Apple M1 Microarchitecture Research by Dougall Johnson

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

SQDMLSL (by element, D)

Test 1: uops

Code:

  sqdmlsl d0, s1, v2.s[1]
  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)03080b18191e1f3a3f4e51inst 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)a0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372300000006125482510001000100039831313018303730372415328951000100030003037303711100110000000000073116112630100030383038303830383038
1004303722000000047125482510001000100039831303018303730372415328951000100030003037303711100110000000000073116112630100030383038303830383038
100430372300000006125482510001000100039831303018303730372415328951000100030003037303711100110000000000073116112630100030383038303830383038
100430372300000006125482510001000100039831303018303730372415328951000100030003037303711100110000000000073116112630100030383038303830383038
100430372400000006125482510001000100039831303018303730372415328951000100030003037303711100110000000000073116112630100030383038303830383038
100430372200000006125482510001000100039831303018303730372415328951000100030003037303711100110000000000073116112630100030383038303830383038
100430372200000006125482510001000100039831303018303730372415328951000100030003037303711100110000000000073116112630100030383038303830383038
100430372200000006125482510001000100039831303018303730372415328951000100030003037303711100110000000100073116112630100030383038307530383038
1004303725000000061254825100010001000398313030183037303724153289510001000300030373037111001100000002400073116112630100030383038303830383038
100430372400000006125482510001000100039831313018303730372415328951000100030003037303711100110000000000073116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  sqdmlsl d0, s1, v2.s[1]
  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)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)9fa0a1a6a8a9acc2c5branch mispredict (cb)cfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000000061295482510100100100001001000050042773130300183003730037282650328745101002001000020030000300373003711102011009910010010000100000000000710121622296340100001003003830038300383003830038
10204300372250000000103295482510100100100001001000050042773131300183003730037282650328745101002001000020030000300373003711102011009910010010000100000000000710121622296340100001003003830038300383003830038
1020430037225000000061295482510100100100001001000050042773131300183003730037282650328745101002121016120030000300373003711102011009910010010000100000002921000712121622296340100001003003830038300383003830038
1020430037225000000061295482510100100100001001000050042773131300183003730037282650328745101002001000020030000300373003711102011009910010010000100000000000710121622296340100001003003830038300383003830038
1020430037225000000061295482510100100100001001000050042773131300183003730037282650328745101002001000020030000300373003711102011009910010010000100000200000710121622296340100001003003830038300383003830038
1020430037225000000061295482510100100100001001000050042773130300183003730037282650328745101002001000020030000300373003711102011009910010010000100000000000710121632296340100001003003830038300383003830038
1020430037225000000061295482510100100100001001000050042773130300183003730037282650328745101002001000020030000300373003711102011009910010010000100000000000710121622296340100001003003830038300383003830038
1020430037225000000161295482510111100100001001000050042773131300183003730037282650328745101002001000020030000300843003711102011009910010010000100000000000710121623296340100001003003830038300383003830038
1020430037225000000061295482510100100100001001000050042773130300183003730037282650328745101002001000020030000300373003711102011009910010010000100000000010710121622296340100001003003830038300383003830038
1020430037225000000061295482510100100100001001000050042773131300183003730037282650328745101002001000020030000300373003711102011009910010010000100000000000710121622296340100001003003830038300383003830083

