Apple M1 Microarchitecture Research by Dougall Johnson

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

SABA (vector, 4S)

Test 1: uops

Code:

  saba v0.4s, v1.4s, v2.4s
  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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372306125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100030003037303711100110001073116112630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100030003037303711100110001073116112630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100030003037303711100110001073116112630100030383038303830383038
100430372206125482510001000100039831313018303730372415328951000100030003037303711100110001073116112630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372206125482510001000100039831313018303730372415328951000100030003037303711100110000673116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  saba v0.4s, v1.4s, v2.4s
  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)0308091e3a3f4e51inst 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)9fa0a8accfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500006129548251010010010000100100005004277313030018030037300372826532874510100200100002003000030037300371110201100991001001000010000071003163329634100001003003830038300383003830038
102043003722510006129548251010010010000100100005004277313130018030037300372826532874510100200100002003000030037300371110201100991001001000010000071003163329634100001003003830038300383003830038
102043008422500016129548251010010010000100100005004277313030018030084300372826532874510100200100002003000030037300371110201100991001001000010000071013161329634100001003003830038300383003830038
102043003722500906129548251010010010000100100005004277313130018030037300372826532874510100200100002003000030037300371110201100991001001000010000071013163329634100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313030018030037300372826532874510100200100002003000030037300371110201100991001001000010000071013163329634100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313030018030037300372826532874510100200100002003000030037300371110201100991001001000010000071013163329634100001003003830038300383003830087
102043003722500006129548251010010010000100100005004277313130018030037300372826532874510100200100002003000030037300371110201100991001001000010000071013163329634100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313030018030037300372826532874510100200100002003000030037300371110201100991001001000010000071014163329634100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313130018030037300372826532874510100200100002003000030037300371110201100991001001000010000371013163329634100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313130018030037300372826532874510100200100002003000030037300371110201100991001001000010000071013163329634100001003003830038300383003830038

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)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)9fa0a6a7a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722400829295482510010101000010100005042773133001830037300372828762876710010201000020300003003730037111002110910101000010000000640216222963010000103003830038300383003830038
100243003722500692295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000000640216222963010000103003830038300383003830038
100243008422500925295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000000640216222963010000103003830038300383003830038
100243003722500690295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000000640216222963010000103003830038300383003830038
100243003722500661295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000000640765222963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000000640216222963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000000640216222963010000103008530038300383003830038
10024300372250061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000000640216222963010000103003830038300383003830038
100243003722500195295482510010101000810100005042773133001830037300372828732876710010201016220300003003730037111002110910101000010000103640216222966710000103008630038300383003830038
10024301322240082295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037211002110910101000010401000640216222963010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  saba v0.4s, v0.4s, v1.4s
  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)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)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722502332954825101001001000010010000500427731313001803003730037282653287451010020010000200300003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731313001803003730037282653287451010020010000200300003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
10204300372250822954825101001001000010010000500427731313001803003730037282653287451010020010000200300003003730037111020110099100100100001000071001611296340100001003003830038300383003830038
102043003722501262954844101001001000010010000500427731313001803003730037282653287451010020010000200300003003730037211020110099100100100001000071011611296340100001003003830038300383003830086
102043003722501472954825101001001000010010000500427731313001803003730037282653287451010020010000200300003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731313001803003730037282653287451010020010000200300003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731313001803003730037282653287451010020010000200300003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731313001803003730037282653287451010020010000200300003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
1020430037225122332954825101001001000010010000500427731313001803003730037282653287451010020010000200300003003730037111020110099100100100001000071011611296340100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731313001803003730037282653287451010020010000200300003003730037111020110099100100100001000071011611296340100001003003830038300383003830038

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)9fa8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225013929548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100640216222963010000103003830038300383007530038
100243003722506129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100640216222963010000103003830038300383003830038
100243007822406129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000554277313130018300373003728287328767100102010000203000030037300371110021109101010000100640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100640216222963010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  saba v0.4s, v1.4s, v0.4s
  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)03080b18191e3f4e51inst 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)9fa8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372240000018529548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250000014529548251010010010000100100005004277313300183013430037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383008530038
1020430037225000006129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037224000006129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000307101161129634100001003003830038300383003830038
1020430037225000008229548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300853008630038

