Apple M1 Microarchitecture Research by Dougall Johnson

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

MLS (by element, 4S)

Test 1: uops

Code:

  mls v0.4s, v1.4s, 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)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
1004303722006125482510001000100039831313018303730372415328951000100030003037303711100110003073116112630100030383038303830383038
1004303723006125482510001000100039831303018303730372415328951000100030003037303711100110002073116112630100030383038303830383038
1004303723006125482510001000100039831303018303730372415328951000100030003037303711100110002073116112630100030383038303830383038
10043037230046025482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037230966125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
1004303722006125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037220061254825100010001000398313030183037303724153289510001000300030373037111001100003973116112630100030383038303830383038
1004303723006125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
1004303723006125482510001000100039831303018303730372415328951000100030003037303711100110001073116112630100030383038303830383038
10043037230186125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  mls v0.4s, v1.4s, 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): 3.0037

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)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)9fa8accfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000071002162229634100001003003830038300383003830038
10204300372240061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000071002162229634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000071012162229634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000071012163229634100001003003830038300383003830038
10204300372250061295392510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000071012162229634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000071212162229634100001003003830038300383003830038
102043003722500726295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000071012162329634100001003003830038300383003830038
102043003722500536295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000071212162229634100001003003830038300383003830038
10204300372250161295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000071012162229634100001003003830038300383003830038
10204300372240061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000071012162229634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0307080b18191e1f3a3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500000240061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000006403164329630010000103003830038300383003830038
1002430037225000003450061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000006404163329630010000103003830038300383003830038
1002430037224000004320061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000006403162229630010000103003830038300383003830038
1002430037225000005130061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
1002430037225000002880061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000006402163329630010000103003830038300383003830038
10024300372250000060061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000006402163229630010000103003830038300383003830038
100243003722500000330061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000006403163329630010000103003830038300383003830038
10024300372250000060061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000006402163329630010000103003830038300383003830038
10024300372250000000061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000006402163229630010000103003830038300383003830038
10024300372250000060061295482510010101000010100005042773130300543003730037282873287671001020100002030000300373003711100211091010100001000000006402162329630010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  mls v0.4s, v0.4s, 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): 3.0037

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)9fa1a8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250726295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
102043003722566631295488510120100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
102043003722575726295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
10204300372251141562954825101001001000012010000500427731330018301343003728265328745101002141000020030000300373003711102011009910010010000100401126807101161229634100001003003830038300863008630038
1020430037225123170295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
102043003722523461295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010001007321161129634100001003003830038300383003830038
1020430037225174103295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
1020430037225661295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
1020430037224061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03191e3f4e51inst 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)9fa8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500612954825100101010000101000050427731303001830037300372828703287671001020100002030000300373003711100211091010100001001470640716332963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313130018300373003728287032876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287032876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
1002430037225106129548251001010100001010000504277313130018300373003728287032876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313130018300373003728287032876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
1002430037225002532954825100101010000101000050427731303001830037300372828703287671001020100002030000300373003711100211091010100001001710640316332963010000103003830038300383003830038
10024300372240061295482510010101000010100005042773131300183003730037282870328767100102010000203000030037300371110021109101010000100510640316332963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287032876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
1002430037224006129548251001010100001010000504277313030018300373003728287032876710010201017220300003003730037111002110910101000010000640316332963010000103003830038300383003830038
1002530037225006129548251001010100001010000504277313030018300373003728287032876710010201000020300003003730037111002110910101000010090640316332963010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  mls v0.4s, v1.4s, 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): 3.0037

