Apple M1 Microarchitecture Research by Dougall Johnson

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

SMLSL (vector, 2D)

Test 1: uops

Code:

  smlsl v0.2d, v1.2s, v2.2s
  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)60696b6d6edispatch 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
10043037230612548251000100010003983131301803037303724153289510001000300030373037111001100000073116112630100030383038303830383038
10043037230612548251000100010003983130301803037303724153289510001000300030373037111001100000073116112630100030383038303830383038
100430372215612548251000100010003983130301803037303724153289510001000300030373037111001100020073116112630100030383038303830383038
10043037233612548251000100010003983130301803037303724153289510001000300030373037111001100000073116112630100030383038303830383038
10043037230612548251000100010003983131301803037303724153289510001000300030373037111001100000073116112630100030383038303830383038
10043037230612548251000100010003983130301803037303724153289510001000300030373037111001100000073116112630100030383038303830383038
10043037220612548251000100010003983131301803037303724153289510001000300030373037111001100000073116112630100030383038303830383038
10043037230612548251000100010003983130301803037303724153289510001000300030373037111001100000073116112630100030383038303830383038
10043037230612548251000100010003983130301803037303724153289510001000300030373037111001100000073116112630100030383038303830383038
10043037220612548251000100010003983130301803037303724153289510001000300030373037111001100000073116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  smlsl v0.2d, v1.2s, v2.2s
  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)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)9fa0a1a8accfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372253010329548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000371003162229634100001003003830038300383003830038
10204300372251206129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000671002162229634100001003003830038300383003830038
1020430037226006129539251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000071012162229634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000071012163229634100001003003830038300383003830038
1020430037224006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000071012162229634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000071012162229634100001003003830038300383003830038
10204300372250072629548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000071012162229634100001003003830038300383003830038
102043003722501197529548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000071012162229634100001003003830038300383003830038
1020430037225016129548301010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000071012162229634100001003003830038300383003830038
1020430037225006129548251010010010000100101485004277313030018300373003728265328745106322001000020030000300373003711102011009910010010000100000071012162229634100001003003830038300383003830038

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)9fa8c2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372240612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010006402162329630010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010006403163329630010000103003830038300383003830038
10024300372250612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010006403163329630010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001830037300372828732876710010201000020300003008530037111002110910101000010006403164229630010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010006403163329630010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010006403163329630010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010006402162229630010000103003830038300383003830038
10024300372250612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010006403163329630010000103003830038300383003830038
1002430037225013552954825100101010000101000050427731303006530037300372828732876710010201000020300003003730037111002110910101000010006402163329630010000103003830038300383003830038
100243003722501312954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010006402164229630010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  smlsl v0.2d, v0.2s, v1.2s
  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)9fa0a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250612954825101001001000010010000500427731303001803003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
10204300372244176129548251010010010000100100005004277313130018030037300372826512287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722545612954825101001001000010010000500427731303001803003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225345612954825101001001000010010000500427731313001803003730037282653287451010020010000200300003003730037111020110099100100100001000007100161129634100001003003830038300383003830038
102043003722512612954825101001001000010010000500427731303001803003730037282653287451010020010000200300003003730037111020110099100100100001000007411161129634100001003003830038300383003830038
1020430037225264822954825101001001000010010000500427731303001803003730037282653287451010020010000200300003003730037111020110099100100100001000007401161129634100001003003830038300383003830038
10204300372242766129548251010010010000100100005004277313030018030037300372826513287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722512612954825101001001000010010000500427731303001803003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037225417612954825101001001000010010000500427731313001803003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
1020430037224336612954825101001001000010010000500427731313001803003730037282653287451010020010000200300003003730037111020110099100100100001000007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b1e3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)72scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa7a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225102512954825100101010000101000050427731303001830037300372828703287671001020104872030000300373003711100211091010100001000006402162329630010000103003830038300383003830038
100243003722500612954825100101010000101000050427731313001830037300372828703287671001020100002030000300373003711100211091010100001000006402162229630010000103003830038300383003830038
100243003722500612954825100101010000101000050427731313001830037300372828703287671001020100002030000300373003711100211091010100001000006402162229630010000103003830038300383003830038
100243003722500612954825100101010000101000050427731313001830037300372828703287671001020100002030000300373003711100211091010100001000006402162229630010000103003830038300383003830038
100243003722500612954825100101010000101000050427731303001830037300372828703287671001020100002030000300373003711100211091010100001000006402162229630010000103003830038300383003830038
1002430037224002512954825100101010000101000050427731303001830037300372828703287671001020100002030000300373003711100211091010100001000006402162229630010000103003830038300383003830038
100243003722500612954825100101010000101000050427731303001830037300372828703287671001020100002030000300373003711100211091010100001000006402162229630010000103003830038300383003830038
100243003722500612954825100101010000101000050427731303001830037300372828703287671001020100002030000300373003711100211091010100001000006402162229630010000103003830038300383003830038
100243003722500612954825100101010000101000050427731303001830037300372828703287671001020100002030000300373003711100211091010100001000006402162229630010000103003830038300383003830038
10024300372250228612954825100101010000101000050427731303001830037300372828703287671001020100002030000300373003711100211091010100001000006402162229630010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  smlsl v0.2d, v1.2s, v0.2s
  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)03080918191e1f3a3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000114006129548251010010010000100100005004277313130018300373003728265328745101002041000020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
102043003722400000006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000009071011611296340100001003003830038300383003830038
102043003722500000006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000010071011611296340100001003003830038300383003830038
102043003722500000006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000000073511611296340100001003003830038300383003830038
102043003722510000006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
102043003722400000006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
102043003722500000006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011611297110100001003003830038300383003830038
102043003722500000006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
102043003722500000006129548251010010010000100100005004277313130126300373003728265328745101002001000020030000300373003711102011009910010010000100000100071021611296340100001003003830038300383003830038
102043003723200000006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038

