Apple M1 Microarchitecture Research by Dougall Johnson

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

SQDMLAL (by element, 4S)

Test 1: uops

Code:

  sqdmlal v0.4s, v1.4h, v2.h[1]
  movi v0.16b, 1
  movi v1.16b, 2
  movi v2.16b, 3

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 1.000

Issues: 1.000

Integer unit issues: 0.000

Load/store unit issues: 0.000

SIMD/FP unit issues: 1.000

retire (01)cycle (02)03091e3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)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
100430372200612548251000100010003983133018303730372415328951000100030003037303711100110000073216112630100030383038303830383038
100430372300612548251000100010003983133018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372200612548251000100010003983133018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372200612548251000100010003983133018303730372415328951000100030003037303711100110000673116112630100030383038303830383038
100430372309612548251000100010003983133018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372200612548251000100010003983133018303730372415328951000100030003037303711100110002073116112630100030383038303830383038
1004303723018612548251000100010003983133018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372400612548251000100010003983133018303730372415328951000100030003037303711100110003073116112630100030383038303830383038
100430372300612548251000100010003983133018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
1004303723006125482510001000100039831330183037303724153289510001000300030373037111001100011073116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  sqdmlal v0.4s, v1.4h, v2.h[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)0308090b18191e1f3a3f4e51inst 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)9fa0a6a8acc2cfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000000061295482510100100100001001000050042773130300183003730037282650328745101002001000020030000300373003721102011009910010010000100003212844135724297769100001003032630182303623037330321
102043032122711046924264025129548251010010010000100100005004277313030018300373003728265032874510100200100002003000030037300371110201100991001001000010000000710121622296340100001003003830038300383003830038
10204300372250000000035029548251010010010000100100005004277313030018300373003728265032874510100200100002003000030037300371110201100991001001000010000100710121622296340100001003003830038300383003830038
1020430037225000000006129548251010010010000100100005004277313030018300373003728265032874510100200100002003000030037300371110201100991001001000010000000710121622296340100001003003830038300383003830038
1020430037225000000006129548251010010010000100100005004277313030018300373003728265032874510100200100002003000030037300371110201100991001001000010000000710121622296340100001003003830038300383003830038
1020430037225000000006129548251010010010000100100005004277313030018300373003728265032874510100200100002003000030037300371110201100991001001000010000000710121622296340100001003003830038300383003830038
10204300372250000018006129548251010010010000100100005004277313030018300373003728265032874510100200100002003000030037300371110201100991001001000010000200710121622296340100001003003830038300383003830038
1020430037225000000006129548251010010010008100100005004277313030018300373003728265032874510100200100002003000030037300371110201100991001001000010000000710121622296340100001003003830038300383003830038
1020430037225000000006129548251010010010000100100005004277313030018300373003728265032874510100200100002003000030037300371110201100991001001000010000000712121623296340100001003003830038300383003830038
1020430037225000000006129548251010010010000100100005004277313030018300373003728265032874510100200100002003000030037300371110201100991001001000010000000710121622296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030818191e3f4e51inst 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000036403163329630010000103003830038300383003830038
1002430037224000061295482510010101002410100005042842851300183003730037282873287671001020100002030483300853022751100211091010100001000106403163329630010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000006403163329630010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000006403164329630010000103003830038300383003830038
1002430037224000061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003721100211091010100001000537043243329630110000103003830132300863018030038
1002430037225000061295482510010101000010100006142773131300183003730037282873287671001020101622230000300373003711100211091010100001000183956403163429630110000103003830038301813003830133
1002430037225201132742295484510066121000010101495042813841300183003730037282873287671001022100002030000300373003711100211091010100001022406403163329630010000103003830038300383003830038
100243003722501121732295482510010101000010104475042786701300183003730084282873288401001020100002030000300373003711100211091010100001000006403163329630010000103003830038300383003830038
1002430037225100061295482510018101000010100005042773131300183003730037282873287671001020100002030000300373003721100211091010100001000306403163329630010000103003830038300383003830038
1002430037224000061295482510018101000010104475042773131300183003730037282873287671001020100002030000300373003711100211091010100001000683746405164429630010000103003830038301813008630038

Test 3: Latency 1->2

Code:

  sqdmlal v0.4s, v0.4h, v1.h[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)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)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)9fa6a8a9acc2cdcfd0d5d6dbddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000082295482510100100100001001000050042773133001830037300372826503287451010020010332204300003003730037111020110099100100100001000000007100216022296340100001003003830071300383003830038
1020430037225000061295482510100100100001001000050042773133001830037300372826503287451010020010000200300003003730037111020110099100100100001000000007100216022296340100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773133001830037300372826503287451010020010000200300003003730037111020110099100100100001000000007100216022296340100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773133001830037300372826503287451010020010000200300003003730037111020110099100100100001000000007100216022296340100001003003830038300383003830038
1020430037225000061295302510100122100001001000050042773133001830037300372826503287451010020010000200300003003730037111020110099100100100001000000007100216022296340100001003003830038300383003830038
1020430037224000061295482510100100100001001000050042773133001830037300372826503287451010020010000200300003003730037111020110099100100100001000000007100216022296340100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731330018300373003728265032874510100200100002003000030037300371110201100991001001000010000015007100216022296340100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773133001830037300372826503287451010020010000200300003003730037111020110099100100100001000000007100216022296340100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773133001830037300372826503287451010020010000200300003003730084111020110099100100100001000000007100216022296340100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773133001830037300372826503287451010020010000200300003003730037111020110099100100100001000000007411216022296340100001003003830038300383003830038

