Apple M1 Microarchitecture Research by Dougall Johnson

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

FMLA (vector, 2D)

Test 1: uops

Code:

  fmla v0.2d, v1.2d, v2.2d
  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)031e1f3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)696d6edispatch 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
100440373000613407251000100010005319084018403740373258338951000100030004037403711100110000073216223473100040384038403840384038
100440373000613407251000100010005319084018403740373258338951000100030004037403711100110000073216223473100040384038403840384038
100440373000613407251000100010005319084018403740373258338951000100030004037403711100110000073216223473100040384038403840384038
100440373000613407251000100010005319084018403740373258338951000100030004037403711100110003373216223473100040384038403840384038
100440373000613407251000100010005319084018403740373258338951000100030004037403711100110000073216223473100040384038403840384038
100440373000613407251000100010005319084018403740373258338951000100030004037403711100110000073216223473100040384038403840384038
100440373000613407251000100010005319084018403740373258338951000100030004037403711100110000073216223473100040384038403840384038
100440373000613407251000100010005319084018403740373258338951000100030004037403711100110001073216223473100040384038403840384038
100440373000613407251000100010005319084018403740373258338951000100030004037403711100110000073216233473100040384038403840384038
100440373000613407251000100010005319084018403740373258338951000100030004037403711100110000073216223473100040384038403840384038

Test 2: Latency 1->1

Code:

  fmla v0.2d, v1.2d, v2.2d
  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)031e3a3f4e51inst 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)9fa8accdcfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020440037300006139407251010010010000100100005005706908140018400374003738108033874510100200100002023000040037400371110201100991001001000010006071002162239479100001004003840038400384003840038
10204400373000072639407251010010410006100100005005706908140018400374003738108033874510100200100002003000040037400371110201100991001001000010000071002162339479100001004003840038400384003840038
1020440037300006139407251010010010000100100005005706908040018400374003738108033874510100200100002003000040037400371110201100991001001000010003071002162239479100001004003840038400384003840038
1020440037300006139407441010010010000100100005005706908140018400374003738108033874510100200100002003000040037400371110201100991001001000010000071012162239479100001004003840038400384003840038
10204400373000061394072510100100100001001000050057069081400184003740037381080338745102612001000020030000400374003711102011009910010010000100012071012162339479100001004003840038400384003840038
1020440037300001534394072510100100100001001000050057069081400184003740037381080338745101002001000020030000400374003711102011009910010010000100090071012162339479100001004003840038400384003840038
102044003730100613940745101001001000010010000500570690814001840037400373810803387451010020010000200300004003740037111020110099100100100001000138071012162239479100001004003840038400384003840038
102044003729900613940725101001001000010010000500570690814001840037400373810803387451010020010000200300004003740037111020110099100100100001000123071012162239479100001004003840038400384003840038
102044003729944406139407251010010010000100100005005706908140018400374003738108033874510100200100002003000040037400371110201100991001001000010000071012162239479100001004003840038400384003840038
1020440037300006139407251010010010000100100005005706908140018400374003738108033874510100200100002003000040037400371110201100991001001000010009071012162239479100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)03080918191e3f4e51inst 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)9fa7a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002440037299000006139407251001010100001010000505706908040018400374003738130033876710010201000020300004003740037111002110910101000010003640316223953510000104003840038400384003840038
10024400373000000072639407251001010100001010000505706908040018400374003738130033876710010201000020300004003740037111002110910101000010003640216223947310000104003840038400384003840038
1002440037299000006139407251001010100001010000505706908040018400374003738130033876710010201000020300004003740037111002110910101000010009640216223947310000104003840038400384003840038
10024400372990000061394072510010101000010100005057069081400184003740037381300338767100102010000203000040037400371110021109101010000100084640216223947310000104003840038400384003840038
100244003730000000613940725100101010000101000050570690814001840037400373813003387671001020100002030000400374003711100211091010100001000102640216223947310000104003840038400854003840038
1002440037299000006139407251001010100001010000505706908040018400374003738130033876710010201000020300004003740037111002110910101000010003640216223947310000104003840038400384003840038
100244003730000000613940725100101010000101000050570690804001840037400373813003387671001020100002030000400374003711100211091010100001000117640216223947310000104003840038400384003840038
100244003730200000613940725100101010000101000050570690814001840037400373813003387671001020100002030000400374003711100211091010100001000201640216223947310000104003840038400384003840038
100244003730000000613940725100101010000101000050570690804001840037400373813003387671001020100002030000400374003711100211091010100001000138640216223947310000104003840038400384003840038
1002440037300000006139407251001010100001010000505706908040018400374003738130033876710010201000020300004003740037111002110910101000010006640216223947310000104003840038400384003840038

