Apple M1 Microarchitecture Research by Dougall Johnson

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

MLS (vector, 8B)

Test 1: uops

Code:

  mls v0.8b, v1.8b, v2.8b
  movi v0.16b, 1
  movi v1.16b, 2
  movi v2.16b, 3

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 1.000

Issues: 1.000

Integer unit issues: 0.000

Load/store unit issues: 0.000

SIMD/FP unit issues: 1.000

retire (01)cycle (02)031e3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)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
10043037230612548251000100010003983133018303730372415328951000100030003037303711100110000073216112630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100030003037303711100110001073116112630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100030003037303711100110004073116112630100030383038303830383038
10043037220612548251000100010003983133018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037230612548251000100010003983133018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037220612548251000100010003983133018303730372415328951000100030003037303711100110000073116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  mls v0.8b, v1.8b, v2.8b
  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
10204300372240061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000071012162229634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000071012162229634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010172200300003003730037111020110099100100100001000071012162229634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000071012162229634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000071012162229634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000071012162229634100001003003830038300383003830038
10204300372240061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000071012163229634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000071013163229634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000071012162229634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000071012162229634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0308181e1f3f4e51inst 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)9fa6a8acc2cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000640316222963010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000640217222963010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773130300543003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001001000640216222963010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000640216322963010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000640216232963010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
100243003722500120103295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001001300640216222963010000103003830038300383003830038
100243003722500120103295302510018101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  mls v0.8b, v0.8b, v1.8b
  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)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722506129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830085300383003830038
102043003722506129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
1020430037225010629548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313030018300373003728265828763101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
1020430037225186129548251010010010000125100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038

1000 unrolls and 10 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)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)9fa8c5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250612954825100101010000101000050427731313001803003730037282873287671001020100002030000300373003711100211091010100001000640316332963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731313001803003730037282873287671001020100002030000300373003711100211091010100001000640316332963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731313006303003730037282873287671001020100002030000300373003711100211091010100001000640316332963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001803003730037282873287671001020100002030000300373003711100211091010100001000640316332963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001803003730037282873287671001020100002030000300373003711100211091010100001000640316332963010000103003830038300383003830038
100243003722501452954825100101010000101000050427731303001803003730037282873287671001020100002030000300373003711100211091010100001000640316332963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001803003730037282873287671001020100002030000300373003711100211091010100001000640316332963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001803003730037282873287671001020100002030000300373003711100211091010100001000640316332963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001803003730037282873287671001020100002030000300373003711100211091010100001000640316332963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001803003730037282873287671001020100002030000300373003711100211091010100001000640316332963010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  mls v0.8b, v1.8b, v0.8b
  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)031e1f3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225633521702954825101001001000010010149561428123803001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011711296340100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000017771011611296340100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
1020430037224007262954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000971011611296340100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03090b191e3f4e51inst 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)9fa0a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722520034092954825100101010000101000050427731330018030037300372828732876710010201000020300003003730037111002110910101000010000640416332963010000103003830038300383003830038
100243003722500018612954825100101010000101000050427731330018030037300372828732876710010201000020300003003730037211002110910101000010000640316332963010000103003830038300383003830038
100243003722500024612954825100101010000101000050427731330018030037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
100243003722400015612954825100101010000101000050427731330018030037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
10024300372240000612954825100101010000101000050427731330018030037300372828732876710010201000020300003008430037111002110910101000010000640316332963010000103003830038300383003830038
100243003722400021822954825100101010000101000050427731330018030037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
1002430037225000271702954825100101010000101000050427731330018030037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
10024300372250002643462954825100101010000101000050427731330018030037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
100243003722500018612954825100101010000101000050427731330018030037300372828732876710010201000020300003003730037111002110910101000010003640316332963010000103003830038300383003830038
10024300372330000612954825100101010000101000050427731330018030037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  mls v0.8b, v8.8b, v9.8b
  movi v1.16b, 0
  mls v1.8b, v8.8b, v9.8b
  movi v2.16b, 0
  mls v2.8b, v8.8b, v9.8b
  movi v3.16b, 0
  mls v3.8b, v8.8b, v9.8b
  movi v4.16b, 0
  mls v4.8b, v8.8b, v9.8b
  movi v5.16b, 0
  mls v5.8b, v8.8b, v9.8b
  movi v6.16b, 0
  mls v6.8b, v8.8b, v9.8b
  movi v7.16b, 0
  mls v7.8b, v8.8b, v9.8b
  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)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)60696d6e74scheduler 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)9fa0a8acc5branch mispredict (cb)cdcfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160204200651500029258011610080016100800285006401961200452006520065071280128200800282002400842006520065111602011009910010016000010000611110119011600200621600001002006620066200662006620066
160204200651500029258011610080016100800285006401960200452006520065061280128200800282002400842006520065111602011009910010016000010000011110119001600200621600001002006620066200662006620066
1602042006515101829258011610080016100800285006401960200452006520065061280128200800282002400842006520065111602011009910010016000010001911110119001600200621600001002006620066200662006620066
160204200651510029258011610080016100800285006401960200452006520065061280128200800282002400842006520065111602011009910010016000010002311110119001600200621600001002006620066200662006620066
160204200651500029258011610080016100800285006401960200452006520065061280128200800282002400842006520065111602011009910010016000010000011110119001600200621600001002006620066200662006620066
160204200651500029258011610080016100800285006401960200452006520065061280128200800282002400842006520065111602011009910010016000010000011110119001600200621600001002006620066200662006620066
1602042006515100292580116100800161008002850064019602004520065200650612801282008002820024008420065200651116020110099100100160000100001511110119001600200621600001002006620066200662006620066
1602042014815000409258011610080016100800285006401960200452006520065061280128200800282002400842015620065111602011009910010016000010000011110119001600200621600001002006620066200662006620066
160204200651510029258011610080016100800285006401960200452006520065061280128200800282002400842006520065111602011009910010016000010000011110119001600200621600001002006620066200662006620066
1602042006515000292580116100800161008002850064019602004520065200650612801282008002820024008420065200651116020110099100100160000100021811110119001600200621600001002006620066200662006620066