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)9fa6a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372251986129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640316332963010000103003830038300383003830038
10024300372254836129548251001010100001010000504277313130018300373003728287328767106102010000203000030037300371110021109101010000100000640316332963010000103003830038300383003830038
100243003722536363129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640316332963010000103003830038300383003830038
100243003722435772629548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640316332963010000103003830038300383003830038
100243003722540553629548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640316332963010000103003830038300383003830038
1002430037225393346295482510010101000010100005042773130300183003730037282872528767100102010000203000030037300371110021109101010000100000640316332963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313130018300373003728287328767101602010000203000030037300371110021109101010000100000640316332963010000103003830038300383003830038
10024300372254146129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640316332963010000103003830038300383003830038
100243003722440544129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640316332963010000103003830038300383003830038
10024300372254596129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640316332963010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  saba v0.4s, v8.4s, v9.4s
  movi v1.16b, 0
  saba v1.4s, v8.4s, v9.4s
  movi v2.16b, 0
  saba v2.4s, v8.4s, v9.4s
  movi v3.16b, 0
  saba v3.4s, v8.4s, v9.4s
  movi v4.16b, 0
  saba v4.4s, v8.4s, v9.4s
  movi v5.16b, 0
  saba v5.4s, v8.4s, v9.4s
  movi v6.16b, 0
  saba v6.4s, v8.4s, v9.4s
  movi v7.16b, 0
  saba v7.4s, v8.4s, v9.4s
  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)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)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)9fcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160204200771500392580100100800001008000050064000002004520064200643228010020080000200240000200642006411160201100991001001600001001011111611200611600001002006520065200652006520065
160204200641500392580100100800001008000050064000002004520064200643228010020080000200240000200642006411160201100991001001600001001011111611200611600001002006520065200652006520065
1602042006415072392580100100800001008000050064000002004520064200643228010020080000200240630200642014411160201100991001001600001001011111611200611600001002006520065200652006520065
16020420064150234392580100100800001008000050064000002004520064200643228010020080000200240000200642006411160201100991001001600001001011111611200611600001002006520065200652006520065
160204200641500392580100100800001008000050064000002004520064200643228010020080000200240000200642006411160201100991001001600001001011111611200611600001002006520065200652006520065
160204200641500392580100100800001008000050064000002004520064200643228010020080000200240000200642006411160201100991001001600001001011111611200611600001002006520065200652006520065
160204200641510392580100100800001008000050064000002004520064200643228010020080000200240000200642006411160201100991001001600001001011111611200611600001002006520065200652006520065
160204200641500392580100100800001008000050064000002004520064200643228010020080000200240000203622006411160201100991001001600001001011111611200611600001002006520065200652006520065
160204200641510392580100100800001008000050064000002004520064200643228010020080000200240000200642006411160201100991001001600001001011111611200611600001002006520065200652006520065
160204200641506392580100100800001008000050064000002004520064200643228010020080000200240000200642006411160201100991001001600001001011111611200611600001002006520065200652006520065

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03081e1f3f51inst 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)9fa1a6a7a8accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1600242010915000087278001212800001280000626400001120032200512025432280012208000020240000200512005111160021109101016000010000001003131113252111510200482201160000102005220052200522005220052
16002420051150033045278001212800001280000626400001120032200512023332280012208000020240000200512005111160021109101016000010000001003731115252111510200482201160000102005220052200522005220052
16002420051150030452780012128000012800006264000011200322005120274322800122080000202400002005120051111600211091010160000100000010038311825211916200482201160000102012220052200522005220052
1600242005115000045278001212800001280000626400001120032200512027232280012208000020240000200512005111160021109101016000010000001003231110252111416200482201160000102005220052200522005220052
16002420051150100452780012128000012800006264000011200322005120248322800122080000202400002005120051111600211091010160000100000010037311925211816200482201160000102005220052200522005220052
160024200511500297045278001212800001280000626400001120032200512026732280012208000020240000200512005111160021109101016000010000001003831116252111511200482201160000102005220052200522005220052
1600242005115000045278001214800001280000626400001120032200512026432280012208000020240000200512005111160021109101016000010000101003831115252111517200482201160000102005220052200522005220052
160024200511500004527800121280000128000062640000112003220051202333228001220800002024000020051201751116002110910101600001000000100393119252111612200482201160000102005220052200522005220052
160024200511500004527800121280000128000062640000112003220051202763228001220800002024000020051200511116002110910101600001000000100333111025211917200482201160000102005220052200522005220052
160024200511500004527800121280000128000062640000112003220051202953228001220800002024000020051200511116002110910101600001040000100333111025211917200482201160000102005220052200522005220052

