Apple M1 Microarchitecture Research by Dougall Johnson

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

SQDMLAL2 (by element, 2D)

Test 1: uops

Code:

  sqdmlal2 v0.2d, v1.4s, 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)030b181e3f4e51inst 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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372300058925482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372300010525482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037220006125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037220006125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037230006125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037220006125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372300068625482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
100430372200017025482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037230006125482510001000100039831313018303730372415328951000100030003037303711100110000073116112630100030383038303830383038
10043037230006125482510001000100039831303018303730372415328951000100030003037303711100110000073116112630100030383038303830383038

Test 2: Latency 1->1

Code:

  sqdmlal2 v0.2d, v1.4s, 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)03090b3a3f4e51inst 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)9fa1accdcfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250006129548251010010010000100100005004277313030018300373003728265328745101002001016620031488301333003711102011009910010010000100430710021622296340100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000710021622296340100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000710021622296340100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000710021622296350100001003003830038300383003830038
102043003722500098529548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000710121622296340100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000710121622296340100001003003830038300383003830038
10204300372240006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000712121622296340100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000710121622296340100001003003830038300383003830038
10204300372250008229548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000710121632296340100001003003830038300383003830038
10204300372250006129548251010010010000100100005004277313030018300373003728265328745101002001000020030000300373003711102011009910010010000100000710121622296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03191e1f3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250006129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372250008429548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372240006129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225001086129548251001010100001010000504277313300183003730037282873287671001020100002030000300373003711100211091010100001000640216222963010000103003830038300383003830038

Test 3: Latency 1->2

Code:

  sqdmlal2 v0.2d, v0.4s, 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)033a3f4e51inst 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)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
10204300372250612954825101001001000010010000500427731303001803003730037282650328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731313001803003730037282650328745101002001000020430000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731313001803003730037282650328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731313001803003730037282650328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731303001803003730037282650328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731303001803003730037282650328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731303001833003730037282650328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372251612954825101001001000010010000500427731303001803003730037282650328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731303001803003730037282650328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731303001803003730037282650328745101002001000020030000300373003711102011009910010010000100007101161129634100001003003830038300383003830038

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)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)9fa6a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250061295482510010101000010100005042773130300183003730037282870328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773130300183003730037282870328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773130300183003730037282870328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773130300183003730037282870328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773130300183003730037282870328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773130300183003730037282870328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722500170295482510010101000010100005042773130300183003730037282870328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773130300183003730037282870328767100102010000203000030037300371110021109101010000100000640216212963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773130300183003730037282870328767100102010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773130300183003730037282870328767101582010000203000030037300371110021109101010000100000640216222963010000103003830038300383003830038

Test 4: Latency 1->3

Code:

  sqdmlal2 v0.2d, v1.4s, 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)03191e1f3a3f4e51inst 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)9fa8acc2c5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037224000061295484510100100100001001000064442773131300183003730037282653287451010020010000200304923003730037111020110099100100100001001300710116122963411100001003003830133300383003830038
1020430037225000010329548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100130071011611296340100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
102043003722500006129548441010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100002071011611296700100001003003830038300383003830038
102043003722501210806129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100030071011611296340100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100030071011611296340100001003003830038300383003830038
1020430037225012006129548251010010010000100100005004277313130018300373003728265328745101002001000020030498300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
1020430037225000185029548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
102043003722510006129548251010010010000100100005004277313130018300373003728265328745101002001000020030000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0307080a0b18191e1f3a3f4e51inst 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)9fa0a1a6a8a9acc2cfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225101000002682954825100101010000101000050427731314300183003730037282873287671001020100002030000300373003711100211091010100001000000006444111612729630010000103003830038300383003830038
10024300372251010000026829548251001010100001010000504277313143001830037300372828732876710010201000020300003003730037111002110910101000010000000064241116111129630010000103003830038300383003830038
10024300372251010000026829548251001010100001010000504277313143001830081300372828732876710010201000020300003003730037111002110910101000010000000064231116111129630010000103003830038300383003830038
100243003722510100000273829548251001010100001010000504277313133001830037300372828732876710010201000020300003003730037111002110910101000010000000064431116111129630010000103003830038300383003830038
10024300372251010000026829548251001010100001010000504277313133001830037300372828732876710010201000020300003003730037111002110910101000010000000064431116121229630010000103003830038300383003830038
10024300372251010000026829548251001010100001010000504277313133001830037300372828732876710010201000020300003003730037111002110910101000010000108361064431116111129630010000103003830038300383003830038
10024300372251010000026829548251001010100001010000504277313133001830084300372828732876710010201000020300003003730037111002110910101000010000000064431116121129630010000103003830038300383003830225
1002430037224101000002682954825100101010000101000050427731313300183003730037282873287671001020100002030000300373003711100211091010100001000000006443111611629630010000103003830038300383003830038
1002430037225101000002682954825100101010000101059650427731313300183003730037282873287671001020100002030000300373003711100211091010100001000000026443111661129630010000103003830038300383003830038
100243003722510100000273329548251001010100001010000504277313133001830037300372828732876710010201000020300003003730037111002110910101000010000000064431116111129630010000103003830038300383003830038

