Apple M1 Microarchitecture Research by Dougall Johnson

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

FCVTZU (vector, integer, 2D)

Test 1: uops

Code:

  fcvtzu v0.2d, v0.2d
  movi v0.16b, 1
  movi v1.16b, 2

(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)030a181e3f4e51inst 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
10043037232006125472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372320017025472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372320014525472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372320012725472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
10043037242006125472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372320010325472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372320010325472510001000100039816013018303730372414328951000100010003037303711100110000373216222629100030383038303830383038
10043037252006125472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
10043037252006125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
10043037242006125472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtzu v0.2d, v0.2d
  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)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)9fa6a8acc5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372320336129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000100710116112963300100001003003830038300383003830038
10204300372330336129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000000710116112963300100001003003830038300383003830038
102043003723304746129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000000710116112963300100001003003830038300383003830038
10204300372330308929547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000000710116112963300100001003003830038300383008530038
10204300372330126129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000000710116112963300100001003003830038300383003830038
10204300372320186129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000000710116112963300100001003003830038300383003830038
1020430037232006129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000000710116112963300100001003003830038300383003830038
102043003723301597429547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000000710116112963300100001003003830038300383003830038
1020430037233066129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000000710116112963300100001003003830038300383003830038
1020430037232006129547251010010010000100100005004277160300183003730037282643287451010020010000200100003003730037111020110099100100100001000000710116112963300100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)031e3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)696b6d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722525515629547251001010100001010000504277160300180300373003728286328767100102010000201000030037300371110021109101010000100006404162229629010000103003830038300383003830038
1002430037225072629547251001010100001010000504277160300180300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
1002430037225072629547251001010100001010000504277160300180300373003728286328767100102010000201000030037300371110021109101010000100006542162229629010000103003830038300383003830086
10024300372252434629547251001010100001010000504277160300180300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
1002430037225306129547251001010100001210000604277160300180300373003728286328767100122010000201000030037300371110021109101010000100006422162229629010000103003830038300383003830038
1002430037225396129547251001010100001010000504277160300180300373003728286328767100102010000201000030037300371110021109101010000100006402162629631010000103003830038300383003830038
100243003722506129547251001010100001010000504277160300180300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
100243003722566129547251001010100001010000504277160300180300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
1002430037225308929547251001212100001210000504277160300183300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038
100243003722566129547251001010100001010000504277160300180300373003728286328767100102010000201000030037300371110021109101010000100006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtzu v0.2d, v8.2d
  fcvtzu v1.2d, v8.2d
  fcvtzu v2.2d, v8.2d
  fcvtzu v3.2d, v8.2d
  fcvtzu v4.2d, v8.2d
  fcvtzu v5.2d, v8.2d
  fcvtzu v6.2d, v8.2d
  fcvtzu v7.2d, v8.2d
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2505

retire (01)cycle (02)03080918191e1f3f51inst 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)9fa1a6a7a8a9acc2c5branch mispredict (cb)cdcfd5d6e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420048155000000302580108100800081008002050064013212002020039201969977699908012020080032200800322003920039118020110099100100800001000001000111511801620036800001002004020040200402004020040
8020420039156000090302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039418020110099100100800001000001000111511801620036800001002004020040200402004020040
8020420039156000000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000000111511801620036800001002004020040200402004020040
8020420039155000000302580108100800081008002050064013202002020039200399977699908012020080346200800322003920039118020110099100100800001000000000111511801620036800001002004020040200402004020040
802042024715500002103342580108100800081008002050064013202018020039200399977699908012020080032200800322003920039118020110099100100800001000000000111511801620036800001002004020040200402004020040
80204200391550000630302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000000111511801620036800001002004020040200402004020040
8020420039155000000722580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000000111511801720036800001002004020040200402004020040
802042003915500004680302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000000111511801620036800001002004020040200402004020040
80204200391550000002522580108100800081008002050064013212002020039200399977699908012020080032200800322003920241118020110099100100800001000000000111511801620119800001002004020040200402004020040
802042003915600000352302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000000000111511801620036800001002004020040200402004020040

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2505

retire (01)cycle (02)030818191e3a3f51inst 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)9fa0a8acc2cfd5d6d9dcddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915600000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100000502061620532003680000102004020152201542004020040
80024201021550103151614380010108009610802095064083602002020039200399996310019800102080000208000020039200391180021109101080000100000502031600352003680000102004020040200402004020040
8002420039155000120402580010108000010800005064000012002020039200899996310019800102080000208000020039200391180021109101080000100000502031600352003680000102004020040200932004020040
80024200391550003540402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100030502041600352003680000102004020040200402004020040
80024200391550001590402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100000502061600632003680000102004020040200402004020040
80024201121561002700402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000502061600562003680000102004020040200402004020040
800242003915500060402580010108000010800005064000002002020039200399996310019800102080000208000020092200391180021109101080000100000502031600542003680000102004020040200402004020040
8002420039156000510612580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100100502031600532003680000102004020040200402004020040
8002420039155000008472580010108009610800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100200502051600642003680000102004020040200402004020040
8002420039155000270402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100000502051600532007680000102004020040200402004020040