Apple M1 Microarchitecture Research by Dougall Johnson

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

FMLAL2 (by element, 2S)

Test 1: uops

Code:

  fmlal2 v0.2s, v1.2h, 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)033f4e51inst 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)a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100440373061340725100010001000531908140184037403732583389510001000300040374037111001100000073216223473100040384038403840384038
100440373061340725100010001000531908040184037403732583389510001000300040374037111001100000073216223473100040384038403840384038
100440373061340725100010001000531908040184037403732583389510001000300040374037111001100000073216223473100040384038403840384038
100440373061340725100010001000531908040184037403732583389510001000300040374037111001100000073216223473100040384038403840384038
100440373061340725100010001000531908040184037403732583389510001000300040374037111001100000073216223473100040384038403840384038
100440373061340725100010001000531908040184037403732583389510001000300040374037111001100000073216223473100040384038403840384038
100440373061340725100010001000531908040184037403732583389511471000300040374037111001100000073216223473100040384038403840384038
100440373082340725100010001000531908140184037403732583389510001000300040374037111001100000073316223473100040384038403840384038
100440373161340725100010001000531908040184037403732583389510001000300040374037111001100000073216223473100040384038403840384038
1004403730143340725100010001000531908040184037403732583389510001000300040374037111001100001073216223473100040384038403840384038

Test 2: Latency 1->1

Code:

  fmlal2 v0.2s, v1.2h, 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)030b181e3a3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)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)9fa1a6a8a9accfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020440037299000061394072510100100100001001000050057069084001840037400373810833874510100200100002003000040037400371110201100991001001000010000100710021622394790100001004003840038400384003840038
1020440037300000061394072510100100100001001000050057069084001840037400373810833874510100200100002003000040037400372110201100991001001000010000000710021622394790100001004003840038400384003840038
102044003729900005363940725101001001000010010000500570690840018400374003738108338745101002001000020030000400374003711102011009910010010000100003700710121622394790100001004003840038400384003840038
1020440037300000061394072510100100100001001000050057069084001840037400373810833874510100200100002003000040037400371110201100991001001000010000000710121622394790100001004003840038400384003840038
1020440037300000061394072510100100100001001000050057069084001840037400373810833874510100200100002003000040037400371110201100991001001000010000000710121622394790100001004003840038400384003840038
1020440037299000061394072510100100100001001000050057069084001840037400373810833874510100200100002003000040037400371110201100991001001000010000000710121622394790100001004003840038400384003840038
1020440037300000061394072510100100100001001000050057069084001840037400373810833874510100200100002003000040037400371110201100991001001000010000000710131632394790100001004003840038400384003840038
1020440037300000061394072510100100100001001000050057069084001840037400373810833874510100200100002003000040037400371110201100991001001000010000000710121622394790100001004003840038400384003840038
1020440037300000061394072510100100100001001000050057069084001840037400373810833874510100200100002003000040037400371110201100991001001000010000000710121622394790100001004003840038400384003840038
1020440037300000061394072510100100100001001000050057069084001840083400373810833874510100200100002003000040037400371110201100991001001000010000000710121622394790100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)0308090b18191e1f3f4e51inst 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)9fa1a6a7a8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100244003730000000006139407251001010100001010000505706908140018400374003738130033876710010201000020300004003740037111002110910101000010000000640216323947310000104003840038400384003840038
100244003730000000006139407251001010100001010000505706908140018400374003738130033876710010201000020300004003740037111002110910101000010000000640217223947310000104003840038400384003840038
100244003730000000906139407251001010100001010000505706908140018400374003738130033876710010201000020300004003740037111002110910101000010000000640216223947310000104003840038400384003840038
100244003730000000006139407251001010100001010000505706908040018400374003738130033876710010201000020300004003740226111002110910101000010000000640216223947310000104003840038400384003840038
100244003730000000006139407251001010100001010000505706908140018400374003738130033876710010201000020300004003740037111002110910101000010000000640216223947310000104003840038400384003840038
100244003730000000006139407251001010100061010000505706908140018400374003738130033876710010201000020300004003740037111002110910101000010000000640216223947310000104003840038400384003840038
100244003730000000006139407251001010100001010000505706908140018400374003738130033876710010201000020300004003740037111002110910101000010000000640216223947310000104003840038400384003840038
100244003729900000006139407251001010100001010000505706908040018400844003738130033876710010201000020300004003740037111002110910101000010000000640216223947310000104003840082400384003840038
100244003729900000006139407251001010100001010000505706908140018400374003738130033876710010201000020300004003740037111002110910101000010000000640216223947310000104003840038400384003840038
100244003730000000006139407251001010100001010000505706908140018400374003738130033876710010201000020300004003740037111002110910101000010000000640216223947310000104003840038400384003840038

