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, 8H)

Test 1: uops

Code:

  uaba v0.8h, 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)031e3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)696d6edispatch 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)a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372206125482510001000100039831330183037303724153289510001000300030373037111001100000073316442630100030383038303830383038
100430372206125482510001000100039831330183037303724153289510001000300030373037111001100000073316332630100030383038303830383038
10043037220612548251000100010003983133018303730372415328951000100030003037303711100110000079873316332630100030383038303830383038
100430372306125482510001000100039831330183037303724153289510001000300030373037111001100040073316332630100030383038303830383038
100430372306125482510001000100039831330183037303724153289510001000300030373037111001100000073316332630100030383038303830383038
100430372208225482510001000100039831330183037303724153289510001000300030373037111001100020073316332630100030383038303830383038
100430372306125482510001000100039831330183037303724153289510001000300030373037111001100000073316332630100030383038303830383038
100430372306125482510001000100039831330183037303724153289510001000300030373037111001100010073316332630100030383038303830383038
100430372206125482510001000100039831330183037303724153289510001000300030373037111001100030073316332630100030383038303830383038
100430372206125482510001000100039831330183037303724153289510001000300030373037111001100000073316332630100030383038303830383038

Test 2: Latency 1->1

Code:

  uaba v0.8h, 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
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000071014163329634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000071014163329634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000071013163329634100001003003830038300383003830038
10204300372243061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000071013163329634100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731303001830037300372826525287451010020010000200300003003730037111020110099100100100001000071013163329634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000071013163329634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000071013163329634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000071013163329634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000071013163329634100001003003830038300383003830038
10204300372250161295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000071013163329634100001003003830038300383003830038

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)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)9fc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037224240612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100640316332963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100640316332963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100640316332963010000103003830038300383003830038
100243003722400612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100640316332963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100640416332963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100640316332963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100640316432963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100640316332963010000103003830085300383003830038
100243003722500612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100640316332963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100640316332963010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  uaba v0.8h, 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)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)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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000000612954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
10204300372250000000612954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
10204300372250000000662954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
10204300372250000000612954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
102043003722500000001032954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
10204300372250000000612954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
10204300372250000600612954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
1020430037225000015600612954825101001001000010010000500427731330018300373003728265328745101002041000020030000300373008621102011009910010010000100000000071011611296340100001003003830038300383003830038
10204300372250000000612954844101001001000010010000500427731330018300373008528265328745102722001000020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
10204300372250000000612954825101001001000010010000500427731330018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03070a0b181e1f3a3f4e51inst 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)9fa0a6a8acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000024006129548251001010100001010000504277313030018300373003728287032876710010201000020300003003730037111002110910101000010002900640216222963010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313030018300373003728287032876710010201000020300003003730037111002110910101000010000000640216222963010000103003830038300383003830038
100243003724700009006129548251001010100001010000504277313030018300373003728287032876710010201000020300003003730037111002110910101000010000000640216222963010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313030018300373003728287032876710010201000020300003003730037111002110910101000010000000640216222963010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313030018300373003728287032876710010201000020300003003730037111002110910101000010000000640216222963010000103003830038300383003830038
100243003722500000006129530251001010100001010000504277313030018300373003728287732876710010201000020300003003730037111002110910101000010000000640216222963010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313030018300373003728287032876710010201000020300003003730037111002110910101000010000000640216222963010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313030018300373003728287032876710010201000020300003003730037111002110910101000010000000640216222963010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313030018300373003728287032876710010201000020300003003730037111002110910101000010000001640216222963010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313030018300373003728287032876710010201000020300003003730037111002110910101000010010000640216222963010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  uaba v0.8h, 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)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)9fa8cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100007102162229634100001003003830038300383003830038
1020430037224006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100007102162229634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100007102163229634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100007102162229634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100007102162229634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100007102162229634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100007102162229634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100007102162229634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100007102162229634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100007102162229634100001003003830038300383003830038

