Apple M1 Microarchitecture Research by Dougall Johnson

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

UABA (vector, 16B)

Test 1: uops

Code:

  uaba v0.16b, v1.16b, v2.16b
  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)696d6edispatch stall (70)72scheduler 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)a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037241261254825100010001000398313301830373037241503289510001000300030373037111001100000073116112630100030383038303830383038
1004303724082254825100010001000398313301830373037241503289510001000300030373037111001100000073116112630100030383038303830383038
1004303723961254825100010001000398313301830373037241503289510001000300030373037111001100000073116112630100030383038303830383038
1004303723061254825100010001000398313301830373037241503289510001000300030373037111001100000073116112630100030383038303830383038
1004303725061254825100010001000398313301830373037241503289510001000300030373037111001100000073116112630100030383038303830383038
1004303724061254825100010001000398313301830373037241503289510001000300030373037111001100000373116112630100030383038303830383038
1004303722061254825100010001000398313301830373037241503289510001000300030373037111001100000073116112630100030383038303830383038
1004303722061254825100010001000398313301830373037241503289510001000300030373037111001100000073116112630100030383038303830383038
1004303723061254825100010001000398313301830373037241503289510001000300030373037111001100000073116112630100030383038303830383038
1004303723061254825100010001000398313301830373037241503289510001000300030373037111001100000073116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  uaba v0.16b, v1.16b, v2.16b
  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)030708181e3a3f4e51inst 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)9faccfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372241000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000710131633296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000710131633296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000710131633296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000710131634296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000710131633296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000710131633296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000710131633296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000710131633296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000710131633296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000710131633296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0318191e3f4e51inst 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)9faccfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722400126129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100640216222963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100640216222963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100640216222963010000103003830038300383003830038
100243003722500023329548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100640216222963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100640216222963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313130018300373003728287328786100102010000203000030037300371110021109101010000100640216222963010000103003830038300383003830038
10024300372250006129548251001010100001010150504277313130018300373003728287328767100102010000203000030037300371110021109101010000100640216222963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100640216222963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100640216222963010000103003830038300383003830038
1002430037225000198329548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100640216222963010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  uaba v0.16b, v0.16b, v1.16b
  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)03081e1f3a3f4e51inst 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)9fa0a1a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500006129548251010010010000100100005004277313130018030037300372826532874510100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313030018030037300372826532876310100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313030018030037300372826532874510100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
10204300372250159006129548251010010010000100100005004277313030018030037300372826532874510100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
1020430037224000012429548251010010010000100100005004277313030018030037300372826532874510100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313030018030037300372826532874510100200100002003000030037300371110201100991001001000010000105544071011611296340100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313030018030037300372826532874510100200100002003000030037300371110201100991001001000010000103071011611296340100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313130018030037300372826532874510100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313030018030037300372826532874510100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313030018030037300372826532874510100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03181e3f4e51inst 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)9faccfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225006129548251001010100001010000504277313130018300373003728287328767100102010000203000030037302281110021109101010000100640216222963010000103003830038300383003830038
1002430037224006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287328767103092010000203000030037300371110021109101010000100640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100640216222963010000103003830038300383003830038
1002430037224006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100640216222963010000103008530038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100640216222963010000103003830038300383003830038
10024300372250010329548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100640216222963010000103003830038300383003830038
1002430037225106129548251001010100001010000504277313130018300373003728287328786100102010000203000030037300371110021109101010000100640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100640216222963010000103003830038300383003830038
100243003722500631629548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100640217222963010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  uaba v0.16b, v1.16b, v0.16b
  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)03191e3f4e51inst 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)9fa8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372240061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042786701300183003730037282653287651010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000017101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372240061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03090b1e3f4e51inst 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)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000640316222963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300713003830038
100243003722500061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225000420295482510010101000010101495042773130300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722400061295392510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001010640216222963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773130300183008530037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  uaba v0.16b, v8.16b, v9.16b
  movi v1.16b, 0
  uaba v1.16b, v8.16b, v9.16b
  movi v2.16b, 0
  uaba v2.16b, v8.16b, v9.16b
  movi v3.16b, 0
  uaba v3.16b, v8.16b, v9.16b
  movi v4.16b, 0
  uaba v4.16b, v8.16b, v9.16b
  movi v5.16b, 0
  uaba v5.16b, v8.16b, v9.16b
  movi v6.16b, 0
  uaba v6.16b, v8.16b, v9.16b
  movi v7.16b, 0
  uaba v7.16b, v8.16b, v9.16b
  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)03070b191e3f51inst 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)9fa1a6a8a9acc5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16020420088150000123925801251258000012580000650640000120045200642006432280100200800002002400002006420064111602011009910010016000010000000010112216222006101600001002006520065200652006520065
1602042006415000003925801001008000010080000500640000120045200642006432280100200800002002400002006420064111602011009910010016000010000000010112216222006101600001002006520065200652006520065
1602042006415100003925801001008000010080000500640000120045200642006432280100200800002002400002006420064111602011009910010016000010000000010112216222006101600001002006520065200652006520065
1602042006415110003925801001008000010080000500640000020045200642006432280100200800002002400002006420064111602011009910010016000010000000010117217222006101600001002006520065200652006520065
16020420064150100039258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100000015010112216222006101600001002006520065200652006520065
16020420064150000333925801001008000010080000500640000020045200642006432280100200800002002400002006420064111602011009910010016000010000000010112216222006101600001002006520065200652006520065
1602042006415000003925801001008000010080000500640000020045200642006432280100200800002002400002006420064111602011009910010016000010000000010112216222006101600001002006520065200652006520065
160204200641500002133925801001008000010080000500640000020045200642006432280100200800002002400002006420064111602011009910010016000010000000010117216222006101600001002006520065200652006520065
160204200641500002493925801001008000010080000500640000020045200642006432280100200800002002400002006420064111602011009910010016000010000000010112216222006101600001002006520065200652006520065
1602042006415010003925801001008000010080000500640000020045200642006432280100200800002002400002006420064111602011009910010016000010000000010112216222006101600001002006520065200652006520065