Test 3: Latency 1->2

Code:

  fmlal2 v0.2s, v0.2h, 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)031e3f4e5051inst 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)9fa6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102044003730006139407400212510100100100001001000050057069084001804003740037381083387451010020010000200300004003740037111020110099100100100001000007102161139479100001004003840038400384003840038
1020440037300053639407400212510100100100001001000050057069084001804003740037381083387451010020010000200300004003740037111020110099100100100001000007101161139479100001004003840038400384003840038
10204400373000613940702510100100100001001000050057069084001804003740037381083387451010020010000200300004003740037111020110099100100100001000007101161139479100001004003840038400384003840038
10204400373000613940702510100100100001001000050057069084001804003740037381083387451010020010000200300004003740037111020110099100100100001000007101161139479100001004003840038400384003840086
10204400373000613940702510100100100001001000050057069084001804003740037381083387451010020010000200300004003740037111020110099100100100001000007101161139479100001004003840038400384003840038
10204400373000613940702510100100100001001000050057069084001804003740037381083387451010020010000200300004003740037111020110099100100100001000007101161139479100001004003840038400384003840038
10204400373000613940702510100100100001001000050057069084001804003740037381083387451010020010000200300004003740037111020110099100100100001000107101161139479100001004003840038400384003840038
10204400373000613940702510100100100001001000050057069084001804003740037381083387451010020010000200300004003740037111020110099100100100001000007101161039479100001004003840038400384003840038
10204400373000613940702510100100100001001000050057069084001804003740037381083387451010020010000200300004003740037111020110099100100100001000007101161139479100001004003840038400384003840038
10204400373000613940702510100100100001001000050057069084001804003740037381083387451010020010000200300004003740037111020110099100100100001000007101161139479100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)03091e3f4e51inst 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
10024400373000961394072510010101000010100005057069080400184003740037381303387671001020100002030000400374003711100211091010100001000640316223947310000104003840038400384003840038
10024400372990061394072510010101000010100005057069080400184003740037381303387671001020100002030000400374003711100211091010100001000640216323947310000104003840038400384003840038
10024400372990061394072510010101000010100005057069080400184003740037381303387671001020100002030000400374003711100211091010100001000640216223947310000104003840038400384003840038
100244003729909170394072510010101000010100005057069080400184003740037381303387671001020100002030000400374003711100211091010100001003640216223947310000104003840038400384003840038
10024400373000082394072510010101000010100005057069080400184003740037381303387671001020100002030000400374003711100211091010100001000640216323947310000104003840038400384003840038
10024400373000061394072510010101000010100005057069080400184003740037381303387671001020100002030000400374003711100211091010100001000640216323947310000104003840038400384003840038
100244003729900726394072510010101000010100005057069080400184003740037381303387671001020100002030000400374003711100211091010100001000640216323947310000104003840038400384003840038
10024400373000061394072510010101000010100005057069080400184003740037381303387671001020100002030000400374003711100211091010100001000640216223947310000104003840038400384003840038
10024400373000061394072510010101000010100005057069080400184003740037381303387671001020100002030000400374003711100211091010100001000640216323947310000104003840038400384003840038
10024400373000061394072510010101000010100005057069080400184003740037381303387671001020100002030000400374003711100211091010100001000640216223947310000104003840038400384003840038