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)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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372240612954825100101010000101000050427731303001830037300372828703287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372250612954825100101010008101000050427731303001830037300372828703287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001830037300372828703287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722501902954825100101010000101000050427731303001830037300372828703287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001830037300372828703287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372250822954825100101010000101000050427731303001830037300372828703287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001830037300372828703287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372256612954825100101010000101000050427731303001830037300372828703287671001020100002030000300373003711100211091010100001000640216222963010000103008630038300383003830038
10024300372250612954825100101010000101000050427731303001830037300372828703287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731313001830037300372828703287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  sqdmlal v0.4s, v1.4h, v0.h[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)03181e1f3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa6a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030084300372110201100991001001000010000007101161129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
1020430037225000943295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129683100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
1020430037225000536295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
1020430037225000150295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
1020430037225000726295482510100100100001001000050042773133001830037300372826532874510100200100002003000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038

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)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)9fa8a9accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225036329548251001010100241010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640316222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
1002430037225636129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722506129548251001012100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
1002430037225025129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
10024300372254359429548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100001640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  sqdmlal v0.4s, v8.4h, v9.h[1]
  movi v1.16b, 0
  sqdmlal v1.4s, v8.4h, v9.h[1]
  movi v2.16b, 0
  sqdmlal v2.4s, v8.4h, v9.h[1]
  movi v3.16b, 0
  sqdmlal v3.4s, v8.4h, v9.h[1]
  movi v4.16b, 0
  sqdmlal v4.4s, v8.4h, v9.h[1]
  movi v5.16b, 0
  sqdmlal v5.4s, v8.4h, v9.h[1]
  movi v6.16b, 0
  sqdmlal v6.4s, v8.4h, v9.h[1]
  movi v7.16b, 0
  sqdmlal v7.4s, v8.4h, v9.h[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)031e3a3f51inst 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)6061696d6e74scheduler 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)9fa1a8a9acc5cfd0d2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160204200891500011992580100100800001008000050064000000200452006420064032280100200800002002400002006420064111602011009910010016000010000000101120061622200611600001002006520065200652006520065
16020420064150009962580100100800001008000050064000000200452006420064032280100200800002002400002006420064111602011009910010016000010000000101120021622200611600001002006520065200652006520065
1602042006415001812580100100800001008000050064000000200452006420064032280100200800002002400002006420064111602011009910010016000010000000101120021622200611600001002006520065200652006520065
16020420064150007642580100100800001008000050064000000200452006420064032280100200800002002400002006420064111602011009910010016000010000000101120025822200611600001002006520065200652006520065
160204200641500094465801001008000010080000500640000102004520064200640322801002008000020024000020064200641116020110099100100160000100017000101125021622200611600001002006520065200652006520065
1602042006415000392580100100800001008000050064000015200452006420064032280100200800002002400002006420064111602011009910010016000010000000101120021622200611600001002006520065200652006520065
1602042006415100392580100100800001008000050064000005200452006420064032280100200800002002400002006420064111602011009910010016000010000000101120021622200611600001002006520065200652006520065
1602042006415000392580100100800001008000050064000000200452006420064032280100200800002002400002006420064111602011009910010016000010000000101125021622200611600001002006520065200652006520065
16020420064150007112580100100800001008000050064000005200452006420064032280100200800002002400002006420064111602011009910010016000010000100101125021622200611600001002006520065200652006520065
1602042006415100392580100100800001008000050064000000200452006420064032280100200800002002400002006420064111602011009910010016000010000000101120021622200611600001002006520065200652006520065

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b18191e3f51inst 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)9fa0a6a7a8acc2cdcfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaebec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1600242008415000004529800121380000128000062640000112003202005120051322800122080000202400002005120051111600211091010160000100000000100396222025211191420048220765160000102005220052200522006120052
1600242005115000004529800121280000128000062640000012003202006020051322800122080000202400002005120051111600211091010160000100000000100396221334422131320057240685160000102006120061200612006120061
1600242006015100005129800121280000128000062640000012004102006020060322800122080000202400002006020060111600211091010160000100000000100446221934422121320057240794160000102006120061200612006120061
1600242006015000004529800121280000128000062640000012004102006020060322800122080000202400002006020060111600211091010160000100000000100376221134421111320057240755160000102006120061200612006120061
1600242006015000005129800121280000128000062640000012004102006020060322800122080000202400002006020060111600211091010160000100000000100396221334422111320057240814160000102006120061200612006120061
1600242006015000005129800121280000128000062640000002003202006020060322800122080000202400002006020060111600211091010160000100000000100406221334421191420057240744160000102006120061200612006120061
1600242006015000005129800121280000128000062640000002004102006020060322800122080000202400002006020051111600211091010160000100000000100376211134422121920057240724160000102005220052200522005220052
1600242005115000004529800121280000128000062640000012004102006020060322800122080000202400002006020060111600211091010160000100001000100376111425211141320048220795160000102005220052200522005220052
1600242005115100004529800121280000128000062640000012004102006020060322800122080000202400002006020060111600211091010160000100000000100363111325221121820057220655160000102005220052200522005220052
1600242005115000004529800121280000128000062640000012004102006020060322800122080000202400002006020060111600211091010160000100000000100376211134422141220057240635160000102006120061200612006120061

