000040039400391112002110910101200001000000075223117162116640030020105120000104004040040400404004040040
12002440039300000000067356892512001010120000101200005056306401140020400394003924955325019120010201200002036000041686400391112002110910101200001000000075223115162115840030020105120000104004041688400404004040040