Test 4: Latency 1->3

Code:

  fmlal2 v0.2s, v1.2h, 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)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)9fa8acc5cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102044003730000000061394072510100100100001001000050057069084001840037400373810833874510100200100002003000040037400371110201100991001001000010000007102161139479100001004003840038400384003840038
1020440037300000000613940725101001001000010010000500570690840018400374003738108338745101002001000020030000400374003711102011009910010010000100015017101161139479100001004003840038400854003840038
102044003730000000061394072510100100100001001000050057069084001840037400373810833874510100200100002003000040037400371110201100991001001000010000007101161139479100001004003840038400384003840038
102044003730000000061394072510100100100001001000050057069084001840037400373810833874510100200100002003000040037400371110201100991001001000010000007101161139479100001004003840038400384003840038
102044003730000000061394072510100100100001001000050057069084001840037400373810833874510100200100002003000040037400371110201100991001001000010016007101161139479100001004003840038400384003840038
1020440037300002212161393982510100100100001001000050057069084001840037400373810833874510100200100002003000040037400371110201100991001001000010023007321161139479100001004003840038400384003840038
102044003730100000061394072510100100100001001000050057069084001840037400373810833874510100200100002003000040037400371110201100991001001000010000007101161139479100001004003840038400384003840038
102044003730000000061394072510100100100001001000050057069084001840037400373810833874510100200100002003000040080400371110201100991001001000010000007101161139479100001004003840038400384003840084
102044008530000000061394072510100100100001001000050057069084001840037400373810833874510100200100002003000040037400371110201100991001001000010000007101161139479100001004003840038400384003840038
1020440037300000000103394072510100100100001001000050057069084001840037400373810833874510100200100002003000040037400371110201100991001001000010003007101161139479100001004003840038400384003840038

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)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)9fa8a9acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100244003730000061394072510010101000010100005057069080400180400374003738130338767100102010000203000040037400371110021109101010000100000640216223947310000104003840038400384003840038
100244003730000061394072510010101000010100005057069080400180400374003738130338767100102010000203000040037400371110021109101010000100000640216223947310000104003840038400384013340038
1002440037300000346394072510010101000010100005057069080400180400374003738130338767100102010000203000040037400371110021109101010000100000640216223947310000104003840038400384003840038
100244003730000061394072510010101000010100005057069080400180400374003738130338767100102010000203000040037400371110021109101010000100000640216223947310000104003840038400384003840038
100244003730000061394072510010101000010100005057069080400180400374003738130338767100102010000203000040037400371110021109101010000100000640216223947310000104003840038400384003840038
100244003730000061394072510010101000010100005057069080400180400374003738130338767100102010000203000040037400371110021109101010000100000640216223947310000104003840038400384003840038
100244003730000061394072510010101000010100005057069080400180400374003738130338767100102010000203000040037400371110021109101010000100000640216323947310000104003840038400384003840038
100244003730000061394072510010101000010100005057069080400180400374003738130338767100102010000203000040037400371110021109101010000100000640216223947310000104003840038400384003840038
100244003730000061394072510010101000010100005057069080400180400374003738130338767100102010000203000040037400371110021109101010000100000640216223947310000104003840038400384003840038
100244003730000061394072510010101000010100005057069080400180400374003738130338767100102010000203000040037400371110021109101010000100000640216223947310000104003840038400384003840038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  fmlal2 v0.2s, v8.2h, v9.h[1]
  movi v1.16b, 0
  fmlal2 v1.2s, v8.2h, v9.h[1]
  movi v2.16b, 0
  fmlal2 v2.2s, v8.2h, v9.h[1]
  movi v3.16b, 0
  fmlal2 v3.2s, v8.2h, v9.h[1]
  movi v4.16b, 0
  fmlal2 v4.2s, v8.2h, v9.h[1]
  movi v5.16b, 0
  fmlal2 v5.2s, v8.2h, v9.h[1]
  movi v6.16b, 0
  fmlal2 v6.2s, v8.2h, v9.h[1]
  movi v7.16b, 0
  fmlal2 v7.2s, v8.2h, 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)03080a0b18191e1f3f51inst 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)9fa1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16020420065150000000082258010010080000100800005006400001200462006520065323801002008000020024000020065200651116020110099100100160000100000000010113316332006201600001002006620066200662006620066
160204200651500000000395258010010080000100800005006400001200462006520065323801002008000020024000020065200651116020110099100100160000100000000010113316232006201600001002006620066200662006620066
16020420065150000000040258010010080000100800005006400001200462006520065323801002008000020024000020065200651116020110099100100160000100000000010113316332006201600001002006620066200662006620066
16020420065150000000040258010010080000100800005006400001200462006520065323801002008000020024000020065200651116020110099100100160000100000000010113316332006201600001002006620066200662006620066
16020420065150000000040258010010080000100800005006400001200462006520065323801002008000020024000020065200651116020110099100100160000100000000010113316332006201600001002006620066200662006620066
16020420065150000000063258010010080000100800005006400001200462006520065323801002008000020024000020065200651116020110099100100160000100000000010113316332006201600001002006620066200662006620066
160204200651510000000774258010010080000100800005006400001200462006520065323801002008000020024000020065200651116020110099100100160000100000000010113316332006201600001002006620066200662006620066
16020420065151000000040258010010080000100800005006400001200462006520065323801002008000020024000020065200651116020110099100100160000100000000010113316332006201600001002006620066200662006620066
16020420065151000000040258010010080000100800005006400001200462006520065323801002008000020024000020065200651116020110099100100160000100000000010113316332006201600001002006620066200662006620066
16020420065150000000040258010010080000100800005006400001200462006520065323801002008000020024000020065200651116020110099100100160000100000000010113316332006201600001002006620066200662006620066