Test 3: Latency 1->2

Code:

  fmla v0.2d, v0.2d, v1.2d
  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)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)9fa0a8acc2c5branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102044003730000061394072510100100100001001000050057069081400184003740037381083387451010020010000200300004003740037111020110099100100100001000000007101161139479100001004003840038400384003840038
102044003730000061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000000007101161139479100001004003840038400384003840038
1020440037299000536394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000000007101161139479100001004003840038400384003840038
102044003730000061394072510100100100001001000050057069081400184003740037381083387451010020010000200300004003740037111020110099100100100001000000007101161139479100001004003840038400384003840038
102044003730000061394072510100100100001001000050057069081400184003740037381083387451010020010000200300004003740037111020110099100100100001000000007101161139479100001004003840038400384003840038
102044003730000061394072510100100100001001000050057069081400184003740037381083387451010020010000200300004003740037111020110099100100100001000000007101161139479100001004003840038400384003840038
102044003730000061394072510100100100001001000050057069081400184003740037381083387451010020010000200300004003740037111020110099100100100001000000007101161139479100001004003840038400384003840038
102044003729900061394072510100100100001001000050057069081400184003740037381083387451010020010000200300004003740037111020110099100100100001000000017101161139479100001004003840038400384003840038
102044003730000061394072510100100100001001000050057069081400184003740037381083387451010020010000200300004003740037111020110099100100100001000000007101161139479100001004003840038400384003840038
102044003730000061394072510100100100001001000050057069081400184003740037381083387451010020010000200300004003740037111020110099100100100001000000007101161139479100001004003840038400384003840038

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)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)9fa8accdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024400372990000128739407251001010100001010000505706908040018400374003738130338767100102010000203000040037400371110021109101010000100006403163339473010000104003840038400384003840038
10024400373000000149394072510010101000010100005057069080400184003740037381303387671001020100002030000400374003711100211091010100001002406403163339473010000104003840038400384003840038
1002440037300000079039407251001010100001010000505706908040018400374003738130338767101582010000203000040037400371110021109101010000100006403163339473010000104003840038400384003840038
100244003730000008439407251001010100001010000505706908040018400374003738130338767100102010000203000040037400371110021109101010000100006403163339473010000104003840038400384003840038
100244003729900008439407251001010100001010000505706908140018400374003738130338767100102010000203000040037401322110021109101010000100006403163339473010000104003840038400384003840038
1002440037299000072639407251001010100001010000505706908040018400374003738130338767101582010000203000040037400371110021109101010000100006403163339473010000104003840038400384003840038
1002440037300000010539407251001010100001010000505706908040018400374003738130338767100102010000203000040037400371110021109101010000100006403163339473010000104003840038400384003840038
1002440037299000010739407251001010100001010000505706908040018400374003738130338767100102010000203000040037400371110021109101010000100006403163339473010000104003840038400384003840038
1002440037300000010539407251001010100001010000505706908040018400374003738130338767100102010000203000040037400371110021109101010000100006403163339473010000104003840038400384003840038
10024400373000000104939407441001010100001010000505706908040018400374003738130338767100102010000203000040037400371110021109101010000100006403163339473010000104003840038400384003840038

