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, 2S)

Test 1: uops

Code:

  mls v0.2s, v1.2s, v2.2s
  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)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)a0a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037230612548251000100010003983131301830373037241532895100010003000303730371110011000000673116112630100030383038303830383038
100430372303302548251000100010003983131301830373037241532895100010003000303730371110011000000073116112630100030383038303830383038
10043037230612548251000100010003983131301830373037241532895100010003000303730371110011000000073116112630100030383038303830383038
10043037220612548251000100010003983131301830373037241532895100010003000303730371110011000000073116112630100030383038303830383038
10043037230612548251000100010003983131301830373037241532895100010003000303730371110011000001073116112630100030383038303830383038
10043037230612548251000100010003983131301830373037241532895100010003000303730371110011000001073116112630100030383038303830383038
10043037230612548251000100010003983131301830373037241532895100010003000303730371110011000000073116112630100030383038303830383038
10043037230612548251000100010003983131301830373037241532895100010003000303730371110011000000073116112630100030383038303830383038
10043037230612548251000100010003983131301830373037241532895100010003000303730371110011000000073116112630100030383038303830383038
10043037230612548251000100010003983131301830373037241532895100010003000303730371110011000000073116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  mls v0.2s, v1.2s, v2.2s
  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)030b181e1f3a3f4e51inst 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)9fa8acc2cfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000071012162229634100001003003830038300383003830038
10204300372240000061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000071012162229634100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000071012162229634100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000071012162229634100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000071013162229634100001003003830038300383003830038
10204300372250000082295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000071012162229634100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000071012162229634100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000071012162229634100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000071012162229634100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000071012162229634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b18191e3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500006129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000640216322963010000103003830038300383003830038
100243003722500066129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500006129548251001910100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313300653003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313300183003730037282873287671015820100002030000300373003711100211091010100001000640316232963010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000640216232963010000103007130038300383003830038
100243003722500006129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  mls v0.2s, v0.2s, v1.2s
  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)0318191f3f4e51inst 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)9fa8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
1020430037224000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
1020430037225130612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
1020430037225000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
1020430037225000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010007101161129634100001003003830134300863008630038
1020430037225100612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
1020430037225000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
1020430037225000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
1020430037225000612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
1020430037225000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03183f4e51inst 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)9faccfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225061295482510010101000010100005042773130300180300373003728287328767100102010000203000030037300371110021109101010000103640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001803003730037282873287671001020100002030000300373003711100211091010100001078640216222963010000103003830038300383003830038
100243003722501032954825100101010000101000050427731303001803003730037282873287671001020100002030000300373003711100211091010100001090640216222963010000103003830038300383003830038
10024300372251612954825100101010000101000050427731303001803003730037282873287671001020100002030000300373003711100211091010100001096640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001803003730037282873287671001020100002030000300373003711100211091010100001084640216222963010000103003830038300383003830038
10024300372240612954825100101010000101000050427731303001803003730037282873287671001020100002030000300373003711100211091010100001084640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001803003730037282873287671001020100002030000300373003711100211091010100001081640216222963010000103003830038300383003830038
10024300372240612954825100101010000101000050427731303001803003730037282873287671001020100002030000300373003711100211091010100001078640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001803003730037282873287671001020100002030000300373003711100211091010100001081640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001803003730037282873287671001020100002030000300373003711100211091010100001081640216222963010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  mls v0.2s, v1.2s, v0.2s
  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)03183f4e51inst 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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722502512954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010047007101161129634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000307101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100014407101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010064007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010005407101161129634100001003003830038300383003830038
10204300372251612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010006907101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010009307101161129634100001003003830038300383003830038
10204300372240612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010008407101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010008407101171129634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000607101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b181e1f3f4e51inst 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)9fa6a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100426640216222963010000103003830038300383003830038
100243003722500008429548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100100640216222963010000103003830038300383008130038
100243003722500006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100100640216222963010000103003830038300383003830038
100243003722400006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100100640216222963010000103003830038300383003830038
10024300372250000286629548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100100640216222963010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100103640216222963010000103003830038300383003830038
100243003722510006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100300640216222963010000103003830038300383003830038
100243003722400006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100200640216222963010000103003830038300383003830038
100243003722500008229548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100100640216222963010000103003830038300383003830038
10024300372250044708229548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100100640216222963010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  mls v0.2s, v8.2s, v9.2s
  movi v1.16b, 0
  mls v1.2s, v8.2s, v9.2s
  movi v2.16b, 0
  mls v2.2s, v8.2s, v9.2s
  movi v3.16b, 0
  mls v3.2s, v8.2s, v9.2s
  movi v4.16b, 0
  mls v4.2s, v8.2s, v9.2s
  movi v5.16b, 0
  mls v5.2s, v8.2s, v9.2s
  movi v6.16b, 0
  mls v6.2s, v8.2s, v9.2s
  movi v7.16b, 0
  mls v7.2s, v8.2s, v9.2s
  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)03081e3f51inst 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)9fa0a1a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16020420065150003925801001008000010080000500640000020045200642006432280100200800002002400002006420064111602011009910010016000010000006001011111611200611600001002006520065200652006520065
16020420064151003925801001008000010080000500640000120045200642006432280100200800002002400002006420064111602011009910010016000010000003001011111611200611600001002006520065200652006520065
1602042006415000229258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100003703001011111611200611600001002006520065200702006520065
160204200641500039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100004906001011111611200611600001002006520065200652006520065
16020420064150048339258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100003903001011111611200611600001002006520065200652006520065
16020420064150003925801001008000010080000500640000120045200642006432280100200800002002400002006420064111602011009910010016000010000003201011111611200611600001002006520065200652006520065
16020420064150003925801001008000010080000500640000120045200642006432280100200800002002400002006420064111602011009910010016000010000000001011111612200611600001002006520065200652006520065
16020420064150003925801001008000010080000500640000120045200642006432280100200800002002400002006420064111602011009910010016000010000000001011111611200611600001002006520065200712006520065
16020420064151003925801001008000010080000500640000120045200642006432280100200800002002400002006420064111602011009910010016000010000103001011111611200611600001002006520065200652006520065
16020420064150003925801001008000010080000500640000120045200642006432280100200800002002400002006420064111602011009910010016000010000480120001011111611200611600001002006520065200652006520065

