Apple M1 Microarchitecture Research by Dougall Johnson

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

FMLAL2 (vector, 2S)

Test 1: uops

Code:

  fmlal2 v0.2s, v1.2h, v2.2h
  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)accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10044037309613407251000100010005319081401840374037325833895100010003000403740371110011000073116113473100040384038403840384038
10044037310613407251000100010005319081401840374037325833895100010003000403740371110011000073116113473100040384038403840384038
10044037300613407251000100010005319081401840374037325833895100010003000403740371110011000073116113473100040384038403840384038
10044037300613407251000100010005319080401840374037325833895100010003000403740371110011000073116113473100040384038403840384038
10044037300613407251000100010005319080401840374037325833895100010003000403740371110011000073116113473100040384038403840384038
10044037300613407251000100010005319080401840374037325833895100010003000403740371110011000073116113473100040384038403840384038
10044037300613407251000100010005319080401840374037325833895100010003000403740371110011000073116113473100040384038403840384038
10044037300613407251000100010005319080401840374037325833895100010003000403740371110011000073116113473100040384038403840384038
10044037300613407251000100010005319080401840374037325833895100010003000403740371110011000073116113473100040384038403840384038
100440373027613407251000100010005319081401840374037325833895100010003000403740371110011000073116113473100040384038403840384038

Test 2: Latency 1->1

Code:

  fmlal2 v0.2s, v1.2h, v2.2h
  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)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)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)9fa0a1a6a8a9acc2cfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204400373000000000124394072510100100100061001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000000000710121622394790100001004003840038400384003840038
1020440037299000000061394072510100100100001001000050057069081400184003740037381083387451010020010000200300004003740037111020110099100100100001000000030712131622394790100001004003840038400384003840038
1020440084300000000061394072510100100100001001000050057069081400184003740037381083387451010020010000200300004003740037111020110099100100100001000000000712121632394790100001004003840038400384003840038
1020440037300000000061394072510100100100001001000050057069081400184003740037381083387451010020010000200300004003740037111020110099100100100001000000000712121622394790100001004003840038400384003840038
1020440037300000000061394072510100100100001001000050057069081400184003740037381083387451010020010000200300004003740037111020110099100100100001000000000710121632394790100001004003840038400384003840038
1020440037300000000061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000000000710121622394790100001004003840038400384003840038
1020440037300000000061394072510100100100001001000050057069081400184003740037381083387451010020010000200300004003740037111020110099100100100001000000000712121622394790100001004003840038400384003840038
1020440037299000000061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000000000710121622394790100001004003840038400384003840038
1020440037300000000061394072510100100100001001000050057069081400184003740037381083387451010020010000200300004003740037111020110099100100100001000000000710131622394790100001004003840038400384003840038
1020440037300000000061394072510100100100001001000050057069081400184003740037381083387451010020010000200300004003740037111020110099100100100001000000000712131622394790100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)030b1e1f3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)696d6edispatch 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)9fa6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002440037300000613940725100101010000101000050570690840018400374003738130033876710010201000020300004003740037111002110910101000010000640316223947310000104003840038400384003840038
1002440037300000613940725100101010000101000050570690840018400374003738130033876710010201000020300004003740037111002110910101000010000640316223947310000104003840038400384003840038
1002440037300000613940725100101010000101000050570690840018400374003738130033876710010201000020300004003740037111002110910101000010000640416223947310000104003840038400384003840038
1002440037299000613940725100101010000101000050570690840018400374003738130033876710010201000020300004003740037111002110910101000010000640216223947310000104003840038400384003840038
1002440037300000613940725100101010000101000050570690840018400374003738130033876710010201000020300004003740037111002110910101000010000640216223947310000104003840038400384003840038
1002440037300000613940725100101010000101000050570690840018400374003738130033876710010201000020300004003740037111002110910101000010000640216223947310000104003840038400384003840038
1002440037300000613940725100101010000101000050570690840018400374003738130033876710010201000020300004003740037111002110910101000010000640216223947310000104003840038400384003840038
1002440037300000613940725100101010000101000050570690840018400374003738130033876710010201000020300004003740037111002110910101000010000640216223947310000104003840038400384003840038
1002440037300000613940725100101010000101000050570690840018400374003738130033876710010201000020300004003740037111002110910101000010000640216223947310000104003840038400384003840038
10024400373000240613940725100101010000101000050570690840018400374003738130033876710010201000020300004003740037111002110910101000010000640216223947310000104003840038400384003840038