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2507

retire (01)cycle (02)031e3f51inst 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)9fa8accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16002420089150951298001212800001280000626400000120041200602006032280012208000020240000200512006011160021109101016000010001003362243442277200572202160000102006120061200522006120061
16002420051150051278001212800001280000626400001120032200602005132280012208000020240000200512006011160021109101016000010401591003262162522257200572402160000102006120052200612006120052
16002420060150051298001212800001280000626400001120041200602006032280012208000020240000200602006011160021109101016000010601003262263441274200482402160000102006120052200612006120061
16002420060150351298001212800001280000626400000120032200602006032280012208000020240000200602005111160021109101016000010031002962233442185200572202160000102006120052200612006120061
1600242005115105129800121280000128000062640000112004120060200513228001220800002024000020060200601116002110910101600001001261002661233442235200572402160000102006120061200612006120061
1600242006015054651298001212800001280000626400000120041200602006032280012208000020240000200602005111160021109101016000010131003131282542187200482402160000102006120061200612006120061
16002420060150051278001212800001280000626400000120041200602005132280117208000020240000200602006011160021109101016000010001003162253442264200572402160000102005220061200612006120061
16002420060150051298001212800001280000626400001120032200512006032280012208000020240000200602006011160021109101016000010031003062173422174200572402160000102005220061200612006120061
160024203031510512780012128000012800006264000001200412006020060322800122080000202400002006020051111600211091010160000101701003132153422147200482402160000102006120052200612005220061
160024200601500512980012128000012800006264000001200412006020060322800122080000202400002006020060111600211091010160000103061003362133422156200572401160000102006120061200612006120061

