Apple M1 Microarchitecture Research by Dougall Johnson

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

FMLSL2 (by element, 4S)

Test 1: uops

Code:

  fmlsl2 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)0318191e1f3f4e51inst 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
10044037300000613407251000100010005319081401840374037325833895100010003000403740371110011000073216223473100040384038403840384038
10044037300000613407251000100010005319081401840374037325833895100010003000403740371110011000073216223473100040384038403840384038
10044037300000613407251000100010005319081401840374037325833895100010003000403740371110011000073216223473100040384038403840384038
10044037300000613407251000100010005319081401840374037325833895100010003000403740371110011000173216223473100040384038403840384038
10044037300000613407251000100010005319081401840374037325833895100010003000403740371110011000073216223473100040384038403840384038
10044037300000613407251000100010005319081401840374037325833895100010003000403740371110011000073216223473100040384038403840384038
100440373000120613407251000100010005319081401840374037325833895100010003000403740371110011000073216223473100040384038403840384038
10044037311100613407251000100010005319081401840374037325833895100010003000403740371110011000073216223473100040384038403840384038
10044037300000613407251000100010005319081401840374037325833895100010003000403740371110011000073216223473100040384038403840384038
10044037300000613407251000100010005319081401840374037325833895100010003000403740371110011000073216223473100040384038403840384038

Test 2: Latency 1->1

Code:

  fmlsl2 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)030b18191e1f3a3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~issue ld/st (55)~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)9fa0a1a6a8a9acc2cfd0itlb miss (d4)d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102044003730000000066394072510100100100000100100005005706908140018040037400373810833874510100200100002003000040037400371110201100991001001000010000000007101021622394790100001004003840038400384003840038
1020440037300000000613940710210108100100000100100005005706908140018040037400373810833874510100200100002003000040037400371110201100991001001000010000000007101021622394790100001004003840038400384003840038
102044003730000000061394072510100100100000100100005005706908140018040037400373810833874510100200100002003000040037400371110201100991001001000010000010007101021623394790100001004003840038400384003840038
102044003729900000061394072510100100100000100100005005706908140018040037400373810833874510100200100002003000040037400371110201100991001001000010000020007101021622394790100001004003840038400384003840038
102044003730000000061394072510100100100000100100005005706908140018040037400373810833874510100200100002003000040037400371110201100991001001000010000000007101021622394790100001004003840038400384003840038
102044003730000000061394072510100100100000100100005005706908140018040037400373810833874510100200100002003000040037400371110201100991001001000010000000007101021632394790100001004003840038400384003840038
102044003729900000061394072510100100100000100100005005706908140018040037400373810833874510100200100002003000040037400371110201100991001001000010000000007101021622394790100001004003840038400384003840038
102044003729900000061394072510100100100000100100005005706908140018040084400373810833874510100200100002003000040037400371110201100991001001000010000000007101021622394790100001004003840038400384003840038
102044003730000000061394072510100100100000100100005005706908140018040037400373810833874510100200100002003000040037400371110201100991001001000010000000007101021622394790100001004003840038400384003840038
102044003730000000061394072510100100100000100100005005706908140018040037400373810833874510100200100002003000040037400371110201100991001001000010000010007101021622394790100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)030b1e3f4e51inst 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)9fa8acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024400373000061394072510010101000010100005057069081400184003740037381303387671001020100002030000400374003711100211091010100001000006403162239473010000104003840038400384003840038
100244003730000103394072510010101000010100005057069081400184003740037381303387671001020100002030000400374003711100211091010100001000006403162239473110000104003840038400384003840038
100244003729911261393894510010101000010100005057069081400184003740037381303387671001020100002030000400374003711100211091010100001000006402162239473010000104003840038400384003840038
10024400373000061394072510010101000010100005057069081400184003740037381303387671001020100002030000400374003711100211091010100001003006402162239473010000104003840038400384003840038
1002440037300012613940725100101010000101000050570690814001840037400373813033876710160201000020300004003740037111002110910101000010012406402162239473010000104003840038400384003840085
10024400372990300156394072510010101000010100005057069081400184003740037381303387671001020100002030000400374003711100211091010100001000006402162239473010000104003840038400384003840038
10024400373000061394072510010101000010100005057069081400184003740037381303387671001020100002030000400374003711100211091010100001000006402162239473010000104003840038400384003840038
10024400373000061394072510010101000010100005057069080400184003740037381303387671001020100002030000400374003711100211091010100001000006402162239473010000104003840038400384003840038
10024400373000061394072510010101000010100005057069081400184003740037381303387671001020100002030000400374003711100211091010100001000006402162239473010000104003840038400384003840038
10024400372990061394072510010101000010100005057069081400184003740037381303387671001020100002030000400374003711100211091010100001000006402162239473010000104003840038400384003840038