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03091e3a3f51inst 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)9fa0a8a9acbranch mispredict (cb)cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160024200611510008727800121280000128000062640000115200322005120051322800122080000202400002005120051111600211091010160000100330001003013312625211117200482401160000102005220052202612005220052
160024200511510005027800121280000128000062640000111020032200512005132280012208000020240000200512005111160021109101016000010000301003013311525211119200482201160000102005220052202432006120052
160024200511510004527800121280000128000062640000111020032200512005132280012208000020240000200512005111160021109101016000010000301003416411525211117200572201160000102005220052202452006120052
160024200511500004527800121280000128000062640000111020032200512005132280012208000020240000200512005111160021109101016000010000001003413411525211117200482201160000102005220052202362006120052
160024200511500004566800121280000128000062640000111020032200512005132280012208000020240000200512005111160021109101016000010000001003413517252111511200482201160000102005220052202282006120061
16002420051150000452780012128000012800006264000011102003220051200513228001220800002024000020051200511116002110910101600001001030100341351725211711200482201160000102005220052204042051720052
160024200511500004527800121280000128000062640000111020032200512005132280012208000020240000200512005111160021109101016000010000001003013517252111513200482402160000102005220052202662005220061
160024200511500004527800121280000128000062640000111020032200512005132280012208000020240000200512005111160021109101016000010002001003013611534211815200482401160000102005220052202462005220052
16002420051150000452780012128000012800006264000011102003220051200513228001220800002024000020051200601116002110910101600001000000100301361825211138200482401160000102005220061202432006120052
160024200511500004527800121280000128000062640000111020032200512005132280012208000020240000200512005111160021109101016000010010301003616619344211515200482201160000102006120052202682005220052

