Apple M1 Microarchitecture Research by Dougall Johnson

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

SQRDMLAH (vector, 4S)

Test 1: uops

Code:

  sqrdmlah v0.4s, v1.4s, v2.4s
  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)03080b18191e1f3f4e51inst 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)a0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037230000001032548251000100010003983131301830373037241532895100010003000303730371110011000000000073116112630100030383038303830383038
1004303722000090612548251000100010003983131301830373037241532895100010003000303730371110011000000000073116112630100030383038303830383038
1004303722000000612548251000100010003983131301830373037241532895100010003000303730371110011000000000073116112630100030383038303830383038
1004303723000000612548251000100010003983131301830373037241532895100010003000303730371110011000000000073116112630100030383038303830383038
10043037220000001032548251000100010003983131301830373037241532895100010003000303730371110011000000000073116112630100030383038303830383038
1004303723000000612548251000100010003983131301830373037241532895100010003000303730371110011000000000079116112630100030383038303830383038
1004303723000000612548251000100010003983131301830373037241532895100010003000303730371110011000000003073116112630100030383038303830383038
1004303723000000612548251000100010003983131301830373037241532895100010003000303730371110011000000000073116112630100030383038303830383038
1004303722000000612548251000100010003983131301830373037241532895100010003000303730371110011000000000073116112630100030383038303830383038
1004303723000000612548251000100010003983131301830373037241532895100010003000303730371110011000000000073116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  sqrdmlah v0.4s, v1.4s, v2.4s
  movi v0.16b, 1
  movi v1.16b, 2
  movi v2.16b, 3

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b18191e1f3a3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa0a1a6a7a8acc2cfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000710031622296340100001003003830038300383003830038
1020430037225000000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000030712021622296340100001003003830086300383003830038
10204300372250000150061295482510100100100001001000051142773130300183003730037282653287451010020010497200300003003730037111020110099100100100001000000000712021622296340100001003003830038300383003830038
1020430037225000000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000710021622296340100001003003830038300383003830038
1020430037224000000061295482510100100100001001000050042773130300183003730037282653287621010020010000200304923003730037311020110099100100100001000000000710021622296340100001003003830038300383003830038
10204300372240000000726295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000710021622296340100001003003830038300383003830086
1020430037225000030061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000000130710021622296340100001003003830038300383003830038
1020430037224000000061295482510112100100001001014950042773131300183003730037282653287451010020010000200304953003730037111020110099100100100001000000000712021622296340100001003003830038300383003830038
1020430037225001000061295482510100100100001001000050042773130300183003730037282653287451010020010000200300003003730037111020110099100100100001000000100710021622296340100001003003830038300383003830038
1020430037225000000061295482510100100100001001000050042786750300183003730037282653287451010020010000200300003003730037111020110099100100100001000000000755024022296344100001003003830038301353008630180

