Apple M1 Microarchitecture Research by Dougall Johnson

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

SMLSL2 (vector, 4S)

Test 1: uops

Code:

  smlsl2 v0.4s, 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)03070a1e1f3a3f4e51inst 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)a1a8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303723100006125482510001000100039831303018303730372415328951000100030003037303711100110000073616662630100030383038303830383038
1004303722006006125482510001000100039831303018303730372415328951000100030003037303711100110000073516662630100030383038303830383038
1004303722000006125482510001000100039831303018303730372415328951000100030003037303711100110000073616652630100030383038303830383038
1004303722000006125482510001000100039831303018303730372415328951000100030003037303711100110000073616662630100030383038303830383038
10043037230012006125482510001000100039831303018303730372415328951000100030003037303711100110000073616662630100030383038303830383038
10043037230000025125482510001000100039831303018303730372415328951000100030003037303711100110000073616662630100030383038303830383038
1004303722000006125482510001000100039831303018303730372415328951000100030003037303711100110000073616662630100030383038303830383038
1004303722000006125482510001000100039831303018303730372415328951000100030003037303711100110000073616662630100030383038303830383038
1004303723006006125482510001000100039831303018303730372415328951000100030003037303711100110000073516662630100030383038303830383038
1004303722000006125482510001000100039831303018303730372415328951000100030003037303711100110000073616662630100030383038303830383038

Test 2: Latency 1->1

Code:

  smlsl2 v0.4s, 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)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)9fa8accfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000071002412229634100001003003830038300383003830038
102043003722500729295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000071002162329634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000071012162229634100001003003830038300383003830038
10204300372240061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000071012162229634100001003003830038300383003830038
10204300372240061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000071012162229634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000071012512229634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000071012162229634100001003003830038300383003830038
10204300372240061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000071012162229634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000071012163229634100001003003830038300383003830038
10204300372250161295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000071012162229634100001003003830038300383003830038

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)696b6d6edispatch 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500612954825100101010000101000050427731330018030037300842828703287671001020100002030000300373003711100211091010100001000640616222963010000103003830038300383003830038
1002430037225007262954825100101010000101000050427731330018030037300372828703287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731330018030037300372828703287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731330018030037300372828703287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731330018030037300372828703287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731330018030037300372828703287671001020100002030000300373003711100211091010100001000640216222963010000103003830061300383003830038
100243003722500612954825100101010000101000050427731330018030037300372828703287671001020100002030000300373003711100211091010100001000640216322963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731330018030037300372828703287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225002512954825100101010000101000050427731330018030037300372828703287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731330018030037300372828703287671001020100002030000300373003711100211091010100001000640316222963010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  smlsl2 v0.4s, 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)031e1f3a3f4e51inst 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
10204300372250006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100008081161129634100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100607101161129634100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100008031161129634100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03181e3a3f4e51inst 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)9fa0a8acc2c5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000006402162229630010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000006402162229630010000103003830038300383003830038
10024300372250450612954825100101010000101000050427731313001830037300372828732876210010201000020300003003730037111002110910101000010000006402162229630010000103003830038300383003830038
1002430037224000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000006402162229630010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000006402162229630010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010003006402162229630210000103003830133300383003830038
1002430037225000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000006402162229630010000103003830038300383003830038
1002430037225000612954825100101010000121000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000006402162229630010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731303001830037300372828732876710010201000020300003003730037111002110910101000010000006402162229630010000103003830038300383003830038
10024300372250001052954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000006402162229630010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  smlsl2 v0.4s, 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)0318191e1f3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500360612954825101001001000010010000500427731313001830037300372826503287451010020010000200300003003730037111020110099100100100001000071021622296340100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731313001830037300372826503287451010020010000200300003003730037111020110099100100100001000071021622296340100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731313001830037300372826503287451010020010000200300003003730037111020110099100100100001000071021622296340100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731313001830037300372826503287451010020010000200300003003730037111020110099100100100001000071021622296340100001003003830038300383003830038
10204300372250000612954825101001001000010010000500427731313001830037300372826503287451010020010000200300003003730037111020110099100100100001000071021623296340100001003003830038300383003830038
102043008122500001242954825101001001000010010000500427731313001830037300372826503287451010020010000200300003003730037111020110099100100100001000071021622296340100001003003830038300383003830038
102043003722500007262954825101001001000010010000500427731313001830037300372826503287451010020010000200300003003730037111020110099100100100001000071021622296340100001003003830038300383003830038
102043003722500007262954825101001001000010010000500427731313001830037300372826503287451010020010000200300003003730037111020110099100100100001000071021622296340100001003003830038300383003830038
102043003722500007262954825101001001000010010000500427731313001830037300372826503287451010020010000200300003003730037111020110099100100100001000071021622296340100001003003830038300383003830038
10204300372240000612954825101001001000010010000500427731313001830037300372826503287451010020010000200300003003730037111020110099100100100001000071021622296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)031e1f3f4e51inst 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)9fa8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722410612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722514788612954869100201210000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  smlsl2 v0.4s, v8.8h, v9.8h
  movi v1.16b, 0
  smlsl2 v1.4s, v8.8h, v9.8h
  movi v2.16b, 0
  smlsl2 v2.4s, v8.8h, v9.8h
  movi v3.16b, 0
  smlsl2 v3.4s, v8.8h, v9.8h
  movi v4.16b, 0
  smlsl2 v4.4s, v8.8h, v9.8h
  movi v5.16b, 0
  smlsl2 v5.4s, v8.8h, v9.8h
  movi v6.16b, 0
  smlsl2 v6.4s, v8.8h, v9.8h
  movi v7.16b, 0
  smlsl2 v7.4s, 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)0309191e3f51inst 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)9fa1a6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1602042009015000039258010010080000100800005006400000200452006420064322801002008000020024000020064200641116020110099100100160000100000010111116112006101600001002006520065200652006520065
1602042006415000039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100000010111116112006101600001002006520065200652006520065
1602042006415000039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100000010111116112006101600001002006520065200652006520065
1602042006415100039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100000010111116112006101600001002006520065200652006520065
1602042006415000039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100000010111116112006101600001002006520065200652006520065
1602042006415010039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100000010111116112006101600001002006520065200652006520065
1602042006415000039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100000010111116112006101600001002006520065200652006520065
1602042006415000039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100000010111116112006101600001002006520065200652006520065
1602042006415000039258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100000010111116112006101600001002006520065200652006520065
1602042006415000081258010010080000100800005006400001200452006420064322801002008000020024000020064200641116020110099100100160000100000010111116112006101600001002006520065200652006520065