Test 5: throughput

Count: 8

Code:

  movi v0.16b, 0
  sqdmlal2 v0.2d, v8.4s, v9.s[1]
  movi v1.16b, 0
  sqdmlal2 v1.2d, v8.4s, v9.s[1]
  movi v2.16b, 0
  sqdmlal2 v2.2d, v8.4s, v9.s[1]
  movi v3.16b, 0
  sqdmlal2 v3.2d, v8.4s, v9.s[1]
  movi v4.16b, 0
  sqdmlal2 v4.2d, v8.4s, v9.s[1]
  movi v5.16b, 0
  sqdmlal2 v5.2d, v8.4s, v9.s[1]
  movi v6.16b, 0
  sqdmlal2 v6.2d, v8.4s, v9.s[1]
  movi v7.16b, 0
  sqdmlal2 v7.2d, v8.4s, 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)031e3f51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
16020420089151039258010010080000100800005006400002011020064200643228010020080000200240000200642006411160201100991001001600001000010111116112006101600001002006520065200652006520065
16020420064151039258010010080000100800005006400002004520064200643228010020080000200240000200642006411160201100991001001600001000010111116112006101600001002006520065200652006520065
16020420064150039258010010080000100800005006400002004520064200643228010020080000200240000200642006411160201100991001001600001000010111116112006101600001002006520065200652006520065
160204200641500229258010010080000100800005006400002004520064200643228010020080000200240000200642006411160201100991001001600001001010111116112006101600001002006520065200652006520065
16020420064150039258010010080000100800005006400002004520064200643228010020080000200240000200642006411160201100991001001600001000010111116112006101600001002006520065200652006520065
16020420064150039258010010080000100800005006400002004520064200643228010020080000200240000200642006411160201100991001001600001000010111116112006101600001002006520065200652006520065
16020420064150039258010010080000100800005006400002004520064200643228010020080000200240000200642006411160201100991001001600001000010111116112006101600001002006520065200652006520065
1602042006415037539258010010080000100800005006400002004520064200643228010020080000200240000200642006411160201100991001001600001000310111116112006101600001002006520065200652006520065
16020420064150039258010010080000100800005006400002004520064200643228010020080000200240000200642006411160201100991001001600001000010111116112006101600001002006520065200652006520065
16020420064150039258010010080000100800005006400002004520064200643228010020080000200240000200642006411160201100991001001600001000010111116112006101600001002006520065200652006520065

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03070b181e1f3f51inst 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)9fa8a9acc5cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1600242006215000000452580012128000012800006264000010200312005020050322800122080000202400002004620046111600211091010160000100000100303111220211107200432150160000102004720047200472004720047
160024200461500001710615258001212800001280000626400001120027200462004632280012208000020240000200462004611160021109101016000010000010033622824422107200472300160000102005120051200512005120051
1600242005015100000452580012128000012800006264000011200272004620046322800122080000202400002004620046111600211091010160000100000100333217202111010200432150160000102004720047200472004720047
1600242004615000000452580012128000012800006264000011200272004620046322800122080000202400002004620046111600211091010160000100000100366221024422108200472300160000102005120051200512005120051
1600242005015000000452580012128000012800006264000011200312005020050322800122080000202400002004620046111600211091010160000100000100366221024422710200472300160000102005120051200512005120051
1600242004615000000452580012128000012800006264000011200272004620050322800122080000202400002004620046111600211091010160000100000100333121024221107200432150160000102004720047200472004720047
16002420050150000001082580012128000012800006264000011200312004620046322800122080000202400002004620050111600211091010160000100000100333211020211107200432150160000102004720047200472004720047
1600242005015000000452580012128000012800006264000011200272005020046322801172080208202400002004620289111600211091010160000100000100333111020211108200432150160000102004720047200472004720047
1600242004615000000452580012128000012800006264000011200272004620046322800122080000202400002004620046111600211091010160000100000100333111020211107200432150160000102004720047200472004720047
1600242004615100000452580012128000012800006264000011200272004620046322800122080000202400002004620046111600211091010160000100000100303111020211710200432150160000102004720047200472004720047