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b18191e3f4e51inst 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)9fa7a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640316342963010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010010640316332963010000103003830081300383003830038
10024300372250000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010003640316432963010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
10024300372240000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038
10024300372250000612954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640316432963010000103003830038300383003830038
100243003722500005362954825100101010000101000050427731313001830037300372828732876710010201000020300003003730037111002110910101000010000640316332963010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  sqrdmlah v0.4s, v0.4s, v1.4s
  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)0308090b18191e1f3a3f4e51inst 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
10204300372250000000025329548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
1020430037225000000006129548251010010010000100100005004277313130018300373003728265328745101002001018020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
1020430037224000000006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
1020430037225000000006129548251010010010000100100005004277313030018300373003728265328745101002001000020430000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
10204300372250000057006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
102043003722500000297006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
1020430037225000000006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
1020430037225000000006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
102043003722500000243006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038
1020430037225000000006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000000071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b181e3f4e51inst 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)9fa0a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372260003306129548251001010100001010000504277313030162300373003728287328767100102010000203000030037300371110021109101010000100202006402162229630010000103003830038300383003830038
1002430037225000156129548251001012100001010000504277313030018300373003728287328767100102010000203000030037302271110021109101010000100000006402162229630110000103003830038302063003830038
100243003722500406129548251002912100001210000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100020845506402162229630010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313130018300373003728287328767100102010000203097230037300371110021109101010000100000006402162229630010000103003830038300383003830038
10024300372250004176129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
1002430037225000072629548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000006402162229630010000103003830038300383003830038
100243003722500006129548251001010100001010000504277313130018300843008528287328767100102010000203000030037300371110021109101010000100000006402162329630010000103003830038300383003830038
1002430037224000061295482510010101000010100006042773131300183003730037282872128767100102010000203000030037300371110021109101010000100010006402162229630010000103003830038300383003830038
100243008422500045910329548251001010100001010000504277313130018300853003728287328767100102010000203000030037300371110021109101010000100000606402162229630010000103003830134300383003830038
10024300372251105526129548251001010100001010000504277313130018300373003728287328767100102010000203000030037300371110021109101010000100000006402162229630010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  sqrdmlah v0.4s, v1.4s, v0.4s
  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)0318191e1f3a3f4e51inst 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)9fa1a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372240010500612954825101001001000010010148500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
1020430037225002100612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000710116112963410100001003003830038300383003830038
1020430037225004500612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
1020430037225005100612954825101001001000010010000500427731303001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296910100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731313001830037300372827832874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
102043003722400000612954825101001001000810010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
1020430037225001200612954825101001001000010010148500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
1020430037225004200612954825101001001000010010000500427731313001830037300372826532874510100200100002003000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
102043003722500210061295482510100100100001001000050042773131300183003730037282653287451010020010000200300003003730037111020110099100100100001000017471011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b181e3a3f4e51inst 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
1002430037225002126629548251001010100001010000504277313300183008430037282873287671001020101622030486300373003711100211091010100001000000006441116101129630010000103003830038300383003830038
10024300372250002662954825100101010000101000050427731330018300373003728287328767100102010000203000030037300371110021109101010000100001060644816111129630010000103003830038300383003830038
1002430037225004502662954825100101010000101000050427731330018300373003728287328836100102010000203000030037300843110021109101010000100000000644548101029666010000103003830038301343021630038
10024300372260055226629548441001012100001010000504277313301263003730037282873287671001020103302230000300373003711100211091010100001000000006441016111129630010000103017830038300383003830038
100243008522500026629512251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000000284806441016101529630010000103013230038300383003830038
100243003722500026629548251001014100001010000504277313300183003730037282873287671031020100002030000300373003711100211091010100001040000006441016101029774010000103003830038300383003830225
100243003722500026629512251001010100001010596504277313301263003730037282873287671001020100002030000300373003711100211091010100001000000006441016101029630010000103003830038300383003830038
100243003722510026629548251001010100001010000504277313300183003730037282933287671001020100002031956300373017811100211091010100001000300006441116101129630010000103003830038300383003830038
10024300372251054326629548251001010100001010000504277313300183003730037282873287671001020100002030000300373003741100211091010100001000002306441116111229630010000103003830038300383003830038
10024300372250002662954825100101010008121014950427731330018300373003728287328911106092010000203000030037300371110021109101010000100000060644101651029630010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  sqrdmlah v0.4s, v8.4s, v9.4s
  movi v1.16b, 0
  sqrdmlah v1.4s, v8.4s, v9.4s
  movi v2.16b, 0
  sqrdmlah v2.4s, v8.4s, v9.4s
  movi v3.16b, 0
  sqrdmlah v3.4s, v8.4s, v9.4s
  movi v4.16b, 0
  sqrdmlah v4.4s, v8.4s, v9.4s
  movi v5.16b, 0
  sqrdmlah v5.4s, v8.4s, v9.4s
  movi v6.16b, 0
  sqrdmlah v6.4s, v8.4s, v9.4s
  movi v7.16b, 0
  sqrdmlah v7.4s, v8.4s, v9.4s
  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)031e1f3f51inst 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)9fa8acc5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160204200781503303925801001008000010080000500640000120045200642006432280100200800002002400002006420064111602011009910010016000010000010112216222006101600001002006520065200652006520065
160204200641514203925801001008000010080000500640000020045200642006432280100200800002002400002006420064111602011009910010016000010000010112216222006101600001002006520065200652006520065
160204200641501203925801001008000010080000500640000020045200642006432280207200800002002400002006420064111602011009910010016000010000010112216222006101600001002006520065200652006520065
16020420064151003925801001008000010080000500640000020045200642006432280100200800002002400002006420064111602011009910010016000010000010112216222006101600001002006520065200652006520065
160204200641511503925801001008000010080000500640000020045200642006432280100200800002002400002006420064111602011009910010016000010000010112216222006101600001002006520065200652006520065
160204200641502103925801001008000010080000500640000020045200642006432280100200800002002400002006420064111602011009910010016000010000010112216222006101600001002006520065200652006520065
16020420064151003925801001008000010080000500640000120045200642006432280100200800002002400002006420064111602011009910010016000010000010112216222006101600001002006520065200652006520065
16020420064150303925801001008000010080000500640000120045200642006432280100200800002002400002006420064111602011009910010016000010000010112216222006101600001002006520065200652006520065
16020420064150903925801001008000010080000500640000120045200642006432280100200800002002400002006420064111602011009910010016000010000010112216222006101600001002006520065200652006520065
160204200641502103925801001008000010080000500640000120045200642006432280100200800002002400002006420064111602011009910010016000010000010112216222006101600001002006520065200652006520065