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b18191e1f3f4e51inst 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)9fa0a1a6a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500000061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000000006403162229630010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
1002430037224000000567295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000000006403162329630010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773133001830037300372828732876710010201000020305013003730037111002110910101000010000000006402162229630010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
1002430037233000000103295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000000006402163229630010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000000006403163229630010000103003830038300383003830059
100243003722500000061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000000006402162229630010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773133001830037300372828732876710010201000020300003003730037111002110910101000010000000006402162229630010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  sqdmlsl d0, s0, v1.s[1]
  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)030b18191e1f3a3f4e51inst 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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722400000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
102043003722500000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
102043003722500000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
102043003722500000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
102043003722500000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
102043003722500000061295482510100100100001001000050042773131300543003730037282653287451010020010000200300003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
102043003722500000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000071011610296340100001003003830038300383003830038
102043003722600000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
102043003722500000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
102043003722500000061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030809191e3f4e51inst 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)9fa0a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640316222963010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500005362954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500005782954825100101010000101000050427731313001830037300372828732876710010201000020300003003730084311002110910101000010000640216222963010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731313001830037300372828732876710010201000020300003008430037111002110910101000010000705216222963010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010070640216222963010000103003830038300383003830038
100243003722400005372954825100101010000101000050427731313001830037300372828732876710158201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  sqdmlsl d0, s1, v0.s[1]
  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)03080918191e1f3f4e51inst 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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500000061295482510100100100001001000050042773130300183003730037282726287411010020010008200300243003730037111020110099100100100001000000007101161129634100001003003830038300383003830038
102043003722500000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020210099100100100001000000007101161129634100001003003830038300383003830038
1020430037235000000929295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038
1020430037225000000441295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038
102043003722500000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000007101160129634100001003003830038300383003830038
102043003722500000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038
102043003722500000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000047101161129634100001003003830038300383003830038
1020430037225000000726295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000307101161129634100001003003830038300383003830038
1020430037225000000631295482510100100100071001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038
1020430037225000000156295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03070918191e1f3f4e51inst 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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372240000006129548251001010100001010000504277313030018030037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250000006129548251001010100001010000504277313030018030037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250000006129548251001010100001010000504277313030018030037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250000006129548251001010100001010000504277313030018030037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250000006129548251001010100001010000504277313030018030037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250000006129548251001010100001010000504277313030018030037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250000006129548251001010100001010000504277313030018030037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250000006129548251001010100001010000504277313030018030037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250000006129548251001010100001010000504277313030018030037300372828732876710010201000020300003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773130300183300373003728287328767100102010000203000030037300371110021109101010000102000640216222963010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  sqdmlsl d0, s8, v9.s[1]
  movi v1.16b, 0
  sqdmlsl d1, s8, v9.s[1]
  movi v2.16b, 0
  sqdmlsl d2, s8, v9.s[1]
  movi v3.16b, 0
  sqdmlsl d3, s8, v9.s[1]
  movi v4.16b, 0
  sqdmlsl d4, s8, v9.s[1]
  movi v5.16b, 0
  sqdmlsl d5, s8, v9.s[1]
  movi v6.16b, 0
  sqdmlsl d6, s8, v9.s[1]
  movi v7.16b, 0
  sqdmlsl d7, s8, v9.s[1]
  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)03090b181e3a3f51inst 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)5f60696d6escheduler 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)9fa8accficache miss (d3)d5d6daddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16020420091151000006225801001008000010080000500640000002004520064200643228010020080000200240000200642006411160201100991001001600001004501011101160112006101600001002006520065200652006520065
1602042006415000000392580124100800001008000050064000000200452006420064322801002008000020024000020064200641116020110099100100160000100001011101160112006101600001002006520065200652006520065
1602042006415001000392580100100800001008000050064000000200452006420064322801002008000020024000020064200641116020110099100100160000100101011101160112006101600001002006520065200652006520065
16020420064150000180392580100100800001008000050064000000200452006420064322801002008000020024000020064200641116020110099100100160000100001011101160112006101600001002006520065200652006520065
16020420064151000003925801001008000010780000644640000002004520064200643228010020080000200240000200642006411160201100991001001600001003301011101161432006101600001002007220072200652006520065
1602042006415000000392580100100800001008000050064000000200452006420064322801002008000020024000020064200641116020110099100100160000100001011101162442006101600001002006520065200652006520065
1602042006415000000392580100100800001008000050064000000200452006420064351801002008000020024000020064200641116020110099100100160000100001011103160132006101600001002006520065200652006520065
1602042006415100000392580100100800001008000050064000000200452006420064322801002008000020024000020064200641116020110099100100160000100201011101160112006101600001002006520065200652006520065
1602042006415000000392580100100800001008000050064000000200452006420064322801002008000020024000020064200641116020110099100100160000100001011101160112006101600001002006520065200652006520065
1602042006415000000392580100106800001008000050064000000200452006420064322801002008000020024000020064200641116020110099100100160000100001011101160112006101600001002006520065200652006520065

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e3a3f51inst 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)9fa0a1a8accdcfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaebec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160024200681500035395800121280000128000062640000110200272004620046322800122080000202400002004620050111600211091010160000100000010027311320211432004321500160000102005120047200472004720047
16002420046150004590800121280000128000062640000110200312005020046322800122080000202400002004620046111600211091010160000100000010026311320221352004321500160000102004720047200472004720047
160024200461500045908001212800001280000626400001102002720046200463228001220800002024000020046200461116002110910101600001000100100503114202111462004321500160000102012620047200472004720047
160024200461501204590800121280000128000062640000110200272004620046322800122080000202400002004620046111600211091010160000102426010050311452211342004321500160000102004720047200472004720047
1600242004615512122690800121280000128010462640000110200272004620046322800122080000202400002004620046111600211091010160000100010010027311320211442004321500160000102004720047200472004720047
1600242004615012045908001212800001280000626400001102002720046200463228001220800002024000020046200461116002110910101600001000612010026311420211432004321500160000102004720047200472004720047
16002420050150004590800121280000128000062640000110200272004620046322800122080000202400002005020046111600211091010160000100000010026311320211442004321500160000102004720047200472004720047
160024200461511208790800121280000128000062640000110201342004620046322800122080000202400002004620046111600211091010160000100010010027311420211442004321500160000102004720047200472004720047
16002420046150004590800121280000128000062640000110200272004620046322800122080000202400002004620046111600211091010160000100000010027311420211442004321500160000102004720051200472004720047
16002420046150004591800121280000128000062640000110200272004620046322800122080000202400002004620050111600211091010160000100000010027311420211442004321500160000102004720047200512004720047