Test 4: Latency 1->3

Code:

  fmla v0.2d, v1.2d, v0.2d
  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)0308090b18191e3f4e51inst 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)6061696d6edispatch 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)9fa0a8acc2cfd0d2d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102044003730000000018739407251010010010000100100005005706908134001840037400373810833874510100200100002003000040037400371110201100991001001000010000307103311611394790100001004007940038400384003840038
1020440037300000000106839407251010010010000100100005005706908104001840085400373810833874510100200100002003000040037400371110201100991001001000010002007100011611394790100001004003840038400384003840038
1020440037299000000103739407251010010010000100100005005706908004001840037400373810833874510100200100002003000040037400371110201100991001001000010000007100015011394790100001004003840038400384003840038
1020440037300000000104839407251010010010000100100005005706908104001840037400373810833874510100200100002003000040037400371110201100991001001000010000007100311611394790100001004003840038400384003840038
1020440037300000000107739407251010010010000100100005005706908004001840037400373810833874510100200100002003000040037400371110201100991001001000010000007100011611394790100001004003840038400384003840038
1020440037299000000104339407251010010010000100100005005706908004001840037400373810833874510100200100002003000040037400371110201100991001001000010000007103311611394790100001004003840038400384003840038
102044003730000000061339407251010010010000111101485005706908104001840037400373810833874510100200100002003000040037400371110201100991001001000010000007100011611394790100001004003840038400384003840038
102044003729900000010539407251010010010000100100005005706908034001840037400373810833874510100200100002003000040037400371110201100991001001000010000007100011611394790100001004003840038400384003840038
102044003730000000012639407251010010010000100100005005706908034001840037400373810833874510100200100002003000040037400371110201100991001001000010000007100011611394790100001004003840038400384003840038
10204400373000000006139407251010010010000100100005005706908104001840037400373810833874510100200100002003000040037400371110201100991001001000010000307103314911394790100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)031e3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)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)9fa1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002440037299121243940725100101010000101000050570690814001840037400373813033876710010201000020300004003740037111002110910101000010210640216323947310000104003840038400384008640038
100244003730004413940725100101010000101000050570690804001840037400373813033876710010201000020300004003740037111002110910101000010000640216223947310000104003840038400384003840038
100244003730001723940725100101010000101000050570690804001840037400373813033878610010201000020300004003740037111002110910101000010000640216223947310000104003840038400384003840038
10024400373000613940725100101010000101000050570690804001840037400373813033876710010201000020300004003740037111002110910101000010000640216223947310000104003840038400384003840038
10024400373000613940725100101010000101000050570690804001840037400373813033876710010201000020300004003740037111002110910101000010000640316223947310000104003840038400384003840038
10024400373000613940725100101010000101000050570690814001840037400373813033876710010201000020300004003740037111002110910101000010000640216223947310000104003840038400384003840038
100244003730009433940725100101010000101000050570690814001840037400373813033876710010201000020300004003740037111002110910101000010000640216223947310000104003840038400384003840038
100244003730001033940725100101010000101000050570690814001840037400373813033876710010201000020300004003740037111002110910101000010000640216223947310000104003840038400384003840038
10024400372990613940725100101010000101000050570690814001840037400373813033876710010201000020300004003740037111002110910101000010003640216223947310000104003840038400384003840038
10024400373000613940725100101010000101000050570690814001840037400373813033876710161201000020300004003740037211002110910101000010020640216223947310000104003840038400384003840038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  fmla v0.2d, v8.2d, v9.2d
  movi v1.16b, 0
  fmla v1.2d, v8.2d, v9.2d
  movi v2.16b, 0
  fmla v2.2d, v8.2d, v9.2d
  movi v3.16b, 0
  fmla v3.2d, v8.2d, v9.2d
  movi v4.16b, 0
  fmla v4.2d, v8.2d, v9.2d
  movi v5.16b, 0
  fmla v5.2d, v8.2d, v9.2d
  movi v6.16b, 0
  fmla v6.2d, v8.2d, v9.2d
  movi v7.16b, 0
  fmla v7.2d, v8.2d, v9.2d
  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)03181e3f51inst 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)60696b6d6escheduler 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)9fa8acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16020420091150004025801251008000010080000500640000020046020065200654123801002008000020024000020065200651116020110099100100160000100000010111716112006201600001002006620066200662006620066
1602042006515000402580100100800001008000050064000002004602006520065323801002008000020024000020065200651116020110099100100160000100000010111116112006201600001002006620066200662006620066
1602042006515000402580125100800001008000050064000002004602006520065323801002008000020024000020065200651116020110099100100160000100030010111116112006201600001002006620066200662006620066
1602042006515000402580100100800001008000050064000002004602006520065323801002008000020024000020065200651116020110099100100160000100002010111116112006201600001002006620066200662006620066
1602042006515000402580100100800001008000050064000002004602006520065323801002008000020024000020065200651116020110099100100160000100000010111116112006201600001002006620066200662006620066
16020420065150021402580100100800001008000050064000002004602006520065323801002008000020024000020065200651116020110099100100160000100000010111116112006201600001002006620066200662006620066
1602042006515000402580100100800001008000050064000002004602006520065323801002008000020024000020065200651116020110099100100160000100000010111116212006201600001002006620066200662006620066
1602042006515000402580100100800001008000065064000002004602006520065323801002008000020024000020065200651116020110099100100160000100000010111116112006201600001002006620066200662006620066
1602042006515000402580100100800001008000050064000002004602006520065323801252008000020024000020065200651116020110099100100160000100000010111116112006201600001002006620066200662006620066
1602042006515000402580100100800001008000050064000002004602006520065323801002008000020024000020065200651116020110099100100160000100030010111116112006201600001002006620066200662006620066