Test 6: throughput

Count: 16

Code:

  mls v0.8b, v16.8b, v17.8b
  mls v1.8b, v16.8b, v17.8b
  mls v2.8b, v16.8b, v17.8b
  mls v3.8b, v16.8b, v17.8b
  mls v4.8b, v16.8b, v17.8b
  mls v5.8b, v16.8b, v17.8b
  mls v6.8b, v16.8b, v17.8b
  mls v7.8b, v16.8b, v17.8b
  mls v8.8b, v16.8b, v17.8b
  mls v9.8b, v16.8b, v17.8b
  mls v10.8b, v16.8b, v17.8b
  mls v11.8b, v16.8b, v17.8b
  mls v12.8b, v16.8b, v17.8b
  mls v13.8b, v16.8b, v17.8b
  mls v14.8b, v16.8b, v17.8b
  mls v15.8b, v16.8b, v17.8b
  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)03191e1f373f51inst 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)9fa1a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602044007530000017422516010010016000010016000050023989991400294004840039199733199971601002001600002004800004004940040111602011009910010016000010000001011031633400371600001004004040050400504004040049
1602044003929900017502516011710016000010016000050024388651400214004840039199733199971601002001600002004800004003940039111602011009910010016000010000101011031633400361600001004004040040400404005040041
1602044004030000004125160117100160000100160000500128000014002040048400391997331999716010020016000020048000040039400391116020110099100100160000100005601011031633400361600001004004140041400414004040050
160204400393000001502516011710016001810016000050012800001400304003940039199733199971601002001600002004800004004040039111602011009910010016000010000001011031633400361600001004004140041400404004140040
160204400483000000422516011710016001710016000050012800001400294004040039199733200061601002001600002004800004003940039111602011009910010016000010000001011031633400361600001004004140050400404004940040
1602044004029900018502516010010016000110016000050023990551400204003940040199733200061601002001600002004800004004840039111602011009910010016000010000001011031633400361600001004004040049400404004040041
160204400393000000412516010110016001710016000050013199981400204003940040199733200411601002001600002004800004004840039111602011009910010016000010000001011041633400361600001004005040050400504004040049
160204400403000000422516011710016000010016000050013199981400204003940039199733200061601002001600002004800004003940039111602011009910010016000010000001011031633400451600001004004040050400494004040049
1602044004929900017162516010010016000010016000050012800001400204003940039199733199971601002001600002004800004003940048111602011009910010016000010000001011031633400371600001004004940041400404004040040
160204400393000000412516010010016000010016000050012800001400304003940039199733199981601002001600002004800004004940040111602011009910010016000010000001011031633400451600001004004140049400504004040041

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b18191e1f373f4e51inst 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)9fa1a6a8a9acc2cdcfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1600244004929900000184602516002810160018101600005023990270154002040049400491999632002916001020160000204800004004940049111600211091010160000100000000100228211716211147400460207160000104005240040400404005040040
1600244004930000000185602516002810160018101600005024388651154003040049400491999632001916001020160000204800004004940049111600211091010160000100000000100228411616211166400460207160000104004140041400494004940050
16002440049299000001856025160028101600001016000050243886511540030400494004919996320029160010201600002048070540092400391116002110910101600001000100001020684119112411722405861406160000104062940588405734053840622
16002440524303010107923521292059019716099311161497121616467124014901154051340676406642012449203801613992016119020484200406514067551160021109101016000010233454500010172113214141411175405864406160000104071840637406604066340714
16002440679305110513208801112105133210161008121609781316108565254470711540473408594078019996320029160010201600002048000040049400491116002110910101600001000003001002211411616211616400460206160000104004340040400404005040050
160024400493000000018560251600281016000010160000502438865115400204004940039199963200291600102016000020480000400394004911160021109101016000010000000010022841161621116144004602014160000104004140040400404005040050
1600244004929900000185602516002810160000101600005024388651154002040049400391999632002916001020160000204800004003940039111600211091010160000100000000100228411716211166400460407160000104004140040400494004940050
160024400483000000018560251600281016001810160000502438865115400204004940049199963200291600102016000020480000400494003911160021109101016000010000000010022851516211166400460407160000104004140050400504004140050
1600244004930000000185602516002810160018101600005024388651154002140049400491999632002916001020160000204800004004940049111600211091010160000100000000100228411616211616400460207160000104005340040400494004040040
16002440049300000120185602516002810160017101600005023990271154003040049400491999632001916001020160000204800004004940049111600211091010160000100000000100228411616221616400460207160000104004040040400504005040050