Test 3: Latency 1->2

Code:

  fmlsl2 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)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)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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204400373000006139407251010010010000100100005005706908040018400374003738108338745101002001000020030000400374003711102011009910010010000100207101161139479100001004003840038400384003840038
10204400373000006139407251010010010000100100005005706908040018400374003738108338745101002001000020030000400374003711102011009910010010000100007101161139479100001004003840038400384003840038
10204400373000006139407251010010010000100100005005706908040018400374003738108338745101002001000020030000400374003711102011009910010010000100007101161139479100001004003840038400384003840038
10204400373000006139407251010010910000100100005005706908040018400374003738108338745101002041000020030000400374003711102011009910010010000100007101161139479100001004003840038400384003840038
10204400373000006139407251010010010000100100005005706908140018400374003738108338745101002001033220030000400374003711102011009910010010000100007101161139479100001004003840038400384003840038
10204400373000006139407251010010010000100100005005706908040018400374003738108338745101002001000020030000400374003711102011009910010010000100007101161139479100001004003840038400384003840038
10204400373000006139407251010010010000100100005005706908140018400374003738108338745101002001000020030000400374003711102011009910010010000100007101161139479100001004003840038400384003840038
10204400373000006139407251010010010000100100005005706908040018400374003738108338745101002001000020030000400374003711102011009910010010000100007101161139479100001004003840038400384003840038
10204400373000006139407251010010010000100100005005706908040018400374003738108338745101002001000020030000400374003711102011009910010010000100007101161139479100001004003840038400384003840038
10204400373000006139407251010010010000100100005005706908040018400374003738108338745101002001000020030000400374003711102011009910010010000100007101161139479100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)03080b18191e3a3f4e51inst 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)9fa7a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002440037300010000613940725100101010000101000050570690840018400374003738130338767100102010000203000040037400371110021109101010000100006404163339473010000104003840038400384003840038
10024400373000000009533940725100101010000101000050570690840018400374003738130338767100102010000203000040037400371110021109101010000100006403163339473010000104003840038400384003840038
1002440037300000000613940725100101010000101000050570690840018400374003738130338767100102010000203000040037400371110021109101010000100036403163339473010000104003840038400384003840038
100244003730000002707263938925100101010000101000050570690840018400374003738130338767100102010000203000040037400371110021109101010000100006403163339473410000104003840038400384003840038
10024400373000000120613940725100101010000101000050570690840018400854003738130338767100102010000203000040037400371110021109101010000100006403163339473010000104003840038400384003840038
1002440037300000000613940725100101010000131000050570690840018400374003738130338767100102010000203000040037400371110021109101010000100036403163339473010000104003840038400384003840038
10024400373000000120613940725100101010000101000050570690840018400374003738130338767100102010000203000040037400371110021109101010000100007043163339473010000104003840038400384003840038
1002440037300000000613940725100101010000101000050570690840018400374003738130338767100102010000203000040037400371110021109101010000100006403163339473010000104003840038400384003840038
100244003730000005700613940725100101010000101000050570690840018400374008438130338767100102010000203000040037400371110021109101010000100006403163339473010000104003840038400384003840038
1002440037300000000613940725100101010000101000050570690840018400374003738130338767100102010000203000040037400371110021109101010000100006403163339473010000104003840038400384003840038