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e1f3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)5f6061696d6escheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa1a8accdcfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16002420076150004625800121280000128000062640000110200282004720047323800122080000202400002004720386111600211091010160000102330100376211126322111220048230160000102005220054200542013520052
16002420051150004625800121280000128000062640000010200322005120051323800122080000202400002004720047111600211091010160000100000100333119202118920044215160000102004820048200482004820048
1600242004715000462580012128000012800006264000011020028200472004732380012208000020240000200472004711160021109101016000010000010034711920211111120044215160000102004820048200482004820048
16002420047150007225800121280000128000062640000110200282004720047323800122080000202400002004720047111600211091010160000100000100323119202119820044215160000102004820048200482004820048
1600242004715000462580012128000012800006264000011020028200472004732380012208000020240000200472004711160021109101016000010000010031311820211101120044215160000102004820048200482004820048
16002420047150006925800121280000128000062640000110200282004720047323800122080000202400002004720047111600211091010160000100190010032311112021110920044215160000102004820048200482004820048
16002420047151009602580012128000012800006264000011020028200472004732380012208000020240000200472004711160021109101016000010000010032311122021110920044215160000102005220048200482004820048
160024200471510046258001212800001280000627444721102002820047200473238001220800002024000020047200471116002110910101600001000001003261110202119920044215160000102004820048200482004820048
160024200471500086625800121280000128000062640000110200282004720047323800122080000202400002004720047111600211091010160000100000100348311020211101120044215160000102004820048200482004820048
1600242004715000462580012128000012800006264000011520028200472004732380012208000020240000200472004711160021109101016000010000010035821920211101120044215160000102004820048200482004820048

Test 6: throughput

Count: 16

Code:

  fmla v0.2d, v16.2d, v17.2d
  fmla v1.2d, v16.2d, v17.2d
  fmla v2.2d, v16.2d, v17.2d
  fmla v3.2d, v16.2d, v17.2d
  fmla v4.2d, v16.2d, v17.2d
  fmla v5.2d, v16.2d, v17.2d
  fmla v6.2d, v16.2d, v17.2d
  fmla v7.2d, v16.2d, v17.2d
  fmla v8.2d, v16.2d, v17.2d
  fmla v9.2d, v16.2d, v17.2d
  fmla v10.2d, v16.2d, v17.2d
  fmla v11.2d, v16.2d, v17.2d
  fmla v12.2d, v16.2d, v17.2d
  fmla v13.2d, v16.2d, v17.2d
  fmla v14.2d, v16.2d, v17.2d
  fmla v15.2d, v16.2d, v17.2d
  movi v16.16b, 17
  movi v17.16b, 18