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e3a3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)5f6061696d6escheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16002420065150004625800121280000128000062640000115200282004720047323800122080000202400002004720051111600211091010160000100010030111257244222420048230160000102005220052200522004820052
16002420051151009425800121280000128000062640000015200322005120047323800122080000202400002005120051111600211091010160000100310027115212244222420044230160000102004820052200482005220052
16002420051150005225801151280000128000062640000015200322005120051323800122080000202400002005120047111600211091010160000100010025115252244222420048230160000102004820048200522005220048
16002420051150005225800121280000128000062640000015201442005120047323800122080000202400002004720051111600211091010160000100010030115213244112420044215160000102005420052200522005220052
16002420051150005225800121280000128011262640000115200322005120053323800122080000202400002005120051111600211091010160000100010030115244244222420044230160000102004820052200522005220048
16002420051150005225800121280000128000062640000015200322004720051323800122080000202400002005120053111600211091010160000100010030115225244224220048215160000102005220048200522005220052
160024200471500079925800121280000128000062640000115200322004720051323800122080000202400002005120051111600211091010160000100010030115244244122420048230160000102005220052200522005220052
16002420051150005225800121280000128000062640000115200282005120047323800122080000202400002005120053111600211091010160000100010030115214242222420044215160000102004820048200482004820048
16002420047150005812580012128000012800006264000011520028200472004732380012208000020240000200472004711160021109101016000010001002584252202112420046215160000102005220052200522005220052
16002420047150004625800121280000128000062640000115200282004720047323800122080000202400002004720047111600211091010160000100010028115225202116620044215160000102004820048200482005220048