Test 4: Latency 1->3

Code:

  fmlsl2 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)03080b18191e1f3a3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020440037309000090061394072510100100100001001000050057069080400184003740037381080338745101002001000020030000400374003711102011009910010010000100000000071011611394790100001004003840038400384003840038
1020440037300000000061394072510100100100001001000050057069081400184003740037381080338745101002001016420230000400374003711102011009910010010000100000000071011611394790100001004003840038400384003840038
1020440037300000000061394072510100100100001001000050057069081400184003740037381080338745101002001000020030000400374003711102011009910010010000100000000071011611394790100001004003840038400384003840038
1020440037300000000061394072510100100100001001000050057069081400184003740037381080338745101002001000020030000400374003711102011009910010010000100000000071011611394790100001004003840038400384003840038
1020440037300000000061394072510100100100001001000050057069080400184003740037381080338745101002001000020030000400374003711102011009910010010000100000000071011611394790100001004003840038400384003840083
1020440037300000000089394072510100100100001001000050057069081400184003740037381080338745101002001000020030000400374003711102011009910010010000100000000071011611394790100001004003840038400384003840038
1020440037300000000061394072510100100100001001000050057069081400184003740037381080338745101002001000020030000400374003711102011009910010010000100000000071011611394790100001004003840038400384003840038
1020440037300000000061394072510100100100001001000050057069081400184003740037381080338745101002001000020030000400374003711102011009910010010000100000000071011611394790100001004003840038400384003840038
1020440037300000000061394072510100100100001001000050057069080400184003740037381080338745101002001000020030000400374003711102011009910010010000100000000071011611394790100001004003840038400384003840038
1020440037300000000061394072510100100100001001000050057069080400184003740037381080338745101002001000020030000400374003711102011009910010010000100000100071011611394790100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)031e3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696b6d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa1a6acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002440037300061394072510010101000010100005057069081400183400374003738130338767100102010000203000040037400371110021109101010000100000640516443947310000104003840038400384003840038
10024400373000613940725100101010000101000050570690814001804003740037381303387671001020100002030000400374003711100211091010100001000240640416443947310000104003840038400384003840038
1002440037300061394072510010101000010100005057069081400180400374003738130338767100102010161203048340037400371110021109101010000100000640316443947310000104003840038400384003840038
1002440037300061394072510010101000010100005057069081400180400374003738130338767100102010000203000040037400371110021109101010000100090640416443947310000104003840038400384003840038
1002440037299061394072510010101000010100005057069081400180400374003738130338767100102010000203000040037400371110021109101010000100000640416433947310000104003840038400384003840038
1002440037300061394072510010101000010100005057069081400180400374003738130338767100102010000203000040037400371110021109101010000100000640316433947310000104003840038400384003840038
1002440037300061394072510010101000010100005057069081400180400374003738130338767100102010000203000040037400371110021109101010000100000640416443947310000104003840038400384003840038
1002440037300061394072510010101000010100005057069081400180400374003738130338767100102010000203000040037400371110021109101010000100000640416443947310000104003840038400384003840038
1002440037299061394072510010101000010100005057069081400180400374003738130338767100102010000203000040037400371110021109101010000100000640416343947310000104003840038400384003840038
1002440037300061394072510010101000010100005057069081400180400374003738130338767100102010000203000040037400371110021109101010000100000640416343947310000104003840038400384003840038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  fmlsl2 v0.4s, v8.4h, v9.h[1]
  movi v1.16b, 0
  fmlsl2 v1.4s, v8.4h, v9.h[1]
  movi v2.16b, 0
  fmlsl2 v2.4s, v8.4h, v9.h[1]
  movi v3.16b, 0
  fmlsl2 v3.4s, v8.4h, v9.h[1]
  movi v4.16b, 0
  fmlsl2 v4.4s, v8.4h, v9.h[1]
  movi v5.16b, 0
  fmlsl2 v5.4s, v8.4h, v9.h[1]
  movi v6.16b, 0
  fmlsl2 v6.4s, v8.4h, v9.h[1]
  movi v7.16b, 0
  fmlsl2 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)030b1e3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)5f60696d6escheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa0a1a8branch mispredict (cb)cfd2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602042006515000402580100100800001008000050064000001200462006520065323801002008000020024000020065200651116020110099100100160000100000010111011611200621600001002006620066200662006620066
16020420065151001032580100100800001008000050064000000200462006520065323801002008000020024000020065200651116020110099100100160000100000010111011611200621600001002006620066200662006620066
1602042006515000402580100100800001008000050064000000200462006520065323801002008000020024000020065200651116020110099100100160000100000010111011611200621600001002006620066200662006620066
1602042006515000612580100100800001008000050064000000200462006520065323801002008000020024000020065200651116020110099100100160000100000010111011611200621600001002006620066200662006620066
1602042006515300402580100100800001008000050064000000200462006520065323801002008000020024000020065200651116020110099100100160000100000010111211611200621600001002006620066200662006620066
1602042006515000402580100100800001008000050064000000200462006520065323801002008000020024000020065200651116020110099100100160000100000010111011611200621600001002006620066200662006620066
1602042006515100682580100100800001008000050064000000200462006520065323801002008000020024000020065200651116020110099100100160000100000010111211611200621600001002006620066200662006620066
1602042006515000402580100100800001008000050064000000200462006520065323801002008000020024000020065200651116020110099100100160000100000010111011611200621600001002006620066200662006620066
1602042006515100632580100100800001008000050064000000200462006520065323801002008000020024000020065200651116020110099100100160000100000010111011611200621600001002006620066200662006620066
1602042006515000612580100100800001008000050064000000200462006520065323801002008000020024000020065200651116020110099100100160000100000010111011611200621600001002006620066200662006620066

