Apple M1 Microarchitecture Research by Dougall Johnson

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

SUBHN2 (vector, 8H)

Test 1: uops

Code:

  subhn2 v0.16b, v1.8h, v2.8h
  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)0318191e3f4e51inst 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
100430372300010325482510001000100039831313018303730372415328951000100030003037303711100110000073216112630100030383038303830383038
10043037230006125482510001000100039831303018303730372415328951000100030003037303711100110000673116112630100030383038303830383038
10043037220006125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037230008225482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037220006125482510001000100039831303018303730372415328951000100030003037303711100110007073116112630100030383038303830383038
10043037230006125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037230006125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037220006125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037230006125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037220006125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  subhn2 v0.16b, v1.8h, v2.8h
  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)03080b18191e1f3a3f4e51inst 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)9fa0a7a8a9accfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372240000000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000000710121622296340100001003003830038300383003830038
10204301332250000000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000000710121622296340100001003003830038300383003830038
102043003722500000006129539251011010010000100100005004278670130054300373003728265112874510100200101672003049830085300371110201100991001001000010000000712121622296340100001003003830038300383003830038
10204300372250000900612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000000710121622296340100001003003830038300383003830038
10204300372250000000942954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000000710121622296340100001003003830038300383003830038
102043003722500001200612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000020710121632296340100001003003830038300383003830038
10204300372250000000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000000710121622296680100001003003830038300383003830038
10204300372250000600612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000000710121622296340100001003003830038300383008730038
1020430037225000060012429539251011010410000104102985004277313130018300373003728269328745101002001000020030000300373003711102011009910010010000100411099371288432992215100001003051430612304213040930615
102043003728901149118870406409294671221010010010000100100005114277313130522304653075828315252874512224200100002223000030037300371110201100991001001000010000000710121622296340100001003003830038300383003830038

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)9fa6a8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722506129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722406129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100000640316222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640916222963010000103003830038300383003830038
10024300372250307429548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640316222963010000103003830038300383003830038
100243003722506129548441001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313030018300373003728287328767100102010000203000030037300371110021109101010000100100640516222963010000103003830038300383003830038
10024300372250286629548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  subhn2 v0.16b, v0.8h, v1.8h
  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)0308090b191e1f3f4e51inst 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)9fa1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250200360612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010040000071011611296340100001003003830038300383003830038
10204300372250000005362954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
1020430037225000000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
102043003722500005188822954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
1020430037225000000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
1020430037225000000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000100071011611296340100001003003830038300383003830038
1020430037225000000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071011611296344100001003003830038300383003830038
1020430037225000000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038
1020430037224000000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000400071011611296340100001003003830038300383003830038
1020430037225000000612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000000071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030818191e1f3f4e51inst 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)9fa0a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000630612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100006402162429630010000103003830038300383003830038
1002430037225014150612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
100243003722500000612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300372110021109101010000100006402162229630010000103003830038300383003830038
100243003722500000612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630110000103003830038300383003830038
100243003722500000612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
100243003722400000612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
100243003722500060612954825100101010007101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
100243003722400000612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
1002430037225000002322954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
1002430037225000510612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  subhn2 v0.16b, v1.8h, v0.8h
  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)0308090b181e1f3f4e51inst 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
10204300372250000006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100107102162229634100001003003830038300383003830038
102043003722500001206129538251010010010000100100005004277313030054300843003728268328745101002001000020030000300373003711102011009910010010000100007102162229634100001003003830038300383003830038
1020430037225000012010329548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100007102162229634100001003003830038300383003830038
102043003722400000010329548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100007102162229634100001003003830038300383003830038
10204300372250000006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100007102162229634100001003003830038300383003830038
102043003722500000061295484410147115100001001014950042773130300183003730037282651728745102522001000020030000300373003711102011009910010010000100067102162229634100001003003830038300383003830038
10204300372250000006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100007102162229634100001003003830038300383003830038
10204300372250000006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100007102162229634100001003003830038300383003830038
10204300372250100906129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100007102162229634100001003003830038300383003830038
102043003722500002106129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100107102162229634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b181e1f3f4e51inst 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)9fa8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722400300612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630110000103013230086300383013130085
100243008322511688612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
100243003722500007502954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000101006402162229630010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300853003830038
10024300372250000612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
10024300372250000612954825100101010000101000055427731330018300373003728287328767100102010000203000030037300371110021109101010000100006402162229630010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100006402162229702010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  subhn2 v0.16b, v8.8h, v9.8h
  movi v1.16b, 0
  subhn2 v1.16b, v8.8h, v9.8h
  movi v2.16b, 0
  subhn2 v2.16b, v8.8h, v9.8h
  movi v3.16b, 0
  subhn2 v3.16b, v8.8h, v9.8h
  movi v4.16b, 0
  subhn2 v4.16b, v8.8h, v9.8h
  movi v5.16b, 0
  subhn2 v5.16b, v8.8h, v9.8h
  movi v6.16b, 0
  subhn2 v6.16b, v8.8h, v9.8h
  movi v7.16b, 0
  subhn2 v7.16b, v8.8h, v9.8h
  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)0307080918191e1f3f51inst 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)9fa1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602042010115100000003925801001008000010080000500640000120045200642006432280100200800002002400002006420064111602011009910010016000010000000010111116112006101600001002006520065200652006520065
1602042006415000000003925801001008000010080000500640000120045200642006432280100200800002002400002006420064111602011009910010016000010000000010111116112006101600001002006520065200652006520065
1602042006415000000003925801001008000010080000500640000120045200642006432280100200800002002400002006420064111602011009910010016000010000000010111116112006101600001002006520065200652006520065
1602042006415000000003925801001008000010080000500640000020045200642006432280100200800002002400002006420064111602011009910010016000010000000010111116112006101600001002006520065200652006520065
16020420064150000000039258010010080000100800005006400001200452006420064272280100200800002002400002006420064111602011009910010016000010000000010111116112006101600001002006520065200652006520065
1602042006415000000003925801001008000010080000500640000120045200642006432280100200800002002400002006420064111602011009910010016000010000000010111116112006101600001002006520065200652006520065
1602042006415000000603925801001008000010080000500640000020045200642006432280100200800002002400002006420064111602011009910010016000010000000010111116112006101600001002006520065200652006520065
1602042006415000000003925801001008000010080000500640000120045200642006432280100200800002002400002006420064111602011009910010016000010000000010111116112006101600001002006520065200652006520065
1602042006415500000003925801001008000010080000500640000120045200642006432280100200800002002400002006420064111602011009910010016000010000000010111116112006101600001002006520065200652006520065
1602042006415000000003925801001008000010080000500640000120045200642006432280100200800002002400002006420064111602011009910010016000010000000010111116112006101600001002006520065200652006520065