Test 3: Latency 1->2

Code:

  fmlal2 v0.2s, v0.2h, v1.2h
  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)030b191e1f3f4e51inst 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)9fa8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020440037300000061394072510100100100001001000050057069081400184003740037381083387451010020010000200300004003740037111020110099100100100001000007101161139479100001004003840038400384003840038
1020440037299000061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000007101161139479100001004003840038400384003840038
10204400373000030726394072510100102100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000007101161139479100001004003840038400384003840038
1020440037300000061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000007101161139479100001004003840038400384003840038
102044003730000013261394072510115100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000007101161139479100001004003840038400384003840038
1020440037300000061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000007101161139479100001004003840038400384003840038
1020440037300000061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000007101161139479100001004003840038400384003840038
1020440037300000061394072510126100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000007101161139479100001004003840038400384003840038
1020440037300000061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001001007101161139479100001004003840038400384003840038
1020440037299010061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000007101161139479100001004003840038400384003840038

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)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)9fa0a8acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002440037300000000061394072510010101000010100005057069084001840037400373813033876710010201000020300004003740037111002110910101000010000006402162239473010000104003840038400384003840038
1002440037300000000061394072510010101000010100005057069084001840037400373813033876710010201000020300004003740037111002110910101000010000006402162239473010000104003840038400384003840038
10024400373000000000726394072510010101000010100005057069084001840037400373813033876710010201000020300004003740037111002110910101000010000006402162239473010000104003840038400384003840038
1002440037299000000061394072510010101000010100005057069084001840037400373813033876710010201000020300004003740037111002110910101000010000006402162239473010000104003840038400384003840038
1002440037299000000061394072510010101000010100005057069084001840037400373813033876710010201000020300004003740037111002110910101000010000006402162239473010000104003840038400384003840038
100244003730000000013261394072510010101000010100005057069084001840037400373813033876710010201000020300004003740037111002110910101000010000006402162239473010000104003840038400384003840038
10024400373000000000232394072510010101000010100005057069084001840037400373813033876710010201000020300004003740037111002110910101000010000006402162239473010000104003840038400384003840038
1002440037300000000061394072510010101000010100005057069084001840037400373813033876710010201000020300004003740037111002110910101000010000006402162239473010000104003840038400384003840038
10024400372990000000631394072510010101000010100005057069084001840037400373813033876710010201000020300004003740037111002110910101000010000006402162239473010000104003840038400384003840038
1002440037300000000061394072510010101000010100005057069084001840037400373813033876710010201000020300004003740037111002110910101000010000006402162239473010000104003840038400384003840038

Test 4: Latency 1->3

Code:

  fmlal2 v0.2s, v1.2h, v0.2h
  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)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)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)9fa0a1a6a8a9acc2c5cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204400373000000053404413940725101001001000010010000500570690814001840037400373810833874510100200100002003000040037400371110201100991001001000010000012000071011611394790100001004003840038400384003840038
10204400373000000029701473940725101001001000010010000500570690814001840037400373810833874510100200100002003000040037400371110201100991001001000010000000000071011611394790100001004003840038400384003840038
1020440037300000004380613940725101001001000010010000500570690804001840037400373810833874510100200100002003000040037400371110201100991001001000010000000000071011611394790100001004003840038400384003840038
1020440037300000005280613940725101001001000010010000500570690814001840037400373810833874510100200100002003000040037400371110201100991001001000010000000000071011611394790100001004003840038400384003840038
102044003730000000498061394072510100100100001001000050057069081400184003740037381083387451010020010000210300004003740037111020110099100100100001000005402100171011611394790100001004003840038400384003840038
1020440037300000005070613940725101001001000010010000500570690814001840037400373810833874510100200100002003000040037400371110201100991001001000010000000000071011611394790100001004003840038400384003840038
102044003730000000906139407251010010010000100100005005706908140018400374003738108338745101002001000020030000400374003711102011009910010010000100000101445600071011611394790100001004003840038400854013440038
102044003730000000450613940725101001001000010010000500570690814001840037400373810833874510100200100002003000040037400371110201100991001001000010000010300071011611394790100001004003840038400384003840038
1020440037299000004950613940725101001001000010010000500570690814001840037400373810833874510100200100002003000040037400371110201100991001001000010000000000071011611394790100001004003840038400384003840038
102044003730000000450613940725101001001000010010000500570690814001840037400373810833874510100200100002003000040037400371110201100991001001000010000000000071011611394790100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)0318191e3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002440037300001561394072510010101000010100005057069081400184003740037381303387671001020100002030000400374003711100211091010100001000640416223947310000104003840038400384003840038
100244003730000661394072510010101000010100005057069081400184003740037381303387671001020100002030000400374003711100211091010100001000640216223947310000104003840038400384003840038
10024400373000018613940725100171010000101000050570690804001840037400373813033876710010201000020300004003740037111002110910101000010118640216223947310000104003840038400384003840038
1002440037300114261394072510010101000010100005057069080400184003740037381303387671001020100002030000400374003711100211091010100001000640216223947310000104003840038400384003840038
1002440037300001861394072510010101000010100005057069080400184003740037381303387671001020100002030000400374003711100211091010100001000640216223947310000104003840038400384003840038
100244003729900661394072510010101000010100005057069080400184003740037381303387671001020100002030000400374003711100211091010100001000640216223947310000104003840038400384003840038
100244003730000661394072510010101000010100005057069081400184003740037381303387671001020100002030000400374003711100211091010100001000640216223947310000104003840038400384003840038
10024400373000027061394072510010101000010100005057069081400184003740037381303387671001020100002030000400374003711100211091010100001000640216223947310000104003840038400384003840038
1002440037299013361394072510010101000010100005057069080400184003740037381303387671001020100002030000400374003711100211091010100001000640216223947310000104003840038400384003840038
100244003730000661394072510010101000010100005057069081400184003740037381303387671001020100002030000400374003711100211091010100001000640216223947310000104003840038400384003840038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  fmlal2 v0.2s, v8.2h, v9.2h
  movi v1.16b, 0
  fmlal2 v1.2s, v8.2h, v9.2h
  movi v2.16b, 0
  fmlal2 v2.2s, v8.2h, v9.2h
  movi v3.16b, 0
  fmlal2 v3.2s, v8.2h, v9.2h
  movi v4.16b, 0
  fmlal2 v4.2s, v8.2h, v9.2h
  movi v5.16b, 0
  fmlal2 v5.2s, v8.2h, v9.2h
  movi v6.16b, 0
  fmlal2 v6.2s, v8.2h, v9.2h
  movi v7.16b, 0
  fmlal2 v7.2s, v8.2h, v9.2h
  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)0318191e1f3a3f51inst 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)9fa0a1a8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160204200911510000040258010010080000100800005006400001200462006520065323801002008000020024042020077200651116020110099100100160000100000001011111622200621600001002006620066200662006620066
160204200651500000040258010010080000100800005006400000200462006520065323801002008000020024000020065200651116020110099100100160000100000001011221622200621600001002006620066200662006620066
1602042006515000180040258010010080000100800005006400000200462006520065323801002008000020024000020065200651116020110099100100160000100000031011121611200621600001002006620066200662006620066
1602042006515000000402580100100800001008000050064000012004620338200653723801002008000020024000020065200651116020110099100100160000100000001011121611200621600001002006620066200662006620066
160204200651500000040258010010080000100800005006400000200462006520065323801002008000020024000020065200651116020110099100100160000100000001011121611200621600001002006620066200662006620066
160204200651500100040258010010080000100800005006400000200462006520065323801002008010920024000020065200651116020110099100100160000100900001011211611200621600001002006620066200662006620066
16020420065150000004025801001008000010080000500640000120046200652006532380221200800002002400002006520065211602011009910010016000010000055301011111611200621600001002006620066200662006620066
160204200651500000040258010010080000100800005006400000200462006520065323801002008000020024000020065200651116020110099100100160000100000001011111611200621600001002006620066200662006620066
160204200651500000040258010010080000100800005006400000200462006520065323801002008000020024000020065200651116020110099100100160000100000001011111612200621600001002006620066200662006620066
16020420065150000108040258010010080000100800005006400001200462006520065323801002008000020024000020065200651116020110099100100160000100001301011111611200621600001002006620066200662006620066

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03071e3f51inst 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)9fa8a9accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1600242007615000462780012128000012800006264000011020033200522005232380012208000020240000200522005211160021109101016000010000100353119252111012200492201160000102005320053200532005320053
16002420052150004627800121280000128000062640000110200332005220052323800122080000202400002005220052111600211091010160000101001003531111252111011200492201160000102005320053200532005320053
1600242005215000462780012128000012800006264000011020033200522005232380012208000020240000200522005211160021109101016000010100100313119252111011200492201160000102005320053200532005320053
16002420052150012462780012128000012800006264000011520033200522005232380012208000020240000200522005211160021109101016000010000100308218252111212200492201160000102005320053200532005320053
1600242005215000711278001212800001280000626400001152003320052200523238001220800002024000020052200521116002110910101600001002310033821825211910200492201160000102005320053200532005320053
16002420052150004627801221280000138000062640000115200422006120063323800122080000202400002006120061111600211091010160000100001003611311134321118200582412160000102005320062200622006220062
16002420063150005227800121280000128000062640000015200442005220052323800122080000202400002005220052111600211091010160000100001003383210253221212200602202160000102006220053200622005320053
16002420061151004629800121280000128000062640000015200332006120061323800122080000202400002005220061111600211091010160000100001003511311225212911200602402160000102006220062200532005320062
160024200521510046278001212800001280000626400000152004220061200613238001220800002024000020061200611116002110910101600001000010035113111343221212200582202160000102006220053200642005320064
160024200631500046298001212800001280000626400000152003320061200523238001220800002024000020061200611116002110910101600001010150100341132834322910200602202160000102006220053200622006220062

