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, 4S)

Test 1: uops

Code:

  fmlal2 v0.4s, v1.4h, v2.4h
  movi v0.16b, 1
  movi v1.16b, 2
  movi v2.16b, 3

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 1.000

Issues: 1.000

Integer unit issues: 0.000

Load/store unit issues: 0.000

SIMD/FP unit issues: 1.000

retire (01)cycle (02)03081e3f4e51inst 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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100440373003614534072510001000100053190814018403740373258338951000100030004037403711100110000073216113473100040384038403840384038
1004403730096134072510001000100053190814018403740373258338951000100030004037403711100110000073116113473100040384038403840384038
1004403731006134072510001000100053190814018403740373258338951000100030004037403711100110000073116113473100040384038403840384069
1004403730006134072510001000100053190814018403740373258338951000100030004037403711100110000073116113473100040384038403840384038
1004403730006134072510001000100053190814018403740373258338951000100030004037403711100110000073116113473100040384038403840384038
1004403730006134072510001000100053190814018403740373258338951000100030004037403711100110000073116113473100040384038403840384038
10044037300396134072510001000100053190814018403740373258338951000100030004037403711100110000073116113473100040384038403840384038
1004403730006134072510001000100053190814018403740373258338951000100030004037403711100110000073116113473100040384038403840384038
1004403730006134072510001000100053190814018403740373258338951000100030004037403711100110000073116113473100040384038403840384038
1004403731006134072510001000100053190814018403740373258338951000100030004037403711100110000073116113473100040384038403840384038

Test 2: Latency 1->1

Code:

  fmlal2 v0.4s, v1.4h, v2.4h
  movi v0.16b, 1
  movi v1.16b, 2
  movi v2.16b, 3

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)0318191e3a3f4e51inst 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)9fa8acc2c5cfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102044003730000003313940725101001001000010010000500570690840018400374003738108338745101002001000020030000400374003721102011009910010010000100000071014162339479100001004003840038400384003840038
10204400373000000613940725101001001000010010000500570690840018400374003738108338745101002001000020030000400374003711102011009910010010000100000071012162239479100001004003840038400384003840038
10204400373000000613940725101001001000010010000500570690840018400374003738108338745101002001000020030000400374003711102011009910010010000100000071012162239479100001004003840038400384003840038
102044003729900003463940725101001001000010010000500570690840018400374003738108338745101002001000020030000400374003711102011009910010010000100030071012162239479100001004003840038400384003840038
10204400373000001613940725101001001000010410000500570690840018400374003738108338745101002001000020030516400374003711102011009910010010000100134071012162339479100001004003840038400384003840038
10204400372990000613940725101001001000010010000500570690840018400374003738108338745101002001000020030000400374003711102011009910010010000100000071012162239479100001004003840038400384003840038
10204400373000000613940725101001001000010010000500570690840018400374003738108338745101002001000020030000400374003711102011009910010010000100000071013162239479100001004003840038400384003840086
1020440037301211380613940744101001021000010410148500570970040018400374003738108338745101002001000020030000400374003711102011009910010010000100030071012162339479100001004003840038400384003840038
102044003730000908043940725101001001000010010000500570690840018400374003738108338745101002001000020030000400374003711102011009910010010000100000071012162239479100001004003840038400384003840038
10204400373000000613940725101001001000010010000500570690840018400374003738108338745101002001000020030000400374003711102011009910010010000100000171012162239479100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)030818191e1f3a3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024400373000000006139407251001010100001010000505706908400184003740037381303387891001020100002030000400374003711100211091010100001000000006402162239473010000104003840038400384003840038
10024400373000000006139407251001010100001010000505706908400184003740037381303387671001020100002030000400374003711100211091010100001000000006402162239473010000104003840038400384003840038
10024400373000000006139407251001010100001010000505706908400184003740037381303387671001020100002030000400374003721100211091010100001000000006402163339473010000104003840038400384003840038
10024400373000000006139407251001010100001010000505706908400184003740037381303387671001020100002030000400374003711100211091010100001000000006402162339473010000104003840038400384003840038
10024400373000000006139407251001010100001010000505706908400184003740037381303387671001020100002030000400374003711100211091010100001000000006402162239473010000104003840038400384003840038
10024400373000000006139407251001010100001010000505706908400184003740037381303387671001020100002030000400374003711100211091010100001000000006402163239473010000104003840038400384003840038
10024400373000000006139407251001010100001010000505706908400184003740037381303387671001020100002030000400374003711100211091010100001000000006402162239473010000104003840038400384003840038
10024400373000000006139407251001010100001010000505706908400184003740037381303387671001020100002030000400374003711100211091010100001000000006402163239473010000104003840038400384003840038
10024400373000000006139407251001010100001010000505706908400184003740037381303387671001020100002030000400374003711100211091010100001000000006402163239473010000104003840038400384003840038
10024400373000000006139407251001010100001010000505706908400184003740037381303387671001020100002030000400374003711100211091010100001000000006402162239473010000104003840038400384003840038

