Apple M1 Microarchitecture Research by Dougall Johnson

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

FMLS (by element, S)

Test 1: uops

Code:

  fmls s0, s1, v2.s[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)03091e3f4e51inst 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)a0a7a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100440373000613407251000100010005319080401840374037325833895100010003000403740371110011000000073216223473100040384038403840384038
100440373000613407251000100010005319080401840374037325833895100010003000403740371110011000001073216223473100040384038403840384038
100440373000613407251000100010005319080401840374037325833895100010003000403740371110011000000073216223473100040384038403840384038
1004403731006134072510001000100053190804018403740373258338951000100030004037403711100110000027373216223473100040384038403840384038
100440373000613407251000100010005319080401840374037325833895100010003000403740371110011000000367573216223473100040384038403840384038
100440373100613407251000100010005319080401840374037325833895100010003000403740371110011000000073216223473100040384038403840384038
1004403730006134072510001000100053190804018403740373258338951000100030004037403711100110000006973216223473100040384038403840384038
10044037310061340725100010001000531908040184037403732583389510001000300040374037111001100000010573216223473100040384038403840384038
100440373000613407251000100010005319081401840374037325833895100010003000403740371110011000000673216223473100040384038403840384038
100440373000613407251000100010005319081401840374037325833895100010003000403740371110011000000073216223476100040384038403840384038

Test 2: Latency 1->1

Code:

  fmls s0, s1, v2.s[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)0308191e3a3f4e51inst 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)9fa8a9acc2cfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102044003730000006139407251010010010000100100005005706908140018400374003738108338745101002001000020030000400374003711102011009910010010000100000071003163339479100001004003840038400384003840038
102044003730000006139407251010010010000100100005005706908040018400374003738108338745101002001000020030000400374003711102011009910010010000100010071013163339479100001004003840086400384003840038
102044003730000006139407251010010010000100100005005706908040018400374003738108338745101002001000020030000400374003711102011009910010010000100000071013163339479100001004003840038400384003840038
102044003729900006139407251010010010000100100005005706908040018400374003738108338745101002001000020030000400374003711102011009910010010000100000071013164339479100001004003840038400384003840038
102044003730000006139407251010010010000100100005005706908040018400374003738108338745101002001000020030000400374003711102011009910010010000100000071013163339479100001004003840038400384003840038
102044003730000006139407251010010010000100100005005706908040018400374003738108338745101002001000020030000400374008521102011009910010010000100000071013163339479100001004003840038400384003840038
102044003729900006139407251010010010000100100005005706908040018400374003738108338745101002001000020030000400374003711102011009910010010000100000071014164339479100001004003840038400384003840038
102044003730000009439407251010010010006100100005005706908040018400374003738108338745101002001000020030000400374003711102011009910010010000100000071013163339479100001004003840038400384003840038
102044003730000016139407251010010010000100100005005706908040018400374003738108338745101002001000020030000400374003711102011009910010010000100000071013163339479100001004003840038400384003840038
102044003730000006139407251010010010000100100005005706908040018400374003738108338745101002001000020030000400374003711102011009910010010000100000071013163339479100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)0318191e1f3f4e51inst 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)9fa8a9acc5cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024400372990000613940725100101010000101000050570690814001804003740037381303387671001020100002030000400374003711100211091010100001000000640616333947310000104003840038400384003840038
10024400373000000613940725100101010000101000050570690814001804003740037381303387671001020100002030000400374003711100211091010100001000000640416343947310000104003840038400384003840038
10024400373000000613940725100101010000101000050570690814001804003740037381303387671001020100002030000400374003711100211091010100001000000640316333947310000104003840038400384003840038
10024400373000000613940725100101010000101000050570690814001804003740037381303387671001020100002030000400374003711100211091010100001000000640316353947310000104003840038400384003840038
10024400372990000613940725100101010000101000050570690814001804003740037381303387671001020100002030000400374003711100211091010100001000000640316333947310000104003840038400384003840038
10024400373000000613940725100101010000101000050570690814001804003740037381303387671001020100002030000400374003711100211091010100001010000640416433947310000104003840038400384003840038
10024400373000000613940725100101010000101000050570690814001804003740037381303387671001020100002030000400374003711100211091010100001000000640416333947310000104003840038400384003840038
10024400373000000613940725100101010000101000050570690814001804003740037381303387671001020100002030000400374003711100211091010100001000000640316433947310000104003840038400384003840038
10024400373000000613940725100101010000101000050570690814001804003740037381303387671001020100002030000400374003711100211091010100001000000640316343947310000104003840038400384003840038
10024400373000000613940725100101010000101000050570690814001804003740037381303387671001020100002030000400374003711100211091010100001000000640416433947310000104003840038400384003840038