Test 6: throughput

Count: 12

Code:

  fmlal2 v0.2s, v12.2h, v13.2h
  fmlal2 v1.2s, v12.2h, v13.2h
  fmlal2 v2.2s, v12.2h, v13.2h
  fmlal2 v3.2s, v12.2h, v13.2h
  fmlal2 v4.2s, v12.2h, v13.2h
  fmlal2 v5.2s, v12.2h, v13.2h
  fmlal2 v6.2s, v12.2h, v13.2h
  fmlal2 v7.2s, v12.2h, v13.2h
  fmlal2 v8.2s, v12.2h, v13.2h
  fmlal2 v9.2s, v12.2h, v13.2h
  fmlal2 v10.2s, v12.2h, v13.2h
  fmlal2 v11.2s, v12.2h, v13.2h
  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)03081e373f4e51inst 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)9fa0a8cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
120204400393000018299612512010010012000010012000050058518694002040039400392493232499712010020012000020036000041691400391112020110099100100120000100007610116114003001200001004004041687400404168741687
120204416913000006199612512010010012000010012000050056306404167240039416912493232499712010020012000020036000040039416861112020110099100100120000100007610116114168301200001004004040040400404004041692
1202044169130000061379662512010110012000210012000050056306404002040039400392493232499712010020012000020036000040039400391112020110099100100120000100007610116114167701200001004004041692400404168740040
120204400393120016199612512010010012000010012000050058519934167241691400392493232499712010020012000020036000040039400391112020110099100100120000100007610116114003001200001004169240040416924004041692
12020440039299000187379662512010310012000310012000050056306404002040039400392658232664412010020012000020036000040039400391112020110099100100120000100007610116114003001200001004004041692400404169240040
120204400393120006199612512010010012000010012000050056306404167241691400392493232499712010020012000020036000040039416861112020110099100100120000100207610116114003001200001004168740040416924004040040
120204400392990006199612512010010012000010012000050056306404002040039416912493232499712010020012000020036000040039400391112020110099100100120000100007610116114168301200001004169240040416924004041692
120204416863000016199612512010010012000010012000050058518694002040039400392493232499712010020012000020036000040039416911112020110099100100120000100007610116114003001200001004168740040416874004041692
120204400393120006199612512010010012000010012000050056306404002040039416912657732664912010020012000020036000041691400391112020110099100100120000100007610116114167701200001004004040040400404004040040
120204400393000006199612512010010012000010012000050058518694167241686400392493232499712010020012000020036000040039416911112020110099100100120000100007610116114003001200001004169240040416924004041692

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0304080b18191e1f373a3f4e51inst 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)9fa1a7a8a9accdcfd0d2icache miss (d3)itlb miss (d4)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaebec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
12002441106300100000010172996125120010101200001012000050563064011400204003940039249553250191200102012000020360000400394003911120021109101012000010000000752331103216111202640030021115120000104004040040400404004040040
12002440039299000000030109996125120010101200001012000050563064011400204003940039249553250191200102012000020360000400394003911120021109101012000010000000752231102616111292040030021115120000104004040040400404004040040
12002440039300000000000195996125120010101200001012000050563064011400204003940039249553250191200102012000020360000400394003911120021109101012000010000000752231102816111182740030021125120000104004040040400404004040040
1200244003930000000001067996125120010101200001012000050563064011400204003940039249553250191200102012000020360000400394003911120021109101012000010000000752231102816111262940030041215120000104004040040400404004040040
12002440039300000001201073996125120010101200001012000050563064001400204003940039249553250191200102012000020360000400394003911120021109101012000010000000752331102816114252740030041119120000104004040040400404004040040
1200244003930000000000067996125120010101200001012000050563064011400204003940039249553250191200102012000020360000400394003911120021109101012000010000000752562202816322282840030041219120000104004040040400404004040040
1200244003930000000002073996125120010101200001012000050563064001400204003940039249553257431200102012000020360000400394247011120021109101012000010000000752562202416312262440030021115120000104004040040400404004040040
1200244003930000000000073996125120010101200001012000050563064011400204003940039249553250191200102012000020360000400394003911120021109101012000010000000752331102816111192840030041119120000104004040040400404004040040
1200244003930000000003067996125120010101200001012000050563064011400204003940039249553250191200102012000020360000400394003911120021109101012000010000000752462202716322282440030041219120000104004040040400404004040040
1200244003930000000001067996125120010101200001012000050563064011400204003940039249553250191200102012000020360000400394003911120021109101012000010000000752462202816322212840030041219120000104004040040400404004040040