Apple M1 Microarchitecture Research by Dougall Johnson

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

SQDMLSL2 (by element, 2D)

Test 1: uops

Code:

  sqdmlsl2 v0.2d, 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)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)a8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037220612548251000100010003983131301830373037241532895100010003000303730371110011000073216112630100030383038303830383038
10043037230612548251000100010003983131301830373037241532895100010003000303730371110011000073216222630100030383038303830383038
10043037230612548251000100010003983131301830373037241532895100010003000303730371110011000073216222630100030383038303830383038
10043037220612548251000100010003983131301830373037241532895100010003000303730371110011000073216222630100030383038303830383038
100430372301662548251000100010003983131302230373037241532895100010003000303730371110011000073216112630100030383038303830383038
10043037230612548251000100010003983130301830373037241532895100010003000303730371110011000173216212630100030383038303830383038
10043037220612548251000100010003983130301830373037241532895100010003000303730371110011000073116112630100030383038303830383038
100430372201032548251000100010003983131301830373037241532895100010003000303730371110011000073116222630100030383038303830383038
10043037220612548251000100010003983131301830373037241532895100010003000303730371110011000073216222630100030383038303830383038
10043037230842548251000100010003983130301830373037241532895100010003000303730371110011000073216212630100030383038303830383038

Test 2: Latency 1->1

Code:

  sqdmlsl2 v0.2d, 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)030718191e3a3f4e51inst 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)9facc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000006129548251010010010000100100005004277313130018300373003728272728740101002001000820030024300373003711102011009910010010000100011171801600296460100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313130018300373003728272728740101002001000820030024300373003711102011009910010010000100011171701600296470100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313030018300373003728272628741101002001000820030024300373003711102011009910010010000100011171701600296460100001003003830038300383003830038
10204300372250003006129548251010010010000100100005004277313130018300373003728272728740101002001000820030024300373003711102011009910010010000100011171801600296460100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313130018300373003728272728740101002001000820030024300373003711102011009910010010000100011171701600296460100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313130018300373003728272628741101002001000820030024300373003711102011009910010010000100011171701600296460100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313130018300373003728272728740101002001000820030024300373003711102011009910010010000100011171701600296460100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313130018300373003728272728741101002001000820030024300373003711102011009910010010000100011171801600296460100001003003830038300383003830038
1020430037226000006129548251010010010000100100005004277313130018300373003728272728740101002001000820030024300373003711102011009910010010000100011171701600296470100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313130018300373003728272728740101002001000820030024300373003711102011009910010010000100011171801600296460100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0308090b18191e1f3f4e51inst 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)9fa0a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000001206129548251001010100001010000504277313030018300373003728287032876710010201000020300003003730037111002110910101000010000000640216222963010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313030018300373003728287032876710010201000020300003003730037111002110910101000010000000640216222963010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313030018300373003728287032876710010201000020300003003730037111002110910101000010000000640216222963010000103003830038300383003830038
100243003722400000006129548251001010100001010000504277313030018300373003728287032876710010201000020300003003730037111002110910101000010000000640216222963010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313030018300373003728287032876710010201000020300003003730037111002110910101000010000000640216222963010000103003830038300383003830038
100243003722500000006129548251001010100001010148504277313030018300373003728287732876710010201000020300003003730037111002110910101000010000000640216222963010000103003830038300383003830038
1002430037225000000015629548251001010100001010000504277313030018300373003728287032876710010201000020300003003730037111002110910101000010000000640216222963010000103003830038300383003830038
1002430037225000000025129548251001010100001010000504277313030018300373003728287032876710010201000020300003003730037111002110910101000010000000640216222963010000103003830038300383003830038
1002430037225010000072629548251001010100001010000504277313030018300373003728287032876710010201000020300003003730037111002110910101000010000000640216222963010000103003830038300383003830038
1002430037225000000053629548251001010100001010000504277313030018300373003728287032876710010201000020300003003730037111002110910101000010000000640216222963010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  sqdmlsl2 v0.2d, 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)030b1e1f3f4e51inst 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)9fa0a1a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000040007101161129634100001003003830038300383003830038
102043003722409061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000307101161129634100001003003830038300383003830038
1020430037225000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000009607101161129634100001003003830038300383003830038
1020430037225000189295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000020607101161129634100001003003830038300383003830038
1020430037225000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000008707161161129634100001003003830038300383003830038
1020430037225000612954844101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000680307101161129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001002050007101161129634100001003003830038300383003830038
102043003722503061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000040607101161129634100001003003830038300383003830038
1020430037225000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000025707101161129634100001003003830038300383003830038
1020430037226000612954825101161001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000420007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b1e3f4e51inst 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
100243003722500612954825100101010000101000050427731313001830037300372828702628767100102010000203000030037300371110021109101010000102100640216222963010000103003830038300383003830038
1002430037225008929548251001010100001010000504277313130018300373003728287032876710010201000020300003003730037111002110910101000010800640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731303001830037300372828703287671001020100002030000300373003711100211091010100001026112330640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287032876710010201000020300003003730037111002110910101000010900640216222963010000103003830038300383003830038
10024300372240071295482510010101000010100005042773131300183003730037282870328767100102010000203000030037300371110021109101010000101000640216222963010000103003830038300383003830038
1002430037224006129548251001010100001010000504277313030018300373003728287032876710010201000020300003003730037111002110910101000010600640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313130018300373003728287032877110010201000020300003003730037111002110910101000010990640216222963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773131300183003730037282870328767100102010000203000030037300371110021109101010000102730640216222963010000103003830038300383003830038
100243003722400612954825100101010000101000050427731303001830037300372828702928767100102010000203000030037300371110021109101010000100960640216222963010000103003830038300383008530038
10024300372250061295482510010101000010100005042773130300183003730037282870328767100102010000203000030037300371110021109101010000101001640216222963010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  sqdmlsl2 v0.2d, 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)030b0e1e3f4e51inst 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)9fa1a7a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100001071021611296340100001003003830038300383003830038
10204300372251006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100001071011611296340100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100001071011611296340100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100001071011611296340100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100001071011611296340100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100010371011611296340100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100001071011611296340100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100002071011611296340100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03081e3f4e51inst 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)e0ec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000102466403163329630010000103003830038300383003830038
10024300372250061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001026126403163329630010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000102236403163329630010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313130018300373003728287328767100102010172203000030037300371110021109101010000102736403163329630010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100846403163329630010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000102796403163329630010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000101396403163329630010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000102766403163329630010000103003830038300383003830038
1002430037225096129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000102866403163329630010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100816403163329630010000103003830038300383008630038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  sqdmlsl2 v0.2d, v8.4s, v9.s[1]
  movi v1.16b, 0
  sqdmlsl2 v1.2d, v8.4s, v9.s[1]
  movi v2.16b, 0
  sqdmlsl2 v2.2d, v8.4s, v9.s[1]
  movi v3.16b, 0
  sqdmlsl2 v3.2d, v8.4s, v9.s[1]
  movi v4.16b, 0
  sqdmlsl2 v4.2d, v8.4s, v9.s[1]
  movi v5.16b, 0
  sqdmlsl2 v5.2d, v8.4s, v9.s[1]
  movi v6.16b, 0
  sqdmlsl2 v6.2d, v8.4s, v9.s[1]
  movi v7.16b, 0
  sqdmlsl2 v7.2d, 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)03080b18191e1f3f51inst 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)9fa0a1a6a7a8a9accfd5d6ddinst fetch restart (de)dfe0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160204200881510000003925801001008000010080000500640000020045200642006432280100200800002002400002006420064111602011009910010016000010000000015101165161122006101600001002006520065200652006520065
16020420064150000000392580100100800001008000050064000002004520064200643228010020080000200240000200642006411160201100991001001600001000000000101161161122006101600001002006520065200652006520065
16020420064150000000392580100100800001008000050064000002004520064200643228010020080000200240000200642006411160201100991001001600001000000220101161161122006101600001002006520065200652006520065
16020420064151000000392580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000000000101161161122006101600001002006520065200652006520065
16020420064150000000392580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000000300101161161122006101600001002006520065200652006520065
160204200641500000002312580100100800001008000050064000002004520064200643228010020080000200240000200642006411160201100991001001600001000000103101161161122006101600001002006520065200652006520065
16020420064150000000392580100100800001008000050064000002004520064200643228010020080000200240000200642006411160201100991001001600001000000003101161161122006101600001002006520065200652006520065
16020420064150000000392580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000000003101161161122006101600001002006520065200652006520065
16020420064150000000392580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000000100101161161122006101600001002006520065200652006520065
16020420064150000000392580100100800001008000050064000002004520064200643228010020080000200240000200642006411160201100991001001600001000000100101161161122006101600001002006520065200652006520065

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03070a3a3f51inst 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)6061696d6escheduler 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)9fa8a9accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160024200521500007525800121280000128000062640000102003320052200523228001220800002024000020052200521116002110910101600001000010056113237263221831200492310160000102005320053203212007120053
16002420052150001512580012128000012800006264000015200332005220052322800122080000202400002005220052111600211091010160000104431005865234263223334200492310160000102005320053202962007020053
1600242005215022063258001212800001280000626400001520033200522005232280012208000020240000200522005211160021109101016000010300310058115236263223221200492310160000102005320053202882007020053
160024200521502306925800121280000128000062640000102003320052200523228001220800002024000020052200521116002110910101600001050910060115235263223434200492310160000102005320053203022007020053
160024200521502209025800121280000128000062640000152003320052200523228001220800002024000020052200521116002110910101600001010310059115217263223334200492310160000102005320053203062007020053
160024200521503306325800121280000128000062640000152003320052200523228001220800002024000020052200521116002110910101600001000121006165234263223435200492310160000102005320053203292007020053
160024200521502216925800121280000128000062640000152003320052200523228001220800002024000020052200521116002110910101600001000310042115219263223133200492310160000102005320053203022007020053
16002420052150331632580012128000012800006264000005200332005220052322800122080000202400002005220052111600211091010160000103509100441152182632233352004923125160000102005320053203082007020053
16002420052151230752580012128000012800006264000005200332005220052322800122080000202400002005220052111600211091010160000101091005684132202111834200432150160000102004720047202962006920053
16002420053150221632580012128000012800006264000015200332005220052322800122080000202400002005220052111600211091010160000101091005865233263223231200492310160000102005320053203002006920053

