Apple M1 Microarchitecture Research by Dougall Johnson

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

MLA (by element, 4S)

Test 1: uops

Code:

  mla v0.4s, 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)033f4e51inst 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)a0a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372361254825100010001000398313030183037303724153289510001000300030373037111001100001073216112630100030383038303830383038
100430372261254825100010001000398313030183037303724153289510001000300030373037111001100000673116112630100030383038303830383038
100430372361254825100010001000398313030183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
100430372361254825100010001000398313030183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
100430372382254825100010001000398313030183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
100430372361254825100010001000398313030183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
100430372361254825100010001000398313030183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
100430372261254825100010001000398313030183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
100430372361254825100010001000398313030183037303724153289510001000300030373037111001100000073116112630100030383038303830383038
100430372361254825100010001000398313030183037303724153289510001000300030373037111001100000073116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  mla v0.4s, 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)03093a3f4e51inst 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)9fa8cdcfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500612954825101001001000010010000500427731303001803003730037282653287451010020010000200300003003730037111020110099100100100001000071003162229634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731303001803003730037282653287451010020010000200300003003730037111020110099100100100001000071012162329634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731313001803003730037282653287451010020010000200300003003730037111020110099100100100001000071012162229634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731303001803003730037282653287641010020010000200300003003730037111020110099100100100001000071012162229634100001003003830038300383003830038
102043003722400822954825101001001000010010000500427731303001803003730037282653287451010020010000200300003003730037111020110099100100100001000071012162229634100001003003830038300383003830038
102043003722410612954825101001001000010010000500427731303001803003730037282653287451010020010000200300003003730037111020110099100100100001000071012162229634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731303001803003730037282653287451010020010000200300003003730037111020110099100100100001000071012162229634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731303001803003730037282653287451010020010000200300003003730037111020110099100100100001000071012162329634100001003003830038300383003830038
102043003722500822954825101001001000010010000500427731303001803003730037282653287451010020010000200300003003730037111020110099100100100001000071012162229634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731303001803003730037282653287451010020010000200300003003730037111020110099100100100001000071012162229634100001003003830038300383003830038

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)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)9fa8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000021229548251001010100001010000504277313130018030037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225000080629548251001010100001010000504277313130018030037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225000093429548251001010100001010000504277313130018030037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500096129548251001010100001010000504277313030018030037300372828732876710010201000020300003003730037111002110910101000010001640216222963010000103003830038300383003830038
10024300372250000116229548251001010100001010000504277313030018030037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372240000101229548251001010100001010000504277313030018030037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225000085029548251001010100001010000504277313030018030037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250000100729548251001010100001010000504277313130018030037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225000022929548251001010100001010000504277313030018330037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250000116729548251001010100001010000504277313030018030037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  mla v0.4s, 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)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)9facbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100007102161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020030000301793003711102011009910010010000100007341161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100017101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722508229548251010010010000100100005004277313030018300373003728265328745101002001000020031974300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722506129529251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038