Test 3: Latency 1->2

Code:

  fmls s0, s0, v1.s[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)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)696b6d6edispatch 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)9fa1a8a9acc2c5cfd5d6ddinst fetch restart (de)e0eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102044003730006139407251010010010000100100005005706908400180400374003738108033874510100200100002003000040037400371110201100991001001000010000000071011611394790100001004003840038400384003840038
1020440037300061394072510100100100001001000050057069084001804003740037381080338745101002001000020030000400374003711102011009910010010000100000270071011611394790100001004003840038400384003840038
102044003730007263940725101001001000010010000500570690840018040037400373810803387451010020010000200300004003740037111020110099100100100001000101440071011611394790100001004003840038400384003840038
10204400373000613940725101001001000010010000500570690840018040037400373810801238779101002001000020030000400374003711102011009910010010000100000994071011611394790100001004003840038400384003840038
1020440037300061394072510100100100001001000050057069084001804003740037381080338745101002001000020030000400374003711102021009910010010000100000180071011611394790100001004003840038400384003840038
1020440037300061394072510100100100001001000050057069084001804003740037381080338745101002001000020030000400374003711102011009910010010000100000210071011611394790100001004003840038400384003840038
1020440037300061394072510100100100001001000050057069084001804003740037381080338745101002001000020030000400374003711102011009910010010000100000420071011611394790100001004003840038400384003840038
1020440037299061394072510100100100001001000050057069084001804003740037381080338745101002001000020030000400374003711102011009910010010000100000300071011611394790100001004003840038400384003840038
10204400373000613940725101001001000010010000585570970040018040037400373810803387451010020010000200300004003740037111020110099100100100001000021170071011611394790100001004003840038400384003840038
1020440037300061394072510100100100001001000050057069084001804003740037381080338745101002001000020030000400374003711102011009910010010000100000210071021611394790100001004003840038400384003840038

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)9fa7a8a9acc2branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024400373000061394072510010101000010100005057069080400184003740037381303387671001020100002030000400374003711100211091010100001002012000640216223947310000104003840038400384003840038
1002440037300006139407251001010100001010000505706908140018400374003738130338767100102010000203000040037400371110021109101010000100103000640216223947310000104003840038400384003840038
10024400373000061394072510010101000010100005057069081400184003740037381303387671001020100002030000400374003711100211091010100001002300000640216223947310000104003840038400384003840038
1002440037300006139407251001010100001010000505706908140018400374003738130338767100102010000203000040037400371110021109101010000100106000640216223947310000104003840038400384003840038
10024400372990061394072510010101000010100005057069081400184003740037381303387671001020100002030000400374003711100211091010100001004006000640216223947310000104003840038400384003840038
1002440037300006139407251001010100001010000505706908040018400374003738130338767100102010000203000040037400371110021109101010000100809000640216223947310000104003840038400384003840038
10024400373000061394072510010101000010100005057069080400184003740037381303387671001020100002030000400374003711100211091010100001003200000640216223947310000104003840038400384003840038
10024400373000061394072510010101000010100005057069081400184003740037381303387671001020100002230000400374003711100211091010100001001106000640216223947310000104003840038400384003840038
100244003730000613940725100101010000101000050570690804001840037400373813033876710010201000020300004003740037111002110910101000010018012000640216223947310000104003840038400384003840038
100244003729900103394072510010101000010100005057069081400184013140037381303387671001020100002030000400374003711100211091010100001001420200640133223947310000104003840038400384003840038