Test 6: throughput

Count: 12

Code:

  sqdmlal v0.4s, v12.4h, v13.h[1]
  sqdmlal v1.4s, v12.4h, v13.h[1]
  sqdmlal v2.4s, v12.4h, v13.h[1]
  sqdmlal v3.4s, v12.4h, v13.h[1]
  sqdmlal v4.4s, v12.4h, v13.h[1]
  sqdmlal v5.4s, v12.4h, v13.h[1]
  sqdmlal v6.4s, v12.4h, v13.h[1]
  sqdmlal v7.4s, v12.4h, v13.h[1]
  sqdmlal v8.4s, v12.4h, v13.h[1]
  sqdmlal v9.4s, v12.4h, v13.h[1]
  sqdmlal v10.4s, v12.4h, v13.h[1]
  sqdmlal v11.4s, v12.4h, v13.h[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)0308090b18191e1f373f4e51inst 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)9fa0a1a6a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
12020430060225000000035767025120204100120036100120000500960000030020300393174816653314997120100200120000200360000317483003911120201100991001001200001000000007610216223003601200001003004031749300403174930040
12020530039225000000018444025120101100120018100120000500960000130020300393174816653316706120100200120000200360000317483003911120201100991001001200001000000007610216223174501200001003174930040300413004030040
1202043003923800000001167671325120118100120018100120000500960000130020317483003914973314997120100200120000200360630300393003911120201100991001001200001000000007610216223174501200001003004031749300403174931749
1202043174822400000000941671325120100100120000100120000500990000131729317483003914973314997120100200120000200360000300393004011120201100991001001200001000000007610216223174501200001003004031749300403174930041
12020430040225000000001573671325120118100120001100120000500960000130020300393003914973314997120100200120000200360000317483003911120201100991001001200001000000007610216223003601200001003004031749300403004130040
1202043003923700000000876671325120118100120018100120000500960000130020300393004014973316706120100200120000200360000300403003911120201100991001001200001000000007610216223003601200001003174930040300413004030041
120204317482250000000183658671325120118100120018100120000500960000131729317483003914973314997120100200120000200360000300393174811120201100991001001200001000000007610216223003701200001003004030041300403174931749
1202043174822500000001932025120100100120000100120000500990000031729300393174816653316706120100200120000200360000300393174811120201100991001001200001000000007610216223003601200001003174930040317493004031749
12020430040225000000018835671325120118100120018100120000500960000030020300393174814973316706120100200120000200360000300393174811120201100991001001200001000000007610216223003601200001003004030040300403004030040
1202043003922500000000180025120118100120018100120000500960000031729300403003914973314997120100200120000200360000300393101011120201100991001001200001000000007610216223003601200001003004330041300403174930040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030407090a0b181e3a3f51inst 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)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)9faccfd0d2icache miss (d3)itlb miss (d4)d5d6d9dadbddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
120024309222250101000022625120010101200001012000050960000113002030039300391499631501912012720120000203600003003930039111200211091010120000100752331113016111142730036165120000103004030040300403004030040
120024300392241110000095251200101012000010120000509600001130020300393003914996291501712001020120000203600003003930039111200211091010120000100752331112616111262630036165120000103004030040300403004030040
1200243003922511110001126825120010101200001012000050960000113002030039300391499631501912001020120000203600003003930039111200211091010120000100752331111816111261930036165120000103004030040300403004030040
120024300392251011000093825120010101200001012000050960000113002030039300391499631501912001020120000203600003003930039111200211091010120000100752431111816111271630036165120000103004030040300403004030040
120024300392251010000192325120010101200001012000050960000113002030039300391499631501912001020120000203600003003930039111200211091010120000100752431111716111261930036165120000103004030040300403004030040
120024300392241010000195325120010101200001012000050960000113002030039300391499631501912001020120000203600003003930039111200211091010120000100752331112616111172630036165120000103004030040300403004030040
120024300392241010000181825120010101200001012000050960000113002030039300391499631501912001020120000203600003003930039111200211091010120000100752331111916111271630036165120000103004030040300403004030040
120024300392251111000017025120010101200001012000050960000113002030039300391499631501912001020120000203600003003930039111200211091010120000100752331112716111292730036165120000103004030040300403004030040
120024300392251111000094525120010101200001012000050960000113002030039300391499631501912001020120000203600003003930039111200211091010120000100752431112716111281630036165120000103004030040300403004030040
120024300392251011000198725120010101200001012000050960000113002030039300391499631501912001020120000203600003003930039111200211091010120000100752431112616111172530036165120000103004030040300403004030040