Test 6: throughput

Count: 16

Code:

  mls v0.2s, v16.2s, v17.2s
  mls v1.2s, v16.2s, v17.2s
  mls v2.2s, v16.2s, v17.2s
  mls v3.2s, v16.2s, v17.2s
  mls v4.2s, v16.2s, v17.2s
  mls v5.2s, v16.2s, v17.2s
  mls v6.2s, v16.2s, v17.2s
  mls v7.2s, v16.2s, v17.2s
  mls v8.2s, v16.2s, v17.2s
  mls v9.2s, v16.2s, v17.2s
  mls v10.2s, v16.2s, v17.2s
  mls v11.2s, v16.2s, v17.2s
  mls v12.2s, v16.2s, v17.2s
  mls v13.2s, v16.2s, v17.2s
  mls v14.2s, v16.2s, v17.2s
  mls v15.2s, v16.2s, v17.2s
  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)030818191e1f373f4e51inst 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)9fa0a1a6a8a9acc2c5branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160204400913000000014102516010010016000010016000050012800001400304003940039199733199981601002001600002004800004003940039111602011009910010016000010000000000010110616114003601600001004005040050400504005040050
160204400493000000004102516010010016000010016000050012800001400204004040039199733199971601002001600002004800004004940039111602011009910010016000010000000000010110116114003601600001004004140040400404004040040
16020440039300000008470602516010010016000010016000050024388651400204004840039199733199981601002001600002004800004003940039111602011009910010016000010000000000010110116114004601600001004004140040400404004040050
160204400493000000004102516010010016000010016000050012800001400294003940039199733199971601002001600002004800004003940039111602011009910010016000010000000000010110116114003601600001004004040040400404004040040
160204400393000000004102516010010016000010016000050012800001400204003940048199733199971601002001600002004800004003940039111602011009910010016000010000000000010110116114003601600001004005040050400404004040040
1602044003930000000094602516010010016000010016000050012800001400204004940049199733200071601002001600002004800004004040039111602011009910010016000010000000000010110116114004601600001004005040040400404004040040
160204400393000000007902516010010016000010016000050012800001400204003940048199733199971601002001600002004800004004040039111602011009910010016000010000000000110110116114003601600001004005040050400504005040040
1602044004930000000070602516010010016000010016000050012800001400204003940039199733199971601002001600002004800004004940049111602011009910010016000010000000000010110116114003601600001004004040040400404004040040
160204400392990000004102516010010016000110016000050013200001400204003940039199733199971601002001600002004800004003940039111602011009910010016000010000000000010110116114003601600001004004040040400414004040050
160204400493000000004102516011810016000010016000050012800001400204003940039199733199971601002001600002004800004003940039111602011009910010016000010004000000010110116114004601600001004005040050400504005040040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0308191e373f51inst 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)9fa1a6a8a9accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160024400393000000672516002710160017101600005023989991110400294004940040199963200191600102016000020480000400394004811160021109101016000010000001002213316162111010400450155160000104004040049400404004940049
160024400393000001746251600101016000010160000501280000111040020400394004819996320019160010201600002048000040052400481116002110910101600001000000100221331101621196400360155160000104004140049400404004940049
160024400483000001755251600271016000010160000501280000111040020400394004819996320019160010201600002048000040049400481116002110910101600001000000100221331716211510400450155160000104004940040400494004040049
16002440048300000046251600101016000010160000502279215111040020400394004819996320028160010201600002048000040039400481116002110910101600001000020100221351101621186400450155160000104004040049400404004940040
1600244004830000005525160027121600001016000050239899911104002940048400481999632001916001020160000204800004004840048111600211091010160000100000010022135181621179400450155160000104004040049400404004940040
1600244004930000004625160027101600171016000050128000011104002040039400481999632002916001020160000204800004003940048111600211091010160000100000010022135171621179400360155160000104004940040400504004040049
16002440048300000175525160010101600001016000050239899911104002040048400481999632001916001020160000204800004003940048111600211091010160000100000010022135181621168400360155160000104004940049400404004940049
160024400393000001746251600101016001710160000501280000111040029400484004819996320028160010201600002048000040039400481116002110910101600001000000100221351101621169400360155160000104004940049400404005040040
16002440048300009174625160027101600171016000050239902711104002940039400481999632002816001020160000204800004004840039111600211091010160000100000010022135181621196400450155160000104004940049400494004940040
16002440039299100175525160027101600171016000050239899911104002940048400481999632002816001020160000204800004004840048111600211091010160000100000010022135181621168400360155160000104004040049400404004940049