Test 4: Latency 1->3

Code:

  fmls s0, s1, v0.s[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)0308191e3f4e51inst 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)9fa0a8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204400372990001363940725101001001000010010148500570690840018400374003738108338745101002001000020030000400374003711102011009910010010000100050071011611394790100001004003840038400384003840038
10204400373000006139407251010010010000100100005005706908400184003740037381083387451010020010000200300004003740037111020110099100100100001000280071011611394790100001004003840038400384003840038
10204400373000006139407251010010010000100100005005706908400184003740037381083387451010020010000200300004003740037111020110099100100100001000590071011611394790100001004003840038400384003840038
10204400373000006139407251010010010000100100005005706908400184003740037381083387451010020010000200300004003740037111020110099100100100001000915071011611394790100001004003840038400384003840038
10204400373000006139407251010010010000100100005005706908400184003740037381083387451010020010000200300004003740037111020110099100100100001000912071011611394790100001004003840038400384003840038
10204400372990006139407251010010010000100100005005706908400184003740037381083387451010020010000200300004003740037111020110099100100100001000415071011611395510100001004003840038400384003840038
10204400373000006139407251010010010000100100005005706908400184003740037381083387451010020010000200300004003740037111020110099100100100001000712071011611394790100001004003840038400384003840038
1020440037300000613940725101001001000610010000500570690840018400374003738108338745101002001000020030000400374003711102011009910010010000100079071011611394790100001004003840038400384003840038
10204400373000006139407251010010010000100100005005706908400184003740037381083387451010020010000200300004003740037111020110099100100100001000157071011611394790100001004003840038400384003840038
10204400373000006139407251010010010000100100005005706908400184003740037381083387451010020010000200300004003740037111020110099100100100001000812171011611394790100001004003840038400384003840038