Test 6: throughput

Count: 12

Code:

  sqdmlal2 v0.2d, v12.4s, v13.s[1]
  sqdmlal2 v1.2d, v12.4s, v13.s[1]
  sqdmlal2 v2.2d, v12.4s, v13.s[1]
  sqdmlal2 v3.2d, v12.4s, v13.s[1]
  sqdmlal2 v4.2d, v12.4s, v13.s[1]
  sqdmlal2 v5.2d, v12.4s, v13.s[1]
  sqdmlal2 v6.2d, v12.4s, v13.s[1]
  sqdmlal2 v7.2d, v12.4s, v13.s[1]
  sqdmlal2 v8.2d, v12.4s, v13.s[1]
  sqdmlal2 v9.2d, v12.4s, v13.s[1]
  sqdmlal2 v10.2d, v12.4s, v13.s[1]
  sqdmlal2 v11.2d, v12.4s, 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): 0.2503

retire (01)cycle (02)030b18191e1f373f4e51inst 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)9fa0a6a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1202043011323001030053149702512010110012000010012000050096000003002330039300391497331499712010020012000020036000030042300391112020110099100100120000100000007610216113003901200001003094430040300403004030040
1202043003922500000041025120101100120000100120000500428953903002030943300391497331590112010020012000020036000030943300391112020110099100100120000100000007610116113003601200001003004030043300403004030041
1202043003922500000534102512011710012000010012000050096000003002130039300391497331590112010020012000020036000030042300391112020110099100100120000100001007610116113094001200001003092330040300403004030040
120204300392310000004102512010010012000110012000050096000003002330039300391497331499712010020012000020036000030039317381112020110099100100120000100000007610116113003601200001003004330040300403004330040
120204309432250000004134052512010010012003410012000050096000003002030039309221497331499712010020012000020036000030039300391112020110099100100120000100002007610116113094001200001003004330040300403004030040
120204300392310000004402512010010012000110012000050096000013002030943300391497331500012010020012000020036000030042300391112020110099100100120000100000007610116113003601200001003004330040300403004030040
120205300392250000004102512010010012000010012000050096000013092430039300391497331499712010020012000020036000030922300391112020110099100100120000100000007610116113094001200001003004030944300403004030040
1202043003922500000141025120101100120000100120000500428340003002030042300391582831499712010020012000020036000030039300421112020110099100100120000100000007610116113003601200001003175030040309233004030040
120204300392320000006102512010110012000010012000050099000003002030042300391497331500012010020012000020036000030039300391112020110099100100120000100000007610116113003601200001003004030040300433004030944
120204300392250000006102512010111412000010012000050096000003002030039300391497331588012010020012000020036000030039309221112020110099100100120000100000007610116113003601200001003125430096300403004030040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030408090b18191e1f373a3f4e51inst 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)9fa0a6a8a9accfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
120024300502250000001200046025120010101200001012000050960000015300203003930039149963150191200102012000020360000300393003911120021109101012000010001609375251162341632227283003603117120000103004030040300403004030040
1200243003922500000000005802512001010120000121200005011303560153002130039300391499681599012043420120000203606603003930039111200211091010120000100042075501162271632228283003603110120000103004030040300433004030040
1200243003922500000000015202512001010120000101200005096000001530020300393003914996315019120010201200002036000030039300391112002110910101200001000250975241162161632226263003603110120000103004030040300413004030040
12002430039225000000600158025120010101200001012000050960000015300203003930039149963150191200102012000020360000300393003911120021109101012000010002901575251152281632227263003603110120000103004030040300403004030040
120024300392250000000000523405251200101012000010120000509600000153002130039309221499631501912001020120000203600003003930039111200211091010120000100070375241162141632227123003603110120000103004030040300433004030040
1200243003922500000000015202512001010120000101200005096000001103002030039300391499631501912001020120000203600003003930039111200211091010120000100000075241672231632228283003603110120000103004030040300403004030040
120024300392250000000000460251200101012000010120000509600000110300203092230039149963150191200102012000020360000300393003911120021109101012000010004048375251662261632226273003603110120000103004030040300403101130040
1200243003922500000000005802512001010120000101200005096000001103002030039300391499631501912001020120000203600003003930039111200211091010120000100010075241672281632229303003603110120000103004030040300403004030040
1200243003922500000000005802512001010120000101200005096000001103002030039300391499631501912001020120000203600003003930039111200211091010120000100010075251672271632216283003603110120000103004030040300403004030040
1200243003922500000000015802512001010120000101200005096000001103002030039300391499631501912001020120000203600003003930039111200211091010120000100010075241672271632227223003603110120000103004030040300423004030040