Test 6: throughput

Count: 12

Code:

  sqdmlsl d0, s12, v13.s[1]
  sqdmlsl d1, s12, v13.s[1]
  sqdmlsl d2, s12, v13.s[1]
  sqdmlsl d3, s12, v13.s[1]
  sqdmlsl d4, s12, v13.s[1]
  sqdmlsl d5, s12, v13.s[1]
  sqdmlsl d6, s12, v13.s[1]
  sqdmlsl d7, s12, v13.s[1]
  sqdmlsl d8, s12, v13.s[1]
  sqdmlsl d9, s12, v13.s[1]
  sqdmlsl d10, s12, v13.s[1]
  sqdmlsl d11, s12, v13.s[1]
  movi v12.16b, 13
  movi v13.16b, 14

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2575

retire (01)cycle (02)03080b18191e1f373f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696b6d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa0a1a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
120204309222330000120014202512021310012009710012000050043995240317290317483003914973314997120100200120000200360000300393003911120201100991001001200001000000607610116113003601200001003004030040317493004031749
1202043174822400000018830251201011171200181001200005009600000300200300393004016653316706120100200120000200360000300403003911120201100991001001200001000020307610116113003601200001003004030040300413004031763
120204300392410100900101402512010010012000010012000050043995240300200300393003914973316706120100200120000200360000300393174811120201100991001001200001000000007610116113003601200001003004130040317493004031749
120204317482250000000616713251201011001200181001200005009600000300210317483003914973314997120100200120000200360000300393003911120201100991001001200001000000007610116113003701200001003004130040317493004031749
12020430039225000000184202512010010012000010012000050043995240317290317483003914973314998120100200120000200360000317483003911120201100991001001200001000040007610116113003601200001003004031749300403004031749
120204317482250000001861025120118100120000100120000500439952403002133004030039149733167061201002001200002003600003003931748111202011009910010012000010000003007610116113003601200001003004030040300403004330040
1202043003923700000006167132512010010012000010012000050043995240317430300393175314973314997120100200120000200360000300393175311120201100991001001200001000010007610116113003601200001003004030040317493004030040
1202043003923800000006167132512010110012001810012000050043995240317290317483173814973314997120100200120000200360000300393174811120201100991001001200001000000007610116113003601200001003004030042300403174931749
1202043176222500000004102512010010012000010012000050043995240317290317483003914973314997120100200120000200360000300393004011120201100991001001200001000000007610116013003601200001003004030041300403174930040
1202043003923800000004102512010010012001810012000050043809880317190300393003914973314998120100200120000200360000317483003911120201100991001001200001000000007610116113003701200001003004030040300403004131749

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080b191e1f373f51inst 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)6061696d6edispatch 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)9fa0a1a7a8acc2c5branch mispredict (cb)cdcfd0d2icache miss (d3)d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
12002430583227000000402512001110120000121200005096000010300203003930039149963150191200102012000020360000300393003911120021109101012000010000200000752003051611300360120000103004030040300403004030040
12002430039225000000402512001010120000101200005096000010300203003930039149963150191200102012000020360000300393003911120021109101012000010000000000752003011611300360120000103004030040300403004030040
120024300392240000004025120010101200001012000050960000003002030039300391499631501912001020120140203600003003930039111200211091010120000100003300000752000011611300360120000103004030040300403004030040
12002430039225000000402512001010120000101200005096000005300203003930039149963150191200102012000020360000300393003911120021109101012000010000590000752054011611300360120000103004030040300403004030943
12002430039225000000402512001010120000101200005096000010300203092230039149963150191200102012000020360000300393003911120021109101012000010000100000752054011611300360120000103004030042300403004030040
12002430039225000000402512001012120000101200005096000010300203003930039149963150191200102012000020360000300393003911120021109101012000010100100000752000011611300360120000103004030040300403004030040
12002430039225000000402512001010120018101200005096000005300203003930039149963150191200102012000020360000300393003911120021109101012000010000200000752000021611300360120000103004030040300403004030040
1200243003922500000184025120010101200001012000050960000053002030039300391499631501912001020120000203600003003930039111200211091010120000100003500000752000011611300360120000103004030923300403004030040
12002430039225000000402512001010120018101200005096000010300203003930039149963150191200102012000020360000300393003911120021109101012000010000100000752054011611300360120000103004030040300403004030040
120024300392250002400402512001010120000101200005099000005300203003930039149963150191200102012000020360000300393003911120021109101012000010000100000752000011611300360120000103004030040300403004030040