Test 6: throughput

Count: 12

Code:

  sqdmlsl2 v0.2d, v12.4s, v13.s[1]
  sqdmlsl2 v1.2d, v12.4s, v13.s[1]
  sqdmlsl2 v2.2d, v12.4s, v13.s[1]
  sqdmlsl2 v3.2d, v12.4s, v13.s[1]
  sqdmlsl2 v4.2d, v12.4s, v13.s[1]
  sqdmlsl2 v5.2d, v12.4s, v13.s[1]
  sqdmlsl2 v6.2d, v12.4s, v13.s[1]
  sqdmlsl2 v7.2d, v12.4s, v13.s[1]
  sqdmlsl2 v8.2d, v12.4s, v13.s[1]
  sqdmlsl2 v9.2d, v12.4s, v13.s[1]
  sqdmlsl2 v10.2d, v12.4s, v13.s[1]
  sqdmlsl2 v11.2d, 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)031e373f4e51inst 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)9fa0a8c5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
12020430133225017104025120100100120000100120000500960000030020030039300391497331499712010020012000020036000030039300391112020110099100100120000100010761011611300361200001003004030043300403004030040
120204300392250041667125120101100120000100120000500960000030020030039300421497331499712010020012000020036000030039300391112020110099100100120000100001761011611300361200001003004030923300403004030040
120204300392310044025120100100120017100120000500960000030020030040300391497331499712010020012000020036000030042300391112020110099100100120000100000761011611300391200001003004030944300403004030040
12020430039225035410251201001001200001001200005004283400030020030039300391497331499712010020012000020036000030039300391112020110099100100120000100000761011611300361200001003004030040309443004030043
120204300392250044340525120100100120017100120000500960000030924030039300391497331499712010020012000020036000030039300391112020110099100100120000100000761011611300361200001003004030040300403004030534
1202043003922505361340525120100100120001100120000500960000030023030039300391497331499712010020012000020036000030039300391112020110099100100120000100000761011611300361200001003004030040300403004030040
12020430039225001240251201001001200011001200005004283622130903030039300391497331499712010020012000020036000030039300391112020110099100100120000100000761011611300361200001003004030944300403004030040
120204300392310141025120100100120000100120000500960000130020030039300421497331499712010020012000020036000030039300421112020110099100100120000100000761011611300361200001003004030043300403004030040
1202043003922501744025120100100120001100120000500960000130924030039300891497331499712010020012000020036000030039300391112020110099100100120000100000761011611300361200001003004030043300403004030040
120204300392250041025120101100120000100120000500960000030020030042300391497331499712010020012000020036000030039309221112020110099100100120000100000761011611300361200001003004030923300403004030040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0308090b18191e1f373a3f4e51inst 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)5f60696b6d6edispatch 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)9fa0a1a6a7a8a9acc2cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1200243005022900000000014102512001010120000101200005096000000300200300393004214996315019120010201200002036000030039300391112002110910101200001000000000752261271642264300360305120000103004030040300403004030040
1200243003922500000000052025120010101200001012000050960000013002003003930039149963150201200102012000020360000300393175011120021109101012000010000020007524621416422643003603010120000103004030041300413175130041
1200243003923800000000052025120010101200001012000050960000103002003003930039149963150191200102012000020360000300393003911120021109101012000010000000007524622616422463003603010120000103004130040300403004030040
12002430040225000000000460251200101012003510120000509600000130020030951300391499631501912001020120000203600003004030039111200211091010120000100000300007524622616222463003601510120000103004030040300403175130040
12002430039224000000000460251200101012000010120000509600000030020031750300391499625150191200102012000020360000300393003911120021109101012000010000000007524311516412643003603010120000103004030040300403004030040
1200243003922500000000052025120010101200001012000050960000003090303003931750149963150191200102012000020360000300393003911120021109101012000010000000007524652616422643003603010120000103004030040300403004030040
12002430039225000000000520251200101012000010120000504402296013002003003930951149963150191200102012000020360000300393003911120021109101012000010000000007524622616422643003609910120000103004030040300403004030040
12002430040225000001200052025120010101200001012000050960000003002003003930039149963150191200102012000020360000317503003911120021109101012000010000000007524622616422463003603020120000103004030040309433004030040
120024300392250000021000523489251200621012005210120000504394061003173103003930040149963150191200102012000020360000300393003911120021109101012000010000010007524622616422643003603010120000103004030040317513004131751
1200243175022500000000052025120010101200001012000050960000013093203003930039149963150191200102012000020360000309513003911120021109101012000010000000007524622616422463003603010120000103004030040300433004130041