Test 6: throughput

Count: 12

Code:

  fmlal2 v0.2s, v12.2h, v13.h[1]
  fmlal2 v1.2s, v12.2h, v13.h[1]
  fmlal2 v2.2s, v12.2h, v13.h[1]
  fmlal2 v3.2s, v12.2h, v13.h[1]
  fmlal2 v4.2s, v12.2h, v13.h[1]
  fmlal2 v5.2s, v12.2h, v13.h[1]
  fmlal2 v6.2s, v12.2h, v13.h[1]
  fmlal2 v7.2s, v12.2h, v13.h[1]
  fmlal2 v8.2s, v12.2h, v13.h[1]
  fmlal2 v9.2s, v12.2h, v13.h[1]
  fmlal2 v10.2s, v12.2h, v13.h[1]
  fmlal2 v11.2s, v12.2h, 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)03090b1e1f373f4e51inst 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)9fa8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
12020440039300000006199612512010010012000010012000050058519931400204169140039265820324997120100200120000200360000400394003911120201100991001001200001000007610216114003001200001004004041687400404169240040
120204400393120000361356892512010310012000010012000050056306401400204003940039249320326649120100200120000200360000416864003911120201100991001001200001000007610116114003001200001004168740040416874004041687
12020441686300000006199612512010010012000010012000050056306401416724168640039249320324997120100200120000200360000416864003911120201100991001001200001000007610116114167701200001004168740040416874004041692
120204416863000000061356892512010010012000010012000050058518691416724168640039249320324997120100200120000200360000400394168611120201100991001001200001002407610116114170701200001004205241726416924168740040
120204400393121100161356892512016110012000010012000050056306401416674168641691265770324997120100200120000200361167400394168611120201100991001001200001001007610116114003001200001004004041692400404168740040
12020440039312000018299612512010210012000010012000050058518691416674168640039249320324997120100200120000200360000416864003911120201100991001001200001000007610116114003001200001004168740040416874004041687
120204416913000000161363482512010010012000010012000050056306401416674168640039249320324997120100200120000200360000400394168611120201100991001001200001000007610116114003001200001004004041687400404169240040
120204400393131000361996147120100100120004115120000500577860814002041686401502493201026656120100200120000200360000416864003911120201100991001001200001000037610116114003001200001004168740040416874004041692
1202044169129900000103379662512010310012000110012000050056306401400204003941686265770326644120100200120000200360000416914003911120201100991001001200001001007610116114168301200001004004041687400404168740040
12020441686300000006199612512010010012000010012000050056306401416724168640039249320324997120100200120000200360000416914168611120201100991001001200001000007610133114003001200001004169240040416924004041687

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080b18191e1f373f4e51inst 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)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)cfd2icache miss (d3)d5d6daddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
12002440039312000000061996125120010101200001012000050585199301400200400394003924955325019120010201200002036000040039400391112002110910101200001000000000756600151601817400300120000104004040040400404004040040
12002440039312000000061996125120010101200001012000050563064000400200400394003924955325019120010201200002036000040039400391112002110910101200001000000000757101181601816400300120000104004040040400404004040040
12002440039300000000061996125120010101200001012000050563064000400203400394003924955325019120010201200002036000040039400391112002110910101200001000000000756700121601715400300120000104004040040400404004040040
12002440039300000000061996125120010101200001012000050596638601400200400394003924955325019120010201200002036000040039400391112002110910101200001000000000756600171601716400300120000104004040040400404004040040
12002440039300000000061996150120014101200031012000050563064001400200400394003924955326671120010201200002036000040039400391112002110910101200001000000000756700141601614400300120000104004040040400404004041687
12002440039312000000161996125120010101200001012000050563064001400200400394003924955325019120010201200002036000040039400391112002110910101200001000000000756500171601611400300120000104004040040400404004040040
12002440039300000000061996125120010101200001012000050563064001400200400394003924955325019120010201200002036000040039400391112002110910101200001000000000756500151601615400300120000104004040040400404004040040
12002440039299000000061996125120010101200001012000050563064001400200400394003924955325019120010201200002036000040039400391112002110910101200001000000300757200181601219400300120000104004040040400404004040040
120024400393001012001730996124312017712120158101203996157597820141239041579416222603171252821217802012115622365388415564132110112002110910101200001002012626520780500199702021414114120000104128641358413874143541098
1200244134631000101114558801831163180829512040413121082131223545557015450141554041404416132613294264561223742012239520367842412594195591120021109101012000010442229755207870003111401515400300120000104004040040400404004040040