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)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)9fa6a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100244003729900613940725100101010000101000050570690840018400374003738130338767100102010000203000040037400371110021109101010000100100640216223947310000104003840038400384003840038
100244003729900613940725100351010000101000050570690840018400844008538130338767100102010000203000040037400371110021109101010000100000640216223947310000104003840038400384003840038
1002440037300005363940725100101010000101000050570690840018400374003738130338767100102010000203000040037400371110021109101010000100300640216223947310000104003840038400384003840038
100244003730000613940725100101010000101000050570690840018400374003738130338767100102010000203000040037400371110021109101010000100400640216223947310000104003840038400384003840038
100244003730000613940725100101010000101000050570690840018400374003738130338767100102010000203000040037400371110021109101010000100400640216223947310000104003840038400384003840038
100244003730000613940725100101010000101000050570690840018400374003738130338767100102010000203000040037400371110021109101010000100300640216223947310000104003840038400384003840038
10024400373000072639407104100101210000101000050570690840018400374003738130338767100102010000203000040037400371110021109101010000100400640216223947310000104003840038400384003840038
1002440037300009433940725100101010000101000050570690840018400374003738130338767100102010000203000040037400371110021109101010000100300640216223947310000104003840038400384003840038
100244003730000613940725100101010000101000050570690840018400374003738130338767100102010000203000040037400371110021109101010000100200640216223947310000104003840038400384003840038
1002440037300057613940725100101010000101000050570690840018400374003738130338767100102010000203000040037400371110021109101010000100100640216223947310000104003840038400384003840038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  fmls s0, s8, v9.s[1]
  movi v1.16b, 0
  fmls s1, s8, v9.s[1]
  movi v2.16b, 0
  fmls s2, s8, v9.s[1]
  movi v3.16b, 0
  fmls s3, s8, v9.s[1]
  movi v4.16b, 0
  fmls s4, s8, v9.s[1]
  movi v5.16b, 0
  fmls s5, s8, v9.s[1]
  movi v6.16b, 0
  fmls s6, s8, v9.s[1]
  movi v7.16b, 0
  fmls s7, s8, v9.s[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)03191e3f51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160204200771500040258010010080000100800005006400000200462006520065323801002008000020024000020065200651116020110099100100160000100001011111611200621600001002006620066200662006620066
160204200651500040258010010080000100800005006400000200462006520065323801002008000020024000020065200651116020110099100100160000100001011111611200621600001002006620066200662006620066
160204200651500040258010010080000100800005006400000200462006520065323801002008000020024000020065200651116020110099100100160000100001011111611200621600001002006620066200662006620066
160204200651500040258010010080000108801095006400000200462006520065323801002008000020024000020065200651116020110099100100160000100381681011111611201521600001002006620066200662006620066
160204200651500040258010010080000100800005006400001200462006520065323801002008000020024000020065200651116020110099100100160000100131011111611200621600001002006620066200662006620066
160204200651500040258010010080000100800005006400000200462006520065323801002008000020024000020065200651116020110099100100160000100101011111611200621600001002006620066200662006620066
160204200651500040258010010080000100800005006400000200462006520065323801002008000020024000020065200651116020110099100100160000100201011111611200621600001002006620066200662006620066
160204200651500940258010010080000100800005006400000200462006520065323801002008000020024000020065200651116020110099100100160000100101011111611200621600001002006620066200662006620066
16020420065150004025805621008000010080000500640000120046200652006532380100200800002002400002006520065111602011009910010016000010050961011111611200621600001002006620066200662006620066
1602042006515100402580100100800001008000050064000002004620065200653238010020080000200240000200652006511160201100991001001600001004431011111611200621600001002006620066200662006620066

1000 unrolls and 10 iterations

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

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)5f6061696b6d6escheduler 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
160024200621500046278001212800001280000626400001152003302005220052323800122080000202400002005220061111600211091010160000100001003083152521176200492201160000102005320053200532005320053
160024200521500046278001212800001280000626400001152003302005220052323800122080000202400002005220052111600211091010160000101001002882172521155200492201160000102005320053200532005320053
160024200521500046278001212800001280000626400001152003302005220052323800122080000202400002005220052111600211091010160000101001002883172521166200492201160000102005320053200532005320053
160024200521500046278001212800001280000626400001152003302005220052323800122080000202400002005220052111600211091010160000100001003083152521156200492201160000102005320053200532005320053
1600242005215000462780012128000012800006264000011520033020052200523238001220801092024000020052200521116002110910101600001049001003083172521154200492201160000102005320053200532005320053
160024200521500046278001212800001280000626400001152003302005220052323800122080000202400002005220052111600211091010160000100001002883162521166200492201160000102005320053200532005320053
160024200521500046278001212800001280000626400001152003302005220052323800122080000202400002005220052111600211091010160000100001002883172521154200492201160000102005320053200532005320053
1600242005215000462780012128000012800006264000011520033020052200523238001220800002024000020052200521116002110910101600001044031002983162521187200492201160000102005320053200532005320053
160024200521500046278001212800001280000626400001152003302005220052323800122080000202400002005220052111600211091010160000100001003083172521177200492201160000102005320053200532005320053
160024200521500046858001212802171280000626400001152003302005220052323800122080000202400002005220052111600211091010160000100001002883172521166200492201160000102005320053200532005320053