Test 3: Latency 1->2

Code:

  fmlal2 v0.4s, v0.4h, v1.4h
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)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)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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102044003730006139407251010010010000100100005005706908400184003740037381083387451010020010000200300004003740037111020110099100100100001000007101161139479100001004003840038400384003840038
102044003730006139407251010010010000100100005005706908400184003740037381083387451010020010000200300004017940037111020110099100100100001000607101161239479100001004003840038400384003840038
102044003730006139407251010010010000100100005005706908400184003740037381083387451010020010000200300004003740037111020110099100100100001000007101161139479100001004003840038400384003840038
1020440037300053639407251010010010000100100005005706908400184003740037381083387451010020010000200300004003740037111020110099100100100001000007101161139479100001004003840038400384003840038
102044003730006139407251010010010000100100005005706908400184003740037381083387451010020010000200300004003740037111020110099100100100001000007101161139479100001004003840038400384003840038
102044003729906139407251010010010000100100005005706908400184003740037381083387451010020010000200300004003740037111020110099100100100001000007101161139479100001004003840038400384003840038
102044003730006139407251010010010000100100005005706908400184003740037381083387451010020010000200300004003740180111020110099100100100001000007101161139479100001004003840038400384003840038
102044003729906139407251010010010000100100005005706908400184003740037381083387451010020010000200300004003740037111020110099100100100001000007101161139479100001004003840038400384003840038
102044003730006139407251010010010000100100005005706908400184003740037381083387451010020010000200300004003740037111020110099100100100001000007101161139479100001004003840038400384003840038
102044003730006139407251010010010000100100005005706908400184003740037381083387451010020010000200300004003740037111020110099100100100001000007101161139479100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)030b181e3f4e51inst 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)9fa8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100244003730000061394072510010101000010100005057069084001840037400373813033876710010201000020300004003740037111002110910101000010000640316223947310000104003840038400384003840038
1002440037300000536394072510010101000010100005057069084001840037400373813033876710010201000020300004003740037111002110910101000010000640216223947310000104003840038400384003840038
100244003730000061394072510010101000010100005057069084001840037400373813033876710010201000020300004003740228111002110910101000010000640616223947310000104003840038400384008540038
100244003730000061394072510010101000010100005057069084001840037400373813033876710010201000020300004003740037111002110910101000010000640216223947310000104008640085400384008640038
100244003729912061394072510010101000010100005057097004001840037400373813533876710010201000020300004003740037111002110910101000010300682232643959310000104003840038400384008440038
1002440037300005461393892510010101000010100005057069084001840037400373813033876710010201000020300004003740037111002110910101000010030640216223947310000104003840038400384003840038
100244003730000961394072510010101000010100005057069084001840037400373813033876710010201000020300004003740037111002110910101000010000640216223947310000104003840038400384003840038
1002440037300000726394072510010101000010100005057069084001840037400373813033876710010201000020300004003740225111002110910101000010000640316223947310000104003840038400384003840038
100244003729900061394072510010101000010100005057069084001840037400373813033876710010201000020300004003740037111002110910101000010000640216223947310000104003840038400384003840038
100244003730000061394072510010101000010100005057069084001840037400373813033876710010201000020300004003740037111002110910101000010000640216223947310000104003840038400384003840038