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030708090b18191e1f3f51inst 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)9fa0a1a6a8a9acc2cfd0d1d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16002420072150000000304525800121280000128000068640000112003120046200523228001220800002024000020046200461116002110910101600001000000001003660229204111111200432300160000102005320053200532005120051
16002420050150000000905125800121280000128000062640000002003120050200523228001220800002024000020050200501116002110910101600001000000001003230119202111112200432150160000102004720047200472004720047
16002420093150000000304525800121280000128000062640000112002720046200463228001220800002024000020046200461116002110910101600001000000001003430119202111011200432150160000102004720047200472004720047
160024200461500000003030615258001212800001280000626400001120027200502004632280012208000020240000200462004611160021109101016000010000000010037301192021199200432150160000102004720047200472004720047
1600242004615000000012066258001212800001280000626400001120027200462004632280012208000020240000200502005011160021109101016000010000000010035602211244221212200472300160000102005120051200532005320053
1600242005015000000045045258001212800001280000626400001120027200462005032280012208000020240000200462004611160021109101016000010000000010036602212264221010200492310160000102005120053200532005120051
16002420052150000000219045258001212800001280000626400001120027200462005032280012208000020240000200462004611160021109101016000010000000010035301192021189200432150160000102004720136200472004720047
160024200501500000009045258001212800001280000626400001120027200462005032280012208000020240000200462004611160021109101016000010000000010035602282432299200472300160000102005120051200512005320051
160024200501510000002106152580012128000012800006264000011200272004620050322800122080000202400002004620046111600211091010160000100000215010036602210243221212200472300160000102005120051200512005120051
160024200501500000000051258001212800001280000626400000120033200502005032280012208000020240000200502005011160021109101016000010000000010032301111202111110200432150160000102004720047200472004720047

Test 6: throughput

Count: 16

Code:

  sqrdmlah v0.4s, v16.4s, v17.4s
  sqrdmlah v1.4s, v16.4s, v17.4s
  sqrdmlah v2.4s, v16.4s, v17.4s
  sqrdmlah v3.4s, v16.4s, v17.4s
  sqrdmlah v4.4s, v16.4s, v17.4s
  sqrdmlah v5.4s, v16.4s, v17.4s
  sqrdmlah v6.4s, v16.4s, v17.4s
  sqrdmlah v7.4s, v16.4s, v17.4s
  sqrdmlah v8.4s, v16.4s, v17.4s
  sqrdmlah v9.4s, v16.4s, v17.4s
  sqrdmlah v10.4s, v16.4s, v17.4s
  sqrdmlah v11.4s, v16.4s, v17.4s
  sqrdmlah v12.4s, v16.4s, v17.4s
  sqrdmlah v13.4s, v16.4s, v17.4s
  sqrdmlah v14.4s, v16.4s, v17.4s
  sqrdmlah v15.4s, v16.4s, v17.4s
  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)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)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)9fa0a1a6a7a8acc2branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
160204400402990000510041025160100100160000100160000500128000014002940049400391997303199971601002001600002004800004003940039111602011009910010016000010000001000010110116114003601600001004004140040400504004940040
16020440039300000000041025160100100160000100160000500128000014002040048400391997303199971601002001600002004800004003940039111602011009910010016000010000000000010110116114004601600001004005040040400404005040040
16020440049300000000041025160100100160000100160000500131999904002040049400481997303200061601002001600002004800004008940049111602011009910010016000010000000000010110116114003601600001004004040040400504004940040
16020440039299000000041025160100100160017100160000500128000014002040039400401997303199971601002001600002004800004003940040111602011009910010016000010000000000010110116114003601600001004004040040400504004940049
16020440039300000100041025160100100160000100160000500128000004002940049400391997303200061601002001600002004800004003940039111602011009910010016000010000000000110110116114003601600001004004040040400504004940040
16020440039300000000041025160100100160017100160000500128000004002940039400391997373199971601002021600002004800004003940088111602011009910010016000010000000000010110116114004501600001004004040040400404005040040
16020440039300000000051025160100100160000100160000500239902714003340049400481997303199971601002001600002004800004004940039111602011009910010016000010000000000010110116114004501600001004004940040400404004940040
16020440039300000000061025160100100160000100160000500239902704002940049400391997303200071601002001600002004800004003940039111602011009910010016000010000000000010110116114004501600001004004040040400404004140040
16020440039300000000050025160117100160000100160000500239899904002040048400711997303200291601002001600002004800004003940040111602011009910010016000010000000000010110116114004601600001004004040049400404004940040
16020440039300000026400105025160117100160000100160000500128000004003040048401031997303199971601002001600002004800004003940040111602011009910010016000010000002000010110116114004601600001004004940040400404004040040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03070a1e373a3f51inst 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)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)9fa6a8a9acc2c5branch mispredict (cb)cdcfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1600244004930001001582516001010160000101600005012800001104003040039400391999603200191600102016000020480000400394003911160021109101016000010000000001002485147161111826400362217160000104005040040400904004040040
16002440039300101501682516001010160000101600005012800001154002040039400391999603200191600102016000020480000400394003911160021109101016000010000000001002483124161111526400360217160000104004040040400404004040050
1600244003930011000462516001010160000101600005012800001154003040039400391999603200191600102016000020480000400394003911160021109101016000010000000001002234128161112626400360217160000104004040040400404004040040
160024400393001300172325160010101600181016011250243886511540020400394003919996032001916001020160000204800004003940039311600211091010160000100421200001002484126161812527400450217160000104005040050400404004040040
16002440039300010170472516009610160000101600005012800001154002040039400491999603200191600102016000020480000400394003911160021109101016000010000000001002485116161112620400360217160000104005040050400404004040040
1600244003930011000582516002810160000101600005012800001154002040039400491999603200191600102016000020480000400404003911160021109101016000010000000001002485127161112626400360217160000104004040040400404004040040
16002440039300110011532516001010160018101600005012800001154002040040400482001803200191600102016000020480000400394003911160021109101016000010002900001002485127271112627400360217160000104004040040400404004040040
1600244003930011243514902516002810160000101600005012800001154002040039400391999603200191600102016000020480000400394004911160021109101016000010000000001002485126161112721400460217160000104004040040400404004040040
1600244003930000001882516001010160000101600005024388651154002940039400391999603200191600102016000020480420400394003911160021109101016000010010300001002486127161112126400360217160000104004040041400404004040040
1600244003930011001582516001010160000101600005012800001154002340039400491999603200191600102016000020480000400394003911160021109101016000010000000001002285125161111428400360217160000104004040040400404004040040