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030708090b191e1f3a3f51inst 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)9fa0a6a8a9accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)dfe0? int output thing (e9)eaec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160024200741611000000045278001212800001280000626400001152023320051200513228001220800002024000020051200511116002110910101600001000003100418219252111174200482201160000102005220061200522005220052
1600242005116110000120145278001212800001280000626400001152003220064200513228001220800002024000020051200511116002110910101600001000003100411431825211884200482201160000102005220052200522005220052
16002420051161100002700452780012128000012800006264000011520032200512005132280012208000020240000200512005111160021109101016000010001031004485283821110104200482201160000102005220052200522005220053
160024200511610000090011925800121280000128000062641672110200322005120051322801392280000202400002004620050111600211091010160000100000010041311820211794200432150160000102004720047200472004720047
160024200461610010000045258001212800001280000626400001102002720046200463228001220800002024000020046200461116002110910101600001000000100463111020211994200432150160000102004720047202852004720047
160024200461550000000045258001212800001280000626400001102002720207200463228001220800002024000020046200461116002110910101600001000000100443111020211884200432150160000102004720047200472004720047
160024200461560000000045258001212802091280000626400001102002720046200463228001220800002024000020046200461116002110910101600001022000100686211120412884200432300160000102004720051200472005120047
1600242004615500000000330258001212800001280000626400001102003120050200463228001220800002024000020046200501116002110910101600001000043100463129204227114200432150160000102005120047200512004720047
160024200461560000000051258001212800001380000626400001102002720046200503228001220800002024000020046200501116002110910101600001000000101363218204128104200432150160000102004720051200472005120047
16002420046153000000015125800121280000128000062640000010200272005020046162280012208000020240000200462004611160021109101016000010000001004318218242211174200472300160000102004720051200472005120047