Test 4: Latency 1->3

Code:

  fmlal2 v0.4s, v1.4h, v0.4h
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)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)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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020440037299000000061394072510100100100001001000050057069081400180400374003738108338745101002001000020030000400374003711102011009910010010000100000000071211611394790100001004003840038400384003840038
10204400372990000000613940725101001001000010010000500570690814001804003740037381082838745101002001000020030000400374003711102011009910010010000100000000071011611394790100001004003840038400384003840038
1020440037300000000061394072510100100100001001000050057069081400180400374003738108338745101002001000020030000400374003711102011009910010010000100000000071011611394790100001004003840038400384003840038
1020440037300000000061394072510100100100001001000050057069081400180400374003738108338745101002001000021630000400374003711102011009910010010000100000000071011611394790100001004003840038400384003840038
1020440037300000000061394072510100100100001001000050057069081400180400374003738108338745101002001000020030000400374003711102011009910010010000100000000071011611394790100001004003840038400384003840038
10204400373000000000613940725101001001000010010000500570690814001804003740037381083387451010020010000200300004003740037111020110099100100100001000004021071011611394790100001004003840038400384003840038
1020440037300000000061394072510100100100001001000050057069081400180400374003738108338745101002001000020030000400374003711102011009910010010000100000000071011611394790100001004003840038400384003840038
1020440037300000030061393802510100100100001001000050057069081400180400374003738108338745101002001000020030000400374003711102011009910010010000100000000071011611394790100001004003840038400384003840038
1020440037299000000061394072510100100100001001000050057069081400180400374003738108338745101002001000020830000400374003711102011009910010010000100000000071011611394790100001004003840038400384003840038
1020440037300000000061394072510100100100001001000050057069081400180400374003738108338745101002001000020030000400374003711102011009910010010000100000000071011611394790100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)03090b18191e1f3f4e51inst 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)9fa7a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024400373000000006139407251001010100001010000505706908140018400374003738130338767100102010000203000040037400371110021109101010000100000640216223947310000104003840038400384003840038
10024400373000000006139407251001010100001010444505706908040018400374003738130338767100102010000203000040037400371110021109101010000100160640216223947310000104003840038400384003840038
1002440037299000012012439407251001010100001010000505706908040018400374003738144338767100102010000203000040037400371110021109101010000100000640216223967710000104003840038400384003840038
10024400373001000006139407251001010100001010000505706908040018400374003738130338767100102010000203000040037400371110021109101010000100000640216323947310000104003840038400384003840038
10024400372990000006139407251001010100001010000505706908040018400374003738130338767100102010000203000040131400371110021109101010000102200640216323947310000104003840038400384003840038
10024400373000000006139407251001010100001010000505706908040018400374003738130338767100102010000203000040037400371110021109101010000100000640216223947310000104003840038400384003840038
10024400373000120006139407251001010100001010000505706908040018400374003738130338767100102010000203000040037400371110021109101010000100000640216223947310000104003840038400384003840038
10024400373000000006139407251001010100001010000505706908040018400374003738130338767100102010000203000040037400371110021109101010000100000640216223947310000104003840038400384003840038
100244003730000000010339407251001010100001010000505706908040018400374003738130338767100102010000203000040037400371110021109101010000100030640216223947310000104003840038400384003840038
10024400373001000906139407251001010100001010000505706908040018400374003738130338786100102010809203000040037401801110021109101010000100130640216223947310000104003840038400384003840038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  fmlal2 v0.4s, v8.4h, v9.4h
  movi v1.16b, 0
  fmlal2 v1.4s, v8.4h, v9.4h
  movi v2.16b, 0
  fmlal2 v2.4s, v8.4h, v9.4h
  movi v3.16b, 0
  fmlal2 v3.4s, v8.4h, v9.4h
  movi v4.16b, 0
  fmlal2 v4.4s, v8.4h, v9.4h
  movi v5.16b, 0
  fmlal2 v5.4s, v8.4h, v9.4h
  movi v6.16b, 0
  fmlal2 v6.4s, v8.4h, v9.4h
  movi v7.16b, 0
  fmlal2 v7.4s, v8.4h, v9.4h
  movi v8.16b, 9
  movi v9.16b, 10