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)9fa1accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372253361295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722524361295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722545612954825100101010000101000050427731313001830037300372828719287671001020100002030000300373003711100211091010100001000640216432963010000103003830038300383003830038
1002430037225661295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722426161295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225255691295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722525561295482510010101000010100005042773130300183003730037282877287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225961295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372251561295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  smlsl v0.2d, v8.2s, v9.2s
  movi v1.16b, 0
  smlsl v1.2d, v8.2s, v9.2s
  movi v2.16b, 0
  smlsl v2.2d, v8.2s, v9.2s
  movi v3.16b, 0
  smlsl v3.2d, v8.2s, v9.2s
  movi v4.16b, 0
  smlsl v4.2d, v8.2s, v9.2s
  movi v5.16b, 0
  smlsl v5.2d, v8.2s, v9.2s
  movi v6.16b, 0
  smlsl v6.2d, v8.2s, v9.2s
  movi v7.16b, 0
  smlsl v7.2d, v8.2s, v9.2s
  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)030818191e1f3f5051inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602042009015000090390258010010080000100800005006400001200452038220064322801002008000020024000020064200641116020110099100100160000100000000010111116112006101600001002006520065200652006520168
16020420155151000006090258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100000000010111116112006101600001002006520065200652006520065
16020420064150000210600258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100000000010111116112006101600001002006520065200652006520065
1602042006415000000390258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100000000010111116112006101600001002006520065200652006520065
16020420064151000150390258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100000000010111116112006101600001002006520065200652006520065
1602042006415000000390258010010080000100800005006400001200452006420064343801002008000020024000020064200641116020110099100100160000100000000010111116112006101600001002006520065200652006520065
1602042015615000000390258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100000000010111116112006101600001002006520065200652006520065
1602042006415000000390258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100000000010111116112006101600001002006520065200652006520065
160204200641500000039025801001008000010080000500640000120045200642006432280100200800002002400002006420064111602011009910010016000010000000132010111116112006101600001002006520065200652006520065
16020420064150000009820258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100000000010111116112006101600001002006520065200652006520065

1000 unrolls and 10 iterations

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

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)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)9fa8accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160024200621500045278001212800001280000626400001152003220051200513228001220800002024000020051200511116002110910101600001000100448312025211819200482201160000102005220052200522005220052
16002420051150004527800121280000128000062640000115200322005120051322800122080000202400002005120051111600211091010160000100010030841625211619200482201160000102005220052200522005220052
160024200511500045278001212800001280000626400001152003220051200513228001220800002024000020051200511116002110910101600001000100438411925211619200482201160000102005220052200522005220127
16002420051150004527800121280000128000062640000115200322005120051322800122080000202400002005120051111600211091010160000100010043841625211198200482201160000102005220052200522005220052
160024200511500045278001212800001280000626400001152016220051200513228001220800002024000020051200511116002110910101600001000100328419252111919200482201160000102005220154200522014120052
1600242006015100452780012128000012800006264000011520032200512005132280012208000020240000200512005111160021109101016000010001004611521934422198200572402160000102006120061200612006120061
16002420060150004527800121280000128000062640000115200322005120051322800122080000202400002005120051111600211091010160000100010046115219344221919200572402160000102006120061200612006120061
1600242006015029706627800121280000128000062640000115200322005120051322800122080000202400002005120051111600211091010160000100010043841825211198200482201160000102005220052200522005220052
160024200511500045278001212800001280000626400001152003220051200513228001220800002024000020051200511116002110910101600001000100438411825211198200482201160000102005220052200522005220052
1600242005115000452780012128000012800006264000011520032200512005132280012208000020240000200512006011160021109101016000010001003284119252111919200482201160000102005220052200522005220052