Test 6: throughput

Count: 12

Code:

  fmls s0, s12, v13.s[1]
  fmls s1, s12, v13.s[1]
  fmls s2, s12, v13.s[1]
  fmls s3, s12, v13.s[1]
  fmls s4, s12, v13.s[1]
  fmls s5, s12, v13.s[1]
  fmls s6, s12, v13.s[1]
  fmls s7, s12, v13.s[1]
  fmls s8, s12, v13.s[1]
  fmls s9, s12, v13.s[1]
  fmls s10, s12, v13.s[1]
  fmls s11, s12, v13.s[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)03181e373f4e51inst 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)9fa0a7a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1202044098430000061996125120100100120000100120000500585199314167204169140039249323249971201002001200002003600004168740039111202011009910010012000010000000761011611400301200001004169240040416924004041692
120204416913000120612608125120100100120000100120000500585186914002004003940039249323249971201002001200002003600004003940039111202011009910010012000010000000761011611400301200001004169240040416924004041692
120204416912990002323796625120101100120001100120000500563064014167204169140039249323249971201002001200002003600004003941691111202011009910010012000010001200761011611400301200001004169240040416924004041692
12020441691299001189996125120100100120000100120000500563064014002004003941691265823249971201002001200002003600004003941691111202011009910010012000010000000761011611400301200001004004040040416924004041692
12020441691300001613796625120101100120001100120000500585186914167204169140039249323249971203032001200002003600004169141686111202011009910010012000010020000761011611400301200001004004041692400404122641692
1202044169129900061996125120101100120001100120000500563064014002004003941691265823266441201002001200002003600004169140039111202011009910010012000010000000761011611400301200001004004040040416924004041692
1202044169130000161996125120200100120000100120000500585186904166704169141686249323249971201002001200002003600004003941691111202011009910010012000010000000761011611400301200001004004040040400404004040040
1202044003931200061996125120100100120000100120000500585186904002004003940039249323249971201002001200002003600004003941691111202011009910010012000010000000761011611400301200001004004040040416924004041692
1202044169130000061996125120100100120000100120000500585186914002004003941691249323249971201002001200002003600004003940039111202011009910010012000010000000761011611416831200001004004041692400404168741692
1202044169130000061996125120100100120000100120000500585186914166704169140039249323249971201002001200002003600004003941691111202011009910010012000010000000761011611400301200001004004041692400404004040040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03081e373a3f4e51inst 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)9fa0a1a7a8a9accfd0d5d6d9ddinst fetch restart (de)dfe0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
120024400393120000619961251200101012000010120000505630640400200400394003924955325019120010201200002036000040039416881112002110910101200001000000075200121601011040030120000104004040040400404004040088
120024400393000000619961251200101012000010120000505630640416670400394003924955325019120010201200002036000040039416861112002110910101200001000000075300111601111040030120000104004040040400404004040040
120024400392990000619961251200101012000010120000505630640400200400394003924955325019120010201200002036000040039400391112002110910101200001000000075200131601211040030120000104004040040400404004040040
120024416863000000619961251200101012000010120000505630640400200400394003924955325019120010201200002036000040039417212112002110910101200001000000075200101601110041693120000104004040040416874004040040
120024400393000000619961251200101012000010120000505851869400200416864003924955325019120010201200002036000040039400391112002110910101200001000000075200121601012040030120000104004040040400404004040040
120024400392990000619961251200131012000410120000505630640400200400394003924955325019120010201200002036000040039400391112002110910101200001000000075200101601112040030120000104169241692416884004040040
120024400393120000156356892512001010120000101200005058518694166704003940039249552725019120010201200002036000040039400391112002110910101200001000000075200121601012040030120000104004040040400404004040040
120024416863000000619961251200101012000010120000505851993400200400394003924955325019120010201200002036000040039408681112002110910101200001000000075200121601310240030120000104004041687400404004040040
1200244003930001200619961251200101012000010120000505630640400200416864003924955325019120010201200002036000040039416911112002110910101200001000000075200131621211040030120000104004040040400404004040040
120024400393001000619961251200101012000010120000505630640400200400394003924955325019120010201200002036000040039400391112002110910101200001000000075206131601212040030120000104004040040400404004040040