1000 unrolls and 10 iterations

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

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)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)9fa1a8a9acc2cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160024200881500000004527800121280000118000062640000105200322005120051322800122080000202400002005120051111600211091010160000100000010028114282542242200572402160000102006120061200522006120061
160024200601500000005129800121280000128000062640000015200322006020060322800122080000202400002006020051111600211091010160000100000010031114223442224200572402160000102006120061200612006120061
160024200601500000005129800121280000128000062640000015200412006020060322800122080000202400002006020051111600211091010160000100000010030114263442242200572401160000102006120061200612006120061
160024200601500000005129800121280000128000062640000015200412006020051322800122080000202400002006020060111600211091010160000100003010030114243442224200572402160000102006120129200612006120061
160024200601500000005129800121280000128000062640000015200412006220060322800122080000202400002006020060111600211091010160000100000010030114243442242200572402160000102006120061200612006120061
160024200601500000005129800121280000128000062640000015200412006020060322800122080000202400002006020060111600211091010160000100000010032114223442224200572402160000102006120061200612006120061
16002420060150000000512980012128000012800006264000001520041200512005132280012208000020240000200512005111160021109101016000010000001002683122521124200482201160000102005220052200522005220052
16002420051150000000452780012128000012800006264000011520032200532005132280012208000020240000200512005111160021109101016000010000001002583142521124200482201160000102005220052200522005220052
16002420051150000000452780012128000012800006264000011520032200512005132280012208000020240000200512005111160021109101016000010000001002783132521154200482201160000102005220052200522005220052
160024200511500000004527800121280000128000062640000115200322006020060322800122080000202400002006020060111600211091010160000100000010029114253442242200572402160000102006120061200612006120061