Test 6: throughput

Count: 16

Code:

  smlsl v0.2d, v16.2s, v17.2s
  smlsl v1.2d, v16.2s, v17.2s
  smlsl v2.2d, v16.2s, v17.2s
  smlsl v3.2d, v16.2s, v17.2s
  smlsl v4.2d, v16.2s, v17.2s
  smlsl v5.2d, v16.2s, v17.2s
  smlsl v6.2d, v16.2s, v17.2s
  smlsl v7.2d, v16.2s, v17.2s
  smlsl v8.2d, v16.2s, v17.2s
  smlsl v9.2d, v16.2s, v17.2s
  smlsl v10.2d, v16.2s, v17.2s
  smlsl v11.2d, v16.2s, v17.2s
  smlsl v12.2d, v16.2s, v17.2s
  smlsl v13.2d, v16.2s, v17.2s
  smlsl v14.2d, v16.2s, v17.2s
  smlsl v15.2d, v16.2s, v17.2s
  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)03081e373f51inst 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)9fa1a8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602044007129900141251601001001600001001600005001280000400204004840049199733199971601002001600002004800004003940048111602011009910010016000010000001011021632400361600001004005040041400404004040049
1602044003930000141501601011001600171001600005002398999400214004840039199733200061601002001600002004800004004040039111602011009910010016000010000001011031622400361600001004004040049400404004940049
1602044004830000141251601181001600171001600005002398999400204004840039199733199971601002001600002004800004003940039111602011009910010016000010000001011025234400451600001004004040049400404004140040
16020440039300001741251601001001600171001600005002398999400214003940048199733200061601002001600002004800004003940048111602011009910010016000010000001011021633400361600001004004940049400494004940049
16020440092300101750441601001001600171071601525001280000400204004840039199738201181601002001600002004806034004040039211602011009910010016000010000001011021623400361600001004004140040400494004940040
1602044003929900041251601001001600001001600005001280000400294004840039199733200061601002001600002004800004003940039111602011009910010016000010000001011041623400451600001004004940040400414004040040
16020440039300001741251601001001600001001600005001280000400204004840049199733200061601002001600002004800004004840039111602011009910010016000010000001011031622400451600001004004040040400494004040041
1602044004830006050251601001001600181001600005001280000400204004840039199733200061601002001600002004800004004040048111602011009910010016000010020001011021622400361600001004004040040400494004040049
1602044003930000050251601001001600001001600005002398999400294004840052199733199971601002001600002004800004004040048111602011009910010016000010000001011031632400361600001004004940040400494004040049
1602044004829900042251601001001600001001600005002398999400294003940048199733200061601002001600002004800004004840039111602011009910010016000010000001011021622400361600001004004140040400494004040040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0308191e373f51inst 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
160024400493000001752251600101016000010160000501280000010400204003940039199963200281600102016000020480000400394003911160021109101016000010001002231238164221919400363010160000104004040040400404004040040
16002440039299000046251600101016000010160000502438865110400204003940039199963200191600102016000020480000400394003911160021109101016000010001002462219164222621400363010160000104004040040400504004040040
16002440039300000046251600101016000010160000501280000110400204003940039199963200191600102016000020480000400394003911160021109101016000010001002462219164221519400363010160000104004040040400404004040040
1600244003930000004625160010101600001016000050128000011040030400394003919996320019160010201600002048000040039400391116002110910101600001000100223111916211201940036155160000104004040040400404004040040
16002440039300000185225160010101600001016000050128000011040020400484003919996320028160010201600002048000040039400391116002110910101600001000100223111516211191540036155160000104004040040400404004040040
1600244003930000004625160010101600001016000050128000011040020400394004919996320029160010201600002048000040039400391116002110910101600001000100223111916211191940036155160000104004040040400504004040040
16002440039300003046251600101016000010160000502438865110400204003940040199963200191600102016000020480000400394003911160021109101016000010001002462225164221520400363010160000104005040040400404004040040
1600244003929900004625160010101600001016000050128000011040020400394003919996320019160010201600002048000040039400391116002110910101600001000100223111516211191540036155160000104004040040400404004040040
1600244004930000004625160010101600001016000050128000011040020400394003919996320019160010201600002048000040039400391116002110910101600001000100223111916211191940036155160000104004140049400494004940040
1600244003930000014625160010101600001016000050128000011040020400394003919996320019160010201600002048000040040400391116002110910101600001030100223111916211181940036155160000104004040040400404004040040