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2502

retire (01)cycle (02)0309191e373f4e51inst 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)9fa7a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602044016230800004289372516016010016005110016000050012800001400214004042314199730321148160100200160000200480000423094004011160201100991001001600001000001011021611423151600001004067842319400414004140041
16020440040317000040502516015310016000010016000050012800001422994004040040199730319998160100200160000200480000400404004011160201100991001001600001000001011011611400371600001004231940041423194004140041
16020440040317000022189282516015310016005310016000050058683331400214231840040222220322276160100200160000200480000400404004011160201100991001001600001000001011011661400371600001004004142282400424004140041
160204422812990005112602516010110016000010016000050012800001422994004040041199730319999160100200160000200480000400404004011160201100991001001600001000001011011611423151600001004004142319400414004140041
160204400402990005151789702516015110016000010016000050012800001400214231840040199730319998160100200160000200480000400404004011160201100991001001600001000001011011611423151600001004230642306400414004140041
16020440040300000046789702516010010016000010016000050013200001400214004042318222220322272160100200160000200480000400404004011160201100991001001600001000001011011611423151600001004231040041400414004140041
16020442309300000045402516010010016000010016000050012800001400214231840040199730319998160100200160000200480000423054004211160201100991001001600001000001011011611400371600001004004140041400414004140041
16020440040300000042402516015310016005310016000050012800001400214004040040199730320010160100200160000200480000411904004011160201100991001001600001000001011011611423151600001004004142319400414004140041
16020440040316000041189282516010010016000010016000050058682061422994004042318222220319998160100200160000200480000422814004011160201100991001001600001000001011011711423151600001004004142319400414231940041
16020442318300000048702516010010016000010016000050012800001422904004042318199730319998160100200160000200480000423184004011160201100991001001600001000001011011611423151600001004004140042400414004142319

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2502

retire (01)cycle (02)03181e1f373f4e51inst 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)5f6061696d6edispatch 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)9fa8acc2cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1600244210131700004788962516001010160035101600005012800001154002140040412451999632002016001020160000204800004004040044111600211091010160000100001002281161681110840038209160000104229540041400414004140041
160024400403000000470251600101016000010160000501280000115400214004042294199963200201600102016000020480000400404007811160021109101016000010000100228416164114742315207160000104004142319400414231940041
160025400403000000670251600451016000010160000501280000115400214004040040199963200201600102016000020480363400404004511160021109101016000010000100228416164115440037207160000104124640041400414004140041
160024412453000000670251600101016000010160000501280000115400214004042294199963200201600102016000020480000411904229611160021109101016000010100100228415164118540037208160000104119140041400414228640041
160024400402990000470251600101016000010160000501280000115423084004040040199963200201600102016000020480000400404004411160021109101016000010000100228416166126642276208160000104004140041412034004140041
160024400403000000478863251600101016003510160000501280000115422774004040040199963222741600102016000020480000400404229611160021109101016000010000100248514164117940037409160000104004140041400414004140041
1600244004030000005302516001010160000101600005012800001154002140040400401999632002016001020160000204800004004040044111600211091010160000100001002485241662278400374018160000104004140041412464004140041
16002440040300000053025160010101600001016000050128000001540021412454229422220320020160010201600002048031542294423091116002110910101600001070010024115181662278400374022160000104004240041400414004140041
16002440040300000175302516001010160000101600005013199991154002140041400401999632229816001020160000204800004004040043111600211091010160000100001002411528166227641242407160000104004140041400414004140041
1600244004030000005302516001010160035101600005012800000154226642294412452117332002016001020160000204800004004040041111600211091010160000100001002211414164216642291208160000104124642295400414004140041