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)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)9faccfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100640316332963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100640316332963010000103003830038300383003830038
10024300372240612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100640316332963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731330018300373003728287328767100102010000223000030037300371110021109101010000100640316332963010000103003830038300383003830038
10024300842250612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100642316332963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100640316332963010000103003830038300383003830038
1002430037225151742954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100640316332963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100640316332963010000103003830038300383003830038
10024300372250822954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100640316332963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100640316332963010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  mla v0.4s, 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)03080a181e1f3f4e51inst 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)9fa0a6a8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000061295482510100100100071001000050042773133001830037300372826503287451010020010000200300003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773133001830037300372826503287451010020010000200300003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
10204300372250100061295482510100100100001001000050042773133001830037300372826503287451010020010000200300003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773133001830037300372826503287451010020010000200300003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773133001830037300372826503287451010020010000210300003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773133001830037300372826503287451010020010000200300003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
10204300372240000061295482510100100100001001000050042773133001830037300372826503287451010020010000200300003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773133001830037300372826503287451010020010000200300003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773133001830037300372826503287451010020010000200300003003730037111020110099100100100001000000071011611296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773133001830037300372826503287451010020010000200300003003730037211020110099100100100001000000071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)031e3a3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8c2c5cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225006129548251001010100001010000504277313130018300373003728287328767100102410000203000030037300371110021109101010000100000640216222968510000103003830038300383003830038
1002430037225006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000102000640216222963010000103003830038300383003830038
1002430037224006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728290828786101622010323203048930037300841110021109101010000100000640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
1002430037224006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100001640316222963010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  mla v0.4s, v8.4s, v9.s[1]
  movi v1.16b, 0
  mla v1.4s, v8.4s, v9.s[1]
  movi v2.16b, 0
  mla v2.4s, v8.4s, v9.s[1]
  movi v3.16b, 0
  mla v3.4s, v8.4s, v9.s[1]
  movi v4.16b, 0
  mla v4.4s, v8.4s, v9.s[1]
  movi v5.16b, 0
  mla v5.4s, v8.4s, v9.s[1]
  movi v6.16b, 0
  mla v6.4s, v8.4s, v9.s[1]
  movi v7.16b, 0
  mla v7.4s, 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)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)9fa6a9acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16020420090150198292580116100800161008002850064019612004520065200656128012820080028200240084200652006511160201100991001001600001000001111011911600200621600001002006620066200662006620066
1602042006515057292580116100801231158002850064019612004520065200656128012820080028200240084200652006511160201100991001001600001000001111011907100200621600001002006620066200662006620066
1602042006515048392580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000000001011111611200611600001002006520065200652006520065
16020420064150510392580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000000001011111611200611600001002006520065200652006520065
160204200641509392580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000000001011111611200611600001002006520065200652006520065
160204200641509392580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000000001011111611200611600001002006520065200652006520065
160204200641510392580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000000001011111611200611600001002006520065200652006520065
160204200641500392580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000000001011111611200611600001002006520065200652006520065
160204200641500392580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000000001011111611200611600001002006520065200652006520065
160204200641510392580100100800001008000050064000012004520064200643228010020080000200240000200642006411160201100991001001600001000000001011111611200611600001002006520065200652006520065

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080a0b18191e1f3a3f51inst 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)9fa1a6a7a8acc2cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1600242007715000000000452780012128000012800006264000011102003220051200513228001220800002024000020051200511116002110910101600001000000010036134118252111310200482201160000102005220052200522005220052
1600242005115000000660045278001212800001280000626400001110200322005120051322800122080000202400002005120051111600211091010160000100000001003113511025211129200482201160000102005220052200522005220052
160024200511500000043500452780012128000012800006264000011102003220051200513228001220800002024000020051200511116002110910101600001000000010044136114252111314200482201160000102005220052200522005220052
1600242005115000000390045278001212800001280000626400001110200322005120051322800122080000202400002005120051111600211091010160000100000001003513611725212920200482201160000102005220052200522005220052
160024200511500000000045278001212800001280000626400001110200322005120051322800122080000202400002005120051111600211091010160000100000001004213611225211168200482201160000102005220052200522005220052
1600242005115000000000452780012128000012800006264000011102003220051200513228001220800002024000020051200511116002110910101600001000000010039136113252211911200482201160000102005220052200522005220052
16002420051150000006300452780012128000012800006264000011102003220051200513228001220800002024000020051200511116002110910101600001000000010036136113252111212200482201160000102005220052200522005220052
160024200511500000000045278001212800001280000626400001110200322005120051322800122080000202400002005120051111600211091010160000100000001003313618252111112200482201160000102005220052200522005220052
1600242005115000000000452780012128000012800006264000011102003220051200513228001220800002024000020051200511116002110910101600001000000010040136110252121613200482201160000102005220052200522005220052
1600242005115000000000452780012128000012800006264000011102003220051200513228001220800002024000020051200511116002110910101600001000000010036137113252111013200482201160000102005220052200522005220052