retire (01)cycle (02)030818191e1f3f4e51inst 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)9fa6a8acc2c5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100013007101161129634100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100020007101161129634100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100010007101161129634100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000215007101161129634100001003003830038300383003830038
1020430037225010006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100010007101161129634100001003003830038300383003830038
1020430037224000006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100010007101161129634100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100010007101161129634100001003003830038300383003830038
1020430037224000006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100010007101161129634100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100300007101161129634100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100010007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b18191e1f3f4e51inst 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)9fa0a1a6a8acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000000612954825100101010000101000050427731313001830037300372828703287671001020100002030000300373003711100211091010100001000013006402162229630010000103003830038300383003830038
1002430037225000000612954825100101010000101000050427731313001830037300372828703287671001020100002030000300373003711100211091010100001000020006402162229630010000103003830038300383003830038
10024300372250000007262954825100101010000101000050427731303001830037300372828703287671001020100002030000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372250000007882954825100101010000101000050427731313001830037300372828703287671001020100002030000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
1002430037225000000612954825100101010000101000050427779903001830037300372828703287671001020100002030000300373003711100211091010100001000003006402162229630010000103003830038300383003830038
1002430037224010000612954825100101010000101000050427731313001830037300372828703287671001020100002030000300373003711100211091010100001000010006402162229630010000103008630038300383003830038
100243003722500000061295394410020101000012101958142854551302703036730369283090302887711061221098322329283035830368811002110910101000010000116883207693722429884310000103032130368303593036930359
10024303692281078798528202529485157100681710048111104371428681213023430085303702831603328891101612411156203344430368301808110021109101010000104022416673407894733329882110000103041330412304633046630462
100243046422810361200792519129503197100671710067141119276428952613030630418304642832103287671001020100002030000300373003711100211091010100001000000006402162229630010000103008530038300383003830038
1002430037224000000612954825100101010000101000050427731303001830037300372828773287671001020100002030000300373003711100211091010100001000020006402162229630010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  mls v0.4s, v8.4s, v9.s[1]
  movi v1.16b, 0
  mls v1.4s, v8.4s, v9.s[1]
  movi v2.16b, 0
  mls v2.4s, v8.4s, v9.s[1]
  movi v3.16b, 0
  mls v3.4s, v8.4s, v9.s[1]
  movi v4.16b, 0
  mls v4.4s, v8.4s, v9.s[1]
  movi v5.16b, 0
  mls v5.4s, v8.4s, v9.s[1]
  movi v6.16b, 0
  mls v6.4s, v8.4s, v9.s[1]
  movi v7.16b, 0
  mls v7.4s, v8.4s, 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)0318191e1f3f51inst 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)9fa0a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16020420089150000039258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100000101763010111616112006101600001002006520065200652006520065
16020420064150009039258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100000200010111116112006101600001002006520065200652006520065
160204200641510000324258010010080000100800005006400000201762006420064322801002008000020024000020064200641116020110099100100160000100000103010111116112006101600001002006520065200652006520065
16020420064151000039258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100000100010111116112006101600001002006520065200652006520065
16020420064150000039258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100000000010182116112006101600001002006520065200652006520065
16020420064150000039258010010080000100800005006423200200452006420064322801002008000020024000020064200641116020110099100100160000100000303010111116112006101600001002006520065200652006520065
16020420064150000039258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100000000010111116112006101600001002006520065200652006520065
16020420064150000039258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100000100010111116112006101600001002006520065200652006520065
160204200641500000392580100100800001008000050064000002004520064200643228010020080000200240000200642006411160201100991001001600001000003303010111116112006101600001002006520065200652006520065
160204200641500000392580100100800001008000050064000002004520064200643228010020080000200240000200642006411160201100991001001600001000001603010111116112006101600001002006520065200652038720065

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0304070a183a3f51inst 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)5f60696b6d6escheduler 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)9fa1a8a9acc2cfd0d2icache miss (d3)itlb miss (d4)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1600242006715000000452580012128000012800006264000001200330200522005232280012208000020240000200522005211160021109101016000010010001004465213226322182920043215160000102005320053200532005320053
1600242005215010001572580012128000012800006264000001200330200522005232280012208000020240000200522005211160021109101016000010000001005665213026322212920049231160000102005320053200532005320053
1600242005215010001572580012128000012800006264000001200330200522005232280012208000020240000200522005211160021109101016000010010001005665212326322291720049230160000102005320053200532005320053
1600242005215010000512580012128000012800006264000001200330200502005232280012208000020240000200522005211160021109101016000010010001004465211826322282020049231160000102005320053200532005320053
1600242005215010001512580012128000012800006264000001200330200522005232280012208000020240000200522005211160021109101016000010000001005565213026322242820049231160000102005320053200532005320053
1600242005215012101692580012128000012800006264000001200330200522005232280012208000020240000200522005211160021109101016000010000001005565212826322233220049231160000102005320053200532005320053
1600242005215012200692580012128000012800006264000001200330200522005232280012208000020240000200522005211160021109101016000010010601004365212226322313020049231160000102005320053200532005320053
16002420052150121005718580012128000012800006264000001200330200522005232280012208000020240000200522005211160021109101016000010000001005865213226322253020049231160000102005320053200532005320053
1600242005215112200632580012128000012800006264000001200330200522005232280012208000020240000200522005211160021109101016000010000001005665213126322313120049231160000102005320053200532005320053
1600242005215012201632580012128000012800006264000001200330200522005232280012208000020240000200522005211160021109101016000010000001005865213026322183020049231160000102005320053200532005320053