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)0307080a0b18191e1f3f51inst 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)9fa0a1a6a8a9acc2c5branch mispredict (cb)cdcfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160204200781501010000029258011610080016100800285006401960200462006520065612801282008002820024008420065200651116020110099100100160000100000000011110122000111610099200620001600001002006620066200662006620066
16020420065150101000002925801161008001610080028500640196020046200652006561280128200800282002400842006520065111602011009910010016000010000000001111012600091600078200620001600001002006620066200662006620066
160204200651500000000040258010010080000100800005006400000200462006520065323801002008000020024000020065200651116020110099100100160000100000000000010120300916001109200620001600001002006620066200662006620066
16020420065150000000120402580100100800001008000050064000002004620065200653238010020080000200240000200652007711160201100991001001600001000000000000101200005160001011200620001600001002006620066200662006620066
160204200651510000000026625801001008000010080000500640000020046200652006532380100200800002002400002006520078111602011009910010016000010000000000001011500010160101011200620001600001002006620066200662006620066
1602042006515000000000402580100100800001008000050064000002004620065200653238010020080000200240000200652014721160201100991001001600001000000000000101150001016000510200620001600001002006620066200662006620066
1602042006515100000000402580124100800001008000050064000002005920065200653238010020080000200240000200652007811160201100991001001600001000000000000101190009160001010200620001600001002006620066200662007920066
160204200651500000002104025801001008000010080000500640000020046200652006532380100200800002002400002006520078111602011009910010016000010000000000001012000010160111011200620001600001002007920078200792007920066
160204200651500000000040258010010080000100800005006400000200462006520065323801002008000020024000020065200781116020110099100100160000100000100000010119010101600098200620001600001002006620066200662006620066
160204200651500000000040258010010080000100800005006400000200462006520065323801002008000020024000020065200651116020110099100100160000100000000000010120000916000105200620001600001002006620066200662006620066

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0308090b1e3f51inst 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)9fa1a6branch mispredict (cb)cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160024200971510000462780012128000012800006264000011200332005220052323800122080000202400002006120052111600211091010160000100001002962243442233200582402160000102006220053200622006220053
160024200611500000742980012128000012800006264000011200332006120052323800122080326202400002005220052111600211091010160000100001002631132521133200492201160000102005320053200532005320053
160024200521501000672780012128000012800006264000011200332005220052323800122080000202400002005220052111600211091010160000100001002631132521133200492201160000102005320053200532005320053
1600242005215000001782780012128000012800006264000011200332005220052323800122080000202400002005220052111600211091010160000100001002631142521123200492201160000102005320053200532005320053
160024200521500000462780012128000012800006264000011200332005220052323800122080000202400002005220052111600211091010160000100001002631122521133200492201160000102005320053200532005320053
160024200521500000462780012128000012800006264000011200332005220052323800122080000202400002005220052111600211091010160000100001002631132521133200492201160000102005320053200532005320053
160024200521500010462780012128000012800006264000011200332005220052323800122080000202400002021820052111600211091010160000100001002531122521133200492201160000102005320053200532005320053
160024200521500000462780012128000012800006264000011200332005220052323800122080000202400002005220052111600211091010160000100011002661222521133200492201160000102005320053200532005320053
160024200521510000462980012128000012800006264000011200332005220052323800122080000202400002005220052111600211091010160000100001002531132521143200492201160000102005320062200532005320053
1600242006115000001462780012128000012800006264000011200332005220052323800122080000202400002005220052111600211091010160000100001002632132521133200492201160000102005320053200532005320053