Test 6: throughput

Count: 12

Code:

  mla v0.4s, v12.4s, v13.s[1]
  mla v1.4s, v12.4s, v13.s[1]
  mla v2.4s, v12.4s, v13.s[1]
  mla v3.4s, v12.4s, v13.s[1]
  mla v4.4s, v12.4s, v13.s[1]
  mla v5.4s, v12.4s, v13.s[1]
  mla v6.4s, v12.4s, v13.s[1]
  mla v7.4s, v12.4s, v13.s[1]
  mla v8.4s, v12.4s, v13.s[1]
  mla v9.4s, v12.4s, v13.s[1]
  mla v10.4s, v12.4s, v13.s[1]
  mla v11.4s, 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)03070b1e1f3f51inst 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)9fa6a7a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
12020431212225000041251201001001200001001200005009600001300203003930039149733167321201002001200002003600003003930039111202011009910010012000010000007610116113003601200001003004030040300403004030040
120204300392250000412512010010012000010012000050096000013002030041300391497331670612012520012000020036000030039300391112020110099100100120000100000076101162130036251200001003004030040300403004030040
1202043003922510483041251201001001200001001200005009600001300203004230039149733149971201252001200002003600003099930042111202011009910010012000010000007610116113003601200001003004030040300403004030040
1202043003922500267041251201001001200001001200005009600001300203003930039149733149971201002001200002003600003003930039111202011009910010012000010000007612116113003601200001003004030040300403004030040
12020430943225000041251201001001200001001200005009600000300203003930039149733149971201002001200002003600003003930039111202011009910010012000010000007610116113003601200001003004030040300403004030040
12020430039225000041251201001001200001001200005009600000300203003930039149733167321201002001200002003600003003930039111202011009910010012000010000007610116113003901200001003004030040300403004030040
12020430039225000041251201001251200001251200005009600001300203003930039149733149971201002001200002003600003003930039111202011009910010012000010000007612116113003601200001003004030040300403004030040
12020430039224000041251201251001200001001200005009600001300203003930039149733149971201002001200002003600003003930039111202011009910010012000010000007610116113003601200001003004030040300403004030040
120204300392250000412512010010012000010012000050096000013002030039300391497331499712010020012000020036000030386300391112020110099100100120000100000076101161130036251200001003004030040300403004030040
12020430039225000040251201001001200001001200005009600001300203003930039149733149971201002001200002003600003003930039111202011009910010012000010000007610116113003601200001003004030040300403004030040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b1e1f373f4e51inst 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)d5d6d9dadbddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
120024300402240150046025120010101200001012000050960000113002130039300391499631502012001020120000203600003003930039111200211091010120000100752231124162119630036206120000103004030040300403004030040
1200243003922502700046025120010101200001012000050960000113002030039300391499631501912001020120000203600003004030039111200211091010120000100752231191621161530036206120000103004030040300403004030040
12002430039225017700460251200101012000010120000509600001130020300393003914996315019120010201200002036000030039300391112002110910101200001007524622716211514300362012120000103004030040300403004030040
1200243003922502400520251200101012000010120000509600000130020300393003916680315019120010201200002036000030039300391112002110910101200001007522622716422147300364012120000103004030040300403004030040
120024300392240210052025120010101200001012000050960000013002030039300391667731501912001020120000203600003003930039111200211091010120000100752432371642268300364012120000103004030040300403004030040
1200243003922503120043202512001010120000101200005096000001300203003930039149963150191200102012000020360000300393003911120021109101012000010075246115162118630036206120000103004030040300403004030040
1200243003922503360046025120010101200001012000050960000013002030039300391499631501912001020120000203600003003930039111200211091010120000100752232281642276300364012120000103004030040300403004030040
120024300392250294003310251200101012000010120000509600000130020300393003914996315019120010201200002036000030039300391112002110910101200001007546922716422138300362021120000103004030040300403004030040
1200243003922503120052025120010101200001012000050960000013002030039300391499631501912001020120000203600003003930039111200211091010120000100752462171641166300362012120000103004030040300403004030040
120024300392250361760527025120010101200001012000050960000013002030039300391499631501912001020120000203600003003930039111200211091010120000100752433161621167300364012120000103004030040300403004030040