Test 6: throughput

Count: 16

Code:

  subhn2 v0.16b, v16.8h, v17.8h
  subhn2 v1.16b, v16.8h, v17.8h
  subhn2 v2.16b, v16.8h, v17.8h
  subhn2 v3.16b, v16.8h, v17.8h
  subhn2 v4.16b, v16.8h, v17.8h
  subhn2 v5.16b, v16.8h, v17.8h
  subhn2 v6.16b, v16.8h, v17.8h
  subhn2 v7.16b, v16.8h, v17.8h
  subhn2 v8.16b, v16.8h, v17.8h
  subhn2 v9.16b, v16.8h, v17.8h
  subhn2 v10.16b, v16.8h, v17.8h
  subhn2 v11.16b, v16.8h, v17.8h
  subhn2 v12.16b, v16.8h, v17.8h
  subhn2 v13.16b, v16.8h, v17.8h
  subhn2 v14.16b, v16.8h, v17.8h
  subhn2 v15.16b, v16.8h, v17.8h
  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): 0.2503

retire (01)cycle (02)031e373f51inst 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)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)9fa6a7a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160204400582990042125160100100160000100160000500128000000400294003940039199730319997160100200160000200480000400484003911160201100991001001600001000000010110316454003601600001004004940040400494004040049
16020440048300305025160117100160017100160000500128000000400204004840039199730319997160100200160000200480000400394004811160201100991001001600001000000010110516554003601600001004004040049400494004040040
160204400393000174125160117100160000100160000500128000001400204003940039199730319998160100200160000200480000400484003911160201100991001001600001000024010110416444004501600001004004040049400404004040040
16020440039300004125160117100160017100160000500128000000400204004840039199730320006160100200160000200480000400484003911160201100991001001600001000000010110316534003601600001004004040049400404004940049
160204400483000071251601001001600001061600985001280000004002940048400391998303200371601002001600002004800004003940039211602011009910010016000010000000101105165340045231600001004015240100400404004940119
16020440049299005025160100100160000100160000500239899900400294003940048199730320006160100200160000200480000400484003911160201100991001001600001000000010110416454003601600001004004040040400494004040040
1602044003930001723125160117100160017100160000500239899900400294004840048199730319997160100200160000200480000400394004811160201100991001001600001000000610110416344004501600001004004040040400494004040040
160204400493000174125160100100160000100160000500239899900400204003940048199730319997160100200160000200480000400394003911160201100991001001600001002000010110516554003601600001004005040040400494004040040
1602044003930012178325160100100160000100160000500239899900400294003940049199730319997160100200160000200480000400394003911160201100991001001600001000000310110416444003601600001004004040049400404004940040
16020440039300153021825160117100160155100160106500239899900400294004840039199730319997160100200160209200480000400484004811160201100991001001600001000000010110516534003601600001004004940040400404004940049

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e373f51inst 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)9facc5cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16002440049300004625160010101600171016000050128000011400200400394003919996320019160010201600002048000040039400391116002110910101600001000100223118162117164003615108160000104004040040400404004040040
160024400393000055251600101016000010160000501280000114002004003940039199963200191600102016000020480609400394003911160021109101016000010001002231113162111664003615108160000104004040040400404004140040
16002440039300004625160010101600001016000050128000011400200400494004919996320019160010201600002048000040039400391116002110910101600001000100223111616211616400361587160000104004040040400404004040040
1600244003929900562516001010160000101600005012800001140020040039400491999632002916001020160000204800004003940039111600211091010160000100010022311616211616400361598160000104004040040400404004040040
16002440039300004625160010101600181016000050243886511400200400394003919996320019160010201600002048000040039400391116002110910101600001000100223111616211166400361589160000104004040040400404004040088
16002440039300004625160010101600001016000050128000011400200400394003919996320019160010201600002048000040039400391116002110910101600001000100223111616211166400361594160000104004040040400404004040040
16002440039300017711251600101016000010160000502438865114002004003940039199963200191600102016000020480000400394003911160021109101016000010001002231161621116164003615105160000104004040040400404004040040
160024400393000046251600271016000010160000501280000114002004003940040199963200201600102016000020480000400494003911160021109101016000010001002231116162111616400361592160000104004040040400404004040040
16002440039300004625160010101600001016000050128000011400200400484003919996320019160010201600002048000040039400391116002110910101600001000100223111616211166400361586160000104005040040400404004040049
16002440049300004625160010101600001016000050128000011400200400484003919996320019160010201600002048000040039400481116002110910101600001000100223116162111316400361585160000104004040050400404004040040