Test 6: throughput

Count: 16

Code:

  smlsl2 v0.4s, v16.8h, v17.8h
  smlsl2 v1.4s, v16.8h, v17.8h
  smlsl2 v2.4s, v16.8h, v17.8h
  smlsl2 v3.4s, v16.8h, v17.8h
  smlsl2 v4.4s, v16.8h, v17.8h
  smlsl2 v5.4s, v16.8h, v17.8h
  smlsl2 v6.4s, v16.8h, v17.8h
  smlsl2 v7.4s, v16.8h, v17.8h
  smlsl2 v8.4s, v16.8h, v17.8h
  smlsl2 v9.4s, v16.8h, v17.8h
  smlsl2 v10.4s, v16.8h, v17.8h
  smlsl2 v11.4s, v16.8h, v17.8h
  smlsl2 v12.4s, v16.8h, v17.8h
  smlsl2 v13.4s, v16.8h, v17.8h
  smlsl2 v14.4s, v16.8h, v17.8h
  smlsl2 v15.4s, 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)03191e373f51inst 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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160204400703000003025160108100160017100160020500128013214002940049400481997761999016012020016003220048009640048400391116020110099100100160000100031111011821622400371600001004005040049400724004940050
1602044003930000123025160117100160058100160020500128013214002040039400391997761999016012020016003220048009640039400391116020110099100100160000100061111011811622400461600001004004140040400404004040050
1602044004929900140251601171001600081001600205001280132140020400394004019977619991160120200160032200480096400394004911160201100991001001600001000211111011821622400361600001004004040050400494004040040
160204400483000003025160117100160017100160020500239918704002040040400391997762002216012020016003220048009640039400391116020110099100100160000100061111011821612400451600001004004040040400494004040114
160204400393000004125160117100160000100160000500239899904002040048400391997332000716010020016000020048000040039400391116020110099100100160000100000001011031633400361600001004004040072400404007240040
160204400393000005125160100100160000100160000500128000004002940048400391997331999716010020016000020048000040039400481116020110099100100160000100000001011031632400361600001004004940040400414004040050
16020440048300000502516011710016000010016000050023989990400204003940039199733199971601002001600002004800004003940048111602011009910010016000010001200001011021623400361600001004004040041400404004040040
1602044004829900051251601171001600001001600005001280000040030400394003919973319997160100200160000200480000400394003911160201100991001001600001000990001011031632400371600001004004040040400504004040050
16020440039300001741251601001001600171001600005002398999140052400484003919973319998160100200160000200480000400404004911160201100991001001600001000120001011031632400361600001004004040050400494007240049
160204400403000004125160100100160017100160000500239899914002140039400711997331999716010020016000020048000040039400391116020110099100100160000100090001011031633400461600001004004940040400404004940040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03181e1f373f51inst 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)9fa0a8acbranch mispredict (cb)cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160024400873010000562516001010160000101600005012800000140020400394003919996320029160010201600002048000040039400391116002110910101600001000001002231135162111015400361510160000104004040040400404005040040
16002440049300000046251600101016000010160000502438865114002040039400391999632001916001020160000204800004004840048111600211091010160000100000100223111516211211640036155160000104004940040400504005040040
16002540048300000055251600101016000010160000501280000114002040039400491999632001916001020160000204800004003940039111600211091010160000100000100223112216211102040036155160000104004040040400404004040040
16002440039301000046251600101016000110160000502398999114002040039400391999632001916001020160000204800004003940039111600211091010160000100000100223111516211151640036155160000104004040040400404005040050
16002440039300000046251600101016000010160000502438865114002040039400391999632001916001020160000204800004003940039111600211091010160000100000100223111116211141440036155160000104004040040400404004040040
160024400393000000711251600101016001810160000501280000114002940039400391999632001916001020160000204800004003940039111600211091010160000100030100223111416211122040036155160000104004040040400504005040050
16002440039300000046251600101016000010160000501280000114002040048400391999632001916001020160000204800004003940039111600211091010160000100000100223111916211111440036155160000104004040040400404005040040
160024400393000001846251600101016000010160000502438865114002040039400391999632001916001020160000204800004003940040111600211091010160000100000100223111116211141140036155160000104004040049400494004940040
16002440039300000146251600991016001710160000501280000114003040039400391999632001916001020160000204800004004940039111600211091010160000100000100223111416211181840037155160000104004040040400404005040040
16002440039300000046251600101016000010160000501280000114003040039400391999632002916001020160000204800004003940039111600211091010160000100000100223111016211151140036155160000104004040040400404004040040