Test 6: throughput

Count: 12

Code:

  fmlal2 v0.4s, v12.4h, v13.4h
  fmlal2 v1.4s, v12.4h, v13.4h
  fmlal2 v2.4s, v12.4h, v13.4h
  fmlal2 v3.4s, v12.4h, v13.4h
  fmlal2 v4.4s, v12.4h, v13.4h
  fmlal2 v5.4s, v12.4h, v13.4h
  fmlal2 v6.4s, v12.4h, v13.4h
  fmlal2 v7.4s, v12.4h, v13.4h
  fmlal2 v8.4s, v12.4h, v13.4h
  fmlal2 v9.4s, v12.4h, v13.4h
  fmlal2 v10.4s, v12.4h, v13.4h
  fmlal2 v11.4s, v12.4h, v13.4h
  movi v12.16b, 13
  movi v13.16b, 14

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.3341

retire (01)cycle (02)03373f4e51inst 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)9fa8cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
12020440039299061996125120100100120000100120000500585199314166704168840039249323249971201002001200002003600004003941686111202011009910010012000010000761011611400301200001004168740040416874004041687
12020441686300061996125120100100120000100120000500585199314166704168640039265773266441201002001200002003600004168640039111202011009910010012000010000761011611400301200001004169240040416924004041687
12020441691300061996125120100100120000100120000500585199304149504168640039249323249971201002001200002003600004169141691111202011009910010012000010000761011611416771200001004004041687400404168741687
120204416863000613568925120100100120000100120000500585199304002004168640039249323249971201002001200002003600004003941686111202011009910010012000010000761011611400301200001004004041687400404168740040
12020441701312061996125120100100120000100120000500563064004002004003941686265773249971201002001200002003600004003941688111202011009910010012000010000761011611400301200001004168740040416924168740040
120204400393123613568925120103100120003100120000500563064014002004003941686265773266441201002001200002003600004003941691111202011009910010012000010000761011611400301200001004004041687400404168740040
120204400893180613568925120101100120003100120000500563064014002004003941686265773249971201002001200002003600004003940039111202011009910010012000010000761011611416771200001004004041692400404169240040
12020440039312161996125120100100120000100120000500563064004002004003941686265773266441201002001200002003600004003940039111202011009910010012000010000761011611416771200001004168740040416874004041687
120204416862990613796625120103100120003100120000500563064014166704168640039249323249971201002001200002003600004168640089111202011009910010012000010000761011611400301200001004168740040416874004041692
12020441686300361996125120103100120003100120000500563064004002034168840039249323249971201002001200002003600004169140039111202011009910010012000010000761011611416771200001004004041687400404168740040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080b1e373f4e51inst 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)9fa7a8acc5cdcfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0eaebec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1200244003930000006799612512001010120000101200005056306401140020400394003924955325019120010201200002036000040039400391112002110910101200001000600752462131621123400301594120000104004040040400404004040040
12002440039300000067996125120010101200031012000050563064011400204003940039249553250191200102012000020360000400394003911120021109101012000010004200752231131621133400301594120000104004040040400404004040040
120024400393000000679961251200101012000010120000505630640114002040039400392495532501912001020120000203600004003940039111200211091010120000100012000755031131621133400301594120000104004040040400404004040040
120024400393000000679961251200101012000010120000655630640114002040039400392495532501912001020120000203600004003940039111200211091010120000100042007522311316211234003015174120000104004040040400404004040040
12002441691300000073299614712001010120000131200005056306401140020400394003924955325019120010201200002036000040039400391112002110910101200001000000752231132421133400301594120000104004040040401484004040040
1200244003930000006799612512001010120002101200005056306401140020400394003924955325019120010201200002036000040039400391112002110910101200001000000752231131621132400301594120000104004042471400404004040040
12002440039300001206799612512001010120003101200005056306401140020400394003924955325019120010201200002036000040039400391112002110910101200001001300752231141621133400301594120000104004040040400404004040040
120024400393000017106724024661201751012000010120196505630640214002040039400392495532501912001020120000203600004003940039111200211091010120000100112000752231131621133400301594120000104004040040400404004040040
12002440039300000010999612512001010120000101200005056530321140020400394003924955325019120010201200002036000040039400391112002110910101200001000900752231131621133400301594120000104169240040400404004040040
12002441691300009167379662512001010120003101200005056306401140020416914003924955325019120010201200002036000040039400391112002110910101200001000600752231131621133400301594120000104004040040400404004040040