Test 6: throughput

Count: 16

Code:

  saba v0.4s, v16.4s, v17.4s
  saba v1.4s, v16.4s, v17.4s
  saba v2.4s, v16.4s, v17.4s
  saba v3.4s, v16.4s, v17.4s
  saba v4.4s, v16.4s, v17.4s
  saba v5.4s, v16.4s, v17.4s
  saba v6.4s, v16.4s, v17.4s
  saba v7.4s, v16.4s, v17.4s
  saba v8.4s, v16.4s, v17.4s
  saba v9.4s, v16.4s, v17.4s
  saba v10.4s, v16.4s, v17.4s
  saba v11.4s, v16.4s, v17.4s
  saba v12.4s, v16.4s, v17.4s
  saba v13.4s, v16.4s, v17.4s
  saba v14.4s, v16.4s, v17.4s
  saba v15.4s, v16.4s, v17.4s
  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)0304191e373f4e51inst 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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160204401233001013217503925160117100160000100160000500239899914002904008940052199733199981601002001600002004813354004840039111602011009910010016000010000210110116114004501600001004004040040400494004940049
16020440039300009003350251601171001600001001600005001280000140021040048400391997331999716010020016000020048000040039400391116020110099100100160000100000101101161140036241600001004004940049400494004040040
16020440051300004261741025160100100160000100160000500128000014002004003940040199733200061607552001600002004800004003940048111602011009910010016000010000010110116114004501600001004004940040400404004040040
1602044003930000300050025160100100160000100160000500239899914002004004840039199733199971601002001600002004800004003940039111602011009910010016000010000010110116114003601600001004004940040400404004940049
160204400393000010217410251601001001600001001600005002399082140020040048400391997317199971601002001600002004800004004840048111602011009910010016000010000010110142114004501600001004004940049400404004040049
160204400393000093041025160100100160000100160000500239902714002004003940049199733199971601002001600002004800004003940039111602011009910010016000010000010110116114004501600001004004040049400494004040040
160204400392990099041025160117100160000100160000500131999914003004003940039199733199971601002001600002004800004004840048111602011009910010016000010000010110116114003601600001004004040041400494004040040
160204400483000099041025160117100160000100160000500239899914002004003940039199733199971601002001600002004800004003940039111602011009910010016000010000010110116114003601600001004004040040400494004940040
1602044004930002153050025160100100160017100160000500128000014002004004840039199733199971601002001600002004800004004840039111602011009910010016000010003010110116114003601600001004004040040400494004040040
16020440048299001200410251601001001600171001600005002398999140020040039400491997316200061601002001600002004800004004840039111602011009910010016000010000010110116114003601600001004004040049400404004040049

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2502

retire (01)cycle (02)0307090a191e1f373f51inst 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)9fa1a6a7a8a9accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160024400493000000150174625160027101600171016000050128000001104002140039400401999632001916001020160000204800004004040039111600211091010160000100000001002213512616211242440036206160000104004940040400404004040040
16002440039299000000175525160010101600001016000050239899911104002040040400391999632001916001020160000204800004004840049111600211091010160000100000001002213512516211262540045209160000104005040040400404004140040
1600244003929900000004625160010101600171016000050128000011104002040040400391999632001916001020160000204800004003940039111600211091010160000100000001002213512616211252640037206160000104004040041400504004040040
1600244003930000000005625160027101600001016000050128000011104002040039400391999632002916001020160000204800004003940040111600211091010160000100000001002213512416211242440037209160000104004940040400494004040049
1600244003930000000015625160011101600001016000050131999811104002040039400391999632002816001020160000204800004004840040111600211091010160000100000001002213512616211202640036206160000104004940040400494004040040
1600244004830000000004625160011101600001016000050128000011104002040039402621999632002916001020160000204800004003940048111600211091010160000100000001002213512616211272540036209160000104004940040400404004040040
1600244004830000000015525160010101600001016000050128000011104002040039400391999632002016001020160000204800004003940048111600211091010160000100000001002213512316211272640036207160000104004940049400404004040040
1600244009830000000005525160010101600001016000050239899911104002040048400391999632001916001020160000204800004003940039111600211091010160000100000001002213512816211272440045209160000104004040040400404004040049
160024400393000000001752125160027101600171016000050128000011104002940039400391999632002816001020160000204800004004840039111600211091010160000100000001002213612516211242740036206160000104004040040400404004040040
16002440039300000000174625160010101600001016000050239899911104002040039400391999632001916001020160000204800004003940039111600211091010160000100000001002213512416211252640036209160000104004040049400404004040040