Test 6: throughput

Count: 12

Code:

  mls v0.4s, v12.4s, v13.s[1]
  mls v1.4s, v12.4s, v13.s[1]
  mls v2.4s, v12.4s, v13.s[1]
  mls v3.4s, v12.4s, v13.s[1]
  mls v4.4s, v12.4s, v13.s[1]
  mls v5.4s, v12.4s, v13.s[1]
  mls v6.4s, v12.4s, v13.s[1]
  mls v7.4s, v12.4s, v13.s[1]
  mls v8.4s, v12.4s, v13.s[1]
  mls v9.4s, v12.4s, v13.s[1]
  mls v10.4s, v12.4s, v13.s[1]
  mls v11.4s, v12.4s, 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): 0.2503

retire (01)cycle (02)0308181e373f4e51inst 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)9fa0a1a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1202043023122500018300251201531001200081001200205009901320300203003930042149776149901201202001200322003600963003930943111202011009910010012000010000031117618116003003901200001003004030043300403004030943
120204300392250000300251201081001200081001200205009601321300203003930042149776149901201202001200322003600963003930042111202011009910010012000010000001117618016003003901200001003004030040300403004330040
120204300392250000330251201531001200001001200005009600000300203003930042149733149971201002001200002003600003003930943111202011009910010012000010000230007610116113003901200001003004030040302523009530040
120204309432250000410251201011001200001001200005009900000300203004230039149733150001201002001200002003600003004230039111202011009910010012000010000000007610116113003601200001003092330040300433004030043
1202043003922500053410251201011001200001001200005009900000300203004230039149733150001201002001200002003600003003930042111202011009910010012000010000000007610116113003601200001003092330040300433004030043
120204300392250001410251201011001200001001200005009900000300233003930039149733149971201002001200002003600003003930042111202011009910010012000010000000007610116113003901200001003004330040300403004030040
120204300422250000613489251201001001200011001200005009600000300203094330039149733150001201002001200002003600003004230039111202011009910010012000010000000007610116113091901200001003004030040300403004030043
120204300392250000410251201011001200001001200005009900000300203003930042149733150001201002001200002003600003094330039111202011009910010012000010000000007610116113003601200001003004330040300403004331737
120204309432250000410251201001001200001001200005009600000309243003930039149733149971201002001200002003600003003930042111202011009910010012000010000000007610116113003601200001003004030040300403004330040
120204300392250000610251201001001200001001200005009600000300233004130039149733149971201002001200002003600003004230039111202011009910010012000010000000007610116113003601200001003004030043300403004030040

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2503

retire (01)cycle (02)0308373f51inst 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)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)9fa1accdcfd5d6daddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
120024300482250040251200101012000010120000509600000030020300393003914996031501912001020120000203600003003930039111200211091010120000100007520916019930036120000103004030040300403004030040
1200243003922500402512001010120000101200005096000000300203003930039149960315019120010201200002036000030039300391112002110910101200001000075208160191930036120000103004030040300403004030040
120024300392250051525120010101200001012000050960000003002030039300391499603150191200102012000020360000300393003911120021109101012000010000752019160191930036120000103004030040300403004030040
1200243003922501751525120010101200001012000050960000003002030039300391499603150191200102012000020360000309223004111120021109101012000010000752019160191930036120000103004030040300403004030040
1200243003922500402512001010120000101200005096000000300203003930039149960315019120010201201402036000030039300391112002110910101200001000075201916019730036120000103004030040300403004030040
12002430039225007052512001010120000101200005096000000309033003930039149960315019120010201200002036000030922300391112002110910101200001000075201916019730036120000103004030040300403004030040
1200243003922500135251200101012000010120000509600000030020300393003914996031501912001020120000203600003003930039111200211091010120000100007520716091930036120000103004030040300403004030040
1200243003922500402512001010120000101200005096000000300203003930039149960315019120010201200002036000030039300391112002110910101200001000075202016019830036120000103004030040300403004030040
12002430039225004025120010101200001012000050960000003002030039300391499603150191200102012000020360000300393003911120021109101012000010200752019160191930036120000103004030040300403004030040
120024309512370040251200101012000010120000509600000030020300393003914996031501912001020120000203600003003930039111200211091010120000100007520916019930036120000103004030040300403004030040