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)9fa6a8acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
100243003722500586295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003721100211091010100001000000640216222963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
100243003722500156295482510010101000010100005042773130300183003730037282873287671001020100002030000300373003711100211091010100001000000640216222963010000103003830038300383003830038
100243003722500726295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001000000640217222963010000103003830038300383003830038
10024300372250108631295482510010101000010100005042773131300183003730037282873287671001020100002030000300373003711100211091010100001001000640216222963010000103008530038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  uaba v0.8h, v8.8h, v9.8h
  movi v1.16b, 0
  uaba v1.8h, v8.8h, v9.8h
  movi v2.16b, 0
  uaba v2.8h, v8.8h, v9.8h
  movi v3.16b, 0
  uaba v3.8h, v8.8h, v9.8h
  movi v4.16b, 0
  uaba v4.8h, v8.8h, v9.8h
  movi v5.16b, 0
  uaba v5.8h, v8.8h, v9.8h
  movi v6.16b, 0
  uaba v6.8h, v8.8h, v9.8h
  movi v7.16b, 0
  uaba v7.8h, 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)030818191e1f3a3f51inst 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)696d6escheduler 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)9fa6a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160204200891500000003925801001008000010080000500640000200452006420064322801002008000020024000020064200641116020110099100100160000100000010112216222006101600001002006520065200652006520065
160204200641510000003925801001008000010080000500640000200452006420064322801002008000020024000020064200641116020110099100100160000100000010112216222006101600001002006520065200652006520065
160204200641510000003925801001008000010080000500640000200452006420064322801002008000020024000020064200641116020110099100100160000100010010112216222006101600001002006520065200652006520065
160204200641510000003925801001008000010080000500640000200452006420064322801002008000020024000020064200641116020110099100100160000100000010112216222006101600001002006520065200652006520065
160204200641500000003925801001008000010080000500640000200452006420064322801002008000020024000020064200641116020110099100100160000100040310112216222006101600001002006520065200652006520065
16020420064150000120083258010010080000100800006506400002004520064200643228010020080000200240000200642006411160201100991001001600001000009101122162320061181600001002006520065200652006520065
1602042006415001008803925801001008000010080000500640000200452006420064322801002008000020024000020064200641116020110099100100160000100070310112216322006101600001002006520065200652006520065
160204200641500110013925801001008000010080000500640000200452006420064322801002008000020024000020064200641116020110099100100160000100000010112216222006101600001002006520065200652006520065
160204200641510000003925801001008000010080000500640000200452006420064322801002008000020024000020064200641116020110099100100160000100000010112216222006101600001002006520065200652006520065
160204200641510000003925801001008000010080000500640000200452006420064322801002008000020024000020064200641116020110099100100160000100000010112216222006101600001002006520065200652006520065

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03193f51inst 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)9fa6a8a9acc2cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160024200671500452580012128000012800006264000011020027020046200463228001220800002024000020046200461116002110910101600001021030100363111720411121320043215160000102005520047200472004720047
1600242004615014525800121280000128000062640000110200270200462004632280012208000020240000200462004611160021109101016000010000001003131182021112820043215160000102006820047200472004720047
160024200461500452580012128000012800006264000011020027020046200463228001220800002024000020046200461116002110910101600001000002100363111420211141420043215160000102005920047200472004720051
160024200461500452580012128000012800006264000011020027020046200463228001220800002024000020046200461116002110910101600001000000100353111420211101420043215160000102006720047200472004720047
1600242004615004525800121280000128000062640000110200270200462004632280012208000020240000200462004611160021109101016000010057000100373111420211141420043215160000102005920047200472004720047
160024200461500615258001212800001280000626400001102002702004620046322800122080000202400002004620046111600211091010160000100003010035311142021191220043215160000102005520047200472004720047
160024200461500452580012128000012800006264000011020027020046200463228001220800002024000020046200461116002110910101600001006000100373111320211141420043215160000102005520047200472004720047
16002420046150045258001212800001280000626400001102002702004620046322800122080000202400002004620046111600211091010160000100000010031311142021114920043215160000102005520047200472004720047
160024200461500452580012128000012800006264000011020027020046200463228001220800002024000020046200461116002110910101600001002000100353111320211121220043215160000102005520047200472004720047
160024200461500452580012128000012800006264000011020027020046200463228001220800002024000020046200461116002110910101600001000000100313111620211141420043215160000102005620047200472004720047