1000 unrolls and 10 iterations

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

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)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)eaebec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160024200781511804627800121280000128000062640000115200332020820061323800122080000202400002005220061111600211091010160000100508100308411625211862004922001160000102005320053200532005320053
160024200521500046278001212800001280000626400001152003320200200523238001220800002024000020052200521116002110910101600001000100378411325211952004922001160000102005320053200532005320053
16002420052150270462780012128000012800006264000011520033201992005232380012208000020240000200522005211160021109101016000010631003184114252117520049220048160000102005320053200532005320053
160024200521506046278001212800001280000626400001152003320197200613238001220800002024000020052200521116002110910101600001000100298416252114132004922001160000102005320053200532005320053
160024200521500046278001212800001280000626400001152003320190200613238001220800002024000020052200521116002110910101600001000100338515252211111200492201633160000102005320053200532005320053
16002420052150141884627800121280000128000062640000115200332017320052323800122080000202400002005220052111600211091010160000100010030841725211662004922001160000102005320053200532005320053
16002420052150004627800121280000128000062640000115200332017820061323800122080000202400002005220052111600211091010160000100010033841725211862004922001160000102005320053200532005320053
160024200521500046278001212800001280000626400001152003320175200523238001220800002024000020052200521116002110910101600001000100328418252117132004924001160000102005320053200532005320053
160024200521500046278001212800001280000626400001152003320164200613238001220800002024000020052200521116002110910101600001000100328416252116112004922001160000102005320053200532005320053
1600242005215118046278001212800001280000626400001152003320210200523238001220800002024000020052200521116002110910101600001000100298415252117152004922001160000102005320053200532005320053