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03070a1e1f3a3f51inst 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)5f6061696b6d6escheduler 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)9fa8branch mispredict (cb)cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16002420049151000016825800121280000128000062640000110200270200462004632280012208000020240000200462004611160021109101016000010001004161121202111918200432150160000102004720047200472004720047
16002420046150010005125800121280000128000062640000110200270200462005032280012208000020240000200502005011160021109101016000010001004031218244111918200472150160000102005120047200472004720047
1600242004615001276005725800121280000128000062640000110200270200462004632280012208000020240000200462004611160021109101016000010001003932116244121616200472150160000102004720047200472004720047
16002420046150000004525800121280000128000062640000210200270200462004632280012208000020240000200462004611160021109101016000010001003631119202111819200432150160000102004720047200472004720047
16002420046150010005725800121280000128000062640000010200310200502005032280012208000020240000200502005011160021109101016000010001003931116202211819200432300160000102004720047200512004720047
16002420050150110004525800121280000128000062640000010200310200502005032280012208000020240000200502005011160021109101016000010001003861119204122020200432150160000102004720047200472005120051
16002420050150110004525800121280000128000062640000010200310200462005032280012208000020240000200502005011160021109101016000010001004331116204122019200432150160000102004720047200472004720047
16002420046150010004525800121280000128000062640000110200270200462004632280012208000020240000200502004611160021109101016000010001004431118204111618200432300160000102004720047200472005120047
16002420046150110005725800121280000128000062640000010200310200502005032280012208000020240000200502005011160021109101016000010001004132220244222023200472300160000102005120051200512005120051
1600242005015011171005125800121280000128000062640000110200270200462005032280012208000020240000200462005011160021109101016000010001004132219244221917200472300160000102005120051200512005120051