Test 6: throughput

Count: 16

Code:

  uaba v0.8h, v16.8h, v17.8h
  uaba v1.8h, v16.8h, v17.8h
  uaba v2.8h, v16.8h, v17.8h
  uaba v3.8h, v16.8h, v17.8h
  uaba v4.8h, v16.8h, v17.8h
  uaba v5.8h, v16.8h, v17.8h
  uaba v6.8h, v16.8h, v17.8h
  uaba v7.8h, v16.8h, v17.8h
  uaba v8.8h, v16.8h, v17.8h
  uaba v9.8h, v16.8h, v17.8h
  uaba v10.8h, v16.8h, v17.8h
  uaba v11.8h, v16.8h, v17.8h
  uaba v12.8h, v16.8h, v17.8h
  uaba v13.8h, v16.8h, v17.8h
  uaba v14.8h, v16.8h, v17.8h
  uaba v15.8h, 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): 0.2502

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)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
16020440060300004125160100100160000100160000500239899914002940039400401997331999716010020016000020048000040039400391116020110099100100160000100001011011611400361600001004004940040400404004040041
16020440039300005025160100100160018100160000500239899914002040040400391997331999716010020016000020048000040039400481116020110099100100160000100101011011611401121600001004004040040400404004040040
16020440039300004125160117100160000100160000500128000014002140048400391997331999716010020016000020048000040049400391116020110099100100160000100001011011611400361600001004004940049400404004040050
16020440048300005025160100100160000100160000500239908214002040039400481997331999716010020016000020048000040039400481116020110099100100160000100001011011611400451600001004004940040400404004940040
16020440039300004125160117100160000100160000500239899914002040048400481997331999716010020016000020048000040048400391116020110099100100160000100001011011611400361600001004005040040400404004040050
160204400393003052525160100100160000100160000500239899914002940039400391997332000616010020016000020048000040048400481116020110099100100160000100001011011611400451600001004004940049400494004040040
160204400393000041251601171001600001001600005001280000140029400484003919973320006160100200160000200480000400394003911160201100991001001600001002301011011611400361600001004005040049400404011840040
16020440039300004125160100100160000100160000500128000014002040039400391997331999716010020016000020048000040039400391116020110099100100160000100001011011611400361600001004004940040400404004040049
16020440039300004125160100100160000100160000500128000014002940039400481997331999716010020016000020048000040039400401116020110099100100160000100001011011611400361600001004004140050400404004040040
16020440039300005025160100100160001100160000500128000014002940039400481997332000616010020016000020048000040049400391116020110099100100160000100001011011611400361600001004004040049400494004040049

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)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)9fa0a1a8acc2c5cdcfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16002440062300270522516001010160000101600005012800000154002040039400391999632002916001020160000204800004003940039111600211091010160000100000000100228212016211212140045155160000104005040050400404004040050
16002440049300004625160010101600001016000050128000011540020400394003919996320019160010201600002048000040049400391116002110910101600001000000001002482210164122010400361510160000104004040040400404004040049
160024400392990073251600101016000010160000501280000115400204003940039199963200291600102016000020480000400394003911160021109101016000010201000010022811201641118940036155160000104004040040400404005040040
160024400393000046251600101016000010160000501280000105400204003940039199963200191600102016000020480000400394003911160021109101016000010000001010022811916211201040036155160000104004040040400404005040040
1600244004930000462516002810160000101600005012800001054002040039400391999632002916001020160000204800004003940039111600211091010160000100000000100223212016211212140036155160000104004040040400404004040040
16002440039299018462516001010160000101600005012800000154002040039400391999632001916001020160000204800004003940039111600211091010160000100000000100228211016211201040036155160000104004040040400404005040040
1600244003930000462516001010160000101600005012800000104006940039400391999632001916001020160000204800004003940039111600211091010160000100000000100223212016211101740036155160000104004940040400404004040040
16002440039300004625160028101600171016000050243886500040020400394003919996320019160010201600002048000040049400491116002110910101600001020000001002232120162221017400361510160000104005040050400404004040040
16002440039300004625160010101600171016000050243886510040030400394003919996320019160010201600002048000040049400391116002110910101600001000000001002283220164221020400363010160000104004040050400504005040040
1600244003929900462516001010160000101600005012800001154002040039400391999632001916001020160000204800004003940039111600211091010160000100000000100223211016211201040036305160000104004040040400404005040040