Test 6: throughput

Count: 12

Code:

  fmlsl2 v0.4s, v12.4h, v13.h[1]
  fmlsl2 v1.4s, v12.4h, v13.h[1]
  fmlsl2 v2.4s, v12.4h, v13.h[1]
  fmlsl2 v3.4s, v12.4h, v13.h[1]
  fmlsl2 v4.4s, v12.4h, v13.h[1]
  fmlsl2 v5.4s, v12.4h, v13.h[1]
  fmlsl2 v6.4s, v12.4h, v13.h[1]
  fmlsl2 v7.4s, v12.4h, v13.h[1]
  fmlsl2 v8.4s, v12.4h, v13.h[1]
  fmlsl2 v9.4s, v12.4h, v13.h[1]
  fmlsl2 v10.4s, v12.4h, v13.h[1]
  fmlsl2 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)0318191e373f4e51inst 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)9fa8cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
120204400392990039061996125120100100120001100120000500586048814002041687400392493203249971201002001200002003600004003940039111202011009910010012000010000761011611400301200001004004040040400404168941689
1202044168830000120613568925120101100120000100120000500563064014002042470400392493203249971201002001200002003600004003941688111202011009910010012000010000761011611400301200001004169240040400404004040040
12020440039312000061993825120100100120000100120000500563064014166941691400392657903249971201002001200002003600004003940039111202011009910010012000010000761011611400301200001004004040040400404169240040
120204400393000027161996125120100100120000100120000500585694214002041691400392493203249971201002001200002003600004168740039111202011009910010012000010001761011611400301200001004004041689400404004040040
12020440039312000161996125120100100120000100120000500563064014002040039400392657903266461201002001200002003600004003941688111202011009910010012000010000761011611416821200001004004040040400404168940040
120204400393000001613642925120103100120000100120000500586048814166941699400392493203249971201002001200002003600004247040039111202011009910010012000010000761011611400301200001004004040040400404168740040
120204400393000012061996125120101100120000100120000500563064014002041691400392657903249971201002001200002003600004003941688111202011009910010012000010000761011611400301200001004004040040400404004040040
120204400393000027061996125120100100120003100120000500563064014002041675416872657903249971201002001200002003600004003941688111202011009910010012000010000761011611416821200001004004041689400404004040040
120204400393130021161996125120100100120001100120000500563064014002041691416882657903266451201002001200002003600004168840039111202011009910010012000010000761011611400301200001004004041689400404004040040
12020440091312006161996125120100100120000100120000500585694214002042470400392493203249971201002001200002003600004003940039111202011009910010012000010000761011611400301200001004004040040416884004040040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030418191e373f4e51inst 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)9fa6a8acc2c5cdcfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0eaebec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1200244110629910090679961251200101012000010120000505630640114168040039416862495532501912001020120000203600004003940039111200211091010120000100000007522311716211774003020105120000104004040040400404004041687
120024400392990002706799612512001010120000101200005056306401141672400394168624955325019120010201200002036000040039400391112002110910101200001000180007522311616211654003020105120000104004040040400404004040040
1200244169130000000739961251200101012000310120000505630640014121840039410752660032501912001020120000203606064169140039111200211091010120000103034007522311524211584003020100120000104004040040416874004040040
12002440039312000120679961251200101012000310120000505630640114167240039400392495532666612001020120000203600004003940039111200211091010120000100100007522311516211774167820105120000104004040040400404004040040
1200244003929900000679961251200101012000010120000505630640114166740039416912660032501912001020120000203600004003940039111200211091010120000100000007522311616211874003020105120000104004041687412514169240040
12002440039300000240679961251200101012000010120000505630640114002040039400392495532501912001020120000203600004003940039111200211091010120000100000007522311616211654003020105120000104004040040400404004040040
12002440039300000006735689251200101012000010120000505630640114002040039400392660032666612001020120000203600004003940039111200211091010120000100000007522311716211884167820105120000104004041692400404169240040
1200244003930000003679961251200111012000310120000505630640114165640039400392495532501912001020120000203600004003940039111200211091010120000100000007522311516211774003020105120000104004040040400404168740040
1200244003930000000679961251200101012000010120000505851869114002040039400392495532501912001020120000203600004003940039111200211091010120000100000007522311616211674003020100120000104004040040400404004040040
1200244168630000000679961251200101012000010120000505630640114002040039400392660032501912001020120000203600004003940039111200211091010120000100300007522311616211854003020100120000104004040040400404004041692