Test 6: throughput

Count: 16

Code:

  uaba v0.16b, v16.16b, v17.16b
  uaba v1.16b, v16.16b, v17.16b
  uaba v2.16b, v16.16b, v17.16b
  uaba v3.16b, v16.16b, v17.16b
  uaba v4.16b, v16.16b, v17.16b
  uaba v5.16b, v16.16b, v17.16b
  uaba v6.16b, v16.16b, v17.16b
  uaba v7.16b, v16.16b, v17.16b
  uaba v8.16b, v16.16b, v17.16b
  uaba v9.16b, v16.16b, v17.16b
  uaba v10.16b, v16.16b, v17.16b
  uaba v11.16b, v16.16b, v17.16b
  uaba v12.16b, v16.16b, v17.16b
  uaba v13.16b, v16.16b, v17.16b
  uaba v14.16b, v16.16b, v17.16b
  uaba v15.16b, v16.16b, v17.16b
  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)031e1f373a3f51inst 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)6061696b6d6edispatch 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)9fa8accfd0d2d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602044006730000170502516010010016001810016000050012800001240020040039400491997332000616010020016000020048000040039400391116020110099100100160000100001011020116114003601600001004004040050400404004040040
160204400393000001712516010010016001710016000050012800001240020040039400391997331999716010020016000020048000040039400391116020110099100100160000100001011021116114003701600001004004940049402494010640050
160204400393000000462516010010016001710016000050012800001240020040039400391997331999716010020016000020048000040048400481116020110099100100160000100001011022116114003601600001004004040040400494004040049
160204400392990000412516010010016001710016000050012800001240020040039400401997331999716010020016000020048000040039400391116020110099100100160000100001011020116114004601600001004004940040400504004940040
160204400393000000502516010010016000010016000050012800001240029040048400391997331999716010020016000020048000040039400481116020110099100100160000100001011020116114003601600001004004940049400494004040040
160204400483000000502516011710016001710016000050012800001240020040048400391997331999716010020016000020048000040039400391116020110099100100160000100001011020116114003601600001004004040040400404004040040
160204400393000000502516011710016000010016000050012800001240020040049400391997331999716010020016000020048000040048400481116020110099100100160000100001011020116114003601600001004004940040402704004040041
160204400392990000412516011710016000010016000050013200001240029040039400391997331999716010020016000020048000040039400391116020110099100100160000100001011022116114004501600001004005040040400404004040040
16020440039300001707162516010010016000010016000050023989991240020040039400391997331999716010020016000020048000040048400391116020110099100100160000100001011020116114003601600001004004040040400494004040040
1602044003930000170412516011710016000010016000050012800001240020040039400391997331999716010020016000020048000040048400391116020110099100100160000100001011022116114004501600001004004040040400404004040040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03081e373f4e51inst 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)9fa8accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16002440049300121015002516001010160017101600005012800001154002940039400391999632001916001020160000204800004003940039111600211091010160000100010022811211621113740068206160000104004140040400404004940049
1600244004830000175502516001110160061101600005023989991154002040071400391999632001916001020160000204800004003940039111600211091010160000100010022841161621171740068209160000104007240040400404004940110
1600244004829900614602516002710160017101600005053871881154002940039400711999632002816001020160000204800004007140048111600211091010160000100010022841141621116840036206160000104004040040402834004140049
16002440048300006167025160027101600171016000050239899901540020400394004819996320028160010201600002048000040048400391116002110910101600001000100228411216211171740036206160000104004940049400404004040040
1600244004830000062025160010101600171016000050538718811540052400394004819996320019160010201600002048000040039400481116002110910101600001000100228411416211161640036206160000104004040072400494004040049
16002440048300000550251600101016000010160000501280000110400204003940048199963200191600102016000020480000400394003911160021109101016000010001002284171621113740036209160000104004040049400724004040072
160024400712990061462525160071101600001016000050239899911540029400394007119996320019160010201600002048000040039400481116002110910101600001000100228511716221191340036206160000104004040040400504004040049
1600244004830000046025160027101600001016000050128000011540020400394003919996320020160010201600002048000040039400391116002110910101600001000100228411316211131340036206160000104004940300400504004940072
160024400393000061462525160071101600011016000050128000011540029400394004819996320028160010201600002048000040039400391116002110910101600001000100228411316211131340045208160000104004940072400494007240049
160024400483000004602516002710160000101600005053871881154002040039400481999632002816001020160000204800004004840071111600211091010160000102610022841716211131140036209160000104004040049400404004940040